Vital sign monitoring equipment and monitoring method thereof

Abstract

The invention relates to vital sign monitoring equipment and a monitoring method thereof. The monitoring method comprises the following steps that vital sign related parameters of a user in the primary monitoring process are collected through a monitoring pad; sending the vital sign related parameters to a cloud server; after receiving the vital sign related parameters, the cloud server performs data analysis based on the vital sign related parameters to obtain a vital sign monitoring result; and the cloud server visually displays the vital sign monitoring result and feeds back the vital sign monitoring result to a preset IP terminal. On one hand, the whole monitoring process is non-contact, namely, a user does not need to wear any equipment, the use is convenient, the sleep quality of the user is not influenced, long-time continuous monitoring can be realized, and comprehensive data can be provided; and on the other hand, the sleep state of the user is analyzed in a period continuation mode, the degree of dependence on the accuracy of the data is not high, and the problem that the accuracy of subsequent algorithm analysis is finally affected due to fluctuation of the data monitored in a non-contact monitoring scene can be well solved.

Description

Technical Field

[0001] The present invention relates to the technical field related to health monitoring, and in particular to a vital sign monitoring device and a monitoring method thereof. Background Art

[0002] Home vital signs monitoring devices refer to devices used in home environments to monitor the physiological parameters of individuals or family members. The original intention of designing such devices is to improve the efficiency of health management and disease prevention, so that users can more conveniently understand their health status and seek medical treatment in a timely manner when necessary.

[0003] Existing vital signs monitoring devices often need to be worn on the human body, collect data through built-in sensors, and then use corresponding algorithms to analyze the data to obtain the corresponding. If the vital signs monitoring device is installed on the human body, it will inevitably affect the user experience. If the vital signs monitoring device is not installed on the human body, it may cause fluctuations in the monitored data and ultimately affect the accuracy of subsequent algorithm analysis. Summary of the invention

[0004] The purpose of the present invention is to solve at least one of the deficiencies of the prior art and to provide a vital sign monitoring device and a monitoring method thereof.

[0005] In order to achieve the above object, the present invention adopts the following technical solutions:

[0006] Specifically, a vital sign monitoring device and a monitoring method thereof are proposed, including the following:

[0007] The monitoring pad is used to collect the user's vital sign related parameters during a monitoring process;

[0008] Sending the vital sign related parameters to a cloud server;

[0009] After receiving the vital sign related parameters, the cloud server performs data analysis based on the vital sign related parameters to obtain vital sign monitoring results;

[0010] The cloud server visualizes the vital signs monitoring results and feeds them back to the preset IP terminal.

[0011] Furthermore, specifically, the vital signs related parameters include respiratory rate and heart rate, and the collected respiratory rate and heart rate are collected according to a preset period T, that is, the respiratory rate and heart rate sent to the cloud each time are multi-period collection data, and M real-time respiratory rate and heart rate data are collected in each period.

[0012] Further, specifically, the vital sign monitoring results are obtained by performing data analysis based on the vital sign related parameters, including:

[0013] Analyze and determine the proportion of each type of sleep state of the user based on the collected heart rate data;

[0014] Analyze and determine the user's body movement based on the collected breathing rate data;

[0015] The proportion of each type of sleep state and body movement are used as vital sign monitoring results;

[0016] The various sleep states include wakefulness, light sleep, and deep sleep.

[0017] Further, specifically, based on the collected heart rate data, the proportion of each type of sleep state of the user is analyzed and determined, including:

[0018] For the heart rate data of the i-th cycle T collected, the value range of i is 1 to the maximum cycle T, and the sampling number is assumed to be N, and its average value avg_i is calculated;

[0019] When i is 1, it is directly determined that the user is awake in the first cycle;

[0020] When i is not 1, continue the following process:

[0021] Determine whether avg_i is greater than a first threshold, if so, it is determined that the state is awake;

[0022] If it is not greater than the first threshold, all M real-time heart rate data collected in the i-1th period T are obtained;

