CN115316956A - Sleep detection system and method - Google Patents

Abstract

The invention discloses a sleep detection system and a sleep detection method. The method is characterized by comprising the following steps: the system comprises at least one physiological signal acquisition module and a signal analysis module connected with the physiological signal acquisition module, wherein the physiological signal acquisition module is used for responding to a sleep detection request and acquiring a target physiological signal of a target user corresponding to the sleep detection request under the condition that the target user is in a sleep state; the signal analysis module is used for acquiring the target physiological signal and analyzing the target physiological signal to obtain a sleep detection result. The method and the device realize accurate detection of the sleep of the user and generate a detection report according to the sleep detection result.

Description

Sleep detection system and method

Technical Field

The invention relates to the technical field of sleep detection, in particular to a sleep detection system and method.

Background

With the improvement of the social living standard, the sleep quality and the sleep related diseases gradually enter the visual field of people, the human body can be detected during the sleep of the people, and the sleep quality and the sleep related diseases can be judged through the extracted biological information and characteristics.

In the prior art, when a human body is detected in sleep, physiological information related to sleep is often recorded, cannot be analyzed, cannot provide a corresponding sleep detection result for a user, and cannot directly obtain the sleep detection result.

Disclosure of Invention

The invention provides a sleep detection system and a sleep detection method, which are used for acquiring and detecting signals of a user in a sleep process and analyzing and generating a detection result.

According to an aspect of the present invention, there is provided a sleep detection system including: at least one physiological signal acquisition module and a signal analysis module connected with the physiological signal acquisition module, wherein,

the physiological signal acquisition module is used for responding to a sleep detection request and acquiring a target physiological signal corresponding to the sleep detection request of a target user under the condition that the target user is in a sleep state;

the signal analysis module is used for acquiring the target physiological signal and analyzing the target physiological signal to obtain a sleep detection result.

According to another aspect of the present invention, there is provided a sleep detection method including:

responding to a sleep detection request through at least one physiological signal acquisition module, and acquiring a target physiological signal corresponding to the sleep detection request from the target user under the condition that the target user is in a sleep state;

and acquiring the target physiological signal through a signal analysis module, and analyzing the target physiological signal to obtain a sleep detection result.

According to another aspect of the invention, a sleep detection mattress is provided, comprising a sleep detection system implementing any of the embodiments of the invention.

According to another aspect of the present invention, there is provided a sleep detection wearable device including a sleep detection system according to any embodiment of the present invention.

According to the technical scheme of the embodiment of the invention, the physiological signal acquisition module can be used for acquiring the target physiological signal corresponding to the sleep detection request of the target user under the condition that the target user is in a sleep state, and after the physiological signal acquisition module acquires the target physiological signal, the signal analysis module is used for analyzing the target physiological signal to generate the sleep detection result. Through the physiological signal under the sleep state of acquireing according to user's sleep detection request, and then carry out accurate detection and analysis to the sleep information to show the sleep testing result directly perceived, look over for the user, solved among the prior art unable to carry out the analysis to the physiological information that the sleep is relevant, unable technical problem who provides corresponding sleep testing result, promoted the intelligent degree that the sleep detected.

It should be understood that the statements in this section are not intended to identify key or critical features of the embodiments of the present invention, nor are they intended to limit the scope of the invention. Other features of the present invention will become apparent from the following description.

Drawings

In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings required to be used in the description of the embodiments are briefly introduced below, and it is obvious that the drawings in the description below are only some embodiments of the present invention, and it is obvious for those skilled in the art that other drawings can be obtained according to the drawings without creative efforts.

Fig. 1 is a schematic structural diagram of a sleep detection system according to an embodiment of the present invention;

fig. 2 is a schematic structural diagram of a circuit in which a piezoelectric thin film sensor is connected to two sets of current-voltage conversion circuits according to an embodiment of the present invention;

fig. 3 is a schematic structural diagram of a differential amplifier circuit according to an embodiment of the present invention;

fig. 4 is a schematic structural diagram of a frequency-dependent negative resistance trap circuit according to an embodiment of the present invention;

fig. 5 is a flowchart illustrating a sleep detection method according to an embodiment of the present invention.

Detailed Description

In order to make the technical solutions of the present invention better understood, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be obtained by a person skilled in the art without making any creative effort based on the embodiments in the present invention, shall fall within the protection scope of the present invention.

It should be noted that the terms "first," "second," and the like in the description and claims of the present invention and in the above-described drawings are used for distinguishing between similar users and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used is interchangeable under appropriate circumstances such that the embodiments of the invention described herein are capable of operation in sequences other than those illustrated or described herein. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed, but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.

Fig. 1 is a schematic structural diagram of a sleep detection system according to an embodiment of the present invention, where the embodiment is applicable to a monitoring request during a sleep process of a user, the system may be implemented by a sleep detection device, and the sleep detection device may be implemented in a form of hardware and/or software. As shown in fig. 1, the system includes: at least one physiological signal acquisition module 110 and a signal analysis module 120 connected to the physiological signal acquisition module 110.

