Sleep estimation system and sleep estimation method

Abstract

To easily estimate sleep stages.SOLUTION: A sleep estimation device includes: a first acquisition unit for acquiring blood flow data; a generation unit for generating a frequency spectrum of the blood flow data by executing frequency analysis processing on the blood flow data; and a first determination unit for determining the sleep stage of a subject on the basis of the frequency spectrum.SELECTED DRAWING: Figure 1

Description

Technical Field

[0001] The present disclosure relates to the estimation of the sleep stage of a subject.

Background Art

[0002] Patent Document 1 describes a technique for detecting a sleep stage.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

[0004] A sleep estimation system according to an aspect of the present disclosure includes a determination unit that determines the sleep stage of a subject based on the frequency spectrum of the blood flow data of the subject. When the sleep stages in non-REM sleep are set as Stage 1, Stage 2, and Stage 3 in order from the lighter sleep stage, the determination unit determines that the sleep stage of the subject has transitioned from Stage 1 to Stage 2 or 3 when at least the frequency spectrum includes a region having a predetermined shape in a frequency band of 0.2 Hz or more and 0.3 Hz or less.

[0005] Furthermore, a sleep estimation system according to an aspect of the present disclosure includes a determination unit that determines the sleep stage of a subject based on the frequency spectrum of the blood flow data of the subject. When the sleep stages in non-REM sleep are set as Stage 1, Stage 2, and Stage 3 in order from the lighter sleep stage, the determination unit determines whether the sleep stage of the subject has transitioned from Stage 1 to Stage 2 or 3 when the frequency spectrum of the blood flow data is given to a learned model that has been learned using, as teacher data, a frequency spectrum having a predetermined shape in a region including a frequency band of 0.2 Hz or more and 0.3 Hz or less, which is specified as corresponding to Stage 2 or 3 based on biological information different from the blood flow data.

[0006] Furthermore, a sleep estimation method according to an aspect of the present disclosure includes a determination step of determining a sleep stage of a subject based on a frequency spectrum of blood flow data of the subject. When the sleep stages in non-REM sleep are set as stages 1, 2, and 3 in order from a light sleep stage, in the determination step, when at least the frequency spectrum includes a predetermined shape in a region including a frequency band of 0.2 Hz or more and 0.3 Hz or less, it is determined that the sleep stage of the subject has transitioned from the stage 1 to the stage 2 or 3.

[0007] Furthermore, a sleep estimation method according to an aspect of the present disclosure includes a determination step of determining a sleep stage of a subject based on a frequency spectrum of blood flow data of the subject. When the sleep stages in non-REM sleep are set as stages 1, 2, and 3 in order from a light sleep stage, in the determination step, for a learned model that has been learned using, as teacher data, a frequency spectrum having a predetermined shape in a region including a frequency band of 0.2 Hz or more and 0.3 Hz or less, which is specified as corresponding to the stage 2 or 3 based on biological information different from the blood flow data, when the frequency spectrum of the blood flow data is given, it is determined whether the sleep stage of the subject has transitioned from the stage 1 to the stage 2 or 3.

Brief Description of the Drawings

[0008]

Figure 1

Figure 2

Figure 3

Figure 4

Figure 5

Figure 6

Figure 7

Figure 8

Mode for Carrying Out the Invention

[0009] Hereinafter, the determination (estimation) of the sleep stage of the subject according to the present disclosure will be described. First, the principle underlying the determination of the sleep stage of the subject according to the present disclosure will be described. It should be noted that when "A to B" is described in this specification, it indicates "A or more and B or less". Also, in this specification, as an example of the blood flow data used for the determination of the sleep stage, blood flow waveform data will be described.

[0010] 〔Principle〕 Figure 2 is a graph showing an example of blood flow waveform data detected by a blood flow meter. In Figure 2, the vertical axis indicates a value proportional to the blood flow volume per unit time [unit: dimensionless], and the horizontal axis indicates the measurement time [unit: min]. The blood flow meter can acquire raw waveform data W1 and processed waveform data W2 as shown in Figure 2 as blood flow waveform data. The processed waveform data W2 is waveform data obtained by processing the raw waveform data W1 so as to easily acquire the peak of the R wave. The processed waveform data W2 is generated, for example, by performing a smoothing process on the raw waveform data W1. In the processed waveform data W2, the time interval between adjacent peaks (the blood flow volume at the position indicated by the inverted triangle shape in the figure) indicates the R-R interval (RRI). Similarly, in the raw waveform data W12 of the heartbeat shown in Figure 4, the time interval between adjacent peaks (the blood flow volume at the position indicated by the inverted triangle shape in the figure) indicates the R-R interval (RRI).