[0023] A two-dimensional coordinate system is constructed with the acquisition time as the horizontal coordinate and the value of the heart rate data as the vertical coordinate. At this time, all M real-time heart rate data collected in the i-1th period T form M coordinate points in the two-dimensional coordinate system;

[0024] A data curve is obtained by curve fitting for the M coordinate points, and then the data curve is translated rightward along the x-axis for a period T to obtain a data discrimination curve for the i-th period T;

[0025] For all M real-time heart rate data collected in the i-th period T, calculate the minimum distance to the data discriminant curve to obtain M minimum distances, count the number of minimum distances greater than the second threshold, and then calculate the ratio Q of the number of minimum distances greater than the second threshold to M;

[0026] Determine whether the ratio Q is greater than a third threshold value. If it is greater than the third threshold value, it is determined that the heart rate fluctuation is large at this time, and it is determined that the person is in a light sleep state at this time. If it is not greater than the third threshold value, it is determined that the heart rate fluctuation is small at this time, and the person is in a deep sleep state at this time.

[0027] The corresponding sleep state of all cycles is determined in the above manner, and the number of cycles corresponding to the awake state, light sleep state and deep sleep state are counted, and then the proportion of the awake state, light sleep state and deep sleep state in this monitoring process is calculated.

[0028] Further, specifically, the user's body movement is analyzed and determined based on the collected respiratory rate data, including:

[0029] Preprocessing the collected respiratory rate data to obtain high-quality respiratory rate data;

[0030] Extracting respiratory signals from high-quality respiratory rate data to obtain respiratory signals;

[0031] Performing body motion detection on the breathing signal to obtain a body motion detection result;

[0032] The body movement detection result is input into a pre-trained machine learning model to output the type and intensity of the body movement, and the type and intensity of the body movement are the user's body movement conditions.

[0033] Further, specifically,

[0034] Respiration rate and heart rate data are collected through one or more combinations of piezoelectric sensors or micro-motion sensors.

[0035] Further, specifically, the cloud server visualizes the vital signs monitoring results and feeds them back to the preset IP terminal, including:

[0036] A corresponding IP terminal is bound to each user's registered account in advance in the cloud server. When the vital signs monitoring results are obtained, the vital signs monitoring results are generated into corresponding charts according to a preset mode, and the charts are sent to the preset IP terminal to inform the user.

[0037] The present invention also provides a vital sign monitoring device, which applies the vital sign monitoring method, comprising:

[0038] A monitoring mat and a control box thereof, wherein the monitoring mat is fixedly mounted on a hard bed board and electrically connected to the control box, the control box is connected to the mains, the monitoring mat is used to collect parameters related to the user's vital signs, and the control box is used to upload the collected relevant information of the user to a cloud server.

[0039] The beneficial effects of the present invention are:

[0040] The present invention proposes a vital signs monitoring device and a monitoring method thereof. On the one hand, the vital signs related parameters of the user's breathing rate and heart rate are obtained by installing a monitoring pad under the mattress. The whole process is non-contact, that is, the user does not need to wear any equipment. It is easy to use, will not affect the user's sleep quality, can be monitored continuously for a long time, and provide comprehensive data. On the other hand, the user's sleep state is analyzed by a continuous cycle, and the degree of dependence on the accuracy of the data is not high. It can well deal with the problem that the data monitored in the non-contact monitoring scenario fluctuates and ultimately affects the accuracy of the subsequent algorithm analysis. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] The above and other features of the present disclosure will become more apparent by describing in detail the embodiments shown in the accompanying drawings. The same reference numerals in the accompanying drawings of the present disclosure represent the same or similar elements. Obviously, the accompanying drawings described below are only some embodiments of the present disclosure. For those skilled in the art, other accompanying drawings can be obtained based on these accompanying drawings without creative work. In the accompanying drawings:

[0042] Figure 1 Shown is a schematic diagram of the installation of the vital signs monitoring device of the present invention;

[0043] Figure 2 Shown is a schematic diagram of two monitoring pads connected in series in a preferred embodiment of the present invention;

[0044] Figure 3 Shown is a flow chart of the vital signs monitoring method of the present invention. DETAILED DESCRIPTION

[0045] The following will be combined with the embodiments and drawings to clearly and completely describe the concept, specific structure and technical effects of the present invention, so as to fully understand the purpose, scheme and effect of the present invention. It should be noted that the embodiments in this application and the features in the embodiments can be combined with each other without conflict. The same reference numerals used throughout the drawings indicate the same or similar parts.

