Nursing information processing method and system

Abstract

The invention provides a nursing information processing method and system. The method comprises the steps that physical sign information of patients and old people is collected in real time; obtaining a distance unit of the human body target according to the preprocessed physical sign information; separating the respiration signal and the heartbeat signal in the phase to obtain a respiration time domain signal and a heartbeat time domain signal, and estimating a respiration frequency and a heartbeat frequency; detecting the respiratory frequencies to identify abnormal respiratory frequencies in the respiratory frequencies; pulse signals are generated based on the heartbeat frequency, baseline drift in the pulse signals is eliminated, feature points in the pulse signals with the baseline drift eliminated are extracted, and corresponding blood pressure is obtained based on the feature points; constructing a visual state diagram according to the blood pressure, the pulse signal with the baseline drift eliminated and the respiratory rate, and judging the health conditions of the patient and the old based on the visual state diagram. Physical conditions of patients and old people are judged in real time, measures can be taken in time according to the physical conditions, and nursing efficiency is improved.

Description

Technical Field

[0001] The present invention relates to the field of information processing technology, and in particular to a nursing information processing method and system. Background Art

[0002] As people pay more attention to their health, especially the physical condition of patients with chronic diseases and the elderly, more attention needs to be paid. In order to enable nurses to more intuitively understand the physical condition of patients and the elderly, it is necessary to process the nursing information of patients and the elderly, so that nurses can better manage the health status of patients and the elderly, thereby effectively improving the nursing efficiency of nurses.

[0003] In the existing technology, nurses usually observe the various physiological indicators of patients through instruments and test reports to check the health status of patients and the elderly, and then judge the health status of patients and the elderly based on the actual situation. This not only fails to judge the physical condition of patients and the elderly in a timely manner, but also fails to monitor and judge the physiological condition of patients and the elderly in real time, resulting in difficulty in timely judgment of physiological changes of patients and the elderly, and thus makes it impossible for nurses to take correct measures for patients and the elderly based on real-time nursing information. Summary of the Invention

[0004] Based on this, the purpose of the present invention is to provide a nursing information processing method and system to solve the above-mentioned deficiencies in the prior art.

[0005] In a first aspect, the present invention provides a nursing information processing method, the method comprising:

[0006] Based on the millimeter wave radar, the vital sign information of patients and the elderly is collected in real time, and the vital sign information is preprocessed to obtain preprocessed vital sign information;

[0007] Executing the CFAR algorithm on the pre-processed vital sign information based on the distance dimension and the velocity dimension respectively to obtain the distance unit of the human target, and extracting the phase corresponding to the distance unit;

[0008] Separating the respiratory signal and the heartbeat signal in the phase to obtain a time domain signal of the respiratory signal and a time domain signal of the heartbeat, and estimating the respiratory frequency and the heartbeat frequency based on the time domain signal of the respiratory signal and the time domain signal of the heartbeat;

[0009] Building an abnormal breathing database, detecting the respiratory frequency according to the abnormal breathing types in the abnormal breathing database and based on a non-parametric time detection algorithm to identify abnormal respiratory frequencies in the respiratory frequencies;

[0010] generating a pulse signal based on the heart rate, eliminating baseline drift in the pulse signal, extracting characteristic points from the pulse signal with the baseline drift eliminated, and obtaining corresponding blood pressure based on the characteristic points;

[0011] A visual state diagram is constructed according to the blood pressure, the pulse signal with baseline drift eliminated, and the respiratory rate, and the health status of the patient and the elderly is judged based on the visual state diagram.

[0012] Compared with the existing technology, the beneficial effects of the present invention are: the vital signs information of patients and the elderly can be collected contactlessly through millimeter wave radar, so that patients and the elderly can be monitored in real time, and the respiratory rate can be detected through the abnormal breathing database and non-parametric time detection algorithm, so that the abnormal breathing conditions of patients and the elderly can be obtained, and the blood pressure, pulse signal and respiratory rate generated by the pulse signal can be used to construct a visual status diagram of the patients and the elderly, so that the physical condition of the patients and the elderly can be judged in time according to the visual status diagram, and preventive measures can be taken in time to improve nursing efficiency.

[0013] Furthermore, the steps of collecting the vital signs information of patients and elderly people in real time based on the millimeter wave radar and preprocessing the vital signs information include:

[0014] Based on FMCW millimeter wave radar, the location information of patients and the elderly is collected in real time to achieve human target positioning;

[0015] and detecting distance information, speed information, and angle information of the human target based on a change in the phase of an intermediate frequency signal in a frequency modulated continuous wave signal of the FMCW millimeter wave radar, and obtaining vital sign information based on the distance information, the speed information, and the angle information, wherein the vital sign information includes respiratory rate information and heart rate information;

[0016] A vector mean cancellation algorithm is used to remove DC from the vital sign information, and a heartbeat bandpass filter is used to separate the respiratory frequency information and the heartbeat frequency information.

