Radial artery three-part pulse condition acquisition system based on artificial intelligence

Abstract

The invention discloses a radial artery three-part pulse condition collection system based on artificial intelligence, and relates to the technical field of pulse condition detection. The system comprises an MCU control unit, and an air pump air bag unit, a stepping motor unit and a pulse condition acquisition unit which are respectively connected with the MCU control unit, the MCU control unit controls the air pump air bag unit to add / deflate air and controls the stepping motor unit to move up and down at the same time, and the applied pressure value is further finely adjusted. And the pulse condition acquisition unit acquires pulse condition signal data based on the change of the pressure value and records the pulse condition signal data. The pulse condition collecting device solves the problem that the pulse feeling pressure of an existing pulse condition collecting device cannot be accurately controlled and cannot be independently controlled.

Description

Technical Field

[0001] The present invention relates to the technical field of pulse condition detection, and more specifically, to an artificial intelligence-based three-part radial artery pulse acquisition system. Background Art

[0002] Pulse diagnosis, also known as "feeling the pulse" or "examining the pulse", "pressing the pulse", "holding the pulse", is a method of diagnosing diseases in which a doctor touches the patient's radial artery with fingers to explore the pulse condition and understand the changes in the disease condition. The commonly selected pulse-taking site in modern times is the "Cunkou", that is, the superficial part of the patient's radial artery behind the wrist. The "Cunkou" is divided into three parts: Cun, Guan, and Chi. Regarding the division of the three-part pulse corresponding to the zang-fu organs, the commonly used division method in current clinical practice is: the right Cun corresponds to the lung, the right Guan corresponds to the spleen and stomach, and the right Chi corresponds to the kidney (Mingmen); the left Cun corresponds to the heart, the left Guan corresponds to the liver, and the left Chi corresponds to the kidney.

[0003] Three different finger forces are often used in pulse diagnosis. Gently pressing on the skin is the floating pulse-taking, called "lifting"; heavily pressing until reaching the muscles and bones is the deep pulse-taking, called "pressing"; pressing moderately without being too light or too heavy to reach the muscles is the middle pulse-taking, called "searching". Each of the three parts of Cun, Guan, and Chi has three pulses of floating, middle, and deep, which are collectively called "three-part and nine-pulse".

[0004] Pulse diagnosis is a real-time, accurate, and personalized diagnosis method, which can help doctors differentiate syndromes and predict the changes in the disease condition. However, pulse diagnosis is also affected by many factors. Pulse diagnosis is an operation process of feeling the different pulsation images of the patient's floating, middle, and deep pulses. The main judgment process is based on subjective experience and lacks objective quantitative standards. Coupled with the scarcity of experienced traditional Chinese medicine doctors, the development of traditional Chinese medicine pulse diagnosis has always been difficult.

[0005] The existing pulse acquisition instruments on the market have the following deficiencies: First, there is no corresponding automatic pressure addition and subtraction mode, making it difficult to obtain pulse condition information under different pressures of "floating, middle, and deep" advocated by traditional Chinese medicine; second, this diagnosis method still requires users to find the best pulse-taking position and pulse-taking pressure by themselves, which may affect the accuracy of pulse condition information and the popularization of this device. Summary of the Invention

[0006] In view of this, the present invention provides an artificial intelligence-based three-part radial artery pulse acquisition system to solve the problems that the pulse-taking pressure of the existing pulse acquisition device cannot be accurately controlled and cannot be controlled separately.

[0007] To achieve the above object, the present invention adopts the following technical solutions: An artificial intelligence-based radial artery three-part pulse acquisition system, comprising: an MCU control unit, and an air pump airbag unit, a stepping motor unit, and a pulse acquisition unit respectively connected to the MCU control unit; the MCU control unit controls the air pump airbag unit to inflate / deflate, and at the same time controls the stepping motor unit to move up and down to further finely adjust the applied pressure value; the pulse acquisition unit collects pulse signal data based on the change of the pressure value and records it.

