Health monitoring method, apparatus and system

Abstract

Embodiments of the present specification provide a health monitoring method, device and system. The method comprises: transmitting a detection signal to a chest position of a target user through a radar, and receiving a reflected echo signal of the detection signal reflected by the chest position through the radar; performing health monitoring on the target user based on the detection signal and the echo signal to obtain health monitoring data; determining target phase change information of the echo signal compared with the detection signal in at least part of the period during the health monitoring, and performing user identification based on the target phase change information to determine a user identifier of the target user, and then associating and outputting the user identifier of the target user with the health monitoring data. The above scheme can continuously identify the user identity and associate and output the health monitoring data, thereby improving the efficiency and reliability of health monitoring.

Description

Technical Field

[0001] This specification relates to the field of healthcare, and in particular to a health monitoring method, device, and system. Background Technology

[0002] Currently, health monitoring technology is widely used in various scenarios such as homes, medical institutions, and gyms. In these scenarios, health monitoring systems are typically shared by multiple users, meaning multiple users take turns using the system. If the health monitoring data from multiple users is mixed up, it could lead to serious medical accidents, such as misdiagnosis or inappropriate treatment. To avoid these problems, before each user undergoes health monitoring, the user or staff usually needs to manually enter the user's identity information into the health monitoring system so that the system can recognize the subsequently collected health monitoring data as that user's data.

[0003] However, the above methods require manual information entry before each health monitoring session, resulting in low efficiency. Furthermore, these methods essentially only verify user identity before monitoring; if a user changes during the monitoring process, it can lead to data confusion between different users.

[0004] The information in the background section is merely information known only to the inventor and does not imply that such information had entered the public domain before the date of this application, nor does it imply that it can be considered prior art in this disclosure. Summary of the Invention

[0005] This specification provides a health monitoring method, device, and system that continuously identifies user identifiers and associates user identifiers with health monitoring data during the health monitoring process, thereby improving the efficiency of health monitoring and preventing confusion between health monitoring data from different users.

[0006] In a first aspect, this specification provides a health monitoring method, comprising: transmitting a detection signal to the chest cavity location of a target user via radar, and receiving an echo signal formed by the reflection of the detection signal at the chest cavity location via the radar; performing health monitoring on the target user based on the detection signal and the echo signal to obtain health monitoring data; determining target phase change information of the echo signal relative to the detection signal during at least a portion of the health monitoring process, and performing user identification based on the target phase change information to determine the user identifier of the target user, wherein the target phase change information includes at least a phase change caused by physiological activity within the chest cavity; and associating and outputting the user identifier of the target user with the health monitoring data.

[0007] In some embodiments, determining the target phase change information of the echo signal relative to the probe signal includes: performing a mixing process on the probe signal and the echo signal to obtain an intermediate frequency signal; determining the co-directional component and the quadrature component in the intermediate frequency signal; and obtaining the target phase change information by performing an arctangent operation on the co-directional component and the quadrature component.

[0008] In some embodiments, obtaining the target phase change information by performing an arctangent operation on the co-directional component and the quadrature component includes: performing an arctangent operation on the co-directional component and the quadrature component to obtain initial phase change information; and preprocessing the initial phase change information to remove phase changes caused by the target user's limb movements to obtain the target phase change information.

[0009] In some embodiments, the initial phase change information represents the phase value at different times. The preprocessing of the initial phase change information to remove phase changes caused by the target user's limb movements to obtain the target phase change information includes: marking the intervals in the initial phase change information where the phase change value exceeds a preset value to obtain multiple marked intervals; for any marked interval among the multiple marked intervals, if the duration of the marked interval is less than a preset duration, then the information in the initial phase change information located within the marked interval is deleted.

[0010] In some embodiments, the step of identifying the user based on the target phase change information to determine the user identifier of the target user includes: extracting features from the target phase change information to obtain target phase change features; and matching the target phase change features with the phase change features of different users stored in the database to determine the user identifier of the target user.

[0011] In some embodiments, the step of identifying the user based on the target phase change information to determine the user identifier of the target user includes: inputting the target phase change information into a pre-trained user identification model, so as to obtain the user identifier of the target user by performing user identification based on the target phase change information through the user identification model, wherein the user identification model is trained using sample phase change information corresponding to multiple sample users and is trained to have the ability to identify users.

[0012] In some embodiments, the user identification model is trained as follows: A sample dataset is obtained, comprising sample phase change information corresponding to multiple sample users and the real user identifiers of the multiple sample users; the sample phase change information corresponding to the multiple sample users is input into the user identification model to perform user identification on the multiple sample users, thereby obtaining predicted user identifiers for the multiple sample users; the user identification model is iteratively trained multiple times with the training objective of minimizing the difference between the predicted user identifiers and the real user identifiers of the multiple sample users, to obtain the trained user identification model.

[0013] In some embodiments, the sample phase change information corresponding to each sample user is obtained by: transmitting a sample detection signal to the chest cavity location of the sample user via radar, and receiving the sample echo signal formed by the reflection of the sample detection signal by the chest cavity location via radar; and obtaining the sample phase change information based on the sample echo signal and the sample detection signal.

[0014] In some embodiments, the step of performing health monitoring on the target user based on the detection signal and the echo signal to obtain health monitoring data includes: determining M monitoring items to be monitored, and the signal difference dimension of interest for each monitoring item, where M is an integer greater than or equal to 1; for each of the M monitoring items, obtaining the difference information between the echo signal and the detection signal on the signal difference dimension of interest for the monitoring item, and performing feature extraction on the difference information to obtain the monitoring data corresponding to the monitoring item; and summarizing the monitoring data corresponding to each of the M detection items to obtain the health monitoring data of the target user.

[0015] In some embodiments, the health monitoring data includes at least one of the following: respiratory rate, respiratory depth, heart rate, and heart rate variability.

[0016] In some embodiments, the method further includes: during the health monitoring process, identifying the sleep state of the target user, the sleep state including one of deep sleep, light sleep, and wakefulness; the at least part of the time period includes the time period during which the target user is in deep sleep.

[0017] In some embodiments, the at least part of the time period includes a plurality of sub-time periods that are evenly distributed at preset intervals during the health monitoring process.

[0018] In some embodiments, the at least partial time period includes a first sub-time period starting from the start time of the health monitoring process.

[0019] In some embodiments, the physiological activities within the thoracic cavity include at least one of the following: heartbeat, breathing.

[0020] In some embodiments, the radar is a millimeter-wave radar, and the detection signal is a frequency-modulated continuous wave signal.

[0021] Secondly, this specification also provides a health monitoring device, comprising: at least one storage medium storing at least one instruction set for performing health monitoring; and at least one processor communicatively connected to the at least one storage medium, wherein, when the health monitoring device is running, the at least one processor reads the at least one instruction set and executes the health monitoring method described in any one of the first aspects according to the instructions of the at least one instruction set.

[0022] Thirdly, this specification also provides a health monitoring system, comprising: a radar that, when in operation, transmits a detection signal toward the chest cavity of a target user and receives an echo signal formed by the reflection of the detection signal at the chest cavity; and a health monitoring device that is communicatively connected to the radar and configured to perform the health monitoring method described in any one of the first aspects above.

[0023] In some embodiments, the radar is a millimeter-wave radar, and the detection signal is a frequency-modulated continuous wave signal.