[0046] Example 1, reference Figure 3 The present invention proposes a vital sign monitoring method, comprising the following:

[0047] Step 110, collecting the user's vital sign related parameters during a monitoring process through the monitoring pad;

[0048] Step 120: Send the vital sign related parameters to the cloud server;

[0049] Step 130: After receiving the vital sign related parameters, the cloud server performs data analysis based on the vital sign related parameters to obtain vital sign monitoring results;

[0050] Step 140: The cloud server visualizes the vital sign monitoring results and feeds them back to the preset IP terminal.

[0051] In this embodiment 1, on the one hand, the user's vital sign related parameters of breathing rate and heart rate are obtained by installing a monitoring pad under the mattress. The whole process is non-contact, that is, the user does not need to wear any equipment, it is easy to use, will not affect the user's sleep quality, can be monitored continuously for a long time, and provide comprehensive data; on the other hand, the user's sleep state is analyzed by a continuous cycle, and the degree of dependence on the accuracy of the data is not high, which can well deal with the problem that the data monitored in the non-contact monitoring scenario fluctuates and ultimately affects the accuracy of the subsequent algorithm analysis.

[0052] As a preferred embodiment of the present invention, specifically, the vital signs related parameters include respiratory rate and heart rate, and the collected respiratory rate and heart rate are collected according to a preset period T, that is, the respiratory rate and heart rate sent to the cloud each time are multi-period collection data, and M real-time respiratory rate and heart rate data are collected in each period.

[0053] In this preferred embodiment, the collection of vital sign related parameters in the above manner can facilitate subsequent analysis and processing.

[0054] As a preferred embodiment of the present invention, specifically, the vital sign monitoring results are obtained by performing data analysis based on the vital sign related parameters, including:

[0055] Analyze and determine the proportion of each type of sleep state of the user based on the collected heart rate data;

[0056] Analyze and determine the user's body movement based on the collected breathing rate data;

[0057] The proportion of each type of sleep state and body movement are used as vital sign monitoring results;

[0058] The various sleep states include wakefulness, light sleep, and deep sleep.

[0059] In this preferred embodiment, by analyzing and judging the proportion of each type of sleep state of the user based on the collected heart rate data; and analyzing and judging the user's body movement based on the collected respiratory rate data, the vital signs monitoring results of the corresponding user can be accurately obtained.

[0060] As a preferred embodiment of the present invention, specifically, the proportion of various sleep states of the user is analyzed and determined based on the collected heart rate data, including:

[0061] For the heart rate data of the i-th cycle T collected, the value range of i is 1 to the maximum cycle T, and the sampling number is assumed to be N, and its average value avg_i is calculated;

[0062] When i is 1, it is directly determined that the user is awake in the first cycle;

[0063] When i is not 1, continue the following process:

[0064] Determine whether avg_i is greater than a first threshold, if so, it is determined that the state is awake;

[0065] If it is not greater than the first threshold, all M real-time heart rate data collected in the i-1th period T are obtained;

[0066] A two-dimensional coordinate system is constructed with the acquisition time as the horizontal coordinate and the value of the heart rate data as the vertical coordinate. At this time, all M real-time heart rate data collected in the i-1th period T form M coordinate points in the two-dimensional coordinate system;

[0067] A data curve is obtained by curve fitting for the M coordinate points, and then the data curve is translated rightward along the x-axis for a period T to obtain a data discrimination curve for the i-th period T;

