Intelligent blood pressure measurement method, system and storage medium

Abstract

The present invention relates to the field of medical detection technology, and more specifically to an intelligent blood pressure measurement method, system and storage medium. The method comprises: by defining a first position and a second position, placing a first detection unit and a second detection unit at the first position and the second position, a control unit triggering a light source to emit light, a camera unit receiving light passing through a finger, and shooting a blood flow image sequence; during the inflation and deflation process, continuously acquiring the blood flow image sequence again and merging it into a target image, comparing the brightness change of the time series, calculating pulse wave data, merging it into a complete pulse waveform, determining a first time point and a second time point, and calculating the pressure value at each time point; collecting the sound generated by the blood vessels of the user's finger through a sound sensor, comparing the pressure values ​​at the same time point, and acquiring the user's systolic and diastolic pressures when the comparison results are all less than a preset difference, thereby improving the accuracy of blood pressure measurement through the present invention.

Description

Technical Field

[0001] The present invention relates to the field of medical detection technology, and more specifically to an intelligent blood pressure measurement method, system and storage medium. Background Art

[0002] There are two mainstream sphygmomanometers at present, one is mercury sphygmomanometer and the other is electronic sphygmomanometer (oscillometric method). Mercury sphygmomanometer uses auscultation method (Korotkoff sound method) to measure blood pressure, which requires subjective judgment of people to measure blood pressure. Delayed response and misoperation of people will lead to inaccurate blood pressure measurement. Another oscillometric method is also called oscillation method. Its principle is to automatically adjust the inflation volume of the cuff wrapped around the upper arm to change the pressure. The blood flow through the blood vessels has a certain oscillation wave, which is received by the pressure sensor and gradually deflated. According to the change of the oscillation wave, the pressure and fluctuation detected by the pressure sensor also change accordingly. The moment with the largest fluctuation is selected as the reference point. Based on this point, the fluctuation point of a certain value is found forward as the systolic pressure, and the fluctuation point of a certain value is found backward as the diastolic pressure. The value is set differently by different manufacturers. The clinical verification of this sphygmomanometer is designed with auscultation method as the standard and statistical methods. This method requires the accumulation of a large amount of measurement data. The appropriate fluctuation points are selected as systolic and diastolic pressures by statistical methods. Because of the differences in human structure or physical state, the measurement results will have a greater impact, which is easy to cause inaccurate measurements.

[0003] The existing application document with publication number CN110720902A discloses a blood pressure measurement method and a sphygmomanometer, which obtain audio information of Korotkoff sounds of a tissue to be measured and pressure information of the tissue to be measured; screen multiple Korotkoff sounds in a starting time period in the audio information, select the Korotkoff sound with the largest decibel amplitude change among the multiple Korotkoff sounds as the first Korotkoff sound, screen multiple Korotkoff sounds in an ending time period in the audio information, select the Korotkoff sound with the largest decibel amplitude change among the multiple Korotkoff sounds as the second Korotkoff sound; determine a first time point corresponding to the first Korotkoff sound, determine a second time point corresponding to the second Korotkoff sound, determine a first pressure value of the tissue to be measured based on the first time point and the pressure information, and determine a second pressure value of the tissue to be measured based on the second time point and the pressure information, wherein the first pressure value and the second pressure value are the high and low pressures of the tissue to be measured.

[0004] There is also an application document with publication number CN116898414A, which provides a blood pressure measurement method and a wearable blood pressure measurement device, including: obtaining an initial pressure value of a first pressure of a pressure-applying piece; if the initial pressure value of the first pressure is greater than or equal to a first pressure threshold, determining that the pressure-applying piece and the wrist are in an overly tight fit state; if the initial pressure value of the first pressure is less than the first pressure threshold, and the initial pressure value of the first pressure is greater than or equal to a second pressure threshold, determining that the pressure-applying piece and the wrist are in a moderate fit state, and performing a blood pressure measurement operation; if the initial pressure value of the first pressure is less than the second pressure threshold, determining that the pressure-applying piece and the wrist are in a loose fit state.

[0005] However, the accuracy of blood pressure measurement in the above two inventions still needs to be improved. Therefore, the present invention provides an intelligent blood pressure measurement method, system and storage medium to improve the accuracy of blood pressure measurement. Summary of the invention

[0006] By defining a first position and a second position, the first detection unit and the second detection unit are placed at the first position and the second position, the control unit triggers the light source to emit light, the camera unit receives the light passing through the finger, and shoots a blood flow image sequence; during the inflation and deflation process, the blood flow image sequence is continuously acquired again and merged into a target image, the brightness change of the time series is compared, the pulse wave data is calculated, and merged into a complete pulse waveform, the first time point and the second time point are determined, and the pressure value at each time point is calculated; the sound generated by the blood vessels of the user's finger is collected by a sound sensor, and the pressure values ​​at the same time point are compared. When the comparison results are all less than the preset difference, the user's systolic and diastolic pressures are acquired, and the accuracy of blood pressure measurement is improved by the present invention.

[0007] To achieve the above object, the present invention provides an intelligent blood pressure measurement method, which is implemented by executing the following steps:

[0008] Step S1: taking a finger corresponding to an arm of a user not wearing the cuff as a first position, and taking a finger corresponding to another arm of the user wearing the cuff as a second position, placing a first detection unit and a second detection unit at the first position and the second position respectively, wherein the detection units are respectively provided with a light source and a camera unit, wherein the detection units include the first detection unit and the second detection unit;

[0009] Step S2: the control unit triggers the light sources on the first detection unit and the second detection unit to emit light, and receives the light transmitted through the finger through the camera units on the first detection unit and the second detection unit respectively, and continuously photographs the finger at a preset time interval to obtain a first blood flow image sequence and a second blood flow image sequence;

[0010] Step S3: inflating the airbag of the cuff by the air pump, and adjusting the amount of gas flowing into the airbag by the control unit to adjust the pressure applied to the user's arm, until the pressure remains stable for a preset time, and the first blood flow image sequence and the second blood flow image sequence are continuously acquired, and after the pressure remains stable for the preset time, the airbag of the cuff is deflated by the exhaust valve, and the first blood flow image sequence and the second blood flow image sequence are continuously acquired again, until the blood pressure measurement of the user is completed;

[0011] Step S4: processing the first blood flow image sequence and the second blood flow image sequence respectively, and merging the first blood flow image sequence into a first target image and the second blood flow image sequence into a second target image based on the timestamp respectively, comparing the brightness changes of the time series in the first target image and the second target image respectively, calculating the first pulse wave data and the second pulse wave data, and merging the first pulse wave data and the second pulse wave data into a complete first pulse waveform and a second pulse waveform based on the first pulse waveform and the second pulse waveform, determining a first time point and a second time point based on the first pulse waveform and the second pulse waveform, and respectively calculating the pressure value of the blood vessels of the finger of the user at the first time point and the pressure value at the second time point when the blood vessels are affected by the cuff pressure;

[0012] Step S5: The detection units are also respectively provided with sound sensors, which collect the sounds generated by the blood vessels of the user's fingers through the sound sensors, calculate the third time point and the pressure value corresponding to the third time point, the fourth time point and the pressure value corresponding to the fourth time point based on the sounds, compare the pressure value in the second pulse wave data at the same time point with the pressure value corresponding to the sounds, and obtain comparison results. When the comparison results are all less than a preset difference, the pressure value corresponding to the first time point or the third time point is used as the systolic pressure of the user, and the pressure value corresponding to the second time point or the fourth time point is used as the diastolic pressure of the user.

