A control method and device of a device, an air conditioning device, and a storage medium

Abstract

Embodiments of the present application relate to a control method and device of an apparatus, an air conditioning apparatus and a storage medium. The method comprises: when detecting that a target object enters a preset area, sending a first signal to a preset position of the target object; receiving a second signal, the second signal being a signal reflected back by the first signal contacting the target object; extracting a physiological signal of the target object from the second signal; and controlling the apparatus according to the physiological signal. Thus, the control strategy of the apparatus can be customized according to the physiological condition of the human body, the operation of the apparatus is controlled, and the comfort and sleep quality of the user are improved.

Description

TECHNICAL FIELD

[0001] Embodiments of the present application relate to the technical field of smart home, and in particular to a device control method and device, an air conditioning device and a storage medium. BACKGROUND

[0002] For the acquisition of heartbeats and breaths, there are usually two types of contact and non-contact. The contact examination instruments include electrocardiogram, stethoscope, breathing bandage, etc., and the non-contact examination techniques include laser detection, infrared detection, etc. The contact detection instrument usually affects the user experience, and the data obtained by the non-contact detection has low accuracy.

[0003] The conventional non-contact physiological signal detection device cannot be combined with smart home such as air conditioning, and cannot control the air conditioner according to the physiological signal of the user, so that accurate human physiological information cannot be effectively obtained, and the sleep condition of the user cannot be monitored in real time and the environmental parameters cannot be controlled. Therefore, how to control the air conditioner according to the physiological signal of the user has become a problem to be solved at present. SUMMARY

[0004] In view of this, in order to solve the technical problem of controlling the air conditioner according to the physiological signal, embodiments of the present application provide a device control method and device, an air conditioning device and a storage medium.

[0005] In a first aspect, the embodiments of the present application provide a device control method, comprising:

[0006] When a target object is detected to enter a preset area, a first signal is sent to a preset position of the target object;

[0007] A second signal is received, the second signal being a signal reflected back by the first signal contacting the target object;

[0008] A physiological signal of the target object is extracted from the second signal;

[0009] The device is controlled according to the physiological signal.

[0010] In one possible implementation, the extracting of the physiological signal of the target object from the second signal comprises:

[0011] The second signal is denoised by an empirical mode decomposition algorithm to obtain a denoised second signal;

[0012] The denoised second signal is input into a trained signal separation model, so that the signal separation model outputs a breathing signal and a heartbeat signal of the target object;

[0013] The breathing signal and the heartbeat signal are taken as the physiological signal.

[0014] In a possible implementation, the denoising processing of the second signal by the empirical mode decomposition algorithm comprises:

[0015] determining a plurality of IMF component signals of the second signal by the empirical mode decomposition algorithm;

[0016] determining a target IMF component signal from the plurality of IMF component signals;

[0017] removing the target IMF component signal to obtain the second signal with noise removed.

[0018] In a possible implementation, the signal separation model is obtained by training in the following manner:

[0019] obtaining a breathing heartbeat signal of a target object in a breathing state, and obtaining a breath-holding heartbeat signal of the target object in a breath-holding state;

[0020] training an initial model by taking the breath-holding heartbeat signal as a desired signal and taking the breathing heartbeat signal as an input signal, and obtaining a trained signal separation model by using an LMS algorithm.

[0021] In a possible implementation, the obtaining of the breathing heartbeat signal of the target object in the breathing state and the breath-holding heartbeat signal of the target object in the breath-holding state comprises:

[0022] when detecting normal breathing of the target object, sending the first signal to a preset position of the target object, and receiving a third signal returned after the first signal contacts the target object;

[0023] when detecting breath-holding of the target object, sending the first signal to a preset position of the target object, and receiving a fourth signal returned after the first signal contacts the target object;

[0024] performing denoising processing on the third signal by the empirical mode decomposition algorithm to obtain a breathing heartbeat signal with noise removed;

[0025] performing denoising processing on the fourth signal by the empirical mode decomposition algorithm to obtain a breath-holding heartbeat signal with noise removed.

[0026] In a possible implementation, the control of the device according to the physiological signal comprises:

[0027] determining a physiological parameter of the target object according to the physiological signal, the physiological parameter comprising a heart rate parameter and a breathing rate parameter;

[0028] determine state information of the target object according to the physiological parameter;

[0029] determine a target operation mode of the device according to the state information, the operation mode including preset power, preset operation duration, preset air outlet temperature and preset air outlet direction of the device;

[0030] control the device to operate in the target operation mode.

[0031] In one possible implementation, the method further includes:

[0032] when the heart rate parameter or the respiration rate parameter is in a set threshold range, control the device to generate an alarm event.

[0033] In a second aspect, an embodiment of the present application provides a device control apparatus, including:

[0034] a sending module configured to send a first signal to a preset position of a target object when it is detected that the target object enters a preset area;

[0035] a receiving module configured to receive a second signal returned after the first signal contacts the target object;

[0036] an extracting module configured to extract a physiological signal of the target object from the second signal;

[0037] a control module configured to control the device according to the physiological signal.

[0038] In a third aspect, an embodiment of the present application provides an air conditioner device, including a processor and a memory, the processor being configured to execute a device control program stored in the memory to implement the device control method in any of the first aspect.

[0039] In a fourth aspect, an embodiment of the present application provides a storage medium, the storage medium storing one or more programs, the one or more programs being executable by one or more processors to implement the device control method in any of the first aspect.

