WO2024180948A1 - Respiration determination system, respiration determination method, and program - Google Patents

Abstract

The present disclosure addresses the problem of determining the condition of a human in more detail. This respiration determination system (1) is provided with an acquisition unit (131), a waveform estimation unit (133), and a determination unit (134). The acquisition unit (131) acquires a Doppler signal on the basis of an output from a radio wave sensor (3). The waveform estimation unit (133) estimates the respiratory waveform of a human (H1) on the basis of the Doppler signal acquired by the acquisition unit (131). The determination unit (134) determines whether or not the human (H1) is in an anomalous condition by comparing a feature amount of the respiratory waveform estimated by the waveform estimation unit (133) with a predetermined value.

Description

Breathing determination system, breathing determination method, and program

The present disclosure generally relates to a breathing determination system, a breathing determination method, and a program. More specifically, the present disclosure relates to a breathing determination system, a breathing determination method, and a program that estimate a human breathing waveform.

The signal processing system described in Patent Document 1 includes a complementation unit and a determination unit. The complementation unit estimates the person's second respiratory waveform. The determination unit determines the state of the person based on the time variation of the second respiratory waveform. The time variation of the second respiratory waveform is the amount of variation, variance, or standard deviation of a parameter such as the peak value or period of the second respiratory waveform.

The determination unit in Patent Document 1 is thus configured to determine a person's condition from simple information such as respiratory rate. However, it is desirable to be able to make more detailed determinations.

JP 2021-171271 A

The present disclosure aims to provide a breathing assessment system, breathing assessment method, and program that can assess a person's condition in more detail.

The breathing determination system according to one aspect of the present disclosure includes an acquisition unit, a waveform estimation unit, and a determination unit. The acquisition unit acquires a Doppler signal based on the output of a radio wave sensor. The radio wave sensor includes a transmitter that transmits radio waves as detection waves, and a receiver that receives reflected waves generated when the detection waves are reflected by a person. The Doppler signal is a signal that indicates the difference between the detection wave and the reflected wave. The waveform estimation unit estimates the person's breathing waveform based on the Doppler signal acquired by the acquisition unit. The determination unit compares the feature amount of the breathing waveform estimated by the waveform estimation unit with a predetermined value to determine whether the person is in an abnormal state.

The breathing determination method according to one aspect of the present disclosure includes an acquisition step, a waveform estimation step, and a determination step. In the acquisition step, a Doppler signal is acquired based on the output of a radio wave sensor. The radio wave sensor includes a wave transmitter that transmits radio waves as detection waves, and a wave receiver that receives reflected waves generated when the detection waves are reflected by a person. The Doppler signal is a signal that indicates the difference between the detection wave and the reflected wave. In the waveform estimation step, the person's breathing waveform is estimated based on the Doppler signal acquired in the acquisition step. In the determination step, a feature of the breathing waveform estimated in the waveform estimation step is compared with a predetermined value to determine whether the person is in an abnormal state.

A program according to one aspect of the present disclosure is a program for causing one or more processors of a computer system to execute the breathing determination method.

FIG. 1 is a block diagram of a breathing determination system according to an embodiment. FIG. 2 is a block diagram of a signal processing circuit used with the above-mentioned breathing determination system. FIG. 3 is a waveform diagram of a Doppler signal detected by the above-mentioned breathing determination system. FIG. 4 is a waveform diagram showing a respiration waveform measured by a sensor and a respiration waveform estimated by the above-mentioned respiration determination system. FIG. 5 is a waveform diagram of a Doppler signal used for estimating a respiratory waveform in the above-mentioned breathing determination system. FIG. 6 is a waveform diagram showing a respiration waveform estimated by the above-mentioned respiration determination system. FIG. 7 is a waveform diagram showing a respiration waveform estimated by the above-mentioned respiration determination system. FIG. 8 is a flowchart showing an example of the operation of the breathing determination system.

(Embodiment)
A breathing determination system 1 according to an embodiment will be described below with reference to the drawings. However, the embodiment described below is merely one of various embodiments of the present disclosure. The embodiment described below can be modified in various ways depending on the design, etc., as long as the object of the present disclosure can be achieved. Furthermore, each figure described in the embodiment described below is a schematic diagram, and the ratio of the size of each component in the figure does not necessarily reflect the actual dimensional ratio.

(overview)
The breathing determination system 1 determines whether the person H1 is in an abnormal state based on the breathing of the person H1. For example, the breathing determination system 1 determines that the person H1 is in an abnormal state when the breathing of the person H1 is different from that of a healthy person, when the breathing of the person H1 is different from the average breathing of a plurality of (a large number of) people, and when the breathing of the person H1 is different from normal. In addition, the breathing determination system 1 determines that the person H1 is in an abnormal state when the breathing of the person H1 is similar to that of a patient with a specific disease (a disease related to breathing or a disease unrelated to breathing) and when the breathing of the person H1 is similar to a breathing that requires attention. Examples of the breathing that requires attention include the breathing of a person who is under a lot of stress and the breathing of a person who shows signs of illness.

As shown in FIG. 1, the breathing judgment system 1 of this embodiment includes an acquisition unit 131, a waveform estimation unit 133, and a judgment unit 134. The acquisition unit 131 acquires a Doppler signal based on the output of the radio wave sensor 3. The radio wave sensor 3 includes a wave transmitter 31 that transmits radio waves as detection waves W1, and a wave receiver 32 that receives reflected waves W2 generated when the detection waves W1 are reflected by the person H1. The Doppler signal is a signal that indicates the difference between the detection waves W1 and the reflected waves W2. The waveform estimation unit 133 estimates the breathing waveform of the person H1 based on the Doppler signal acquired by the acquisition unit 131. The judgment unit 134 judges whether or not the person H1 is in an abnormal state by comparing the feature amount of the breathing waveform estimated by the waveform estimation unit 133 with a predetermined value.

