An attachable human body audio acquisition device and a human body audio acquisition and analysis system

Abstract

The present application relates to the technical field of flexible wearable diagnosis and treatment equipment, and discloses a pasting type human body audio acquisition device and a human body audio acquisition and analysis system. The device comprises: a flexible encapsulated contact type vibration sensor, which is used for acquiring human body audio signals; a flexible circuit connected with the contact type vibration sensor; the flexible circuit comprises a noise reduction module and a wireless transmission module, wherein the noise reduction module is used for performing preliminary noise reduction processing on the human body audio signals acquired by the contact type vibration sensor and converting the signals into digital signals; and the wireless transmission module is used for transmitting the digital signals to a processing module or a server. The device can be attached to uneven skin surfaces to be measured, can continuously acquire sound data of a user for a long time, and can realize high-quality sound signal extraction, noise reduction processing and data uploading through an intelligent analysis system.

Description

TECHNICAL FIELD

[0001] The present application belongs to the technical field of flexible wearable diagnosis and treatment equipment, and particularly relates to an attachable human audio frequency acquisition device and a human audio frequency acquisition and analysis system. BACKGROUND

[0002] Various sounds are produced by the human body during life activities. For example, when communicating, air passing through the vocal organs produces language; when breathing, air flowing through the respiratory tract produces respiratory sounds; when the heart beats, it produces heart sounds; when the gastrointestinal tract peristalsis, it produces gurgling sounds; when the fetus moves in the pregnant woman's belly, it produces fetal movement and fetal sounds, etc. These human body sounds contain a large amount of human physiological and pathological information, and we can monitor health and interact information through these human body sounds. For example, intelligent monitoring of respiratory sounds, heart sounds, and gurgling sounds can timely understand and warn the health status and high-risk of the corresponding physiological system; human-to-human communication or human-computer interaction through intelligent voice recognition.

[0003] However, the traditional human body sound acquisition device (electronic stethoscope, electronic artificial larynx) has the defects of large volume, hard base, easy to be disturbed by environmental noise, unable to continuously collect data for a long time, and needing to be held by hand, which limits the data collection range and convenience, and makes it difficult to play the advantages of intelligent auscultation, and limits their application in specific scenarios. SUMMARY

[0004] In view of the above defects or improvement needs of the prior art, the present application designs an attachable human audio frequency acquisition device, which uses a flexible packaged contact vibration sensor, a flexible circuit board, and software technology, so that the device can continuously collect sound data of the user for a long time in a comfortable condition, and realize high-quality sound signal extraction, noise reduction processing, and data uploading through an intelligent analysis system.

[0005] To achieve the above purpose, in the first aspect of the present application, an attachable human audio frequency acquisition device is provided, comprising:

[0006] a flexible packaged contact vibration sensor, the contact vibration sensor being used for collecting human audio frequency signals;

[0007] a flexible circuit connected with the contact vibration sensor; the flexible circuit comprises a noise reduction module and a wireless transmission module, wherein the noise reduction module is used for preliminarily reducing the noise of the human audio frequency signals collected by the contact vibration sensor and converting them into digital signals; and the wireless transmission module is used for transmitting the digital signals to a processing module or a server.

[0008] As a preferred embodiment of the present application, the flexible circuit is filled with a flexible material; the flexible material is silicone, hydrogel, or polydimethylsiloxane.

[0009] As a preferred embodiment of the present application, the attachable human audio acquisition device further comprises an attachable patch for wrapping the flexible encapsulated contact vibration sensor and the flexible circuit between the attachable patch and the surface of the skin to be measured, so that the flexible encapsulated contact vibration sensor directly contacts and adheres to the surface of the skin to be measured.

[0010] As a preferred embodiment of the present application, the flexible encapsulating material in the flexible encapsulated contact vibration sensor is a thermoplastic material with a thickness less than 1 mm.

[0011] As a preferred embodiment of the present application, the contact vibration sensor is prepared by a flexible electret film; the contact vibration sensor is an electrostatic vibration sensor, a capacitive vibration sensor, a resistive vibration sensor, a laser interference vibration sensor or an optical fiber vibration sensor.