The physiological signal acquiring module 110 is configured to, in response to the sleep detection request, acquire a target physiological signal of the target user corresponding to the sleep detection request when the target user is in a sleep state; the signal analysis module 120 is configured to obtain the target physiological signal, and analyze the target physiological signal to obtain a sleep detection result.

The sleep detection request may be an operation of a user to start sleep detection in the sleep detection system through the user operation module. Wherein the sleep detection result comprises disease early warning information and/or health guidance information. The health guidance information may be information for guiding the user to develop a healthy lifestyle habit. Illustratively, the health guidance information may include at least one of diet advice information, work and rest advice information, and exercise advice information.

For example, a user may specifically acquire a target physiological signal corresponding to a sleep detection type through the physiological signal acquisition module 110, and then analyze the target physiological signal through the signal analysis module 120 to obtain a sleep detection result.

Optionally, in another embodiment of the present invention, the sleep detection system further includes: the system comprises a user information input module and a user information storage module; the user information input module is used for receiving user basic information input by a target user; the user information storage module is used for storing the basic information of the user and correspondingly storing the acquired target physiological signal, the physiological detection result and the basic information of the user.

The user basic information may be basic information related to sleep detection, which is entered by a user. Exemplary user basic information includes, but is not limited to: at least one of name, gender, age, height, weight, physical condition, and disease history.

Specifically, a target user can select an enabling control of the user information entry module in the sleep detection system, the sleep detection system opens an interface for user information entry according to a triggering operation of the target user for triggering the enabling control of the user information entry module, an input box corresponding to the basic information of the user is displayed in the interface for user information entry, and the target user inputs the basic information of the user in the corresponding input box. Further, the user information entry module is further configured to receive a confirmation trigger operation that a user acts on an information confirmation control, and send the user basic information to the user information storage module, so as to complete entry and storage of the basic information. Besides the enabling control and the information confirming control, the user information input interface can also comprise other information editing controls, such as an information selection button, an operation cancel button, an information deletion control and the like. It is understood that the representation form of the control may be various, for example, it may be in a button form, a progress bar form, a disk form, or a touch area, and the like, and the display form of the control is not limited herein.

Specifically, the user information storage module stores the user basic information input by the target user after the target user input module receives the user basic information input by the target user, and correspondingly stores the acquired target physiological signal, the physiological detection result and the user basic information. The method has the advantages that the user information and the users can be correspondingly stored, the targeted management is realized, the method is particularly suitable for the condition that a plurality of users use the same sleep detection system, the information confusion and the storage confusion are avoided, and the information of each user can be conveniently checked and managed.

Optionally, the user information storage module may be a local storage server and/or a cloud storage space in the sleep detection system, after receiving the entered user basic information, the entered user basic information is sent to the local storage server and/or the cloud storage space, after receiving the user basic information, the local storage server and/or the cloud storage space creates a corresponding storage space according to the user basic information, and is used for storing the user basic information of the target user, and when the acquired target physiological signal and physiological detection result are obtained, the target physiological signal and physiological detection result are stored in the storage space corresponding to the user basic information.

Optionally, in another embodiment of the present invention, the sleep detection system further includes: and the user information verification module is used for acquiring the basic information of the target user and verifying the basic information of the target user. Specifically, the user information verification module obtains the basic information of the target user after the target user entry module receives the basic information of the user entered by the target user, performs information verification on the basic information of the target user, compares the obtained basic information of the user with the basic information of the target user, and determines whether the entered basic information of the user is the same as the basic information of the target user, if so, the verification is successful, and if not, the verification fails. The method has the advantage that under the condition that basic information of the user needs to be verified, such as information storage, information inquiry, information modification and the like, the safety of information application can be effectively ensured through user information verification.

Optionally, in another embodiment of the present invention, the system further includes: the user operation module is connected with the physiological signal acquisition module; the user operation module is used for receiving a sleep detection request of a user and determining a physiological signal acquisition module corresponding to the sleep detection request.

Optionally, the user operation module may include a request input control for determining a sleep detection mode and/or a sleep detection type. The sleep detection mode comprises a mode for manually selecting a sleep detection type and a mode for automatically selecting the sleep detection type, wherein the sleep detection type comprises a disease type, a physiological index, a sleep stage, a health level and/or the like. The disease type may include, among others, sleep apnea syndrome and/or atrial fibrillation. For example, the physiological index may be heart rate, respiration rate, sleep depth, blood oxygen saturation, muscle activity status, and the like.

Optionally, the user operation module may be specifically configured to receive a sleep detection request input for the request input control. For example, a user may trigger a request input control for determining a sleep detection type to generate a sleep detection request.

Optionally, in another embodiment of the present invention, the system further includes: the information display module is connected with the signal analysis module; the information display module is used for acquiring the sleep detection result and displaying the sleep detection result.

