Anti-interference non-contact blood pressure detection method, device, equipment and storage medium
Through millimeter wave radar and thermal image processing technology, combined with pre-trained models, contactless and anti-interference blood pressure detection is achieved, solving the problems of time-consuming and unfavorable contact of traditional methods, and improving the accuracy and efficiency of detection.
Patent Information
- Application Number
- CN202410414943.2
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2024-04-08
- Publication Date
- 2024-11-12
- Estimated Expiration
- 2044-04-08
AI Technical Summary
Traditional inflatable blood pressure measurement methods require contact with users, which is time-consuming and unfavorable to health, and it is difficult to efficiently perform blood pressure testing in places with high traffic.
The area under test of the back of the hand was scanned by millimeter wave radar, combined with thermal image processing and pre-trained anti-interference blood pressure detection model, blood flow velocity and temperature characteristics were obtained through contactless mode and blood pressure detection was performed.
It realizes contactless and anti-interference blood pressure detection, improves the accuracy and efficiency of the detection, and is suitable for places with large flow of people.
Smart Images

Figure CN118177761B_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the field of artificial intelligence technology, and in particular to an interference-resistant contactless blood pressure detection method, device, equipment and computer-readable storage medium. Background Art
[0002] In the medical field, measuring blood pressure is an essential physical indicator. However, in large-scale medical settings, such as when there is a large flow of people, such as during vaccinations, the traditional method of measuring blood pressure with air is not only time-consuming, but also requires physical contact with the user, which can easily cause indirect contact with the user and is not conducive to the user's health. Summary of the invention
[0003] The present invention provides an interference-resistant non-contact blood pressure detection method, device, equipment and storage medium, the main purpose of which is to perform non-contact blood pressure detection on a user, improve the anti-interference ability during detection, and improve the accuracy of blood pressure detection.
[0004] To achieve the above object, the present invention provides an interference-resistant non-contact blood pressure detection method, comprising:
[0005] The millimeter wave radar is used to scan the measured area on the back of the hand to obtain the primary blood flow velocity curve and the back of the hand scanning image sequence;
[0006] Performing an edge detection operation based on the blood vessel range on the hand back scan image sequence to obtain a blood vessel display range, and performing a supervision operation based on width shrinkage and expansion and position movement on the blood vessel display range to obtain a position coordinate sequence and a blood vessel shrinkage and expansion sequence;
[0007] Acquire a thermal image sequence of the measured area on the back of the hand, identify the air temperature and the back of the hand temperature, and adjust the resolution of the thermal image sequence according to a preset self-appropriate resolution strategy, the air temperature and the back of the hand temperature to obtain a back of the hand temperature dissipation image sequence;
[0008] Using a pre-trained anti-interference blood pressure detection model, a velocity repair operation is performed on the primary blood flow velocity curve according to the position coordinate sequence to obtain a blood flow velocity curve;
[0009] Performing feature extraction on the hand back temperature dissipation image sequence and the blood vessel contraction and expansion sequence to obtain a blood vessel contraction and expansion feature set, and performing feature extraction on the blood flow velocity curve to obtain a blood flow velocity change feature set;
[0010] Fully connected blood pressure prediction is performed on the blood vessel contraction and expansion feature set and the blood flow velocity change feature set to obtain a blood pressure detection value.
[0011] Optionally, performing a velocity repair operation on the primary blood flow velocity curve according to the position coordinate sequence to obtain the blood flow velocity curve includes:
[0012] Calculating the blood vessel position movement vector in adjacent unit time according to the position coordinate sequence;
[0013] Calculating the acceleration change sequence of the primary blood flow velocity curve, and performing a product operation on the acceleration change sequence according to the blood vessel position movement vector to obtain a repaired blood flow velocity acceleration sequence;
[0014] According to the repaired blood flow velocity acceleration sequence, acceleration calculation is performed on the initial velocity of the primary blood flow velocity curve to obtain a blood flow velocity curve.
[0015] Optionally, the step of adjusting the resolution of the thermal image sequence according to a preset self-appropriate resolution strategy, the air temperature and the hand back temperature to obtain the hand back temperature dissipation image sequence includes:
[0016] Automatically adjusting the resolution of the thermal image sequence according to the adaptive resolution strategy, and using an edge detection algorithm to monitor the thermal image sequence in real time;
[0017] Identifying and judging whether a preset thermal stratification feature appears in the thermal image sequence according to the air temperature and the back of the hand temperature;
[0018] When a preset thermal stratification feature appears in the thermal image sequence, the contrast of the image parts of the skin layer, the skin adjacent layer and the air layer in the thermal image sequence is adjusted according to the preset contrast configuration to obtain a hand back temperature dissipation image sequence.
[0019] Optionally, the method of scanning the measured area on the back of the hand using a millimeter wave radar to obtain a primary blood flow velocity curve includes:
[0020] generating an initial millimeter wave signal using a radar transmitter of a millimeter wave radar;
[0021] Using a signal receiver to receive a signal after the initial millimeter wave signal penetrates the measured area on the back of the hand, to obtain a reflected signal;
[0022] The primary blood flow velocity curve is calculated based on the initial millimeter wave signal and the reflected signal using a Doppler frequency shift algorithm.