[0012] As a preferred embodiment of the present application, the flexible encapsulated contact vibration sensor and the flexible circuit are connected by magnetic attraction or fixedly bonded.

[0013] As a preferred embodiment of the present application, the wireless transmission module is Bluetooth, WIFI, Zigbee or radio frequency.

[0014] As a preferred embodiment of the present application, the attachable human audio acquisition device further comprises an analysis processing module for real-time analysis and processing of the digital signal.

[0015] In another aspect of the present application, a human audio acquisition and analysis system is provided, comprising:

[0016] a flexible encapsulated contact vibration sensor for acquiring human audio signals by a contact vibration sensor;

[0017] a flexible circuit comprising a noise reduction module and a wireless transmission module; the noise reduction module is used for preliminary noise reduction processing of the human audio signals acquired by the contact vibration sensor and converting the signals into digital signals; the wireless transmission module is used for transmitting the digital signals to a processing module or a server;

[0018] an analysis processing module or a server for real-time analysis and processing of the digital signal.

[0019] Overall, compared with the prior art, the above technical solutions conceived by the present application mainly have the following technical advantages:

[0020] (1) The present application provides an attachable human audio acquisition device, which utilizes a flexible encapsulated contact vibration sensor, a flexible stretchable electrode, an artificial intelligence noise reduction technology, and a flexible material filling, so that the device can continuously acquire user's voice data for a long time in a comfortable condition, and realize high-quality voice signal extraction, noise reduction processing and data uploading through an intelligent analysis system.

[0021] Compared with existing human audio acquisition devices, the present application realizes sustainable and long-term stable data acquisition based on the cooperation of device hardware and software, thereby realizing accurate, real-time and intelligent data analysis.

[0022] (2) In the device of the present application, the high-sensitivity contact vibration sensor is encapsulated by flexible material, which makes it more attached to the skin surface to be measured, and can efficiently convert the human vibration signal into an electrical signal and then enter the noise reduction and amplification module for preliminary processing.

[0023] In addition, the flexible electronic material and design make the device have excellent mechanical elasticity, which can adapt to the body surface curves of different parts, ensure the close attachment, thereby obtaining high-quality voice data, and ensure the comfort and stability of long-term wear. At the same time, through close fitting, the noise interference from the external environment is effectively reduced, and the accuracy and clarity of the voice signal of the contact vibration sensor are improved.

[0024] (3) The device of the present application also contains an attachable patch for wrapping the flexible encapsulated contact vibration sensor and flexible circuit between the attachable patch and the skin surface to be measured. Due to the use of flexible electronic materials and innovative attachment technology, when this device is attached to the skin surface to be measured, it not only further improves the adhesion, reduces the noise interference from the external environment, and improves the accuracy and clarity of the voice signal; secondly, it does not need to wear a heavy device, which improves the convenience and use experience of voice data acquisition.

[0025] (4) In the device of the present application, the acquired audio data can be transmitted to the cloud server through wireless connection through the wireless transmission module, realizing convenient data transmission, real-time monitoring, analysis and storage.

[0026] (5) In the device of the present application, the human audio acquisition and analysis system can realize real-time analysis and processing of voice signals through advanced artificial intelligence technology. Among them, the noise reduction technology can effectively reduce environmental noise and extract pure voice signals, thereby improving the accuracy of data. In addition, the device combines an intelligent analysis system, which provides personalized voice data analysis and suggestions for users through algorithm processing of the collected data. BRIEF DESCRIPTION OF DRAWINGS

[0027] Figure 1The schematic diagram of the attachable human body audio acquisition device of the embodiment example of the present application;

[0028] Figure 2 The physical diagram of the double-layer electret diaphragm element with cross-shaped support structure of the embodiment example of the present application;

[0029] Figure 3 The signal receiving flow chart of the acquisition device and intelligent analysis system of the embodiment example of the present application.