[0017] Furthermore, the steps of executing the CFAR algorithm based on the distance dimension and the velocity dimension on the preprocessed vital sign information to obtain the distance unit of the human target and extracting the phase corresponding to the distance unit include:

[0018] Sampling distance dimension information in the vital sign information based on a CFAR algorithm, and detecting the distance dimension information according to the CFAR algorithm to obtain distance unit information of the human chest cavity;

[0019] Sampling velocity dimension information in the vital sign information based on a CFAR algorithm, and detecting the distance dimension information according to the CFAR algorithm to obtain velocity unit information of the human chest cavity;

[0020] The distance unit of the human target is obtained based on the distance unit information and the speed unit information, and the corresponding phase of the distance unit is extracted using a forward and inverse tangent function.

[0021] Furthermore, the steps of separating the respiratory signal and the heartbeat signal in the phase to obtain a time domain signal of the respiratory signal and a time domain signal of the heartbeat, and estimating the respiratory frequency and the heartbeat frequency based on the time domain signal of the respiratory signal and the time domain signal of the heartbeat include:

[0022] Separating the respiratory signal and the heartbeat signal in the phase based on a wireless impulse response filter and a finite impulse response filter, and obtaining a time domain signal of the respiratory signal and a time domain signal of the heartbeat according to the respiratory signal and the heartbeat signal;

[0023] Decomposing the time domain signal of respiration and the time domain signal of heartbeat into a sine wave of respiration and a sine wave of heartbeat based on discrete Fourier transform;

[0024] One-dimensional FFT and two-dimensional FFT are performed on the respiratory sinusoidal wave and the heartbeat sinusoidal wave in sequence to obtain the respiratory frequency and the heartbeat frequency, and noise of the respiratory frequency and the heartbeat frequency is eliminated by a parameter filtering elimination method.

[0025] Furthermore, the expression of the discrete Fourier transform is:

[0026]

[0027] Where X(k) represents the frequency domain signal after discrete Fourier transform, k represents the frequency domain index, N represents the total number of discrete time samples, n represents the fast time index, and x(n) represents the discrete time domain signal. represents the rotation factor, represents the complex exponential function, j represents the imaginary unit, Indicates the rotation angle.

[0028] Furthermore, the expression of the one-dimensional FFT is:

[0029]

[0030] Where S If,1D (k) represents the discrete spectrum of the one-dimensional intermediate frequency signal, k represents the frequency domain index, N represents the total number of discrete time samples, y[n,m] represents the discrete intermediate frequency signal, n represents the fast time index, m represents the slow time index, The kernel function representing the discrete Fourier transform;

[0031] The expression of the two-dimensional FFT is:

[0032]

[0033] Where S lf,2D (k,l) represents a two-dimensional spectrum, k represents the distance dimension, l represents the Doppler dimension, 4πx(mT s ) represents the phase change caused by the target micro-motion, x(mT s ) represents slow time mT s Displacement at time, T s represents the pulse repetition interval, λ c represents the carrier wavelength, Represents discrete Fourier transform, and M represents the total number of sampling points in the slow time dimension.

[0034] Furthermore, the steps of eliminating the baseline drift in the pulse signal, extracting characteristic points in the pulse signal with the baseline drift eliminated, and obtaining the corresponding blood pressure based on the characteristic points include:

[0035] Extracting all extreme points in the pulse signal, the extreme points including local maxima and local minima, and performing interpolation among the local maxima and the local minima to obtain an upper envelope and a lower envelope;

[0036] Calculating a mean envelope of the upper envelope and the lower envelope, and extracting detail features in the pulse signal according to the mean envelope;

[0037] Repeating the steps of extracting all extreme points in the pulse signal, wherein the extreme points include local maxima and local minima, interpolating the local maxima and local minima to obtain an upper envelope and a lower envelope, calculating a mean envelope of the upper envelope and the lower envelope, and extracting detailed features from the pulse signal based on the mean envelope until the mean envelope becomes a monotonic function, thereby eliminating baseline drift and obtaining the pulse signal;

[0038] Corresponding feature points in the pulse signal are extracted, and corresponding blood pressure is obtained based on the corresponding feature points.

[0039] In a second aspect, the present invention further provides a nursing information processing system, the system comprising:

[0040] An acquisition and preprocessing module is used to collect the vital sign information of patients and the elderly in real time based on the millimeter wave radar, and preprocess the vital sign information to obtain preprocessed vital sign information;

[0041] An extraction module is configured to execute a CFAR algorithm on the pre-processed vital sign information based on the distance dimension and the velocity dimension to obtain a distance unit of the human target and extract a phase corresponding to the distance unit;

[0042] a separation and estimation module, configured to separate the respiratory signal and the heartbeat signal in the phase to obtain a time domain signal of the respiratory signal and a time domain signal of the heartbeat, and estimate the respiratory frequency and the heartbeat frequency based on the time domain signal of the respiratory signal and the time domain signal of the heartbeat;

[0043] Building an identification module for building an abnormal breathing database, detecting the respiratory frequency according to the abnormal breathing types in the abnormal breathing database and based on a non-parametric time detection algorithm to identify abnormal respiratory frequencies among the respiratory frequencies;

[0044] a generation and elimination module, configured to generate a pulse signal based on the heart rate, eliminate baseline drift in the pulse signal, extract characteristic points from the pulse signal with the baseline drift eliminated, and obtain corresponding blood pressure based on the characteristic points;

[0045] A judgment module is constructed to construct a visual state diagram according to the blood pressure, the pulse signal with baseline drift eliminated, and the respiratory rate, and to judge the health status of the patient and the elderly based on the visual state diagram.

