CN117892202A - Nursing action monitoring method and electronic equipment based on millimeter wave signals - Google Patents

Abstract

The application provides a nursing action monitoring method and electronic equipment based on millimeter wave signals, wherein the method comprises the following steps: periodically transmitting millimeter wave signals with preset frequency to a space where a user is located; respectively receiving millimeter wave signals and forming a plurality of different target millimeter wave signals after the millimeter wave signals are reflected by a user; processing each target millimeter wave signal based on an FFT algorithm, a DOA estimation algorithm and a CFAR algorithm to obtain point cloud information corresponding to the whole of each target millimeter wave signal; and sending each point cloud data frame in the point cloud information to a computing terminal, so that the computing terminal receives a plurality of point cloud data frames in a preset time window, judges whether the time window is a nursing window, if so, inputs each point cloud data frame in the nursing window to a pre-trained deep learning model, and outputs a corresponding nursing action result. The nursing monitoring method and the nursing monitoring system can effectively reduce the flow complexity of the nursing monitoring method, effectively reduce the nursing monitoring cost, and further effectively improve the experience of patients.

Description

Nursing action monitoring method and electronic equipment based on millimeter wave signals

Technical Field

The present application relates to the field of nursing monitoring, and in particular to a nursing action monitoring method and electronic equipment based on millimeter wave signals.

Background technique

Millimeter-wave radar has been widely used in fields such as autonomous driving, industry, drones, and medical applications. Millimeter-wave radar has relatively high perception accuracy and strong anti-interference ability. With the help of FMCW modulation technology, information such as the distance, angle, and speed of the target can be obtained at low cost. In addition, millimeter-wave signals are not easily affected by the external environment, can penetrate smoke and water vapor, and are not easily affected by lighting conditions. Millimeter-wave sensing technology has been widely used, such as gesture recognition, gait recognition, and heartbeat and breathing recognition based on millimeter waves, which can provide us with a more intelligent, convenient, and high-quality product experience.

Existing nursing monitoring methods are highly complex, costly, and provide poor user experience.

Summary of the invention

In view of this, the embodiments of the present application provide a nursing action monitoring method and device based on millimeter wave signals to eliminate or improve one or more defects existing in the prior art.

The first aspect of the present application provides a nursing action monitoring method based on millimeter wave signals, the method comprising:

Periodically sending millimeter wave signals of a preset frequency to the space where the user is located;

Respectively receiving the millimeter wave signals reflected by users to form a plurality of different target millimeter wave signals; the users include caregivers and care recipients;

Processing each of the target millimeter wave signals based on an FFT algorithm, a DOA estimation algorithm, and a CFAR algorithm to obtain point cloud information corresponding to each of the target millimeter wave signals as a whole;

Each point cloud data frame in the point cloud information is sent to a computing terminal, so that the computing terminal receives multiple point cloud data frames in a preset time window, and determines whether the time window is a nursing window. If so, each point cloud data frame in the nursing window is input into a pre-trained deep learning model, and the corresponding nursing action result is output.

In some embodiments of the present application, the processing of each of the target millimeter wave signals based on the FFT algorithm, the DOA estimation algorithm, and the CFAR algorithm to obtain point cloud information corresponding to each of the target millimeter wave signals as a whole includes:

Performing FFT calculations on the frame length dimensions of each of the target millimeter wave signals to obtain Doppler characteristic matrices and distance characteristic matrices corresponding to each of the target millimeter wave signals;

Based on the DOA estimation algorithm and each of the target millimeter wave signals, a distance angle matrix corresponding to each of the target millimeter wave signals as a whole is obtained;

Based on the CFAR target detection algorithm, each of the Doppler feature matrices and the corresponding distance angle matrix are processed respectively to obtain the point cloud information corresponding to the overall millimeter wave signal of each target.

In some embodiments of the present application, the step of obtaining a distance angle matrix corresponding to each target millimeter wave signal as a whole based on the DOA estimation algorithm and each target millimeter wave signal includes:

Obtaining a conversion coefficient matrix corresponding to each of the receiving antennas based on the arrangement of the receiving antennas corresponding to each of the target millimeter wave signals;

Each of the conversion coefficient matrices is multiplied by its corresponding distance feature matrix and then processed using a DOA estimation algorithm to obtain the distance angle matrix.

