CN106175770A - Apneic determination methods and system during a kind of sleep - Google Patents

Abstract

The present invention relates to a method and system for judging apnea during sleep, wherein the method comprises: step 1: collecting sleep breathing signals during sleep of a subject in real time; step 2: processing the sleep breathing signals to obtain a respiration rate waveform Figure and pulse rate waveform; step 3: analyze the respiration rate waveform and pulse rate waveform to determine whether apnea occurs during sleep. Therefore, the present invention realizes the determination of sleep suspension without contacting the subject through the above-mentioned scheme, no radiation, accurate detection results, easy to carry, convenient and fast to use, and can satisfy the needs of users at home or on business trips. It can be used in the detection and investigation of apnea in other environments, reducing time and money costs.

Description

Method and system for judging apnea during sleep

technical field

The invention relates to a sleep apnea detection technology suitable for daily life environment, in particular to a sleep apnea detection technology which monitors breathing, pulse and other vital signs during sleep in a non-contact manner and judges the apnea state during sleep. A method and system for judging period apnea.

Background technique

Sleep Apnea Syndrome—Sleep Apnea Syndrome (SAS) is a common disease that occurs during sleep. Specifically, it refers to repeated episodes of apnea for more than 30 times or more during 7 hours of sleep per night. A sleep apnea-hypopnea index (usually abbreviated as AHI) ≥ 5 times/hour and accompanied by clinical symptoms such as lethargy. SAS has become an invisible killer that endangers human life. According to statistics, SAS patients diagnosed and treated in developed countries account for 20% of the total number of patients, and our country accounts for 2%. The main reason is that the standard monitoring method polysomnography (PSG) has a complicated process, high cost, and poor user experience, which makes it difficult to popularize and apply. Therefore, researching a convenient and highly accurate detection method to replace PSG will provide strong technical support for the early detection and diagnosis of SAS patients, and has high practical value.

At present, the existing methods for detecting sleep apnea syndrome generally have the following types:

1. Reduce the physiological parameters of PSG measurement and measure the main parameters related to sleep apnea: for example, patent document CN202776304U discloses a device for analyzing sleep apnea events, which uses mouth and nose airflow sensors, chest and abdomen breathing motion sensors, body position sensors A variety of physiological signals are detected to identify the occurrence of sleep breathing events. Although this type of method has fewer monitoring parameters than PSG, it still requires the subject to wear a variety of sensors, which affects the sleep state of the subject.

2. Adopt a non-contact measurement method or use fewer monitoring signals to make the operation as simple as possible and have as little impact on the user's sleep as possible: as the patent document CN102475541A discloses a simple sleep state breathing pulse detection alarm device, using Breathing sounds and body temperature sensors are used to monitor, that is, a loudspeaker is set at the bedside while using a body temperature sensor, and breathing movements during sleep are monitored based on the body temperature and breathing sounds of the subject in sleep. Since this type of method distinguishes the state of apnea mainly based on breath sounds, it is possible to identify sounds in the same frequency band as breath sounds as breath sounds, which has the problem of low measurement accuracy.

3. Use other physiological characteristics to judge apnea: For example, the patent document CN102973244A discloses a non-contact sleep apnea monitoring method and device based on thermal infrared imaging technology, which uses a thermal imager to collect real-time data from the nostrils and oral cavity during human sleep. Thermal infrared images, enabling non-contact monitoring of sleep apnea by analyzing images. For example, patent document CN102641125A discloses a sleep apnea judging device, which realizes judging the apnea state by detecting reflected waves of microwaves emitted by the detected chest and abdomen during sleep. This type of method must be based on the detection of the subject's nostrils to achieve thermal imaging, and the use of microwave reflections has a certain impact on the health and safety of the subject. Both of these methods affect the normal sleep health of the subject. Long-term use There may even be potential safety hazards.