[0046] In a third aspect, the present invention further provides an electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the above-mentioned nursing information processing method when executing the computer program.

[0047] In a fourth aspect, the present invention further provides a storage medium storing a computer program, which implements the above-mentioned nursing information processing method when executed by a processor. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] Figure 1 is a flowchart of a nursing information processing method in a first embodiment of the present invention;

[0049] Figure 2 is a structural block diagram of a nursing information processing system in a second embodiment of the present invention;

[0050] Figure 3 FIG. 4 is a schematic diagram of the hardware structure of an electronic device in a third embodiment of the present invention.

[0051] Description of main component symbols:

[0052] 10. Acquisition and preprocessing module; 20. Execution and extraction module; 30. Separation and estimation module; 40. Construction and identification module; 50. Generation and elimination module; 60. Construction and judgment module;

[0053] 70. Bus; 71. Processor; 72. Memory; 73. Communication interface.

[0054] The following specific embodiments will further illustrate the present invention in conjunction with the above-mentioned drawings. DETAILED DESCRIPTION

[0055] To facilitate understanding of the present invention, the present invention will be described more fully below with reference to the accompanying drawings. The drawings illustrate several embodiments of the present invention. However, the present invention may be implemented in many different forms and is not limited to the embodiments described herein. Rather, these embodiments are provided to provide a more thorough and comprehensive understanding of the present invention.

[0056] It should be noted that when an element is referred to as being "fixed to" another element, it may be directly on the other element or there may be an intermediate element. When an element is referred to as being "connected to" another element, it may be directly connected to the other element or there may be an intermediate element. The terms "vertical," "horizontal," "left," "right," and similar expressions used herein are for illustrative purposes only.

[0057] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those skilled in the art to which this invention pertains. The terms used in this specification of the present invention are for the purpose of describing specific embodiments only and are not intended to limit the present invention. The term "and / or" as used herein includes any and all combinations of one or more of the associated listed items.

[0058] Example 1

[0059] See also Figure 1 , which shows a nursing information processing method in a first embodiment of the present invention, the method includes steps S1 to S6:

[0060] S1, collecting vital sign information of patients and elderly people in real time based on millimeter wave radar, and preprocessing the vital sign information to obtain preprocessed vital sign information;

[0061] Specifically, the step S1 includes steps S11 to S13:

[0062] S11, based on FMCW millimeter wave radar, collects and calculates the position information of patients and elderly people in real time to achieve human target positioning;

[0063] S12, detecting distance information, speed information, and angle information of the human target based on a phase change of an intermediate frequency signal in a frequency modulated continuous wave signal of the FMCW millimeter wave radar, and obtaining vital sign information based on the distance information, the speed information, and the angle information, wherein the vital sign information includes respiratory rate information and heart rate information;

[0064] S13, removing DC from the vital sign information using a vector mean cancellation algorithm, and separating the respiratory rate information and the heart rate information by using a heartbeat bandpass filter;

[0065] It can be understood that FMCW millimeter-wave radar has the ability to measure distance, speed and angle, can calculate the position information of the target, and can be used for human target positioning during vital sign detection. FMCW millimeter-wave radar adopts an orthogonal receiving frame mechanism. The phase change of the intermediate frequency signal in the frequency-modulated continuous wave signal emitted by the millimeter-wave radar can not only detect the movement of the human body, but also detect the displacement change of the human chest movement, thereby obtaining the breathing rate information and heart rate information of patients and the elderly, and then obtaining the vital sign information of patients and the elderly.

[0066] It should be noted that because FMCW millimeter-wave radar uses an orthogonal receiving frame structure, the echo signal received by the radar is mixed with the local oscillator signal in the mixer. This may be affected by internal circuit components and poor isolation between the transmitting and receiving antennas, generating DC noise. In this embodiment, a mean cancellation algorithm is used to remove DC noise from the vital sign information obtained by the radar. The normal human respiratory rate ranges from 0.1Hz to 0.5Hz, and the heart rate ranges from 0.8Hz to 2Hz. These two frequency ranges can serve as the passband cutoff frequencies of the two filters. In this embodiment, an IIR filter is used to separate the respiratory and heart rate information.

[0067] S2, executing the CFAR algorithm based on the distance dimension and the velocity dimension on the pre-processed vital sign information to obtain the distance unit of the human target and extracting the phase corresponding to the distance unit;

[0068] Specifically, step S2 includes steps S21 to S23:

[0069] S21, sampling distance dimension information in the vital sign information based on a CFAR algorithm, and detecting the distance dimension information according to the CFAR algorithm to obtain distance unit information of the human chest cavity;

[0070] S22, sampling the velocity dimension information in the vital sign information based on the CFAR algorithm, and detecting the distance dimension information according to the CFAR algorithm to obtain velocity unit information of the human chest cavity;

[0071] S23, obtaining a distance unit of the human target based on the distance unit information and the velocity unit information, and extracting a corresponding phase of the distance unit using a forward and reverse tangent function;

[0072] It can be understood that CFAR is a method for achieving target detection by adaptively estimating the background clutter level. The specific process is to adaptively estimate the threshold of each unit based on the statistical characteristics of the background clutter while maintaining a certain false alarm probability, so that the distance unit information and the velocity unit information of the human chest can be obtained according to the distance dimension information and the velocity dimension information respectively. Then, the inverse tangent function can be used to extract the phase corresponding to the distance unit based on the distance unit information and the velocity unit information of the human chest.