In some embodiments of the present application, the CFAR target detection algorithm processes each of the Doppler feature matrices and the corresponding distance angle matrices respectively to obtain point cloud information corresponding to the entirety of each target millimeter wave signal, including:

Calculate the position information of the weighted distance angle matrix based on the CFAR target detection algorithm;

Based on each of the Doppler characteristic matrices and the position information, point cloud information corresponding to each target millimeter wave signal as a whole is obtained.

The second aspect of the present application provides a nursing action monitoring method based on millimeter wave signals, the method comprising:

Receiving each point cloud data frame in the point cloud information sent by the millimeter wave radar in a preset time window; the point cloud information is formed by the millimeter wave radar periodically sending a millimeter wave signal of a preset frequency to the space where the user is located, and receiving the millimeter wave signal respectively after being reflected by the user to form a plurality of different target millimeter wave signals; processing each of the target millimeter wave signals based on the FFT algorithm, the DOA estimation algorithm and the CFAR algorithm to obtain the user, wherein the user includes a caregiver and a person being cared for;

Determine whether the time window is a nursing window; if so, input each point cloud data frame within the nursing window into a pre-trained deep learning model, and output the corresponding nursing action result.

In some embodiments of the present application, in the nursing action monitoring method based on millimeter wave signals provided in the second aspect of the present application, the step of determining whether the time window is a nursing window includes:

Determine whether the number of point cloud data frames received per second within the time window is greater than a preset number threshold, and whether the ratio of the number of point cloud data frames in a preset spatial range per second to the total number of point cloud data frames received per second is greater than a preset ratio threshold. If both are true, determine that the time window is a nursing window.

In some embodiments of the present application, in the nursing action monitoring method based on millimeter wave signals provided in the second aspect of the present application, each point cloud data frame in the nursing window is input into a pre-trained deep learning model, and the corresponding nursing action result is output, including:

Inputting each point cloud data frame in the nursing window into the convolutional neural network, and extracting multi-dimensional features corresponding to each point cloud data frame;

Each of the multi-dimensional features is input into the recurrent neural network in chronological order, the correlation information of each of the multi-dimensional features in the time dimension is extracted, and the nursing action feature matrix is output.

The nursing action result is obtained based on the nursing action feature matrix and the preset nursing action label.

The third aspect of the present application provides an electronic device, which, if the electronic device is a millimeter wave radar, is used to implement the nursing action monitoring method based on millimeter wave signals as described in the first aspect above;

If the electronic device is a computing terminal, the computing terminal includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the nursing action monitoring method based on millimeter wave signals as described in the second aspect above is implemented.

The fourth aspect of the present application provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the nursing action monitoring method based on millimeter wave signals described in the aforementioned second aspect.

The fifth aspect of the present application provides a computer program product, including a computer program, which, when executed by a processor, implements the nursing action monitoring method based on millimeter wave signals described in the second aspect.

In summary, the present application provides a method for monitoring nursing actions based on millimeter wave signals, the method comprising: periodically sending millimeter wave signals of a preset frequency to the space where the user is located; receiving the millimeter wave signals respectively and forming a plurality of different target millimeter wave signals after being reflected by the user; processing each target millimeter wave signal based on the FFT algorithm, the DOA estimation algorithm and the CFAR algorithm to obtain the point cloud information corresponding to each target millimeter wave signal as a whole; sending each point cloud data frame to the computing terminal, so that the computing terminal receives a plurality of point cloud data frames in a preset time window, and determines whether the time window is a nursing window, and if so, inputs each point cloud data frame in the nursing window into a pre-trained deep learning model, and outputs the corresponding nursing action result. The present application can effectively reduce the process complexity of the nursing monitoring method, and effectively reduce the nursing monitoring cost, thereby effectively improving the patient experience.

Additional advantages, purposes, and features of the present application will be partially described in the following description, and will become partially apparent to those skilled in the art after studying the following, or may be learned from the practice of the present application. The purposes and other advantages of the present application can be achieved and obtained by the structures specifically pointed out in the specification and the drawings.

Those skilled in the art will understand that the purposes and advantages that can be achieved by the present application are not limited to the above specific description, and the above and other purposes that can be achieved by the present application will be more clearly understood based on the following detailed description.