According to this embodiment, the breathing determination system 1 estimates a breathing waveform and determines whether or not person H1 is in an abnormal state from the breathing waveform. Therefore, the state of person H1 can be determined in more detail compared to determining the state of person H1 simply from the breathing rate. Furthermore, in this embodiment, the breathing waveform can be estimated without contact, and therefore, unlike measuring the breathing waveform with a contact sensor, it is possible to eliminate the hassle of wearing a contact sensor, as well as the sense of restraint and discomfort caused by wearing it.

Furthermore, functions similar to those of the breathing determination system 1 can be embodied in a breathing determination method. The breathing determination method of this embodiment has an acquisition step, a waveform estimation step, and a determination step. In the acquisition step, a Doppler signal is acquired based on the output of the radio wave sensor 3. The radio wave sensor 3 includes a wave transmitter 31 that transmits radio waves as detection waves W1, and a wave receiver 32 that receives reflected waves W2 generated when the detection waves W1 are reflected by the person H1. The Doppler signal is a signal that indicates the difference between the detection waves W1 and the reflected waves W2. In the waveform estimation step, the breathing waveform of the person H1 is estimated based on the Doppler signal acquired in the acquisition step. In the determination step, the feature amount of the breathing waveform estimated in the waveform estimation step is compared with a predetermined value to determine whether or not the person H1 is in an abnormal state.

The breathing determination method can also be embodied as a program. The program of this embodiment is a program for causing one or more processors of a computer system to execute the breathing determination method. The program may be recorded on a non-transitory recording medium that can be read by the computer system.

(detail)
1 is a block diagram of a breathing detection system 100. The breathing detection system 100 includes a breathing determination system 1, an input device 2, a radio wave sensor 3, a signal processing circuit 4, an output device 5, and an equipment control device 6.

The respiration detection system 100 is used, for example, in a facility, which may be, for example, a building or a mobile object. Examples of buildings as facilities are houses, office buildings, factories, commercial complexes, libraries, art galleries, museums, amusement facilities, airports, train stations, hotels, nursing homes, hospitals, etc. Examples of mobile objects as facilities are ships, railroad cars, aircraft, etc. Furthermore, facilities are not limited to indoor facilities, and may be outdoor facilities.

Furthermore, the breath detection system 100 is not limited to being used in a specific facility. At least a portion of the configuration of the breath detection system 100 may be portable.

The breathing detection system 100, for example, targets a sleeping person H1 or a person H1 at rest, performs measurements using a radio wave sensor 3, estimates a breathing waveform, and determines whether the person H1 is in an abnormal state. By using the breathing detection system 100, for example, it is possible to detect a state in which the person H1 feels uncomfortable sleeping, sleep apnea syndrome, heat stroke, and a worsening condition of an illness (for example, aggravation of COVID-19 infection), etc.

The breath detection system 100 controls the spatial equipment 7. The spatial equipment 7 is, for example, an air conditioning device or a lighting device. The air conditioning device is, for example, an air conditioner, a heater, a refrigerator, an air conditioning duct, a humidifier, a dehumidifier, an air purifier, a blower, or a ventilation system.

The spatial device 7 adjusts the environment of the space. For example, the spatial device 7 adjusts at least one of the temperature, humidity, air volume, air speed, air direction, brightness, color temperature, and color deviation of the space.

(2) Input Device The input device 2 receives operations from a user. The user in the present disclosure may be the same person as the person H1 whose respiratory waveform is to be estimated, or may be a different person. The input device 2 outputs information input by the user's operations to the breathing determination system 1.

The input device 2 includes, for example, at least one of a mouse, a keyboard, a button, a touch panel, a touch pad, and a track pad. The input device 2 may also be, for example, a smartphone equipped with a touch panel or the like, or a remote controller equipped with multiple buttons or the like. The input device 2 may also include a microphone for the user to input voice. In this case, the voice input corresponds to the user's operation.

The user operates the input device 2 to input, for example, information regarding the control conditions of the spatial device 7. The user also operates the input device 2 to control the breathing determination system 1.

(3) Radio Wave Sensor The radio wave sensor 3 is installed, for example, on a ceiling or a wall. The radio wave sensor 3 includes a wave transmitter 31 and a wave receiver 32.

The wave transmitter 31 includes a transmission antenna. When an oscillation signal S1 having a predetermined frequency is input, the wave transmitter 31 transmits a detection wave W1 having the predetermined frequency to the detection area. The oscillation signal S1 is an electrical signal. The detection wave W1 is a radio wave. The wave transmitter 31 may include an amplifier that amplifies the oscillation signal S1.

The receiver 32 includes a receiving antenna. The receiver 32 receives a reflected wave W2 that occurs when the detection wave W1 is reflected by a person H1 present in the detection area, and generates a received signal S2. In other words, the receiver 32 converts the received radio wave (reflected wave W2) into a received signal S2, which is an electrical signal. The receiver 32 may also be equipped with an amplifier that amplifies the received signal S2.

The radio wave sensor 3 receives an oscillation signal S1 from the signal processing circuit 4. The radio wave sensor 3 also transmits a received signal S2 to the signal processing circuit 4.

(4) Signal Processing Circuit The signal processing circuit 4 is a circuit that generates a Doppler signal corresponding to the movement of the person H1 based on the output of the radio wave sensor 3. The signal processing circuit 4 generates the Doppler signal intermittently (for example, every unit time).