[0024] As can be seen from the above technical solutions, in the health monitoring method, device, and system provided in this specification, the health monitoring device 400 can transmit a detection signal to the chest cavity location of the target user via radar, and receive the echo signal formed by the reflection of the detection signal by the chest cavity location via radar; based on the detection signal and the echo signal, health monitoring is performed on the target user to obtain health monitoring data; during at least a portion of the health monitoring process, the target phase change information of the echo signal relative to the detection signal is determined, and user identification is performed based on the target phase change information, and the user identifier of the target user is associated with the health monitoring data and output. Therefore, the above solution can automatically identify the user identifier of the target user based on the detection signal and the echo signal during the health monitoring process, thus eliminating the need for manual entry of relevant information before health monitoring, improving the efficiency of health monitoring, and reducing human error. Furthermore, the above solution can continuously identify the user during at least a portion of the health monitoring process and associate the user identifier with the health monitoring data, thereby effectively avoiding confusion of health monitoring data from different users.

[0025] Other functions of the health monitoring methods, devices, and systems provided in this specification will be partially listed in the following description. The inventive aspects of the health monitoring methods, devices, and systems provided in this specification can be fully understood through practice or use of the methods, devices, and combinations described in the detailed examples below. Attached Figure Description

[0026] To more clearly illustrate the technical solutions in the embodiments of this specification, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of this specification. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0027] Figure 1 A schematic diagram of a health monitoring scenario provided according to embodiments of this specification is shown;

[0028] Figure 2 A hardware schematic diagram of a health monitoring device provided according to an embodiment of this specification is shown;

[0029] Figure 3 A flowchart of a health monitoring method provided according to an embodiment of this specification is shown;

[0030] Figure 4A A schematic diagram of a frequency-modulated continuous wave signal provided according to an embodiment of this specification is shown;

[0031] Figure 4B A schematic diagram of the detection signal, echo signal, and intermediate frequency signal provided according to embodiments of this specification is shown;

[0032] Figure 5 A schematic diagram of preprocessing initial phase change information according to an embodiment of this specification is shown;

[0033] Figure 6 A network architecture diagram of a user identification model provided according to embodiments of this specification is shown; and

[0034] Figure 7 A schematic diagram of an interactive page provided according to an embodiment of this specification is shown. Detailed Implementation

[0035] The following description provides specific application scenarios and requirements for this specification, intended to enable those skilled in the art to make and use the contents of this specification. Various partial modifications to the disclosed embodiments will be apparent to those skilled in the art, and the general principles defined herein can be applied to other embodiments and applications without departing from the spirit and scope of this specification. Therefore, this specification is not limited to the embodiments shown, but rather to the widest scope consistent with the claims.

[0036] The terminology used herein is for the purpose of describing particular exemplary embodiments only and is not restrictive. For example, unless the context clearly indicates otherwise, the singular forms “a,” “an,” and “the” used herein may also include the plural forms. When used in this specification, the terms “comprising,” “including,” and / or “containing” mean that the associated integers, steps, operations, elements, and / or components are present, but do not exclude the presence of one or more other features, integers, steps, operations, elements, components, and / or groups, or that other features, integers, steps, operations, elements, components, and / or groups may be added to the system / method.

[0037] Considering the following description, these and other features of this specification, as well as the operation and function of the related components of the structure, and the economy of assembly and manufacture of the parts, can be significantly improved. All of these form part of this specification with reference to the accompanying drawings. However, it should be clearly understood that the drawings are for illustrative and descriptive purposes only and are not intended to limit the scope of this specification. It should also be understood that the drawings are not drawn to scale.

[0038] The flowcharts used in this specification illustrate operations implemented according to some embodiments of this specification. It should be clearly understood that the operations in the flowcharts may not be implemented in a sequential order. Instead, the operations may be implemented in reverse order or simultaneously. Furthermore, one or more additional operations may be added to the flowcharts. One or more operations may be removed from the flowcharts.

[0039] As mentioned earlier, currently, user identity information needs to be manually entered before health monitoring for each user, resulting in low efficiency. Furthermore, this entry method requires data entry before each health monitoring session, and if the user changes during the monitoring process, it can lead to data confusion. This specification provides a health monitoring method that automatically identifies the target user's identity using radar-transmitted detection signals and received echo signals during health monitoring, and then associates this identity with the collected health monitoring data for output. This method eliminates the need for manual entry of user identity information before health monitoring, improving efficiency. Additionally, this method allows for continuous user identification during health monitoring, avoiding data confusion caused by personnel changes.

[0040] Before describing the specific embodiments in this specification, the application scenarios of this specification will be introduced as follows.

[0041] The technical solutions provided in this manual can be used in health monitoring scenarios. These scenarios can be any environment requiring health monitoring, such as home health monitoring, health monitoring in medical institutions (e.g., hospitals, nursing homes, rehabilitation centers), or health monitoring in gyms or sports centers.

[0042] The following is combined with Figure 1 Examples of health monitoring scenarios are provided.

[0043] Figure 1 A schematic diagram of a health monitoring scenario provided according to embodiments of this specification is shown. See also Figure 1 This scenario may include a target user 100 and a health monitoring system. The health monitoring system is used to monitor the health of the target user 100. The health monitoring system includes a radar 200 and a health monitoring device 400.

[0044] The target user 100 can be any living being, such as a human or an animal. The target user 100 can be healthy or unhealthy.

[0045] Radar 200 is an electronic device that detects targets using radio waves. In this specification, radar 200 can transmit detection signals to a target user 100 and receive the echo signals formed by the reflection of the detection signals by the target user 100, thereby monitoring the physiological activity characteristics of the target user 100. The following describes its application in conjunction with... Figure 1 Taking the monitoring of respiratory and heart rate characteristics as examples, the monitoring principle will be explained with examples.

[0046] exist Figure 1 In the application scenario shown, target user 100 is lying in bed. The target user 100's heartbeat and breathing cause the chest cavity to rise and fall. Radar 200 emits detection signals towards the target user 100's chest cavity. When these detection signals come into contact with the target user 100's chest cavity, they are reflected back. Because the chest cavity moves up and down, the echo signals reflected back by the target user 100 carry heartbeat and breathing vibration signals. Therefore, health monitoring of the target user 100 can be achieved through the detection signals and echo signals. It should be noted that this specification does not limit the type of radar 200. For example, the radar 200 mentioned above can be a lidar, millimeter-wave radar, ultrasonic radar, or other radars. It is understood that there can be 1, 2, 3...N radars, where N is an integer greater than 1. This specification does not limit the number of radars 200.

[0047] The health monitoring device 400 may be a device with certain computing capabilities. The health monitoring device 400 is communicatively connected to the radar 200. The health monitoring device 400 can obtain the detection signals emitted and the echo signals received from the radar 200. Based on the detection signals and the echo signals, the health monitoring device 400 performs certain analysis and calculations to determine the health monitoring data corresponding to the target user 100. For example, the health monitoring device 400 can obtain the health monitoring data of the target user 100 by utilizing the frequency change and / or phase change of the echo signal compared to the detection signal.

[0048] Furthermore, each user typically possesses unique physiological activity characteristics, which vary among different users. The phase change information between the echo signal and the probe signal includes at least the phase change caused by physiological activity within the chest cavity. Therefore, during at least a portion of the health monitoring process for the target user 100, the health monitoring device 400 can identify the target user 100 based on the phase change information between the echo signal and the probe signal to obtain the user identifier of the target user 100. In this way, the health monitoring device 400 can automatically identify the user identifier of the target user 100 during health monitoring, eliminating the need for manual entry of relevant information before health monitoring and improving the efficiency of health monitoring. Furthermore, the health monitoring device 400 can continuously identify users during health monitoring and associate the identified user identifier with the collected health monitoring data for output. Thus, even if a user changes during monitoring, the health monitoring device 400 can promptly detect the change and automatically associate the changed user identifier with the health monitoring data for output, thereby avoiding confusion between health monitoring data from different users.

