Method and apparatus for calibrating a blood pressure estimation model for determining a blood pressure graph

Abstract

The embodiment of the present application provides a calibration method and device for a blood pressure estimation model for determining a blood pressure map, which relates to the intersection of biomedicine and science and engineering. The method includes: after applying a first pressure to a first preset position, determining the conduction time of each pulse wave in a preset area during a preset action within a plurality of preset time periods; for each preset time period, obtaining the first pressure at each first moment and the first height difference of the first preset position relative to the heart position; obtaining the second pressure based on the first pressure at all first moments; determining the sample blood pressure information within the preset time period based on the second pressure and the first height difference to calibrate the blood pressure estimation model, and obtaining continuous beat-by-beat blood pressure information based on the blood pressure estimation model, and obtaining a blood pressure map based on the beat-by-beat blood pressure information and the target photoelectric capacitance signal. The embodiment of the present application can calibrate the blood pressure estimation model without the aid of a cuff-type blood pressure measurement device, and can obtain a high-precision blood pressure map.

Description

Technical Field

[0001] The present application relates to the interdisciplinary field of biomedicine and science and engineering. Specifically, the present application relates to a calibration method and apparatus for a blood pressure estimation model for determining a blood pressure graph. Background Art

[0002] Cardiovascular disease is the leading cause of death and disability worldwide and the world's number one killer. Among the various fatal factors of cardiovascular disease, hypertension ranks first and is the most important risk factor. Therefore, it is very important to measure blood pressure in daily life.

[0003] Existing devices for measuring blood pressure are wearable blood pressure measurement devices. Wearable blood pressure measurement devices measure blood pressure through a blood model. The blood pressure estimation model reflects the relationship between surface blood pressure information and physiological signals. After the blood model is constructed, the wearable blood pressure measurement device inputs the collected physiological signals into the corresponding blood pressure estimation model to obtain blood pressure information. However, most blood pressure estimation models have corresponding calibration parameters. The calibration parameters are unknown constant parameters. The process of determining these calibration parameters is called the calibration process of the blood pressure model. The existing solution for the calibration process of the blood pressure model is: using a cuff-type blood pressure measurement device to measure multiple single-time sample blood pressures, substituting the multiple single-time sample blood pressures into the blood pressure estimation model, and calculating the calibration parameters. Obviously, the entire calibration process requires the additional use of a cuff-type blood pressure measurement device. It is necessary to manually substitute the multiple single-time sample blood pressures measured by the cuff-type blood pressure measurement device into the blood pressure estimation model to obtain the unknown constant parameters. The process is relatively cumbersome and complicated. Summary of the Invention

[0004] The present invention provides a method, apparatus, electronic device, computer-readable storage medium, and computer program product for calibrating a blood pressure estimation model for determining a blood pressure graph. These methods address the need to calibrate the blood pressure estimation model using sample blood pressure measurements taken with an additional cuff-type blood pressure measurement device. The technical solution is as follows:

[0005] According to a first aspect of an embodiment of the present application, a method for calibrating a blood pressure estimation model for determining a blood pressure map is provided, the method comprising:

[0006] In response to applying a first pressure of a predetermined degree to a first predetermined position, determining the pulse wave transmission time of each pulse wave at each moment in a predetermined region of the target object during a predetermined movement within a plurality of predetermined time periods; the predetermined region being a region starting from the first predetermined position;

[0007] For each preset time period, a curve formed by pulse wave transmission times at each moment in the preset time period is derived, and the moment at which the derivative meets a first preset condition is determined as the first moment; a first pressure at each first moment is obtained, and a second pressure is obtained based on the distribution of the first pressures at all first moments; a first height difference between the first preset position and the heart position at the first moment is obtained, and a first target height difference is obtained based on the distribution of all first height differences; sample blood pressure information within the preset time period is determined based on the second pressure and the first target height difference; the sample blood pressure information includes at least one of the sample average blood pressure, the sample systolic pressure, and the sample diastolic pressure;

[0008] Based on sample blood pressure information and sample physiological signals of multiple preset time periods, calibrating a pre-established initial blood pressure estimation model indicating the relationship between the blood pressure information and the physiological signals to obtain a target blood pressure estimation model;

[0009] Acquiring a continuous target physiological signal from a target subject, inputting the continuous target physiological signal into a target blood pressure estimation model, and obtaining a plurality of beat-by-beat blood pressure information output by the target blood pressure estimation model; the target physiological signal includes a target photoplethysmography signal;

[0010] A blood pressure map of the target subject is determined based on the continuous target photoplethysmography signal and the beat-by-beat blood pressure information.

[0011] In one possible implementation, determining the sample blood pressure information within a preset time period based on the second pressure and the first target height difference further includes:

[0012] Determine the sample photoplethysmography signal at the first preset position, and determine each time when the oscillation amplitude of the pulse wave is the maximum value as the second time;

[0013] Obtaining the first pressure at each second moment, and obtaining the third pressure according to the distribution of the first pressures at all second moments;

[0014] Obtaining a second height difference between the first preset position and the heart position at a second moment, and obtaining a second target height difference based on a distribution of all the second height differences;

[0015] determining an average of the second pressure and the third pressure as a fourth pressure; and taking an average of the first target height difference and the second target height difference as a third target height difference;

[0016] The sample blood pressure information within a preset time period is determined according to the fourth pressure and the third target height difference.

[0017] In one possible implementation, determining a blood pressure map of a target subject based on a continuous target photoplethysmography signal and beat-by-beat blood pressure information includes:

[0018] A transfer function between a pre-established target photoplethysmography signal and blood pressure information is determined, and the beat-by-beat blood pressure information and the continuous photoplethysmography signal are input into the transfer function to obtain a blood pressure graph output by the transfer function.

[0019] In one possible implementation, determining the sample blood pressure information within each preset time period according to the second pressure and the first target height difference includes:

[0020] Acquiring a blood density of the target object, and determining a first blood static pressure at a first preset position according to the blood density and a first target height difference;

[0021] The blood pressure information of the samples in each preset time period is determined according to the second pressure and the first blood static pressure.

[0022] In one possible implementation, determining the sample blood pressure information within each preset time period based on the second pressure and the first blood static pressure includes:

[0023] The sum of the second pressure and the first blood static pressure is taken as the sample average blood pressure;

[0024] determining a blood pressure at a first preset ratio of the rising edge of the derivative as a first systolic pressure, and taking the sum of the first systolic pressure and the first blood static pressure as the sample systolic pressure;

[0025] The blood pressure at a second preset ratio of the falling edge of the derivative is determined as the first diastolic pressure, and the sum of the first diastolic pressure and the first blood static pressure is used as the sample diastolic pressure.

[0026] In one possible implementation, determining the sample blood pressure information within a preset time period based on the fourth pressure and the third target height difference includes:

[0027] obtaining a blood density of the target object, and determining a second blood static pressure at a first preset position according to the blood density and a third target height difference;

[0028] The blood pressure information of the samples within the preset time period is determined according to the fourth pressure and the second blood static pressure.

[0029] In one possible implementation, determining the sample blood pressure information within a preset time period based on the fourth pressure and the second blood static pressure includes:

[0030] The sum of the fourth pressure and the second static blood pressure is taken as the sample average blood pressure;

[0031] determining an envelope of an oscillation wave of the sample photoplethysmography signal at a first preset position, determining a blood pressure at a third preset ratio of a rising edge of the envelope as a second systolic pressure, and using the sum of the second systolic pressure and the second static blood pressure as the sample systolic pressure;

[0032] The blood pressure at a fourth preset ratio of the falling edge of the envelope is determined as the second diastolic pressure, and the sum of the second diastolic pressure and the second blood static pressure is used as the sample diastolic pressure.

[0033] In one possible implementation, applying a first pressure of a preset degree to the first preset position includes:

[0034] At the first preset position, a first pressure of a preset degree is applied by conditioning the diameter or contact pressure of the target ring.

[0035] In one possible implementation, the target ring-type device is worn at a first preset position, which is the distal end of the finger; the preset area also includes a second preset position. If the second preset position is the proximal end of the finger, a non-adjustable ring-type device that can collect photoplethysmography signals is worn at the second preset position; if the second preset position is other than the proximal end of the finger, a corresponding external electronic device that can collect photoplethysmography signals is worn at the second preset position.

[0036] In one possible implementation, the sample photoplethysmography signal or the target photoplethysmography signal is filtered as follows:

[0037] Acquire raw photoplethysmography signals of multiple channels;

[0038] For the original photoplethysmography signal of any channel, the target component in the photoplethysmography signal is extracted by integrating constrained independent component analysis, adaptive filtering, and the base source number hypothesis method, and the target component is input into the adaptive filter to instruct the adaptive filter to reply the photoplethysmography signal according to the target component to obtain a sample photoplethysmography signal or a target photoplethysmography signal.

[0039] In one possible implementation, after determining a blood pressure map of the target subject based on the continuous target photoplethysmography signal and the beat-by-beat blood pressure information, the method further includes:

[0040] The blood pressure graph is sent to an external display device to instruct the external display device to display the blood pressure graph.

[0041] According to a second aspect of an embodiment of the present application, there is provided a calibration apparatus for determining a blood pressure estimation model of a blood pressure diagram, the apparatus comprising:

[0042] a pulse wave transit time determination module, configured to determine, in response to a first pressure of a predetermined degree being applied to a first predetermined position, the pulse wave transit time of each pulse wave at each moment in a predetermined region of a predetermined portion of the target object during a predetermined motion within a plurality of predetermined time periods; the predetermined region being a region starting from the first predetermined position;

[0043] The sample blood pressure information determination module is configured to, for each preset time period, derive a curve formed by pulse wave transmission times at each moment within the preset time period, and determine a moment at which the derivative meets a first preset condition as a first moment; obtain a first pressure at each first moment, and obtain a second pressure based on a distribution of the first pressures at all first moments; obtain a first height difference between a first preset position and a heart position at the first moment, and obtain a first target height difference based on a distribution of all first height differences; and determine sample blood pressure information within the preset time period based on the second pressure and the first target height difference; the sample blood pressure information including at least one of a sample mean blood pressure, a sample systolic pressure, and a sample diastolic pressure;

[0044] a blood pressure estimation model acquisition module, configured to calibrate a pre-established initial blood pressure estimation model indicating the relationship between the blood pressure information and the physiological signals based on sample blood pressure information and sample physiological signals for a plurality of preset time periods, to obtain a target blood pressure estimation model;

[0045] a beat-by-beat blood pressure information determination module, configured to obtain a continuous target physiological signal at a first preset location of a target subject, input the continuous target physiological signal into a pre-established target blood pressure estimation model, and obtain a plurality of beat-by-beat blood pressure information output by the target blood pressure estimation model; the target physiological signal includes a target photoplethysmography signal;

[0046] The blood pressure map determination module is used to determine the blood pressure map of the target object based on the continuous target photoplethysmography signal and the beat-by-beat blood pressure information.

[0047] According to a third aspect of an embodiment of the present application, an electronic device is provided, which includes a memory, a processor, and a computer program stored in the memory, and when the processor executes the program, the steps of the method provided in the first aspect are implemented.

[0048] According to a fourth aspect of an embodiment of the present application, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps of the method provided in the first aspect are implemented.