[0030] Legend: 1: medical patch, 2: lithium battery, 3: pressure sensor, 4: flexible circuit, 5: packaging software. DETAILED DESCRIPTION

[0031] In order to make the purpose, technical scheme and advantages of the present application more clear, the present application is further described in detail below in combination with the drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and do not limit the present application. In addition, the technical features involved in each embodiment of the present application described below can be combined with each other as long as they do not conflict with each other.

[0032] In the embodiment of the present application, an attachable human body audio acquisition device is provided, which comprises a flexible packaged contact vibration sensor and a flexible circuit, wherein the flexible circuit contains an intelligent module (flexible electrode, noise reduction module and wireless transmission module). The present application integrates software program with hardware material with flexible design.

[0033] In the embodiment of the present application, the flexible packaged contact vibration sensor is packaged by thermoplastic material, for example, packaged by using ethylene-vinyl acetate copolymer film. The thickness of the single layer of the flexible packaging material is less than 1 mm, and the shape is not limited to oval or rectangular.

[0034] Further, the contact vibration sensor uses a flexible electret diaphragm element to prepare a disposable attachable contact vibration sensor. The vibration sensor is a piezoelectric vibration sensor, a capacitive vibration sensor, a resistive vibration sensor, a laser interference vibration sensor or a fiber optic vibration sensor.

[0035] The flexible packaged contact vibration sensor is used to acquire human body audio signals. When the contact vibration sensor is packaged with flexible material, it is closely attached to the surface of the skin to be measured. Especially attached to the uneven surface of the skin to be measured, such as the throat and other parts of the human body.

[0036] In the embodiments of the present application, the flexible circuit is connected with the flexible packaged contact vibration sensor, connected by magnetic attraction, or fixedly bonded. For example, the flexible packaged contact vibration sensor is connected with the flexible circuit by simple magnetic attraction, and the flexible packaged contact vibration sensor is used as disposable collection consumables at this time, that is, combined for use during use, facilitating one-time use.

[0037] In addition, the flexible circuit comprises a flexible electrode, a noise reduction module and a wireless transmission module.

[0038] In the flexible circuit, a mixed flexible circuit is prepared by using a flexible stretchable electrode, so that the circuit board is more flexible.

[0039] The flexible circuit is connected with the contact vibration sensor, and the noise reduction module in the flexible circuit receives the human vibration signal converted into an electrical signal by the contact vibration sensor, performs first filtering noise reduction processing to remove low-frequency sound signals, and performs preliminary processing of signal amplification; then the analog signal is converted into a digital signal by the single-chip microcomputer.

[0040] For example, the respiratory sound signal s(t) is subjected to first filtering to remove low-frequency sound signals by the filtering circuit, and after filtering, s1(t) is obtained, which can be expressed as:

[0041] s1(t) = a * s(t) + (1-a) * s(t-1)

[0042] In the formula, a is a filtering coefficient, s(t) is a current sampling value, s(t-1) is a last filtering output value, and s1(t) is a current filtering output value.

[0043] The wireless transmission module in the flexible circuit is used to upload the signal subjected to first filtering by the circuit to the upper computer for second filtering through the wireless transmission module, for example, Bluetooth. After second filtering, the data is transmitted to the data processing module for processing.

[0044] For example, the sound is divided into many small segments by selecting the signal of the frequency band where the respiratory sound is located at the upper computer end, and there is a certain overlap between frames. Each frame length is 25 ms, and the frame shift is 10 ms, and there is an overlap of 25-10=15 ms between two frames. After framing, the audio data becomes many small segments, and then feature extraction is performed on the small segments. Common methods for extracting features include linear predictive coding (Linear Predictive Coding, LPC), Mel-frequency cepstrum coefficient (Mel-frequency Cepstrum), and the process of converting a frame of waveform into a multi-dimensional vector is acoustic feature extraction. The intercepted signal will be disturbed by additive white Gaussian noise (AWGN). The sampling sequence model is given by the following formula:

[0045]

[0046] where k is an integer, A is the amplitude. f is the initial frequency, θ is the initial phase, φ is the instantaneous phase, and n(k) is the Gaussian white noise. The sound signal features are used as initial features without any other feature enhancement processing, and are adjusted to a size suitable for network input by a bicubic interpolation algorithm, and finally the respiratory sound recognition is performed by a calibrated database.