Specifically, the signal analysis module 120 analyzes the target physiological signal to obtain a sleep detection result, and sends the sleep detection result to the information display module, and the information display module displays the sleep detection result on the information display module after obtaining the sleep detection result. In an embodiment of the present invention, the target physiological signal may be a physiological signal detected during a sleep detection process of the user. Illustratively, the target physiological signal may be an electrical cardiac signal, a cardiac cycle, a muscle electrical signal, esophageal pressure, upper airway resistance and ventilation, and the like.

Specifically, when the user performs sleep detection, the physiological signal collection module 110 is disposed at the target detection position of the user according to the target victory signal to be collected. The physiological signal collecting module 110 responds to the sleep detection request, and collects a target physiological signal corresponding to the sleep detection request from the target user when the target user is in a sleep state.

Optionally, in another embodiment of the present invention, the physiological signal acquisition module includes a cardiac shock signal acquisition unit, and the cardiac shock signal acquisition unit includes a piezoelectric thin film sensor, two sets of current-voltage conversion circuits, a differential amplification circuit, and a frequency-dependent negative resistance type trap circuit, where the two sets of current-voltage conversion circuits are respectively connected to two ends of the piezoelectric thin film sensor, and are configured to convert interference noise introduced by coupling between two electrode plates of the piezoelectric thin film sensor and the outside into a common mode signal for output, and convert a cardiac shock signal into a differential mode signal for output; the differential amplification circuit is connected with the current-voltage conversion circuit and is used for amplifying the differential mode signal and inhibiting the common mode signal; the frequency-variable negative resistance type trap circuit is connected with the differential amplification circuit and is used for filtering power frequency interference in an output signal of the differential amplification circuit.

Fig. 2 is a schematic structural diagram of a circuit in which a piezoelectric thin film sensor and two sets of current-voltage conversion circuits are connected according to an embodiment of the present invention, and as shown in fig. 2, the two sets of current-voltage conversion circuits are respectively connected to two ends of the piezoelectric thin film sensor, and are used for converting interference noise introduced by coupling between two electrode plates of the piezoelectric thin film sensor and the outside into a common mode signal and converting a ballistocardiogram signal into a differential mode signal to be output. The PVDF is a piezoelectric film sensor, C1 is a first current-voltage conversion circuit first capacitor, R1 is a first change circuit resistor, C3 is a first change circuit second capacitor, U1 is a first operational amplifier, C2 is a second change circuit first capacitor, R2 is a second change circuit resistor, C4 is a second change circuit second capacitor, U2 is a second operational amplifier, VOUT + is an output voltage anode, VOUT-is an output voltage cathode.

Fig. 3 is a schematic structural diagram of a differential amplifier circuit according to an embodiment of the present invention, as shown in fig. 3: the differential amplification circuit is connected with the current-voltage conversion circuit, amplifies the differential mode signal through the positive input end and the negative input end of the direct current, inhibits the common mode signal and outputs the amplified differential mode signal. VIN + is the positive pole of the input voltage, VIN-is the negative pole of the input voltage, R1 is the first resistor, R2 is the second resistor, VOUT is the output end of the circuit.

Fig. 4 is a schematic structural diagram of a frequency-dependent negative resistance type trap circuit according to an embodiment of the present invention, as shown in fig. 4: after the input signal is input into the frequency-variable negative resistance type trap circuit, the power frequency interference in the output signal of the differential amplification circuit is filtered by a low-pass filter and a high-pass filter, then the filtered output signal is amplified by a differential amplifier, and the filtered and amplified differential mode signal is output. The embodiment of the invention adopts measures such as an active shielding layer driving circuit and the like to further reduce the interference introduced by the outside, and can acquire the heart impact signal with high accuracy and strong stability. VIN is an input voltage, R1 is an adjustable resistor, C1 is a first capacitor, C2 is a second capacitor, C3 is a third capacitor, R is a filter resistor, U1 is a first operational amplifier, U2 is a second operational amplifier, U3 is a third operational amplifier, and VOUT is an output voltage.

Optionally, in another embodiment of the present invention, the physiological signal acquiring module further includes: at least one of a heart-shake signal acquisition unit, an electrocardiosignal acquisition unit and an electroencephalogram signal acquisition unit.

The heart attack signal acquisition unit is used for acquiring physiological signals reflecting mechanical motion of the heart, and the heart rate and the respiratory rate can be calculated through the heart attack signals. Illustratively, the cardiac shock signal can be collected by using the piezoelectric film sensor as a cardiac shock signal collecting unit. The heart-shaking signal acquisition unit is used for acquiring vibration signals generated by a body when the heart beats periodically. For example, the seismic signal acquisition unit typically places the sensor at the chest of the user. The electrocardiosignal acquisition unit is used for acquiring electric signals reflecting the heart fluctuation. The brain electrical signal acquisition unit is used for acquiring electrophysiological activity of the cranial nerve tissue to generate an electrical signal. Optionally, after the physiological signal acquisition module 110 acquires the target physiological signal, the target physiological signal is sent to the signal analysis module 120, the signal analysis module 120 acquires the target physiological signal and analyzes the target physiological signal to obtain a sleep detection result, and the signal analysis module 120 sends the sleep detection result to the information display module through the sleep detection system. The sleep detection result is used for reflecting the sleep condition of the target user.