[0011] A blood flow meter that detects blood flow waveform data is a sensor that can detect blood flow waveform data indicating the blood flow of a subject by receiving scattered light generated by irradiating light onto the blood vessels of the subject. The blood flow meter may include a light emitting unit that irradiates light onto the blood vessels of the subject and a light receiving unit that receives the scattered light.

[0012] Generally, when laser light is irradiated onto a fluid, the irradiated laser light is scattered by (i) scatterers contained in the fluid and moving together with the fluid, and (ii) stationary objects such as a tube for flowing the fluid, and scattered light is generated. Generally, the scatterers cause non-uniformity in the complex refractive index in the fluid.

[0013] The scattered light generated by the scatterers moving together with the fluid is subject to a wavelength shift due to the Doppler effect according to the flow velocity of the scatterers. On the other hand, the scattered light generated by the stationary objects is not subject to a wavelength shift. Since these scattered lights cause optical interference, an optical beat (beating) is observed.

[0014] The blood flow meter may be a sensor that utilizes this phenomenon. That is, the blood flow meter may be a laser Doppler blood flow meter that irradiates laser light onto the blood vessels of the subject and detects, as blood flow waveform data, the optical beat brought about in the scattered light generated in the blood as a fluid.

[0015] More specifically, the processor included in the blood flow meter may analyze the acquired light reception signal and calculate frequency analysis data indicating the signal intensity for each frequency of the light reception signal. As an example, the processor may perform analysis on the acquired light reception signal using a method such as FFT (Fast Fourier Transformation).

[0016] The processor may further generate blood flow waveform data indicating the variation pattern of the blood flow volume of the subject based on the frequency analysis data. As an example, the processor may calculate the sum X of the first moments of the acquired frequency analysis data as the blood flow waveform data. More specifically, the processor may calculate the sum X of the first moments of the acquired frequency analysis data using the following formula. The processor uses the following formula to calculate the sum X of the first moments in a partial (e.g., 1 to 20 kHz) frequency band X = Σfx × P(fx) Here, "fx" is the frequency, and "P(fx)" is the value of the signal intensity at the frequency fx.

[0017] The sum X of the first moments calculated by the processor based on the frequency analysis data can be a value proportional to the blood flow volume of the subject. The processor may generate pattern data indicating the variation pattern of the blood flow volume of the subject over time by calculating the sum X of the first moments for each of the plurality of frequency analysis data. Also, the processor may generate blood flow waveform data using the data included in a partial frequency band among the data included in the frequency analysis data. The processor can output the generated blood flow waveform data.

[0018] The blood flow waveform data may include, in addition to the blood flow volume, data related to at least one of, for example, the cardiac output and the coefficient of variation of vasomotion. The cardiac output is the amount of blood pumped out by one heartbeat of the heart. Vasomotion is a spontaneous and rhythmic contraction and relaxation movement of blood vessels. The coefficient of variation of vasomotion is a value indicating the variation in blood flow volume caused by vasomotion as a dispersion.

[0019] Also, the blood flow waveform data may include a pulse wave.

[0020] FIG. 3 is a graph showing an example of a frequency spectrum generated by performing Fourier transform processing on the blood flow waveform data as shown in FIG. 2. The vertical axis represents the intensity of the frequency spectrum [unit: dB], and the horizontal axis represents the frequency [unit: Hz]. The Fourier transform processing is an example of frequency analysis processing and is a process for generating a frequency spectrum of waveform data that does not include temporal changes.

[0021] FIG. 3 shows frequency spectra FW1 and FW2 corresponding to each sleep stage. The frequency spectrum FW1 is a frequency spectrum generated as a result of performing Fourier transform processing on the raw waveform data W1. The frequency spectrum FW2 is a frequency spectrum generated as a result of performing Fourier transform processing on the heart rate interval (RRI) of the processed waveform data W2.

[0022] The above sleep stages can be classified into three stages: wakefulness, REM sleep, and non-REM sleep. Non-REM sleep can be further classified into stage 1 (N1), stage 2 (N2), and stage 3 (N3) in order from the lighter sleep stage. REM sleep is sleep accompanied by rapid eye movement (REM). Non-REM sleep is sleep without rapid eye movement.

[0023] This classification is performed based on the electroencephalogram data detected by an electroencephalograph worn by the subject. Electroencephalograms are classified into four types in order from the longest wavelength: β waves, α waves, θ waves, and δ waves. β waves are electroencephalograms with a frequency of about 38 to 14 Hz, for example. α waves are electroencephalograms with a frequency of about 14 to 8 Hz, for example. θ waves are electroencephalograms with a frequency of about 8 to 4 Hz, for example. δ waves are electroencephalograms with a frequency of about 4 to 0.5 Hz, for example.