4. Apply artificial intelligence technology to improve detection accuracy: For example, patent document CN103083770A discloses a system and method for diagnosing and treating patients' breathing patterns, which monitors the patient's airflow through an oral and nasal mask, and records the median, average, and The range and standard deviation are summed and input to the neural network, and the patient status is detected through the neural network. Also as the patent document CN103690168A discloses a detection method of obstructive sleep apnea syndrome, by detecting three parameters of blood oxygen saturation, snoring sound and breathing signal, according to the artificial intelligence decision theory, a fuzzy element set membership function is constructed, and then passed The principle of maximum membership determines whether to suffer from sleep apnea syndrome. Algorithms such as neural networks and maximum membership elements used in such methods lack certain prior knowledge, and lack credibility in the judgment process of apnea.

Therefore, the above-mentioned methods for judging apnea all need to rely on PSG, which is complex and cumbersome and has extremely low user experience, and can only be detected and checked in a hospital environment, and cannot be applied to daily life environments such as home or business travel.

Contents of the invention

The purpose of the present invention is to solve the shortcomings and deficiencies of the above-mentioned prior art, and provide a method and system for judging apnea during sleep, which can realize the judgment of apnea without contact with the subject, without radiation, and can detect The result is accurate, easy to carry, convenient and quick to use, and can meet the needs of users in the detection and troubleshooting of apnea at home or on business trips, reducing time and money costs.

In order to achieve the above object, the technical scheme adopted in the present invention is as follows:

First, a method for judging apnea during sleep is provided, which includes the following steps:

Step 1: Collect the sleep breathing signal of the subject during sleep in real time;

Step 2: processing the sleep respiration signal to obtain a respiration rate waveform and a pulse rate waveform;

Step 3: Analyze the respiration rate waveform diagram and the pulse rate waveform diagram to obtain a judgment conclusion whether apnea occurs during sleep.

Specifically, in the step 1, the following steps are specifically included:

Step 11: collecting the simulated sleep breathing signal of the subject during sleep in real time through the piezoelectric sensor;

Step 12: Convert the sleep breathing analog signal into a sleep breathing digital signal through an A/D conversion module.

Further, in the step 2, the following steps are specifically included:

Step 21: Preliminarily analyze the sleep breathing digital signal to obtain the waveform of the respiratory rate and the waveform of the pulse rate;

Step 22: Process the waveform of the respiration rate and the waveform of the pulse rate respectively through morphological filtering, peak filtering and covariance matching, calculate the accurate respiration rate and pulse rate, and generate corresponding respiration rate waveforms respectively graph and pulse rate waveform graph.

Further, in the step 3, the following steps are specifically included:

Step 31: In the same time period of the respiration rate waveform diagram and the pulse rate waveform diagram, respectively extract the respiration rate of 20s and the pulse rate of 20s in the stable period, and take a respiration rate every second within 20s The maximum value Xi and the maximum value Yi of a pulse rate, where i is an integer, and 1≤i≤20;

Step 32: According to the formula Calculate and obtain the preliminary threshold value M of apnea state discrimination;

Step 33: When collecting the sleep respiration signal during the sleep of the subject in real time, cache the respiration rate data and pulse rate data of 5s in the same time period in the step 31, and take each second within 5s A maximum value Ai' of the respiration rate and a maximum value Bi' of the pulse rate, where i' is an integer, and 1≤i'≤5;

Step 34: According to the formula Calculate the parameter N of apnea state discrimination;

Step 35: When collecting the sleep respiration signal of the subject during sleep in real time, cache the respiration rate and pulse rate signal for 5s each time, repeat the step 33 and the step 34 every 1s, and cycle in turn until the sleep period Finish;

Step 36: Set the initial number of times of apnea count=0, and compare the size of N and 7×M every time step 33 and step 34 are repeated; if and only when N>7×M, count=count+1, indicating An apnea event has occurred; when count>2, compare the size of N and 14×M, if and only if N>14×M, count=count+1, indicating that an apnea event has occurred; get sleep period Whether there is apnea and the judgment conclusion of the number of apnea.