Optionally, the information display module obtains the sleep detection result through the sleep detection system, and displays the sleep detection result through the visual display area.

According to the technical scheme of the embodiment of the invention, the physiological signal acquisition module can acquire the target physiological signal corresponding to the sleep detection request of the target user under the condition that the target user is in a sleep state, and the signal analysis module analyzes the target physiological signal after the physiological signal acquisition module acquires the target physiological signal to generate the sleep detection result. Through the physiological signal under the sleep state of acquireing according to user's sleep detection request, and then carry out accurate detection and analysis to the sleep information to show the sleep testing result directly perceived, look over for the user, solved among the prior art unable to carry out the analysis to the physiological information that the sleep is relevant, unable technical problem who provides corresponding sleep testing result, promoted the intelligent degree that the sleep detected.

Optionally, in another embodiment of the present invention, the signal analysis module is specifically configured to acquire the target physiological signal, extract a target characteristic parameter corresponding to the sleep detection request in the target physiological signal, and determine a sleep detection result according to the target characteristic parameter.

The target characteristic parameter may be a characteristic parameter that can feed back a sleep state of the user, and for example, the target characteristic parameter may be a heart rate parameter, a respiration rate parameter, and the like.

Specifically, the signal analysis module 120 obtains the target physiological signal, extracts a target characteristic parameter corresponding to the sleep detection request from the target physiological signal according to the sleep detection request, and determines the sleep detection result according to the target characteristic parameter.

Optionally, the signal analysis module is specifically configured to extract a target feature parameter corresponding to the sleep detection request from the target physiological signal through a preset feature extraction algorithm or a pre-trained feature extraction network, where the preset feature extraction algorithm includes at least one of a peak detection method, a wavelet decomposition method, a low-pass filtering method, a high-pass filtering method, a power spectral density analysis method, and an envelope detection method, and the feature extraction network is trained based on the sample physiological signal and an expected feature parameter corresponding to the sample physiological signal.

Specifically, the signal analysis module 120 obtains the target physiological signal, determines a preset feature extraction algorithm according to the sleep detection request, extracts a target feature parameter corresponding to the sleep detection request from the target physiological signal according to the preset feature extraction algorithm, and determines the sleep detection result according to the target feature parameter.

Optionally, the signal analysis module 120 obtains a target physiological signal, inputs the target physiological signal to the feature extraction network, and the feature extraction network outputs a target feature parameter corresponding to the sleep detection request, and determines the sleep detection result according to the target feature parameter.

Illustratively, training the feature extraction network training process based on the sample physiological signal and the expected feature parameters corresponding to the sample physiological signal is as follows: inputting the sample physiological signal into a feature extraction network to be trained, outputting a training feature parameter by the feature extraction network according to the input sample physiological signal, performing loss calculation on the output training feature parameter and an expected feature parameter corresponding to the sample physiological signal, and adjusting parameters in the feature extraction network to be trained according to the calculated loss. And when the loss function convergence in the feature extraction network to be trained is detected, finishing the training of the feature extraction network to be trained to obtain the feature extraction network. The loss function of the feature extraction network may include, but is not limited to: a mean square error function, a mean absolute value error function, and a cross entropy error function.

Optionally, the signal analysis module is specifically configured to determine a sleep detection result according to the target characteristic parameter and a pre-trained sleep detection model, where the sleep monitoring model is trained based on a sample characteristic parameter and an expected detection result corresponding to the sample characteristic parameter.

Specifically, after the signal analysis module 120 extracts the target characteristic parameters, the target characteristic parameters are input to the sleep monitoring model, and the sleep monitoring model determines and outputs the sleep detection result according to the input target characteristic parameters.

Illustratively, the training process of training the sleep monitoring model based on the sample characteristic parameters and the expected detection results corresponding to the sample characteristic parameters is as follows: inputting the sample characteristic parameters into a sleep monitoring model to be trained, outputting a training detection result by the sleep monitoring model according to the input sample characteristic parameters, performing loss calculation on the output training detection result and an expected detection result corresponding to the sample characteristic parameters, and adjusting parameters in the sleep monitoring model to be trained according to the calculated loss. And when the convergence of the loss function in the sleep monitoring model to be trained is detected, finishing the training of the sleep monitoring model to be trained to obtain the sleep monitoring model. The loss function of the sleep monitoring model may include, but is not limited to: a mean square error function, a mean absolute value error function, and a cross entropy error function.