[0023] Optionally, before using the pre-trained anti-interference blood pressure detection model, the method further includes:
[0024] Obtain a pre-built anti-interference blood pressure detection model and a pre-built blood pressure measurement sample of a population;
[0025] Extracting a target sample from the blood pressure measured samples of the population in turn, and performing network forward calculation on the target sample using the anti-interference blood pressure detection model to obtain a predicted blood pressure value;
[0026] Using a cross entropy loss algorithm, a cross entropy calculation is performed on the true blood pressure label value of the target sample and the predicted blood pressure value to obtain a loss value;
[0027] Minimizing the loss value to obtain the network model parameters when the loss value is the smallest, and performing a network reverse update operation on the network model parameters to obtain an updated anti-interference blood pressure detection model;
[0028] Determine whether the loss value is less than a preset qualified threshold;
[0029] When the loss value is greater than or equal to the qualified threshold, returning to the above operation step of sequentially extracting a target sample from the blood pressure measured samples of the population, and iteratively optimizing the updated anti-interference blood pressure detection model;
[0030] When the loss value is less than the qualified threshold, the training process is stopped to obtain a trained anti-interference blood pressure detection model.
[0031] Optionally, the performing a supervision operation based on width shrinkage and expansion and position movement on the blood vessel display range to obtain a position coordinate sequence and a blood vessel shrinkage and expansion sequence includes:
[0032] Recording the maximum width and the minimum width of the blood vessel display range each time to obtain a blood vessel contraction and expansion sequence;
[0033] A marker search is performed on the blood vessel display range to obtain a target blood vessel region, and coordinate mapping is performed on the target blood vessel region to obtain a position coordinate sequence.
[0034] Optionally, the extracting features of the hand back temperature dissipation image sequence and the blood vessel contraction and expansion sequence to obtain a blood vessel contraction and expansion feature set includes:
[0035] Performing a convolution operation on the hand back temperature dissipation image sequence to obtain a convolution matrix set;
[0036] Performing average pooling and flattening operations on the convolution matrix set to obtain a reduced-dimensional vascular contraction and expansion feature set;
[0037] A quantization operation is performed on the vascular contraction and expansion sequence, and a feature splicing operation based on corresponding ordinals is performed on the quantization result and the reduced-dimensional vascular contraction and expansion feature set to obtain a vascular contraction and expansion feature set.
[0038] In order to solve the above problems, the present invention further provides an anti-interference non-contact blood pressure detection device, the device comprising:
[0039] A millimeter wave scanning module is used to scan the measured area of the back of the hand using a millimeter wave radar to obtain a primary blood flow velocity curve and a back of the hand scanning image sequence;
[0040] A data extraction module is used to perform an edge detection operation based on the blood vessel range on the hand back scan image sequence to obtain a blood vessel display range, and perform a supervision operation based on width expansion and position movement on the blood vessel display range to obtain a position coordinate sequence and a blood vessel expansion and contraction sequence;
[0041] The temperature dissipation image acquisition module is used to acquire the thermal image sequence of the measured area of the back of the hand, identify the air temperature and the back of the hand temperature, and adjust the resolution of the thermal image sequence according to the preset self-appropriate resolution strategy, the air temperature and the back of the hand temperature to obtain the back of the hand temperature dissipation image sequence;
[0042] The model blood pressure prediction module is used to use the pre-trained anti-interference blood pressure detection model to perform a velocity repair operation on the primary blood flow velocity curve according to the position coordinate sequence to obtain a blood flow velocity curve, and to perform feature extraction on the back of the hand temperature dissipation image sequence and the blood vessel contraction and expansion sequence to obtain a blood vessel contraction and expansion feature set, and to perform feature extraction on the blood flow velocity curve to obtain a blood flow velocity change feature set, and to perform full-connected blood pressure prediction on the blood vessel contraction and expansion feature set and the blood flow velocity change feature set to obtain a blood pressure detection value.
[0043] In order to solve the above problem, the present invention further provides an electronic device, the electronic device comprising:
[0044] at least one processor; and,
[0045] a memory communicatively connected to the at least one processor; wherein,
[0046] The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can perform the above-mentioned anti-interference non-contact blood pressure detection method.
[0047] In order to solve the above problems, the present invention also provides a computer-readable storage medium, in which at least one computer program is stored. The at least one computer program is executed by a processor in an electronic device to implement the above-mentioned anti-interference contactless blood pressure detection method.
[0048] The embodiment of the present invention first locates the user's blood flow velocity and blood vessel position through millimeter wave radar to provide a basis for subsequent blood pressure measurement, and then provides blood temperature change characteristics for blood pressure detection through the hand back temperature dissipation image sequence with adaptive resolution; then the embodiment of the present invention uses the anti-interference blood pressure detection model to first perform anti-interference processing on the blood flow velocity according to the blood vessel position, and then extracts comprehensive features of the hand back temperature dissipation image sequence and the blood vessel contraction and expansion sequence and the blood flow velocity curve to achieve comprehensive features of temperature change, blood vessel contraction, and blood flow velocity, and then calculates a more accurate blood pressure detection value through the model. Therefore, the anti-interference non-contact blood pressure detection method, device, equipment and storage medium provided by the embodiment of the present invention can detect the user's blood pressure without contact, improve the anti-interference ability during detection, and improve the accuracy of blood pressure detection. BRIEF DESCRIPTION OF THE DRAWINGS
[0049] Figure 1 A schematic diagram of a flow chart of an anti-interference non-contact blood pressure detection method provided by an embodiment of the present invention;
[0050] Figure 2 A detailed flow chart of a step in the anti-interference non-contact blood pressure detection method provided by an embodiment of the present invention;
[0051] Figure 3 A detailed flow chart of a step in the anti-interference non-contact blood pressure detection method provided by an embodiment of the present invention;
[0052] Figure 4 A functional module diagram of an anti-interference non-contact blood pressure detection device provided by an embodiment of the present invention;
[0053] Figure 5 A schematic diagram of the structure of an electronic device for implementing the anti-interference contactless blood pressure detection method provided by an embodiment of the present invention.