[0040] The device control scheme provided by the embodiment of the present application can achieve the following effects: when it is detected that a target object enters a preset area, a first signal is sent to a preset position of the target object; a second signal is received, the second signal being a signal reflected back by the first signal contacting the target object; a physiological signal of the target object is extracted from the second signal; and the device is controlled according to the physiological signal. Thus, the device control strategy can be customized according to the physiological condition of a human body to control the device to operate, so as to improve the comfort of a user when using the device by controlling the operation mode of the device. BRIEF DESCRIPTION OF DRAWINGS

[0041] Figure 1 A flowchart of a control method of a device provided by an embodiment of the present application is shown in

[0042] Figure 2 A flowchart of another control method of a device provided by an embodiment of the present application is shown in

[0043] Figure 3 A flowchart of a training method of a signal separation model provided by an embodiment of the present application is shown in

[0044] Figure 4 A flowchart of another training method of a signal separation model provided by an embodiment of the present application is shown in

[0045] Figure 5 A physiological signal display diagram provided by an embodiment of the present application is shown in

[0046] Figure 6 A sleep report diagram provided by an embodiment of the present application is shown in

[0047] Figure 7 A structural diagram of a control device of a device provided by an embodiment of the present application is shown in

[0048] Figure 8 A structural diagram of an air conditioning device provided by an embodiment of the present application is shown in DETAILED DESCRIPTION

[0049] To make the objectives, technical solutions and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are some but not all of the embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative work fall within the scope of protection of the present application.

[0050] To make the objectives, technical solutions and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are some but not all of the embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative work fall within the scope of protection of the present application.

[0051] Figure 1 A flowchart of a control method of a device provided by an embodiment of the present application is shown in Figure 1 The method specifically includes:

[0052] S11, when detecting that a target object enters a preset area, sending a first signal to a preset position of the target object.

[0053] The control method of the device provided by the embodiment of the present application is applied to a smart home device, which can be an air conditioning device, a temperature and humidity adjusting device, etc. The control of the device is specifically realized by acquiring a physiological signal of a target object in a sleep process, and the target object is a human body, an animal, or other living beings.

[0054] In the embodiment, a preset area is divided in advance. The preset area can be understood as an identifiable area, that is, the control of the device can be realized only when the target object appears in the preset area. The position of the area is usually set on a bed body near the device. When the target object appears in the preset area, it indicates that the target object is located above the bed body. The size of the area can be determined according to actual needs. For this, the embodiment is not specifically limited (for example, a fan-shaped area, a circular area, a square area, etc.).

[0055] When the target object enters the preset area is detected by a human body detection device (for example, an infrared sensor arranged above the preset area, a pressure sensor arranged below the bed body corresponding to the preset area, a UWB device arranged on the air conditioner, etc.), it is determined whether the current posture of the target object is lying on the bed body. The determination method can be acquiring an image of the target object, determining the similarity between the image and a pre-stored image of the target object lying on the bed body, and determining that the target object is currently lying on the bed body when the similarity is greater than a set threshold.

[0056] Further, the preset position corresponding to the target object is a position on the surface of the target object that can reflect the physiological change (for example, the respiratory change) of the target object. When the target object is a human body, the chest surface of the human body is used as the preset position because the chest of the human body will fluctuate when the human body breathes. The position of the chest of the target object is determined by identifying different parts of the human body, and the first signal is continuously sent to the position of the chest. The first signal is an electromagnetic wave pulse signal continuously emitted by a UWB radar device. The UWB radar can be arranged inside or on the surface of the device, so that the radar will not be affected by other objects when emitting the first signal. The specific position is not limited in the embodiment (for example, the air outlet of the air conditioner, the position of the lower surface of the air conditioner close to the bed body, etc.).

[0057] In one possible implementation, a face image of the object is acquired when the object enters the preset area is detected, and it is determined that the object is the target object when the similarity between the face image and a pre-stored face image is greater than a set threshold. In this way, a specific user can be detected.

[0058] S12, receiving a second signal; extracting a physiological signal of the target object from the second signal.

[0059] In the embodiment, when the pulse signal reaches the preset position of the target object and contacts the target object, a reflected echo signal is generated, and the UWB radar continuously receives the echo signal, and takes the received echo signal as the second signal.

[0060] Further, since the heartbeat and respiration of the target object are closely related to the fluctuation of the chest cavity, the fluctuation of the chest cavity causes a slow time domain periodic signal in the echo signal, which contains the respiration signal generated during respiration and the heartbeat signal generated during heartbeat. Therefore, the second signal needs to be denoised to extract the heartbeat signal and the respiration signal. The denoising method can include but is not limited to processing the echo signal by an empirical mode decomposition (EMD) method to filter out a large amount of noise in the echo signal, thereby obtaining a denoised echo signal.

[0061] Further, a signal separation model is pre-trained, which can separate the denoised echo signal into a respiration signal and a heartbeat signal. The training method of the model can include obtaining a respiration heartbeat mixed signal of a user during respiration and a separate breath holding heartbeat signal of the user when holding breath as training samples to train until the model converges, thereby obtaining a signal separation model that can separate the respiration heartbeat mixed signal into a respiration signal and a heartbeat signal. The heartbeat signal and the respiration signal can be extracted from the denoised echo signal by the model, and the respiration signal and the heartbeat signal are taken as physiological signals.

[0062] S13, controlling the device according to the physiological signal.

[0063] In the embodiment, the physiological signal is analyzed, different physiological parameters corresponding to different physiological signals are pre-set, and the physiological parameters can include but are not limited to: (1) respiratory rate: average number of breaths per minute; (2) heart rate: average number of heartbeats per minute; (3) signal strength: signal strength of the body sign reflected by the human body; (4) distance: straight-line distance from the radar to the nearest human body movement part; (5) sign abnormality: suspected respiration abnormality warning or heartbeat abnormality warning. The state of the human body corresponding to the physiological parameter in different threshold ranges is pre-set, and the current state of the target object is determined according to the threshold range in which the determined physiological parameter is located. The current state includes but is not limited to: a first state: the target object has no limb movement, the heart rate is in a first threshold range, and the respiration is in a second threshold range, which is generally an about-to-sleep state or a light sleep state; a second state: the limb has no movement, the heart rate is in a third threshold range, and the respiration is in a fourth threshold range, which is generally a deep sleep state; a third state: the limb has movement, the heart rate is in a fifth threshold range, and the respiration is in a sixth threshold range, which is generally an awake state; and a fourth state: the heart rate is in a seventh threshold range, or the respiration is in an eighth threshold range, which is generally a respiration or heartbeat abnormality state.