[0068] For all M real-time heart rate data collected in the i-th period T, calculate the minimum distance to the data discriminant curve to obtain M minimum distances, count the number of minimum distances greater than the second threshold, and then calculate the ratio Q of the number of minimum distances greater than the second threshold to M;

[0069] Determine whether the ratio Q is greater than a third threshold value. If it is greater than the third threshold value, it is determined that the heart rate fluctuation is large at this time, and it is determined that the person is in a light sleep state at this time. If it is not greater than the third threshold value, it is determined that the heart rate fluctuation is small at this time, and the person is in a deep sleep state at this time.

[0070] The corresponding sleep state of all cycles is determined in the above manner, and the number of cycles corresponding to the awake state, light sleep state and deep sleep state are counted, and then the proportion of the awake state, light sleep state and deep sleep state in this monitoring process is calculated.

[0071] In this preferred embodiment, considering the different heart rate variation characteristics of people in the sleep stage in actual situations,

[0072] Awake state: When awake, the heart rate is usually high and fluctuates greatly.

[0073] Early stage of falling asleep (light sleep stage): After entering the light sleep stage, the heart rate begins to gradually decrease, but there is still a certain fluctuation.

[0074] Deep sleep (deep sleep stage): In the deep sleep stage, the heart rate drops further, with less fluctuation and is relatively stable;

[0075] The above-mentioned targeted algorithm design is firstly carried out, that is, the first threshold is determined through experiments, that is, if the mean heart rate of one cycle is above the first threshold, it proves that the user is awake at this time; if the mean heart rate of one cycle is below the first threshold, then the adjacent cycles are further judged in the above-mentioned manner whether the heart rates of adjacent continuous cycles are relatively stable; the number of points with a large distance (greater than the second threshold) from the i-th cycle to the data discrimination curve formed based on the i-1-th cycle is calculated to determine whether it is too high (higher than the third threshold); if so, it is considered that the heart rate fluctuation is large; if not, it is considered that the heart rate fluctuation is small, so that the user's sleep stage can be accurately judged, and then the number of cycles corresponding to the awake state, light sleep state and deep sleep state are obtained by statistics, and the proportion of the awake state, light sleep state and deep sleep state in this monitoring process can be calculated, wherein the first threshold, the second threshold and the third threshold are all determined in a manually set form through preliminary experiments.

[0076] As a preferred embodiment of the present invention, specifically, analyzing and judging the user's body movement based on the collected respiratory rate data includes:

[0077] Preprocessing the collected respiratory rate data to obtain high-quality respiratory rate data;

[0078] Extracting respiratory signals from high-quality respiratory rate data to obtain respiratory signals;

[0079] Performing body motion detection on the breathing signal to obtain a body motion detection result;

[0080] The body movement detection result is input into a pre-trained machine learning model to output the type and intensity of the body movement, and the type and intensity of the body movement are the user's body movement conditions.