In order to further improve the accuracy of the judgment conclusion, as a further improvement of the present invention, the step 3 also includes the following steps:

Step 37: In the step 36, when the count value is increased by 1, a second judgment is performed on the basis of the judgment conclusion in the step 36; the second judgment specifically includes the following steps:

Step 371: Perform 10-fold down-sampling processing and 10-fold interpolation processing on the respiratory rate data and pulse rate data buffered in step 33 for 5 s respectively, wherein the sampling frequency fs=1000 Hz, and the number obtained within the 5 s is 5 × fs = 5000 points of respiratory rate data and 5 × fs = 5000 points of pulse rate data; record the respiratory rate data of 5000 points as a _i" respectively, and record the pulse rate data of 5000 points as b _{i "} , where i" is an integer, and 1≤i"≤5000;

Step 372: According to the formula Calculate the value of the line slope variance S2 of the respiration rate data and the pulse rate data ^;

Step 373: According to the multiple groups of parameters N in which apnea events occur in step 36, it is determined that the value range of the slope variance of the line where apnea events do occur;

Step 374: When the row slope variance value calculated by the step 372 is within the value range in the step 373, it is concluded that the subject has an apnea event during sleep; otherwise, when the step is passed When the row slope variance value calculated in step 372 is outside the value range in step 373, it is determined that the subject does not have apnea events during sleep.

As a further improvement of the present invention, in the step 373, the determination of the range range of the slope variance of the line that does have an apnea event specifically includes the following steps:

Step 3731: According to the step 33 and the step 34, obtain the group C apnea state discrimination parameter N, and judge the C group apnea state discrimination parameter N according to the step 35 and the step 36, in The group C apnea state discrimination parameter N is selected from the D group apnea state discrimination parameter N in which apnea events occur; wherein C and D are both positive integers, C>D, and 50≤C≤500;

Step 3732: According to the step 371, the respiration rate data and pulse rate data within 5s corresponding to the apnea state discrimination parameter N of the group D are respectively processed, and after the processing, the step 372 is used to calculate the pulse rate data of each group in the D group. The value of the row slope variance, and respectively labeled as

Step 3733: The value of the row slope variance in the D group Select a minimum line slope variance value Q ₁ and a maximum line slope variance value Q ₂ , and obtain the value range of the line slope variance of the apnea event that actually occurs as (Q ₁ , Q ₂ ) or [Q ₁ , _Q2 ].

In order to further simplify the structure of the system of the present invention and ensure the comfort of the subject without affecting the sleep experience of the subject, as a further improvement of the present invention, in the step 11, the piezoelectric sensor is arranged on the subject's pillow The bottom realizes the real-time collection of sleep breathing simulation signals of the subject during sleep.

As a further improvement of the present invention, the A/D conversion module includes a filter circuit, an amplification circuit, and an A/D conversion circuit that are electrically connected in sequence; the filter circuit is electrically connected to the piezoelectric sensor, and is connected to the piezoelectric sensor The transmitted analog signal is filtered and then input to the amplifying circuit; the amplifying circuit amplifies the filtered analog signal and transmits it to the A/D conversion circuit, and the A/D conversion circuit will sequentially pass through Filter and amplify the processed analog signal into a digital signal.

In order to further simplify the calculation steps and processing process, as a further improvement of the present invention, in the step 21, by inputting the sleep breathing digital signal to a processor or a computer, the waveform and pulse of the respiratory rate are obtained through preliminary analysis by LabVIEW software. rate waveform.