[0073] S3, separating the respiratory signal and the heartbeat signal in the phase to obtain a time domain signal of the respiratory signal and a time domain signal of the heartbeat, and estimating the respiratory frequency and the heartbeat frequency based on the time domain signal of the respiratory signal and the time domain signal of the heartbeat;

[0074] Specifically, step S3 includes steps S31 to S33:

[0075] S31, separating the respiratory signal and the heartbeat signal in the phase based on a wireless impulse response filter and a finite impulse response filter, and obtaining a time domain signal of the respiratory signal and a time domain signal of the heartbeat according to the respiratory signal and the heartbeat signal;

[0076] It can be understood that the heart rate range and the respiratory rate range are different, so two filters can be used to separate the respiratory signal and the heart rate signal in the phase. In this embodiment, separation is performed using a wireless impulse response filter and a finite impulse response filter, and the time domain signal of the respiratory signal and the time domain signal of the heart rate are obtained based on the respiratory signal and the heart rate signal.

[0077] S32, decomposing the time domain signal of respiration and the time domain signal of heartbeat into a respiration sine wave and a heartbeat sine wave based on discrete Fourier transform;

[0078] The expression of the discrete Fourier transform is:

[0079]

[0080]

[0081] Where X(k) represents the frequency domain signal after discrete Fourier transform, k represents the frequency domain index, N represents the total number of discrete time samples, n represents the fast time index, and x(n) represents the discrete time domain signal. represents the rotation factor, represents the complex exponential function, j represents the imaginary unit, Indicates the rotation angle.

[0082] S33, performing one-dimensional FFT and two-dimensional FFT on the respiratory sine wave and the heartbeat sine wave in sequence to obtain respiratory frequency and heartbeat frequency, and eliminating noise of the respiratory frequency and heartbeat frequency by a parameter filtering elimination method;

[0083] The expression of the one-dimensional FFT is:

[0084]

[0085] Where S If,1D (k) represents the discrete spectrum of the one-dimensional intermediate frequency signal, k represents the frequency domain index, N represents the total number of discrete time samples, y[n,m] represents the discrete intermediate frequency signal, n represents the fast time index, m represents the slow time index, The kernel function representing the discrete Fourier transform;

[0086] The expression of the two-dimensional FFT is:

[0087]

[0088] Where S lf,2D (k,l) represents a two-dimensional spectrum, k represents the distance dimension, l represents the Doppler dimension, 4πx(mT s ) represents the phase change caused by the target micro-motion, x(mT s ) represents slow time mT s Displacement at time, T s represents the pulse repetition interval, λ c represents the carrier wavelength, Represents discrete Fourier transform, and M represents the total number of sampling points in the slow time dimension.

[0089] It is understandable that both respiratory information and heartbeat information are included in the phase. By performing one-dimensional FFT and two-dimensional FFT in sequence and finding the peak in the two-dimensional FFT, the corresponding respiratory frequency and heartbeat frequency can be obtained.

[0090] In addition, it should be explained that the noise of the respiratory frequency and heart rate can be eliminated by parameter filtering to avoid harmonics from drowning the frequencies in the respiratory signal and heart rate signal.

[0091] S4, building an abnormal breathing database, detecting the respiratory rate according to the abnormal breathing types in the abnormal breathing database and based on a non-parametric time detection algorithm to identify abnormal respiratory rates among the respiratory rates;

[0092] It can be understood that the types of abnormal breathing include Cheyne-Stokes respiration, Cheyne-Stokes variant respiration, dysrhythmic respiration, Biot's respiration and Kumar's respiration, and the abnormal breathing database includes Cheyne-Stokes respiration radar echo time domain waveform diagram, Cheyne-Stokes variant respiration radar echo time domain waveform diagram, dysrhythmic respiration radar echo time domain waveform diagram, Biot's respiration radar echo time domain waveform diagram and Kumar's respiration radar echo time domain waveform diagram.

[0093] It should be noted that the respiratory frequency is compared with the radar echo time domain waveform of abnormal breathing in the abnormal breathing database through the non-parametric time detection algorithm and abnormal breathing type, so as to analyze the abnormal breathing conditions of patients and the elderly.