[0008] Optionally, the pulse signal data collected by the pulse acquisition unit is transmitted to the host computer through a Type-c unit or a wireless communication unit.

[0009] Optionally, it further comprises a multi-parameter acquisition unit connected to the MCU control unit, and the multi-parameter acquisition unit includes a PPG photoplethysmography sensor, an ECG electrocardiogram sensor, a body temperature sensor, and an EMG electromyogram sensor.

[0010] Optionally, the air pump airbag unit comprises an ultra-quiet pump, an airbag, a barometric pressure sensor, and a solenoid valve; the ultra-quiet pump is respectively connected to the airbag, the barometric pressure sensor, and the solenoid valve through an air pipe; a plurality of airbags are provided, and a limit sensor is arranged between the airbags to prevent over-inflation.

[0011] Optionally, the stepping motor unit includes a stepping motor, and the stepping motor is provided with upper and lower stroke limit switches for applying pressure to the cun-guan-chi of the wrist.

[0012] Optionally, the pulse acquisition unit is divided into a cun-part pulse acquisition part, a guan-part pulse acquisition part, and a chi-part pulse acquisition part; the cun-part pulse acquisition part is further divided into a cun pulse channel center sensor module, a cun upper pulse position sensor module, and a cun lower pulse position sensor module; the guan-part pulse acquisition part is further divided into a guan pulse channel center sensor module, a guan upper pulse position sensor module, and a guan lower pulse position sensor module; the chi-part pulse acquisition part is further divided into a chi pulse channel center sensor module, a chi upper pulse position sensor module, and a chi lower pulse position sensor module; the pulse acquisition unit has a total of 9 stress zones, and the 9 stress zones respectively perform action pressure combinations to obtain the specific information conduction mechanisms and markers of the corresponding organs in each zone; and use neural network learning; and feedback the collected pulse signal data to the MCU single-chip microcomputer.

[0013] Optionally, the PPG photoplethysmography sensor is attached to the wrist of the person to be measured to obtain heart rate, blood oxygen saturation, blood pressure, and respiratory rate according to the change of blood volume; the ECG electrocardiogram sensor is attached to the wrist of the person to be measured to obtain electrocardiogram data; the body temperature sensor is attached to the wrist of the person to be measured to obtain the body temperature; the EMG electromyogram sensor is attached to the wrist of the person to be measured to obtain electromyogram data.

[0014] Optionally, the MCU control unit is further connected to a stress finger motion transmission mechanism. The stress finger motion transmission mechanism is divided into three stress finger tips, which apply pressure towards the pulse condition acquisition unit respectively. Pressure feedback sensors are built into the stress finger tips to automatically adjust the applied pressure according to the feedback pressure.

[0015] Optionally, the pulse condition acquisition unit is encapsulated on an FPC flexible board. Three FPC flexible boards are combined together to simulate the contact of three fingers with the radial artery of the wrist for traversing the horizontal position of the wrist.

[0016] As can be seen from the above technical solutions, compared with the prior art, the present invention provides an artificial intelligence-based radial artery three-part pulse condition acquisition system, which has the following beneficial effects: 1. The present invention uses a new type of pressure addition and subtraction system combining an airbag and a stepping motor to control the pulse-taking pressure, continuously adding and subtracting pressure separately or simultaneously at the three positions of cun, guan, and chi on the wrist, simulating the acquisition method of three-part and nine-region diagnosis, collecting more comprehensive pulse condition information, and being able to find the optimal pulse-taking pressure faster, which is more stable and accurate than the traditional overall airbag pressurization or mechanical pressurization.

[0017] 2. The MCU control unit module uses a low-power and high-integration microcontroller, and the power consumption of the whole system is lower.

[0018] 3. Using an FPC flexible board to contact the radial artery of the wrist can traverse the horizontal position of the wrist without worrying about the problem of inaccurate user positioning.