The signal processing circuit 4 may be, for example, a known circuit. As shown in FIG. 2, for example, the signal processing circuit 4 has an oscillator circuit 41, a phase shift circuit 42, and a phase detection unit 43.

The oscillator circuit 41 is, for example, an oscillator circuit using a quartz crystal oscillator or a ceramic oscillator, an LC oscillator circuit, or a clock IC (Integrated Circuit) that generates a clock signal. The oscillator circuit 41 generates an oscillation signal (sine wave signal) S1 of a reference frequency, and outputs the oscillation signal S1 to the phase shift circuit 42 and the phase detection unit 43. The oscillator circuit 41 also outputs the oscillation signal S1 to the transmitter 31.

The phase-shift circuit 42 generates a signal S3 (called a phase-shift signal) by shifting the phase of the oscillation signal S1 by (π/2), and outputs the phase-shift signal S3 to the phase detection unit 43.

The phase detection unit 43 has two detection units (a first detection unit 43A and a second detection unit 43B).

The first detection unit 43A includes a first mixer 44A, a first filter 45A, and a first amplifier 48A.

The first mixer 44A mixes (multiplies or adds) the received signal S2 and the oscillation signal S1 (reference signal) to output the difference and sum of the frequencies of the two signals as signals. If the frequency (reference frequency) of the oscillation signal S1 is f1 and the frequency of the received signal S2 is f2, a signal that is the sum of frequencies f1 and f2 and a signal that is the difference between frequencies f1 and f2 are output. Here, the first mixer 44A is a passive mixer that uses, for example, diodes, but it may also be an active mixer that uses transistors.

The first filter 45A includes a first LPF (Low Pass Filter) 46A and a first HPF (High Pass Filter) 47A.

The first LPF 46A passes frequency components below a predetermined first cutoff frequency from the output signal of the first mixer 44A. In other words, the first LPF 46A attenuates the sum of the frequency of the received signal S2 and the frequency of the oscillation signal S1, and passes the difference between the frequency of the received signal S2 and the frequency of the oscillation signal S1. The received signal S2 output from the receiver 32 contains a signal (Doppler signal) that has been frequency-shifted by hitting and reflecting off a moving object, and a signal (DC component signal) that has not been frequency-shifted by hitting and reflecting off a stationary object. Therefore, the output signal of the first mixer 44A contains not only a Doppler signal, but also a DC component signal, and the output of the first LPF 46A contains a Doppler signal and a DC component signal.

The first HPF 47A passes frequency components higher than a predetermined second cutoff frequency from the output signal of the first LPF 46A, and attenuates the DC component signal. In other words, the first HPF 47A attenuates the DC component signal contained in the output signal of the first LPF 46A and passes the Doppler signal.

The first amplifier 48A amplifies the output of the first HPF 47A and outputs it to the breathing determination system 1.

The second detection unit 43B includes a second mixer 44B, a second filter 45B, and a second amplifier 48B.

The second mixer 44B mixes (multiplies or adds) the received signal S2 and the phase-shifted signal S3 to output the difference and sum of the frequencies of the two signals as signals. The frequency of the phase-shifted signal S3 is the same as the frequency (reference frequency) of the oscillation signal S1. Here, the second mixer 44B is a passive mixer using, for example, a diode, but it may also be an active mixer using a transistor.

The second filter 45B includes a second LPF 46B and a second HPF 47B.

The second LPF 46B passes frequency components below a predetermined third cutoff frequency from the output signal of the second mixer 44B. In other words, the second LPF 46B attenuates the sum of the frequency of the received signal S2 and the frequency of the phase-shift signal S3, and passes the difference between the frequency of the received signal S2 and the frequency of the phase-shift signal S3. Note that the output signal of the second mixer 44B contains not only a Doppler signal but also a DC component signal, so the output of the second LPF 46B contains a Doppler signal and a DC component signal. Here, the third cutoff frequency of the second LPF 46B only needs to be set to the same value as the first cutoff frequency of the first LPF 46A.

The second HPF 47B passes frequency components higher than a predetermined fourth cutoff frequency from the output signal of the second LPF 46B, and attenuates the DC component signal. In other words, the second HPF 47B attenuates the DC component signal contained in the output signal of the second LPF 46B and passes the Doppler signal. Here, the fourth cutoff frequency of the second HPF 47B only needs to be set to the same value as the second cutoff frequency of the first HPF 47A.

The second amplifier 48B amplifies the output of the second HPF 47B and outputs it to the breathing determination system 1.

The breathing determination system 1 estimates the breathing waveform of person H1 based on at least one of the Doppler signals amplified by the first amplifier 48A and the second amplifier 48B.

(5) Breathing Determination System As shown in FIG. 1 , the breathing determination system 1 includes a communication unit 11, a storage unit 12, and a processing unit 13.

The breathing determination system 1 includes a computer system having one or more processors and a memory. At least some of the functions of the breathing determination system 1 are realized by the processor of the computer system executing a program recorded in the memory of the computer system. The program may be recorded in the memory, or may be provided via a telecommunications line such as the Internet, or may be recorded on a non-transitory recording medium such as a memory card and provided.

The storage unit 12 includes the memory of the computer system. The processing unit 13 includes one or more processors of the computer system. The processing unit 13 executes a program to realize a predetermined function.