[0054] The realization of the purpose, functional features and advantages of the present invention will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION
[0055] It should be understood that the specific embodiments described herein are only used to explain the present invention, and are not used to limit the present invention.
[0056] The embodiment of the present application provides an interference-resistant contactless blood pressure detection method. In the embodiment of the present application, the execution subject of the interference-resistant contactless blood pressure detection method includes but is not limited to at least one of the electronic devices such as the server, the terminal, etc. that can be configured to execute the method provided by the embodiment of the present application. In other words, the interference-resistant contactless blood pressure detection method can be executed by software or hardware installed on a terminal device or a server device, and the software can be a blockchain platform. The server includes but is not limited to: a single server, a server cluster, a cloud server or a cloud server cluster, etc. The server can be an independent server, or it can be a cloud server that provides cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, content delivery networks (Content Delivery Network, CDN), and basic cloud computing services such as big data and artificial intelligence platforms.
[0057] Reference Figure 1 FIG. 1 is a flow chart of an anti-interference non-contact blood pressure detection method provided by an embodiment of the present invention. In this embodiment, the anti-interference non-contact blood pressure detection method includes:
[0058] S1. Use millimeter wave radar to scan the measured area on the back of the hand to obtain a primary blood flow velocity curve and a back of the hand scan image sequence.
[0059] In the embodiment of the present invention, the millimeter wave radar is a radar system that uses millimeter waves for detection and measurement. Millimeter waves refer to electromagnetic waves with a wavelength between 1 mm and 10 mm, which have the characteristics of high frequency, high energy, high speed and high precision. They can not only analyze the user's body movements at low resolution, but also identify the user's health data with high accuracy, such as heart rate, blood flow rate, etc.
[0060] The embodiment of the present invention performs signal enhancement through the reflected signal of the millimeter wave radar, performs distance measurement, azimuth and elevation angle measurement and other operations according to the enhanced signal, and performs image reconstruction according to each measurement result to obtain a hand back scanning image sequence.
[0061] Then, through specific signal characteristics, the signal absorbed by the blood is identified, thereby measuring the primary blood flow velocity curve.
[0062] In detail, in the embodiment of the present invention, the method of scanning the measured area on the back of the hand with a millimeter wave radar to obtain a primary blood flow velocity curve includes:
[0063] generating an initial millimeter wave signal using a radar transmitter of a millimeter wave radar;
[0064] Using a signal receiver to receive a signal after the initial millimeter wave signal penetrates the measured area on the back of the hand, to obtain a reflected signal;
[0065] The primary blood flow velocity curve is calculated based on the initial millimeter wave signal and the reflected signal using a Doppler frequency shift algorithm.
[0066] The Doppler frequency shift algorithm is an algorithm for measuring the speed of a target object relative to a radar system. When the target object moves relative to the radar system, the frequency of the reflected signal will change. The blood flow velocity in the blood vessel can be obtained through the Doppler frequency shift algorithm.
[0067] S2. Performing an edge detection operation based on the blood vessel range on the hand back scan image sequence to obtain a blood vessel display range, and performing a supervision operation based on width expansion and position movement on the blood vessel display range to obtain a position coordinate sequence and a blood vessel expansion and contraction sequence.
[0068] In the embodiment of the present invention, the user's hands may shake in a specific measurement scenario, causing the primary blood flow velocity curve to be inaccurate. Therefore, the user's hand movements need to be considered.
[0069] In detail, in an embodiment of the present invention, the supervision operation based on width shrinkage and expansion and position movement is performed on the blood vessel display range to obtain a position coordinate sequence and a blood vessel shrinkage and expansion sequence, including:
[0070] Recording the maximum width and the minimum width of the blood vessel display range each time to obtain a blood vessel contraction and expansion sequence;
[0071] A marker search is performed on the blood vessel display range to obtain a target blood vessel region, and coordinate mapping is performed on the target blood vessel region to obtain a position coordinate sequence.
[0072] The embodiment of the present invention monitors the blood vessels in the back of the hand scan image sequence through the edge contact algorithm, thereby observing the shrinkage and expansion of the blood vessels. In addition, the embodiment of the present invention can also locate the blood vessels according to the characteristics of the blood vessels, such as blood vessel damage and the skeleton muscle type around the blood vessels, thereby obtaining the position coordinate sequence.
[0073] S3. Obtain a thermal image sequence of the measured area on the back of the hand, identify the air temperature and the back of the hand temperature, and adjust the resolution of the thermal image sequence according to a preset self-appropriate resolution strategy, the air temperature and the back of the hand temperature to obtain a back of the hand temperature dissipation image sequence.
[0074] In the embodiment of the present invention, the back of the hand area can be photographed by an infrared thermal imager to obtain a thermal image sequence.
[0075] Furthermore, the self-adaptive resolution strategy refers to a resolution configuration method that automatically changes in order to enable the thermal image to clearly show the boundaries between skin temperature, skin dissipation temperature and ambient temperature.