Secondly, in order to achieve another purpose of the present invention, the present invention also provides a system for judging apnea during sleep corresponding to the method for judging apnea during sleep, which system includes piezoelectric sensors connected in sequence, A/ D conversion modules and processors;

The piezoelectric sensor is used to collect the sleep breathing analog signal of the subject during sleep in real time, and transmit it to the A/D conversion module;

The A/D conversion module is used to convert the sleep breathing analog signal into a sleep breathing digital signal and send it to the processor;

The processor is used to process the sleep breathing digital signal to obtain a waveform diagram of a respiratory rate and a waveform diagram of a pulse rate, and analyze the waveform diagram of a respiratory rate and a waveform diagram of a pulse rate to obtain a judgment conclusion whether apnea occurs during sleep.

Through the above technical solution, the method and system for judging apnea during sleep of the present invention have achieved the following beneficial technical effects:

1) Use the piezoelectric sensor to detect the change of the pressure on the pillow when the subject is sleeping, analyze the two-way signal of the subject's pulse and respiration, and combine the data of the two-way signal of the subject's pulse and respiration to comprehensively judge the respiration Pause, which is more reliable than the existing breathing signal alone, and can realize the judgment of sleep apnea without contact with the subject, no radiation, and the detection result is accurate; and it solves the existing need for accurate detection Under the conditions of judging the state of apnea and making a correct assessment of sleep quality, patients must rely on the expensive polysomnogram PSG. Monitoring electrodes, thereby affecting the sleep quality of the subject, also consumes the time and money cost of the consumer, and the detection system of the present invention can realize the discrimination of the apnea state of the subject without contact with the subject, and the detection system Small and portable, convenient and quick to use, it can meet the needs of users in the detection and troubleshooting of apnea at home or on business trips, reducing time and money costs.

2) Through the step 371, the excessively high or low points in the respiratory rate and pulse rate data are removed, which is beneficial to the smoothing of the respiratory rate waveform and pulse rate waveform curve;

3) Through the steps 372-374, a second judgment is performed on the apnea event that has been judged once, so that the judgment accuracy of the apnea during sleep can be further improved by making two judgments.

For better understanding and implementation, the present invention will be described in detail below in conjunction with the accompanying drawings.

Description of drawings

Fig. 1 is a brief flow diagram of the method for judging apnea during sleep of the present invention;

Fig. 2 is the structural diagram of the judging system of apnea during sleep of the present invention;

FIG. 3 is a further improved structure diagram of the system for judging apnea during sleep in FIG. 2 .

detailed description

Please refer to Fig. 1, in order to solve the problems in the prior art, the present invention provides a method for judging apnea during sleep, which includes the following steps:

Step 1: collecting the sleep breathing signal of the subject during sleep in real time; specifically, the step 1 includes the following steps:

Step 11: collecting the simulated sleep breathing signal of the subject during sleep in real time through the piezoelectric sensor;

Step 12: Convert the sleep breathing analog signal into a sleep breathing digital signal through an A/D conversion module.

Step 2: processing the sleep respiration signal to obtain a respiration rate waveform and a pulse rate waveform; specifically, the step 2 includes the following steps:

Step 21: Preliminarily analyze the sleep breathing digital signal to obtain the waveform of the respiratory rate and the waveform of the pulse rate;

Step 22: Process the waveform of the respiration rate and the waveform of the pulse rate respectively through morphological filtering, peak filtering and covariance matching, calculate the accurate respiration rate and pulse rate, and generate corresponding respiration rate waveforms respectively graph and pulse rate waveform graph.