[0019] 4. The user only needs to place the wrist at the position specified by the arrow on the strap and fasten the strap to complete the accurate acquisition of pulse condition information. No special traditional Chinese medicine knowledge is required, and the operation is convenient, which can be widely applied to personal and family health care.

[0020] 5. The mobile phone platform or the PC side can analyze and process the pulse condition data, and store it in real time to establish a personal database for providing reference for expert diagnosis, realizing the sharing of precious medical resources. At the same time, a large amount of pulse condition data provides a valuable pulse training set, paving the way for the realization of intelligent medical care. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required to be used in the description of the embodiments or the prior art. Obviously, the following drawings are only the embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained according to the provided drawings without creative efforts.

[0022] Figure 1 It is a schematic diagram of the internal structure principle of the present invention; Figure 2 It is an exploded view of the physical structure of the present invention; Figure 3 Overall diagram of the physical structure of the present invention; Wherein, 1 - outer shell, 2 - MCU control unit, 3 - air pressure sensor, 4 - ultra - quiet pump, 5 - solenoid valve, 6 - large airbag, 7 - small airbag, 8 - limit sensor, 9 - stepper motor, 10 - upper pulse position sensor, 11 - pulse channel center sensor, 12 - lower pulse position sensor, 13 - PPG photoplethysmography sensor, 14 - ECG electrocardiogram sensor, 15 - body temperature sensor, 16 - EMG electromyogram sensor, 17 - stress finger motion transmission mechanism, 18 - pressure feedback sensor, 19 - wireless communication unit, 20 - Type - c unit, 21 - trachea, 22 - sheath. Specific embodiments

[0023] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all of the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0024] Embodiment 1 The embodiment of the present invention discloses an artificial - intelligence - based radial artery three - part pulse acquisition system, as Figures 1 - 3 shown, including: an MCU control unit 2, and an air pump airbag unit, a stepper motor unit, and a pulse acquisition unit respectively connected to the MCU control unit 2; the MCU control unit 2 controls the inflation / deflation of the air pump airbag unit, and at the same time controls the up - and - down movement of the stepper motor 9 unit to further finely adjust the applied pressure value; the pulse acquisition unit acquires pulse signal data based on the change of the pressure value and records it.

[0025] Specifically, in this embodiment, the MCU control unit 2 controls the air pump airbag unit to inflate, controls the solenoid valve 5 to deflate, and the motor unit to pressurize. The pulse signal collected by the pulse acquisition unit, and the heart rate, blood oxygen saturation, blood pressure, respiratory rate, electrocardiogram, body temperature, and electromyogram signals collected by the multi-parameter acquisition unit are transmitted to the host computer through the Type-c unit 20 and the wireless communication unit 19. The air pump airbag unit includes 4 ultra-quiet pumps 4, 4 airbags, 4 air pressure sensors 3, and 4 solenoid valves 5. The ultra-quiet pump 4 generates gas for the airbag and the air pressure sensor 3. The airbag inflates to apply pressure to the cun, guan, and chi positions on the wrist. An in-built limit sensor 8 protects the wrist of the person being measured from pain caused by excessive pressure. When the set air pressure is exceeded, the solenoid valve 5 operates to deflate. The stepping motor unit contains 4 stepping motors 9, each with upper and lower stroke limit switches. The stepping motor 9 operates to apply pressure to the cun, guan, and chi positions on the wrist. The pulse acquisition unit is divided into 3 acquisition parts with 9 acquisition modules to obtain the pulse signals at the cun, guan, and chi positions on the wrist. The multi-parameter acquisition unit includes a PPG photoplethysmogram sensor 13, an ECG electrocardiogram sensor 14, a body temperature sensor 15, and an EMG electromyogram sensor 16. The heart rate, blood oxygen saturation, blood pressure, respiratory rate, electrocardiogram, body temperature, and electromyogram signals at the wrist of the person being measured are obtained. The stress finger motion transmission mechanism 17 (servo motor and muscle hydraulic transmission mechanism) is divided into 3 stress finger tips, with 3 pressure feedback sensors 18 built-in, which automatically adjusts the pressure applied to the cun, guan, and chi positions according to the feedback pressure.