[0013] As a preferred technical solution of the present invention, after calculating the first pulse wave data and the second pulse wave data in step S4, and before merging the first pulse wave data and the second pulse wave data into a complete first pulse waveform and a complete second pulse waveform, the method further includes:

[0014] The heartbeat unit obtains the user's heart rate through the first pulse wave data, and obtains the trend of the heart rate changing over time, and uses the difference between the maximum heart rate and the minimum heart rate in the heart rate changing trend as the heart rate changing value;

[0015] When the heart rate data is less than the preset heart rate threshold and the heart rate change value is less than the heart rate change threshold, it is defined that the user is in a calm state. When the user is in the calm state, continue to execute step S4, otherwise, suspend the blood pressure measurement.

[0016] As a preferred technical solution of the present invention, in step S4, based on the first pulse waveform and the second pulse waveform, determining a first time point and a second time point, and respectively calculating the pressure value of the blood vessels of the finger of the user at the first time point and the pressure value at the second time point when the user is affected by the cuff pressure, include:

[0017] When the second pulse waveform rises again or the second pulse wave data changes again, recording the time point at this time as the first time point, and recording the pressure value corresponding to the first time point;

[0018] Determine the period and height of the first pulse waveform and the second pulse waveform, and as the pressure on the user's arm begins to be released, when the period and height of the second pulse waveform are the same as those of the first pulse waveform, record the time point at this time as a second time point, and record the pressure value corresponding to the second time point.

[0019] As a preferred technical solution of the present invention, in step S4, respectively comparing the brightness changes of the time series in the first target image and the second target image to calculate the first pulse wave data and the second pulse wave data includes:

[0020] Extracting the shape and position of the blood vessel from the first target image, and forming a simplified blood vessel image based on the shape and position of the blood vessel, and using signal processing technology to identify a periodic pattern of brightness changes in the simplified blood vessel image, wherein the periodic pattern corresponds to a pulse wave;

[0021] Performing time series analysis on the detected periodic pattern and acquiring first pulse wave data, wherein the first pulse wave data includes a timestamp and a corresponding pressure value;

[0022] Repeat the above steps to obtain the second pulse wave data.

[0023] As a preferred technical solution of the present invention, in step S4, merging into a complete first pulse waveform and a second pulse waveform includes:

[0024] Respectively obtain a first start time and a second start time in the first pulse wave data and the second pulse wave data, and when the first start time is not equal to the second start time, calculate a time offset between the first start time and the second start time, and based on the time offset, add or subtract the time offset from the timestamp of each sample in the second pulse wave data, wherein the first start time indicates the time when the first pulse wave data is started to be obtained, and the second start time indicates the time when the second pulse wave data is started to be obtained;

[0025] Based on the first start time and the second start time, the first pulse wave data and the second pulse wave data are fused together using a Kalman filter method, and the first pulse waveform and the second pulse waveform are displayed on the same time axis.

[0026] As a preferred technical solution of the present invention, step S5 further includes:

[0027] The sound sensor starts to collect the sound generated by the blood vessels of the user's fingers after the air pump inflates the air bag of the cuff and the pressure on the user's arm stabilizes, and records the corresponding third time point and the pressure value corresponding to the third time point when the sound first appears, and records the corresponding fourth time point and the pressure value corresponding to the fourth time point when the pressure on the user's arm is released and the sound disappears;

[0028] Compare the pressure value of the user's blood vessel at the first time point with the pressure value at the third time point, and obtain a first comparison result, compare the pressure value of the user's blood vessel at the second time point with the pressure value at the fourth time point, and obtain a second comparison result, and when any one of the first comparison result and the second comparison result is greater than or equal to the preset difference, re-measure the user's blood vessel pressure value until both the first comparison result and the second comparison result are less than the preset difference.

[0029] As a preferred technical solution of the present invention, determining the period and height of the first pulse waveform and the second pulse waveform includes:

[0030] Identifying the time interval between two consecutive pulse wave peaks in the first pulse waveform to determine the period of the first pulse wave, and measuring the vertical distance between adjacent wave peaks and wave troughs in the first pulse waveform to determine the height of the first pulse wave;

[0031] Repeat the above steps to determine the period of the second pulse waveform and the height of the second pulse waveform.

[0032] The present invention also provides an intelligent blood pressure measurement system as described above, a cuff with an air bag, an air pump and an exhaust valve installed on the cuff, and includes the following modules:

[0033] The detection unit is configured to take the finger corresponding to the arm of the user not wearing the cuff as the first position, and take the finger corresponding to the other arm of the user wearing the cuff as the second position, and place the first detection unit and the second detection unit at the first position and the second position respectively, and the detection unit is respectively provided with a light source and a camera unit, wherein the detection unit includes the first detection unit and the second detection unit;

[0034] A sound sensor is also provided respectively, and the sound generated by the blood vessels of the user's fingers is collected by the sound sensor;

[0035] The control unit is configured to trigger the light sources on the first detection unit and the second detection unit to emit light, and receive the light transmitted through the finger through the camera units on the first detection unit and the second detection unit respectively, and continuously photograph the finger at a preset time interval to obtain a first blood flow image sequence and a second blood flow image sequence;

[0036] Inflate the airbag of the cuff through the air pump, and adjust the pressure applied to the user's arm by adjusting the amount of gas flowing into the airbag through the control unit, until the pressure remains stable for a preset time, and the first blood flow image sequence and the second blood flow image sequence are continuously acquired, and after the pressure remains stable for the preset time, deflate the airbag of the cuff through the exhaust valve, and continue to acquire the first blood flow image sequence and the second blood flow image sequence again, until the blood pressure measurement of the user is completed;

[0037] a calculation unit, configured to process the first blood flow image sequence and the second blood flow image sequence respectively, and merge the first blood flow image sequence into a first target image and the second blood flow image sequence into a second target image based on a timestamp, respectively compare brightness changes of the time series in the first target image and the second target image, calculate first pulse wave data and second pulse wave data, and merge the first pulse wave data and the second pulse wave data into a complete first pulse waveform and a second pulse waveform, determine a first time point and a second time point based on the first pulse waveform and the second pulse waveform, and respectively calculate a pressure value of a blood vessel of a finger of the user at the first time point and a pressure value at the second time point when the blood vessel is affected by the cuff pressure;

[0038] A verification unit is used to calculate, based on the sound, a third time point and a pressure value corresponding to the third time point, a fourth time point and a pressure value corresponding to the fourth time point, compare the pressure value in the second pulse wave data at the same time point with the pressure value corresponding to the sound, and obtain a comparison result, and when the comparison results are all less than a preset difference, use the pressure value corresponding to the first time point or the third time point as the user's systolic pressure, and use the pressure value corresponding to the second time point or the fourth time point as the user's diastolic pressure.