[0047] Further, the wireless transmission mode includes WIFI, Zigbee or radio frequency (RF) and the like in addition to Bluetooth.

[0048] In the embodiment of the present application, the flexible circuit further comprises a power supply and charging block for powering the single-chip microcomputer in the flexible circuit to operate, Bluetooth transmission, and indicator light and the like. In this embodiment, a lithium battery + charging circuit + charging pin are assembled into a charging module. The charging connection mode is not limited to USB-A, USB-C, Lightning, Micro-USB, MagSafe, Wireless charging.

[0049] In the embodiment of the present application, the flexible circuit is filled with a flexible material such as silicone, hydrogel or polydimethylsiloxane.

[0050] In the embodiment of the present application, the collection device further comprises an attachable patch. The device wraps the flexible packaged contact vibration sensor and the flexible circuit between the attachable patch and the skin surface to be measured, and makes the flexible packaged contact vibration sensor directly contact and attach to the skin surface to be measured. This design facilitates attachment to uneven skin surfaces to be measured. For example, the device is used to collect the attachment on the throat and chest of the human body, so that the device continuously, stably and most closely collects the audio signal.

[0051] In the embodiment of the present application, the collection device further comprises a processing and analysis module. The processing and analysis module combines an intelligent analysis system, which can monitor and identify important parameters such as the characteristic sound waveform and voiceprint details emitted by the human respiratory airflow vibration, blood vessel fluctuation, gastrointestinal peristalsis, vocal cord vibration and fetal movement in the abdomen in real time, obtain feedback on physical health and emotional state, and provide personalized sound data analysis and suggestions for users.

[0052] As shown in Figure 1 Fig. 1 is a human audio collection and analysis device provided by an embodiment of the present application, which comprises 1: a medical patch, 2: a lithium battery, 3: a pressure sensor, 4: a flexible circuit, and 5: a packaging software.

[0053] Medical patch: composed of non-woven fabric adhesive, usually uses non-irritating glue, which will not cause allergic or irritant reaction to the skin, suitable for sensitive skin people. At the same time, the non-woven fabric adhesive has air permeability, allowing air and water vapor to pass through, which helps to maintain the proper humidity and ventilation of the skin, and can keep the patch in place during daily activities such as sweating, and is not easy to loosen or fall off. In addition, it has certain elasticity and flexibility, which can fit the curves and shapes of the skin, thus providing better fit and comfort.

[0054] Lithium battery: the small volume and large capacity lithium battery used in the attached type human body audio acquisition device can realize continuous 24-hour signal acquisition.

[0055] Contact vibration sensor: this sensor has low cost, light weight, small size, high sensitivity, and is only sensitive to vibration on the contact plane, which can be used for long-range continuous contact monitoring of respiratory sound in noisy environment. Its structure includes a rubber pad, one side of which is used to contact the chest wall and the other side is used to contact the vibration diaphragm. The vibration diaphragm is made of two layers of special structure of electret film, which can convert mechanical vibration into electrical signal through electrostatic effect. The vibration diaphragm is placed in the diaphragm shell and fixed by a limiting plate. The depth of the diaphragm shell is just enough to make the square convex surface of the rubber pad contact the vibration diaphragm, so that the vibration diaphragm can fully deform and rebound, and the vibration from the chest wall can be transmitted to the maximum. The electret film has a large load resistance, which needs impedance transformation. An impedance matching circuit is placed on the back of the diaphragm shell and protected by a shielding shell. This vibration sensor not only has good performance in sensitivity and response frequency, but also has excellent performance in signal output stability and anti-interference.

[0056] Flexible circuit: made of high-quality copper material. The design concept of this flexible circuit is derived from the plasticity and conductivity of copper material. Through precise process and manufacturing technology, copper material is carefully made into a thin sheet with high flexibility, so that the circuit can adapt to various complex bending and curved shapes without losing performance.

[0057] The flexible devices composed of these five structures can adapt to various shapes and curves, including bending, folding and deformation, without losing performance. This makes them better integrated with different objects, surfaces and environments, providing more design freedom. This makes them very suitable for wearable devices, mobile devices and portable electronic products, etc.