[0049] According to the fifth aspect of the embodiment of the present application, a computer program product is provided, which includes computer instructions, and the computer instructions are stored in a computer-readable storage medium. When the processor of a computer device reads the computer instructions from the computer-readable storage medium, the processor executes the computer instructions, so that the computer device performs the steps of implementing the method provided in the first aspect.

[0050] The beneficial effects of the technical solution provided by the embodiments of the present application are:

[0051] The embodiment of the present application determines the pulse wave transmission time of each pulse wave at each moment in a preset area of ​​a preset part of a target object during a preset action within multiple preset time periods in response to applying a first pressure of a preset degree to a first preset position; the preset area is an area starting from the first preset position; for each preset time period, a curve composed of the pulse wave transmission times at each moment in the preset time period is derived, and the moment when the derivative meets the first preset condition is determined as the first moment; for each first moment, a first pressure at the first moment and a first height difference of the first preset position relative to the heart position at the first moment are obtained; a second pressure is obtained based on the distribution of the first pressures at all first moments; and a second pressure is obtained based on the first pressures at the first moments. The second pressure and the first height difference determine the sample blood pressure information within a preset time period; the sample blood pressure information includes at least one of the sample average blood pressure, the sample systolic pressure and the sample diastolic pressure; based on the sample blood pressure information and the sample physiological signals of multiple preset time periods, the initial blood pressure estimation model that is pre-established and indicates the relationship between the blood pressure information and the physiological signal is calibrated to obtain a target blood pressure estimation model; the continuous target physiological signal of the target object is obtained, the continuous target physiological signal is input into the target blood pressure estimation model, and a plurality of beat-by-beat blood pressure information output by the target blood pressure estimation model is obtained; the target physiological signal includes a target photoplethysmography signal; the blood pressure map of the target object is determined based on the continuous target photoplethysmography signal and the beat-by-beat blood pressure information. The embodiment of the present application can calibrate the initial blood pressure estimation model through the sample blood pressure information at the first preset position to obtain the target blood pressure estimation model, and the initial blood pressure estimation model can be calibrated without the aid of the sample blood pressure information measured by an additional cuff-type blood pressure measurement device. The entire calibration process does not require manual intervention, is automatic and concise, and a high-precision arterial blood pressure map can be obtained through the target blood pressure model. BRIEF DESCRIPTION OF THE DRAWINGS

[0052] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the following briefly introduces the drawings required for describing the embodiments of the present application.

[0053] Figure 1 A schematic diagram of the system architecture for measuring and displaying a blood pressure graph using a blood pressure estimation model provided in an embodiment of the present application;

[0054] Figure 2 A flowchart of a method for calibrating a blood pressure estimation model for determining a blood pressure graph provided in an embodiment of the present application;

[0055] Figure 3a A schematic diagram of the wearing position of a target ring-shaped device provided in an embodiment of the present application;

[0056] Figure 3b A schematic structural diagram of a target ring-shaped device provided in an embodiment of the present application;

[0057] Figure 4a A schematic diagram of a target ring-shaped device with a buckle-type design provided in an embodiment of the present application;

[0058] Figure 4b A schematic diagram of a target ring-shaped device with a magnetic design provided in an embodiment of the present application;

[0059] Figure 4c A schematic diagram of a button-shaped target ring device provided in an embodiment of the present application;

[0060] Figure 4d A schematic diagram of a target ring-type device designed as a small inflatable cuff provided in an embodiment of the present application;

[0061] Figure 5a This is a schematic diagram corresponding to the four-layer structure of the target ring-shaped device provided in an embodiment of the present application;

[0062] Figure 5b A schematic diagram of the outermost layer of the four-layer structure of the target ring-shaped device provided in an embodiment of the present application;

[0063] Figure 5c A schematic diagram of the third layer of the four-layer structure of the target ring-shaped device provided in an embodiment of the present application;

[0064] Figure 5d A schematic diagram of the second layer of the four-layer structure of the target ring-shaped device provided in an embodiment of the present application;

[0065] Figure 5e A schematic diagram of the innermost layer of the four-layer structure of the target ring-shaped device provided in an embodiment of the present application;

[0066] Figure 6 A schematic diagram of the electrical wiring structure of the adjustable finger ring power supply layer provided in an embodiment of the present application;

[0067] like Figure 7a A schematic diagram of a target ring-shaped device combined with a watch according to an embodiment of the present application;

[0068] like Figure 7b Schematic diagram of the target ring-shaped device provided in an embodiment of the present application combined with various other external electronic devices;

[0069] like Figure 8a A schematic diagram of the wearing positions of two finger-ring devices in a dual-ring design during measurement provided in an embodiment of the present application;

[0070] like Figure 8bA schematic diagram of the wearing positions of two finger-ring devices in a dual-ring design during a non-measurement process provided in an embodiment of the present application;

[0071] Figure 9 A schematic diagram of obtaining a continuous blood pressure graph is provided for an embodiment of the present application;

[0072] Figure 10 Schematic diagrams of obtaining calibrated blood pressure information and continuous blood pressure information under two designs are provided for the embodiments of this application;

[0073] Figure 11 A schematic diagram of noise reduction using constrained independent component analysis and adaptive filtering provided in an embodiment of the present application;

[0074] Figure 12 A schematic structural diagram of a calibration device for determining a blood pressure estimation model of a blood pressure graph provided in an embodiment of the present application;

[0075] Figure 13 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0076] The following describes the embodiments of the present application in conjunction with the accompanying drawings. It should be understood that the embodiments described below in conjunction with the accompanying drawings are exemplary descriptions for explaining the technical solutions of the embodiments of the present application and do not constitute a limitation on the technical solutions of the embodiments of the present application.

[0077] Those skilled in the art will understand that, unless otherwise stated, the singular forms "a", "an", "said", and "the" used herein may also include plural forms. It should be further understood that the terms "including" and "comprising" used in the embodiments of the present application mean that the corresponding features can be implemented as the presented features, information, data, steps, operations, elements, and / or components, but do not exclude implementation as other features, information, data, steps, operations, elements, components, and / or combinations thereof supported by the present technical field. It should be understood that when we say that an element is "connected" or "coupled" to another element, the element can be directly connected or coupled to the other element, or it can refer to the element and the other element establishing a connection relationship through an intermediate element. In addition, the "connection" or "coupling" used here can include wireless connection or wireless coupling. The term "and / or" used here indicates at least one of the items defined by the term, for example, "A and / or B" can be implemented as "A", or as "B", or as "A and B".

[0078] In order to make the objectives, technical solutions and advantages of this application clearer, the implementation methods of this application will be further described in detail below with reference to the accompanying drawings.

[0079] Cardiovascular disease is the leading cause of death and disability worldwide and the world's leading cause of death. Among the multiple contributing factors to cardiovascular disease, hypertension ranks first and is the most important risk factor. Once diagnosed, hypertension requires lifelong treatment. Hypertension screening is typically performed based on clinician blood pressure measurements, but misdiagnosis is common due to white coat or masked hypertension. Therefore, outpatient and home blood pressure monitoring has been recommended as the preferred strategy for detecting hypertension and predicting cardiovascular disease risk. The tonoarteriogram (TAG) signal is defined as a graphical recording of the continuous arterial blood pressure signal, which can be obtained by non-intrusive, wearable, or cuffless continuous arterial blood pressure measurement devices. Unlike traditional single-shot and beat-to-beat blood pressure measurements that only measure systolic and diastolic pressure, the tonoarteriogram signal consists of a continuous blood pressure waveform and provides richer physiological information. It not only contains the traditional systolic and diastolic blood pressure values, but also reflects other important blood pressure information beyond these two values, such as key features such as the notch, or cardiac output and peripheral vascular resistance calculated from the tonoarteriogram. The tonoarteriogram can be used for cardiovascular system assessment and early diagnosis of diseases.

[0080] Currently, non-invasive and invasive blood pressure monitoring methods, such as mercury sphygmomanometers, oscillometric sphygmomanometers, and vascular unloading techniques (also known as volume clamps), are commonly used in clinical practice. These methods, such as mercury sphygmomanometers and invasive blood pressure monitoring, have high operator requirements, and invasive blood pressure monitoring carries the risk of infection. Some equipment, such as the volume clamp method, is very expensive, making these methods difficult to implement at home and in daily life. Among these, upper arm cuff-type blood pressure monitors based on oscillometric measurement are the most widely used in outpatient settings. However, upper arm cuffs are not convenient for ambulatory blood pressure monitoring. Furthermore, according to the standards recommended by the American Heart Association, blood pressure cuffs have strict dimensions, making them difficult to miniaturize, hindering the wearability and non-intrusiveness of upper arm blood pressure monitors. With increasing awareness of the importance of blood pressure and advancements in measurement technology, cuffless blood pressure measurement has become a growing trend in blood pressure monitoring. The IEEE 1708 standard provides evaluation criteria for wearable cuffless blood pressure measurement devices. The cuff-free feature allows it to be used on various wearable carriers that can measure blood pressure anytime and anywhere, such as watches, glasses, mobile phones, clothing, electronic skin or skin-friendly flexible devices.

[0081] To enable convenient and quick upper arm blood pressure measurement in daily life and at home, two viable approaches exist: 1) wearable cuffless blood pressure monitoring technology; and 2) alternative body locations that can reduce the size of the cuff. Currently, cuffless approaches must address the challenges of calibration and recalibration before widespread use (sample blood pressure readings from cuff-based blood pressure measurement devices are still required as a reference).

[0082] As an alternative to upper-arm blood pressure monitoring, researchers have developed and studied oscillometric blood pressure monitoring devices using a small inflatable cuff attached to the finger. Studies have shown that when an appropriately sized cuff is used and held at the same height as the heart, the distal finger (i.e., the fingertip) offers an excellent alternative for oscillometric blood pressure measurement, achieving values ​​comparable to those obtained from upper-arm blood pressure measurements. This minimizes the required cuff size and provides the most consistent average blood pressure with the upper arm. Furthermore, because the finger has readily accessible peripheral arterial vessels, it can also collect precise data on vital body signals, furthering the potential use of finger-based health monitoring, such as blood oxygen levels, sleep monitoring, glucose levels, body composition analysis, and hematocrit levels. Compared to smart wristbands worn on the wrist, these devices are somewhat closer to the body, less snug, and susceptible to motion noise, making it difficult to accurately detect true physiological signals.

[0083] In recent years, there have been some studies on health monitoring methods and devices worn on fingers. Some companies, such as Wellue, K Ring, Helios, ORII, and Go2Sleep have already launched a number of smart ring products. However, most of these ring designs and products are limited to step counting, sleep monitoring, heart rate, and blood oxygen level monitoring. They still lack continuous blood pressure monitoring and calibration. Furthermore, some products are still bulky, potentially interfering with user behavior. Some studies and designs, such as a ring device that uses optical sensors to monitor physiological signals (US2021 / 0169345A1), a dual-ring design with potential applications in physiological signal monitoring (US 2021 / 0096657 Al), and a smart ring that can monitor pulse wave signals (CN106510666 A), although there are innovations in the ring design or sensor arrangement, noise reduction, and signal acquisition, and there is potential application in obtaining continuous blood pressure, there is still no function of continuous blood pressure acquisition and calibration; a ring-type physiological information monitoring device (CN1692874A), which can obtain continuous blood pressure information beat by beat, but has no calibration function; some designs such as (US 7,674,231B2) and (US 8,313,439 B2), can be calibrated but there is little description of the continuous blood pressure estimation model; a cuffless blood pressure monitoring and automatic calibration device applicable to fingers based on a somatosensory network (CN 101773387 B), a ring device for continuous blood pressure estimation and calibration (US 7,641,614 B2), etc. This invention not only can obtain continuous blood pressure information, but also has an automatic calibration function. However, some of the blood pressure monitoring functions require additional equipment for initial calibration, or the continuous blood pressure estimation is simply based on linear or nonlinear fitting of the photoelectric volume signal and blood pressure information. The accuracy needs to be improved and frequent calibration may be required.