The communication unit 11 includes a communication interface device. The breathing determination system 1 is capable of communicating with the input device 2, the signal processing circuit 4, the output device 5, and the equipment control device 6 via the communication interface device. In this disclosure, "capable of communication" means that signals can be sent and received directly or indirectly via a network or a repeater, etc., using an appropriate communication method such as wired communication or wireless communication.

The memory unit 12 is a storage device configured with a hard disk drive (HDD) or a solid state drive (SSD) or the like. The memory unit 12 stores information. For example, the memory unit 12 stores a program executed by the processing unit 13. The memory unit 12 also stores, for example, information acquired from the input device 2, a Doppler signal output from the signal processing circuit 4, a respiratory waveform estimated by the processing unit 13, the state of the person H1 determined by the processing unit 13, and the control conditions of the spatial device 7 determined by the processing unit 13.

The processing unit 13 has, for example, an acquisition unit 131, a preprocessing unit 132, a waveform estimation unit 133, a determination unit 134, and an environment control unit 135. Note that these merely indicate the functions realized by the processing unit 13, and do not necessarily indicate a concrete configuration.

(5.1) Acquisition Unit The acquisition unit 131 acquires a Doppler signal based on the output of the radio wave sensor 3. More specifically, the signal processing circuit 4 generates a Doppler signal based on the output of the radio wave sensor 3. The acquisition unit 131 acquires the Doppler signal from the signal processing circuit 4 via the communication unit 11.

(5.2) Pre-Processing Unit The pre-processing unit 132 performs pre-processing on the Doppler signal acquired by the acquisition unit 131. For example, the pre-processing unit 132 performs processing to reduce noise in the Doppler signal, and processing to convert the data format of the Doppler signal.

(5.3) Waveform Estimation Unit The Doppler signal is pre-processed in the pre-processing unit 132 and then input to the waveform estimation unit 133 .

The waveform estimation unit 133 estimates the respiratory waveform of person H1 based on the Doppler signal input to the waveform estimation unit 133. More specifically, the waveform estimation unit 133 is a trained model generated by machine learning, and the trained model estimates the respiratory waveform of person H1 from the Doppler signal. The trained model takes the Doppler signal as input data and the respiratory waveform of person H1 as output data. In other words, the trained model receives the input of the Doppler signal and outputs the respiratory waveform of person H1. The trained model is generated in advance by a learner.

(5.4) Learning Device The learning device generates, by machine learning, a trained model that constitutes the waveform estimation unit 133. A "trained model" refers to a model for which machine learning using a learning dataset has been completed. As an example, the learning device generates a trained model by deep learning.

The trained model referred to here is assumed to include, for example, a trained model using a neural network, or a trained model generated by deep learning using a multi-layer neural network. The neural network may include, for example, a CNN (Convolutional Neural Network). The neural network may also include a recurrent neural network.

A neural network is composed of, for example, an input layer, a CNN layer, an RNN (Recurrent Neural Network) layer, a fully connected layer, and an output layer.

The training data set is a collection of multiple training data. The training data is data that combines Doppler signals with the respiratory waveforms that correspond to the Doppler signals, and is so-called teacher data. In other words, the training data is data that associates Doppler signals with the respiratory waveforms that correspond to the Doppler signals.

The Doppler signal data and respiratory waveform data included in the teacher data are obtained by measurement using sensors. For example, a Doppler signal can be obtained for one or more subjects using a radio wave sensor 3 and a signal processing circuit 4. Also, for example, a respiratory waveform can be measured for one or more subjects using a respiratory sensor. The respiratory sensor is preferably a contact type sensor. The respiratory sensor measures the respiratory waveform based on, for example, the movement of the subject's chest or abdomen.

　The Doppler signal is obtained and the respiratory waveform is measured simultaneously. The time axis of the Doppler signal data and the respiratory waveform data contained in one learning data set is the same.

Furthermore, with regard to the Doppler signal data and respiratory waveform data contained in one learning data set, the subject to whom the radio waves (detection wave W1) are applied to obtain the Doppler signal and the subject to whom the respiratory waveform is measured are the same person.

The one or more subjects may or may not include a person H1 whose condition is to be determined by the breathing determination system 1.

The Doppler signal input to the waveform estimation unit 133 may contain components due to the breathing of person H1, components due to the body movement of person H1, components due to the heart rate of person H1, noise, etc. Body movement refers to bodily movement in general.

The waveform estimation unit 133 (trained model) estimates the respiratory waveform of person H1 based on the input Doppler signal. Therefore, the learning device learns to distinguish the components of the Doppler signal caused by person H1's breathing from other components (i.e., components caused by the body movement of person H1, components caused by person H1's heart rate, noise, etc.).

FIG. 3 shows an example of Doppler signals D1 and D2 that are measured on a specific subject and included in the learning data. Doppler signals D1 and D2 are signals (I signal and Q signal) output from the first detection unit 43A and the second detection unit 43B (see FIG. 2), respectively.

FIG. 4 shows an example of a respiratory waveform B1 measured by a respiratory sensor for the above-mentioned specified subject. The learning device performs machine learning to estimate the respiratory waveform using the Doppler signals D1 and D2 and the respiratory waveform B1 as training data. The respiratory waveform B2 in FIG. 4 is an example of a respiratory waveform estimated by the trained model (waveform estimation unit 133) generated by machine learning.

FIG. 5 also shows an example of Doppler signals D3 and D4 measured for person H1. Doppler signals D3 and D4 are signals (I signal and Q signal) output from the first detection unit 43A and the second detection unit 43B (see FIG. 2), respectively.

The respiratory waveform B3 in FIG. 6 is obtained by inputting the Doppler signals D3 and D4 in FIG. 5 to the waveform estimation unit 133.