[0058] In the embodiment of the present application, as shown in Figure 2 EVA film with good resilience, flexibility and thermoplasticity is selected as the raw material of the cross-shaped support structure. The cross-shaped support structure is prepared by template imprinting method. Specifically as follows:

[0059] First, a suitable size of 50um thick ethylene-vinyl acetate copolymer (EVA) film is cleaned with ethanol and deionized water and dried, then placed on a steel film plate with a cross-shaped support structure array. The cross-shaped groove depth of the template is about 0.3mm, the longest diameter is about 1.5mm, and the cross-shaped grooves are closely connected. Then, a layer of e-PTFE film soaked in ethanol liquid is covered on the ethylene-vinyl acetate copolymer (EVA) film, and finally a clean and smooth steel sheet is covered, and hot-pressed at a temperature of 70℃ and a mechanical pressure of 5MPa for 8 seconds. After taking out, the ethylene-vinyl acetate copolymer (EVA) film with cross-shaped support structure is obtained. Then the prepared EVA film is magnetron sputtered with a layer of Au on the convex side. Then, a layer of Au metal layer is magnetron sputtered on the FEP film with a thickness of 20μm, and the FEP side of the FEP / Au composite film is negatively corona charged. Specifically, the FEP side is placed 5cm below the corona needle tip, and a polarization voltage of-18kV is applied for about 5 minutes. Finally, the FEP layer of the FEP / Au component is placed opposite to the Au electrode layer of the EVA / Au component, and the edges are bonded and packaged.

[0060] In an embodiment of the present application, a human audio acquisition and analysis system is provided, comprising:

[0061] A flexible packaged contact vibration sensor is used to acquire human audio signals through the contact vibration sensor.

[0062] A noise reduction module is used to preliminarily reduce the noise of the human audio signals acquired by the contact vibration sensor and convert them into digital signals.

[0063] A flexible circuit includes a noise reduction module and a wireless transmission module. The noise reduction module is used to preliminarily reduce the noise of the human audio signals acquired by the contact vibration sensor and convert them into digital signals. The wireless transmission module is used to transmit the digital signals to a processing module or a server.

[0064] An analysis and processing module or a server is used to analyze and process the digital signals in real time.

[0065] The analysis and processing module can realize the functions of the system of the present application on the device side or outside the device. In some embodiments, the data is further reduced in noise by the analysis and processing module through an algorithm, and then analyzed by an artificial intelligence algorithm.

[0066] As shown in Figure 3 The steps of intelligently acquiring human audio signals through the human audio acquisition and analysis system are as follows:

[0067] Step 1: Attach the attachable human audio acquisition device to the surface of the part to be tested, collect the respiratory sound through the contact vibration sensor (new piezoelectric sensor in the figure), and convert the respiratory sound into an electrical signal.

[0068] Step 2: After noise reduction and filtering, signal amplification processing and digital signal conversion are performed.

[0069] Step 3: Through a level cache and Bluetooth transmission to the analysis and processing module (software receiving end in the figure).

[0070] In an embodiment of the present application, the step of intelligently collecting human audio signals further includes

[0071] Using the analysis and processing module, after successfully matching with the attachable human audio acquisition device through the built-in Bluetooth module, the stethoscope can receive the respiratory sound data transmitted back; further analysis and application based on the received digital signal.

[0072] For example, when the analysis and processing module is a PC, the corresponding functions of this module are mainly divided into two categories:

[0073] 1. Real-time playback of respiratory sound, display and save of waveform, etc.:

[0074] (1) Respiratory sound data received through the Bluetooth module is stored in the buffer. Fixed length data is taken from the buffer each time, and after adding an audio data header, it is played.

[0075] (2) The software can draw a waveform graph of the currently played audio data on the interface.

[0076] (3) The software can save real-time audio data as a wav or mp3 file to the local.

[0077] 2. Intelligent identification of respiratory sound:

[0078] (1) The intelligent identification function is realized through a cloud server. The reason for this architecture is to adapt to devices of multiple systems (Android, Windows, iOS).