[0084] The calibration method, device, electronic device, computer-readable storage medium, and computer program product for determining a blood pressure estimation model of a blood pressure graph provided in this application are intended to solve the above technical problems in the prior art.

[0085] The following describes several exemplary embodiments to illustrate the technical solutions of the embodiments of the present application and the technical effects produced by the technical solutions of the present application. It should be noted that the following embodiments can refer to, draw on, or combine with each other, and the same terms, similar features, and similar implementation steps in different embodiments will not be repeated.

[0086] Figure 1 A schematic diagram of the system architecture for implementing measurement and display of a blood pressure graph using a blood pressure estimation model provided in an embodiment of the present application, including a target ring-type device 110, an external display device 120, and a storage platform 130, as well as data exchange after a communication connection is established between the three. The target ring-type device 110 is a device equipped with multiple sensors. The target ring-type device 110 can collect multiple physiological signals. The blood pressure information of the target subject can be obtained by inputting the collected multiple physiological signals into the target blood pressure estimation model. The external display device 120 can display the multiple physiological signals, blood pressure information, etc. collected by the target ring-type device 110. The storage platform 130 can store the multiple physiological signals, blood pressure information, etc. collected by the target ring-type device 110. The storage platform 130 can be a cloud database 131 or a telemedicine platform 132, etc., and the embodiments of the present application are not limited to this.

[0087] In an embodiment of the present application, a calibration method for a blood pressure estimation model for determining a blood pressure graph is provided, such as Figure 2 As shown, the method includes:

[0088] Step S201, in response to applying a first pressure of a preset degree to a first preset position, determines the pulse wave transmission time of each pulse wave at each moment in a preset area during a preset action at a preset part of the target object within multiple preset time periods; the preset area is an area with the first preset position as the starting position.

[0089] In the embodiment of the present application, the first preset position refers to the distal end of the target object's finger, that is, the fingertip. The target object wears a target finger-ring device on the fingertip. The target finger-ring device is a device with adjustable diameter or contact pressure, made of a material that is not easily deformed, and applies a uniform annular constant pressure, that is, the first pressure, to the fingertip.

[0090] The ring-shaped device targeted by the embodiment of the present application is equipped with a variety of sensors, which can be used to collect a variety of physiological signals, such as photoelectric capacitance sensors, electrocardiogram sensors, pressure sensors, accelerometers, and the like.

[0091] The target ring-type device is provided with a photoelectric capacitance sensor composed of red / infrared LEDs, or a multi-wavelength photoelectric capacitance sensor composed of LEDs, a photodetector (PD) and a pressure sensor at the finger ring that contacts the fingertip, and an accelerometer at the finger ring that contacts the nail. This design takes into account that the fingertip is rich in peripheral arterial blood vessels that are easy to sense, so as to obtain high-quality signals. The accelerometer is located at the nail to prevent the accelerometer from being affected by blood pressure pulsation-related signals. In this invention, the selection and placement of the sensor is only one embodiment of the invention. Figure 3a As shown, it exemplarily shows a schematic diagram of the wearing position of the target ring-type device, which is located at the fingertip of the target object; Figure 3b As shown, it exemplarily shows a structural diagram of the target finger-ring type device of the present application, which includes an accelerometer, a pressure sensor, a photoelectric sensor, an LED photodetector and multiple LEDs.

[0092] The ring-type devices targeted by the embodiments of the present application include, but are not limited to, a buckle-type design, a magnetic-type design, a button-type design, and a small inflatable cuff design.

[0093] like Figures 4a-4d As shown, several types of target ring-type devices are exemplified, 4a shows a buckle-type design, 4b shows a magnetic-type design, Figure 4c 4D shows a small inflatable cuff design. The small inflatable cuff design includes semi-enclosed and fully enclosed inflatable cuff structures. It is wrapped around the fingertips when in use. A micro air pump inflates the small inflatable cuff and pressurizes the measurement site to a pressure exceeding the human body's systolic pressure. A pressure relief valve is used to uniformly release the air in the detachable cuff. After sampling blood pressure information based on the oscillation measurement method, the cuff is comfortably worn near the finger after pressure relief. The blood pressure information is obtained by calibrating the pre-established initial blood pressure estimation model.

[0094] The adjustable target ring device of the embodiment of the present application is composed of 4 layers, such as Figure 5a As shown; Figures 5b-5e Shown are the outermost layer, the third layer, the second layer and the innermost layer in sequence. Figure 5b The outermost layer shown is made of a hard material that is not easily deformed and protects the internal structure from damage by external forces; Figure 5c The third layer shown is the electrical wiring diagram of the adjustable finger ring power supply layer, which is used to power the sensor and transmit signals. Figure 6 This is a schematic diagram of the electrical wiring structure of the adjustable finger ring power supply layer according to an embodiment of the present application; Figure 5d The second layer shown is the sensor distribution layer, which is distributed with sensing components such as LEDs, photodiodes, accelerometers, and pressure sensors; Figure 5eThe innermost layer (closest to the skin layer) shown is made of transparent film silicone and other materials to prevent direct contact between the skin and the sensor distribution layer, and to prevent sweat and other substances from interfering with the sensor and circuit. This material is transparent and smooth, does not interfere with the transmission of optical signals, and keeps the ring shell sealed, waterproof and sweat-proof.

[0095] In the embodiment of the present application, the preset part refers to the arm of the target object, and the preset action process refers to the process of the arm repeatedly staying at different heights n times or straightening the arm, raising and lowering it n times at a constant speed. In the embodiment of the present application, what is determined is the pulse wave transmission time of the preset area. The preset area starts at a first preset position, that is, the fingertip is the starting position, and ends at a second preset position. The second preset position can be the user's wrist or the proximal end of the finger. The preset area is a local area. Specifically, the second preset position can be the user's wrist. The target object has a wearable device on its wrist, such as a watch, which can collect photoelectric capacitance at the wrist. The signal can also be other parts, and the other parts are equipped with external electronic devices that can collect photoplethysmography signals, such as headphones, glasses, etc. that can collect photoplethysmography signals. In particular, the second preset position can be the proximal end of the user's finger. When the second preset position is the proximal end of the finger, the proximal end of the target object's finger is worn with a non-adjustable ring, that is, the target object wears two rings, an adjustable target ring-type device at the fingertip and a non-adjustable ring-type device at the proximal end of the finger, both of which are made of materials that are not easily deformed. The ring worn at the proximal end of the finger is a non-adjustable ring-type device, which can obtain a signal of at least one blood pulsation information and is located on the palm side.

[0096] like Figure 7a-7b As shown, it exemplarily shows a schematic diagram of the design of combining the target ring-shaped device of an embodiment of the present application with various external electronic devices, Figure 7a Shown is a schematic diagram of a combined design of a watch and an adjustable target ring-type device, wherein the watch is an external electronic device; Figure 7b The target ring-type device is shown as a schematic diagram of a design that is combined with various other external electronic devices.

[0097] Compared with smart bracelets worn on the wrist, there is still a certain distance from the body, the degree of closeness is not enough, it is easily affected by motion noise, and it is difficult to accurately detect the true situation of physiological signals. Therefore, the embodiment of the present application preferably has a dual-ring design, that is, an adjustable target ring-type device is worn on the distal end (fingertip) of the finger, and a non-adjustable ring-type device is worn on the proximal end of the finger.

[0098] like Figure 8a As shown, it exemplarily shows a schematic diagram of the wearing positions of two ring-type devices in a dual-ring design during the measurement process, wherein the adjustable target ring-type device is located at the distal end (fingertip) of the finger and the non-adjustable ring-type device is located at the proximal end of the finger.

[0099] like Figure 8b As shown, it exemplarily shows a schematic diagram of the wearing positions of two ring-type devices in the dual-ring design during the non-measurement process. The adjustable target ring-type device and the non-adjustable ring-type device are both located proximal to the finger, which will not affect the daily life of the target object.

[0100] When using an appropriately sized cuff held at heart height, the distal tip of the finger—the fingertip—is an excellent alternative location for oscillometric blood pressure measurement, providing comparable, if not identical, blood pressure readings to those obtained from the upper arm. This minimizes the required cuff size and provides the most consistent average blood pressure readings with those obtained from the upper arm. Furthermore, because the finger has readily accessible peripheral arterial vessels, it can also collect additional, precise data on vital body signals, further expanding the potential uses of finger-based health monitoring, such as blood oxygen levels, sleep monitoring, glucose levels, body composition analysis, and hematocrit levels.

[0101] In an embodiment of the present application, after a first pressure of a preset degree is applied to a first preset position via a target ring-shaped device, the arm is repeatedly held at different heights n times, or the arm is straightened, raised, and lowered n times at a constant speed, within a preset time period. Local PTT changes are calculated and obtained using a combination of the ring-shaped device and an external electronic device, or a dual ring device. The local PTT changes in a preset area are calculated and obtained using a combination of the ring-shaped device and an external electronic device, or a dual ring device, to determine the pulse wave transmission time of each pulse wave in the preset area at each moment.

[0102] Local pulse wave transmission time refers to the time difference between the peaks of two blood pulsation signals, such as two photoplethysmography signals, within the same heartbeat cycle. In embodiments of the present application, the two blood pulsation signals can come from the adjustable ring device and the proximal finger ring device in a dual-ring design, respectively; or one blood pulsation signal can come from the photoplethysmography signal of the ring device, while the other blood pulsation signal comes from another external electronic device such as a wearable blood pressure monitoring device, such as a watch, glasses, or headphones.

[0103] Step S202: for each preset time period, derive the curve composed of the pulse wave transmission times at each moment in the preset time period, and determine the moment when the derivative meets the first preset condition as the first moment; obtain the first pressure at each first moment, and obtain the second pressure based on the distribution of the first pressures at all first moments; obtain the first height difference of the first preset position relative to the heart position at the first moment, and obtain the first target height difference based on the distribution of all first height differences; determine the sample blood pressure information within the preset time period based on the second pressure and the first target height difference; the sample blood pressure information includes at least one of the sample average blood pressure, the sample systolic pressure, and the sample diastolic pressure.

[0104] For each preset time period, after determining the pulse wave transit time at each moment within the preset time period, the embodiment of the present application derivates the curve formed by each pulse wave transit time, and determines the moment when the derivative meets the first preset condition as the first moment. For the first-order derivative dPTT, the moment when dPTT is maximum within the preset time period can be determined as the first moment. At the first moment, the transmural pressure at the first preset position is zero. At this time, the blood pressure of the target subject can be regarded as the first pressure applied at the first preset position. However, because the target subject's arm is repeatedly staying at different heights or is repeatedly straightening, lifting, and lowering n times, the blood hydrostatic pressure (BHP) at the first preset position is also constantly changing during the repetitive movements. That is, the blood pressure of the target subject is affected by the BHP.