[0026] The MCU control unit 2 controls the ultra-quiet pump 4 to work to inflate the airbag and controls the solenoid valve to deflate according to the pressure value feedback by the air pressure sensor 3, ensuring that the air pressure value of the airbag is at a constant position. At the same time, it controls the up and down movement of the stepping motor unit to further fine-tune the applied pressure value. When the pulse acquisition unit applies different pressures to the cun, guan, and chi positions, the pulse signal data collected is more accurately and standardly recorded. The MCU control unit 2 of the pulse acquisition unit controls the ultra-quiet pump 4 to work to inflate the airbag and controls the solenoid valve 5 to deflate according to the pressure value feedback by the air pressure sensor 3, ensuring that the air pressure value of the airbag is at a constant position. At the same time, it controls the up and down movement of the stepping motor unit to further fine-tune the applied pressure value. When the pulse acquisition unit applies different pressures to the cun, guan, and chi positions, the pulse signal data collected is more accurately and standardly recorded. The pulse signal data collected by the pulse acquisition unit is transmitted to the host computer through the Type-c unit 20 and the wireless communication unit 19. The host computer analyzes and compares the pulse signal data to obtain a pulse conclusion.

[0027] The air pump airbag unit includes 4 ultra - quiet pumps 4, 4 airbags, 4 air pressure sensors 3, and 4 solenoid valves 5. One ultra - quiet pump 4 is connected to one airbag, one air pressure sensor 3, and one solenoid valve 5 through an air pipe 21. The difference is that among the 4 airbags, 3 small airbags 7 have a width of 1.4 cm and a length of 4 cm, corresponding to the three pulse - taking positions of cun, guan, and chi on the wrist. One large airbag 6 has a width of 6 cm and a length of 4 cm, covering the entire wrist pulse - taking position. This is to achieve applying pressure to the cun, guan, and chi positions of the wrist respectively and applying floating, middle, and sinking pressures to the cun, guan, and chi positions simultaneously. Limit sensors 8 are placed between the airbags to prevent excessive inflation and cause discomfort to the wrist of the person being measured. The ultra - quiet pump 4 inflates the airbag. The airbag applies pressure to the pulse - taking unit after inflation. The air pressure sensor 3 collects the pressure applied to the pulse - taking unit after the airbag is inflated and the pressure feedback from the cun, guan, and chi positions. The solenoid valve 5 is used to deflate the airbag and for rapid deflation in case of a malfunction. The device can set an external mechanical quantity, with the setting range being 0 - 250 mmHg, and the maximum allowable error of the set value being ±15%. The display range of the external mechanical quantity of the device is 0 - 250 mmHg, and the maximum allowable error of the displayed value is ±15%.

[0028] The stepper motor unit contains 4 stepper motors 9, each with upper and lower stroke limit switches. The sliders on the 4 stepper motors 9 are respectively fixed behind the 4 airbags. During pulse - taking, when the airbag pressure is constant, micro - movements are performed. If the measured pressure is less than the set pressure, the slider moves downward to make the measured pressure equal to the set pressure; if the measured pressure is greater than the set pressure, the slider moves upward to make the measured pressure equal to the set pressure. This ensures that when repeatedly collecting pulses, the applied pressure is consistent, thus effectively avoiding the problem of unstable pulse - taking caused by pressure fluctuations, improving the stability of pulse - taking, and providing quantitative data for the pulse sensor to accurately collect pulse results.