[0076] For details, refer to Figure 2 As shown, in the embodiment of the present invention, the resolution of the thermal image sequence is adjusted according to the preset self-appropriate resolution strategy, the air temperature and the hand back temperature to obtain the hand back temperature dissipation image sequence, including:
[0077] S31, automatically adjusting the resolution of the thermal image sequence according to the adaptive resolution strategy, and using an edge detection algorithm to monitor the thermal image sequence in real time;
[0078] S32, identifying and judging whether a preset thermal stratification feature appears in the thermal image sequence according to the air temperature and the hand back temperature;
[0079] S33. When a preset thermal stratification feature appears in the thermal image sequence, the contrast of the image parts of the skin layer, the skin adjacent layer and the air layer in the thermal image sequence is adjusted according to the preset contrast configuration to obtain a hand back temperature dissipation image sequence.
[0080] In the embodiment of the present invention, the layers can be distinguished by an edge detection algorithm, and when the edge detection recognition accuracy is high, the thermal image is enhanced by adjusting the contrast image, thereby obtaining a hand back temperature dissipation image sequence.
[0081] S4. Using the pre-trained anti-interference blood pressure detection model, perform a velocity repair operation on the primary blood flow velocity curve according to the position coordinate sequence to obtain a blood flow velocity curve.
[0082] In an embodiment of the present invention, the anti-interference blood pressure detection method refers to a Transformer-based neural network prediction model, which is used to first perform anti-interference processing on blood characteristics, then mutually verify blood vessel pulsation and temperature changes, and finally predict the user's real-time blood pressure condition.
[0083] For details, refer to Figure 3 As shown, in the embodiment of the present invention, the speed repair operation is performed on the primary blood flow velocity curve according to the position coordinate sequence to obtain the blood flow velocity curve, including:
[0084] S41, calculating the blood vessel position movement vector in adjacent unit time according to the position coordinate sequence;
[0085] S42, calculating the acceleration change sequence of the primary blood flow velocity curve, and performing a product operation on the acceleration change sequence according to the blood vessel position movement vector to obtain a repaired blood flow velocity acceleration sequence;
[0086] S43. According to the repaired blood flow velocity acceleration sequence, acceleration calculation is performed on the initial velocity of the primary blood flow velocity curve to obtain a blood flow velocity curve.
[0087] In the embodiment of the present invention, the blood vessel position displacement vector per unit time is calculated by a position coordinate sequence. The blood vessel position displacement vector has a magnitude and a direction. The magnitude of the blood vessel position displacement vector in the direction of the primary blood flow velocity curve can be used to perform a product operation on the primary blood flow velocity curve to achieve velocity repair and obtain a blood flow velocity curve.
[0088] Furthermore, in an embodiment of the present invention, before using the pre-trained anti-interference blood pressure detection model, the method further includes:
[0089] Obtain a pre-built anti-interference blood pressure detection model and a pre-built blood pressure measurement sample of a population;
[0090] Extracting a target sample from the blood pressure measured samples of the population in turn, and performing network forward calculation on the target sample using the anti-interference blood pressure detection model to obtain a predicted blood pressure value;
[0091] Using a cross entropy loss algorithm, a cross entropy calculation is performed on the true blood pressure label value of the target sample and the predicted blood pressure value to obtain a loss value;
[0092] Minimizing the loss value to obtain the network model parameters when the loss value is the smallest, and performing a network reverse update operation on the network model parameters to obtain an updated anti-interference blood pressure detection model;
[0093] Determine whether the loss value is less than a preset qualified threshold;
[0094] When the loss value is greater than or equal to the qualified threshold, returning to the above operation step of sequentially extracting a target sample from the blood pressure measured samples of the population, and iteratively optimizing the updated anti-interference blood pressure detection model;
[0095] When the loss value is less than the qualified threshold, the training process is stopped to obtain a trained anti-interference blood pressure detection model.
[0096] In an embodiment of the present invention, the actual blood pressure samples of the population refer to a set of samples obtained by simultaneously performing a scanning operation based on millimeter-wave radar and infrared thermal imaging during the traditional pressure measurement of blood pressure of the population, wherein the results of the traditional blood pressure measurement method are configured as the real blood pressure label value corresponding to each sample.
[0097] In the embodiment of the present invention, the loss value between the predicted blood pressure value and the true blood pressure label value is measured by a cross entropy loss algorithm, and the network is reversely parameterized according to the loss value, thereby obtaining an updated anti-interference blood pressure detection model. In addition, in order to ensure that the accuracy of non-contact blood pressure measurement is comparable to that of traditional blood pressure detection, the loss value of the model can be monitored by configuring a lower qualified threshold, thereby completing the training process and obtaining a trained anti-interference blood pressure detection model.
[0098] S5. Perform feature extraction on the hand back temperature dissipation image sequence and the blood vessel contraction and expansion sequence to obtain a blood vessel contraction and expansion feature set, and perform feature extraction on the blood flow velocity curve to obtain a blood flow velocity change feature set.
[0099] In detail, in the embodiment of the present invention, the feature extraction of the hand back temperature dissipation image sequence and the blood vessel contraction and expansion sequence to obtain the blood vessel contraction and expansion feature set includes:
[0100] Performing a convolution operation on the hand back temperature dissipation image sequence to obtain a convolution matrix set;
[0101] Performing average pooling and flattening operations on the convolution matrix set to obtain a reduced-dimensional vascular contraction and expansion feature set;
[0102] A quantization operation is performed on the vascular contraction and expansion sequence, and a feature splicing operation based on corresponding ordinals is performed on the quantization result and the reduced-dimensional vascular contraction and expansion feature set to obtain a vascular contraction and expansion feature set.