[0105] The first pressure is the pressure applied by the target ring-shaped device to the first preset position. The first pressure can be determined by obtaining a pressure signal from a pressure sensor in the target ring-shaped device. In the preset time period, there are multiple first moments. To reduce the error in measuring the first pressure, the second pressure can be obtained based on the distribution of the first pressures at all first moments. Specifically, the distribution of all first pressures P can be determined. Pi The mean P p is the second pressure, which is also expressed as P p Indicates that when the transmural pressure is zero, the second pressure is the pressure applied to the fingertip by the target ring device, which can be regarded as the mean blood pressure MBP of the target subject. h , which is the mean blood pressure MBP affected by blood static pressure h Therefore, it is necessary to correct the influence of blood static pressure on the measured average blood pressure to obtain a more accurate average blood pressure, so that the more accurate average blood pressure can be used as the sample average blood pressure in the subsequent process.

[0106] In order to reduce the influence of blood static pressure on the measurement, the embodiment of the present application needs to determine the first height difference Δh of the first preset position relative to the heart position at each first moment. pi The heart position can be the position of the heart center, and the first target height difference Δh is obtained according to the distribution of all first height differences. p Specifically, all the first height differences Δh pi The mean Δh pi As the first target height difference, the first target height difference is also expressed as Δh p .

[0107] In the embodiment of the present application, a gyroscope or an accelerometer may be used to detect changes in the target object's body position, thereby determining a first height difference between the first preset position and the heart position during the arm raising and lowering process.

[0108] After determining the second pressure and the first target height difference, the embodiment of the present application can correct the blood static pressure in the second pressure according to the first target height difference. The obtained blood pressure is the average blood pressure of the target object, and the blood pressure information is used as the sample average blood pressure for determining the calibration parameters in the blood pressure model. The sample average blood pressure is a type of sample blood pressure information. The sample blood pressure information measured in the embodiment of the present application also includes sample systolic pressure, sample diastolic pressure and sample pulse pressure. The detailed process of determining the sample systolic pressure, sample diastolic pressure and sample pulse pressure is shown in the subsequent part.

[0109] The sample blood pressure information in the embodiment of the present application is the blood pressure information required in the calibration stage of the blood pressure estimation model. The sample blood pressure information can also be referred to as calibration blood pressure. After determining the sample blood pressure information, the embodiment of the present application can input the sample blood pressure information and the sample physiological signal collected at the first moment into the initial blood pressure estimation model to determine the calibration parameters in the blood pressure estimation model.

[0110] Step S203 , based on the sample blood pressure information and sample physiological signals of multiple preset time periods, calibrate the pre-established initial blood pressure estimation model indicating the relationship between the blood pressure information and the physiological signals to obtain a target blood pressure estimation model.

[0111] The embodiment of the present application records various physiological signals of the target object at all times during the process of the arm repeatedly staying at different heights n times or the arm being straightened, raised and lowered at a constant speed n times, including but not limited to photoplethysmography signals, electrocardiogram signals, ultrasound signals, pressure signals, etc., and determines the physiological signal collected at the first moment as the sample physiological signal.

[0112] The blood pressure estimation model in the embodiment of the present application can be any model that can measure blood pressure. Sample blood pressure information of multiple preset time periods and corresponding sample physiological signals are input into an initial blood pressure estimation model containing at least one calibration parameter, and the values ​​corresponding to the calibration parameters in the initial blood pressure model are determined. After determining the values ​​corresponding to each calibration parameter, each calibration parameter in the initial blood pressure estimation model is replaced with the corresponding value to obtain a target blood pressure estimation model that indicates the relationship between the blood pressure information and the physiological signal.

[0113] The process of steps S201-S202 above represents the determination of sample blood pressure information by the pulse wave transit time of the preset area. If the pulse wave transit time is calculated by the single-wavelength photoplethysmography signal of the preset area obtained by the target ring-type device in combination with an external device to determine the sample blood pressure information, then the pulse wave transit time and the sample blood pressure information can be expressed by formula (1), which is:

[0114] BP=f(PTT) (1),

[0115] Among them, BP indicates the sample blood pressure information, PTT indicates the single-wavelength pulse wave transmission time of the preset area, and formula (1) represents the relationship between the sample blood pressure information and the pulse wave transmission time of the preset area. Of course, in addition to the form expressed by formula (1), other forms of formulas can also be used. In addition to determining the sample photoelectric volumetric signal by the pulse wave transmission time, other signals can also be introduced for estimation, such as the amplitude of the photoelectric volumetric signal and other characteristic parameters, which can improve the accuracy of blood pressure estimation to a certain extent.

[0116] Step S204 , obtaining a continuous target physiological signal of the target subject, inputting the continuous target physiological signal into a target blood pressure estimation model, and obtaining a plurality of beat-by-beat blood pressure information output by the target blood pressure estimation model; the target physiological signal includes a target photoplethysmography signal.

[0117] After determining the target blood pressure estimation model, the embodiment of the present application can directly obtain the continuous target physiological signal of the target object, input the continuous target physiological signal into the target blood pressure estimation model, and obtain multiple beat-by-beat blood pressure information output by the target blood pressure estimation model.

[0118] The target physiological signal is obtained by filtering the collected original physiological signal. The original physiological signal can be amplified and then filtered to remove noise interference to obtain the signal frequency band carrying physiological information. The analog signal is then converted into a digital signal through an analog-to-digital conversion unit. During the signal transmission process, since the physiological signal strength is still very weak, it is considered to use a high-frequency and high-energy carrier signal for signal modulation processing to achieve efficient and high-fidelity transmission over a specific distance.

[0119] At the same time, the target photoelectric volumetric signal collected by the sensor is combined with the calibrated beat-by-beat blood pressure information, and a cuff-free continuous arterial blood pressure map and related information are obtained through transfer function processing.

[0120] In the embodiment of the present application, in order to obtain continuous beat-by-beat blood pressure information, a blood pressure estimation model based on multi-wavelength pulse wave time difference (MWPPG TD) and the like can be expressed by formula (2), which is:

[0121] BP=f(MWPPG TD) (2),

[0122] Among them, BP indicates the sample blood pressure information, and MWPPG TD represents the multi-wavelength pulse wave time difference. Of course, in addition to the form expressed by formula (2), other forms of formulas can also be used. In addition to MWPPG TD, other parameter estimates can also be introduced.

[0123] Step S205 : determining a blood pressure map of the target subject based on the continuous target photoplethysmography signal and the beat-by-beat blood pressure information.

[0124] After obtaining continuous beat-by-beat blood pressure information and a target photoplethysmography signal, the embodiment of the present application determines a transfer function between a pre-established target photoplethysmography signal and the blood pressure information, inputs the beat-by-beat blood pressure information and the continuous photoplethysmography signal into the transfer function, and obtains a blood pressure graph output by the transfer function. The detailed process is described in the subsequent section.

[0125] The embodiment of the present application determines the pulse wave transmission time of each pulse wave at each moment in a preset area of ​​a preset part of a target object during a preset action within multiple preset time periods in response to applying a first pressure of a preset degree to a first preset position; the preset area is an area starting from the first preset position; for each preset time period, a curve composed of the pulse wave transmission times at each moment in the preset time period is derived, and the moment when the derivative meets the first preset condition is determined as the first moment; for each first moment, a first pressure at the first moment and a first height difference of the first preset position relative to the heart position at the first moment are obtained; a second pressure is obtained based on the distribution of the first pressures at all first moments; and a second pressure is obtained based on the first pressures at the first moments. The second pressure and the first height difference determine the sample blood pressure information within a preset time period; the sample blood pressure information includes at least one of the sample average blood pressure, the sample systolic pressure and the sample diastolic pressure; based on the sample blood pressure information and the sample physiological signals of multiple preset time periods, the initial blood pressure estimation model that is pre-established and indicates the relationship between the blood pressure information and the physiological signal is calibrated to obtain a target blood pressure estimation model; the continuous target physiological signal of the target object is obtained, the continuous target physiological signal is input into the target blood pressure estimation model, and a plurality of beat-by-beat blood pressure information output by the target blood pressure estimation model is obtained; the target physiological signal includes a target photoplethysmography signal; the blood pressure map of the target object is determined based on the continuous target photoplethysmography signal and the beat-by-beat blood pressure information. The embodiment of the present application can calibrate the initial blood pressure estimation model through the sample blood pressure information at the first preset position to obtain the target blood pressure estimation model, and the initial blood pressure estimation model can be calibrated without the aid of the sample blood pressure information measured by an additional cuff-type blood pressure measurement device. The entire calibration process does not require manual intervention, is automatic and concise, and a high-precision arterial blood pressure map can be obtained through the target blood pressure model.

[0126] An embodiment of the present application provides a possible implementation method for determining sample blood pressure information within a preset time period based on the second pressure and the first target height difference, further comprising:

[0127] Determine the sample photoplethysmography signal at the first preset position, and determine each time when the oscillation amplitude of the pulse wave is the maximum value as the second time;

[0128] Obtaining the first pressure at each second moment, and obtaining the third pressure according to the distribution of the first pressures at all second moments;

[0129] Obtaining a second height difference between the first preset position and the heart position at a second moment, and obtaining a second target height difference based on a distribution of all the second height differences;

[0130] determining an average of the second pressure and the third pressure as a fourth pressure; and taking an average of the first target height difference and the second target height difference as a third target height difference;

[0131] The sample blood pressure information within a preset time period is determined according to the fourth pressure and the third target height difference.

[0132] In addition to determining the sample blood pressure information through the pulse wave transit time PTT alone, the embodiment of the present application can also combine the pulse wave transit time PTT with the photoplethysmography signal to measure the sample blood pressure information.

[0133] Based on the foregoing embodiment, a sample photoplethysmography signal at a first preset position is obtained through a target ring-type device, and the oscillation wave of the pulse wave is determined through the sample photoplethysmography signal. The moments when the oscillation amplitude is maximum are determined as second moments. At each second moment, the transmural pressure at the first preset position is zero.

[0134] In the embodiment of the present application, after determining each second moment, the first pressure P at each second moment is determined by the pressure signal collected at each second moment. ai , the first pressure P at each second moment ai The mean P a As the third pressure, the third pressure is expressed as P a .

[0135] The embodiment of the present application further needs to determine a second height difference Δh between the first preset position and the heart position at each second moment. ai , each second height difference Δh ai The mean Δh a As the second target height difference, that is, the second target height difference is expressed as Δh a .

[0136] In this embodiment of the present application, when determining the first target height difference Δh p and the second target height difference Δh a Then, the first target height difference Δh p and the second target height difference Δh a The mean of is taken as the third height difference Δh, that is

[0137] In the embodiment of the present application, the second pressure P is determined p and the third pressure P a Then, the second pressure P p and the third pressure P aThe mean of is taken as the fourth pressure, and the fourth pressure is The fourth pressure is the pressure applied to the fingertip by the target ring device, which can be regarded as the mean blood pressure MBP of the target subject. h , which is also affected by the mean blood pressure MBP h ,

[0138] After determining the fourth pressure and the third target height difference, the embodiment of the present application can correct the blood static pressure in the fourth pressure according to the third target height difference. The obtained blood pressure is the average blood pressure of the target object, and the average blood pressure is used as the sample average blood pressure for determining the calibration parameter in the blood pressure model. The sample average blood pressure is a type of sample blood pressure information. The sample blood pressure information measured in the embodiment of the present application also includes sample systolic pressure, sample diastolic pressure and sample pulse pressure. The detailed process of determining the sample systolic pressure, sample diastolic pressure and sample pulse pressure is shown in the subsequent part.