[0029] The pulse - taking unit is divided into 144 pressure - collecting sensors (which can be a combination of liquid sensors, flexible sensors, and piezoelectric bridge sensors). The upper pulse - position sensor 10, the pulse - channel center sensor 11, and the lower pulse - position sensor 12 are respectively used to collect the pulse signal data of the cun, guan, and chi on the wrist. The cun - part pulse - taking section is further divided into a cun - pulse - channel center sensor module, a cun - upper - pulse - position sensor module, and a cun - lower - pulse - position sensor module. The guan - part pulse - taking section is further divided into a guan - pulse - channel center sensor module, a guan - upper - pulse - position sensor module, and a guan - lower - pulse - position sensor module. The chi - part pulse - taking section is further divided into a chi - pulse - channel center sensor module, a chi - upper - pulse - position sensor module, and a chi - lower - pulse - position sensor module. There are a total of 9 stress - partition areas, and each sensor module contains 4×4 = 16 pressure sensors. The 9 stress - partition areas perform action - pressure combinations respectively to obtain the specific information conduction mechanisms and markings corresponding to the five internal organs and six hollow organs (ten organs) in each area. And neural network learning is used.

[0030] The organ-specific neural network architecture based on 9 stress-zone dynamic pressure combination is designed as follows, combining biomechanical conduction characteristics and deep learning algorithms: Multi-pressure spatio-temporal feature extraction: Input layer: Let the three-dimensional biological signals of the i-th stress zone (i = 1~9) under k pressure gradients (float / middle / sink) be: ; is the pressure component, is the displacement component, is the shear stress component, and R is the spatial component.

[0031] which includes pressure, displacement, shear stress components, and the sampling duration T.

[0032] Time-frequency-space joint encoding: Use the improved Wigner-Ville distribution for time-frequency analysis: ; Extract spatio-temporal features through 3D convolution: ; where is the learnable three-dimensional convolution kernel (size 5×5×3); ReLU is the real part-taking operation of linear algebraic operations; Organ-specific attention mechanism: Dynamic weight allocation: Define the pressure sensitivity coefficient of organ j (such as heart, liver, kidney) to zone i: ; where is the query vector of the organ; LSTM is the long short-term memory network Pressure-organ association matrix: Construct organ feature mapping:

[0033] is the organ-specific projection matrix; Bidirectional gated graph transduction network: Bioconduction graph modeling: Construct the adjacency matrix according to the relationship between the zang-fu organs in traditional Chinese medicine , and define graph convolution:

[0034] where

[0035] Bidirectional gated update:

[0036]

[0037] Multi-task dynamic decision-making: Organ state prediction:

[0038] Among them represents vector concatenation, is cross-partition aggregation; Loss function design:

[0039] BCE is binary cross-entropy; is the weight coefficient; is the outer product operation.

[0040] It includes multi-task cross-entropy and the traditional Chinese medicine relationship constraint term.

[0041] Pressure-organ response surface optimization: Define the organ diagnostic efficacy surface:

[0042] W is the variance measurement.

[0043] Optimize the pressure combination through the Monte Carlo policy gradient:

[0044] is the gradient of the parameter ; IE is the sampling integral.

[0045] The size of the effective surface of the total sensor perpendicular to the blood vessel is 53 mm ± 10% wide × 30 mm ± 10% long. The collected pulse signal data is fed back to the MCU single-chip microcomputer. Every 48 pressure acquisition sensors are packaged on an FPC flexible board, and 3 FPC flexible boards are combined together to simulate the contact of three fingers with the radial artery of the wrist, which can traverse the horizontal position of the wrist, without worrying about the problem of inaccurate user positioning. At the same time, according to the pulse data collected by the center sensor module of the cun, guan, and chi pulse channels, the upper pulse position sensor module, and the lower pulse position sensor module, fine-tuning is performed left and right, so that the center sensor module of the pulse channel is always pressed on the center position of the wrist blood vessel. The pulse pressure acquisition range is 0 mmHg to 250 mmHg, and the maximum allowable error of the displayed value is ±10%. The pulse rate display range is 40 beats / min to 200 beats / min, the resolution is 1 beat / min, and the maximum allowable error of the displayed value is ±3 beats / min.