Optionally, in another embodiment of the present invention, the signal analysis module 120 is further configured to acquire a ballistocardiogram signal, perform analog-to-digital conversion on the acquired ballistocardiogram signal through the signal conversion unit, further perform low-pass filtering and high-pass filtering on the signal, and generate a smooth ballistocardiogram signal that meets the preset sampling rate. For example, the ballistocardiogram signal with the preset sampling rate may be a 125HZ ballistocardiogram signal.

Optionally, the signal analysis module 120 sends the ballistocardiogram signal to the signal processing unit through the communication bus after acquiring the ballistocardiogram signal with the preset sampling rate, and the signal processing unit performs signal detection on the ballistocardiogram signal after receiving the ballistocardiogram signal through the communication bus, detects a target waveform in the ballistocardiogram signal, and then calculates the heart rate parameter according to the target waveform in the ballistocardiogram signal. The signal detection method may be a peak detection method, and the target waveform may include, but is not limited to, any one of a J wave, a QRS complex, a P wave, and a T wave.

Furthermore, the signal processing unit is further configured to extract a cardiac cycle component from the cardiac shock signal, and separate a respiratory component included in the cardiac cycle component according to the extracted cardiac cycle component. Illustratively, the signal processing unit separates the respiratory component included in the cardiac cycle component from the extracted cardiac cycle component as follows: firstly, 5-order DB6 wavelet decomposition is carried out on an original heart attack signal, the original heart attack signal is divided into 5-order detail coefficients and first-order approximation coefficients, the 1-order and 2-order detail coefficients are used as base signals for heart rate extraction, and the approximation coefficients are used as base signals for respiration rate extraction. Wherein, the detail coefficient of 5 th order and the approximation coefficient of first order reflect the signal characteristics in different frequency ranges respectively.

Optionally, the signal processing unit is further configured to perform signal processing on the high-frequency oscillation included in the cardiac shock signal through envelope detection according to the high-frequency oscillation included in the cardiac shock signal, accurately estimate parameters, determine a processed reconstructed signal, perform power spectral density analysis on the reconstructed signal, extract a local maximum value of the main frequency band, and perform extraction operation to extract the heart rate and the respiratory rate.

Optionally, the signal processing unit is further configured to monitor a target disease, and perform early warning when the target disease is monitored.

Illustratively, the target disease is sleep apnea syndrome: the signal processing unit divides the cardiac shock signal into 20S segments, carries out DB6 wavelet decomposition on the signal to remove high-frequency noise, uses detail coefficients as base signals for sleep apnea syndrome evaluation, extracts relevant features of the sleep apnea syndrome through a feature extraction network, judges whether a sleep apnea event occurs, records the frequency of the sleep apnea event per hour if the sleep apnea event occurs, and then judges whether the user suffers from the sleep apnea syndrome according to the frequency of the sleep apnea event per hour.

Illustratively, the target disease is atrial fibrillation disease: after filtering the original cardioverter signal, the signal processing unit frames the filtered cardioverter signal at intervals of a preset time period (such as 20 seconds) to generate a framed cardioverter frame signal, a time domain, a frequency domain and a time-frequency joint feature of the cardioverter frame signal are extracted for each cardioverter frame signal through a feature extraction network, then a sleep monitoring model is used for carrying out sleep detection on a user, and a sleep detection result is output according to the sleep monitoring model to determine whether the user has atrial fibrillation diseases. According to the embodiment of the application, the sleep condition can be objectively evaluated through long-range multi-night monitoring and recording, the influence of the first-night effect is avoided, and the insomnia condition is objectively evaluated.

Optionally, in another embodiment of the present invention, the information display module is further configured to receive a target physiological signal sent by the physiological signal acquisition module, and generate and display a time-domain waveform diagram and/or a frequency spectrum diagram of the target physiological signal according to the target physiological signal.

Specifically, the physiological signal acquisition module 110 further sends the target physiological signal to the information display module after acquiring the target physiological signal, and the information display module generates and displays a time-domain oscillogram and/or a frequency spectrogram of the target physiological signal according to the target physiological signal after receiving the target physiological signal.

Optionally, the information display module is further configured to be connected to the sleep data management module, and after receiving the target physiological signal, the information display module sends the target physiological signal to the sleep data management module.

The sleep data management module is a data management module based on WEB design.

Specifically, after receiving the target physiological signal, the information display module sends the target physiological signal to the sleep data management module. And the sleep data management module automatically marks events such as sleep time, heart impact events and the like according to the target physiological signal after receiving the target physiological signal, and marks and displays corresponding events in the target physiological signal. The sleep data management module is also used for accurately identifying the waveform of the target physiological signal and forming a sleep report. According to the embodiment of the invention, the data management module can be used for diagnosing and differentially diagnosing the insomnia patient, and the detailed sleep structure data analysis and the sleep respiration related event analysis are adopted, so that the data of the patient can be conveniently and effectively screened, and the long-term curative effect of the insomnia patient can be effectively evaluated.