Step 3: Analyze the respiration rate waveform and the pulse rate waveform to determine whether apnea occurs during sleep; specifically, the step 3 includes the following steps:

Step 31: In the same time period of the respiration rate waveform diagram and the pulse rate waveform diagram, respectively extract the respiration rate of 20s and the pulse rate of 20s in the stable period, and take a respiration rate every second within 20s The maximum value Xi and the maximum value Yi of a pulse rate, where i is an integer, and 1≤i≤20;

Step 32: According to the formula Calculate and obtain the preliminary threshold value M of apnea state discrimination;

Step 33: When collecting the sleep respiration signal during the sleep of the subject in real time, cache the respiration rate data and pulse rate data of 5s in the same time period in the step 31, and take each second within 5s A maximum value Ai' of the respiration rate and a maximum value Bi' of the pulse rate, where i' is an integer, and 1≤i'≤5;

Step 34: According to the formula Calculate the parameter N of apnea state discrimination;

Step 35: When collecting the sleep respiration signal of the subject during sleep in real time, cache the respiration rate and pulse rate signal for 5s each time, repeat the step 33 and the step 34 every 1s, and cycle in turn until the sleep period Finish;

Step 36: Set the initial number of times of apnea count=0, and compare the size of N and 7×M every time step 33 and step 34 are repeated; if and only when N>7×M, count=count+1, indicating An apnea event has occurred; when count>2, compare the size of N and 14×M, if and only if N>14×M, count=count+1, indicating that an apnea event has occurred; get sleep period Whether there is apnea and the judgment conclusion of the number of apnea.

In order to further improve the accuracy of the judgment conclusion, as a better technical solution of the present invention, the step 3 is further improved, and the improved step 3 includes the following steps in addition to steps 31-36:

Step 37: In the step 36, when the count value is increased by 1, a second judgment is performed on the basis of the judgment conclusion in the step 36; the second judgment specifically includes the following steps:

Step 371: Perform 10-fold down-sampling processing and 10-fold interpolation processing on the respiratory rate data and pulse rate data buffered in step 33 for 5 s respectively, wherein the sampling frequency fs=1000 Hz, and the number obtained within the 5 s is 5 × fs = 5000 points of respiratory rate data and 5 × fs = 5000 points of pulse rate data; record the respiratory rate data of 5000 points as a _i" respectively, and record the pulse rate data of 5000 points as b _{i "} , where i" is an integer, and 1≤i"≤5000;

Step 372: According to the formula Calculate the value of the line slope variance S2 of the respiration rate data and the pulse rate data ^;

Step 373: According to the determination of multiple groups of parameters N that the apnea event occurs in step 36, the value range of the line slope variance of the apnea event does occur; specifically, the following steps are included:

Step 3731: According to the step 33 and the step 34, obtain the group C apnea state discrimination parameter N, and judge the C group apnea state discrimination parameter N according to the step 35 and the step 36, in The group C apnea state discrimination parameter N is selected from the D group apnea state discrimination parameter N in which apnea events occur; wherein C and D are both positive integers, C>D, and 50≤C≤500;

Step 3732: According to the step 371, the respiration rate data and pulse rate data within 5s corresponding to the apnea state discrimination parameter N of the group D are respectively processed, and after the processing, the step 372 is used to calculate the pulse rate data of each group in the D group. The value of the row slope variance, and respectively labeled as

Step 3733: The value of the row slope variance in the D group Select a minimum line slope variance value Q ₁ and a maximum line slope variance value Q ₂ , and obtain the value range of the line slope variance of the apnea event that actually occurs as (Q ₁ , Q ₂ ) or [Q ₁ , _Q2 ].

Step 374: When the row slope variance value calculated by the step 372 is within the value range in the step 373, it is concluded that the subject has an apnea event during sleep; otherwise, when the step is passed When the row slope variance value calculated in step 372 is outside the value range in step 373, it is determined that the subject does not have apnea events during sleep.

In addition, in other modified embodiments, the value range of C may be changed so that the obtained value D is as large as possible, which is also beneficial to further improve the accuracy of apnea discrimination.

In order to further simplify the structure of the system of the present invention and ensure the comfort of the subject without affecting the sleep experience of the subject, as a better technical solution of the present invention, in step 11, the piezoelectric sensor is set on the subject Real-time collection of sleep breathing simulation signals of the subject during sleep.