[0139] An embodiment of the present application provides a possible implementation method for determining a target subject's blood pressure map based on a continuous target photoplethysmography signal and beat-by-beat blood pressure information, including:

[0140] A transfer function between a pre-established target photoplethysmography signal and blood pressure information is determined, and the beat-by-beat blood pressure information and the continuous photoplethysmography signal are input into the transfer function to obtain a blood pressure graph output by the transfer function.

[0141] In an embodiment of the present application, a transfer function between a continuous target photoplethysmography signal and continuous beat-by-beat blood pressure information can be pre-established. After obtaining continuous beat-by-beat blood pressure information and a continuous photoplethysmography signal through a blood pressure estimation model, the beat-by-beat blood pressure information and the continuous photoplethysmography signal are input into the transfer function to obtain a blood pressure graph output by the transfer function.

[0142] like Figure 9 The figure shows a schematic diagram of obtaining a continuous blood pressure map provided by an embodiment of the present application, establishing a transfer function between continuous beat-by-beat blood pressure information and a photoplethysmography signal, obtaining an arterial blood pressure waveform by inputting the continuous beat-by-beat blood pressure information and a target photoplethysmography signal, and combining the beat-by-beat blood pressure information with the target photoplethysmography signal to obtain an arterial blood pressure map.

[0143] In an embodiment of the present application, a possible implementation method is provided for determining the blood pressure information of samples within each preset time period based on the second pressure and the first target height difference, including:

[0144] Acquiring a blood density of the target object, and determining a first blood static pressure at a first preset position according to the blood density and a first target height difference;

[0145] The blood pressure information of the samples in each preset time period is determined according to the second pressure and the first blood static pressure.

[0146] In the embodiment of the present application, the first target height difference Δh is obtained. p Then, we get BHP1=ρgΔh p Among them, BHP1 is the first blood static pressure, p is the blood density, and g is the gravity constant, that is, the first blood static pressure is ρgΔh p .

[0147] In the embodiment of the present application, after the second pressure is used as the first average blood pressure affected by the static blood pressure, the diastolic pressure and systolic pressure affected by the static blood pressure need to be determined. Specifically, the blood pressure at the first preset proportion of the rising edge of the derivative of the pulse wave transmission time is determined to be the diastolic pressure affected by the static blood pressure (referred to as the first diastolic pressure in the subsequent process), and the blood pressure at the second preset proportion of the falling edge of the derivative of the pulse wave transmission time is determined to be the systolic pressure affected by the static blood pressure (referred to as the first diastolic pressure in the subsequent process).

[0148] After determining the first average pressure, first diastolic pressure, and first systolic pressure affected by the blood static pressure, the embodiment of the present application determines the sample average pressure based on the average pressure and the first blood static pressure, determines the sample diastolic pressure based on the first diastolic pressure and the first blood static pressure, and determines the sample systolic pressure based on the first systolic pressure and the first blood static pressure.

[0149] In an embodiment of the present application, a possible implementation method is provided for determining the blood pressure information of samples within each preset time period based on the second pressure and the first blood static pressure, including:

[0150] The sum of the second pressure and the first blood static pressure is taken as the sample average blood pressure;

[0151] determining a blood pressure at a first preset ratio of the rising edge of the derivative as a first systolic pressure, and taking the sum of the first systolic pressure and the first blood static pressure as the sample systolic pressure;

[0152] The blood pressure at a second preset ratio of the falling edge of the derivative is determined as the first diastolic pressure, and the sum of the first diastolic pressure and the first blood static pressure is used as the sample diastolic pressure.

[0153] In the embodiment of the present application, the first blood static pressure is obtained as BHP1=ρgΔh p The sum of the second pressure and the first blood static pressure is taken as the sample mean blood pressure MBP, that is, MBP = MBP h +BHP1=MBP h +ρgΔh p , where MBP is the mean blood pressure of the sample, MBP h is the average blood pressure affected by the blood static pressure, BHP1 is the first blood static pressure, ρ is the blood density, g is the gravity constant, Δh p is the first target height difference.

[0154] In the embodiment of the present application, the blood pressure at the first preset ratio of the rising edge of dPTT is determined as the first systolic pressure SBP h , first systolic blood pressure SBP h It is the blood pressure affected by the static blood pressure. The systolic pressure obtained after correcting the influence of the static blood pressure is the sample systolic pressure SBP, SBP = SBP h +BHP1=SBP h +ρgΔh p , where SBP is the sample systolic blood pressure, SBP h is the systolic pressure affected by the blood static pressure, BHP1 is the first blood static pressure, ρ is the blood density, g is the gravity constant, Δh p is the first target height difference.

[0155] In the embodiment of the present application, the blood pressure at the second preset ratio of the falling edge of dPTT is determined as the first diastolic pressure DBP h , first diastolic pressure DBP h It is the blood pressure affected by the static blood pressure. The diastolic pressure obtained after correcting the influence of the static blood pressure is the sample diastolic pressure DBP. DBP = DBP h +BHP1==DBP h +ρgΔh p , where DBP is the sample diastolic pressure, DBP h is the diastolic pressure affected by the blood static pressure, BHP1 is the first blood static pressure, ρ is the blood density, g is the gravity constant, Δh p is the first target height difference.

[0156] In addition, the sample pulse pressure is the difference between the sample systolic pressure and the sample diastolic pressure.

[0157] In an embodiment of the present application, a possible implementation method is provided for determining sample blood pressure information within a preset time period based on the fourth pressure and the third target height difference, including:

[0158] obtaining a blood density of the target object, and determining a second blood static pressure at a first preset position according to the blood density and a third target height difference;

[0159] The blood pressure information of the samples within the preset time period is determined according to the fourth pressure and the second blood static pressure.

[0160] As in the above embodiment, after determining the third target height difference, and the blood density of the target subject, and calculate the second blood static pressure BHP,

[0161] In the embodiment of the present application, after the fourth pressure is used as the second average blood pressure affected by the blood pressure and static pressure, the diastolic pressure and systolic pressure affected by the blood pressure and static pressure need to be determined.

[0162] When the adjustable finger ring is designed as a small inflatable cuff, the fingertip is placed at the height of the heart, and the fingertip is pressurized to a pressure exceeding the human body's systolic pressure by a micro air pump and then the pressure is evenly released. After specific filtering processing, the pressure oscillation wave generated by the pulse pulsation is obtained, and its envelope is extracted. The blood pressure at the third preset ratio of the rising edge of the envelope is determined to be the diastolic pressure affected by the static blood pressure (the subsequent process is referred to as the second diastolic pressure), and the blood pressure at the fourth preset ratio of the falling edge of the envelope is determined to be the systolic pressure affected by the static blood pressure (the subsequent process is referred to as the second diastolic pressure).

[0163] After determining the second mean pressure, the second diastolic pressure, and the second systolic pressure, the embodiment of the present application determines the sample mean pressure based on the second mean pressure and the second blood static pressure, determines the sample diastolic pressure based on the second diastolic pressure and the second blood static pressure, and determines the sample systolic pressure based on the second systolic pressure and the second blood static pressure.

[0164] In an embodiment of the present application, a possible implementation method is provided for determining blood pressure information of samples within a preset time period based on the fourth pressure and the second blood static pressure, including:

[0165] The sum of the fourth pressure and the second static blood pressure is taken as the sample average blood pressure;

[0166] determining an envelope of an oscillation wave of the sample photoplethysmography signal at a first preset position, determining a blood pressure at a third preset ratio of a rising edge of the envelope as a second systolic pressure, and using the sum of the second systolic pressure and the second static blood pressure as the sample systolic pressure;

[0167] The blood pressure at a fourth preset ratio of the falling edge of the envelope is determined as the second diastolic pressure, and the sum of the second diastolic pressure and the second blood static pressure is used as the sample diastolic pressure.

[0168] In the embodiment of the present application, the second blood static pressure is obtained as The sum of the second pressure and the second blood static pressure is taken as the sample mean blood pressure MBP, that is, Among them, MBP is the mean blood pressure of the sample, MBP h is the average blood pressure affected by the blood static pressure, BHP2 is the second blood static pressure, ρ is the blood density, g is the gravity constant, Δh p is the first target height difference, Δh a is the second target height difference.

[0169] In the embodiment of the present application, the blood pressure at the third preset ratio of the rising edge of the envelope is determined as the second systolic pressure SBP h , second systolic blood pressure SBP h It is the blood pressure affected by the static blood pressure. The systolic pressure obtained after correcting the influence of the static blood pressure is the sample systolic pressure SBP. Among them, SBP is the sample systolic blood pressure, SBP h is the systolic pressure affected by the blood static pressure, BHP2 is the second blood static pressure, ρ is the blood density, g is the gravity constant, Δh p is the first target height difference, Δh a The height difference of the second target

[0170] In the embodiment of the present application, the blood pressure at the fourth preset ratio of the falling edge of the envelope is determined as the second diastolic pressure DBP h , second diastolic pressure DBP h It is the blood pressure affected by the static blood pressure. The diastolic pressure obtained after correcting the influence of the static blood pressure is the sample diastolic pressure DBP. Among them, DBP is the sample diastolic pressure, DBP h is the diastolic pressure affected by the blood static pressure, BHP2 is the second blood static pressure, ρ is the blood density, g is the gravity constant, Δh p is the first target height difference, Δh a The height difference of the second target

[0171] In an embodiment of the present application, a possible implementation method is provided, wherein a first pressure of a preset degree is applied to a first preset position, including:

[0172] At the first preset position, a first pressure of a preset degree is applied by adjusting the diameter or contact pressure of the target finger-ring device.

[0173] In the embodiment of the present application, the first preset position is the distal end of the target object's finger, that is, the fingertip. The fingertip is equipped with a wearable target ring-shaped device, and a first pressure of a preset degree can be applied to the first position by adjusting the diameter or contact pressure of the target ring-shaped device.

[0174] A possible implementation method is provided in an embodiment of the present application, where the target ring-type device is worn at a first preset position, which is the distal end of the finger; the preset area also includes a second preset position. If the second preset position is the proximal end of the finger, a non-adjustable ring-type device that can collect photoplethysmography signals is worn at the second preset position; if the second preset position is other than the proximal end of the finger, a corresponding external electronic device that can collect photoplethysmography signals is worn at the second preset position.

[0175] As introduced in the aforementioned embodiments, the preset areas of the present application include a first preset position and a second preset position, and the pulse wave transmission time at each moment can be determined by the photoelectric volumetric signals at the first preset position and the second preset position. A target finger-ring-type device is worn at the first preset position, and the target finger-ring-type device includes multiple sensors that can collect multiple physiological signals; the second preset position also includes a device that can collect photoelectric volumetric signals.

[0176] If the second preset position is the proximal end of the finger, a non-adjustable ring-type device that can collect photoplethysmography signals is worn at the second preset position. Both the first preset position and the second preset position are ring-type devices, that is, the dual-ring design provided in the embodiment of the present application. The blood pressure estimation model is calibrated through the dual-ring design and a continuous blood pressure graph is obtained.

[0177] The second preset position can also be other positions other than the proximal end of the finger. A corresponding external electronic device that can collect photoplethysmography signals is worn at the second preset position, such as a smart watch on the wrist (the wrist is the second preset position, and the smart watch is an external electronic device), smart glasses on the eyes (the eyes are the second preset position, and the smart glasses are external electronic devices), and smart headphones on the ears (the ears are the second preset position, and the smart headphones are external electronic devices). This is the design of the target ring-type device combined with the external electronic device provided in the embodiment of the present application. Through this design, the blood pressure estimation model can also be calibrated and a continuous blood pressure graph can be obtained.