[0049] It should be noted that in practical applications, the radar 200 and the health monitoring device 400 can be deployed in various ways, and this specification does not limit this. For example, in some embodiments, the health monitoring device 400 and the radar 200 can be independent physical devices that can communicate with each other via wired or wireless means. In this case, the health monitoring device 400 can obtain the detection signal and the echo signal from the radar 200 through the aforementioned communication connection. In some embodiments, the health monitoring device 400 and the radar 200 can be integrated into the same physical device. For example, the health monitoring device 400 can correspond to the computing module in the radar 200, and the two can be connected via a communication bus inside the radar 200. In this case, the health monitoring device 400 can obtain the detection signal and the echo signal from the radar 200 through the communication bus.

[0050] In some embodiments, the health monitoring device 400 may further include a display screen, or the health monitoring device 400 may be communicatively connected to an external display device. After the health monitoring device 400 obtains the user identifier and health monitoring data of the target user 100, it can display the user identifier and health monitoring data in association through the display screen or display device. In some embodiments, the health monitoring device 400 may also assess the health status, sleep status, etc. of the target user 100 based on the health monitoring data, and obtain assessment results. Furthermore, the health monitoring device 400 may also formulate a reasonable health improvement plan for the target user 100 based on the above assessment results.

[0051] Figure 2 A hardware schematic diagram of a health monitoring device 400 provided according to an embodiment of this specification is shown. The health monitoring device 400 can perform the health monitoring methods provided in this specification.

[0052] like Figure 2 As shown, the health monitoring device 400 may include one or more of the following components: a processor 410, a memory 420, an input device 430, an output device 440, and a bus 450. The processor 410, memory 420, input device 430, and output device 440 may be connected to each other via the bus 450.

[0053] Processor 410 may include one or more processing cores. Processor 410 connects to various parts within the health monitoring device 400 using various interfaces and lines, and executes the health monitoring methods described herein by running or executing instructions, programs, code sets, or instruction sets stored in memory 420, and by calling data stored in memory 420. In some embodiments, processor 410 may be implemented using at least one hardware form of digital signal processing (DSP), field-programmable gate array (FPGA), or programmable logic array (PLA). Processor 410 may integrate one or more of a central processing unit (CPU), a graphics processing unit (GPU), and a modem. The CPU primarily handles the operating system, user interface, and applications; the GPU is responsible for rendering and drawing the displayed content; and the modem handles wireless communication. It is understood that the modem may also not be integrated into processor 410, but may be implemented separately using a communication chip.

[0054] The memory 420 may include random access memory (RAM) or read-only memory (ROM). Optionally, the memory 420 may include a non-transitory computer-readable storage medium. The memory 420 may be used to store instructions, programs, code, code sets, or instruction sets. The memory 420 may include a program storage area and a data storage area, wherein the program storage area may store instructions for implementing an operating system, instructions for implementing at least one function (e.g., touch function, sound playback function, image playback function, etc.), instructions for implementing the various method embodiments described below, etc. The operating system may be any operating system.

[0055] Input device 430 is used to receive input instructions or data. Input device 430 includes, but is not limited to, a keyboard, mouse, camera, microphone, or touch device. Output device 440 is used to output instructions or data, and output device 440 includes, but is not limited to, display devices and speakers. In one example, input device 430 and output device 440 can be combined, that is, input device 430 and output device 440 can be designed as the same physical device or tightly integrated together.

[0056] In addition, those skilled in the art will understand that the hardware structure of the health monitoring device 400 shown in the above figures does not constitute a limitation on the health monitoring device 400. The health monitoring device 400 may include more or fewer components than shown, or combine certain components, or have different component arrangements. For example, the health monitoring device 400 may also include radio frequency circuits, input units, sensors, audio circuits, a Wireless Fidelity (WiFi) module, a power supply, a Bluetooth module, etc., which will not be described in detail here.

[0057] Figure 3 A flowchart of a health monitoring method P500 according to an embodiment of this specification is shown. As previously described, the health monitoring device 400 can execute the health monitoring method P500 provided in the embodiment of this specification. Specifically, the processor 210 in the health monitoring device 400 can read the instruction set stored in its local storage medium, and then execute the health monitoring method P500 of the embodiment of this specification according to the instructions in the instruction set. Steps S510 to S540 of the health monitoring method P500 will now be described in detail with reference to the accompanying drawings.

[0058] S510: Transmits a detection signal to the chest cavity location of the target user via radar, and receives the echo signal formed by the reflection of the detection signal at the chest cavity location via the radar.

[0059] For example, combining Figure 1 The target user can lie in bed. The radar can be positioned near the bed so that it can transmit a detection signal towards the target user's chest area. For example, the radar can be mounted on the ceiling above the bed, on the headboard, or on a wall near the bed. Of course, the radar can also be positioned in other suitable locations; this manual does not limit the radar's placement.

[0060] The target user can be any user currently undergoing health monitoring. During the health monitoring process, the target user's posture can be lying down, sitting, standing, or squatting; there are no restrictions. The target user needs to remain still during the monitoring process to avoid significant physical movements that could affect the health monitoring results.

[0061] The target user's chest cavity is located within the radar's detection path. The radar can monitor the target user's chest cavity position and obtain monitoring data through changes in its position. The radar monitoring process is as follows: The radar can transmit a detection signal to the target user and receive the echo signal formed by the reflection of the detection signal by the chest cavity. The target user's chest cavity contains physiological organs such as the heart and lungs, therefore, physiological activities occur within the chest cavity. These physiological activities include, but are not limited to, heartbeat and breathing. These physiological activities cause the chest cavity to rise and fall. When the detection signal comes into contact with the target user's chest cavity, it is reflected, forming an echo signal. This echo signal carries relevant information about the physiological activities within the chest cavity.

[0062] In some embodiments, the radar can continuously monitor the target user. That is, during health monitoring of the target user, the radar can continuously emit detection signals towards the target user's chest cavity and receive the echo signals formed by the reflection of the detection signals from the chest cavity. For example, assuming the monitoring starts at 10 PM and ends at 8 AM, the radar can continuously emit detection signals throughout the entire period from 10 PM to 8 AM to achieve continuous health monitoring. Through continuous monitoring, staff can obtain full-time health monitoring data of the target user throughout the monitoring process. This data reflects the target user's physiological activities throughout the entire period, facilitating a more accurate assessment of the target user's health status.

[0063] In some embodiments, the radar can perform periodic monitoring of the target user. That is, if the health monitoring process of the target user is divided into multiple sub-segments, the radar can continuously transmit detection signals during a portion of these sub-segments and receive the echo signals formed by the reflection of the detection signals from the chest cavity. For example, assuming the monitoring starts at 10 PM and ends at 8 AM, and each hour is divided into a sub-segment, the complete health monitoring process can be divided into 10 sub-segments. In this case, the radar can continuously transmit detection signals during the 1st, 3rd, 5th, 7th, and 9th sub-segments to achieve periodic monitoring. Periodic monitoring reduces radar operating losses and saves costs.

[0064] In some embodiments, the radar can be a millimeter-wave radar, i.e., a radar with electromagnetic wave wavelengths of 1 to 10 millimeters. Millimeter-wave radar lies in the wavelength range where microwaves and far-infrared waves overlap, thus possessing characteristics of both wavelengths. According to wave propagation theory, higher frequency and shorter wavelength result in higher resolution and stronger penetration, but also greater loss during propagation and shorter transmission distance. Conversely, lower frequency and longer wavelength result in stronger diffraction and longer transmission distance. Therefore, compared to microwaves, millimeter waves offer higher resolution, better directivity, stronger anti-interference capabilities, and better detection performance. Compared to infrared, millimeter waves experience less atmospheric attenuation, have better penetration through smoke and dust, and are less affected by weather conditions. Therefore, when radar 200 employs millimeter-wave radar, the detection accuracy of vital signs can be improved.