[0081] In this preferred embodiment, the following steps are specifically included: 1. Data acquisition: First, a vital sign monitoring pad or other sensors (such as piezoelectric sensors, micro-motion sensors, radar technology, etc.) are needed to collect the user's breathing rate data. These sensors are usually installed under the mattress and can capture the slight pressure changes or vibrations caused by the user's breathing. 2. Signal preprocessing: The collected raw data usually contains noise and interference, and preprocessing is required to improve the data quality. Common preprocessing steps include: -Filtering: Use a low-pass filter to remove high-frequency noise and retain the breathing signal. Usually, the breathing frequency is between 0.16 and 0.5Hz. -Signal amplification: Amplify the weak electrical signal for subsequent processing. -Baseline correction: Remove the DC component in the signal to make the signal fluctuation more obvious. 3. Respiratory signal extraction: Extract the respiratory signal from the preprocessed data. The following methods can be used: -Peak detection: Detect the peaks and valleys in the signal and calculate the breathing cycle. -Fourier transform: Convert the time domain signal into a frequency domain signal and extract the breathing frequency. -Wavelet transform: Use wavelet transform to perform multi-scale analysis on the signal and extract respiratory features. 4. Body movement detection: Based on the extracted breathing signal, the user's body movement can be analyzed. Common methods include: -Respiratory cycle analysis: A normal breathing cycle should be smooth. If a sudden change or interruption in the breathing cycle is detected, it may indicate that the user has body movement. -Signal energy change: Body movement will cause a sudden increase in signal energy. By calculating the energy change of the signal, body movement can be detected. -Signal frequency analysis: Body movement will cause a sudden change in signal frequency. By analyzing the frequency components of the signal, body movement can be identified. 5. Body movement classification: Further analyze the type and intensity of body movement. The following methods can be used: -Machine learning: Train machine learning models (such as support vector machines, random forests, neural networks, etc.) to classify different types of body movements, such as turning over, sitting up, getting out of bed, etc. -Rule engine: Classify body movements based on predefined rules and thresholds. For example, if the breathing cycle changes exceed a certain threshold, it is judged as turning over.

[0082] As a preferred embodiment of the present invention, specifically,

[0083] Respiration rate and heart rate data are collected through one or more combinations of piezoelectric sensors or micro-motion sensors.

[0084] In this preferred embodiment, the piezoelectric sensor is a sensor that can convert mechanical energy into electrical signals. When the user lies on the mattress, the tiny pressure changes caused by his breathing and heart rate will be captured by the piezoelectric sensor. These pressure changes will be converted into electrical signals, and after processing, information such as breathing rate and heart rate can be extracted. Micro-motion sensor The micro-motion sensor can detect very small movements. When the user breathes or the heart beats, the mattress will produce tiny vibrations, which will be captured by the micro-motion sensor. By analyzing these vibration signals, the user's breathing rate and heart rate can be extracted. Of course, other sensors and combinations thereof that can collect relevant data are also possible.

[0085] As a preferred embodiment of the present invention, specifically, the cloud server visualizes the vital signs monitoring results and feeds them back to the preset IP terminal, including:

[0086] A corresponding IP terminal is bound to each user's registered account in advance in the cloud server. When the vital signs monitoring results are obtained, the vital signs monitoring results are generated into corresponding charts according to a preset mode, and the charts are sent to the preset IP terminal to inform the user.

[0087] Reference Figure 1 as well as Figure 2 The present invention also proposes a vital sign monitoring device, which applies the vital sign monitoring method, including:

[0088] A monitoring mat and a control box thereof, wherein the monitoring mat is fixedly mounted on a hard bed board and electrically connected to the control box, the control box is connected to the mains, the monitoring mat is used to collect parameters related to the user's vital signs, and the control box is used to upload the collected relevant information of the user to a cloud server.

[0089] In the second embodiment, the detection module is formed into a monitoring pad and a monitoring box, and the detection box is separated from the monitoring box, so that the risk of electric shock can be avoided while the monitoring pad is conveniently installed on the bed board.

[0090] Specifically, in actual application, the sleep monitor uses professional sensors to collect the user's physiological parameters in multiple dimensions, including heart rate, respiratory rate, body movement and other data, and uses algorithms to analyze the user's sleep status: including awake, asleep, out of bed, etc. In conjunction with the software system, it can monitor the elderly's real-time dynamics including physiological parameters, sleep status, abnormal conditions, and long-term tracking of the elderly's physiological data, sleep and rest habits, so as to better arrange nursing human resources and improve nursing quality and efficiency.

[0091] The specific installation process is as follows:

[0092] 1. Confirm whether the bed frame and mattress are suitable

[0093] bedstead

[0094] The bed board must be a hard surface. If it is placed on a slatted frame, the width of the slatted frame must be greater than the width of the monitoring mat.

[0095] (7cm);

[0096] 2. Install the SIM card. With the phone turned off, insert the IoT card (metal side facing down, notched corner facing outward) into the SIM card slot. Push it in with your fingernail until you hear a "click" and the edge of the SIM card is in the slot, indicating that the card is in place.