[0094] S5, generating a pulse signal based on the heart rate, eliminating baseline drift in the pulse signal, extracting feature points from the pulse signal with the baseline drift eliminated, and obtaining corresponding blood pressure based on the feature points;

[0095] Specifically, step S5 includes steps S51 to S54:

[0096] S51, extracting all extreme points in the pulse signal, wherein the extreme points include local maxima and local minima, and interpolating the local maxima and local minima to obtain an upper envelope and a lower envelope;

[0097] S52, calculating a mean envelope of the upper envelope and the lower envelope, and extracting detail features in the pulse signal according to the mean envelope;

[0098] S53, repeatedly extracting all extreme points in the pulse signal, wherein the extreme points include local maxima and local minima, interpolating the local maxima and local minima to obtain an upper envelope and a lower envelope, calculating a mean envelope of the upper envelope and the lower envelope, and extracting detailed features from the pulse signal based on the mean envelope until the mean envelope becomes a monotonic function to eliminate baseline drift, thereby obtaining the pulse signal;

[0099] S54, extracting corresponding feature points from the pulse signal, and obtaining corresponding blood pressure based on the corresponding feature points;

[0100] It should be noted that baseline drift refers to the increase in the DC component in the pulse wave signal over time. In this embodiment, the pulse wave signal is preprocessed by empirical mode decomposition to eliminate the noise and baseline drift problems in the signal acquired by the radar, and the corresponding feature points are extracted to obtain the corresponding blood pressure.

[0101] S6, constructing a visual state diagram according to the blood pressure, the pulse signal with baseline drift eliminated, and the respiratory rate, and judging the health status of the patient and the elderly based on the visual state diagram;

[0102] It can be understood that quantitative bar graphs, qualitative bar graphs, quantitative line graphs and qualitative line graphs are constructed based on blood pressure, pulse signals and respiratory rate, so that the physical health status of patients and the elderly can be intuitively obtained, which can better prevent subsequent measures and improve nursing efficiency.

[0103] In summary, the nursing information processing method in the above-mentioned embodiment of the present invention can collect the vital signs information of patients and the elderly without contact through millimeter wave radar, so that patients and the elderly can be monitored in real time, and the respiratory rate can be detected through the abnormal breathing database and the non-parametric time detection algorithm, so as to obtain the abnormal breathing conditions of patients and the elderly, and construct a visual status diagram of patients and the elderly through the blood pressure, pulse signal and respiratory rate generated by the pulse signal, so that the physical condition of patients and the elderly can be judged in time according to the visual status diagram, and preventive measures can be taken in time to improve nursing efficiency.

[0104] Example 2

[0105] See also Figure 2 , which shows a nursing information processing system in a second embodiment of the present invention, the system includes:

[0106] The acquisition and preprocessing module 10 is used to collect the vital sign information of patients and elderly people in real time based on the millimeter wave radar, and preprocess the vital sign information to obtain preprocessed vital sign information;

[0107] An extraction module 20 is configured to execute a CFAR algorithm on the pre-processed vital sign information based on the distance dimension and the velocity dimension to obtain a distance unit of the human target and extract a phase corresponding to the distance unit;

[0108] a separation and estimation module 30 for separating the respiratory signal and the heartbeat signal in the phase to obtain a time domain signal of the respiratory signal and a time domain signal of the heartbeat, and estimating the respiratory frequency and the heartbeat frequency based on the time domain signal of the respiratory signal and the time domain signal of the heartbeat;

[0109] Building an identification module 40 for building an abnormal breathing database, detecting the respiratory frequency according to the abnormal breathing types in the abnormal breathing database and based on a non-parametric time detection algorithm to identify abnormal respiratory frequencies in the respiratory frequencies;

[0110] a generation and elimination module 50 for generating a pulse signal based on the heart rate, eliminating baseline drift in the pulse signal, extracting characteristic points from the pulse signal with the baseline drift eliminated, and obtaining corresponding blood pressure based on the characteristic points;

[0111] A judgment module 60 is constructed to construct a visual state diagram according to the blood pressure, the pulse signal with baseline drift eliminated, and the respiratory rate, and to judge the health status of the patient and the elderly based on the visual state diagram.

[0112] In some optional embodiments, the acquisition preprocessing module 10 includes:

[0113] The acquisition unit is used to collect and calculate the position information of patients and the elderly in real time based on FMCW millimeter wave radar to achieve human target positioning;

[0114] a detection unit, configured to detect distance information, speed information, and angle information of the human target based on a phase change of an intermediate frequency signal in a frequency modulated continuous wave signal of the FMCW millimeter wave radar, and obtain vital sign information based on the distance information, the speed information, and the angle information, wherein the vital sign information includes respiratory rate information and heart rate information;

[0115] The first separation unit is used to remove DC from the vital sign information by adopting a vector mean cancellation algorithm, and to separate the respiratory frequency information and the heart rate information by adopting a heart rate bandpass filter.

[0116] In some optional embodiments, the execution extraction module 20 includes:

[0117] a first sampling unit, configured to sample distance dimension information in the vital sign information based on a CFAR algorithm, and detect the distance dimension information according to the CFAR algorithm to obtain distance unit information of the human chest cavity;

[0118] a second sampling unit, configured to sample velocity dimension information in the vital sign information based on a CFAR algorithm, and detect the distance dimension information according to the CFAR algorithm to obtain velocity unit information of the human chest cavity;

[0119] The first extraction unit is configured to obtain the distance unit of the human target based on the distance unit information and the speed unit information, and extract the corresponding phase of the distance unit using a forward and inverse tangent function.