[0046] The multi-parameter acquisition unit includes a PPG photoplethysmogram sensor 13, an ECG electrocardiogram sensor 14, a body temperature sensor 15, and an EMG electromyogram sensor 16.

[0047] The PPG photoplethysmography sensor 13 is attached to the wrist of the person being measured to detect changes in blood volume, and obtains heart rate, blood oxygen saturation, blood pressure, and respiratory rate. The ECG electrocardiogram sensor 14 is attached to the wrist of the person being measured to obtain electrocardiogram data. The body temperature sensor 15 is attached to the wrist of the person being measured to obtain body temperature. The EMG electromyogram sensor 16 is attached to the wrist of the person being measured to obtain electromyogram data.

[0048] The wireless communication unit 19 includes a wireless Bluetooth transmission module and / or a wireless WIFI transmission module.

[0049] The airbag, the stepper motor 9, the pulse acquisition unit, and the multi-parameter acquisition unit are enclosed in the sheath 22.

[0050] The stress finger of the motion transmission mechanism 17 (servo motor and muscle hydraulic transmission mechanism) is divided into 3 stress finger tips, and has a transmission mechanism that applies pressure towards the pulse acquisition unit. The stress finger tip is internally provided with a pressure feedback sensor 18, which can automatically adjust the applied pressure according to the feedback pressure.

[0051] Furthermore, in this embodiment, the relationship formula between blood oxygen saturation and pulse pressure is: The average value of the pulse pressure P(t) can be expressed as ; The average value of the volume pulse blood flow Q(t) is expressed as ; where P(t) is the pulse pressure curve, Q(t) is the volume pulse blood flow curve, p s is the systolic blood pressure, p d is the diastolic blood pressure, K = (p m - p d ) / (p s - p d ) is the waveform of the pulse pressure, Q max is the maximum value of the blood flow waveform, Q min is the minimum value of the blood flow waveform, K’ = (Q m - Q min ) / Q max - Q min ) is the waveform coefficient of the volume pulse blood flow.

[0052] P m and Q m can be related by the peripheral vascular resistance R (light absorption ratio), that is R = P m / Q m ; Therefore, the relationship between the volume pulse blood flow and the pulse pressure can be expressed as ; According to the Lambert-Beer law and a large number of studies, it shows that: there is a negative linear relationship between R and blood oxygen saturation. The lower R is, the greater the blood oxygen saturation is.

[0053] SpO 2 = a + bR; Therefore, the relationship between blood oxygen saturation and pulse pressure can be obtained as .

[0054] Example 2 The difference between this example and Example 1 is only that: There is a housing 1 outside the device of this example, and an external mechanical quantity can be set. The setting range is 0 - 300 mmHg, and the maximum allowable error of the set value is ±10%. The external mechanical quantity is displayed in a continuous or intermittent stepped range of 0 - 50 mmHg; 50 - 150 mmHg; 150 - 260 mmHg, and the maximum allowable error of the displayed value is ±10%. The direct pressure acquisition range of the actual contact with the radial artery blood vessel is 0 mmHg - 260 mmHg, and the maximum allowable error of the displayed value is ±5%. The feedback beating frequency display range of the radial artery blood vessel is 40 beats / min - 200 beats / min; the resolution is less than 1 beat / min, and the maximum allowable error of the displayed value is ±1 beat / min. The size of the effective surface of the multi-target sensor in the actual contact position with the radial artery blood vessel perpendicular to the wrist skin section is not more than 55 mm ± 10% wide × 35 mm ± 10% long. The noise of the device during normal operation should not be greater than 60 dB(A).

[0055] In this specification, each embodiment is described in a progressive manner. The key point of each embodiment is to illustrate the differences from other embodiments. For the same or similar parts among the embodiments, reference can be made to each other. For the device disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple. For the relevant parts, reference can be made to the description in the method part.