[0103] In the embodiment of the present invention, the hand back temperature dissipation image sequence is feature extracted in the above manner, and then the extracted image features are spliced with the quantization results of the corresponding ordinal vascular contraction and expansion sequence to obtain a vascular contraction and expansion feature set from the two aspects of temperature change and vascular width change. Then, the blood flow velocity curve is subjected to a feature extraction operation based on the blood features through feature extraction to obtain a blood flow velocity change feature set.
[0104] S6. Perform full-connection blood pressure prediction on the blood vessel contraction and expansion feature set and the blood flow velocity change feature set to obtain a blood pressure detection value.
[0105] In the embodiment of the present invention, a feature full connection operation is performed on the blood pressure through two aspects of features, namely, a blood vessel contraction and expansion feature set and a blood flow velocity change feature set, and a model network calculation is performed on the feature full connection result to obtain a blood pressure detection value.
[0106] The embodiment of the present invention first locates the user's blood flow velocity and blood vessel position through millimeter wave radar to provide a basis for subsequent blood pressure measurement, and then provides blood temperature change characteristics for blood pressure detection through the hand back temperature dissipation image sequence with adaptive resolution; then the embodiment of the present invention uses the anti-interference blood pressure detection model to first perform anti-interference processing on the blood flow velocity according to the blood vessel position, and then extracts comprehensive features of the hand back temperature dissipation image sequence and the blood vessel contraction and expansion sequence and the blood flow velocity curve to achieve comprehensive features of temperature change, blood vessel contraction, and blood flow velocity, and then calculates a more accurate blood pressure detection value through the model. Therefore, the anti-interference non-contact blood pressure detection method provided by the embodiment of the present invention can detect the user's blood pressure without contact, improve the anti-interference ability during detection, and improve the accuracy of blood pressure detection.
[0107] like Figure 4 , is a functional module diagram of an anti-interference contactless blood pressure detection device provided by an embodiment of the present invention.
[0108] The anti-interference non-contact blood pressure detection device 100 of the present invention can be installed in an electronic device. According to the functions to be implemented, the anti-interference non-contact blood pressure detection device 100 can include a millimeter wave scanning module 101, a data extraction module 102, a temperature dissipation image acquisition module 103 and a model blood pressure prediction module 104. The module of the present invention can also be called a unit, which refers to a series of computer program segments that can be executed by an electronic device processor and can complete fixed functions, which are stored in the memory of the electronic device.
[0109] In this embodiment, the functions of each module / unit are as follows:
[0110] The millimeter wave scanning module 101 is used to scan the measured area of the back of the hand using the millimeter wave radar to obtain a primary blood flow velocity curve and a back of the hand scanning image sequence;
[0111] The data extraction module 102 is used to perform an edge detection operation based on the blood vessel range on the hand back scan image sequence to obtain a blood vessel display range, and perform a supervision operation based on width expansion and position movement on the blood vessel display range to obtain a position coordinate sequence and a blood vessel expansion and contraction sequence;
[0112] The temperature dissipation image acquisition module 103 is used to acquire a thermal image sequence of the hand back measured area, identify the air temperature and the hand back temperature, and adjust the resolution of the thermal image sequence according to a preset self-appropriate resolution strategy, the air temperature and the hand back temperature to obtain a hand back temperature dissipation image sequence;
[0113] The model blood pressure prediction module 104 is used to use the pre-trained anti-interference blood pressure detection model to perform a velocity repair operation on the primary blood flow velocity curve according to the position coordinate sequence to obtain a blood flow velocity curve, and to perform feature extraction on the back of the hand temperature dissipation image sequence and the blood vessel contraction and expansion sequence to obtain a blood vessel contraction and expansion feature set, and to perform feature extraction on the blood flow velocity curve to obtain a blood flow velocity change feature set, and to perform full-connected blood pressure prediction on the blood vessel contraction and expansion feature set and the blood flow velocity change feature set to obtain a blood pressure detection value.
[0114] In detail, each module described in the anti-interference non-contact blood pressure detection device 100 described in the embodiment of the present application is used in the same manner as described above. Figures 1 to 3 The anti-interference non-contact blood pressure detection method described in the present invention has the same technical means and can produce the same technical effects, so it will not be repeated here.
[0115] like Figure 5 , is a schematic diagram of the structure of an electronic device 1 for implementing an anti-interference contactless blood pressure detection method provided by an embodiment of the present invention.
[0116] The electronic device 1 may include a processor 10, a memory 11, a communication bus 12 and a communication interface 13, and may also include a computer program stored in the memory 11 and executable on the processor 10, such as an anti-interference contactless blood pressure detection program.
[0117] In some embodiments, the processor 10 may be composed of an integrated circuit, for example, a single packaged integrated circuit, or a plurality of packaged integrated circuits with the same or different functions, including one or more central processing units (CPUs), microprocessors, digital processing chips, graphics processors, and combinations of various control chips. The processor 10 is the control core (ControlUnit) of the electronic device 1, and uses various interfaces and lines to connect various components of the entire electronic device, and executes or executes programs or modules stored in the memory 11 (for example, executing an anti-interference contactless blood pressure detection program, etc.), and calls data stored in the memory 11 to execute various functions of the electronic device and process data.
[0118] The memory 11 includes at least one type of readable storage medium, and the readable storage medium includes a flash memory, a mobile hard disk, a multimedia card, a card-type memory (for example, an SD or DX memory, etc.), a magnetic memory, a disk, an optical disk, etc. In some embodiments, the memory 11 may be an internal storage unit of an electronic device, such as a mobile hard disk of the electronic device. In other embodiments, the memory 11 may also be an external storage device of an electronic device, such as a plug-in mobile hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), etc. equipped on the electronic device. Further, the memory 11 may also include both an internal storage unit of the electronic device and an external storage device. The memory 11 can not only be used to store application software and various types of data installed in the electronic device, such as the code of an anti-interference contactless blood pressure detection program, but also can be used to temporarily store data that has been output or is to be output.