[0039] The present invention also provides a storage medium, wherein the storage medium stores computer executable instructions, and when the computer executable instructions are executed by a processor, the above-mentioned intelligent blood pressure measurement method is implemented.

[0040] Compared with the prior art, the beneficial effects of the present invention are at least as follows:

[0041] The technical solution of the present invention is to put a cuff with an air bag on the user's arm, and take the finger corresponding to the user's arm without the cuff as the first position, and the finger corresponding to the other arm of the user wearing the cuff as the second position, and respectively place the first detection unit and the second detection unit at the first position and the second position, and the detection units are respectively provided with a light source and a camera unit. The light source emits light passing through the finger, and the camera unit can capture the light passing through the finger. The user can measure blood pressure at any time, and use multiple pulse wave data to analyze the user's blood pressure, which can reduce the errors that may occur in the traditional blood pressure measurement method, and through the automated light source and camera unit, the pulse wave data can be automatically collected and analyzed, reducing human operation errors and improving the accuracy of measurement.

[0042] The control unit triggers the light source on the first detection unit and the second detection unit to emit light, so as to reduce the influence of ambient light on the blood flow image captured by the camera unit, which helps to improve the signal-to-noise ratio of the image, so as to more accurately analyze the blood flow situation. The camera units on the first detection unit and the second detection unit receive the light transmitted through the finger, and the finger is photographed at a preset time interval to obtain the first blood flow image sequence and the second blood flow image sequence, so that the blood flow changes can be dynamically monitored. Continuous monitoring can better reflect the real state of blood flow than a single measurement, so as to improve the accuracy of blood pressure measurement. The air bag of the cuff is inflated by an air pump, and the amount of gas flowing into the air bag is adjusted by the control unit to adjust the pressure applied to the user's arm until the pressure is continuously stable for a preset time, and the first blood flow image sequence and the second blood flow image sequence are continuously obtained. After the pressure is stable for a preset time, the air bag of the cuff is deflated by the exhaust valve, and the first blood flow image sequence and the second blood flow image sequence are continuously obtained again until the user's blood pressure measurement is completed, so as to monitor the changes in the blood vessels at all times and provide data support for obtaining the user's blood pressure.

[0043] By processing the first blood flow image sequence and the second blood flow image sequence respectively, and merging the first blood flow image sequence into the first target image and the second blood flow image sequence into the second target image based on the timestamp, respectively, comparing the brightness changes of the time series in the first target image and the second target image, calculating the first pulse wave data and the second pulse wave data, and merging the first pulse wave data and the second pulse wave data into a complete first pulse waveform and a second pulse waveform, a more comprehensive understanding of the change law of the pulse wave is obtained, so as to more accurately identify key time points such as systolic pressure (pressure value corresponding to the first time point) and diastolic pressure (pressure value corresponding to the second time point), determine the first time point and the second time point based on the first pulse waveform and the second pulse waveform, and respectively calculate the pressure value of the finger blood vessels at the first time point and the pressure value at the second time point when the user is affected by the cuff pressure.

[0044] The detection unit is also provided with a sound sensor, which collects the sound generated by the blood vessels of the user's fingers, calculates the third time point and the pressure value corresponding to the third time point, the fourth time point and the pressure value corresponding to the fourth time point based on the sound, compares the pressure value in the second pulse wave data at the same time point with the pressure value corresponding to the sound, and the two verify each other to improve the accuracy of blood pressure measurement; when the comparison results are less than the preset difference, the pressure value corresponding to the first time point or the third time point is used as the user's systolic pressure, and the pressure value corresponding to the second time point or the fourth time point is used as the user's diastolic pressure. Through the coordination between the above schemes, the accuracy of blood pressure measurement is further improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying creative work.

[0046] Figure 1 is a flowchart of the steps of the intelligent blood pressure measurement method of the present invention;

[0047] Figure 2 The present invention is a structural diagram of the composition of the intelligent blood pressure measurement system. DETAILED DESCRIPTION

[0048] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0049] It is understood that the terms "first", "second", etc. used in this application may be used herein to describe various elements, but unless otherwise specified, these elements are not limited by these terms. These terms are only used to distinguish a first element from another element. For example, without departing from the scope of this application, a first xx script may be referred to as a second xx script, and similarly, a second xx script may be referred to as a first xx script.

[0050] There are two mainstream sphygmomanometers at present, one is the mercury sphygmomanometer and the other is the electronic sphygmomanometer (oscillometric method). The mercury sphygmomanometer uses the auscultation method (Korotkoff sound method) to measure blood pressure, which requires subjective judgment of people to measure blood pressure. Delayed response and misoperation of people will lead to inaccurate blood pressure measurement. The other oscillometric method is also called the oscillation method. Its principle is to automatically adjust the inflation volume of the cuff wrapped around the upper arm to change the pressure. The blood flow through the blood vessels has a certain oscillation wave, which is received by the pressure sensor and gradually deflated. According to the change of the oscillation wave, the pressure and fluctuation detected by the pressure sensor also change accordingly. The moment with the largest fluctuation is selected as the reference point. Based on this point, the fluctuation point of a certain value is found forward as the systolic pressure, and the fluctuation point of a certain value is found backward as the diastolic pressure. The value is set differently by different manufacturers. Both blood pressure measurement methods will lead to inaccurate measurements.

[0051] In view of the above technical problems, the present invention proposes Figure 1 The smart blood pressure measurement method shown is to wear a cuff with an air bag on the user's arm, and the cuff is equipped with an air pump and an exhaust valve, and is implemented through the following steps:

[0052] Step S1: Take the finger corresponding to the arm of the user who is not wearing the cuff as the first position, and take the finger corresponding to the other arm of the user who is wearing the cuff as the second position, and place the first detection unit and the second detection unit at the first position and the second position respectively, and the detection units are respectively provided with a light source and a camera unit, wherein the detection units include a first detection unit and a second detection unit.

[0053] Specifically, by wearing the first detection unit and the second detection unit on different parts of the user's body, the pulse wave data that is not affected by the cuff pressure (first position) and the pulse wave data that is affected by the cuff pressure (second position) are collected respectively, which can provide more comprehensive pulse wave data and accurately analyze the blood pressure status. For example, if the cuff is worn on the user's right arm, the finger corresponding to the user's left arm is the first position, and the finger corresponding to the user's right arm is the second position. The finger here can be the middle finger or other fingers. It is recommended to use the same finger on the left and right hands when measuring, such as both index fingers or both middle fingers. The device including the first detection unit and the device including the second detection unit can be directly clamped or put on the user's finger. For example, the device can be a finger sleeve. The light source and the camera unit on the detection unit are arranged relatively to each other. The light source emits light that passes through the finger, and the camera unit can capture the light that passes through the finger. At the same time, the device is easy to carry. The user can measure blood pressure at any time. Using multiple pulse wave data to analyze the user's blood pressure can reduce the errors that may occur in traditional blood pressure measurement methods. In addition, through the automated light source and camera unit, the pulse wave data can be automatically collected and analyzed, reducing human operation errors and improving measurement accuracy.