[0065] In some embodiments, the detection signal emitted by the radar can be a frequency-modulated continuous wave signal. That is, the detection signal is a continuous wave whose frequency varies linearly with time. For example, Figure 4A A schematic diagram of a frequency-modulated continuous wave signal provided according to an embodiment of this specification is shown. Figure 4A As shown, the horizontal axis represents time t, and the vertical axis represents frequency f. The radar can linearly increase from the starting frequency f0 to the ending frequency f1 within a complete frequency modulation cycle. In the next frequency modulation cycle, the radar again linearly increases from the starting frequency f0 to the ending frequency f1, and so on.

[0066] In S510, the radar can transmit a detection signal towards the chest cavity of the target user under the control of the health monitoring device, or the radar can transmit a detection signal towards the chest cavity of the target user independently. The radar can send the transmitted detection signal and the received echo signal to the health monitoring device, so that the health monitoring device can perform subsequent steps S520 to S530 based on the detection signal and echo signal.

[0067] S520: Based on the detection signal and the echo signal, perform health monitoring on the target user to obtain health monitoring data.

[0068] As mentioned earlier, physiological activities such as breathing and heartbeat occur within the target user's chest cavity. Therefore, the echo signal received by the radar will differ from the emitted detection signal, generating discrepancies. The health monitoring device 400 processes and analyzes these discrepancies to obtain health monitoring data.

[0069] Health monitoring data refers to a series of data collected through a health monitoring system to characterize the physiological and health status of a target user. Health monitoring data can assist staff in accurately assessing the target user's health condition. In this manual, health monitoring data may include, but is not limited to, respiratory rate, respiratory depth, heart rate, heart rate variability, and blood oxygen saturation.

[0070] The health monitoring device 400 can monitor the health of a target user based on the difference information between the probe signal and the echo signal. The difference information that the health monitoring device 400 needs to extract may differ depending on the type of health monitoring data. For example, for respiratory rate and respiratory depth, the health monitoring device 400 needs to extract the phase change of the echo signal relative to the probe signal. As another example, for heart rate variability, the health monitoring device 400 needs to extract the time interval between two consecutive phase changes of the echo signal relative to the probe signal.

[0071] In some embodiments, to obtain health monitoring data, the health monitoring device 400 can determine M monitoring items to be monitored, and the signal difference dimension of interest for each monitoring item, where M is an integer greater than or equal to 1. For each monitoring item, based on the signal difference dimension of interest for that monitoring item, the difference information between the echo signal and the probe signal in that signal difference dimension is obtained, and then feature extraction is performed on the difference information to obtain the monitoring data corresponding to that monitoring item. The health monitoring device 400 summarizes the monitoring data corresponding to each of the M monitoring items to obtain the health monitoring data of the target user.

[0072] Assuming that the dimension of difference that monitoring item A focuses on is dimension 1, this means that the health monitoring device needs to obtain the monitoring data for monitoring item A based on the difference information between the echo signal and the detection signal in dimension 1. The dimension of difference that each monitoring item focuses on can be preset. For example, by analyzing the physiological activities of a large number of sample users, the dimension of difference that needs to be focused on for different monitoring items can be determined and stored. When monitoring a certain item is required, the dimension of difference that needs to be focused on for that monitoring item is retrieved from the pre-stored data. It should be noted that this specification does not limit the dimension of difference that needs to be focused on for each monitoring item.

[0073] The M monitoring items mentioned above can be those specified by the target user or staff, or items supported by the health monitoring system. These M monitoring items may include, but are not limited to: respiratory rate, respiratory depth, heart rate, heart rate variability, and blood oxygen saturation. The following example illustrates how to obtain the monitoring data corresponding to each monitoring item.

[0074] Respiratory rate refers to the number of breaths a target user takes per unit of time. For respiratory rate, the health monitoring device 400 can determine the phase change information of the echo signal relative to the probe signal based on the probe signal and the echo signal. Furthermore, the health monitoring device 400 can use Fourier transform (FFT) to convert the time-domain signal of the aforementioned phase change information into a frequency-domain signal, thereby identifying the respiratory rate.

[0075] Breathing depth refers to the amount of air inhaled or exhaled by the target user with each breath. For breathing depth, the health monitoring device 400 can determine the phase change information of the echo signal relative to the probe signal based on the probe signal and the probe signal. When the target user's breathing depth is greater, the amplitude of the phase change also increases accordingly. Therefore, the health monitoring device 400 can obtain the breathing depth by analyzing the amplitude of the aforementioned phase change information.

[0076] Heart rate refers to the number of times a target user's heart beats per unit of time. For heart rate, the health monitoring device 400 can determine the phase change information of the echo signal relative to the probe signal based on the probe signal and the probe signal. The minute chest movements caused by the heartbeat result in a minute phase change in the echo signal relative to the probe signal. The health monitoring device 400 can extract the heart rate by performing a Fourier transform on the aforementioned phase change information.

[0077] Heart rate variability refers to the variation in the interval between heartbeats. For heart rate variability, the health monitoring device 400 can determine the phase change information of the echo signal relative to the probe signal based on the probe signal and the echo signal, and then calculate the time interval between adjacent phase changes based on the aforementioned phase change information, thereby extracting the heart rate variability.

[0078] It is understood that, for ease of description, the above embodiments only describe a portion of the monitoring items in health monitoring. Those skilled in the art should understand that other monitoring items not mentioned are also within the scope of protection of this specification, and will not be elaborated upon here.

[0079] S530: During at least a portion of the health monitoring process, determine the target phase change information of the echo signal relative to the detection signal, and perform user identification based on the target phase change information to determine the user identifier of the target user, wherein the target phase change information includes at least the phase change caused by physiological activity in the thoracic cavity.

[0080] In this specification, a user identifier refers to information that can uniquely represent a user. A user identifier can be a user's name, ID, phone number, identity document, etc., and this specification does not limit this specific information.

[0081] As mentioned earlier, the characteristics of physiological activities within the chest cavity (such as heartbeat and respiration) are unique for different users, exhibiting individual differences similar to fingerprints, palm prints, and faces. These characteristics are carried in the echo signal. Therefore, the health monitoring device 400 can infer the characteristics of the target user's physiological activities within the chest cavity by analyzing the differences between the echo signal and the detection signal, thereby achieving user identification. Specifically, the health monitoring device 400 can determine the target phase change information of the echo signal relative to the detection signal, and then perform user identification based on this target phase change information. It is understood that the target phase change information in this specification refers to the phase change information of the echo signal compared to the detection signal. The target phase change information includes at least the phase changes caused by the target user's physiological activities within the chest cavity, such as respiration and heartbeat.

[0082] The target phase change information of the echo signal relative to the probe signal can be determined by various methods. In some embodiments, the target phase change information of the echo signal relative to the probe signal can be determined by phase detection. Specifically, the health monitoring device 400 can obtain the target phase change information by detecting the phase change of the echo signal relative to the probe signal. In some embodiments, the target phase change information of the echo signal relative to the probe signal can be determined by Fourier transform. Specifically, the health monitoring device 400 can use Fourier transform (FFT) or other forms of Fourier transform techniques to convert the time-domain signal into a frequency-domain signal. Subsequently, the health monitoring device 400 extracts the phase change from the frequency-domain signal to obtain the target phase change information. In some embodiments, the target phase change information of the echo signal relative to the probe signal can be determined by time delay estimation. Specifically, since there is a correlation between time delay and phase change, the health monitoring device 400 can indirectly deduce the phase change by measuring the time delay of the echo signal relative to the probe signal, thereby obtaining the target phase change information. It should be noted that the above-described methods for determining the target phase change information are only one of many methods, and other methods for determining the target phase change information are also within the scope of protection of this specification.