[0178] Figure 10 FIG. 1 is a schematic diagram of obtaining calibrated blood pressure information and continuous blood pressure information under two designs provided in an embodiment of the present application. Figure 10 Part (a) shows that in the design of combining the target ring-type device with an external electronic device, the target ring-type device can determine the unknown constants in the blood pressure estimation model of other external electronic devices such as wearable blood pressure monitoring devices, such as watches, glasses, headphones, etc. through the wireless communication unit; or the blood pressure evaluation parameters such as local pulse transit time (PTT) are calculated by using the single photoelectric capacitance signal obtained by the ring-type device and the blood pulsation information obtained by the external electronic device, and a continuous blood pressure estimation model is established. The blood pressure value obtained by the ring-type device is used to calibrate the unknown constants in the blood pressure estimation model to obtain continuous beat-by-beat blood pressure information without a cuff; if it is a multi-wavelength photoelectric capacitance signal, blood pressure evaluation parameters such as multi-wavelength pulse wave time difference (MWPPG TD) are obtained, and the continuous beat-by-beat blood pressure information without a cuff is obtained according to its preset multi-wavelength continuous blood pressure estimation model.

[0179] In the double ring design, such as Figure 10As shown in part (b), the target ring-type device can calibrate other external electronic devices such as wearable blood pressure monitors through a wireless communication unit; or transmit the photoelectric volume accumulation signal and calibration blood pressure information obtained by the ring-type device to the proximal ring device of the finger over a long distance; obtain blood pressure assessment parameters such as local pulse wave transmission velocity through the dual ring device, establish a continuous blood pressure estimation model, and use the sample blood pressure information obtained by the adjustable target ring-type device for calibration to obtain continuous beat-by-beat blood pressure information without a cuff.

[0180] In an embodiment of the present application, a possible implementation method is provided, in which the filtering method of the sample photoplethysmography signal or the target photoplethysmography signal is as follows:

[0181] Acquire raw photoplethysmography signals of multiple channels;

[0182] For the original photoplethysmography signal of any channel, the target component in the photoplethysmography signal is extracted by integrating constrained independent component analysis, adaptive filtering, and the basis-free source number hypothesis method, and the target component is input into the adaptive filter to instruct the adaptive filter to restore the photoplethysmography signal according to the target component to obtain a sample photoplethysmography signal or a target photoplethysmography signal.

[0183] In the aforementioned embodiment, the embodiment of the present application completes the estimation model by acquiring sample photoplethysmography signals. After the blood pressure estimation model is established, continuous beat-by-beat blood pressure information is obtained by inputting continuous target photoplethysmography signals into the blood pressure estimation model.

[0184] The filtering method of the sample photoplethysmography signal or the target photoplethysmography signal mentioned above aims to reduce the motion artifact (MA) problem of multiple photoelectric signals, and applies a method of integrating constrained independent component analysis (cICA) and adaptive filter in the time domain.

[0185] Specifically, constrained independent component analysis is first used to extract the target component of the photoplethysmography signal based on its periodicity, but this results in the loss of amplitude information. An adaptive filtering algorithm is then used to recover this amplitude information, with the target component of the photoplethysmography signal serving as the reference input for the adaptive filter.

[0186] Unlike traditional independent component analysis (ICA) algorithms, constrained ICA makes no assumptions about the actual number of underlying signal sources. The algorithm can automatically extract specific signal sources without assuming the actual number of underlying signal sources. This means it can address the problem of MA signals being complex combinations of multiple signal sources. Therefore, using constrained ICA to automatically obtain components of interest has broad applicability. Furthermore, an adaptive filter is used to effectively reduce MA by restoring the amplitude information of the photoplethysmographic signal.

[0187] like Figure 11 Figure 1 illustrates a schematic diagram of noise reduction using constrained independent component analysis (cICA) and adaptive filtering: (a) The raw photoplethysmography signals from multiple channels are first processed by filters to remove high-frequency noise and DC components. (b) The signal from any channel is subjected to autocorrelation and other processing to obtain the period of the photoplethysmography signal. Based on the obtained period, a reference signal for constrained independent component analysis is generated. (c) The preprocessed photoplethysmography signals from multiple channels and the reference signal generated in step (b) are fed into the constrained independent component analysis algorithm to generate artifact-free photoplethysmography signal correlation components. (d) The artifact-free photoplethysmography signal correlation components are fed into an adaptive filter as reference input to restore the amplitude information of the photoplethysmography signals from multiple channels. The damaged photoplethysmography signals from multiple channels are used as the corresponding desired signals to obtain motion-restored photoplethysmography signals from multiple channels. Furthermore, the number of adaptive filtering algorithms is determined by the number of channels in the photoplethysmography signal, with a minimum of two sets.

[0188] An embodiment of the present application provides a possible implementation method, which includes, after determining a blood pressure map of a target subject based on continuous target photoplethysmography signals and beat-by-beat blood pressure information, further comprising:

[0189] The blood pressure graph is sent to an external display device to instruct the external display device to display the blood pressure graph.

[0190] After obtaining the blood pressure graph, the embodiment of the present application sends the blood pressure graph to an external display device. The external display device can be other external electronic devices outside the target ring-type device. The target ring-type device can interact with the external display device. The external display device includes but is not limited to cuffless wearable blood pressure monitoring devices, mobile phones, tablets, computers and other external electronic devices. It can also be uploaded to a cloud database and a telemedicine platform to continuously record and analyze blood pressure information to realize remote consultation and medical treatment.

[0191] When the embodiment of the present application determines that the blood pressure information is abnormal, an alarm call for help can be issued, and an alarm message can be sent to a local rescue center or an emergency contact to call for help.

[0192] The embodiment of the present application provides a calibration device for determining a blood pressure estimation model of a blood pressure diagram, such as Figure 12 As shown, the apparatus 1200 may include:

[0193] The pulse wave transit time determination module 1210 is configured to determine the pulse wave transit time of each pulse wave at each moment in a preset region of a preset portion of the target object during a preset motion within a plurality of preset time periods in response to a first pressure of a preset degree being applied to a first preset location; the preset region being a region starting from the first preset location;

[0194] The sample blood pressure information determination module 1220 is configured to, for each preset time period, derive a curve formed by pulse wave transmission times at each moment within the preset time period, and determine a moment at which the derivative meets a first preset condition as a first moment; obtain a first pressure at each first moment, and obtain a second pressure based on a distribution of the first pressures at all first moments; obtain a first height difference between a first preset position and a heart position at the first moment, and obtain a first target height difference based on a distribution of all first height differences; and determine sample blood pressure information within the preset time period based on the second pressure and the first target height difference; the sample blood pressure information including at least one of a sample mean blood pressure, a sample systolic pressure, and a sample diastolic pressure.

[0195] A blood pressure estimation model obtaining module 1230 is configured to calibrate a pre-established initial blood pressure estimation model indicating the relationship between the blood pressure information and the physiological signals based on the sample blood pressure information and the sample physiological signals for a plurality of preset time periods, thereby obtaining a target blood pressure estimation model;

[0196] A beat-by-beat blood pressure information acquisition module 1240 is configured to acquire a continuous target physiological signal at a first preset location of the target subject, input the continuous target physiological signal into a pre-established target blood pressure estimation model, and obtain a plurality of beat-by-beat blood pressure information output by the target blood pressure estimation model; the target physiological signal includes a target photoplethysmography signal;

[0197] The blood pressure map determining module 1250 is configured to determine the blood pressure map of the target subject based on the continuous target photoplethysmography signal and the beat-by-beat blood pressure information.

[0198] The embodiment of the present application determines the pulse wave transmission time of each pulse wave at each moment in a preset area of ​​a preset part of a target object during a preset action within multiple preset time periods in response to applying a first pressure of a preset degree to a first preset position; the preset area is an area starting from the first preset position; for each preset time period, a curve composed of the pulse wave transmission times at each moment in the preset time period is derived, and the moment when the derivative meets the first preset condition is determined as the first moment; for each first moment, a first pressure at the first moment and a first height difference of the first preset position relative to the heart position at the first moment are obtained; a second pressure is obtained based on the distribution of the first pressures at all first moments; and a second pressure is obtained based on the first pressures at the first moments. The second pressure and the first height difference determine the sample blood pressure information within a preset time period; the sample blood pressure information includes at least one of the sample average blood pressure, the sample systolic pressure and the sample diastolic pressure; based on the sample blood pressure information and the sample physiological signals of multiple preset time periods, the initial blood pressure estimation model that is pre-established and indicates the relationship between the blood pressure information and the physiological signal is calibrated to obtain a target blood pressure estimation model; the continuous target physiological signal of the target object is obtained, the continuous target physiological signal is input into the target blood pressure estimation model, and a plurality of beat-by-beat blood pressure information output by the target blood pressure estimation model is obtained; the target physiological signal includes a target photoplethysmography signal; the blood pressure map of the target object is determined based on the continuous target photoplethysmography signal and the beat-by-beat blood pressure information. The embodiment of the present application can calibrate the initial blood pressure estimation model through the sample blood pressure information at the first preset position to obtain the target blood pressure estimation model, and the initial blood pressure estimation model can be calibrated without the aid of the sample blood pressure information measured by an additional cuff-type blood pressure measurement device. The entire calibration process does not require manual intervention, is automatic and concise, and a high-precision arterial blood pressure map can be obtained through the target blood pressure model.

[0199] A possible implementation method is provided in an embodiment of the present application. The sample blood pressure information determination module is also used to determine the sample photoelectric volume accumulation signal at the first preset position, and the moments when the oscillation amplitude of the pulse wave is the maximum value are determined as the second moments; obtain the first pressure at each second moment, and obtain the third pressure according to the distribution of the first pressure at all second moments; obtain the second height difference of the first preset position relative to the heart position at each second moment, and obtain the second target height difference according to the distribution of all second height differences; determine the average of the second pressure and the third pressure as the fourth pressure; use the average of the first target height difference and the second target height difference as the third target height difference; and determine the sample blood pressure information within the preset time period according to the fourth pressure and the third target height difference.

[0200] A possible implementation method is provided in an embodiment of the present application. The blood pressure map obtaining module includes:

[0201] The blood pressure map acquisition submodule is used to determine the transfer function between the pre-established target photoplethysmography signal and the blood pressure information, input the beat-by-beat blood pressure information and the continuous photoplethysmography signal into the transfer function, and obtain the blood pressure map output by the transfer function.

[0202] An embodiment of the present application provides a possible implementation method, in which the sample blood pressure information determination module includes:

[0203] a first blood static pressure determination submodule, configured to obtain a blood density of a target object and determine a first blood static pressure at a first preset position according to the blood density and a first target height difference;

[0204] The sample blood pressure information determination submodule is configured to determine the sample blood pressure information within each preset time period according to the second pressure and the first blood static pressure.