In order to obtain sleep breathing digital signals with little external interference, to further improve the accuracy of apnea discrimination, as a better technical solution, the A/D conversion module includes a filter circuit, an amplifier circuit and an A/D converter that are electrically connected in sequence. D conversion circuit. The filter circuit is electrically connected to the piezoelectric sensor, and the analog signal transmitted by the piezoelectric sensor is filtered and then input to the amplifying circuit; the amplifying circuit amplifies the filtered analog signal and sends it to The A/D conversion circuit converts the analog signal that has been filtered and amplified sequentially into a digital signal by the A/D conversion circuit.

In order to further simplify the calculation steps and processing process, as a better technical solution, in the step 21, the waveform of the respiration rate is obtained by inputting the sleep respiration digital signal to a processor or a computer through LabVIEW software for preliminary analysis and pulse rate waveforms. Wherein, the computer can be a portable computer or a desktop computer, and a convenient processing device can be selected according to the environmental needs of the subject.

In addition, in other embodiments, other software besides LabVIEW software can also be used to generate the waveform of the respiration rate and the waveform of the pulse rate, such as MALAB software and the like.

Please refer to Fig. 2, in addition, the present invention also provides a kind of judging system of apnea during sleep corresponding to the judging method of apnea during sleep, the system includes piezoelectric sensor 10, A/D conversion module connected in sequence 20 and processor 30.

The piezoelectric sensor 10 is used to collect the simulated sleep breathing signal of the subject during sleep in real time, and transmit it to the A/D conversion module 20;

The A/D conversion module 20 is used to convert the sleep breathing analog signal into a sleep breathing digital signal, and transmit it to the processor 30;

The processor 30 is used to process the sleep breathing digital signal to obtain a waveform diagram of a respiratory rate and a waveform diagram of a pulse rate, and analyze the waveform diagram of a respiratory rate and a waveform diagram of a pulse rate to obtain a judgment conclusion on whether apnea occurs during sleep.

Please refer to Fig. 3, in order to prevent the piezoelectric sensor 10 from being affected by environmental factors and to prolong the service life of the piezoelectric sensor 10, as a better technical solution, the system for judging apnea during sleep of the present invention is also It includes a sensor mounting plate 40; the piezoelectric sensor 10 is embedded and installed in the middle of the sensor mounting plate 40, and its detection end is leakingly arranged on the surface of the sensor mounting plate 40, and is connected to the sensor mounting plate 40 The surface is even. In this embodiment, the length and width of the sensor mounting plate 40 are preferably consistent with or similar to the length and width of the subject's pillow.

In order to obtain sleep breathing digital signals with little external interference, to further improve the accuracy of apnea discrimination, as a better technical solution, the A/D conversion module 20 includes sequentially electrically connected and integrated on the same PCB board filter circuit, amplifier circuit and A/D conversion circuit. The filtering circuit is electrically connected to the piezoelectric sensor 10, and the analog signal transmitted by the piezoelectric sensor 10 is filtered and then input to the amplifying circuit; the amplifying circuit amplifies the filtered analog signal, and Delivered to the A/D conversion circuit; the A/D conversion circuit is connected with the processor 30 through the serial port on the PCB board, which converts the analog signal through filtering and amplifying successively into a digital signal, and converts the digital signal through the serial port The signal is sent to the processor 30, and the processor 30 analyzes and processes the digital signal to obtain a judgment conclusion of the apnea condition.

When it is necessary to detect respiratory signals and pulse signals, the entire sensor mounting plate 40 is placed on the bottom surface of the pillow that the subject needs to use when sleeping, or inserted into the pillow cover of the pillow, and pressed together with the pillow; and A/ The D conversion module 20 can be placed beside the bed or other convenient places. When the subject is sleeping, the system can detect the respiratory signal and pulse signal, and the processor 30 can continuously process the data during the sleep period of the subject, and complete the subsequent analysis, processing and judgment. Specifically, the working process and working principle of the system for judging apnea during sleep of the present invention can be understood in combination with the method for judging apnea during sleep of the present invention, so details are not repeated here.