[0024] When θ waves and δ waves are dominant compared to β waves and α waves, a person is asleep. Here, "dominant" means that the proportion of a certain wave in the measured brain waves increases. The dominant brain waves are known to change periodically within the range of θ waves and δ waves during sleep. Also, when the proportion of θ waves contained in the brain waves is less than a predetermined value, a person is in the REM sleep state, and when the proportion of θ waves is equal to or more than the predetermined value and δ waves are dominant, a person is in the non-REM sleep state. Stage 1 is, for example, a state where α waves are 50% or less and various low-amplitude frequencies are mixed. Stage 2 is, for example, a state where irregular low-amplitude θ waves and δ waves appear but there are no high-amplitude slow waves. Stage 3 is, for example, a state where the slow waves are 2 Hz or less and 20% or more of the slow waves are 75 μV. A state where the slow waves are 2 Hz or less and 50% or more of the slow waves are 75 μV may be referred to as Stage 4.

[0025] In FIG. 3, as sleep stages, wakefulness is shown as "WK", REM sleep as "RM", non-REM sleep Stage 1 as "N1", non-REM sleep Stage 2 as "N2", and non-REM sleep Stage 3 as "N3".

[0026] As shown in the frequency spectra FW1 and FW2 of FIG. 3, in the frequency spectra obtained from the subjects in the sleep stages of Stage 2 and Stage 3, a significant intensity change is recognized in the frequency band of 0.2 to 0.3 Hz (a predetermined frequency band). In other words, in the frequency spectrum, the intensity in a first range R1 of a part of the frequency band of 0.2 to 0.3 Hz is larger than a predetermined value or more than the intensity in a second range R2 outside the first range R1. Hereinafter, the intensity in the first range R1 is referred to as the first intensity, and the intensity in the second range R2 is referred to as the second intensity.

[0027] The first intensity may be, for example, the maximum intensity in a frequency band of 0.2 to 0.3 Hz. The second intensity may be, for example, the maximum intensity in a second range R2 outside a first range R1 (e.g., about ±0.02 Hz centered on the maximum intensity, but within the frequency band of 0.2 to 0.3 Hz) including this maximum intensity. The predetermined value may be set, for example, from experiments, to a size such that when a characteristic waveform Sh that is not present in adjacent frequency bands is included in the frequency band of 0.2 to 0.3 Hz, the inclusion of the waveform Sh can be specified. The characteristic waveform Sh may be, for example, a convex upward shape and a waveform that is somewhat broad (e.g., a waveform with a full half-value width of 0.03 Hz or more). FIG. 3 shows examples of the first range R1 and the second range R2 in the frequency spectra FW1 and FW2 corresponding to stage 3.

[0028] On the other hand, in the frequency spectra obtained from a subject in the waking state, REM sleep, and the sleep stage of stage 1, no significant intensity change is observed in the frequency band of 0.2 to 0.3 Hz, and no such characteristic waveform Sh as described above is observed either.

[0029] As a result of intensive research, the inventor has found that when a frequency spectrum in which a significant intensity change (characteristic waveform Sh) is observed in the frequency band of 0.2 to 0.3 Hz is obtained, the subject is likely to be in the sleep stage of stage 2 or 3. That is, the inventor has found that when a frequency spectrum having the characteristic waveform Sh is obtained, the subject is likely to be in the sleep stage of stage 2 or 3. In addition, the inventor has found that a significant intensity change is observed in the frequency band of 0.2 to 0.3 Hz, particularly in the frequency spectrum of the blood flow waveform data detected by the above-described blood flow meter (e.g., laser Doppler blood flow meter). Based on these findings, the inventor has developed a sleep estimation device capable of improving the determination accuracy of the sleep stage of a subject.

[0030] (Comparison with electrocardiogram waveform data) In addition, there are differences described below between the electrocardiogram waveform data (electrocardiogram) detected by an electrocardiograph and the blood flow waveform data detected by a blood flow meter.

[0031] FIG. 4 is a graph showing an example of electrocardiogram waveform data detected by an electrocardiograph. In FIG. 4, the vertical axis indicates the intensity of heartbeats [unit: dB], and the horizontal axis indicates the measurement time [unit: min]. In FIG. 4, raw waveform data W11 and W12 of heartbeats are shown as electrocardiogram waveform data.

[0032] FIG. 5 is a graph showing an example of a frequency spectrum generated by performing a Fourier transform process on electrocardiogram waveform data. The vertical axis indicates the intensity of the frequency spectrum [unit: dB], and the horizontal axis indicates the frequency [unit: Hz].

[0033] In FIG. 5, frequency spectra FW11 and FW12 corresponding to each sleep stage are shown. The frequency spectrum FW11 is a frequency spectrum generated as a result of performing a Fourier transform process on the raw waveform data W11. The frequency spectrum FW12 is a frequency spectrum generated as a result of performing a Fourier transform process on the heart rate interval (RRI). The sleep stages corresponding to the frequency spectra FW11 and FW12 are specified based on electroencephalogram data acquired from an electroencephalograph worn by the subject.