[0064] Further, the control strategy of the corresponding device is determined according to different states, and a corresponding relationship between the state and the control strategy is set in advance according to user demand, for example, when the device is an air conditioner, and the state is deep sleep, the control strategy is determined as: the air direction is swept, the user is avoided to be directly blown, and the air conditioner temperature is adjusted to a first preset temperature, or the air conditioner is adjusted to a sleep mode, or the air conditioner is controlled to work in a timing mode; when the state is a wake-up state, the air conditioner is controlled to be adjusted to a second preset temperature, the air direction is set as direct blowing or air supply, and when the state is an abnormal state, the air conditioner is controlled to generate an alarm event. The device is controlled according to the control strategy.

[0065] The device control method provided by the embodiment of the application comprises the following steps: when a target object enters a preset area, a first signal is sent to a preset position of the target object; a second signal is received, the second signal being a signal reflected by the first signal contacting the target object; a physiological signal of the target object is extracted from the second signal; and the device is controlled according to the physiological signal. Thus, the control strategy of the device can be customized according to the physiological condition of the human body, the device is controlled to run, and the comfort and sleep quality of the user are improved.

[0066] Figure 2 Another flowchart of the device control method provided by the embodiment of the application is shown in FIG. 2. Figure 2 The method specifically comprises the following steps.

[0067] S21, when a target object enters a preset area, a first signal is sent to a preset position of the target object.

[0068] In the embodiment, the step S11 is similar, and details are described in the related description. Figure 1 For brevity and conciseness, the details are not described herein.

[0069] S22, a second signal is received, and the second signal is denoised by an empirical mode decomposition algorithm to obtain a denoised second signal.

[0070] In the embodiment, when the pulse signal reaches the preset position of the target object and contacts the target object, a backwave signal is reflected, and the UWB radar continuously receives the backwave signal, and the received backwave signal is taken as the second signal.

[0071] The UWB radar system refers to a radar system with an absolute bandwidth greater than 0.5 GHz at 10 dB of the pulse spectrum or a relative bandwidth greater than 25%. When the UWB radar detects respiration and heartbeat, the radar device transmits a pulse signal to the target object to be detected, the pulse signal reaches the surface of the chest cavity of the target object to be detected, generates a return signal and is received by the radar device. Since heartbeat and respiration are closely related to chest fluctuation, chest fluctuation will cause a slow time domain periodic signal in the return signal, and the return signal is processed by the EMD method. After the air conditioner and the UWB radar device are powered on, generally 10 seconds of return signals need to be accumulated before processing, that is, when powered on in the presence of a person, it takes about 10 seconds to determine whether a person is in the preset area; when a person enters the preset area during device operation, the return signal can be detected and reported in about 1 second. When a person leaves the preset area during device operation, the user can be reported to leave in about 20 seconds.

[0072] The specific processing method of the EMD method for the return signal is: determining a plurality of IMF component signals of the second signal through an empirical mode decomposition algorithm; determining a target IMF component signal from the plurality of IMF component signals; removing the target IMF component signal to obtain a second signal with removed noise.

[0073] The specific steps include: 1. Find all local maxima in the return signal and connect them into an upper envelope with a cubic spline function; similarly, connect all local minima to form a lower envelope with a cubic spline interpolation function;

[0074] 2. Find the average of the upper and lower envelopes, denoted as m1, and find the difference between the original signal and the envelope average: x(t)-m1=h1.

[0075] 3. If h1 satisfies the intrinsic mode function (IMF) condition, that is: the number of local extreme points and zero-crossing points must be equal or differ by at most one in the entire time range; at any time point, the average of the local maximum envelope (upper envelope line) and the local minimum envelope (lower envelope line) must be zero. Then h1 is the first IMF component signal; otherwise, repeat steps 1-2 with h1 as the original signal until the difference h 1，k (k) becomes an IMF after the kth iteration, denoted as: c1(t)=h 1，k (k), and set the termination criterion for k iterations, where c1(t) represents the first iteration of the intrinsic mode function, h 1，k (k) is the iteration method: execute k steps until the above conditions are met.

[0076] 4. Subtract c1(t) from the original signal to obtain the first order residual signal r1(t): r1(t) = s(t) - c1(t)

[0077] 5. Take the residual signal r1(t) as the original signal to perform steps 1-4:

[0078]

[0079] The termination criterion is that the Nth order residual signal rN(t) is sufficiently simple that no more IMFs can be extracted. N

[0080] In summary, the original signal s(t) is decomposed into the following IMFs by the modal decomposition method:

[0081]

[0082] Through the above steps, after the echo signal is decomposed into a finite number of IMF component signals by EMD, each IMF component signal is a single component signal and contains different time characteristic scales, and the time characteristic scale of the IMF component signal gradually increases with the increase of the IMF order, and the frequency scale contained gradually decreases with the increase of the IMF order. In order to determine the information contained in each IMF component signal, the energy rule or the autocorrelation function is used to determine the properties of the IMF component signal. When judging the properties of the IMF component signal, that is, judging which IMF contains more noise and which IMF contains more useful signals, the target IMF component signal is the signal containing more noise, and the IMF component signal with an order greater than a set threshold is taken as the target IMF component signal. If the minimum value point of the IMF energy cannot be found or the minimum value point exists in the IMF component with a high order, the autocorrelation function of all IMF components can be solved. The difference between the autocorrelation function of the IMF component signal with more useful signals and the autocorrelation function of the IMF component signal (target IMF component signal) with more noise is large, and the demarcation point between the target IMF component signal and other IMF component signals is determined. The demarcation point is used to distinguish two different forms of IMF component signals. After the demarcation point is found, a filtering method can be used to selectively remove the target IMF component signal part, extract the effective signal from the echo signal, and obtain the echo signal with noise removed.