[0120] In some optional embodiments, the separation estimation module 30 includes:

[0121] a second separation unit, configured to separate the respiratory signal and the heartbeat signal in the phase based on a wireless impulse response filter and a finite impulse response filter, and obtain a time domain signal of the respiratory signal and a time domain signal of the heartbeat according to the respiratory signal and the heartbeat signal;

[0122] A decomposition unit is configured to decompose the time domain signal of respiration and the time domain signal of heartbeat into a sine wave of respiration and a sine wave of heartbeat based on a discrete Fourier transform, wherein the expression of the discrete Fourier transform is:

[0123]

[0124] Where X(k) represents the frequency domain signal after discrete Fourier transform, k represents the frequency domain index, N represents the total number of discrete time samples, n represents the fast time index, and x(n) represents the discrete time domain signal. represents the rotation factor, represents the complex exponential function, j represents the imaginary unit, Indicates the rotation angle;

[0125] The elimination unit is configured to perform one-dimensional FFT and two-dimensional FFT on the respiratory sine wave and the heartbeat sine wave in sequence to obtain the respiratory frequency and the heartbeat frequency, and eliminate the noise of the respiratory frequency and the heartbeat frequency by a parameter filtering elimination method, wherein the expression of the one-dimensional FFT is:

[0126]

[0127] Where S If,1D (k) represents the discrete spectrum of the one-dimensional intermediate frequency signal, k represents the frequency domain index, N represents the total number of discrete time samples, y[n,m] represents the discrete intermediate frequency signal, n represents the fast time index, m represents the slow time index, The kernel function representing the discrete Fourier transform;

[0128] The expression of the two-dimensional FFT is:

[0129]

[0130] Where S lf,2D (k,l) represents a two-dimensional spectrum, k represents the distance dimension, l represents the Doppler dimension, 4πx(mT s ) represents the phase change caused by the target micro-motion, x(mT s ) represents slow time mT s Displacement at time, T s represents the pulse repetition interval, λ c represents the carrier wavelength, Represents discrete Fourier transform, and M represents the total number of sampling points in the slow time dimension.

[0131] In some optional embodiments, the generation and elimination module 50 includes:

[0132] a second extraction unit, configured to extract all extreme points in the pulse signal, wherein the extreme points include local maxima and local minima, and interpolate the local maxima and local minima to obtain an upper envelope and a lower envelope;

[0133] a calculation unit gate, configured to calculate a mean envelope of the upper envelope and the lower envelope, and extract detail features from the pulse signal according to the mean envelope;

[0134] an extraction and elimination unit, configured to repeatedly extract all extreme value points in the pulse signal, wherein the extreme value points include local maxima and local minima, interpolate the local maxima and local minima to obtain an upper envelope and a lower envelope, calculate a mean envelope of the upper envelope and the lower envelope, and extract detailed features from the pulse signal based on the mean envelope until the mean envelope becomes a monotonic function, thereby eliminating baseline drift and obtaining the pulse signal;

[0135] The third extraction unit is configured to extract corresponding feature points from the pulse signal and obtain corresponding blood pressure based on the corresponding feature points.

[0136] The functions or operation steps implemented when the above modules and units are executed are substantially the same as those in the above method embodiments and will not be repeated here.

[0137] The nursing information processing system provided in the embodiment of the present invention has the same implementation principle and technical effects as those of the aforementioned method embodiment. For the sake of brief description, for matters not mentioned in the system embodiment, reference can be made to the corresponding content in the aforementioned method embodiment.

[0138] Example 3

[0139] See also Figure 3 , shown is an electronic device in a third embodiment of the present invention.

[0140] The electronic device may include a processor 71 and a memory 72 storing computer program instructions.

[0141] Specifically, the processor 71 may include a central processing unit (CPU), or an application specific integrated circuit (ASIC), or may be configured to implement one or more integrated circuits of the present application.

[0142] Among them, the memory 72 may include a large-capacity memory for data or instructions. By way of example and not limitation, the memory 72 may include a hard disk drive (HDD), a floppy disk drive, a solid-state drive (SSD), a flash memory, an optical disk, a magneto-optical disk, a magnetic tape, or a universal serial bus (USB) drive, or a combination of two or more of these. Where appropriate, the memory 72 may include a removable or non-removable (or fixed) medium. Where appropriate, the memory 72 may be inside or outside the data processing device. In a specific embodiment, the memory 72 is a non-volatile memory. In a specific embodiment, the memory 72 includes a read-only memory (ROM) and a random access memory (RAM). Where appropriate, the ROM may be a mask-programmed ROM, a programmable ROM (PROM), an erasable PROM (EPROM), an electrically erasable PROM (EEPROM), an electrically alterable ROM (EAROM) or a flash memory (FLASH), or a combination of two or more of these. Under appropriate circumstances, the RAM can be a static random access memory (SRAM) or a dynamic random access memory (DRAM), where the DRAM can be a fast page mode dynamic random access memory (FPMDRAM), an extended data output dynamic random access memory (EDODRAM), a synchronous dynamic random access memory (SDRAM), etc.

[0143] The memory 72 may be used to store or cache various data files required for processing and / or communication, as well as possible computer program instructions executed by the processor 71 .