[0054] Step S2: The control unit triggers the light sources on the first detection unit and the second detection unit to emit light, and receives the light passing through the finger through the camera units on the first detection unit and the second detection unit respectively, and continuously photographs the finger at preset time intervals to obtain the first blood flow image sequence and the second blood flow image sequence.

[0055] Specifically, by setting a light source in the detection unit and controlling its light emission so that it actively illuminates the finger, the influence of ambient light on the blood flow image captured by the camera unit is reduced, which helps to improve the signal-to-noise ratio of the image, thereby more accurately analyzing the blood flow situation. By continuously photographing the finger at preset time intervals and obtaining a sequence of blood flow images, blood flow changes can be dynamically monitored. Continuous monitoring can better reflect the true state of blood flow than a single measurement, thereby improving the accuracy of blood pressure measurement. Among them, the light source emits light of a specific wavelength that can be significantly absorbed by the blood. For example, the light source can be infrared light, which can penetrate deeply into the skin and tissues and be absorbed by hemoglobin in the blood. As a result, the change in the intensity of the light passing through or reflected corresponds to the change in blood volume.

[0056] Step S3: Inflate the airbag of the cuff through an air pump, and adjust the pressure applied to the user's arm by adjusting the amount of gas flowing into the airbag through the control unit until the pressure remains stable for a preset time, and the first blood flow image sequence and the second blood flow image sequence are continuously acquired. After the pressure is stable for a preset time, deflate the airbag of the cuff through the exhaust valve, and continue to acquire the first blood flow image sequence and the second blood flow image sequence again until the user's blood pressure measurement is completed.

[0057] Specifically, during the blood pressure measurement process, the control unit first controls the air pump to inflate the airbag of the cuff, and gradually increases the pressure in the airbag through the above method until the arterial blood at the arm wrapped by the cuff is completely blocked, that is, when the pulse cannot be felt, the pressure is stabilized for a certain preset time, and the preset time can be pre-defined according to the measurement requirements, which is related to the individual differences of the user, and the time is generally very short. During the blood pressure measurement, the camera unit continuously obtains blood flow images, and the first blood flow image sequence represents a continuous plurality of blood flow images that are not affected by the cuff pressure, and the second blood flow image sequence represents a continuous plurality of blood flow images that are affected by the cuff pressure. When the pressure is maintained for a certain preset time, the control unit controls the exhaust valve to deflate the airbag of the cuff. The deflation process is slow. As the gas is gradually released, the pressure in the blood vessel will also decrease accordingly until the blood vessel is completely restored to a normal state. The camera unit continuously obtains blood flow images during the entire measurement process to monitor the changes in the blood vessels from time to time and provide data support for obtaining the user's blood pressure.

[0058] Step S4: Process the first blood flow image sequence and the second blood flow image sequence respectively, and merge the first blood flow image sequence into a first target image and the second blood flow image sequence into a second target image based on the timestamp, compare the brightness changes of the time series in the first target image and the second target image respectively, calculate the first pulse wave data and the second pulse wave data, and merge the first pulse wave data and the second pulse wave data into a complete first pulse waveform and a second pulse waveform, determine the first time point and the second time point based on the first pulse waveform and the second pulse waveform, and calculate the pressure value of the finger blood vessels at the first time point and the pressure value at the second time point when the user is affected by the cuff pressure respectively.

[0059] Specifically, by processing the blood flow image sequence at each position, the influence of external factors such as ambient light and finger movement on the image quality is eliminated or reduced, ensuring that the analyzed image data is more accurate and improving the accuracy of subsequent blood pressure calculation. The specific processing method belongs to the prior art and will not be repeated here. By merging multiple blood flow images into a target image through a timestamp, the coherence and time consistency of the data can be ensured to more accurately analyze the dynamic changes of blood flow, especially when measuring pulse wave data. The first pulse wave data and the second pulse wave data are obtained from two different positions respectively. The first pulse wave data corresponds to the data monitored from the arm that is not affected by pressure. As reference data, the second pulse wave data is compared with the first pulse wave data to identify the data that needs attention. The pulse wave data at multiple time points are merged into a complete pulse waveform, which can more comprehensively understand the change law of the pulse wave and more accurately identify key time points such as systolic pressure and diastolic pressure. The identification of user systolic pressure and diastolic pressure will be described in detail below. Among them, the merged first pulse waveform and the second pulse waveform are displayed on the same time axis, and the specific method will be described in detail below. After the cuff pressure rises to a certain level, the pressure stabilization stage is entered. At this time, the first pulse waveform shows a normal period and height, and the second pulse waveform shows a relatively stable state, showing an obvious difference. The time when the cuff air bag begins to release the pressure, that is, the time point when the second pulse waveform changes from the original stability to the time point when the second pulse wave data reappears, is the first time point. During the rising process of the second pulse waveform, it gradually becomes consistent with the first pulse waveform. The time point when the second pulse waveform has the same period and height as the first pulse waveform is the second time point, which is the time point when the blood vessel has completed its recovery to normal.

[0060] Step S5: The detection units are also provided with sound sensors, which collect the sound generated by the blood vessels of the user's fingers through the sound sensors, calculate the third time point and the pressure value corresponding to the third time point, the fourth time point and the pressure value corresponding to the fourth time point based on the sound, compare the pressure value in the second pulse wave data at the same time point with the pressure value corresponding to the sound, and obtain the comparison result. When the comparison results are all less than the preset difference, the pressure value corresponding to the first time point or the third time point is used as the user's systolic pressure, and the pressure value corresponding to the second time point or the fourth time point is used as the user's diastolic pressure.

[0061] Specifically, in order to make the user's blood pressure measurement result more accurate, sound sensors are also provided on the detection unit to measure the Korotkoff sounds generated from the blood vessels. When the cuff pressure is reduced enough to allow the blood to start flowing again, that is, at the third time point, a series of sounds can be heard, which are called Korotkoff sounds. The first appearance of Korotkoff sounds is the third time point, which usually corresponds to systolic pressure; continue to release the pressure until the Korotkoff sounds disappear, that is, at the fourth time point, which usually corresponds to diastolic pressure, and record the pressure values ​​of the blood vessels at the beginning and end of the Korotkoff sounds. These two pressure values ​​represent systolic pressure and diastolic pressure, respectively. The pressure value in the second pulse wave data at the same time point is compared with the pressure value corresponding to the sound, and the two verify each other, thereby improving the accuracy of blood pressure measurement and thus improving the accuracy of blood pressure measurement.

[0062] Through the coordination between the above steps, the accuracy of blood pressure measurement is further improved.

[0063] Furthermore, after calculating the first pulse wave data and the second pulse wave data in the above step S4, and before merging the first pulse wave data and the second pulse wave data into a complete first pulse waveform and a complete second pulse waveform, the method further includes:

[0064] The heartbeat unit obtains the user's heart rate through the first pulse wave data, and obtains the trend of the heart rate change over time, and takes the difference between the maximum heart rate and the minimum heart rate in the heart rate change trend as the heart rate change value.