Figure 7 also shows an example of a respiratory waveform.

In the Doppler signal waveform diagrams in Figures 3 and 5, the horizontal axis represents time.

In the respiratory waveform diagram of Figure 4, the horizontal axis represents time, and the vertical axis represents the strength of the output signal from the respiratory sensor. Here, the respiratory sensor is a pressure sensor that detects the movement of the subject's chest or abdomen accompanying breathing as a change in pressure, and the vertical axis in Figure 4 corresponds to the pressure that changes with breathing. Similarly in Figures 6 and 7, the horizontal axis represents time, and the vertical axis corresponds to the pressure that changes with breathing. An increase in pressure represents inhalation, and a decrease in pressure represents exhalation.

(5.5) Determination Unit The determination unit 134 compares the feature amount of the respiratory waveform estimated by the waveform estimation unit 133 with a predetermined value to determine whether or not the person H1 is in an abnormal state.

An example of the features of the respiratory waveform will be described with reference to FIG. 7. The features of the respiratory waveform include, for example, at least one of the following: breath time BT, inspiratory time IT, expiratory time ET, postexpiration pause time PT, an amount equivalent to inspiratory volume IV, an amount equivalent to expiratory volume EV, an amount equivalent to minute ventilation volume, and respiratory rate.

As shown in Fig. 7, the respiratory waveform has repeated peaks and valleys. The respiratory time BT is the time from when the respiratory volume reaches the minimum value _VIST at the valley of the respiratory waveform to when the respiratory volume reaches the minimum value VIST ₊₁ at the next valley and then begins to increase. The respiratory time BT is the sum of the inhalation time IT, the exhalation time ET, and the pause time PT.

The inspiration time IT is the time from the point at which the respiratory volume reaches a minimum value _VIST at the trough of the respiratory waveform to the point at which the respiratory volume reaches a maximum value _VIEO at the next peak.

The expiratory time ET is the time from the point at which the respiratory volume reaches a maximum value V _IEO at the peak of the respiratory waveform to the point at which the respiratory volume reaches a minimum value V _{IST +1} at the next valley.

The pause time PT is the time when the variation in respiratory volume is below a certain value at the trough of the respiratory waveform. When the pause time PT ends, the respiratory volume begins to increase.

The inhalation volume IV is the difference between the minimum value V _IST of the respiratory volume at the trough of the respiratory waveform and the maximum value V _IEO of the respiratory volume at the next peak.

The expiratory volume EV is the difference between the maximum value V _IEO of the respiratory volume at the peak of the respiratory waveform and the minimum value V _IST+1 of the respiratory volume at the following valley.

Minute ventilation is the total amount of gas ventilated in one minute. Minute ventilation is the product of the tidal volume (inspiratory volume IV or expiratory volume EV) and the respiratory rate (number of breaths) per minute.

The determination unit 134 determines whether or not person H1 is in an abnormal state based on, for example, the similarity between the feature amount of the respiratory waveform estimated by the waveform estimation unit 133 and a predetermined value corresponding to an abnormal respiratory pattern. That is, the feature amount of the abnormal respiratory pattern is stored in advance in the storage unit 12 as the above-mentioned predetermined value. Then, the determination unit 134 determines whether or not person H1 is in an abnormal state based on the magnitude relationship between the feature amount of the respiratory waveform estimated by the waveform estimation unit 133 and the above-mentioned predetermined value stored in the storage unit 12. The determination unit 134 determines that person H1 is in an abnormal state when, for example, the difference between the feature amount of the respiratory waveform estimated by the waveform estimation unit 133 and the above-mentioned predetermined value stored in the storage unit 12 is equal to or smaller than a first threshold value.

The determination unit 134 also determines whether or not the person H1 is in an abnormal state based on, for example, the similarity between the feature amount of the respiratory waveform estimated by the waveform estimation unit 133 and a predetermined value corresponding to the breathing pattern of the person H1 measured in advance. That is, the normal respiratory waveform of the person H1 is measured in advance using a respiratory sensor, and the feature amount is stored in the storage unit 12 as the above-mentioned predetermined value. The determination unit 134 determines whether or not the person H1 is in an abnormal state based on the magnitude relationship between the feature amount of the respiratory waveform estimated by the waveform estimation unit 133 and the above-mentioned predetermined value stored in the storage unit 12. The determination unit 134 determines that the person H1 is in an abnormal state when, for example, the difference between the feature amount of the respiratory waveform estimated by the waveform estimation unit 133 and the above-mentioned predetermined value stored in the storage unit 12 is greater than a second threshold value.

When person H1 is placed in a stressful situation, there is a tendency for the respiratory rate and minute ventilation to increase, and for the pause time PT to decrease. Based on this knowledge, an algorithm is determined in advance for the determination unit 134 to determine an abnormality.

The feature quantity of the respiratory waveform may include respiratory interval variation. The respiratory interval variation is expressed as the respiratory rate moving standard deviation or the respiratory irregularity index. The respiratory irregularity index is the absolute value of the difference between the respiratory peak frequency PF and the respiratory center of gravity frequency GF (|PF-GF|). When person H1 is placed in a stressful situation, there is a tendency for changes to occur in the respiratory interval variation. Based on this knowledge, an algorithm is determined in advance for the determination unit 134 to determine an abnormality.

The waveform shown in FIG. 6 has a shape similar to a breathing abnormality called Cheyne-Stokes breathing. In addition to Cheyne-Stokes breathing, Biot breathing and Kussmaul breathing are also known as medically abnormal breathing (breathing abnormalities). Furthermore, buccal breathing, hyperpnea, hypopnea, bradypnea (slow breathing), tachypnea, and breathlessness are also known as breathing abnormalities. The determination unit 134 can determine whether or not person H1 is in an abnormal state based on the similarity between the features of such abnormal breathing patterns and the features of the breathing waveform estimated by the waveform estimation unit 133.