BRIEF DESCRIPTION OF THE DRAWINGS

The drawings described herein are used to provide a further understanding of the present application, constitute a part of the present application, and do not constitute a limitation of the present application. The components in the drawings are not drawn to scale, but are only for the purpose of illustrating the principles of the present application. In order to facilitate the illustration and description of some parts of the present application, the corresponding parts in the drawings may be enlarged, that is, they may become larger relative to other components in the exemplary device actually manufactured according to the present application. In the drawings:

FIG1 is a flow chart of a first nursing action monitoring method based on millimeter wave signals in one embodiment of the present application.

FIG2 is a flow chart of a second nursing action monitoring method based on millimeter wave signals in another embodiment of the present application.

FIG3 is a schematic diagram of the overall architecture of a second nursing action monitoring method based on millimeter wave signals in another embodiment of the present application.

Detailed ways

In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the implementation modes and the accompanying drawings. Here, the illustrative implementation modes and descriptions of the present application are used to explain the present application, but are not intended to limit the present application.

It should also be noted here that in order to avoid obscuring the present application due to unnecessary details, only the structures and/or processing steps closely related to the scheme according to the present application are shown in the accompanying drawings, while other details that are not very relevant to the present application are omitted.

It should be emphasized that the term “include/comprises” when used herein refers to the presence of features, elements, steps or components, but does not exclude the presence or addition of one or more other features, elements, steps or components.

It should also be noted that, unless otherwise specified, the term “connection” herein may refer not only to a direct connection but also to an indirect connection with an intermediate.

Hereinafter, embodiments of the present application will be described with reference to the accompanying drawings. In the accompanying drawings, the same reference numerals represent the same or similar components, or the same or similar steps.

The details are described in detail through the following examples.

The embodiment of the present application provides a first nursing action monitoring method based on millimeter wave signals that can be performed by a millimeter wave radar. Referring to FIG. 1 , the nursing action monitoring method based on millimeter wave signals specifically includes the following contents:

Step 110: Periodically send a millimeter wave signal of a preset frequency to the space where the user is located.

Step 120: receiving the millimeter wave signals respectively and forming a plurality of different target millimeter wave signals after being reflected by users; the users include caregivers and the care recipients.

Step 130: Process each of the target millimeter wave signals based on the FFT algorithm, the DOA estimation algorithm and the CFAR algorithm to obtain point cloud information corresponding to each of the target millimeter wave signals as a whole.

Step 140: Send each point cloud data frame in the point cloud information to the computing terminal, so that the computing terminal receives multiple point cloud data frames in a preset time window, and determines whether the time window is a nursing window. If so, input each point cloud data frame in the nursing window into a pre-trained deep learning model, and output the corresponding nursing action result.

Specifically, the millimeter wave radar (such as Texas Instruments IWR 6843) first periodically sends a millimeter wave signal of a preset frequency to the space where the user is located. Then, multiple receiving antennas are used to receive the millimeter wave signal, which is reflected by the user to form multiple different target millimeter wave signals; then, each target millimeter wave signal is processed based on the FFT (Fast Fourier Transform) algorithm, DOA (Direction of Arrival) estimation algorithm and CFAR (Constant False Alarm Rate) target detection algorithm to obtain the point cloud information corresponding to each target millimeter wave signal as a whole. Finally, each point cloud data frame in the point cloud information is sent to the computing terminal, so that the computing terminal receives multiple point cloud data frames in a preset time window, and determines whether the time window is a nursing window. If so, each point cloud data frame in the nursing window is input into a pre-trained deep learning model, and the corresponding nursing action result is output, so as to effectively reduce the process complexity of the nursing monitoring method and effectively reduce the nursing monitoring cost, thereby effectively improving the patient experience.

The users include caregivers and the care recipients. The millimeter wave signal represents a two-dimensional information, including a signal segment with a fixed number of sampling points and a frequency that changes linearly with time. The target millimeter wave information is a two-dimensional signal, including a frame length and a discrete number of sampling points. The point cloud data frame includes the X, Y, Z three-dimensional coordinates, speed, and signal strength information of multiple points.

In order to further reduce the process complexity of the nursing monitoring method, step 130 includes:

Step 131: performing two FFT calculations on the frame length dimension of each target millimeter wave signal to obtain a Doppler characteristic matrix and a distance characteristic matrix corresponding to each target millimeter wave signal.