[0083] Phase detection methods can be divided into direct phase comparison and mixing methods. If the direct phase comparison method is used, the health monitoring device 400 can obtain the phase difference between the echo signal and the detection signal by directly comparing their phases, thereby obtaining information about the target phase change.

[0084] If a mixing method is used, the health monitoring device 400 needs to perform mixing processing on the detection signal and the echo signal to obtain an intermediate frequency signal. Specifically, the local oscillator (LO) in the health monitoring device 400 generates a local oscillator signal f that is identical to the detection signal. LO The health monitoring device 400 compares the echo signal with the local oscillator signal f. LO Simultaneously input to the mixer. The echo signal and the local oscillator signal f LO The signals are mixed in a mixer to obtain a new signal containing sum and difference frequency components. The health monitoring device 400 extracts the desired intermediate frequency (IF) signal (as IF signal f) from the new signal output by the mixer using a bandpass or low-pass filter. IF express). Figure 4B A schematic diagram of the detection signal, echo signal, and intermediate frequency signal provided according to embodiments of this specification is shown. Figure 4B As shown, the intermediate frequency signal f IF It can be considered as the frequency difference between the echo signal and the probe signal.

[0085] intermediate frequency signal f IF It can be represented as a complex signal for better processing and analysis. A complex signal consists of an in-phase component (I) and a quadrature component (Q). The in-phase component I refers to the component that is in sync with the local oscillator signal f. LO The in-phase signal portion. The in-phase component I corresponds to the real part of the complex number. The quadrature component Q refers to the component that is in phase with the local oscillator signal f. LO The signal components are 90 degrees (π / 2 radians) out of phase. The quadrature component Q corresponds to the imaginary part of the complex number.

[0086] For example, the intermediate frequency signal f IF (t) can be represented as a complex signal, i.e., f IF (t) = I(t) + jQ(t), where j is the imaginary unit (j 2 =-1).

[0087] The process of determining the in-phase and quadrature components in the intermediate frequency signal is as follows: The mixer in the health monitoring device 400 can mix the echo signal with the in-phase signal cos(2πf) generated by the local oscillator LO. LO t) and the orthogonal signal sin(2πf LO The components are mixed. Then, the high-frequency components are filtered out by the low-pass filter (LPF) in the health monitoring device 400 to obtain the in-phase component I(t) and the quadrature component Q(t).

[0088] Health monitoring device 400 determines intermediate frequency signal f IFAfter obtaining the co-directional component I and the quadrature component Q, the target phase change information can be obtained by performing arctangent operation on the co-directional component I and the quadrature component Q.

[0089] For example, if the component in the same direction is denoted as I(t), the orthogonal component as Q(t), and the target phase change information as φ(t), then φ(t) = tan -1 (I(t) / Q(t)).

[0090] During health monitoring of a target user, the user's limb movements cause a phase change in the echo signal relative to the detection signal. In some embodiments, to obtain more accurate target phase change information (i.e., the target phase change information mainly includes phase changes caused by physiological activities within the chest cavity, but excludes phase changes caused by the target user's limb movements), the health monitoring device 400 can refer to the result of performing an arctangent operation on the in-phase and quadrature components as the initial phase change information. Furthermore, the health monitoring device 400 preprocesses the initial phase change information to remove phase changes caused by the target user's limb movements, thereby obtaining the target phase change information.

[0091] The initial phase change information represents the phase value at different times. In other words, the initial phase change information can be represented as a phase curve with time as the horizontal axis and phase as the vertical axis. Figure 5 A schematic diagram illustrating a preprocessing method for initial phase change information according to an embodiment of this specification is shown. Figure 5 As shown, the preprocessing process of the health monitoring device 400 for the initial phase change information can be as follows: First, the health monitoring device 400 marks the intervals in the initial phase change information where the phase change value exceeds a preset value. For example, combined with... Figure 5 Taking the interval between time t1 and t2 as an example, assuming the phase change between time t1 and time t2 is greater than a preset value, the health monitoring device can mark the interval between time t1 and time t2. In this way, the health monitoring device 400 can identify all intervals where the phase changes significantly, thus obtaining multiple marked intervals. For example, combined with... Figure 5 The resulting marked intervals can include: the interval between time t1 and t2, the interval between time t2 and t3, the interval between time t3 and t4, and the interval between time t4 and t5. Subsequently, for any marked interval among these multiple marked intervals, if the duration of the marked interval is less than a preset duration T, it is considered that the phase changes within that marked interval are too frequent or may be caused by noise (such as the target user's body movements), and the information located within that marked interval in the initial phase change information is deleted. For example, combined with... Figure 5, if t2 - t1 < T, t3 - t2 < T, t4 - t3 < T, t5 - t4 < T, then delete the phase information between time t1 and time t2, the phase information between time t2 and time t3, the phase information between time t3 and time t4, and the phase information between time t4 and time t5 from the initial phase change information.

[0092] By preprocessing the initial phase change information, abnormal phase values can be filtered out, and the influence of noise (such as the limb movements of the target user) can be reduced, so that the target phase change information mainly includes the phase changes caused by the physiological activities in the chest cavity.

[0093] In some embodiments, after the health monitoring device preprocesses the initial phase, it can also normalize the phase change information after preprocessing to obtain the target phase change information. Among them, normalization can convert the phase change information to between [0 - 1] to eliminate the dimensional difference and numerical range difference between the phase change information. The normalization process is as follows: According to the number of heart movements per minute of a normal human body being 40 - 208 times, set the sample length, and divide the phase change information after preprocessing into multiple samples. For example, assume the sample length is set to 200, that is, one sample includes 200 data points. The health monitoring device can divide the preprocessed phase change information according to the above sample length to obtain multiple samples, so as to ensure that the length of each sample meets the set standard. If the length of a certain sample is insufficient or exceeds the set length, it can be adjusted by interpolation or cropping.

[0094] Subsequently, normalize the data points in each sample. Specifically, the health monitoring device 400 can convert the data point x in each sample to the normalized x scale , and the formula is as follows:

[0095] x scale =(x - x min ) / (x max - x min )

[0096] Among them, x min represents the minimum phase value in this sample, and x max represents the maximum phase value in this sample. Through this formula, all data points x in the sample will be scaled to the range of 0 to 1.

[0097] After determining the target phase change information of the echo signal compared with the detection signal, the health monitoring device can perform user identification based on the target phase change information. The following will be described in combination with several possible implementation methods.

[0098] In some embodiments, the health monitoring device can extract features from the target phase change information to obtain target phase change features, and then match the target phase change features with the phase change features of different users stored in the database to determine the user identifier of the target user.

[0099] The target phase change characteristics can be data that reflects the phase change properties, obtained by processing and analyzing target phase change information. These characteristics may include, but are not limited to, the frequency, amplitude, duration, and trend of the phase change.

[0100] In some embodiments, when extracting features from target phase change information, various feature extraction methods can be employed, such as time-domain analysis, frequency-domain analysis, time-frequency-domain analysis, and statistical analysis. In some embodiments, a pre-trained feature extraction model can also be used when extracting features from target phase change information. For example, a pre-trained feature extraction model is deployed in a health monitoring device, and this model is trained to have the ability to extract features from phase change information. The health monitoring device inputs the target phase change information into the feature extraction model, and the feature extraction model can output the target phase change features. The aforementioned feature extraction model can be an autoencoder, convolutional neural network, recurrent neural network, etc., and this specification does not limit its application to these models.