[0119] The communication bus 12 may be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc. The bus may be divided into an address bus, a data bus, a control bus, etc. The bus is configured to realize connection and communication between the memory 11 and at least one processor 10, etc.
[0120] The communication interface 13 is used for communication between the above-mentioned electronic device 1 and other devices, including a network interface and a user interface. Optionally, the network interface may include a wired interface and / or a wireless interface (such as a WI-FI interface, a Bluetooth interface, etc.), which is generally used to establish a communication connection between the electronic device and other electronic devices. The user interface may be a display (Display), an input unit (such as a keyboard (Keyboard)), and optionally, the user interface may also be a standard wired interface, a wireless interface. Optionally, in some embodiments, the display may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, and an OLED (Organic Light-Emitting Diode, organic light-emitting diode) touch device, etc. Among them, the display may also be appropriately referred to as a display screen or a display unit, which is used to display information processed in the electronic device and to display a visual user interface.
[0121] Figure 5 Only an electronic device with components is shown, and those skilled in the art will understand that Figure 5The structure shown does not constitute a limitation on the electronic device 1, and may include fewer or more components than shown in the figure, or combine certain components, or arrange the components differently.
[0122] For example, although not shown, the electronic device 1 may also include a power source (such as a battery) for supplying power to each component. Preferably, the power source may be logically connected to the at least one processor 10 through a power management device, so that the power management device can realize functions such as charging management, discharging management, and power consumption management. The power source may also include any components such as one or more DC or AC power sources, recharging devices, power failure detection circuits, power converters or inverters, power status indicators, etc. The electronic device 1 may also include a variety of sensors, Bluetooth modules, Wi-Fi modules, etc., which will not be repeated here.
[0123] It should be understood that the embodiment is for illustration only and the scope of the patent application is not limited to this structure.
[0124] The anti-interference contactless blood pressure detection program stored in the memory 11 of the electronic device 1 is a combination of multiple instructions. When running in the processor 10, it can achieve:
[0125] The millimeter wave radar is used to scan the measured area on the back of the hand to obtain the primary blood flow velocity curve and the back of the hand scanning image sequence;
[0126] Performing an edge detection operation based on the blood vessel range on the hand back scan image sequence to obtain a blood vessel display range, and performing a supervision operation based on width shrinkage and expansion and position movement on the blood vessel display range to obtain a position coordinate sequence and a blood vessel shrinkage and expansion sequence;
[0127] Acquire a thermal image sequence of the measured area on the back of the hand, identify the air temperature and the back of the hand temperature, and adjust the resolution of the thermal image sequence according to a preset self-appropriate resolution strategy, the air temperature and the back of the hand temperature to obtain a back of the hand temperature dissipation image sequence;
[0128] Using a pre-trained anti-interference blood pressure detection model, a velocity repair operation is performed on the primary blood flow velocity curve according to the position coordinate sequence to obtain a blood flow velocity curve;
[0129] Performing feature extraction on the hand back temperature dissipation image sequence and the blood vessel contraction and expansion sequence to obtain a blood vessel contraction and expansion feature set, and performing feature extraction on the blood flow velocity curve to obtain a blood flow velocity change feature set;
[0130] Fully connected blood pressure prediction is performed on the blood vessel contraction and expansion feature set and the blood flow velocity change feature set to obtain a blood pressure detection value.
[0131] Specifically, the specific implementation method of the processor 10 for the above instructions can refer to the description of the relevant steps in the corresponding embodiment of the accompanying drawings, which will not be repeated here.
[0132] Furthermore, if the module / unit integrated in the electronic device 1 is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. The computer-readable storage medium can be volatile or non-volatile. For example, the computer-readable medium can include: any entity or device capable of carrying the computer program code, a recording medium, a USB flash drive, a mobile hard disk, a magnetic disk, an optical disk, a computer memory, and a read-only memory (ROM).
[0133] The present invention further provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor of an electronic device, the computer program can implement:
[0134] The millimeter wave radar is used to scan the measured area on the back of the hand to obtain the primary blood flow velocity curve and the back of the hand scanning image sequence;
[0135] Performing an edge detection operation based on the blood vessel range on the hand back scan image sequence to obtain a blood vessel display range, and performing a supervision operation based on width shrinkage and expansion and position movement on the blood vessel display range to obtain a position coordinate sequence and a blood vessel shrinkage and expansion sequence;
[0136] Acquire a thermal image sequence of the measured area on the back of the hand, identify the air temperature and the back of the hand temperature, and adjust the resolution of the thermal image sequence according to a preset self-appropriate resolution strategy, the air temperature and the back of the hand temperature to obtain a back of the hand temperature dissipation image sequence;
[0137] Using a pre-trained anti-interference blood pressure detection model, a velocity repair operation is performed on the primary blood flow velocity curve according to the position coordinate sequence to obtain a blood flow velocity curve;
[0138] Performing feature extraction on the hand back temperature dissipation image sequence and the blood vessel contraction and expansion sequence to obtain a blood vessel contraction and expansion feature set, and performing feature extraction on the blood flow velocity curve to obtain a blood flow velocity change feature set;
[0139] Fully connected blood pressure prediction is performed on the blood vessel contraction and expansion feature set and the blood flow velocity change feature set to obtain a blood pressure detection value.