[0056] The above description of the disclosed embodiments enables those skilled in the art to implement or use the present invention. Various modifications to these embodiments will be obvious to those skilled in the art. The general principles defined herein can be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to these embodiments shown herein, but will be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A radial artery three-part pulse acquisition system based on artificial intelligence, characterized in that: include: An MCU control unit, and an air pump airbag unit, a stepper motor unit and a pulse acquisition unit respectively connected to the MCU control unit; the MCU control unit controls the air pump airbag unit to add / deflat, and controls the stepper motor unit to move up and down, and further fine-tunes the applied pressure value; the pulse acquisition unit collects pulse signal data based on the change of pressure value and records it.

2. The artificial intelligence-based radial artery three-part pulse acquisition system according to claim 1, characterized in that: The pulse signal data collected by the pulse acquisition unit is transmitted to the host computer via the Type-c unit or the wireless communication unit.

3. The artificial intelligence-based radial artery three-part pulse acquisition system according to claim 1, characterized in that: It also includes a multi-parameter acquisition unit connected to the MCU control unit, and the multi-parameter acquisition unit includes a PPG photoplethysmography sensor, an ECG electrocardiogram sensor, a body temperature sensor and an EMG electromyography sensor.

4. The artificial intelligence-based radial artery three-part pulse acquisition system according to claim 1, characterized in that: The air pump airbag unit includes an ultra-quiet pump, an airbag, an air pressure sensor and an electromagnetic valve; the ultra-quiet pump is connected to the airbag, the air pressure sensor and the electromagnetic valve respectively through an air pipe; there are multiple airbags, and limit sensors are placed between the airbags to prevent over-inflation.

5. The artificial intelligence-based radial artery three-part pulse acquisition system according to claim 1, characterized in that: The stepper motor unit comprises a stepper motor, and the stepper motor is provided with an upper and lower travel limit switch for applying pressure to the wrist.

6. The artificial intelligence-based radial artery three-part pulse acquisition system according to claim 1, characterized in that: The pulse acquisition unit is divided into a Cun pulse acquisition part, a Guan pulse acquisition part and a Chi pulse acquisition part; the Cun pulse acquisition part is further divided into a Cun pulse channel center sensor module, a Cun upper pulse position sensor module and a Cun lower pulse position sensor module; the Guan pulse acquisition part is further divided into a Guan pulse channel center sensor module, a Guan upper pulse position sensor module and a Guan lower pulse position sensor module; the Chi pulse acquisition part is further divided into a Chi pulse channel center sensor module, a Chi upper pulse position sensor module and a Chi lower pulse position sensor module; the pulse acquisition unit has a total of 9 stress partitions, and the 9 stress partitions are respectively combined with action pressure to obtain the specific information conduction mechanism and markers of the corresponding organs of each partition; and learn using neural networks; The collected pulse signal data is fed back to the MCU microcontroller.

7. The artificial intelligence-based radial artery three-part pulse acquisition system according to claim 3, characterized in that: The PPG photoplethysmography sensor is attached to the wrist of the person being measured to obtain heart rate, blood oxygen saturation, blood pressure and respiratory rate according to changes in blood volume; the ECG electrocardiogram sensor is attached to the wrist of the person being measured to obtain electrocardiogram data; the body temperature sensor is attached to the wrist of the person being measured to obtain body temperature; and the EMG electromyography sensor is attached to the wrist of the person being measured to obtain electromyography data.

8. The artificial intelligence-based radial artery three-part pulse acquisition system according to claim 1, characterized in that: The MCU control unit is also connected to the stress finger action transmission mechanism, which is divided into three stress finger ends, which respectively apply pressure to the direction of the pulse acquisition unit. The stress finger ends have built-in pressure feedback sensors, which automatically adjust the applied pressure according to the feedback pressure.

9. The artificial intelligence-based radial artery three-part pulse acquisition system according to claim 6, characterized in that: The pulse acquisition unit is packaged on an FPC soft board, and three FPC soft boards are combined together to simulate the contact of three fingers with the radial artery of the wrist, which is used to traverse the lateral position of the wrist.

Images