(5.6) Environmental Control Unit The environmental control unit 135 controls the spatial environment based on the determination result of the determination unit 134. More specifically, the environmental control unit 135 controls the spatial equipment 7 via the equipment control device 6, thereby controlling the spatial environment.

First, the environmental control unit 135 determines the control conditions for the spatial device 7. Furthermore, the environmental control unit 135 outputs a control signal to the device control device 6 via the communication unit 11. The control signal is a signal indicating the control conditions determined by the environmental control unit 135. The device control device 6 controls the spatial device 7 based on the control signal.

When the spatial device 7 is an air conditioning device, the control signal generated by the environmental control unit 135 specifies, for example, the set temperature, set humidity, set air volume, set air speed, and set air direction of the spatial device 7. When the spatial device 7 is a lighting device, the control signal generated by the environmental control unit 135 specifies, for example, the brightness (dimming rate), color temperature, and color deviation of the spatial device 7. The device control device 6 matches the settings of the spatial device 7 with the settings specified by the control signal.

The judgment result of the judgment unit 134 includes information regarding the type of abnormality. The information regarding the type of abnormality includes, for example, information regarding what kind of illness or disease the person H1 is suspected to have and the degree of suspicion. Furthermore, the memory unit 12 stores, for example, a correspondence between the information regarding the type of abnormality and the control conditions of the spatial device 7. For example, the correspondence input by the user operating the input device 2 may be stored in the memory unit 12, or the correspondence may be stored in advance in the memory unit 12.

When the environmental control unit 135 acquires information regarding the type of abnormality, it determines the control conditions for the spatial equipment 7, for example, based on the correspondence stored in the storage unit 12. For example, if the person H1 is suspected of having heat stroke, the environmental control unit 135 lowers the set temperature of the air conditioning equipment, which is the spatial equipment 7.

(6) Output Device The output device 5 is a device for transmitting information to the user.

The output device 5 includes, for example, a display device such as a display. The output device 5 displays information.

For example, the output device 5 acquires information about the respiratory waveform estimated by the waveform estimation unit 133 from the breathing determination system 1. The information is transmitted to the output device 5 as an image signal. The output device 5 displays the information. In other words, the output device 5 displays the respiratory waveform.

The output device 5 also displays, for example, the determination result of the determination unit 134 output from the breathing determination system 1.

The output device 5 also displays, for example, the control conditions of the spatial device 7 determined by the environment control unit 135 and output from the breathing determination system 1.

The output device 5 may be, for example, a smartphone equipped with a display, etc.

The output device 5 may also include a speaker for transmitting information by audio output.

The output device 5 may also include a printer for transmitting information by printing.

(7) Equipment Control Device The equipment control device 6 controls the spatial equipment 7 based on the control signal generated by the environment control unit 135. The equipment control device 6 causes the settings of the spatial equipment 7 to match the settings specified by the control signal.

(8) Operation Flow Next, an example of the operation flow of the breathing determination system 1 will be described with reference to Fig. 8. However, the flowchart shown in Fig. 8 is merely an example, and the order of processes may be changed as appropriate, and processes may be added or omitted as appropriate.

The breathing determination system 1 acquires a Doppler signal from the signal processing circuit 4 (step ST1). Next, the breathing determination system 1 estimates the breathing waveform of person H1 using a trained model that has been generated in advance by a learning device (step ST2). More specifically, the breathing determination system 1 inputs the Doppler signal to the trained model. Then, the trained model outputs an estimated breathing waveform.

Next, the breathing determination system 1 extracts features of the breathing waveform from the breathing waveform (step ST3). The features of the breathing waveform include, for example, the breathing time BT (see FIG. 7) and the inhalation time IT (see FIG. 7).

The breathing determination system 1 determines whether the extracted feature amount is within the abnormal range (step ST4). For example, if the difference between the feature amount and the predetermined value exceeds a threshold, the breathing determination system 1 determines that the feature amount is within the abnormal range, and if the difference between the feature amount and the predetermined value is equal to or less than the threshold, the breathing determination system 1 determines that the feature amount is not within the abnormal range.

If the feature amount is within the abnormal range (step ST4: Yes), the breathing determination system 1 determines that person H1 is in an abnormal state (step ST5). If the feature amount is not within the abnormal range (step ST4: No), the breathing determination system 1 determines that person H1 is in a normal state (not in an abnormal state) (step ST6).

The breathing determination system 1 outputs the determination result as to whether or not the person H1 is in an abnormal state (step ST7). The output device 5 displays the determination result.

The breathing determination system 1 also determines the control conditions for the spatial device 7 based on the determination result. The breathing determination system 1 controls the spatial device 7 via the device control device 6 based on the determined control conditions (step ST8).

(Modification of the embodiment)
Modifications of the embodiment are listed below. The following modifications may be implemented in appropriate combination. The above-described aspects of the embodiment are hereinafter referred to as "basic examples."

In a basic example, as described above, the computational model (trained model) used in the waveform estimation unit 133 is generated by machine learning. The waveform estimation unit 133 may be implemented as any type of artificial intelligence or system. Here, the machine learning algorithm is, for example, a neural network. However, the machine learning algorithm is not limited to a neural network, and may be, for example, eXtreme Gradient Boosting (XGB) regression, Random Forest, decision tree, Logistic Regression, Support vector machine (SVM), Naive Bayes classifier, k-nearest neighbors, etc. Furthermore, the machine learning algorithm may be, for example, a Gaussian Mixture Model (GMM), k-means clustering, etc.