In other modified embodiments, the processor 30 may be replaced by other intelligent terminal devices such as a computer, a mobile phone, a tablet computer, or a watch.

Compared with the prior art, the method and system for judging apnea during sleep of the present invention can realize the judgment of apnea without contact with the subject, without radiation, with accurate detection results, easy to carry, convenient and quick to use, and can Satisfy the user's use in the detection and troubleshooting of apnea at home or on business trips, reducing time and money costs.

The present invention is not limited to the above-mentioned embodiments, if the various changes or deformations of the present invention do not depart from the spirit and scope of the present invention, if these changes and deformations belong to the claims of the present invention and the equivalent technical scope, then the present invention is also It is intended that such modifications and variations are included.

Claims (10)

1. a method for judging apnea during sleep, characterized in that: comprising the following steps: Step 1: Collect the sleep breathing signal of the subject during sleep in real time; Step 2: processing the sleep respiration signal to obtain a respiration rate waveform and a pulse rate waveform; Step 3: Analyze the respiration rate waveform diagram and the pulse rate waveform diagram to obtain a judgment conclusion whether apnea occurs during sleep. 2. the judgment method of apnea during sleep according to claim 1, is characterized in that: in described step 1, specifically comprises the following steps: Step 11: collecting the simulated sleep breathing signal of the subject during sleep in real time through the piezoelectric sensor; Step 12: Convert the sleep breathing analog signal into a sleep breathing digital signal through an A/D conversion module. 3. the judgment method of apnea during sleep according to claim 2, is characterized in that: in described step 2, specifically comprises the following steps: Step 21: Preliminarily analyze the sleep breathing digital signal to obtain the waveform of the respiratory rate and the waveform of the pulse rate; Step 22: Process the waveform of the respiration rate and the waveform of the pulse rate respectively through morphological filtering, peak filtering and covariance matching, calculate the accurate respiration rate and pulse rate, and generate corresponding respiration rate waveforms respectively graph and pulse rate waveform graph. 4. The method for judging apnea during sleep according to any one of claims 1 to 3, wherein the step 3 specifically includes the following steps: Step 31: In the same time period of the respiration rate waveform diagram and the pulse rate waveform diagram, respectively extract the respiration rate of 20s and the pulse rate of 20s in the stable period, and take a respiration rate every second within 20s The maximum value Xi and the maximum value Yi of a pulse rate, where i is an integer, and 1≤i≤20; Step 32: According to the formula Calculate and obtain the preliminary threshold value M of apnea state discrimination; Step 33: When collecting the sleep respiration signal during the sleep of the subject in real time, cache the respiration rate data and pulse rate data of 5s in the same time period in the step 31, and take each second within 5s A maximum value Ai' of the respiration rate and a maximum value Bi' of the pulse rate, where i' is an integer, and 1≤i'≤5; Step 34: According to the formula Calculate the parameter N of apnea state discrimination; Step 35: When collecting the sleep respiration signal of the subject during sleep in real time, cache the respiration rate and pulse rate signal for 5s each time, repeat the step 33 and the step 34 every 1s, and cycle in turn until the sleep period Finish; Step 36: Set the initial number of times of apnea count=0, and compare the size of N and 7×M every time step 33 and step 34 are repeated; if and only when N>7×M, count=count+1, indicating An apnea event has occurred; when count>2, compare the size of N and 14×M, if and only if N>14×M, count=count+1, indicating that an apnea event has occurred; get sleep period Whether there is apnea and the judgment conclusion of the number of apnea. 