[0097] How to remove the SIM card:

[0098] Use your fingernail to push the SIM card inwards. When you hear a "click", release your finger and the SIM card will pop out partially. Then, hold the SIM card and pull it out.

[0099] 3. Place the monitoring pad

[0100] After lifting the mattress, place the monitoring pad in the middle of the bed frame, 50 to 60 cm away from the head of the bed (approximately 1.5 times the length of the monitoring pad).

[0101] Two monitoring pad connection methods:

[0102] Connect the cable of one monitoring pad to the middle USB port of another monitoring pad, and then place it horizontally on the bed board (this method can effectively deal with the situation in which the bed is too large in some scenarios)

[0103] 4. Connect the control box and monitoring pad and turn on the power

[0104] Plug the monitoring mat connection cable and adapter power cable into the control box, and then plug the adapter into the socket. If the network indicator light is on, it means that the power is on and the machine is turned on successfully. If the monitoring mat indicator light is always green, it means that the monitoring mat is plugged in tightly. If it is not lit, it means that the monitoring mat is not plugged in tightly.

[0105] 5. Close the bottom hatch

[0106] After aligning the bayonet of the bottom hatch cover with the monitoring pad connection cable and the power cable, push the bottom hatch cover inwards. When you hear a "click", it indicates that the bottom hatch cover is in place.

[0107] How to remove the bottom hatch cover:

[0108] After pressing the buckle, the bottom hatch cover will be pushed open, and then you can remove the bottom hatch cover in the direction of the arrow.

[0109] 6.Fix the monitoring mat and control box

[0110] If installing on a lifting bed, please stick the adhesive backing on the back of the monitoring mat and then fix it on the bed board.

[0111] 7. Place the mattress Place the mattress on top of the device.

[0112] In addition, each functional module in each embodiment of the present invention may be integrated into one processing module, or each module may exist physically separately, or two or more modules may be integrated into one module. The above-mentioned integrated module may be implemented in the form of hardware or in the form of software functional modules.

[0113] If the integrated module is implemented in the form of a software function module and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the present invention implements all or part of the processes in the above-mentioned embodiment method, and can also be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium, and the computer program can implement the steps of the above-mentioned various method embodiments when executed by the processor. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. The computer-readable medium may include: any entity or system that can carry the computer program code, recording medium, U disk, mobile hard disk, disk, optical disk, computer memory, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), electrical carrier signal, telecommunication signal and software distribution medium, etc.

[0114] Although the description of the present invention has been quite detailed and specifically describes several described embodiments, it is not intended to be limited to any of these details or embodiments or any particular embodiment, but should be regarded as providing a broad possible interpretation of these claims in view of the prior art by reference to the appended claims, thereby effectively covering the intended scope of the present invention. In addition, the above description of the present invention is based on the embodiments foreseeable by the inventor, and its purpose is to provide a useful description, and those non-substantial changes to the present invention that have not yet been foreseen may still represent equivalent changes to the present invention.

[0115] The above is only a preferred embodiment of the present invention. The present invention is not limited to the above implementation. As long as the technical effect of the present invention is achieved by the same means, it should belong to the protection scope of the present invention. Within the protection scope of the present invention, its technical scheme and / or implementation method can have various modifications and changes.

Claims

1. A method for monitoring vital signs, characterized in that: These include: The monitoring pad is used to collect the user's vital sign related parameters during a monitoring process; Sending the vital sign related parameters to a cloud server; After receiving the vital sign related parameters, the cloud server performs data analysis based on the vital sign related parameters to obtain vital sign monitoring results; The cloud server visualizes the vital signs monitoring results and feeds them back to the preset IP terminal.

2. The vital signs monitoring method according to claim 1, characterized in that: Specifically, the vital signs related parameters include respiratory rate and heart rate, and the collected respiratory rate and heart rate are collected according to a preset period T, that is, the respiratory rate and heart rate sent to the cloud each time are multi-period collection data, and M real-time respiratory rate and heart rate data are collected in each period.