[0065] When the heart rate data is less than the preset heart rate threshold and the heart rate change value is less than the heart rate change threshold, it is defined that the user is in a calm state. When the user is in a calm state, step S4 is continued to be executed, otherwise, the blood pressure measurement is suspended.

[0066] Specifically, when the user is nervous or has just exercised, the accuracy of the measured blood pressure is significantly reduced. To solve this problem, in the above steps, the user's heart rate data and heart rate changes during measurement are judged to determine whether to continue blood pressure measurement, and the heart rate threshold and heart rate change threshold are preset in advance according to the user's age. For example, if the user is a 70-year-old, the preset heart rate threshold can be set to 60 beats / minute, and the heart rate change threshold can be set to 10 beats / minute. When the user's heart rate data is less than 60 beats / minute and the heart rate change value is less than 10 beats / minute, it means that the user is currently in a calm state, and the blood pressure measured at this time is more accurate. Otherwise, the user needs to rest before measuring blood pressure.

[0067] Furthermore, in the above step S4, based on the first pulse waveform and the second pulse waveform, the first time point and the second time point are determined, and the pressure value of the finger blood vessels of the user at the first time point and the pressure value at the second time point when the user is affected by the cuff pressure are respectively calculated, including:

[0068] When the second pulse waveform rises again or the second pulse wave data changes again, the time point at this time is recorded as the first time point, and the pressure value corresponding to the first time point is recorded;

[0069] Determine the period and height of the first pulse waveform and the second pulse waveform. As the pressure on the user's arm begins to release, when the period and height of the second pulse waveform are the same as the first pulse waveform, record the time point at this time as the second time point, and record the pressure value corresponding to the second time point.

[0070] Specifically, by recording the time point when the second pulse waveform rises again or the second pulse wave data changes again as the first time point, the moment when systolic pressure occurs can be accurately captured, because this moment usually corresponds to the highest pressure of blood on the blood vessel wall when the heart contracts. When the second pulse waveform is the same as the first pulse waveform in terms of period and height, as the second time point (between the first time point and the second time point, the second pulse waveform belongs to the stage of gradually recovering to the same stage as the first pulse waveform, and the second pulse waveform and the first pulse waveform are still different at this time), the pressure value recorded at this time reflects the diastolic pressure, that is, the lowest pressure in the blood vessel when the heart relaxes. By comparing the period and height of the two pulse waveforms, the synchronous observation of the pulse waveform during the pressure release process is ensured, which helps to identify and distinguish systolic pressure from diastolic pressure. This method can also capture small changes in blood pressure, especially in individuals with large or unstable blood pressure fluctuations. For example, the user's blood pressure is within the normal range, but there are certain blood pressure fluctuations, and it may be difficult to accurately capture these fluctuations using traditional blood pressure measurement methods. However, through the method in the above steps, the systolic pressure at the first time point can be accurately identified when the second pulse waveform rises again; and as the cuff pressure is released, when the period and height of the second pulse waveform match the first pulse waveform, the diastolic pressure at the second time point can be accurately identified, and accurate blood pressure measurement results can be obtained even when the blood pressure fluctuates.

[0071] Furthermore, in the above step S4, respectively comparing the brightness changes of the time series in the first target image and the second target image, and calculating the first pulse wave data and the second pulse wave data, comprises:

[0072] Extracting the shape and position of the blood vessel from the first target image, and forming a simplified blood vessel image based on the shape and position of the blood vessel, and using signal processing technology to identify a periodic pattern of brightness changes in the simplified blood vessel image, wherein the periodic pattern corresponds to a pulse wave;

[0073] Performing time series analysis on the detected periodic pattern and acquiring first pulse wave data, wherein the first pulse wave data includes a timestamp and a corresponding pressure value;

[0074] Repeat the above steps to obtain the second pulse wave data.

[0075] Specifically, by extracting the shape and position of the blood vessel from the first target image, the blood vessel area can be more accurately located, providing an accurate anatomical basis for subsequent pulse wave detection. A simple blood vessel image is formed based on the extracted blood vessel shape and position, which is convenient for identifying the brightness change of the blood vessel and reducing the interference of other tissues or backgrounds. The signal processing technology is used to identify the periodic brightness change pattern in the simple blood vessel image, which corresponds to the pulse wave, so that the existence of the pulse wave can be accurately detected. The detected periodic pattern is analyzed in time series to obtain the time characteristics of the pulse wave, including information such as period and frequency. The first pulse wave data and the second pulse wave data obtained include a timestamp and a corresponding pressure value, thereby providing detailed data support for the dynamic changes of blood pressure. For example, the user is an elderly person, whose blood vessels are fragile and the pulse waveform may not be obvious enough. It may be difficult to accurately detect the pulse wave using a traditional blood pressure measurement method. However, through the method in the above steps, the shape and position of the blood vessel are first extracted from the first target image, and then a simple blood vessel image is constructed and the periodic brightness change pattern therein is identified. Through time series analysis, the first pulse wave data, including a timestamp and a corresponding pressure value, can be accurately obtained. After repeating this process to obtain the second pulse wave data, the two sets of data can be compared to accurately measure the systolic and diastolic blood pressures. This method not only improves the accuracy of blood pressure measurement, but also reduces the measurement errors caused by fragile blood vessels or unclear pulse waveforms, providing a more reliable means of blood pressure monitoring.

[0076] Furthermore, in the above step S4, the first pulse waveform and the second pulse waveform are combined into a complete one, including:

[0077] Respectively obtain a first start time and a second start time in the first pulse wave data and the second pulse wave data, and when the first start time is not equal to the second start time, calculate a time offset between the first start time and the second start time, and based on the time offset, add or subtract the time offset from the timestamp of each sample in the second pulse wave data, wherein the first start time indicates the time when the first pulse wave data is started to be obtained, and the second start time indicates the time when the second pulse wave data is started to be obtained;

[0078] Based on the first start time and the second start time, the first pulse wave data and the second pulse wave data are fused together using a Kalman filter method, and the first pulse waveform and the second pulse waveform are displayed on the same time axis.

[0079] Specifically, it is assumed that when the user is measuring blood pressure, the first pulse wave data (finger without pressure) shows clear systolic and diastolic peaks, but the second pulse wave data (finger with pressure) is not obvious enough due to the influence of position or pressure. Through the above steps, the time offset of the two sets of data is first calculated, and then the two waveforms are fused using the Kalman filter method. The fused waveform may be smoother and more accurate, and the determination of systolic and diastolic pressure is clearer, thereby providing a more reliable blood pressure measurement result. This method is particularly suitable for situations where the user's blood vessels are unclear or the blood pressure changes are subtle, and can significantly improve the accuracy of blood pressure measurement. Among them, the time offset of the first pulse wave data and the second pulse wave data is calculated to solve the problem of inconsistent starting time of the two pulse wave data. After correction by the above scheme, the two waveform data can be compared and analyzed on the same time basis, providing an accurate basis for subsequent data processing and analysis. Using the Kalman filter method to fuse the two pulse wave data can effectively combine information from different measurement positions, reduce the influence of random noise and system errors, and improve the stability of blood pressure measurement. Among them, the Kalman filter method belongs to the prior art and will not be repeated here.