[0079] (2) The back-end software uploads the respiratory sound files that need to be identified to the cloud server. After receiving the uploaded respiratory sound files, the cloud server extracts the feature vectors of the files through audio preprocessing, then calls a pre-trained deep network model for classification and identification, and sends the identification result to the PC software.

[0080] Further, the attachable audio acquisition device and intelligent analysis system has wide application potential in many fields such as critical medical treatment, old-age care monitoring, battlefield rescue, remote medical treatment, home monitoring, sports training, etc. The device is used for monitoring physiological state of a patient and improving safety, etc. Further, since the device is usually in close contact with an individual, data privacy protection is crucial. Therefore, a modern attachable audio acquisition device and intelligent analysis system usually has a powerful data security protection mechanism to ensure that voice data of a user will not be misused or leaked.

[0081] Those skilled in the art will easily understand that the above description is only the preferred embodiment of the present application, and is not used to limit the present application, and any modification, equivalent replacement and improvement made within the spirit and principle of the present application shall be included in the protection scope of the present application.

Claims

1. An attachable human body audio acquisition device, characterized by, The application relates to a flexible contact vibration sensor for collecting human audio signals, wherein the contact vibration sensor comprises a rubber pad, one flat side of the rubber pad is used for contacting a measuring part, and the other convex side of the rubber pad is connected with a contact vibration diaphragm, the contact vibration diaphragm is placed in a diaphragm shell and fixed by a diaphragm limiting plate, the depth of the diaphragm shell is the distance between the convex side of the rubber pad and the contact vibration diaphragm, the contact vibration diaphragm is made of two layers of cross-shaped structure flexible electret films, the cross-shaped structure flexible electret film comprises an FEP / Au component and an EVA / Au component, the FEP layer of the FEP / Au component is oppositely arranged with the Au electrode layer of the EVA / Au component, the FEP / Au component is a component provided with an Au metal layer on an FEP film, the EVA / Au component is a component provided with an Au electrode layer on an EVA film, and the EVA film is an ethylene-vinyl acetate copolymer film with a cross-shaped support structure, and the Au electrode layer is located on the convex side of the cross-shaped support structure. A flexible circuit is connected with the contact vibration sensor through magnetic attraction or fixed bonding, the flexible circuit comprises a noise reduction module and a wireless transmission module, wherein the noise reduction module is used for carrying out preliminary noise reduction treatment on the human audio signals collected by the contact vibration sensor and converting the human audio signals into digital signals, the wireless transmission module is used for transmitting the digital signals to a processing module or a server, and the flexible circuit is filled with a flexible material, and the flexible material is silicone, hydrogel or polydimethylsiloxane. The attachable human audio collecting device further comprises an attachable patch for wrapping the flexible contact vibration sensor and the flexible circuit between the attachable patch and a skin surface to be measured, so that the flexible contact vibration sensor directly contacts and attaches to the skin surface to be measured.

2. The attachable human body audio acquisition device according to claim 1, wherein, The flexible packaging material in the flexible contact vibration sensor is a thermoplastic material with a thickness less than 1 mm.

3. The attachable human body audio acquisition device according to claim 1, wherein, The contact vibration sensor is prepared by using a flexible electret film, and the contact vibration sensor is an electrostatic vibration sensor, a capacitive vibration sensor, a resistance vibration sensor, a laser interference vibration sensor or an optical fiber vibration sensor.

4. The attachable human body audio acquisition device according to claim 1, wherein, The wireless transmission module is Bluetooth, WIFI, Zigbee or radio frequency.

5. The attachable human body audio acquisition device of claim 1, wherein The attachable human audio collecting device further comprises an analysis processing module for carrying out real-time analysis and processing on the digital signals.

6. The attachable human body audio acquisition device of claim 1, wherein The application relates to an analysis processing module or a server of the attachable human audio collecting device according to any one of claims 1-6, which is used for carrying out real-time analysis and processing on the digital signals in the attachable human audio collecting device.

7. A human audio acquisition analysis system, characterized by ​ ​

Images