5. the method for judging apnea during sleep according to claim 4, characterized in that: said step 3 further comprises the following steps: Step 37: In the step 36, when the count value is increased by 1, a second judgment is performed on the basis of the judgment conclusion in the step 36; the second judgment specifically includes the following steps: Step 371: Perform 10-fold down-sampling processing and 10-fold interpolation processing on the respiratory rate data and pulse rate data buffered in step 33 for 5 s respectively, wherein the sampling frequency fs=1000 Hz, and the number obtained within the 5 s is 5 × fs = 5000 points of respiratory rate data and 5 × fs = 5000 points of pulse rate data; record the respiratory rate data of 5000 points as a _i" respectively, and record the pulse rate data of 5000 points as b _{i "} , where i" is an integer, and 1≤i"≤5000; Step 372: According to the formula Calculate the value of the line slope variance S2 of the respiration rate data and the pulse rate data ^; Step 373: According to the multiple groups of parameters N in which apnea events occur in step 36, it is determined that the value range of the slope variance of the line where apnea events do occur; Step 374: When the row slope variance value calculated by the step 372 is within the value range in the step 373, it is concluded that the subject has an apnea event during sleep; otherwise, when the step is passed When the row slope variance value calculated in step 372 is outside the value range in step 373, it is determined that the subject does not have apnea events during sleep. 6. the method for judging apnea during sleep according to claim 5, is characterized in that: the determination of the value domain range of the row slope variance that really takes place apnea event in the said step 373 specifically comprises the following steps: Step 3731: According to the step 33 and the step 34, obtain the group C apnea state discrimination parameter N, and judge the C group apnea state discrimination parameter N according to the step 35 and the step 36, in The group C apnea state discrimination parameter N is selected from the D group apnea state discrimination parameter N in which apnea events occur; wherein C and D are both positive integers, C>D, and 50≤C≤500; Step 3732: According to the step 371, the respiration rate data and pulse rate data within 5s corresponding to the apnea state discrimination parameter N of the group D are respectively processed, and after the processing, the step 372 is used to calculate the pulse rate data of each group in the D group. The value of the row slope variance, and respectively labeled as Step 3733: The value of the row slope variance in the D group Select a minimum line slope variance value Q ₁ and a maximum line slope variance value Q ₂ , and obtain the value range of the line slope variance of the apnea event that actually occurs as (Q ₁ , Q ₂ ) or [Q ₁ , _Q2 ]. 7. The method for judging apnea during sleep according to claim 2, characterized in that: in the step 11, the piezoelectric sensor is arranged on the bottom of the subject's pillow to realize real-time acquisition of the subject's sleep during sleep Breathing simulation signal. 8. The method for judging apnea during sleep according to claim 2, characterized in that: the A/D conversion module includes a filter circuit, an amplifying circuit and an A/D conversion circuit electrically connected in sequence; the filter circuit and the A/D conversion circuit The piezoelectric sensor is electrically connected, and the analog signal transmitted by the piezoelectric sensor is filtered and then input to the amplifying circuit; the amplifying circuit amplifies the filtered analog signal and transmits it to the A/D A conversion circuit, the A/D conversion circuit converts the analog signal that has been filtered and amplified in sequence into a digital signal. 9. the judgment method of apnea during sleep according to claim 3, is characterized in that: in described step 21, by inputting described sleep breathing digital signal on processor or computer, carry out preliminary analysis by LabVIEW software and obtain breathing rate waveform and pulse rate waveform. 10. A judgment system for apnea during sleep, characterized in that: comprising a piezoelectric sensor, an A/D conversion module and a processor connected in sequence; The piezoelectric sensor is used to collect the sleep breathing analog signal of the subject during sleep in real time, and transmit it to the A/D conversion module; The A/D conversion module is used to convert the sleep breathing analog signal into a sleep breathing digital signal and send it to the processor; The processor is used to process the sleep breathing digital signal to obtain a waveform diagram of a respiratory rate and a waveform diagram of a pulse rate, and analyze the waveform diagram of a respiratory rate and a waveform diagram of a pulse rate to obtain a judgment conclusion whether apnea occurs during sleep.