[0101] The aforementioned database pre-stores phase change features corresponding to multiple known users, and each phase change feature corresponding to a known user is associated with its unique user identifier. The health monitoring device 400 can determine the similarity between the target phase feature and each phase change feature in the database, and identify the user identifier corresponding to the phase change feature with the highest similarity as the user identifier of the target user. Specifically, the phase change features of each known user in the database can be obtained as follows: a detection signal is emitted from a radar towards the chest cavity of the known user, and the echo signal formed by the reflection of the detection signal at the chest cavity is received. Based on the detection signal and the echo signal, the phase change information of the echo signal relative to the detection signal is determined, and feature extraction is performed on the aforementioned phase change information to obtain the phase change feature corresponding to the known user.

[0102] In some embodiments, the health monitoring device can also identify target users based on target phase change information using a pre-trained user identification model. Specifically, the health monitoring device 400 inputs the target phase change information into the pre-trained user identification model to obtain the user identifier of the target user through user identification based on the target phase change information. The user identification model is trained using sample phase change information corresponding to multiple sample users and is trained to have user identification capabilities. That is, during the training process of the user identification model, it has learned the characteristics of phase changes of multiple sample users, so that in the inference and prediction stage, the user identification model can use the knowledge and capabilities learned during the training stage to predict which sample user among the multiple sample users the currently input phase change information corresponds to.

[0103] The training process of the user identification model is described below. The training process can be performed by the health monitoring device 400 or other devices; this manual does not limit this. The following description uses the health monitoring device 400 as an example to illustrate the user identification model training process.

[0104] (1) The health monitoring device 400 obtains a sample dataset. The sample dataset includes sample phase change information corresponding to multiple sample users, as well as the real user identifiers of the multiple sample users.

[0105] The sample phase change information for each sample user can be acquired as follows: a sample detection signal is emitted from a radar towards the chest cavity of the sample user, and the radar receives the sample echo signal formed by the reflection of the sample detection signal from the chest cavity. During the radar acquisition process, the sample user needs to remain still (e.g., lying in bed) and expose the chest cavity to the radar's detection path. Subsequently, the health monitoring device 400 obtains the sample phase change information based on the sample echo signal and the sample detection signal. It should be noted that the method of obtaining the sample phase change information is similar to the method of obtaining the target phase change information described above, and will not be repeated here.

[0106] After obtaining the sample phase change information for each sample user, the sample phase change information can be preprocessed and normalized as described above to finally generate multiple samples. Each sample has a length of 200, meaning each sample includes the phase values ​​corresponding to 200 data points. The dimension of each sample can be represented as 1*200.

[0107] (2) Input the sample phase change information corresponding to the multiple sample users into the user identification model, so as to identify the multiple sample users through the user identification model and obtain the predicted user identifier of the multiple sample users.

[0108] Specifically, for each sample user, the sample phase change information corresponding to that sample user is input into the user identification model. The user identification model can predict the probability that the sample phase change information corresponds to the multiple sample users respectively, and use the user identifier of the sample user with the highest probability as the predicted user identifier.

[0109] The user identification process will be illustrated below with an example of a specific network structure for a user identification model.

[0110] In this specification, the user identification model may include, but is not limited to, Convolutional Neural Networks (CNN), Recurrent Neural Networks (RNN), Long Short-Term Memory (LSTM), Autoencoder, Siamese network, Transformer network, etc.

[0111] It should be noted that this specification does not impose restrictions on the network structure of the user identification model. As an example, Figure 6 A network architecture diagram of a user identification model provided according to an embodiment of this specification is shown. Figure 6 As shown, the user recognition model may include K feature processing units and fully connected layers. The K feature processing units are connected sequentially, and the Kth fully connected layer is connected to other fully connected layers. Each feature processing unit includes: a first convolutional layer, a second convolutional layer, a batch normalization layer, and a max pooling layer.

[0112] The first and second convolutional layers are configured to extract local features with phase change information using convolutional kernels, thereby increasing feature dimensionality. The batch normalization layer is configured to normalize the convolutional features, accelerating training and improving the model's generalization ability. The max pooling layer is configured to downsample the normalized features, reducing the number of data points in the samples. Each feature processing unit has two convolutional layers (i.e., the first and second convolutional layers) before the batch normalization and max pooling layers, enhancing the model's non-linear expressive power, promoting the extraction of hierarchical features, and further improving training efficiency and generalization ability by combining batch normalization and max pooling.

[0113] For example, combining Figure 6Assume the input data of the user recognition model has a data dimension of 128@1*200. Here, 128 represents the number of samples input to the user recognition model in the same batch, and 1*200 represents the data dimension of each sample, meaning each sample includes 200 data points in the time dimension, and each data point has a feature dimension of 1. This input data is fed into the first feature processing unit and processed sequentially by a first convolutional layer (conv1d: 1*32*7), a second convolutional layer (conv1d: 32*32*7), a batch normalization layer, and a max pooling layer. The data dimension after processing by the first convolutional layer is 128@32*194. The data dimension after processing by the second convolutional layer is 128@32*188. The data dimension after processing by the batch normalization layer and the max pooling layer is 128@32*37. Therefore, after the first feature processing unit, the feature dimension of each data point increases from 1 to 32. It should be noted that the structure of the second to Kth feature processing units is similar to that of the first feature processing unit, except that the parameters of each layer are different. This specification will not elaborate on these differences.

[0114] In the K feature processing units, the first few units are configured to progressively increase the feature dimension of each data point, thereby increasing feature richness; the latter few units are configured to decrease the feature dimension of each data point, in order to filter out key features from the richer feature set. For example, with K=3, the first feature processing unit is configured to increase the feature dimension of each data point from 1 to 32, the second unit from 32 to 128, and the third unit from 128 to 32. During the processing of the K feature processing units, the feature dimension of each data point is first gradually increased and then gradually decreased. This allows the model to first capture the complex details and high-level features of the input data by increasing the feature dimension, and then integrate and refine these features by reducing the feature dimension, removing redundant information, thereby improving the model's expressive power and generalization performance while maintaining computational efficiency and training stability.

[0115] See also Figure 6 The fully connected layer is connected to the Kth feature processing unit and is configured to map the phase change features output by the Kth feature processing unit to N categories. N is the number of sample users. Assuming N is 5, the data dimension of the fully connected layer output is 128@5, meaning that the 128 samples in the above input data correspond to the probabilities of 5 sample users respectively. Furthermore, for each sample, the health monitoring device 400 can determine the sample user corresponding to the highest probability as the predicted user identifier corresponding to that sample.

[0116] (3) The user identification model is trained in multiple rounds of iteration with the training objective of minimizing the difference between the predicted user identifier and the real user identifier of the multiple sample users, so as to obtain the trained user identification model.

[0117] Specifically, the health monitoring device 400 can perform multiple rounds of iterative training on the user identification model. In each round of training, the health monitoring device inputs a batch of samples (e.g., 128@1*200) into the user identification model, and the user identification model predicts the predicted user identifier for each sample. Then, the health monitoring device determines the prediction loss based on the difference between the predicted user identifier and the actual user identifier for each sample, and optimizes the parameters of the user identification model with the goal of minimizing this prediction loss to gradually reduce this difference. Commonly used optimization algorithms include gradient descent and stochastic gradient descent. Through multiple rounds of iterative training, the user identification model gradually learns how to more accurately predict the user identifier corresponding to the phase change feature based on the phase change feature.