[0080] Furthermore, the above step S5 also includes:

[0081] The sound sensor starts to collect the sound generated by the blood vessels of the user's fingers after the air pump inflates the air bag of the cuff and the pressure on the user's arm stabilizes. When the sound first appears, the corresponding third time point and the pressure value corresponding to the third time point are recorded. As the pressure on the user's arm is released, when the sound disappears, the corresponding fourth time point and the pressure value corresponding to the fourth time point are recorded.

[0082] Compare the pressure value of the user's blood vessel at a first time point with the pressure value at a third time point, and obtain a first comparison result; compare the pressure value of the user's blood vessel at a second time point with the pressure value at a fourth time point, and obtain a second comparison result; when any one of the first comparison result and the second comparison result is greater than or equal to a preset difference, remeasure the user's blood vessel pressure value until both the first comparison result and the second comparison result are less than the preset difference.

[0083] Specifically, the sound generated by the blood vessels collected by the sound sensor can assist in judging the changes in blood pressure, especially when the pulse waveform is not obvious or there is interference. The time points when the sound first appears and disappears and the corresponding pressure values ​​can more accurately identify the boundaries of systolic and diastolic pressures. Dynamic monitoring of pressure changes during air pump inflation and pressure release can capture the key moments of blood pressure changes, thereby improving the accuracy of the measurement. By comparing the pressure values ​​at different time points and comparing them with the preset difference, possible accidental errors can be identified and re-measurement can be triggered until a stable result is obtained. For example, the user is a patient with a history of hypertension and has large blood pressure fluctuations. During the measurement process, the pressure values ​​at the first time point and the second time point are first determined by the pulse waveform. Subsequently, the sound sensor starts to collect sound after the cuff inflation is stable, and records the third and fourth time points when the sound first appears and disappears and their corresponding pressure values. By comparing the pressure value corresponding to the first time point with the pressure value corresponding to the third time point, it is found that the first comparison result is greater than the preset difference, triggering re-measurement. After several measurements, when both the first comparison result and the second comparison result are less than the preset difference, the blood pressure obtained is more accurate. This method not only improves the accuracy of blood pressure measurement, but also reduces the measurement error caused by blood pressure fluctuations through dynamic monitoring and automated judgment, providing more reliable data for blood pressure monitoring in hypertensive patients.

[0084] Further, determining the period and height of the first pulse waveform and the second pulse waveform includes:

[0085] Identify the time interval between two consecutive pulse wave peaks in the first pulse waveform to determine the period of the first pulse wave, and measure the vertical distance between adjacent peaks and troughs in the first pulse waveform to determine the height of the first pulse wave;

[0086] The above steps are repeated to determine the period of the second pulse waveform and the height of the second pulse waveform.

[0087] Specifically, by identifying the time interval between two consecutive pulse wave peaks, the period of the pulse wave, which is a key parameter in blood pressure measurement, can be determined more accurately. By measuring the vertical distance between adjacent peaks and troughs, the height change of the pulse wave can be quantified, reflecting the dynamic fluctuation of intravascular pressure. For example, the user is a worker who often performs physical labor, and his heart rate and blood pressure may vary due to daily activities. When measuring blood pressure, first identify the time interval between two consecutive pulse wave peaks in the first pulse waveform to determine the period of the pulse wave. Then measure the vertical distance between adjacent peaks and troughs to determine the height of the pulse wave. Repeat the above steps to determine the period and height of the second pulse waveform. In this way, even when the user has a faster heart rate or higher blood pressure, the period and height of the pulse waveform can be accurately measured, thereby more accurately calculating systolic and diastolic pressures.

[0088] The present invention also provides a Figure 2 The intelligent blood pressure measurement system shown includes a cuff with an air bag, an air pump and an exhaust valve installed on the cuff, and includes the following modules:

[0089] A detection unit, used to take a finger corresponding to an arm of a user not wearing a cuff as a first position, and a finger corresponding to another arm of a user wearing a cuff as a second position, and to place a first detection unit and a second detection unit at the first position and the second position respectively, wherein the detection unit is provided with a light source and a camera unit respectively, wherein the detection unit includes a first detection unit and a second detection unit;

[0090] The detection units are also provided with sound sensors, which collect the sound generated by the blood vessels of the user's fingers;

[0091] The control unit is configured to trigger the light sources on the first detection unit and the second detection unit to emit light, and receive the light transmitted through the finger through the camera units on the first detection unit and the second detection unit respectively, and continuously photograph the finger at a preset time interval to obtain a first blood flow image sequence and a second blood flow image sequence;

[0092] Inflate the air bag of the cuff through an air pump, and adjust the amount of gas flowing into the air bag through a control unit to adjust the pressure applied to the user's arm until the pressure stabilizes for a preset time, and continuously acquire the first blood flow image sequence and the second blood flow image sequence. After the pressure stabilizes for a preset time, deflate the air bag of the cuff through an exhaust valve, and continuously acquire the first blood flow image sequence and the second blood flow image sequence again until the blood pressure measurement of the user is completed;

[0093] a calculation unit, configured to process the first blood flow image sequence and the second blood flow image sequence respectively, and merge the first blood flow image sequence into a first target image and the second blood flow image sequence into a second target image respectively based on the timestamp, and compare the brightness changes of the time series in the first target image and the second target image respectively, calculate the first pulse wave data and the second pulse wave data, and merge the first pulse wave data and the second pulse wave data into a complete first pulse waveform and a second pulse waveform, and calculate the pressure value of the blood vessel of the user's finger at the first time point and the pressure value at the second time point based on the first pulse waveform and the second pulse waveform;

[0094] The verification unit is used to calculate the third time point and the pressure value corresponding to the third time point, the fourth time point and the pressure value corresponding to the fourth time point based on the sound, compare the pressure value in the second pulse wave data at the same time point with the pressure value corresponding to the sound, and obtain the comparison result. When the comparison results are all less than the preset difference, the pressure value corresponding to the first time point or the third time point is used as the user's systolic pressure, and the pressure value corresponding to the second time point or the fourth time point is used as the user's diastolic pressure.

[0095] The present invention also provides a computer storage medium, which stores program instructions, wherein when the program instructions are executed, the device where the computer storage medium is located is controlled to execute the above-mentioned intelligent blood pressure measurement method.