[0144] The processor 71 implements the nursing information processing method of the first embodiment by reading and executing computer program instructions stored in the memory 72 .

[0145] In some embodiments, the electronic device may further include a communication interface 73 and a bus 70. Figure 3 As shown, the processor 71, the memory 72, and the communication interface 73 are connected via a bus 70 and communicate with each other.

[0146] The communication interface 73 is used to implement communication between the various modules, devices, units and / or equipment in this application. The communication interface 73 can also implement data communication with other components such as: external devices, image / data acquisition equipment, databases, external storage, and image / data processing workstations.

[0147] The bus 70 includes hardware, software, or both, and couples the components of the device to each other. The bus 70 includes, but is not limited to, at least one of the following: a data bus, an address bus, a control bus, an expansion bus, and a local bus. By way of example and not limitation, bus 70 may include an Accelerated Graphics Port (AGP) or other graphics bus, an Extended Industry Standard Architecture (EISA) bus, a Front Side Bus (FSB), a Hyper Transport (HT) interconnect, an Industry Standard Architecture (ISA) bus, an InfiniBand interconnect, a Low Pin Count (LPC) bus, a memory bus, a Micro Channel Architecture (MCA) bus, a Peripheral Component Interconnect (PCI) bus, a PCI-Express (PCI-X) bus, a Serial Advanced Technology Attachment (SATA) bus, a Video Electronics Standards Association Local Bus (VLB) bus, or other suitable buses, or a combination of two or more of the above. Bus 70 may include one or more buses, where appropriate. Although this application describes and illustrates a particular bus, this application contemplates any suitable bus or interconnect.

[0148] The electronic device can obtain the nursing information processing system and execute the nursing information processing method of the first embodiment.

[0149] In addition, in combination with the nursing information processing method in the first embodiment, the present application may provide a storage medium for implementation. The storage medium stores computer program instructions; when the computer program instructions are executed by a processor, the nursing information processing method in the first embodiment is implemented.

[0150] Throughout this specification, reference to terms such as "one embodiment," "some embodiments," "examples," "specific examples," or "some examples" means that a specific feature, structure, material, or characteristic described in conjunction with that embodiment or example is included in at least one embodiment or example of the present invention. In this specification, schematic representations of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples.

[0151] The above-described embodiments merely illustrate several implementations of the present invention, and while their descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the present invention. It should be noted that a person skilled in the art would be able to make numerous variations and improvements without departing from the spirit of the present invention, all of which fall within the scope of protection of the present invention. Therefore, the scope of protection of the present invention shall be determined by the appended claims.

Claims

1. A nursing information processing method, characterized in that: The method comprises: Based on the millimeter wave radar, the vital sign information of patients and the elderly is collected in real time, and the vital sign information is preprocessed to obtain preprocessed vital sign information; Executing the CFAR algorithm on the pre-processed vital sign information based on the distance dimension and the velocity dimension respectively to obtain the distance unit of the human target, and extracting the phase corresponding to the distance unit; Separating the respiratory signal and the heartbeat signal in the phase to obtain a time domain signal of the respiratory signal and a time domain signal of the heartbeat, and estimating the respiratory frequency and the heartbeat frequency based on the time domain signal of the respiratory signal and the time domain signal of the heartbeat; Building an abnormal breathing database, detecting the respiratory frequency according to the abnormal breathing types in the abnormal breathing database and based on a non-parametric time detection algorithm to identify abnormal respiratory frequencies in the respiratory frequencies; generating a pulse signal based on the heart rate, eliminating baseline drift in the pulse signal, extracting characteristic points from the pulse signal with the baseline drift eliminated, and obtaining corresponding blood pressure based on the characteristic points; A visual state diagram is constructed according to the blood pressure, the pulse signal with baseline drift eliminated, and the respiratory rate, and the health status of the patient and the elderly is judged based on the visual state diagram.

2. The nursing information processing method according to claim 1, characterized in that: The steps of collecting the vital signs information of patients and elderly people in real time based on the millimeter wave radar and preprocessing the vital signs information include: Based on FMCW millimeter wave radar, the location information of patients and the elderly is collected in real time to achieve human target positioning; and detecting distance information, speed information, and angle information of the human target based on a change in the phase of an intermediate frequency signal in a frequency modulated continuous wave signal of the FMCW millimeter wave radar, and obtaining vital sign information based on the distance information, the speed information, and the angle information, wherein the vital sign information includes respiratory rate information and heart rate information; A vector mean cancellation algorithm is used to remove DC from the vital sign information, and a heartbeat bandpass filter is used to separate the respiratory frequency information and the heartbeat frequency information.

3. The nursing information processing method according to claim 1, characterized in that: The steps of executing the CFAR algorithm based on the distance dimension and the velocity dimension on the preprocessed vital sign information to obtain the distance unit of the human target and extracting the phase corresponding to the distance unit include: Sampling distance dimension information in the vital sign information based on a CFAR algorithm, and detecting the distance dimension information according to the CFAR algorithm to obtain distance unit information of the human chest cavity; Sampling velocity dimension information in the vital sign information based on a CFAR algorithm, and detecting the distance dimension information according to the CFAR algorithm to obtain velocity unit information of the human chest cavity; The distance unit of the human target is obtained based on the distance unit information and the speed unit information, and the corresponding phase of the distance unit is extracted using a forward and inverse tangent function.