[0140] In the several embodiments provided by the present invention, it should be understood that the disclosed devices, apparatuses and methods can be implemented in other ways. For example, the device embodiments described above are only schematic, for example, the division of the modules is only a logical function division, and there may be other division methods in actual implementation.
[0141] The modules described as separate components may or may not be physically separated, and the components shown as modules may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
[0142] In addition, each functional module in each embodiment of the present invention may be integrated into one processing unit, each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of hardware plus software functional modules.
[0143] It is obvious to those skilled in the art that the present invention is not limited to the details of the above exemplary embodiments, and that the present invention can be implemented in other specific forms without departing from the spirit or essential characteristics of the present invention.
[0144] Therefore, no matter from which point of view, the embodiments should be regarded as illustrative and non-restrictive, and the scope of the present invention is limited by the appended claims rather than the above description, so it is intended that all changes falling within the meaning and scope of the equivalent elements of the claims are included in the present invention. Any attached figure mark in the claims should not be regarded as limiting the claims involved.
[0145] The blockchain referred to in this invention is a new application mode of computer technologies such as distributed data storage, peer-to-peer transmission, consensus mechanism, encryption algorithm, etc. Blockchain is essentially a decentralized database, a string of data blocks generated by cryptographic methods. Each data block contains a batch of network transaction information, which is used to verify the validity of its information (anti-counterfeiting) and generate the next block. Blockchain can include the underlying blockchain platform, platform product service layer, and application service layer.
[0146] The embodiments of the present application can acquire and process relevant data based on artificial intelligence technology. Among them, artificial intelligence (AI) is the theory, method, technology and application system that uses digital computers or machines controlled by digital computers to simulate, extend and expand human intelligence, perceive the environment, acquire knowledge and use knowledge to obtain the best results.
[0147] In addition, it is clear that the word "comprising" does not exclude other units or steps, and the singular does not exclude the plural. Multiple units or devices stated in the system claim can also be implemented by one unit or device through software or hardware. The words first, second, etc. are used to indicate names, and do not indicate any particular order.
[0148] Finally, it should be noted that the above embodiments are only used to illustrate the technical solution of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solution of the present invention can be modified or replaced by equivalents without departing from the spirit and scope of the technical solution of the present invention.
Claims
1. An anti-interference non-contact blood pressure detection method, characterized in that: The method comprises: The millimeter wave radar is used to scan the measured area on the back of the hand to obtain the primary blood flow velocity curve and the back of the hand scanning image sequence; Performing an edge detection operation based on the blood vessel range on the hand back scan image sequence to obtain a blood vessel display range, and performing a supervision operation based on width shrinkage and expansion and position movement on the blood vessel display range to obtain a position coordinate sequence and a blood vessel shrinkage and expansion sequence; Acquire a thermal image sequence of the measured area on the back of the hand, identify the air temperature and the back of the hand temperature, and adjust the resolution of the thermal image sequence according to a preset adaptive resolution strategy, the air temperature and the back of the hand temperature to obtain a back of the hand temperature dissipation image sequence; Using a pre-trained anti-interference blood pressure detection model, a velocity repair operation is performed on the primary blood flow velocity curve according to the position coordinate sequence to obtain a blood flow velocity curve; Performing feature extraction on the hand back temperature dissipation image sequence and the blood vessel contraction and expansion sequence to obtain a blood vessel contraction and expansion feature set, and performing feature extraction on the blood flow velocity curve to obtain a blood flow velocity change feature set; Performing full-connection blood pressure prediction on the blood vessel contraction and expansion feature set and the blood flow velocity change feature set to obtain a blood pressure detection value; The step of adjusting the resolution of the thermal image sequence according to the preset adaptive resolution strategy, the air temperature and the hand back temperature to obtain the hand back temperature dissipation image sequence includes: Automatically adjusting the resolution of the thermal image sequence according to the adaptive resolution strategy, and using an edge detection algorithm to monitor the thermal image sequence in real time; Identifying and judging whether a preset thermal stratification feature appears in the thermal image sequence according to the air temperature and the back of the hand temperature; When a preset thermal stratification feature appears in the thermal image sequence, contrast adjustment is performed on image portions of the skin layer, the skin adjacent layer and the air layer in the thermal image sequence according to a preset contrast configuration to obtain a hand back temperature dissipation image sequence; The feature extraction of the hand back temperature dissipation image sequence and the blood vessel contraction and expansion sequence to obtain a blood vessel contraction and expansion feature set includes: Performing a convolution operation on the hand back temperature dissipation image sequence to obtain a convolution matrix set; Performing average pooling and flattening operations on the convolution matrix set to obtain a reduced-dimensional vascular contraction and expansion feature set; A quantization operation is performed on the vascular contraction and expansion sequence, and a feature splicing operation based on corresponding ordinals is performed on the quantization result and the reduced-dimensional vascular contraction and expansion feature set to obtain a vascular contraction and expansion feature set.
2. The anti-interference non-contact blood pressure detection method according to claim 1, characterized in that: The step of performing a velocity repair operation on the primary blood flow velocity curve according to the position coordinate sequence to obtain the blood flow velocity curve comprises: Calculating the blood vessel position movement vector in adjacent unit time according to the position coordinate sequence; Calculating the acceleration change sequence of the primary blood flow velocity curve, and performing a product operation on the acceleration change sequence according to the blood vessel position movement vector to obtain a repaired blood flow velocity acceleration sequence; According to the repaired blood flow velocity acceleration sequence, acceleration calculation is performed on the initial velocity of the primary blood flow velocity curve to obtain a blood flow velocity curve.