3. The vital signs monitoring method according to claim 2, characterized in that: Specifically, the vital sign monitoring results are obtained by performing data analysis based on the vital sign related parameters, including: Analyze and determine the proportion of each type of sleep state of the user based on the collected heart rate data; Analyze and determine the user's body movement based on the collected breathing rate data; The proportion of each type of sleep state and body movement are used as vital sign monitoring results; The various sleep states include wakefulness, light sleep, and deep sleep.

4. The vital signs monitoring method according to claim 3, characterized in that: Specifically, based on the collected heart rate data, the proportion of each type of sleep state of the user is analyzed and determined, including: For the heart rate data of the i-th cycle T collected, the value range of i is 1 to the maximum cycle T, and the sampling number is assumed to be N, and its average value avg_i is calculated; When i is 1, it is directly determined that the user is awake in the first cycle; When i is not 1, continue the following process: Determine whether avg_i is greater than a first threshold, if so, it is determined that the state is awake; If it is not greater than the first threshold, all M real-time heart rate data collected in the i-1th period T are obtained; A two-dimensional coordinate system is constructed with the acquisition time as the horizontal coordinate and the value of the heart rate data as the vertical coordinate. At this time, all M real-time heart rate data collected in the i-1th period T form M coordinate points in the two-dimensional coordinate system; A data curve is obtained by curve fitting for the M coordinate points, and then the data curve is translated rightward along the x-axis for a period T to obtain a data discrimination curve for the i-th period T; For all M real-time heart rate data collected in the i-th period T, calculate the minimum distance to the data discriminant curve to obtain M minimum distances, count the number of minimum distances greater than the second threshold, and then calculate the ratio Q of the number of minimum distances greater than the second threshold to M; Determine whether the ratio Q is greater than a third threshold value. If it is greater than the third threshold value, it is determined that the heart rate fluctuation is large at this time, and it is determined that the person is in a light sleep state at this time. If it is not greater than the third threshold value, it is determined that the heart rate fluctuation is small at this time, and the person is in a deep sleep state at this time. The corresponding sleep state of all cycles is determined in the above manner, and the number of cycles corresponding to the awake state, light sleep state and deep sleep state are counted, and then the proportion of the awake state, light sleep state and deep sleep state in this monitoring process is calculated.

5. The vital signs monitoring method according to claim 3, characterized in that: Specifically, the user's body movement is analyzed and determined based on the collected respiratory rate data, including: Preprocessing the collected respiratory rate data to obtain high-quality respiratory rate data; Extracting respiratory signals from high-quality respiratory rate data to obtain respiratory signals; Performing body motion detection on the breathing signal to obtain a body motion detection result; The body movement detection result is input into a pre-trained machine learning model to output the type and intensity of the body movement, and the type and intensity of the body movement are the user's body movement conditions.

6. The vital signs monitoring method according to claim 2, characterized in that: Specifically, Respiration rate and heart rate data are collected through one or more combinations of piezoelectric sensors or micro-motion sensors.

7. The vital signs monitoring method according to claim 1, characterized in that: Specifically, the cloud server visualizes the vital signs monitoring results and feeds them back to the preset IP terminal, including: A corresponding IP terminal is bound to each user's registered account in advance in the cloud server. When the vital signs monitoring results are obtained, the vital signs monitoring results are generated into corresponding charts according to a preset mode, and the charts are sent to the preset IP terminal to inform the user.

8. A vital signs monitoring device, characterized in that: The method for monitoring vital signs according to any one of claims 1 to 7 is applied, comprising: A monitoring mat and a control box thereof, wherein the monitoring mat is fixedly mounted on a hard bed board and electrically connected to the control box, the control box is connected to the mains, the monitoring mat is used to collect parameters related to the user's vital signs, and the control box is used to upload the collected relevant information of the user to a cloud server.

Images