4. The nursing information processing method according to claim 1, characterized in that: The steps of separating the respiratory signal and the heartbeat signal in the phase to obtain a time domain signal of the respiratory signal and a time domain signal of the heartbeat, and estimating the respiratory frequency and the heartbeat frequency based on the time domain signal of the respiratory signal and the time domain signal of the heartbeat include: Separating the respiratory signal and the heartbeat signal in the phase based on a wireless impulse response filter and a finite impulse response filter, and obtaining a time domain signal of the respiratory signal and a time domain signal of the heartbeat according to the respiratory signal and the heartbeat signal; Decomposing the time domain signal of respiration and the time domain signal of heartbeat into a sine wave of respiration and a sine wave of heartbeat based on discrete Fourier transform; One-dimensional FFT and two-dimensional FFT are performed on the respiratory sinusoidal wave and the heartbeat sinusoidal wave in sequence to obtain the respiratory frequency and the heartbeat frequency, and noise of the respiratory frequency and the heartbeat frequency is eliminated by a parameter filtering elimination method.

5. The nursing information processing method according to claim 4, characterized in that: The expression of the discrete Fourier transform is: Where X(k) represents the frequency domain signal after discrete Fourier transform, k represents the frequency domain index, N represents the total number of discrete time samples, n represents the fast time index, and x(n) represents the discrete time domain signal. represents the rotation factor, represents the complex exponential function, j represents the imaginary unit, Indicates the rotation angle.

6. The nursing information processing method according to claim 4, characterized in that: The expression of the one-dimensional FFT is: Where S If,1D (k) represents the discrete spectrum of the one-dimensional intermediate frequency signal, k represents the frequency domain index, N represents the total number of discrete time samples, y[n,m] represents the discrete intermediate frequency signal, n represents the fast time index, m represents the slow time index, The kernel function representing the discrete Fourier transform; The expression of the two-dimensional FFT is: Where S lf,2D (k,l) represents a two-dimensional spectrum, k represents the distance dimension, l represents the Doppler dimension, 4πx(mT s ) represents the phase change caused by the target micro-motion, x(mT s ) represents slow time mT s Displacement at time, T S represents the pulse repetition interval, λ c represents the carrier wavelength, Represents discrete Fourier transform, and M represents the total number of sampling points in the slow time dimension.

7. The nursing information processing method according to claim 1, characterized in that: The steps of eliminating the baseline drift in the pulse signal, extracting characteristic points in the pulse signal with the baseline drift eliminated, and obtaining the corresponding blood pressure based on the characteristic points include: Extracting all extreme points in the pulse signal, the extreme points including local maxima and local minima, and performing interpolation among the local maxima and the local minima to obtain an upper envelope and a lower envelope; Calculating a mean envelope of the upper envelope and the lower envelope, and extracting detail features in the pulse signal according to the mean envelope; Repeating the steps of extracting all extreme points in the pulse signal, wherein the extreme points include local maxima and local minima, interpolating the local maxima and local minima to obtain an upper envelope and a lower envelope, calculating a mean envelope of the upper envelope and the lower envelope, and extracting detailed features from the pulse signal based on the mean envelope until the mean envelope becomes a monotonic function, thereby eliminating baseline drift and obtaining the pulse signal; Corresponding feature points in the pulse signal are extracted, and corresponding blood pressure is obtained based on the corresponding feature points.

8. A nursing information processing system, characterized in that: The system comprises: An acquisition and preprocessing module is used to collect the vital sign information of patients and the elderly in real time based on the millimeter wave radar, and preprocess the vital sign information to obtain preprocessed vital sign information; An extraction module is configured to execute a CFAR algorithm on the pre-processed vital sign information based on the distance dimension and the velocity dimension to obtain a distance unit of the human target and extract a phase corresponding to the distance unit; a separation and estimation module, configured to separate the respiratory signal and the heartbeat signal in the phase to obtain a time domain signal of the respiratory signal and a time domain signal of the heartbeat, and estimate the respiratory frequency and the heartbeat frequency based on the time domain signal of the respiratory signal and the time domain signal of the heartbeat; Building an identification module for building an abnormal breathing database, detecting the respiratory frequency according to the abnormal breathing types in the abnormal breathing database and based on a non-parametric time detection algorithm to identify abnormal respiratory frequencies among the respiratory frequencies; a generation and elimination module, configured to generate a pulse signal based on the heart rate, eliminate baseline drift in the pulse signal, extract characteristic points from the pulse signal with the baseline drift eliminated, and obtain corresponding blood pressure based on the characteristic points; A judgment module is constructed to construct a visual state diagram according to the blood pressure, the pulse signal with baseline drift eliminated, and the respiratory rate, and to judge the health status of the patient and the elderly based on the visual state diagram.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the computer program, the nursing information processing method according to any one of claims 1 to 7 is implemented.

10. A storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the nursing information processing method according to any one of claims 1 to 7 is realized.

Images