For step 131, the Doppler feature (i.e., the velocity feature) is as shown in Formula 1, and the distance feature is as shown in Formula 2:

(1)

in, is the wavelength, /> represents the phase difference between the millimeter wave signal and the target millimeter wave signal, and t represents time.

(2)

Wherein, c is the speed of light, f is the frequency difference between the millimeter wave signal and the target millimeter wave signal, d is the distance between the user and the receiving antenna, and s is the frequency growth slope of the millimeter wave signal.

Step 132: Based on the DOA estimation algorithm and each of the target millimeter-wave signals, a distance angle matrix corresponding to each of the target millimeter-wave signals as a whole is obtained.

Step 133: Based on the CFAR target detection algorithm, each of the Doppler feature matrices and the corresponding distance angle matrix is processed respectively to obtain point cloud information corresponding to the entirety of each target millimeter wave signal.

Specifically, the millimeter-wave radar first performs FFT calculations on the frame length dimension of each target millimeter-wave signal to obtain the Doppler feature matrix and distance feature matrix corresponding to each target millimeter-wave signal; then, based on the DOA estimation algorithm and each target millimeter-wave signal, the distance angle matrix corresponding to each target millimeter-wave signal is obtained; finally, based on the CFAR target detection algorithm, each Doppler feature matrix and the corresponding distance angle matrix are processed separately to obtain the point cloud information corresponding to each target millimeter-wave signal as a whole, thereby further reducing the process complexity of the nursing monitoring method.

In order to effectively obtain the distance angle matrix, step 132 includes:

Based on the arrangement of the receiving antennas corresponding to the target millimeter wave signals, the conversion coefficient matrix corresponding to each receiving antenna is obtained, as shown in Formula 3;

(3)

j represents the imaginary number symbol, Represents the phase difference between the mth receiving antenna and the first receiving antenna.

Each of the conversion coefficient matrices is multiplied by its corresponding distance feature matrix and then processed using a DOA estimation algorithm to obtain the distance angle matrix, as shown in Formula 4.

(4)

in, is the distance feature matrix corresponding to the target millimeter wave signal received by the mth receiving antenna, Represents the conversion coefficient matrix corresponding to the mth receiving antenna.

Specifically, the millimeter-wave radar first obtains the conversion coefficient matrix corresponding to each receiving antenna based on the arrangement of the receiving antennas corresponding to each target millimeter-wave signal; finally, each conversion coefficient matrix is multiplied with the corresponding distance feature matrix and processed using the DOA estimation algorithm to obtain the distance angle matrix.

In order to effectively obtain the point cloud data frame, step 133 includes:

Calculate the position information of the weighted distance angle matrix based on the CFAR target detection algorithm;

Based on each of the Doppler characteristic matrices and the position information, point cloud information corresponding to each target millimeter wave signal as a whole is obtained.

Specifically, the millimeter-wave radar calculates the position information of each Doppler feature matrix and the corresponding distance angle matrix based on the CFAR target detection algorithm; then, based on the position information of each Doppler feature matrix and the corresponding distance angle matrix, the point cloud information corresponding to the overall millimeter-wave signal of each target is obtained.

The embodiment of the present application further provides a second nursing action monitoring method based on millimeter wave signals that can be executed by a computing terminal. Referring to FIG. 2 , the nursing action monitoring method based on millimeter wave signals specifically includes the following contents:

Step 210: receiving each point cloud data frame in the point cloud information sent by the millimeter wave radar in a preset time window; the point cloud information is formed by the millimeter wave radar periodically sending a millimeter wave signal of a preset frequency to the space where the user is located, and receiving the millimeter wave signal respectively after being reflected by the user to form a plurality of different target millimeter wave signals; processing each of the target millimeter wave signals based on the FFT algorithm, the DOA estimation algorithm and the CFAR algorithm, and the users include caregivers and the person being cared for.

Step 220: Determine whether the time window is a nursing window; if so, input each point cloud data frame within the nursing window into a pre-trained deep learning model, and output the corresponding nursing action result.

Specifically, the computing terminal receives each point cloud data frame in the point cloud information sent by the millimeter wave radar in a preset time window;

Determine whether the time window is a nursing window; if so, input each point cloud data frame in the nursing window into a pre-trained deep learning model, and output the corresponding nursing action results, thereby effectively reducing the process complexity of the nursing monitoring method and effectively reducing the nursing monitoring cost, thereby effectively improving the patient experience.