[0205] An embodiment of the present application provides a possible implementation method, in which the sample blood pressure information determination module further includes:

[0206] a sample average blood pressure determination submodule, configured to take the sum of the second pressure and the first blood static pressure as the sample average blood pressure;

[0207] a sample systolic pressure determination submodule, configured to determine the blood pressure at a first preset ratio of the rising edge of the derivative as a first systolic pressure, and to determine the sum of the first systolic pressure and the first blood static pressure as the sample systolic pressure;

[0208] The sample diastolic pressure determination submodule is configured to determine the blood pressure at a second preset ratio of the falling edge of the derivative as the first diastolic pressure, and to determine the sum of the first diastolic pressure and the first blood static pressure as the sample diastolic pressure.

[0209] An embodiment of the present application provides a possible implementation method, in which the sample blood pressure information determination module further includes:

[0210] a second blood static pressure determination submodule, configured to obtain a blood density of the target object and determine a second blood static pressure at the first preset position according to the blood density and a third target height difference;

[0211] The sample blood pressure information determination submodule is configured to determine the sample blood pressure information within a preset time period according to the fourth pressure and the second blood static pressure.

[0212] An embodiment of the present application provides a possible implementation method, in which the sample blood pressure information determination module further includes:

[0213] a sample average blood pressure determination submodule, configured to take the sum of the fourth pressure and the second blood pressure static pressure as the sample average blood pressure;

[0214] a sample systolic pressure determination submodule, configured to determine an envelope of an oscillation wave of a sample photoplethysmography signal at a first preset position, determine a blood pressure at a third preset ratio of a rising edge of the envelope as a second systolic pressure, and use the sum of the second systolic pressure and the second blood pressure static pressure as the sample systolic pressure;

[0215] The sample diastolic pressure determination submodule is configured to determine the blood pressure at a fourth preset ratio of the falling edge of the envelope as the second diastolic pressure, and take the sum of the second diastolic pressure and the second blood static pressure as the sample diastolic pressure.

[0216] In an embodiment of the present application, a possible implementation is provided, in which the pulse wave transit time determination module includes:

[0217] The first pressure applying submodule is configured to apply a first pressure of a preset degree at a first preset position by adjusting the diameter or contact pressure of the target ring-shaped device.

[0218] A possible implementation method is provided in an embodiment of the present application, where the target ring-type device is worn at a first preset position, which is the distal end of the finger; the preset area also includes a second preset position. If the second preset position is the proximal end of the finger, a non-adjustable ring-type device that can collect photoplethysmography signals is worn at the second preset position; if the second preset position is other than the proximal end of the finger, a corresponding external electronic device that can collect photoplethysmography signals is worn at the second preset position.

[0219] In an embodiment of the present application, a possible implementation method is provided, in which the filtering method of the sample photoplethysmography signal or the target photoplethysmography signal is as follows:

[0220] Acquire raw photoplethysmography signals of multiple channels;

[0221] For the original photoplethysmography signal of any channel, the target component in the photoplethysmography signal is extracted by integrating constrained independent component analysis, adaptive filtering, and the base source number hypothesis method, and the target component is input into the adaptive filter to instruct the adaptive filter to reply the photoplethysmography signal according to the target component to obtain a sample photoplethysmography signal or a target photoplethysmography signal.

[0222] A possible implementation method is provided in an embodiment of the present application, wherein the device further includes:

[0223] The display module is used to send the blood pressure graph to an external display device to instruct the external display device to display the blood pressure graph.

[0224] The device of the embodiment of the present application can execute the method provided by the embodiment of the present application, and its implementation principle is similar. The actions performed by each module in the device of each embodiment of the present application correspond to the steps in the method of each embodiment of the present application. For the detailed functional description of each module of the device, please refer to the description in the corresponding method shown in the previous text, and will not be repeated here.

[0225] In an embodiment of the present application, an electronic device is provided, comprising a memory, a processor, and a computer program stored in the memory, wherein the processor executes the computer program to implement the steps of a method for verifying a blood pressure estimation model. Compared with the related art, the following can be achieved: in response to applying a first pressure of a preset degree to a first preset position, the embodiment of the present application determines the pulse wave transmission time of each pulse wave at each moment in a preset area during a preset action at a preset part of a target object within multiple preset time periods; the preset area is an area with the first preset position as the starting position; for each preset time period, a curve composed of the pulse wave transmission time at each moment in the preset time period is derived, and the moment when the derivative meets the first preset condition is determined as the first moment; for each first moment, the first pressure at the first moment and the relative position of the first preset position at the first moment are obtained. A first height difference at the heart position; obtaining a second pressure based on the distribution of the first pressure at all first moments; determining sample blood pressure information within a preset time period based on the second pressure and the first height difference; the sample blood pressure information includes at least one of a sample average blood pressure, a sample systolic pressure, and a sample diastolic pressure; based on the sample blood pressure information and sample physiological signals of multiple preset time periods, calibrating a pre-established initial blood pressure estimation model that indicates the relationship between the blood pressure information and the physiological signal to obtain a target blood pressure estimation model; obtaining a continuous target physiological signal of the target object, inputting the continuous target physiological signal into the target blood pressure estimation model to obtain a plurality of beat-by-beat blood pressure information output by the target blood pressure estimation model; the target physiological signal includes a target photoplethysmography signal; determining the blood pressure map of the target object based on the continuous target photoplethysmography signal and the beat-by-beat blood pressure information. In the embodiment of the present application, the initial blood pressure estimation model can be calibrated to obtain the target blood pressure estimation model through the sample blood pressure information at the first preset position, and the initial blood pressure estimation model can be calibrated without the aid of sample blood pressure information measured by an additional cuff-type blood pressure measurement device. The entire calibration process does not require manual intervention, is automatic and concise, and a high-precision arterial blood pressure map can be obtained through the target blood pressure model.

[0226] In an alternative embodiment, an electronic device is provided, such as Figure 13 As shown, Figure 13The electronic device 4000 shown includes: a processor 4001 and a memory 4003. The processor 4001 and the memory 4003 are connected, for example, via a bus 4002. Optionally, the electronic device 4000 may further include a transceiver 4004, which may be used for data exchange between the electronic device and other electronic devices, such as data transmission and / or data reception. It should be noted that in actual applications, the number of transceivers 4004 is not limited to one, and the structure of the electronic device 4000 does not constitute a limitation on the embodiments of the present application.

[0227] Processor 4001 may be a CPU (Central Processing Unit), a general-purpose processor, a DSP (Digital Signal Processor), an ASIC (Application Specific Integrated Circuit), an FPGA (Field Programmable Gate Array), or other programmable logic devices, transistor logic devices, hardware components, or any combination thereof. It may implement or execute the various exemplary logic blocks, modules, and circuits described in conjunction with the disclosure of this application. Processor 4001 may also be a combination that implements computing functions, such as a combination of one or more microprocessors, a combination of a DSP and a microprocessor, and the like.

[0228] Bus 4002 may include a path for transmitting information between the above components. Bus 4002 may be a PCI (Peripheral Component Interconnect) bus or an EISA (Extended Industry Standard Architecture) bus. Bus 4002 may be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 13 Only one thick line is used in the diagram, but this does not mean that there is only one bus or one type of bus.

[0229] The memory 4003 can be a ROM (Read Only Memory) or other types of static storage devices that can store static information and instructions, a RAM (Random Access Memory) or other types of dynamic storage devices that can store information and instructions, or an EEPROM (Electrically Erasable Programmable Read Only Memory), a CD-ROM (Compact Disc Read Only Memory) or other optical disk storage, optical disk storage (including compact discs, laser discs, optical discs, digital versatile discs, Blu-ray discs, etc.), magnetic disk storage media, other magnetic storage devices, or any other medium that can be used to carry or store computer programs and can be read by a computer, without limitation here.

[0230] The memory 4003 is used to store the computer program for executing the embodiment of the present application, and the execution is controlled by the processor 4001. The processor 4001 is used to execute the computer program stored in the memory 4003 to implement the steps shown in the above method embodiment.

[0231] Among them, the electronic equipment package may include but is not limited to mobile terminals such as mobile phones, laptops, digital broadcast receivers, PDAs (personal digital assistants), PADs (tablet computers), PMPs (portable multimedia players), vehicle-mounted terminals (such as vehicle-mounted navigation terminals), etc., as well as fixed terminals such as digital TVs, desktop computers, etc. Figure 13 The electronic device shown is only an example and should not limit the functions and scope of use of the embodiments of the present disclosure.

[0232] The embodiment of the present application provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps and corresponding contents of the aforementioned method embodiment can be implemented. Compared with the prior art, the embodiment of the present application can be implemented as follows: In response to applying a first pressure of a preset degree to a first preset position, the pulse wave conduction time of each pulse wave at each moment in a preset area of ​​a preset part of a target object during a preset action within multiple preset time periods is determined; the preset area is an area with the first preset position as the starting position; for each preset time period, the curve composed of the pulse wave conduction time at each moment in the preset time period is derived, and the moment when the derivative meets the first preset condition is determined as the first moment; for each first moment, the first pressure at the first moment and the first height difference of the first preset position relative to the heart position at the first moment are obtained; according to the distribution of the first pressures at all first moments, the second pressure is obtained. force; determine the sample blood pressure information within a preset time period based on the second pressure and the first height difference; the sample blood pressure information includes at least one of the sample average blood pressure, the sample systolic pressure, and the sample diastolic pressure; based on the sample blood pressure information and sample physiological signals of multiple preset time periods, calibrate the pre-established initial blood pressure estimation model that indicates the relationship between the blood pressure information and the physiological signal to obtain a target blood pressure estimation model; obtain the continuous target physiological signal of the target object, input the continuous target physiological signal into the target blood pressure estimation model, and obtain multiple beat-by-beat blood pressure information output by the target blood pressure estimation model; the target physiological signal includes a target photoplethysmography signal; determine the blood pressure map of the target object based on the continuous target photoplethysmography signal and the beat-by-beat blood pressure information. The embodiment of the present application can calibrate the initial blood pressure estimation model through the sample blood pressure information at the first preset position to obtain the target blood pressure estimation model, and the initial blood pressure estimation model can be calibrated without the help of sample blood pressure information measured by an additional cuff-type blood pressure measurement device. The entire calibration process does not require manual intervention, is automatic and concise, and a high-precision arterial blood pressure map can be obtained through the target blood pressure model.

[0233] It should be noted that the computer-readable medium mentioned above in the present disclosure may be a computer-readable signal medium or a computer-readable medium, or any combination of the two. A computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or device, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present disclosure, a computer-readable storage medium may be any tangible medium that contains or stores a program that can be used by or in conjunction with an instruction execution system, device, or device. In the present disclosure, a computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, which carries computer-readable program code. Such a propagated data signal may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. A computer-readable signal medium may also be any computer-readable medium other than a computer-readable storage medium that can transmit, propagate, or transport a program for use by or in conjunction with an instruction execution system, apparatus, or device. The program code contained on the computer-readable medium may be transmitted using any suitable medium, including but not limited to wires, optical cables, RF (radio frequency), etc., or any suitable combination thereof.