In addition, in the basic example, the learning method is, as an example, supervised learning. However, the learning method is not limited to supervised learning, and may be unsupervised learning or reinforcement learning.

The determination unit 134 may determine whether the person H1 is in an abnormal state, and generate advice for the person H1 based on the determination result. The advice may be, for example, a suggestion to improve lifestyle habits, or advice to visit a medical institution. The determination unit 134 may generate a predetermined advice for each type of abnormality, for example. The determination unit 134 outputs the generated advice. For example, the determination unit 134 causes the output device 5 to display the advice in the form of characters, drawings, etc.

The Doppler signal may contain components resulting from the breathing of multiple people. Thus, the learning device may learn to distinguish the components of the Doppler signal resulting from the breathing of one person from the components resulting from the breathing of another person.

A plurality of radio wave sensors 3 may be provided. For example, when the breathing determination system 1 estimates the breathing waveforms of each of a plurality of people sleeping in a bedroom, a plurality of radio wave sensors 3 may be provided in one-to-one correspondence with the plurality of people.

The phase detection unit 43 may include only one of the first detection unit 43A and the second detection unit 43B.

The executing entity of the breathing determination system 1 or the breathing determination method in the present disclosure includes a computer system. The computer system is mainly composed of a processor and a memory as hardware. At least a part of the functions of the executing entity of the breathing determination system 1 or the breathing determination method in the present disclosure is realized by the processor executing a program recorded in the memory of the computer system. The program may be pre-recorded in the memory of the computer system, may be provided through an electric communication line, or may be recorded and provided on a non-transitory recording medium such as a memory card, an optical disk, or a hard disk drive that can be read by the computer system. The processor of the computer system is composed of one or more electronic circuits including a semiconductor integrated circuit (IC) or a large scale integrated circuit (LSI). The integrated circuits such as ICs or LSIs referred to here are called different names depending on the degree of integration, and include integrated circuits called system LSIs, VLSIs (Very Large Scale Integration), or ULSIs (Ultra Large Scale Integration). Furthermore, a field-programmable gate array (FPGA) that is programmed after the LSI is manufactured, or a logic device that allows reconfiguration of the connection relationships within the LSI or reconfiguration of the circuit partitions within the LSI, can also be used as a processor. Multiple electronic circuits may be integrated into one chip, or may be distributed across multiple chips. Multiple chips may be integrated into one device, or may be distributed across multiple devices. The computer system referred to here includes a microcontroller having one or more processors and one or more memories. Thus, the microcontroller is also composed of one or more electronic circuits including a semiconductor integrated circuit or a large-scale integrated circuit.

Furthermore, it is not essential for the breathing determination system 1 that multiple functions are concentrated in one device, and multiple components of the breathing determination system 1 may be distributed across multiple devices. Furthermore, at least some of the functions of the breathing determination system 1, for example, some of the functions of the determination unit 134, may be realized by a server or a cloud (cloud computing), etc.

On the other hand, in the embodiment, multiple functions distributed among multiple devices may be consolidated into one device. For example, multiple functions distributed between the signal processing circuit 4 and the breathing determination system 1 may be consolidated into one device.

(summary)
The above-described embodiments and the like disclose the following aspects.

The breathing determination system (1) according to the first aspect includes an acquisition unit (131), a waveform estimation unit (133), and a determination unit (134). The acquisition unit (131) acquires a Doppler signal based on the output of the radio wave sensor (3). The radio wave sensor (3) includes a wave transmitter (31) that transmits radio waves as a detection wave (W1), and a wave receiver (32) that receives a reflected wave (W2) generated when the detection wave (W1) is reflected by the person (H1). The Doppler signal is a signal that indicates the difference between the detection wave (W1) and the reflected wave (W2). The waveform estimation unit (133) estimates the breathing waveform of the person (H1) based on the Doppler signal acquired by the acquisition unit (131). The determination unit (134) compares the feature amount of the breathing waveform estimated by the waveform estimation unit (133) with a predetermined value to determine whether the person (H1) is in an abnormal state.

With the above configuration, the breathing determination system (1) estimates a breathing waveform and determines whether or not the person (H1) is in an abnormal state from the breathing waveform. Therefore, the condition of the person (H1) can be determined in more detail than when the condition of the person (H1) is determined simply from the breathing rate.

In addition, in the breathing determination system (1) according to the second aspect, in the first aspect, the waveform estimation unit (133) estimates the breathing waveform of the person (H1) from the Doppler signal using a trained model generated by machine learning.

With the above configuration, the waveform estimation unit (133) can estimate the respiratory waveform in various situations.

In addition, in the breathing determination system (1) according to the third aspect, in the first or second aspect, the determination unit (134) determines whether or not the person (H1) is in an abnormal state based on the similarity between the feature amount of the breathing waveform estimated by the waveform estimation unit (133) and a predetermined value corresponding to an abnormal breathing pattern.

The above configuration makes it easier for the judgment unit (134) to judge abnormalities in the person (H1).

In addition, in the breathing determination system (1) according to the fourth aspect, in any one of the first to third aspects, the determination unit (134) determines whether or not the person (H1) is in an abnormal state based on the similarity between the feature amount of the breathing waveform estimated by the waveform estimation unit (133) and a predetermined value corresponding to the breathing pattern of the person (H1) measured in advance.

With the above configuration, the determination unit (134) can determine whether the condition of the person (H1) is different from usual.