[0096] In summary, by wearing a cuff with an air bag on the user's arm, and taking the finger corresponding to the user's arm without the cuff as the first position, and the finger corresponding to the other arm of the user wearing the cuff as the second position, the first detection unit and the second detection unit are placed at the first position and the second position respectively, and the detection units are respectively provided with a light source and a camera unit. The light source emits light that passes through the finger, and the camera unit can capture the light that passes through the finger. The user can measure blood pressure at any time, and use multiple pulse wave data to analyze the user's blood pressure, which can reduce the errors that may occur in traditional blood pressure measurement methods, and through the automated light source and camera unit, the pulse wave data can be automatically collected and analyzed, reducing human operation errors and improving the accuracy of measurement. The control unit triggers the light source on the first detection unit and the second detection unit to emit light to reduce the influence of ambient light on the camera unit capturing the blood flow image, which helps to improve the signal-to-noise ratio of the image, thereby more accurately analyzing the blood flow situation. The light transmitted through the finger is received by the camera units on the first detection unit and the second detection unit respectively, and the finger is photographed continuously at a preset time interval to obtain the first blood flow image sequence and the second blood flow image sequence, which can dynamically monitor the blood flow changes. Continuous monitoring can better reflect the real state of blood flow than a single measurement, thereby improving the accuracy of blood pressure measurement. The air bag of the cuff is inflated by an air pump, and the amount of gas flowing into the air bag is adjusted by the control unit to adjust the pressure applied to the user's arm until the pressure remains stable for a preset time, and the first blood flow image sequence and the second blood flow image sequence are continuously obtained. After the pressure remains stable for a preset time, the air bag of the cuff is deflated by the exhaust valve, and the first blood flow image sequence and the second blood flow image sequence are continuously obtained again until the user's blood pressure measurement is completed, so as to monitor the changes in the blood vessels at all times and provide data support for obtaining the user's blood pressure. The first blood flow image sequence and the second blood flow image sequence are processed respectively, and based on the timestamp, the first blood flow image sequence is merged into a first target image, and the second blood flow image sequence is merged into a second target image, respectively, and the brightness changes of the time series in the first target image and the second target image are compared respectively, and the first pulse wave data and the second pulse wave data are calculated, and the first pulse wave data and the second pulse wave data are merged into a complete first pulse waveform and a second pulse waveform, so as to have a more comprehensive understanding of the change law of the pulse wave, so as to more accurately identify key time points such as systolic pressure (pressure value corresponding to the first time point) and diastolic pressure (pressure value corresponding to the second time point), determine the first time point and the second time point based on the first pulse waveform and the second pulse waveform, and respectively calculate the pressure value of the finger blood vessels at the first time point and the pressure value at the second time point when the user is affected by the cuff pressure.

[0097] The detection unit is also provided with a sound sensor, which collects the sound generated by the blood vessels of the user's fingers, calculates the third time point and the pressure value corresponding to the third time point, the fourth time point and the pressure value corresponding to the fourth time point based on the sound, compares the pressure value in the second pulse wave data at the same time point with the pressure value corresponding to the sound, and the two verify each other to improve the accuracy of blood pressure measurement; when the comparison results are less than the preset difference, the pressure value corresponding to the first time point or the third time point is used as the user's systolic pressure, and the pressure value corresponding to the second time point or the fourth time point is used as the user's diastolic pressure. Through the coordination between the above schemes, the accuracy of blood pressure measurement is further improved.

[0098] It should be understood that, although each step in the flow chart of each embodiment of the present invention is shown in sequence according to the indication of the arrow, these steps are not necessarily performed in sequence according to the order indicated by the arrow. Unless there is a clear explanation in this article, the execution of these steps does not have a strict order restriction, and these steps can be performed in other orders. Moreover, at least a portion of the steps in each embodiment may include a plurality of sub-steps or a plurality of stages, and these sub-steps or stages are not necessarily performed at the same time, but can be performed at different times, and the execution order of these sub-steps or stages is not necessarily performed in sequence, but can be performed in turn or alternately with at least a portion of other steps or sub-steps or stages of other steps.

[0099] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program. The above-mentioned program can be stored in a non-volatile computer-readable storage medium. When the program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM is available in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).

[0100] The technical features of the above-mentioned embodiments can be combined arbitrarily. In order to make the description concise, not all possible combinations of the technical features in the above-mentioned embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0101] The above-mentioned embodiments only express several implementation methods of the present invention, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the patent of the present invention. It should be pointed out that, for ordinary technicians in this field, several variations and improvements can be made without departing from the concept of the present invention, and these all belong to the protection scope of the present invention. Therefore, the protection scope of the patent of the present invention shall be subject to the attached claims.

[0102] The above are only preferred embodiments of the present invention and are not intended to limit the present invention. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. An intelligent blood pressure measurement method, wherein a cuff with an air bag is worn on the user's arm, and an air pump and an exhaust valve are installed on the cuff, characterized in that: The method comprises: Step S1: taking a finger corresponding to an arm of a user not wearing the cuff as a first position, and taking a finger corresponding to another arm of the user wearing the cuff as a second position, placing a first detection unit and a second detection unit at the first position and the second position respectively, wherein the detection units are respectively provided with a light source and a camera unit, wherein the detection units include the first detection unit and the second detection unit; Step S2: the control unit triggers the light sources on the first detection unit and the second detection unit to emit light, and receives the light transmitted through the finger through the camera units on the first detection unit and the second detection unit respectively, and continuously photographs the finger at a preset time interval to obtain a first blood flow image sequence and a second blood flow image sequence; Step S3: inflating the airbag of the cuff by the air pump, and adjusting the amount of gas flowing into the airbag by the control unit to adjust the pressure applied to the user's arm, until the pressure remains stable for a preset time, and the first blood flow image sequence and the second blood flow image sequence are continuously acquired, and after the pressure remains stable for the preset time, the airbag of the cuff is deflated by the exhaust valve, and the first blood flow image sequence and the second blood flow image sequence are continuously acquired again, until the blood pressure measurement of the user is completed; Step S4: processing the first blood flow image sequence and the second blood flow image sequence respectively, and merging the first blood flow image sequence into a first target image and the second blood flow image sequence into a second target image based on the timestamp respectively, comparing the brightness changes of the time series in the first target image and the second target image respectively, calculating the first pulse wave data and the second pulse wave data, and merging the first pulse wave data and the second pulse wave data into a complete first pulse waveform and a second pulse waveform based on the first pulse waveform and the second pulse waveform, determining a first time point and a second time point based on the first pulse waveform and the second pulse waveform, and respectively calculating the pressure value of the blood vessels of the finger of the user at the first time point and the pressure value at the second time point when the blood vessels are affected by the cuff pressure; In step S4, based on the first pulse waveform and the second pulse waveform, determining a first time point and a second time point, and respectively calculating a pressure value of a finger blood vessel of the user at the first time point and a pressure value at the second time point when the user is affected by the cuff pressure, include: When the second pulse waveform rises again or the second pulse wave data changes again, recording the time point at this time as the first time point, and recording the pressure value corresponding to the first time point; Determining the period and height of the first pulse waveform and the second pulse waveform, and as the pressure on the user's arm begins to be released, when the period and height of the second pulse waveform are the same as those of the first pulse waveform, recording the time point at this time as a second time point, and recording the pressure value corresponding to the second time point; Step S5: The detection units are also respectively provided with sound sensors, which collect the sounds generated by the blood vessels of the user's fingers through the sound sensors, calculate the third time point and the pressure value corresponding to the third time point, the fourth time point and the pressure value corresponding to the fourth time point based on the sounds, compare the pressure value in the second pulse wave data at the same time point with the pressure value corresponding to the sounds, and obtain comparison results. When the comparison results are all less than a preset difference, the pressure value corresponding to the first time point or the third time point is used as the systolic pressure of the user, and the pressure value corresponding to the second time point or the fourth time point is used as the diastolic pressure of the user.