[0083] S23, input the second signal with noise removed into the trained signal separation model, so that the signal separation model outputs the respiratory signal and the heartbeat signal of the target object; take the respiratory signal and the heartbeat signal as the physiological signals.

[0084] In the embodiment, the signal separation model is trained by the training method of the signal separation model. Figure 3 A flowchart of a training method of a signal separation model provided by an embodiment of the present application is shown in FIG. 2. Figure 4 ​As shown in FIG. 6, a flowchart of another training method of a signal separation model provided by an embodiment of the present application is shown. Figure 3 and Figure 4 As shown in FIG. 6, the method specifically includes the following steps.

[0085] S31, obtaining a breathing heartbeat signal of a target object in a breathing state, and obtaining a breath-holding heartbeat signal of the target object in a breath-holding state.

[0086] In this embodiment, the target object can be any user, and the user is asked to breathe normally and lie in a preset area. After the user manually triggers a first button, a message is sent to the device, which indicates that the user is currently in a normal breathing state. The device detects whether the message is received, and determines that the target object is in a normal breathing state when it is detected that the message is received. At this time, the physiological signal detection step is started, a first signal is sent to the preset position of the target object (the chest position of the user), the first signal is a pulse signal sent by the UWB radar device, and the echo signal returned after the first signal contacts the target object is received as a third signal. The obtained third signal is a mixed signal of breathing and heartbeat.

[0087] Further, the user is asked to hold his breath and lie in a preset area. After the user manually triggers a second button, a message is sent to the device, which indicates that the user is currently in a breath-holding state. The device detects whether the message is received, and determines that the target object is in a breath-holding state when it is detected that the message is received. A first signal is sent to the preset position of the target object, and a fourth signal returned after the first signal contacts the target object is received. At this time, the received fourth signal is an echo signal that does not contain a breathing signal.

[0088] Further, the third signal is denoised by the EMD algorithm in step S22 to obtain a breathing heartbeat signal with noise removed; and the fourth signal is denoised by the EMD algorithm to obtain a breath-holding heartbeat signal with noise removed.

[0089] S32, taking the breath-holding heartbeat signal as an expected signal, taking the breathing heartbeat signal as an input signal, training an initial model by using an LMS algorithm to obtain a trained signal separation model.

[0090] In this embodiment, the initial model is trained by using the least mean square algorithm (LMS) to separate the heartbeat signal and the breathing signal. The breath-holding heartbeat signal is taken as an expected signal d(n) in the LMS algorithm, the breathing heartbeat signal is taken as an input signal x(n), the LMS algorithm is run until the model converges, and a trained signal separation model is obtained. The mixed signal input can be separated to obtain a single heartbeat signal and a breathing signal.

[0091] input the second signal after noise removal into the trained signal separation model, so that the signal separation model outputs a pure breathing signal and a heartbeat signal of the target object; the breathing signal and the heartbeat signal are taken as physiological signals.

[0092] S24, determine a heart rate parameter and a breathing rate parameter of the target object according to the physiological signals; the heart rate parameter and the breathing rate parameter determine state information of the target object; determine a target working mode of the device according to the state information; control the device to operate in the target working mode.

[0093] In this embodiment, the breathing signal and the heartbeat signal are analyzed respectively to obtain the breathing times per minute as the breathing rate parameter and the heartbeat times per minute as the heart rate parameter; the state information of the target object is determined according to the threshold range in which the heart rate parameter and the breathing rate parameter are located, each threshold range corresponds to one state information, and the state information can include but is not limited to deep sleep, light sleep, wake state, abnormal breathing or heartbeat state, etc., and a physiological signal display diagram as shown in FIG. 6 is generated. Figure 5 Figure 5 As shown in FIG. 7, the physiological signal display diagram includes but is not limited to the breathing rate parameter, the heartbeat parameter, the heartbeat signal line chart, the breathing signal line chart, the signal intensity, the signal emission distance, the abnormal breathing or heartbeat situation warning, etc.

[0094] Further, one target working mode corresponding to each state information is set, and the target working mode of the corresponding device is determined according to the state information of the user, and the working mode includes but is not limited to the preset power, the preset working time length, the preset air outlet temperature and the preset air outlet direction of the device, etc. The device is controlled to operate in the target working mode.

[0095] In one possible implementation, physiological parameter analysis obtains the maximum heart rate, the minimum heart rate, the average heart rate, the maximum breathing rate, the minimum breathing rate, the average breathing rate, etc. during the sleep process of the user. A comfort degree model of parameter combinations such as breathing, heart rate, body temperature, motion state, health degree, etc. is established, the current health condition of the user (for example, whether in a sick state, whether feeling cold, etc.) is analyzed, and the device is controlled in real time. For the user with low health degree or in deep sleep, a soft air sweeping strategy, an air sweeping strategy avoiding direct blowing and a temperature desensitization adjustment strategy are implemented to maximize the guarantee of the healthy and comfortable sleep of the user.

[0096] In one possible implementation, when the heart rate parameter or the breathing rate parameter is in a set threshold range, it indicates that the breathing or heartbeat of the target object may be abnormal, at this time, the device is controlled to generate an alarm event, the alarm event can be that the device performs sound and light alarm, sends alarm information to the mobile terminal device of the target object for display and reminder, etc.

[0097] ​In a possible implementation, a sleep report of the target object is generated according to the heart rate parameter and the respiratory rate parameter; and the sleep report is sent to a terminal of the target object, so that the sleep report is displayed on the terminal.