Among them, the point cloud data frame is formed by the millimeter wave radar periodically sending a millimeter wave signal of a preset frequency to the space where the user is located, and the millimeter wave signals are received and reflected by the user to form multiple different target millimeter wave signals; each target millimeter wave signal is processed based on the FFT algorithm, DOA estimation algorithm and CFAR algorithm, and the users include caregivers and care recipients.

In order to effectively obtain the care window, the step 220 of determining whether the time window is a care window includes:

Determine whether the number of point cloud data frames received per second within the time window is greater than a preset number threshold, and whether the ratio of the number of point cloud data frames in a preset spatial range per second to the total number of point cloud data frames received per second is greater than a preset ratio threshold. If both are true, determine that the time window is a nursing window.

Specifically, referring to Figure 3, the computing terminal determines whether the number of point cloud data frames received per second within the time window is greater than the preset number threshold, and whether the ratio of the number of point cloud data frames in the preset spatial range per second to the total number of point cloud data frames received per second is greater than the preset ratio threshold. If both are true, the time window is determined to be a care window.

In order to further reduce the process complexity of the nursing monitoring method and effectively reduce the nursing monitoring cost, the step 220 inputs each point cloud data frame in the nursing window into a pre-trained deep learning model, and outputs the corresponding nursing action results, including:

Each point cloud data frame in the care window is input into the convolutional neural network, and the multi-dimensional features corresponding to each point cloud data frame are extracted, including the position of the point cloud, Doppler velocity and signal strength.

Input each of the multi-dimensional features into the recurrent neural network in chronological order, extract the correlation information of each of the multi-dimensional features in the time dimension, and output a nursing action feature matrix, which includes multiple types of nursing actions and multiple nursing actions corresponding to each type.

The nursing action result is obtained based on the nursing action feature matrix and the preset nursing action label.

Specifically, referring to FIG3, the computing terminal first inputs each point cloud data frame in the nursing window (including spatial information, i.e., X, Y, Z coordinates, Doppler information, and signal strength information) into a convolutional neural network (such as a ResNet network, using only the first three layers of the network) in units of frames, and extracts the multi-dimensional features related to the nursing action corresponding to each point cloud data frame. Then, each multi-dimensional feature is sequentially input into a recurrent neural network (such as an LSTM network, with 1 layer and 128 hidden layer nodes) in chronological order, extracts the association information of each multi-dimensional feature in the time dimension, and outputs the nursing action feature matrix of the continuous frame sequence of the millimeter wave point cloud. Finally, based on the correspondence between the sequence number of the normalized probability maximum value in each row of the nursing action feature matrix and the preset nursing action label (serial number), the type of nursing action is obtained, and the nursing action is saved in the local system, thereby further reducing the process complexity of the nursing monitoring method and effectively reducing the cost of nursing monitoring.

In summary, the present application provides a method for monitoring nursing actions based on millimeter wave signals, the method comprising: periodically sending millimeter wave signals of a preset frequency to the space where the user is located; receiving the millimeter wave signals respectively and forming a plurality of different target millimeter wave signals after being reflected by the user; processing each target millimeter wave signal based on the FFT algorithm, the DOA estimation algorithm and the CFAR algorithm to obtain the point cloud information corresponding to each target millimeter wave signal as a whole; sending each point cloud data frame to the computing terminal, so that the computing terminal receives a plurality of point cloud data frames in a preset time window, and determines whether the time window is a nursing window, and if so, inputs each point cloud data frame in the nursing window into a pre-trained deep learning model, and outputs the corresponding nursing action result. The present application can effectively reduce the process complexity of the nursing monitoring method, and effectively reduce the nursing monitoring cost, thereby effectively improving the patient experience.

The embodiment of the present application also provides an electronic device, such as a central server, which may include a processor, a memory, a receiver and a transmitter, wherein the processor is used to execute the second nursing action monitoring method based on millimeter wave signals mentioned in the above embodiment, wherein the processor and the memory may be connected via a bus or other means, such as by bus connection. The receiver may be connected to the processor and the memory via wired or wireless means.

The processor may be a central processing unit (CPU). The processor may also be other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, or a combination of the above chips.