The embodiment of the invention discloses a sleep detection mattress, which comprises the sleep detection system provided by any embodiment of the invention.

Wherein, sleep detection mattress includes: the mattress body, still set up the sensor that is used for physiological signal to gather in the mattress body, realize when the user sleeps at the mattress body, detect the microsoft pressure conversion that mattress body surface received according to the sensor that sets up in the mattress body and become charge output, and then realize on the sleep detects the mattress and then to user physiological signal's non-contact detection. Illustratively, the sensor disposed in the mattress body may be a flexible film sensor.

Optionally, still set up the bluetooth module that is used for communicating with sleep analytic system in the mattress body, and then detect the mattress in sleep and detect behind the heart impact signal, detect communication bus in the mattress through sleep and will heart impact signal transmission to bluetooth module, realize sleep and detect mattress and sleep analytic system's data transmission. The sleep analysis system is used for connecting the sleep detection mattress, acquiring human physiological signals through the sleep detection mattress and storing and recording physiological signal data in the system; the historical physiological signal data is checked through the sleep analysis system, and the physiological signal data can be edited, modified and deleted.

The sleep detection mattress disclosed by the embodiment of the invention can execute the sleep detection system provided by any embodiment of the invention, has rich application scenes, is simple in design and operation, and supports home environment monitoring.

The embodiment of the invention discloses a sleep detection wearable device, which comprises the sleep detection system provided by any embodiment of the invention.

The sleep detection wearable device can be directly worn on a user, and the sleep detection function is realized through software support, data interaction and cloud interaction. The sleep detection wearable device can detect the activity states of the sleep detection wearable device and a user by a multi-axis gyroscope and an acceleration sensor which are arranged in the sleep detection wearable device, judge the sleep state of the user through the activity state of the user, and judge that the user enters the sleep state when the activity state of the user is small. The sleep detection wearable device is characterized in that the flexible film sensor is arranged in the sleep detection wearable device, when the sleep state of a user is judged, microsoft pressure on the surface of the sleep detection wearable device is converted into electric charge output through the flexible film sensor, and therefore non-contact detection of physiological signals of the user on the sleep detection device is achieved.

Optionally, the sleep detection wearable device is further provided with a bluetooth module for communicating with the sleep analysis system, and then after the sleep detection wearable device detects the heartbeat signal, the heartbeat signal is transmitted to the bluetooth module through a communication bus in the sleep detection wearable device, so that data transmission between the sleep detection wearable device and the sleep analysis system is realized. The sleep analysis system is also used for connecting the sleep detection wearable equipment, acquiring human body physiological signals through the sleep detection wearable equipment, judging the sleep state of a user, and storing and recording physiological signal data in the system; the historical physiological signal data is checked through the sleep analysis system, and the physiological signal data can be edited, modified and deleted.

Optionally, in another optional embodiment disclosed in the embodiment of the present invention, the sleep detection wearable device is at least one of a thoraco-abdominal breathing belt, a wrist-worn device, and a head-worn device.

Alternatively, the thoracoabdominal breathing belt may be a belt-shaped sleep detection device worn by the user on the thoracoabdominal region. Exemplarily, the user dresses chest abdomen respiratory belt when sleeping, and chest abdomen respiratory belt detects the user through setting up behind the multiaxis gyroscope and the acceleration sensor in inside and gets into the sleep state, turns into the output of electric charge through the flexible film sensor who sets up in chest abdomen respiratory belt with the microsoft pressure that chest abdomen respiratory belt surface received, sends the physiological signal who gathers to sleep analytic system through bluetooth module, and then realizes on chest abdomen respiratory belt and then to user's physiological signal's non-contact detection.

Optionally, the wrist-worn device may include at least one of a wristband, a watch, and a wrist strap. Exemplarily, a user wears the wrist wearable device daily, the wrist wearable device detects the activity state of the user through a multi-axis gyroscope and an acceleration sensor arranged inside the wrist wearable device, after the user is detected to enter a sleep state, microsoft pressure on the surface of the wrist wearable device is converted into charge output through a flexible film sensor arranged in the wrist wearable device, the collected physiological signals are sent to a sleep analysis system through a communication module arranged in the wrist wearable device, and then non-contact detection of the physiological signals of the user on the wrist wearable device is achieved.

Alternatively, the head-worn device may be a sleep detection device worn by the user over the head of the wrapped user. Exemplarily, the user wears head-mounted device when sleeping, and head-mounted device detects the user through setting up behind multi-axis gyroscope and the acceleration sensor in inside and gets into the sleep state, turns into the output of electric charge through the flexible film sensor who sets up in head-mounted device with the microsoft pressure that head-mounted device surface received, sends the physiological signal who gathers to sleep analytic system through bluetooth module, and then realizes on head-mounted device and then to user's physiological signal's non-contact detection.