[0098] Specifically, the sleep total duration, the sleep-in time, the wake-up time, the real-time distribution of the sleep staging state, the sleep proportion, the wake-up duration, the wake-up times, the respiratory quality, the sporadic nap duration, the suspected respiratory abnormality times, the effective sleep duration, the sleep efficiency and the like are obtained by analyzing the parameters such as the respiratory rate and the heart rate. Finally, the sleep quality score is obtained, and the user can push the sleep suggestion according to the score, and the sleep report is generated by combining the sleep suggestion, the sleep quality score and the analyzed data, and is sent to the terminal for display. Figure 6 As shown in FIG. 6, it is a sleep report diagram provided by an embodiment of the present application.

[0099] The control method of the device provided by the embodiment of the present application comprises the following steps: when it is detected that the target object enters a preset area, a first signal is sent to a preset position of the target object; a second signal is received, the second signal is denoised by an empirical mode decomposition algorithm to obtain a second signal without noise; the second signal without noise is input into a trained signal separation model, so that the signal separation model outputs a respiratory signal and a heartbeat signal of the target object; the respiratory signal and the heartbeat signal are taken as the physiological signal; the heart rate parameter and the respiratory rate parameter of the target object are determined according to the physiological signal; the state information of the target object is determined according to the heart rate parameter and the respiratory rate parameter; the target working mode of the device is determined according to the state information; and the device is controlled to operate in the target working mode. Therefore, the user's respiratory rate, heart rate and the like can be monitored in real time by the device such as the air conditioner, and the working mode of the air conditioner is controlled, so that the user can use the air conditioner in a personalized and comfortable manner, the sleep overheating or chilling is prevented, the sleep quality and health report is generated, and the health guidance is made.

[0100] Figure 7 The control device of the device provided by the embodiment of the present application comprises the following steps:

[0101] The sending module 71 is configured to send a first signal to a preset position of the target object when it is detected that the target object enters a preset area.

[0102] The receiving module 72 is configured to receive a second signal returned after the first signal contacts the target object.

[0103] The extraction module 73 is configured to extract a physiological signal of the target object from the second signal.

[0104] The control module 74 is configured to control the device according to the physiological signal.

[0105] In a possible implementation, the processing module 75 is configured to perform denoising processing on the second signal by using an empirical mode decomposition algorithm to obtain a denoised second signal.

[0106] The denoised second signal is input into the trained signal separation model, so that the signal separation model outputs a breathing signal and a heartbeat signal of the target object.

[0107] The breathing signal and the heartbeat signal are used as the physiological signals.

[0108] In a possible implementation, the determining module 77 is configured to determine a plurality of IMF component signals of the second signal by using an empirical mode decomposition algorithm.

[0109] A target IMF component signal is determined from the plurality of IMF component signals.

[0110] The processing module is further configured to remove the target IMF component signal to obtain the denoised second signal.

[0111] In a possible implementation, the obtaining module 76 is configured to obtain a breathing heartbeat signal of a target object in a breathing state, and obtain a breath-holding heartbeat signal of the target object in a breath-holding state.

[0112] The processing module 75 is further configured to use the breath-holding heartbeat signal as an expected signal, use the breathing heartbeat signal as an input signal, and train an initial model by using an LMS algorithm to obtain the trained signal separation model.

[0113] In a possible implementation, the sending module is further configured to send the first signal to a preset position of the target object when it is detected that the target object is breathing normally, and the receiving module is further configured to receive a third signal returned after the first signal contacts the target object.

[0114] The sending module is further configured to send the first signal to a preset position of the target object when it is detected that the target object is holding breath, and the receiving module is further configured to receive a fourth signal returned after the first signal contacts the target object.

[0115] The processing module is further configured to perform denoising processing on the third signal by using an empirical mode decomposition algorithm to obtain a denoised breathing heartbeat signal.

[0116] The fourth signal is processed by using an empirical mode decomposition algorithm to obtain a denoised breath-holding heartbeat signal.

[0117] In a possible implementation, the determining module is further configured to determine a heart rate parameter and a respiration rate parameter of the target object according to the physiological signal.

[0118] The heart rate parameter and the respiration rate parameter determine state information of the target object.

[0119] The target working mode of the device is determined according to the state information, and the working mode includes preset power, preset working time length, preset air outlet temperature and preset air outlet direction of the device.

[0120] The control module is specifically configured to control the device to operate in the target working mode.

[0121] In a possible implementation, the control module is specifically configured to control the device to generate an alarm event when the heart rate parameter or the respiration rate parameter is in a set threshold range.

[0122] In a possible implementation, the generating module 78 is configured to generate a sleep report of the target object according to the heart rate parameter and the respiration rate parameter.

[0123] The sending module is further configured to send the sleep report to a terminal of the target object, so as to display the sleep report through the terminal.

[0124] The device control apparatus provided in the embodiment can be an apparatus as shown in Figure 7 , and can perform all steps of the device control method in Figures 1-3 , thereby achieving the technical effects of the device control method in Figures 1-3 . For brevity and conciseness, relevant descriptions are not repeated here. Figures 1-3

[0125] Figure 8 A structural schematic diagram of an air conditioning device provided in the embodiment of the present application is shown in Figure 4 , and the air conditioning device 800 includes at least one processor 801, a memory 802, at least one network interface 804 and other user interfaces 803. The various components in the air conditioning device 800 are coupled together through a bus system 805. It can be understood that the bus system 805 is used to realize the connection and communication between the components. The bus system 805 includes a data bus, a power bus, a control bus and a status signal bus. However, for the purpose of clear illustration, all the buses are marked as the bus system 805 in the Figure 8 .