[0118] In some embodiments, the health monitoring device 400 can divide the sample dataset into three parts: a training set, a validation set, and a test set. The specific division ratio can be adjusted according to actual conditions, for example, 70% as the training set, 15% as the validation set, and 15% as the test set. The health monitoring device 400 can use the training set to optimize the model's parameters, enabling the model to continuously learn the user recognition capabilities. The health monitoring device 400 can use the validation set to evaluate model performance, fine-tune model hyperparameters, and decide whether to stop training. The health monitoring device 400 can use the test set to evaluate the model's generalization ability, i.e., to evaluate the model's performance on completely unseen data.

[0119] The above describes in detail how health monitoring devices identify users based on echo and detection signals. The following provides examples illustrating when health monitoring devices identify users based on echo and detection signals.

[0120] In some embodiments, the health monitoring device 400 can continuously perform user identification throughout the entire health monitoring process. That is, during the health monitoring process, after obtaining echo signals and detection signals at each moment, the health monitoring device determines health monitoring data based on the echo signals and detection signals, and also performs user identification based on the echo signals and detection signals to obtain a user identifier. In this way, the health monitoring device can continuously perform user identification during the health monitoring process, thereby avoiding the problem of data confusion caused by personnel changes during the monitoring.

[0121] In some embodiments, the health monitoring device can perform user identification during a portion of the health monitoring process. This portion of the time period can be any part of the health monitoring process, such as the first half, the second half, or the middle portion. Examples are provided below.

[0122] In some embodiments, the aforementioned time period may include a first sub-time period starting from the start time of the health monitoring process. For example, assuming a sub-time period lasts one hour, user identification is performed within the first hour after each user begins health monitoring. For instance, if user A's health monitoring starts at 10 PM, then between 10 PM and 11 PM, user identification is performed continuously while health monitoring is being conducted on user A. Compared to performing user identification throughout the entire time period, this method can reduce the computational load on the health monitoring device and decrease the consumption of its computing resources.

[0123] In some embodiments, the aforementioned time periods may include multiple sub-time periods evenly distributed at preset intervals during the health monitoring process. For example, assuming the health monitoring starts at 10 PM and ends at 8 AM, dividing each hour into a sub-time period, the complete health monitoring process can be divided into 10 sub-time periods. In this case, the health monitoring device can perform periodic user identification in the 1st, 3rd, 5th, 7th, and 9th sub-time periods. This method enables continuous user identification within each sub-time period, ensuring that health monitoring data from different users are not confused within that sub-time period. Furthermore, because user identification is performed periodically, compared to performing user identification throughout the entire time period, the computational load on the health monitoring device can be reduced to some extent, thus reducing the consumption of the device's computing resources.

[0124] In some embodiments, the health monitoring method provided in this specification can be applied to sleep monitoring scenarios. During health monitoring of a target user, the health monitoring device 400 can automatically identify the target user's current sleep state based on health monitoring data, such as through respiratory rate, respiratory depth, heart rate, and heart rate variability. Sleep states include deep sleep, light sleep, and wakefulness. In this case, the aforementioned time periods include the periods when the target user is in deep sleep. That is, the health monitoring device 400 can identify the target user during the periods when the target user is in deep sleep. In deep sleep, the target user's limb movements are relatively small, and the physiological activities of the chest cavity are relatively stable. By identifying the target user during the periods when the target user is in deep sleep, the health monitoring device 400 can obtain stable phase change information, thereby improving the accuracy and reliability of the user identification results.

[0125] S540: Link and output the target user's user identifier with health monitoring data.

[0126] The aforementioned methods of outputting related information may include, but are not limited to: storing related information in a database, or displaying related information on an interactive page.

[0127] Taking the association storage in the database as an example, the health monitoring device 400 can associate and store user identifiers and health monitoring data in the manner shown in Table 1.

[0128] Table 1 Health Monitoring Data Recording Table

[0129]

[0130] Taking the display on an interactive page as an example, the health monitoring device 400 can present an interactive page to the user. During health monitoring, the health monitoring device 400 can display the user's identifier and health monitoring data in real time on the interactive page. As an example, Figure 7 A schematic diagram of an interactive page provided according to an embodiment of this specification is shown. Figure 7 As shown, during the health monitoring of user A, the health monitoring device 400 displays user A's user identifier and health monitoring data in real time on the interactive page. In some embodiments, the interactive page can also display phase change information corresponding to each collection moment in real time to assist staff in analyzing the health monitoring data.

[0131] In summary, the health monitoring method, device, and system provided in this specification allow the health monitoring device 400 to transmit a detection signal to the chest cavity of a target user via radar and receive the echo signal reflected from the chest cavity via radar. Based on the detection signal and the echo signal, the device performs health monitoring on the target user to obtain health monitoring data. During at least a portion of the health monitoring process, it determines the target phase change information of the echo signal relative to the detection signal, identifies the user based on the target phase change information, and associates the target user's identifier with the health monitoring data. Therefore, the above solution can automatically identify the target user's identifier based on the detection signal and echo signal during health monitoring, eliminating the need for manual entry of relevant information before health monitoring, thus improving the efficiency of health monitoring and reducing human error. Furthermore, the above solution can continuously identify the user during at least a portion of the health monitoring process and associate the user identifier with the health monitoring data, effectively preventing confusion between health monitoring data from different users.

[0132] This specification, in another aspect, provides a non-transitory storage medium storing at least one set of executable instructions for performing health monitoring. When the executable instructions are executed by a processor, they instruct the processor to implement the steps of the health monitoring method P500 described in this specification. In some possible embodiments, various aspects of this specification can also be implemented as a program product comprising program code. When the program product is run on a health monitoring device 400, the program code causes the health monitoring device 400 to perform the steps of the health monitoring method P500 described in this specification. The program product for implementing the above method may employ a portable compact disc read-only memory (CD-ROM) containing program code and may run on the health monitoring device 400. However, the program product of this specification is not limited thereto. In this specification, a readable storage medium may be any tangible medium containing or storing a program that may be used by or in conjunction with an instruction execution system. The program product may employ any combination of one or more readable media. A readable medium may be a readable signal medium or a readable storage medium. A readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of readable storage media include: electrical connections having one or more wires, portable disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof. The computer-readable storage medium may include data signals propagated in baseband or as part of a carrier wave, carrying readable program code. Such propagated data signals may take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. A readable storage medium may also be any readable medium other than a readable storage medium that can send, propagate, or transmit programs for use by or in connection with an instruction execution system, apparatus, or device. Program code contained on a readable storage medium may be transmitted using any suitable medium, including but not limited to wireless, wired, optical fiber, RF, etc., or any suitable combination thereof. Program code for performing the operations described herein can be written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Java and C++, and conventional procedural programming languages ​​such as C or similar languages. The program code can be executed entirely on the health monitoring device 400, partially on the health monitoring device 400, as a standalone software package, partially on the health monitoring device 400 and partially on a remote computing device, or entirely on a remote computing device.

[0133] The foregoing has described specific embodiments of this specification. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recited in the claims may be performed in a different order than that shown in the embodiments and may still achieve the desired result. Furthermore, the processes depicted in the drawings do not necessarily require a specific or sequential order to achieve the desired result. In some embodiments, multitasking and parallel processing are possible or may be advantageous.

[0134] In summary, after reading this detailed disclosure, those skilled in the art will understand that the foregoing detailed disclosure is presented by way of example only and is not restrictive. Although not explicitly stated herein, those skilled in the art will understand that this specification requires various reasonable changes, improvements, and modifications to the embodiments. These changes, improvements, and modifications are intended to be made by this specification and are within the spirit and scope of the exemplary embodiments described herein.