Alternatively, the head-worn device may be a sleep detection device worn on other parts of the head, for example, an eye mask worn on the eyes, or the like.

The sleep detection wearable device disclosed by the embodiment of the invention has the functions and beneficial effects of the sleep detection system provided by any embodiment of the invention, has rich application scenes, is simple to design and operate, and supports home environment monitoring.

Fig. 5 is a schematic flowchart of a sleep detection method provided in an embodiment of the present invention, where the embodiment is applicable to a monitoring request during a sleep process of a user, the method may be executed by a sleep detection system, and the sleep detection system may be implemented in a form of hardware and/or software. As shown in fig. 5, the method includes:

s210, responding to the sleep detection request through a physiological signal acquisition module, and acquiring a target physiological signal corresponding to the sleep detection request from a target user under the condition that the target user is in a sleep state.

S220, acquiring the target physiological signal through a signal analysis module, and analyzing the target physiological signal to obtain a sleep detection result.

Optionally, the physiological signal acquisition module includes a ballistocardiogram signal acquisition unit, the ballistocardiogram signal acquisition unit includes a piezoelectric film sensor, two sets of current-voltage conversion circuits, a differential amplifier circuit and a frequency-dependent negative resistance type trap circuit, wherein, the two sets of current-voltage conversion circuits are respectively connected at two ends of the piezoelectric film sensor, the differential amplifier circuit is connected with the current-voltage conversion circuits, and the frequency-dependent negative resistance type trap circuit is connected with the differential amplifier circuit.

The method may further comprise:

interference noise introduced by coupling the two polar plates of the piezoelectric film sensor with the outside is converted into a common-mode signal through the two groups of current-voltage conversion circuits for output, and a heart impact signal is converted into a differential-mode signal for output;

amplifying the differential mode signal and suppressing the common mode signal through the differential amplifying circuit;

and filtering power frequency interference in the output signal of the differential amplifying circuit through the frequency-variable negative resistance type trap circuit.

Optionally, the physiological signal acquisition module further includes: at least one of a heart-shake signal acquisition unit, an electrocardiosignal acquisition unit and an electroencephalogram signal acquisition unit.

Optionally, the method further includes:

and acquiring the target physiological signal through a signal analysis module, extracting a target characteristic parameter corresponding to the sleep detection request in the target physiological signal, and determining a sleep detection result according to the target characteristic parameter.

Optionally, the method further includes:

extracting target characteristic parameters corresponding to the sleep detection request in the target physiological signals through a signal analysis module through a preset characteristic extraction algorithm or a pre-trained characteristic extraction network, wherein the preset characteristic extraction algorithm comprises at least one of a peak value detection method, a wavelet decomposition method, a low-pass filtering method, a high-pass filtering method, a power spectral density analysis method and an envelope detection method, and the characteristic extraction network is obtained based on sample physiological signals and expected characteristic parameters corresponding to the sample physiological signals.

Optionally, the method further includes:

and determining a sleep detection result through a signal analysis module according to the target characteristic parameters and a pre-trained sleep detection model, wherein the sleep detection model is obtained by training based on sample characteristic parameters and expected detection results corresponding to the sample characteristic parameters.

Optionally, the method further includes:

and receiving the target physiological signal sent by the physiological signal acquisition module through an information display module, and obtaining a time domain oscillogram and/or a frequency spectrogram of the target physiological signal.

Optionally, the method further includes:

receiving user basic information input by a target user through a user information input module;

and storing the basic information of the user through a user information storage module, and correspondingly storing the acquired target physiological signal, the physiological detection result and the basic information of the user.

Optionally, the method further includes:

and obtaining the basic information of the target user through a user information verification module, and performing information verification on the basic information of the target user.

Optionally, the sleep detection system further includes a user operation module.

Accordingly, the method may further comprise:

the method comprises the steps of receiving a sleep detection request of a user through a user operation module, and determining a physiological signal acquisition module corresponding to the sleep detection request.

Optionally, the sleep detection system further includes an information display module.

Accordingly, the method may further comprise:

and acquiring the sleep detection result through an information display module, and displaying the sleep detection result.

According to the technical scheme of the embodiment of the invention, the physiological signal acquisition module can acquire the target physiological signal corresponding to the sleep detection request of the target user under the condition that the target user is in a sleep state, and the signal analysis module analyzes the target physiological signal after the physiological signal acquisition module acquires the target physiological signal to generate the sleep detection result. The physiological signals under the sleep state are acquired according to the sleep detection request of the user, so that the sleep information is accurately detected and analyzed, and the sleep detection result is visually displayed for the user to check, so that the technical problems that the physiological information related to sleep cannot be analyzed and the corresponding sleep detection result cannot be provided in the prior art are solved, and the intelligent degree of sleep detection is improved.

It should be understood that various forms of the flows shown above, reordering, adding or deleting steps, may be used. For example, the steps described in the present invention may be executed in parallel, sequentially, or in different orders, and are not limited herein as long as the desired results of the technical solution of the present invention can be achieved.