[0126] The user interface 803 can include a display, a keyboard or a clicking device (for example, a mouse, a trackball, a touchpad or a touch screen, etc.). ​

[0127] It is to be understood that the memory 802 in embodiments of the present application can be volatile or nonvolatile memory, or can include both volatile and nonvolatile memory. In one embodiment, the nonvolatile memory can be read-only memory (ROM), programmable ROM (PROM), erasable PROM (EPROM), electrically EPROM (EEPROM), or flash memory. The volatile memory can be random access memory (RAM), which is used as external cache. By way of example, and not limitation, many forms of RAM are available, for example, static RAM (SRAM), dynamic RAM (DRAM), synchronous dynamic RAM (SDRAM), double data rate SDRAM (DDR SDRAM), enhanced SDRAM (ESDRAM), Synchlink DRAM (SLDRAM), and direct Rambus RAM (DRRAM). Memory 802 described herein is intended to include, without being limited to, these and any other suitable types of memory.

[0128] In some embodiments, the memory 802 stores the following elements, executable units or data structures, or a subset of them, or an extended set of them: an operating system 8021 and application programs 8022.

[0129] The operating system 8021 includes various system programs, such as a framework layer, a core library layer, a driver layer, etc., for implementing various basic services and processing hardware-based tasks. The application programs 8022 include various application programs, such as a media player, a browser, etc., for implementing various application services. The programs for implementing the method embodiments of the present application can be included in the application programs 8022.

[0130] In embodiments of the present application, by invoking the programs or instructions stored in the memory 802, specifically, the programs or instructions stored in the application programs 8022, the processor 801 is configured to execute the method steps provided by the method embodiments, for example, including:

[0131] When it is detected that the target object enters the preset area, a first signal is sent to a preset position of the target object;

[0132] A second signal is received, which is a signal reflected back by the first signal contacting the target object;

[0133] A physiological signal of the target object is extracted from the second signal;

[0134] The device is controlled according to the physiological signal.

[0135] In one possible implementation, the second signal is denoised by an empirical mode decomposition algorithm to obtain a denoised second signal;

[0136] The denoised second signal is input into a trained signal separation model, so that the signal separation model outputs a breathing signal and a heartbeat signal of the target object;

[0137] The breathing signal and the heartbeat signal are taken as the physiological signal.

[0138] In one possible implementation, a plurality of IMF component signals of the second signal are determined by an empirical mode decomposition algorithm;

[0139] A target IMF component signal is determined from the plurality of IMF component signals;

[0140] The target IMF component signal is removed to obtain a denoised second signal.

[0141] In one possible implementation, a breathing heartbeat signal of a target object in a breathing state is obtained, and a breath-holding heartbeat signal of the target object in a breath-holding state is obtained;

[0142] The breath-holding heartbeat signal is taken as an expected signal, the breathing heartbeat signal is taken as an input signal, an initial model is trained by an LMS algorithm to obtain a trained signal separation model.

[0143] In one possible implementation, when it is detected that the target object is breathing normally, the first signal is sent to a preset position of the target object, and a third signal returned after the first signal contacts the target object is received;

[0144] When it is detected that the target object is holding breath, the first signal is sent to a preset position of the target object, and a fourth signal returned after the first signal contacts the target object is received;

[0145] The third signal is denoised by an empirical mode decomposition algorithm to obtain a denoised breathing heartbeat signal;

[0146] The fourth signal is denoised by an empirical mode decomposition algorithm to obtain a breath-holding heartbeat signal with noise removed.

[0147] In a possible implementation, a physiological parameter of the target object is determined according to the physiological signal, and the physiological parameter includes a heart rate parameter and a respiration rate parameter.

[0148] State information of the target object is determined according to the physiological parameter.

[0149] A target operation mode of the device is determined according to the state information, and the operation mode includes preset power, preset operation duration, preset air outlet temperature, and preset air outlet direction of the device.

[0150] The device is controlled to operate in the target operation mode.

[0151] In a possible implementation, when the heart rate parameter or the respiration rate parameter is in a set threshold range, an alarm event of the device is controlled to occur.

[0152] The method disclosed in the embodiments of the present application can be applied to the processor 801 or implemented by the processor 801. The processor 801 can be an integrated circuit chip having a signal processing capability. In the implementation process, the steps of the above method can be completed by the integrated logic circuits or the instruction of the software form in the processor 801. The processor 801 described above can be a general processor, a digital signal processor (DSP), an application specific integrated circuit (ASIC), a field programmable gate array (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components. The disclosed methods, steps and logic block diagrams in the embodiments of the present application can be implemented or executed. The general processor can be a microprocessor or the processor can also be any conventional processor. The steps of the method disclosed in combination with the embodiments of the present application can be directly embodied as a hardware code processor for execution, or a combination of hardware and software units in the code processor for execution. The software unit can be located in a random access memory, a flash memory, a read only memory, a programmable read only memory, an electrically erasable programmable memory, a register or other mature storage medium in the art. The storage medium is located in the memory 802, and the processor 801 reads the information in the memory 802, and combines the hardware to complete the steps of the above method.

[0153] It can be understood that the embodiments described herein can be implemented in hardware, software, firmware, middleware, microcode, or a combination thereof. For hardware implementation, the processing units can be implemented within one or more application specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSP Devices, DSPDs), programmable logic devices (PLDs), field programmable gate arrays (FPGAs), general purpose processors, controllers, micro-controllers, microprocessors, other electronic units designed to perform the functions described herein, or a combination thereof.

[0154] For software implementation, the techniques described herein can be implemented with a processing unit that executes program components or modules. The software code can be stored in memory and executed by a processor. Memory can be implemented within the processor or external to the processor.