As a non-transient computer-readable storage medium, the memory can be used to store non-transient software programs, non-transient computer executable programs and modules, such as the program instructions/modules corresponding to the second nursing action monitoring method based on millimeter wave signals in the embodiment of the present application. The processor executes various functional applications and data processing of the processor by running the non-transient software programs, instructions and modules stored in the memory, that is, the second nursing action monitoring method based on millimeter wave signals in the above method embodiment is implemented.

The memory may include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application required by at least one function; the data storage area may store data created by the processor, etc. In addition, the memory may include a high-speed random access memory, and may also include a non-volatile memory, such as at least one disk storage device, a flash memory device, or other non-volatile solid-state storage device. In some embodiments, the memory may optionally include a memory remotely arranged relative to the processor, and these remote memories may be connected to the processor via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

The one or more modules are stored in the memory, and when executed by the processor, perform the second nursing action monitoring method based on millimeter wave signals in the embodiment.

In some embodiments of the present application, the user equipment may include a processor, a memory, and a transceiver unit, which may include a receiver and a transmitter. The processor, memory, receiver, and transmitter may be connected through a bus system. The memory is used to store computer instructions, and the processor is used to execute the computer instructions stored in the memory to control the transceiver unit to send and receive signals.

As an implementation method, the functions of the receiver and the transmitter in the present application can be considered to be implemented through a transceiver circuit or a dedicated chip for transceiver, and the processor can be considered to be implemented through a dedicated processing chip, a processing circuit or a general chip.

As another implementation method, it is possible to use a general-purpose computer to implement the server provided in the embodiment of the present application, that is, to store the program code for implementing the functions of the processor, receiver, and transmitter in a memory, and the general-purpose processor implements the functions of the processor, receiver, and transmitter by executing the code in the memory.

The embodiment of the present application also provides a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the steps of the second nursing action monitoring method based on millimeter wave signals are implemented. The computer-readable storage medium can be a tangible storage medium, such as a random access memory (RAM), a memory, a read-only memory (ROM), an electrically programmable ROM, an electrically erasable programmable ROM, a register, a floppy disk, a hard disk, a removable storage disk, a CD-ROM, or any other form of storage medium known in the technical field.

It should be understood by those of ordinary skill in the art that the exemplary components, systems and methods described in conjunction with the embodiments disclosed herein can be implemented in hardware, software or a combination of the two. Whether it is performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application. When implemented in hardware, it can be, for example, an electronic circuit, an application-specific integrated circuit (ASIC), appropriate firmware, a plug-in, a function card, etc. When implemented in software, the elements of this application are programs or code segments used to perform the required tasks. The program or code segment can be stored in a machine-readable medium, or transmitted on a transmission medium or a communication link via a data signal carried in a carrier.

It should be clear that the present application is not limited to the specific configuration and processing described above and shown in the figures. For the sake of simplicity, a detailed description of the known method is omitted here. In the above embodiments, several specific steps are described and shown as examples. However, the method process of the present application is not limited to the specific steps described and shown, and those skilled in the art can make various changes, modifications and additions, or change the order between the steps after understanding the spirit of the present application.

In the present application, features described and/or illustrated for one embodiment may be used in the same manner or in a similar manner in one or more other embodiments, and/or combined with features of other embodiments or replace features of other embodiments.

The above description is only a preferred embodiment of the present application and is not intended to limit the present application. For those skilled in the art, the embodiments of the present application may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application shall be included in the protection scope of the present application.

Claims (10)