The above-described embodiments should not be construed as limiting the scope of the invention. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions may be made in accordance with design requirements and other factors. Any modification, equivalent replacement, and improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims (15)

1. A sleep detection system, comprising: at least one physiological signal acquisition module and a signal analysis module connected with the physiological signal acquisition module, wherein,

the physiological signal acquisition module is used for responding to a sleep detection request, and acquiring a target physiological signal corresponding to the sleep detection request from a target user under the condition that the target user is in a sleep state;

the signal analysis module is used for acquiring the target physiological signal and analyzing the target physiological signal to obtain a sleep detection result.

2. The sleep detection system according to claim 1, wherein the physiological signal collection module comprises a ballistocardiographic signal collection unit, the ballistocardiographic signal collection unit comprises a piezoelectric film sensor, two sets of current-to-voltage conversion circuits, a differential amplification circuit and a frequency-dependent negative resistance type trap circuit, wherein,

the two groups of current-voltage conversion circuits are respectively connected to two ends of the piezoelectric film sensor and are used for converting interference noise introduced by coupling of two polar plates of the piezoelectric film sensor with the outside into a common-mode signal to be output and converting a heart impact signal into a differential-mode signal to be output;

the differential amplification circuit is connected with the current-voltage conversion circuit and is used for amplifying the differential mode signal and inhibiting the common mode signal;

the frequency-variable negative resistance type trap circuit is connected with the differential amplification circuit and is used for filtering power frequency interference in an output signal of the differential amplification circuit.

3. The sleep detection system as claimed in claim 2, wherein the physiological signal acquisition module further comprises: at least one of a heart-shake signal acquisition unit, an electrocardiosignal acquisition unit and an electroencephalogram signal acquisition unit.

4. The sleep detection system according to claim 1, wherein the signal analysis module is specifically configured to obtain the target physiological signal, extract a target characteristic parameter corresponding to the sleep detection request from the target physiological signal, and determine a sleep detection result according to the target characteristic parameter.

5. The sleep detection system according to claim 4, wherein the signal analysis module is specifically configured to extract the target feature parameters corresponding to the sleep detection request from the target physiological signal through a preset feature extraction algorithm or a pre-trained feature extraction network, wherein the preset feature extraction algorithm includes at least one of a peak detection method, a wavelet decomposition method, a low-pass filtering method, a high-pass filtering method, a power spectral density analysis method, and an envelope detection method, and the feature extraction network is trained based on the sample physiological signal and the expected feature parameters corresponding to the sample physiological signal.

6. The sleep detection system according to claim 4, wherein the signal analysis module is specifically configured to determine a sleep detection result according to the target characteristic parameter and a pre-trained sleep detection model, wherein the sleep monitoring model is trained based on a sample characteristic parameter and an expected detection result corresponding to the sample characteristic parameter.

7. The sleep detection system as claimed in claim 1, further comprising: the system comprises a user information input module and a user information storage module; wherein the content of the first and second substances,

the user information input module is used for receiving user basic information input by a target user;

the user information storage module is used for storing the user basic information and correspondingly storing the acquired target physiological signal, the physiological detection result and the user basic information.

8. The sleep detection system as claimed in claim 7, further comprising: a user information verification module, wherein,

and the user information verification module is used for acquiring the basic information of the target user and verifying the basic information of the target user.

9. The sleep detection system as claimed in claim 1, further comprising: the user operation module is connected with the physiological signal acquisition module; wherein the content of the first and second substances,

the user operation module is used for receiving a sleep detection request of a user and determining a physiological signal acquisition module corresponding to the sleep detection request.

10. The sleep detection system as claimed in claim 1, further comprising: the information display module is connected with the signal analysis module; wherein the content of the first and second substances,

and the information display module is used for acquiring the sleep detection result and displaying the sleep detection result.

11. The sleep detection system according to claim 10, wherein the information presentation module is further configured to receive the target physiological signal sent by the physiological signal acquisition module, and generate and present a time-domain waveform diagram and/or a frequency spectrum diagram of the target physiological signal.

12. A sleep detection mattress characterized in that it comprises a sleep detection system according to any one of claims 1-11.

13. A sleep detection wearable device, comprising: the sleep detection wearable device comprising a sleep detection system as claimed in any one of claims 1 to 11.

14. The sleep detection wearable device of claim 13, wherein the sleep detection wearable device is at least one of a thoraco-abdominal breathing belt, a wrist-worn device, and a head-worn device.

15. A sleep detection method, comprising:

responding to a sleep detection request through at least one physiological signal acquisition module, and acquiring a target physiological signal corresponding to the sleep detection request from a target user under the condition that the target user is in a sleep state;

and acquiring the target physiological signal through a signal analysis module, and analyzing the target physiological signal to obtain a sleep detection result.

Images