[0155] The air conditioning device provided by the embodiment can be an air conditioning device as shown in Figure 8 The air conditioning device provided by the embodiment can be an air conditioning device as shown in Figures 1-3 The air conditioning device provided by the embodiment can be an air conditioning device as shown in Figures 1-3 The air conditioning device provided by the embodiment can be an air conditioning device as shown in Figures 1-3 The air conditioning device provided by the embodiment can be an air conditioning device as shown in

[0156] The embodiment of the present application further provides a storage medium (computer readable storage medium). The storage medium stores one or more programs. The storage medium can include a volatile memory, such as a random access memory; the storage medium can also include a non-volatile memory, such as a read-only memory, a flash memory, a hard disk, or a solid state disk; and the storage medium can also include a combination of the above kinds of memories.

[0157] When the one or more programs stored in the storage medium are executed by the one or more processors, the device control method executed at the device side described above can be implemented.

[0158] The processor is configured to execute the device control program stored in the memory, so as to implement the steps of the device control method executed at the device side.

[0159] When the target object is detected to enter the preset area, a first signal is sent to a preset position of the target object;

[0160] A second signal is received, and the second signal is a signal reflected back by the first signal contacting the target object.

[0161] extracting a physiological signal of the target object from the second signal;

[0162] controlling the device according to the physiological signal.

[0163] In a possible implementation, the second signal is denoised by an empirical mode decomposition algorithm to obtain a denoised second signal;

[0164] inputting the denoised second signal into a trained signal separation model, so that the signal separation model outputs a breathing signal and a heartbeat signal of the target object;

[0165] taking the breathing signal and the heartbeat signal as the physiological signal.

[0166] In a possible implementation, a plurality of IMF component signals of the second signal are determined by an empirical mode decomposition algorithm;

[0167] a target IMF component signal is determined from the plurality of IMF component signals;

[0168] the target IMF component signal is removed to obtain the denoised second signal.

[0169] In a possible implementation, a breathing heartbeat signal of a target object in a breathing state is obtained, and a breath-holding heartbeat signal of the target object in a breath-holding state is obtained;

[0170] the breath-holding heartbeat signal is taken as an expected signal, the breathing heartbeat signal is taken as an input signal, an initial model is trained by using an LMS algorithm to obtain a trained signal separation model.

[0171] In a possible implementation, when it is detected that the target object is breathing normally, the first signal is sent to a preset position of the target object, and a third signal returned after the first signal contacts the target object is received;

[0172] when it is detected that the target object is holding breath, the first signal is sent to a preset position of the target object, and a fourth signal returned after the first signal contacts the target object is received;

[0173] the third signal is denoised by an empirical mode decomposition algorithm to obtain a denoised breathing heartbeat signal;

[0174] the fourth signal is denoised by an empirical mode decomposition algorithm to obtain a denoised breath-holding heartbeat signal.

[0175] In a possible implementation, a physiological parameter of the target object is determined according to the physiological signal, and the physiological parameter includes a heart rate parameter and a respiration rate parameter.

[0176] State information of the target object is determined according to the physiological parameter.

[0177] A target operation mode of the device is determined according to the state information, and the operation mode includes preset power, preset operation duration, preset air outlet temperature and preset air outlet direction of the device.

[0178] The device is controlled to operate in the target operation mode.

[0179] In a possible implementation, when the heart rate parameter or the respiration rate parameter is in a set threshold range, an alarm event of the device is controlled to occur.

[0180] Those skilled in the art should further appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented by electronic hardware, computer software, or a combination of both. In order to clearly illustrate the interchangeability of hardware and software, the components and steps of each example have been described in general terms above. Whether the functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of the present application.

[0181] The steps of the method or algorithm described in conjunction with the embodiments disclosed herein can be implemented by hardware, a software module executed by a processor, or a combination of both. The software module can be placed in a random access memory (RAM), a memory, a read-only memory (ROM), an electrically programmable ROM, an electrically erasable programmable ROM, a register, a hard disk, a removable disk, a CD-ROM, or any other form of storage medium known in the art.

[0182] The above detailed description of the specific implementation further describes the purpose, technical solution and beneficial effects of the present application. It should be understood that the above description is only a specific implementation of the present application and is not intended to limit the protection scope of the present application. Any modification, equivalent replacement, improvement, etc. made within the spirit and principles of the present application should be included in the protection scope of the present application.

Claims

1. A control method of an apparatus, characterized by, The method comprises the following steps: When a target object is detected to enter a preset area, a first signal is sent to a preset position of the target object, and the first signal is continuously emitted by a radar device; A second signal is received, and the second signal is a signal reflected back by the target object after the first signal contacts the target object; A physiological signal of the target object is extracted from the second signal, comprising: The second signal is denoised by an empirical mode decomposition algorithm to obtain a denoised second signal; The denoised second signal is input into a trained signal separation model, so that the signal separation model outputs a breathing signal and a heartbeat signal of the target object; The breathing signal and the heartbeat signal are used as the physiological signal; The denoising of the second signal by the empirical mode decomposition algorithm comprises: A plurality of IMF component signals of the second signal are determined by an empirical mode decomposition algorithm; A target IMF component signal is determined from the plurality of IMF component signals, and the target IMF component signal is a signal with more noise, and the IMF component signal with an order greater than a set threshold is used as the target IMF component signal; The target IMF component signal is removed to obtain a denoised second signal; The device is controlled according to the physiological signal, comprising: The physiological signal is analyzed to obtain physiological parameters, and the physiological parameters include: respiratory rate, heart rate, signal intensity, distance, and abnormal physical signs, and the distance is the straight-line distance from the radar device to the nearest human body movement part; The current state information of the target object is determined according to the physiological parameters, and the state information includes an impending sleep state, a light sleep state, a deep sleep state, a wakeful state, and a breathing or heartbeat abnormal state; The target working mode of the device is determined according to the state information, and the working mode includes: preset power, preset working time, preset air outlet temperature, and preset air outlet direction of the device, and when the state information is a deep sleep state, the target working mode is a wind direction sweeping wind, and the air conditioner temperature is adjusted to a first preset temperature; The device is controlled to operate in the target working mode.