[0234] The embodiment of the present application also provides a computer program product, including a computer program, which can implement the steps and corresponding contents of the aforementioned method embodiment when executed by a processor. Compared with the prior art, it can be achieved that: the embodiment of the present application determines the pulse wave conduction time of each pulse wave at each moment in a preset area of ​​a preset part of a target object during a preset action within multiple preset time periods in response to applying a first pressure of a preset degree to a first preset position; the preset area is an area with the first preset position as the starting position; for each preset time period, the curve composed of the pulse wave conduction time at each moment in the preset time period is derived, and the moment when the derivative meets the first preset condition is determined as the first moment; for each first moment, the first pressure at the first moment and the first height difference of the first preset position relative to the heart position at the first moment are obtained; according to the distribution of the first pressures at all first moments, the second pressure is obtained. force; determine the sample blood pressure information within a preset time period based on the second pressure and the first height difference; the sample blood pressure information includes at least one of the sample average blood pressure, the sample systolic pressure, and the sample diastolic pressure; based on the sample blood pressure information and sample physiological signals of multiple preset time periods, calibrate the pre-established initial blood pressure estimation model that indicates the relationship between the blood pressure information and the physiological signal to obtain a target blood pressure estimation model; obtain the continuous target physiological signal of the target object, input the continuous target physiological signal into the target blood pressure estimation model, and obtain multiple beat-by-beat blood pressure information output by the target blood pressure estimation model; the target physiological signal includes a target photoplethysmography signal; determine the blood pressure map of the target object based on the continuous target photoplethysmography signal and the beat-by-beat blood pressure information. The embodiment of the present application can calibrate the initial blood pressure estimation model through the sample blood pressure information at the first preset position to obtain the target blood pressure estimation model, and the initial blood pressure estimation model can be calibrated without the help of sample blood pressure information measured by an additional cuff-type blood pressure measurement device. The entire calibration process does not require manual intervention, is automatic and concise, and a high-precision arterial blood pressure map can be obtained through the target blood pressure model.

[0235] The terms "first," "second," "third," "fourth," "1," "2," and the like (if any) in the specification and claims of this application and the accompanying drawings are used to distinguish similar objects and are not necessarily used to describe a particular order or sequential sequence. It should be understood that the terms used in this manner are interchangeable where appropriate, so that the embodiments of the application described herein can be implemented in an order other than that shown or described in the drawings.

[0236] It should be understood that, although each operation step is indicated by arrows in the flowchart of the embodiment of the present application, the order of implementation of these steps is not limited to the order indicated by the arrows. Unless otherwise clearly stated herein, in some implementation scenarios of the embodiment of the present application, the implementation steps in each flowchart can be performed in other orders according to demand. In addition, some or all of the steps in each flowchart can include multiple sub-steps or multiple stages based on actual implementation scenarios. Some or all of these sub-steps or stages can be executed at the same time, and each sub-step or stage in these sub-steps or stages can also be executed at different times respectively. Under different scenarios at the execution time, the execution order of these sub-steps or stages can be flexibly configured according to demand, and the embodiment of the present application does not limit this.

[0237] The above are only optional implementation methods for some implementation scenarios of this application. It should be pointed out that for ordinary technicians in this technical field, without departing from the technical concept of the solution of this application, the use of other similar implementation methods based on the technical ideas of this application also falls within the protection scope of the embodiments of this application.

Claims

1. A method for calibrating a blood pressure estimation model for determining a blood pressure map, characterized in that include: In response to applying a first pressure of a predetermined degree to a first predetermined position, determining the pulse wave transmission time of each pulse wave in a predetermined region at each moment during a predetermined movement of the predetermined portion of the target object within a plurality of predetermined time periods; The preset area is an area starting from the first preset position; the first preset position is the distal end of the finger, and the first pressure is the pressure applied by the target ring-shaped device to the first preset position; For each preset time period, a curve composed of pulse wave transmission times at each moment in the preset time period is derived, and the moment when the first-order derivative is maximum is determined as the first moment; a first pressure at each first moment is obtained, and the average of the first pressures at all first moments is used as the second pressure; a first height difference of the first preset position relative to the heart position at the first moment is obtained, and a first target height difference is obtained based on the distribution of all first height differences; sample blood pressure information for the preset time period is determined based on the second pressure and the first target height difference; the sample blood pressure information includes at least one of sample average blood pressure, sample systolic pressure, and sample diastolic pressure; Based on the sample blood pressure information and the sample physiological signals of the plurality of preset time periods, calibrating a pre-established initial blood pressure estimation model indicating the relationship between the blood pressure information and the physiological signals to obtain a target blood pressure estimation model; Acquiring a continuous target physiological signal from a target subject, inputting the continuous target physiological signal into the target blood pressure estimation model, and obtaining a plurality of beat-by-beat blood pressure information output by the target blood pressure estimation model; the target physiological signal including a target photoplethysmography signal; determining a blood pressure map of the target subject based on the continuous target photoplethysmography signal and the beat-by-beat blood pressure information; Determining the sample blood pressure information within each of the preset time periods according to the second pressure and the first target height difference includes: obtaining a blood density of the target object, and determining a first blood static pressure at the first preset position according to the blood density and the first target height difference; Determining the blood pressure information of the samples within each of the preset time periods according to the second pressure and the first blood static pressure includes: taking the sum of the second pressure and the first blood static pressure as the sample average blood pressure; determining a blood pressure at a first preset proportion of a rising edge of the first-order derivative as a first systolic pressure, and taking a sum of the first systolic pressure and the first blood static pressure as a sample systolic pressure; The blood pressure at a second preset ratio of the falling edge of the first-order derivative is determined as a first diastolic pressure, and the sum of the first diastolic pressure and the first blood static pressure is used as a sample diastolic pressure.

2. The method according to claim 1, characterized in that The determining of the sample blood pressure information within the preset time period according to the second pressure and the first target height difference further includes: Determining each moment at which the oscillation amplitude of the pulse wave is maximum by the sample photoplethysmography signal at the first preset position as a second moment; Obtaining the first pressure at each of the second moments, and obtaining the third pressure according to the distribution of the first pressures at all the second moments; Acquire a second height difference between the first preset position and the heart position at each of the second moments, and obtain a second target height difference based on the distribution of all the second height differences; determining an average of the second pressure and the third pressure as a fourth pressure; and taking an average of the first target height difference and the second target height difference as a third target height difference; The sample blood pressure information within the preset time period is determined according to the fourth pressure and the third target height difference.

3. The method according to claim 1, characterized in that Determining the blood pressure map of the target subject based on the continuous target photoplethysmography signal and the beat-by-beat blood pressure information includes: A transfer function between the pre-established target photoplethysmography signal and the blood pressure information is determined, and the beat-by-beat blood pressure information and the continuous photoplethysmography signal are input into the transfer function to obtain a blood pressure graph output by the transfer function.

4. The method according to claim 2, characterized in that The determining of the sample blood pressure information within the preset time period according to the fourth pressure and the third target height difference includes: obtaining a blood density of the target object, and determining a second blood static pressure at the first preset position according to the blood density and the third target height difference; The sample blood pressure information within the preset time period is determined according to the fourth pressure and the second blood static pressure.

5. The method according to claim 4, characterized in that The determining of the sample blood pressure information within the preset time period according to the fourth pressure and the second blood static pressure includes: taking the sum of the fourth pressure and the second blood static pressure as the sample average blood pressure; determining an envelope of an oscillation wave of the sample photoplethysmography signal at the first preset position, determining a blood pressure at a third preset ratio of a rising edge of the envelope as a second systolic pressure, and using the sum of the second systolic pressure and the second blood static pressure as the sample systolic pressure; The blood pressure at a fourth preset ratio of the falling edge of the envelope is determined as the second diastolic pressure, and the sum of the second diastolic pressure and the second blood static pressure is used as the sample diastolic pressure.

6. The method according to claim 1, characterized in that The applying a first pressure of a preset degree to the first preset position includes: At the first preset position, a first pressure of a preset degree is applied by adjusting the diameter or contact pressure of the target finger-ring device.

7. The method according to claim 1, characterized in that The target ring-shaped device is worn at the first preset position; the preset area also includes a second preset position, and if the second preset position is the proximal end of the finger, the second preset position A non-adjustable ring-shaped device capable of collecting photoplethysmography signals is worn at the patient's location; If the second preset position is a position other than the proximal end of the finger, a corresponding external electronic device capable of collecting photoplethysmography signals is worn at the second preset position.

8. The method according to claim 2, characterized in that The filtering method of the sample photoplethysmography signal or the target photoplethysmography signal is as follows: Acquire raw photoplethysmography signals of multiple channels; For the original photoplethysmography signal of any channel, the target component in the photoplethysmography signal is extracted by integrating constrained independent component analysis, adaptive filtering, and base-free source number hypothesis method, and the target component is input into the adaptive filter to instruct the adaptive filter to reply the photoplethysmography signal according to the target component to obtain a sample photoplethysmography signal or a target photoplethysmography signal.

9. The method according to claim 1, characterized in that After determining the blood pressure map of the target subject based on the continuous target photoplethysmography signal and the beat-by-beat blood pressure information, The method includes sending the blood pressure graph to an external display device to instruct the external display device to display the blood pressure graph.

10. A calibration device for a blood pressure estimation model for determining a blood pressure diagram, characterized in that include: a pulse wave transit time determination module, configured to determine the pulse wave transit time of each pulse wave at each moment in a preset region of a preset portion of the target object during a preset movement within a plurality of preset time periods in response to applying a first pressure of a preset degree to a first preset location; The preset area is an area starting from the first preset position; the first preset position is the distal end of the finger, and the first pressure is the pressure applied by the target ring-shaped device to the first preset position; a sample blood pressure information determination module configured to, for each preset time period, derive a curve formed by pulse wave transmission times at each moment within the preset time period, determine the moment at which the first-order derivative is maximum as a first moment; obtain a first pressure at each first moment, and take the average of the first pressures at all first moments as a second pressure; obtain a first height difference of the first preset position relative to the heart position at the first moment, and obtain a first target height difference based on the distribution of all first height differences; determine sample blood pressure information within the preset time period based on the second pressure and the first target height difference; the sample blood pressure information comprising at least one of a sample mean blood pressure, a sample systolic pressure, and a sample diastolic pressure; a blood pressure estimation model acquisition module, configured to calibrate a pre-established initial blood pressure estimation model indicating the relationship between the blood pressure information and the physiological signals based on the sample blood pressure information and the sample physiological signals of the plurality of preset time periods, to obtain a target blood pressure estimation model; a beat-by-beat blood pressure information determination module, configured to obtain a continuous target physiological signal at a first preset location of a target subject, input the continuous target physiological signal into a pre-established target blood pressure estimation model, and obtain a plurality of beat-by-beat blood pressure information output by the target blood pressure estimation model; the target physiological signal includes a target photoplethysmography signal; a blood pressure map determining module, configured to determine a blood pressure map of the target subject based on the continuous target photoplethysmography signal and the beat-by-beat blood pressure information; Determining the sample blood pressure information within each of the preset time periods according to the second pressure and the first target height difference includes: obtaining a blood density of the target object, and determining a first blood static pressure at the first preset position according to the blood density and the first target height difference; Determining the blood pressure information of the samples within each of the preset time periods according to the second pressure and the first blood static pressure includes: taking the sum of the second pressure and the first blood static pressure as the sample average blood pressure; determining a blood pressure at a first preset proportion of a rising edge of the first-order derivative as a first systolic pressure, and taking a sum of the first systolic pressure and the first blood static pressure as a sample systolic pressure; The blood pressure at a second preset ratio of the falling edge of the first-order derivative is determined as a first diastolic pressure, and the sum of the first diastolic pressure and the first blood static pressure is used as a sample diastolic pressure.

11. An electronic device comprising a memory, a processor, and a computer program stored in the memory, characterized in that: The processor executes the computer program to implement the steps of the method according to any one of claims 1 to 9.

12. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 9 are implemented.

Images