[0135] Furthermore, certain terms in this specification have been used to describe embodiments of this specification. For example, "an embodiment," "an embodiment," and / or "some embodiments" mean that a particular feature, structure, or characteristic described in connection with that embodiment may be included in at least one embodiment of this specification. Therefore, it is to be emphasized and understood that two or more references to "an embodiment" or "an embodiment" or "alternative embodiment" in various parts of this specification do not necessarily refer to the same embodiment. Moreover, specific features, structures, or characteristics may be suitably combined in one or more embodiments of this specification.

[0136] It should be understood that in the foregoing description of the embodiments in this specification, various features are combined in a single embodiment, drawing, or description for the purpose of simplifying the description and to aid in understanding a feature. However, this does not mean that the combination of these features is necessary, and those skilled in the art, upon reading this specification, may readily identify some of the devices as separate embodiments. That is, the embodiments in this specification can also be understood as an integration of multiple secondary embodiments. And the content of each secondary embodiment is valid even if it contains fewer than all the features of a single foregoing disclosed embodiment.

[0137] Every patent, patent application, publication of a patent application, and other material such as articles, books, specifications, publications, documents, articles, etc., cited herein, except for those inconsistent with or conflicting with this document, or those having a restrictive effect on the widest scope of the claims, may be incorporated herein by reference for all purposes now or hereafter associated with this document. Furthermore, in the event of any inconsistency or conflict between the description, definition, and / or use of relevant terms in any material and the description, definition, and / or use of relevant terms in this document, the terms in this document shall prevail.

[0138] Finally, it should be understood that the embodiments disclosed herein are illustrative of the principles of the embodiments described in this specification. Other modified embodiments are also within the scope of this specification. Therefore, the embodiments disclosed in this specification are merely examples and not limitations. Those skilled in the art can implement the applications described in this specification using alternative configurations based on the embodiments in this specification. Therefore, the embodiments in this specification are not limited to the embodiments precisely described in the applications.

Claims

1. A health monitoring method, characterized in that, include: The radar transmits a detection signal toward the chest cavity of the target user and receives the echo signal formed by the reflection of the detection signal at the chest cavity location. Based on the detection signal and the echo signal, health monitoring is performed on the target user to obtain health monitoring data; During at least a portion of the health monitoring process, target phase change information of the echo signal relative to the detection signal is determined, and user identification is performed based on the target phase change information to determine the user identifier of the target user, wherein the target phase change information includes at least phase changes caused by physiological activities within the thoracic cavity; as well as The user identifier of the target user is associated with the health monitoring data and output.

2. The method according to claim 1, characterized in that, Determining the target phase change information of the echo signal relative to the detection signal includes: The detection signal and the echo signal are mixed to obtain an intermediate frequency signal; Determine the in-phase and quadrature components in the intermediate frequency signal; and The target phase change information is obtained by performing an arctangent operation on the same-direction component and the quadrature component.

3. The method according to claim 2, characterized in that, The step of obtaining the target phase change information by performing an arctangent operation on the same-direction component and the quadrature component includes: Perform arctangent operation on the in-phase component and the quadrature component to obtain initial phase change information; and The initial phase change information is preprocessed to remove phase changes caused by the target user's limb movements, thereby obtaining the target phase change information.

4. The method according to claim 3, characterized in that, The initial phase change information represents the phase value at different times. Preprocessing the initial phase change information to remove phase changes caused by the target user's limb movements, to obtain the target phase change information, includes: The intervals in the initial phase change information where the phase change value exceeds a preset value are marked to obtain multiple marked intervals; For any of the multiple marked intervals, if the duration of the marked interval is less than a preset duration, the information located within the marked interval in the initial phase change information will be deleted.

5. The method according to claim 1, characterized in that, The step of identifying the user based on the target phase change information to determine the user identifier of the target user includes: Feature extraction is performed on the target phase change information to obtain target phase change features; and The target phase change feature is matched with the phase change features of different users stored in the database to determine the user identifier of the target user.

6. The method according to claim 1, characterized in that, The step of identifying the user based on the target phase change information to determine the user identifier of the target user includes: The target phase change information is input into a pre-trained user identification model, which then uses this model to identify the target user based on the target phase change information, thereby obtaining the user identifier of the target user. The user identification model is trained using sample phase change information corresponding to multiple sample users and is trained to have the ability to identify users.

7. The method according to claim 6, characterized in that, The user identification model was trained in the following manner: Obtain a sample dataset, which includes sample phase change information corresponding to multiple sample users, and the real user identifiers of the multiple sample users; The sample phase change information corresponding to the multiple sample users is input into the user identification model, so as to perform user identification on the multiple sample users through the user identification model and obtain the predicted user identifier of the multiple sample users; The user identification model is trained through multiple rounds of iterative training with the training objective of minimizing the difference between the predicted user identifiers and the real user identifiers of the multiple sample users, so as to obtain the trained user identification model.

8. The method according to claim 7, characterized in that, The sample phase change information for each sample user is obtained in the following way: The radar transmits a sample detection signal toward the chest cavity of the sample user, and the radar receives the sample echo signal formed by the reflection of the sample detection signal at the chest cavity. Based on the sample echo signal and the sample detection signal, the sample phase change information is obtained.

9. The method according to claim 1, characterized in that, The health monitoring of the target user based on the detection signal and the echo signal, to obtain health monitoring data, includes: Determine the M monitoring items to be monitored, and the signal difference dimension of interest for each monitoring item, where M is an integer greater than or equal to 1; For each of the M monitoring items, based on the signal difference dimension of interest for the monitoring item, the difference information between the echo signal and the detected signal in that signal difference dimension is obtained, and feature extraction is performed on the difference information to obtain the monitoring data corresponding to the monitoring item; and The monitoring data corresponding to each of the M detection items are summarized to obtain the health monitoring data of the target user.

10. The method according to claim 9, characterized in that, The health monitoring data includes at least one of the following: respiratory rate, respiratory depth, heart rate, and heart rate variability.

11. The method according to claim 1, characterized in that, The method further includes: During the health monitoring process, the sleep state of the target user is identified, and the sleep state includes one of deep sleep, light sleep, and wakefulness. The at least part of the time period includes the time period during which the target user is in a deep sleep state.

12. The method according to claim 1, characterized in that, The at least part of the time period includes multiple sub-time periods that are evenly distributed at preset intervals during the health monitoring process.

13. The method according to claim 1, characterized in that, The at least part of the time period includes the first sub-time period starting from the start time of the health monitoring process.

14. The method according to claim 1, characterized in that, The physiological activities within the thoracic cavity include at least one of the following: heartbeat, breathing.

15. The method according to claim 1, characterized in that, The radar is a millimeter-wave radar, and the detection signal is a frequency-modulated continuous wave signal.

16. A health monitoring device, characterized in that, include: At least one storage medium storing at least one instruction set for health monitoring; as well as At least one processor is communicatively connected to the at least one storage medium. When the health monitoring device is running, the at least one processor reads the at least one instruction set and executes the health monitoring method according to any one of claims 1-15 according to the instructions of the at least one instruction set.

17. A health monitoring system, characterized in that, include: When the radar is in operation, it transmits a detection signal toward the chest cavity of the target user and receives the echo signal formed by the reflection of the detection signal at the chest cavity. as well as A health monitoring device, communicatively connected to the radar, and configured to perform the health monitoring method according to any one of claims 1-15.

18. The system according to claim 17, characterized in that, The radar is a millimeter-wave radar, and the detection signal is a frequency-modulated continuous wave signal.

Images