2. The method of claim 1, wherein, The signal separation model is trained in the following manner: Respiratory heartbeat signals of a target object in a breathing state and breath-holding heartbeat signals of the target object in a breath-holding state are obtained; The breath-holding heartbeat signals are used as expected signals, the respiratory heartbeat signals are used as input signals, an initial model is trained by using an LMS algorithm, and a trained signal separation model is obtained.

3. The method of claim 2, wherein, The respiratory heartbeat signals of the target object in the breathing state and the breath-holding heartbeat signals of the target object in the breath-holding state are obtained in the following manner: When a target object is detected to enter a preset area, a first signal is sent to a preset position of the target object, and the first signal is continuously emitted by a radar device; A second signal is received, and the second signal is a signal reflected back by the target object after the first signal contacts the target object; A physiological signal of the target object is extracted from the second signal, comprising: The second signal is denoised by an empirical mode decomposition algorithm to obtain a denoised second signal; The denoised second signal is input into a trained signal separation model, so that the signal separation model outputs a breathing signal and a heartbeat signal of the target object; The breathing signal and the heartbeat signal are used as the physiological signal; The denoising of the second signal by the empirical mode decomposition algorithm comprises: A plurality of IMF component signals of the second signal are determined by an empirical mode decomposition algorithm; A target IMF component signal is determined from the plurality of IMF component signals, and the target IMF component signal is a signal with more noise, and the IMF component signal with an order greater than a set threshold is used as the target IMF component signal; The target IMF component signal is removed to obtain a denoised second signal; The device is controlled according to the physiological signal, comprising: The physiological signal is analyzed to obtain physiological parameters, and the physiological parameters include: respiratory rate, heart rate, signal intensity, distance, and abnormal physical signs, and the distance is the straight-line distance from the radar device to the nearest human body movement part; The current state information of the target object is determined according to the physiological parameters, and the state information includes an impending sleep state, a light sleep state, a deep sleep state, a wakeful state, and a breathing or heartbeat abnormal state; The target working mode of the device is determined according to the state information, and the working mode includes: preset power, preset working time, preset air outlet temperature, and preset air outlet direction of the device, and when the state information is a deep sleep state, the target working mode is a wind direction sweeping wind, and the air conditioner temperature is adjusted to a first preset temperature; The device is controlled to operate in the target working mode. The signal separation model is trained in the following manner: Respiratory heartbeat signals of a target object in a breathing state and breath-holding heartbeat signals of the target object in a breath-holding state are obtained; The breath-holding heartbeat signals are used as expected signals, the respiratory heartbeat signals are used as input signals, an initial model is trained by using an LMS algorithm, and a trained signal separation model is obtained. The respiratory heartbeat signals of the target object in the breathing state and the breath-holding heartbeat signals of the target object in the breath-holding state are obtained in the following manner: The third signal is denoised by an empirical mode decomposition algorithm to obtain a breathing and heartbeat signal with noise removed; The fourth signal is denoised by an empirical mode decomposition algorithm to obtain a breath-holding and heartbeat signal with noise removed.

4. The method of claim 1, wherein, The device is controlled according to the physiological signal, including: A physiological parameter of the target object is determined according to the physiological signal, and the physiological parameter includes a heart rate parameter and a breathing rate parameter; State information of the target object is determined according to the physiological parameter; A target working mode of the device is determined according to the state information, and the working mode includes preset power, preset working time length, preset air outlet temperature and preset air outlet direction of the device; The device is controlled to operate in the target working mode.

5. The method of claim 4, wherein, The method further includes: When the heart rate parameter or the breathing rate parameter is in a set threshold range, an alarm event of the device is controlled to occur.

6. A control device of an apparatus, characterized by comprising: Including: A sending module is configured to send a first signal to a preset position of a target object when it is detected that the target object enters a preset area, and the first signal is continuously emitted by a radar device; A receiving module is configured to receive a second signal returned after the first signal contacts the target object; An extracting module is configured to extract a physiological signal of the target object from the second signal, including: The second signal is denoised by an empirical mode decomposition algorithm to obtain a denoised second signal; The denoised second signal is input into a trained signal separation model, so that the signal separation model outputs a breathing signal and a heartbeat signal of the target object; The breathing signal and the heartbeat signal are taken as the physiological signal; The second signal is denoised by an empirical mode decomposition algorithm, including: A plurality of IMF component signals of the second signal are determined by an empirical mode decomposition algorithm; A target IMF component signal is determined from the plurality of IMF component signals, the target IMF component signal is a signal with more noise, and an IMF component signal with an order greater than a set threshold is taken as the target IMF component signal; The target IMF component signal is removed to obtain a denoised second signal; A control module is configured to control the device according to the physiological signal, including: The physiological signal is analyzed to obtain a physiological parameter, the physiological parameter includes a breathing rate, a heart rate, a signal strength, a distance and a sign abnormality, and the distance is a straight-line distance from the radar device to the nearest human motion part; State information of the target object is determined according to the physiological parameter, and the state information includes an impending sleep state, a light sleep state, a deep sleep state, a wake state and a breathing or heartbeat abnormality state; A target working mode of the device is determined according to the state information, and the working mode includes preset power, preset working time length, preset air outlet temperature and preset air outlet direction of the device, when the state information is the deep sleep state, the target working mode is a wind direction sweeping wind and the air conditioner temperature is adjusted to a first preset temperature; The device is controlled to operate in the target working mode.

7. An air conditioning apparatus characterized by comprising: Including: A processor configured to execute a control program of the device stored in a memory to implement the control method of the device according to any one of claims 1 to 5.

8. A storage medium, characterized by The storage medium stores one or more programs executable by one or more processors to implement the control method of the device according to any one of claims 1 to 5.

Images