The breathing determination system (1) according to the fifth aspect is any one of the first to fourth aspects and further includes an environmental control unit (135). The environmental control unit (135) controls the spatial environment based on the determination result of the determination unit (134).

The above configuration can improve the condition of the person (H1).

In addition, in the breathing determination system (1) according to the sixth aspect, in any one of the first to fifth aspects, the feature amount includes breathing time.

In addition, in the breathing determination system (1) according to the seventh aspect, in any one of the first to sixth aspects, the characteristic amount includes the inhalation time.

In addition, in the breathing determination system (1) according to the eighth aspect, in any one of the first to seventh aspects, the feature value includes an exhalation time.

In addition, in the breathing determination system (1) according to the ninth aspect, in any one of the first to eighth aspects, the feature amount includes a pause time.

In addition, in the breathing determination system (1) according to the tenth aspect, in any one of the first to ninth aspects, the characteristic amount includes an amount corresponding to the amount of inhaled air.

In addition, in the breathing determination system (1) according to the eleventh aspect, in any one of the first to tenth aspects, the feature amount includes an amount equivalent to the exhaled air volume.

In addition, in the breathing determination system (1) according to the twelfth aspect, in any one of the first to eleventh aspects, the characteristic amount includes an amount equivalent to minute ventilation.

Configurations other than the first aspect are not essential to the breathing determination system (1) and may be omitted as appropriate.

The breathing determination method according to the thirteenth aspect includes an acquisition step, a waveform estimation step, and a determination step. In the acquisition step, a Doppler signal is acquired based on the output of the radio wave sensor (3). The radio wave sensor (3) includes a wave transmitter (31) that transmits radio waves as a detection wave (W1), and a wave receiver (32) that receives a reflected wave (W2) generated when the detection wave (W1) is reflected by the person (H1). The Doppler signal is a signal that indicates the difference between the detection wave (W1) and the reflected wave (W2). In the waveform estimation step, the breathing waveform of the person (H1) is estimated based on the Doppler signal acquired in the acquisition step. In the determination step, the feature amount of the breathing waveform estimated in the waveform estimation step is compared with a predetermined value to determine whether the person (H1) is in an abnormal state.

The above configuration allows the condition of the person (H1) to be determined in more detail.

The program according to the fourteenth aspect is a program for causing one or more processors of a computer system to execute the breathing determination method according to the thirteenth aspect.

The above configuration allows the condition of the person (H1) to be determined in more detail.

In addition to the above aspects, various configurations (including modified examples) of the breathing determination system (1) according to the embodiment can be embodied in a breathing determination method, a (computer) program, or a non-transitory recording medium on which a program is recorded.

1 Breathing determination system 3 Radio wave sensor 31 Transmitter 32 Receiver 131 Acquisition unit 133 Waveform estimation unit 134 Determination unit 135 Environment control unit H1 Person W1 Detection wave W2 Reflected wave

Claims (14)

an acquisition unit that acquires a Doppler signal indicating a difference between the detection wave and the reflected wave based on an output of a radio wave sensor including a transmitter that transmits radio waves as detection waves and a receiver that receives reflected waves generated when the detection wave is reflected by a person;
A waveform estimation unit that estimates a respiratory waveform of the person based on the Doppler signal acquired by the acquisition unit;
and a determination unit that determines whether or not the person is in an abnormal state by comparing the feature amount of the respiratory waveform estimated by the waveform estimation unit with a predetermined value.
Breath detection system. The waveform estimation unit estimates the respiratory waveform of the person from the Doppler signal using a trained model generated by machine learning.
The breathing determination system according to claim 1 . The determination unit determines whether or not the person is in an abnormal state based on a similarity between the feature amount of the respiratory waveform estimated by the waveform estimation unit and the predetermined value corresponding to an abnormal respiratory pattern.
The breathing determination system according to claim 1 or 2. The determination unit determines whether or not the person is in an abnormal state based on a degree of similarity between the feature amount of the respiratory waveform estimated by the waveform estimation unit and the predetermined value corresponding to a respiratory pattern of the person measured in advance.
The breathing determination system according to any one of claims 1 to 3. An environment control unit that controls an environment of the space based on a determination result of the determination unit.
The breathing determination system according to any one of claims 1 to 4. The feature amount includes a breathing time.
The breathing determination system according to any one of claims 1 to 5. The feature amount includes an inhalation time.
The breathing determination system according to any one of claims 1 to 6. The feature amount includes an exhalation time.
The breathing determination system according to any one of claims 1 to 7. The feature amount includes a pause time.
The breathing determination system according to any one of claims 1 to 8. The characteristic amount includes an amount corresponding to an intake amount.
The breathing determination system according to any one of claims 1 to 9. The feature amount includes an amount corresponding to an exhaled air volume.
The breathing determination system according to any one of claims 1 to 10. The feature amount includes an amount corresponding to minute ventilation.
The breathing determination system according to any one of claims 1 to 11. an acquisition step of acquiring a Doppler signal indicating a difference between the detection wave and the reflected wave based on an output of a radio wave sensor including a transmitter that transmits radio waves as detection waves and a receiver that receives reflected waves generated when the detection wave is reflected by a person;
a waveform estimation step of estimating a respiratory waveform of the person based on the Doppler signal acquired in the acquisition step;
and a determination step of determining whether or not the person is in an abnormal state by comparing the feature amount of the respiratory waveform estimated in the waveform estimation step with a predetermined value.
Breathing determination method. The method for determining respiration according to claim 13 is executed by one or more processors of a computer system,
program.

Images