2. The method according to claim 1, characterized in that After calculating the first pulse wave data and the second pulse wave data in step S4, and before merging the first pulse wave data and the second pulse wave data into a complete first pulse waveform and a complete second pulse waveform, the method further includes: The heartbeat unit obtains the user's heart rate through the first pulse wave data, and obtains the trend of the heart rate changing over time, and uses the difference between the maximum heart rate and the minimum heart rate in the heart rate changing trend as the heart rate changing value; When the heart rate data is less than the preset heart rate threshold and the heart rate change value is less than the heart rate change threshold, it is defined that the user is in a calm state. When the user is in the calm state, continue to execute step S4, otherwise, suspend the blood pressure measurement.

3. The method according to claim 1, characterized in that In the step S4, respectively comparing the brightness changes of the time series in the first target image and the second target image to calculate the first pulse wave data and the second pulse wave data includes: Extracting the shape and position of the blood vessel from the first target image, and forming a simplified blood vessel image based on the shape and position of the blood vessel, and using signal processing technology to identify a periodic pattern of brightness changes in the simplified blood vessel image, wherein the periodic pattern corresponds to a pulse wave; Performing time series analysis on the detected periodic pattern and acquiring first pulse wave data, wherein the first pulse wave data includes a timestamp and a corresponding pressure value; Repeat the above steps to obtain the second pulse wave data.

4. The method according to claim 1, characterized in that: In step S4, the first pulse waveform and the second pulse waveform are combined into a complete waveform, including: Respectively obtain a first start time and a second start time in the first pulse wave data and the second pulse wave data, and when the first start time is not equal to the second start time, calculate a time offset between the first start time and the second start time, and based on the time offset, add or subtract the time offset from the timestamp of each sample in the second pulse wave data, wherein the first start time indicates the time when the first pulse wave data is started to be obtained, and the second start time indicates the time when the second pulse wave data is started to be obtained; Based on the first start time and the second start time, the first pulse wave data and the second pulse wave data are fused together using a Kalman filter method, and the first pulse waveform and the second pulse waveform are displayed on the same time axis.

5. The method according to claim 1, characterized in that The step S5 further comprises: The sound sensor starts to collect the sound generated by the blood vessels of the user's fingers after the air pump inflates the air bag of the cuff and the pressure on the user's arm stabilizes, and records the corresponding third time point and the pressure value corresponding to the third time point when the sound first appears, and records the corresponding fourth time point and the pressure value corresponding to the fourth time point when the pressure on the user's arm is released and the sound disappears; Compare the pressure value of the user's blood vessel at the first time point with the pressure value at the third time point, and obtain a first comparison result, compare the pressure value of the user's blood vessel at the second time point with the pressure value at the fourth time point, and obtain a second comparison result, and when any one of the first comparison result and the second comparison result is greater than or equal to the preset difference, re-measure the user's blood vessel pressure value until both the first comparison result and the second comparison result are less than the preset difference.

6. The method according to claim 1, characterized in that Determining the period and height of the first pulse waveform and the second pulse waveform includes: Identifying the time interval between two consecutive pulse wave peaks in the first pulse waveform to determine the period of the first pulse wave, and measuring the vertical distance between adjacent peaks and troughs in the first pulse waveform to determine the height of the first pulse wave; Repeat the above steps to determine the period of the second pulse waveform and the height of the second pulse waveform.

7. An intelligent blood pressure measurement system, a cuff with an air bag, an air pump and an exhaust valve installed on the cuff, used to implement the method according to any one of claims 1 to 6, characterized in that: The system includes the following modules: The detection unit is configured to take the finger corresponding to the arm of the user not wearing the cuff as the first position, and take the finger corresponding to the other arm of the user wearing the cuff as the second position, and place the first detection unit and the second detection unit at the first position and the second position respectively, and the detection unit is respectively provided with a light source and a camera unit, wherein the detection unit includes the first detection unit and the second detection unit; A sound sensor is also provided respectively, and the sound generated by the blood vessels of the user's fingers is collected by the sound sensor; The control unit is configured to trigger the light sources on the first detection unit and the second detection unit to emit light, and receive the light transmitted through the finger through the camera units on the first detection unit and the second detection unit respectively, and continuously photograph the finger at a preset time interval to obtain a first blood flow image sequence and a second blood flow image sequence; Inflate the airbag of the cuff through the air pump, and adjust the pressure applied to the user's arm by adjusting the amount of gas flowing into the airbag through the control unit, until the pressure remains stable for a preset time, and the first blood flow image sequence and the second blood flow image sequence are continuously acquired, and after the pressure remains stable for the preset time, deflate the airbag of the cuff through the exhaust valve, and continue to acquire the first blood flow image sequence and the second blood flow image sequence again, until the blood pressure measurement of the user is completed; a calculation unit, configured to process the first blood flow image sequence and the second blood flow image sequence respectively, and merge the first blood flow image sequence into a first target image and the second blood flow image sequence into a second target image based on a timestamp, respectively compare brightness changes of the time series in the first target image and the second target image, calculate first pulse wave data and second pulse wave data, and merge the first pulse wave data and the second pulse wave data into a complete first pulse waveform and a second pulse waveform, determine a first time point and a second time point based on the first pulse waveform and the second pulse waveform, and respectively calculate a pressure value of a blood vessel of a finger of the user at the first time point and a pressure value at the second time point when the blood vessel is affected by the cuff pressure; In the calculation unit, based on the first pulse waveform and the second pulse waveform, a first time point and a second time point are determined, and the pressure value of the blood vessels of the finger of the user at the first time point and the pressure value at the second time point when the user is affected by the cuff pressure are respectively calculated, including: when the second pulse waveform rises again or the second pulse wave data changes again, the time point at this time is recorded as the first time point, and the pressure value corresponding to the first time point is recorded; the period and height of the first pulse waveform and the second pulse waveform are determined, and as the pressure on the user's arm begins to be released, when the period and height of the second pulse waveform are the same as those of the first pulse waveform, the time point at this time is recorded as the second time point, and the pressure value corresponding to the second time point is recorded; A verification unit is used to calculate, based on the sound, a third time point and a pressure value corresponding to the third time point, a fourth time point and a pressure value corresponding to the fourth time point, compare the pressure value in the second pulse wave data at the same time point with the pressure value corresponding to the sound, and obtain a comparison result, and when the comparison results are all less than a preset difference, use the pressure value corresponding to the first time point or the third time point as the user's systolic pressure, and use the pressure value corresponding to the second time point or the fourth time point as the user's diastolic pressure.

8. A computer storage medium, characterized in that The storage medium stores program instructions, wherein when the program instructions are executed, the device where the storage medium is located is controlled to execute the intelligent blood pressure measurement method according to any one of claims 1 to 6.

Images