3. The anti-interference non-contact blood pressure detection method according to claim 1, characterized in that: The method of scanning the measured area on the back of the hand using a millimeter wave radar to obtain a primary blood flow velocity curve includes: generating an initial millimeter wave signal using a radar transmitter of a millimeter wave radar; Using a signal receiver to receive a signal after the initial millimeter wave signal penetrates the measured area on the back of the hand, to obtain a reflected signal; The primary blood flow velocity curve is calculated based on the initial millimeter wave signal and the reflected signal using a Doppler frequency shift algorithm.
4. The anti-interference non-contact blood pressure detection method according to claim 1, characterized in that: Before using the pre-trained anti-interference blood pressure detection model, the method further includes: Obtain a pre-built anti-interference blood pressure detection model and a pre-built blood pressure measurement sample of a population; Extracting a target sample from the blood pressure measured samples of the population in turn, and performing network forward calculation on the target sample using the anti-interference blood pressure detection model to obtain a predicted blood pressure value; Using a cross entropy loss algorithm, a cross entropy calculation is performed on the true blood pressure label value of the target sample and the predicted blood pressure value to obtain a loss value; Minimizing the loss value to obtain the network model parameters when the loss value is the smallest, and performing a network reverse update operation on the network model parameters to obtain an updated anti-interference blood pressure detection model; Determine whether the loss value is less than a preset qualified threshold; When the loss value is greater than or equal to the qualified threshold, returning to the above operation step of sequentially extracting a target sample from the blood pressure measured samples of the population, and iteratively optimizing the updated anti-interference blood pressure detection model; When the loss value is less than the qualified threshold, the training process is stopped to obtain a trained anti-interference blood pressure detection model.
5. The anti-interference non-contact blood pressure detection method according to claim 1, characterized in that: The monitoring operation based on width shrinkage and expansion and position movement is performed on the blood vessel display range to obtain a position coordinate sequence and a blood vessel shrinkage and expansion sequence, including: Recording the maximum width and the minimum width of the blood vessel display range each time to obtain a blood vessel contraction and expansion sequence; A marker search is performed on the blood vessel display range to obtain a target blood vessel region, and coordinate mapping is performed on the target blood vessel region to obtain a position coordinate sequence.
6. An anti-interference non-contact blood pressure detection device, characterized in that: The device comprises: A millimeter wave scanning module is used to scan the measured area of the back of the hand using a millimeter wave radar to obtain a primary blood flow velocity curve and a back of the hand scanning image sequence; A data extraction module is used to perform an edge detection operation based on the blood vessel range on the hand back scan image sequence to obtain a blood vessel display range, and perform a supervision operation based on width expansion and position movement on the blood vessel display range to obtain a position coordinate sequence and a blood vessel expansion and contraction sequence; A temperature dissipation image acquisition module is used to acquire a thermal image sequence of the measured area on the back of the hand, identify the air temperature and the back of the hand temperature, and adjust the resolution of the thermal image sequence according to a preset adaptive resolution strategy, the air temperature and the back of the hand temperature to obtain a back of the hand temperature dissipation image sequence; A model blood pressure prediction module is used to use a pre-trained anti-interference blood pressure detection model to perform a velocity repair operation on the primary blood flow velocity curve according to the position coordinate sequence to obtain a blood flow velocity curve, and to perform feature extraction on the back of the hand temperature dissipation image sequence and the blood vessel contraction and expansion sequence to obtain a blood vessel contraction and expansion feature set, and to perform feature extraction on the blood flow velocity curve to obtain a blood flow velocity change feature set, and to perform full-connection blood pressure prediction on the blood vessel contraction and expansion feature set and the blood flow velocity change feature set to obtain a blood pressure detection value; The temperature dissipation image acquisition module adjusts the resolution of the thermal image sequence according to a preset adaptive resolution strategy, the air temperature and the hand back temperature to obtain the hand back temperature dissipation image sequence, including: Automatically adjusting the resolution of the thermal image sequence according to the adaptive resolution strategy, and using an edge detection algorithm to monitor the thermal image sequence in real time; Identifying and judging whether a preset thermal stratification feature appears in the thermal image sequence according to the air temperature and the back of the hand temperature; When a preset thermal stratification feature appears in the thermal image sequence, contrast adjustment is performed on image portions of the skin layer, the skin adjacent layer and the air layer in the thermal image sequence according to a preset contrast configuration to obtain a hand back temperature dissipation image sequence; The feature extraction of the hand back temperature dissipation image sequence and the blood vessel contraction and expansion sequence to obtain a blood vessel contraction and expansion feature set includes: Performing a convolution operation on the hand back temperature dissipation image sequence to obtain a convolution matrix set; Performing average pooling and flattening operations on the convolution matrix set to obtain a reduced-dimensional vascular contraction and expansion feature set; A quantization operation is performed on the vascular contraction and expansion sequence, and a feature splicing operation based on corresponding ordinals is performed on the quantization result and the reduced-dimensional vascular contraction and expansion feature set to obtain a vascular contraction and expansion feature set.
7. An electronic device, characterized in that: The electronic device comprises: at least one processor; and, a memory communicatively connected to the at least one processor; wherein, The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the interference-resistant non-contact blood pressure detection method as described in any one of claims 1 to 5.
8. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the interference-resistant non-contact blood pressure detection method according to any one of claims 1 to 5 is implemented.