1. A nursing action monitoring method based on millimeter wave signals, characterized by comprising: Periodically sending millimeter wave signals of a preset frequency to the space where the user is located; Respectively receiving the millimeter wave signals reflected by users to form a plurality of different target millimeter wave signals; the users include caregivers and care recipients; Processing each of the target millimeter wave signals based on an FFT algorithm, a DOA estimation algorithm, and a CFAR algorithm to obtain point cloud information corresponding to each of the target millimeter wave signals as a whole; Each point cloud data frame in the point cloud information is sent to a computing terminal, so that the computing terminal receives multiple point cloud data frames in a preset time window, and determines whether the time window is a nursing window. If so, each point cloud data frame in the nursing window is input into a pre-trained deep learning model, and the corresponding nursing action result is output. 2. The nursing action monitoring method based on millimeter wave signals according to claim 1 is characterized in that the processing of each of the target millimeter wave signals based on the FFT algorithm, the DOA estimation algorithm and the CFAR algorithm to obtain the point cloud information corresponding to each of the target millimeter wave signals as a whole includes: Performing FFT calculations on the frame length dimensions of each of the target millimeter wave signals to obtain Doppler characteristic matrices and distance characteristic matrices corresponding to each of the target millimeter wave signals; Based on the DOA estimation algorithm and each of the target millimeter wave signals, a distance angle matrix corresponding to each of the target millimeter wave signals as a whole is obtained; Based on the CFAR target detection algorithm, each of the Doppler feature matrices and the corresponding distance angle matrix are processed respectively to obtain the point cloud information corresponding to the overall millimeter wave signal of each target. 3. The nursing action monitoring method based on millimeter wave signals according to claim 2 is characterized in that the distance angle matrix corresponding to each target millimeter wave signal as a whole is obtained based on the DOA estimation algorithm and each target millimeter wave signal, comprising: Obtaining a conversion coefficient matrix corresponding to each of the receiving antennas based on the arrangement of the receiving antennas corresponding to each of the target millimeter wave signals; Each of the conversion coefficient matrices is multiplied by its corresponding distance feature matrix and then processed using a DOA estimation algorithm to obtain the distance angle matrix. 4. The nursing action monitoring method based on millimeter wave signals according to claim 2 is characterized in that the CFAR target detection algorithm is used to process each of the Doppler feature matrices and the corresponding distance angle matrices respectively to obtain point cloud information corresponding to each target millimeter wave signal as a whole, including: Calculate the position information of the weighted distance angle matrix based on the CFAR target detection algorithm; Based on each of the Doppler characteristic matrices and the position information, point cloud information corresponding to each target millimeter wave signal as a whole is obtained. 5. A nursing action monitoring method based on millimeter wave signals, characterized by comprising: Receiving each point cloud data frame in the point cloud information sent by the millimeter wave radar in a preset time window; the point cloud information is formed by the millimeter wave radar periodically sending a millimeter wave signal of a preset frequency to the space where the user is located, and receiving the millimeter wave signal respectively after being reflected by the user to form a plurality of different target millimeter wave signals; processing each of the target millimeter wave signals based on the FFT algorithm, the DOA estimation algorithm and the CFAR algorithm to obtain the user, wherein the user includes a caregiver and a person being cared for; Determine whether the time window is a nursing window; if so, input each point cloud data frame within the nursing window into a pre-trained deep learning model, and output the corresponding nursing action result. 6. The nursing action monitoring method based on millimeter wave signals according to claim 5, characterized in that the step of determining whether the time window is a nursing window comprises: Determine whether the number of point cloud data frames received per second within the time window is greater than a preset number threshold, and whether the ratio of the number of point cloud data frames in a preset spatial range per second to the total number of point cloud data frames received per second is greater than a preset ratio threshold. If both are true, determine that the time window is a nursing window. 7. The nursing action monitoring method based on millimeter wave signals according to claim 5, characterized in that each point cloud data frame in the nursing window is input into a pre-trained deep learning model, and the corresponding nursing action result is output, comprising: Input each point cloud data frame in the nursing window into a convolutional neural network to extract multi-dimensional features corresponding to each point cloud data frame; Input each of the multi-dimensional features into a recurrent neural network in chronological order, extract the correlation information of each of the multi-dimensional features in the time dimension, and output a nursing action feature matrix; The nursing action result is obtained based on the nursing action feature matrix and the preset nursing action label. 8. An electronic device, characterized in that, if the electronic device is a millimeter wave radar, it is used to implement the nursing action monitoring method based on millimeter wave signals as described in any one of claims 1 to 4; If the electronic device is a computing terminal, the computing terminal includes a memory, a processor, and a computer program stored in the memory and executable on the processor, and when the processor executes the computer program, the nursing action monitoring method based on millimeter wave signals as described in any one of claims 5 to 7 is implemented. 9. A computer-readable storage medium having a computer program stored thereon, wherein when the computer program is executed by a processor, the method for monitoring nursing actions based on millimeter wave signals as described in any one of claims 5 to 7 is implemented. 10. A computer program product, comprising a computer program, characterized in that when the computer program is executed by a processor, the nursing action monitoring method based on millimeter wave signals as described in any one of claims 5 to 7 is implemented.