[0034] As shown in FIG. 5, in the frequency spectra FW11 and FW12 obtained by converting the electrocardiogram waveform data detected from the subjects in the sleep stages of stage 2 and 3, no significant intensity change (characteristic waveform Sh) is observed in the frequency band of 0.2 to 0.3 Hz. Regarding the frequency spectrum FW12 corresponding to the sleep stages of stage 2 and 3, it has a convex upward shape in the frequency band of 0.2 to 0.3 Hz. However, the frequency spectrum FW12 corresponding to the sleep stage of stage 1 also has the same shape as the frequency spectrum FW12 corresponding to stages 2 and 3. Therefore, it is not recognized that the frequency spectrum FW12 corresponding to stages 2 and 3 has a significant intensity change in the frequency band of 0.2 to 0.3 Hz.

[0035] As a result of intensive research, the inventor has found that the significant intensity change observed in the frequency band of 0.2 to 0.3 Hz is an event peculiar to the frequency spectrum of blood flow waveform data. Accordingly, the inventor has found that by determining the sleep stage of the subject using the frequency spectrum converted from blood flow waveform data rather than electrocardiogram waveform data, it is highly likely that the subject is accurately determined to be in the sleep stage of stage 2 or 3.

[0036] (Regarding the frequency band) Due to the blood flow meter used and individual differences of the subject, etc., there may be a slight spread in the frequency band where the above-mentioned significant intensity change is observed. Considering this point, there is a sufficient possibility that a significant intensity change not observed in the electrocardiogram waveform data is observed in the frequency band of, for example, 0.15 to 0.4 Hz of the frequency spectra FW1 and FW2 corresponding to stage 2 or 3. In the following description, it is described that the frequency band where the above-mentioned significant intensity change is observed is 0.2 to 0.3 Hz.

[0037] [Wavelet transform processing] In the above principle, the explanation was made using the frequency spectrum obtained by performing Fourier transform processing as the frequency analysis processing. However, the sleep stage of the subject may be determined based on the frequency spectrum obtained by performing wavelet transform processing as the frequency analysis processing. Wavelet transform processing is an example of time-frequency analysis processing. Time-frequency analysis processing is a process of generating the frequency spectrum of waveform data including temporal changes. Wavelet transform processing is a process of generating the frequency spectrum of waveform data using a mother wavelet which is an arbitrary reference waveform.

[0038] The mother wavelet used in the wavelet transform process is defined as follows. In the following formula, "t" is the time variable, "a" is the scale parameter (the parameter for expanding or contracting the mother wavelet in the time axis direction), and "b" is the translation parameter (the parameter for translating the mother wavelet in the time axis direction).

[0039] [Number]

[0040] Also, the function for performing the wavelet transform process is defined as follows. In the following formula, "f(t)" is the waveform data, and "*" indicates the conjugate complex number. By substituting the mother wavelet with the values of "a" and "b" adjusted above into the following formula, the frequency spectrum of the waveform data can be generated.

[0041] [Number]

[0042] By using the wavelet transform process, the intensity in the frequency band of 0.2 to 0.3 Hz (hereinafter referred to as the target intensity) can be relatively emphasized compared to other frequency bands. As described in the above principle, when a frequency spectrum having a characteristic waveform Sh in the frequency band of 0.2 to 0.3 Hz is obtained, the subject is likely to be in the sleep stage of stage 2 or 3. Therefore, by emphasizing the target intensity using the wavelet transform process, the possibility of more accurately determining whether the subject is in the sleep stage of stage 2 or 3 can be increased.

[0043] In the wavelet transform process, the mother wavelet set so that the target intensity is emphasized as described above may be used. The mother wavelet with an increased target intensity can be set by adjusting the values of the above "a" and "b". Also, Morlet may be used as the mother wavelet. In this case, the scale parameter "a" has a relationship of "ω = 2π / a" and represents a local angular frequency. Since the angular frequency "ω" can be expressed as "ω = 2πf", the wavelet transform process may be executed with this "f (frequency)" part set to 0.2 to 0.3 Hz. The target intensity may be the intensity over the entire frequency band of 0.2 to 0.3 Hz, or may be the intensity in a partial range of the frequency band (e.g., the first range R1).

[0044] Also, as a result of the wavelet transform process on the blood flow waveform data, intensity change data indicating the temporal change of the intensity in each frequency band within a predetermined time can be generated. The predetermined time may be set, for example, by experiment, to a time that enables accurate determination of the sleep stage of the subject. In this embodiment, the predetermined time may be set to, for example, 2.5 minutes.

[0045] Unlike the Fourier transform process, the wavelet transform process can generate a frequency spectrum including the temporal change of intensity, so the number of data can be increased compared to the Fourier transform process. Generally, in the generation of the learned model described below, the more data there are (the more features to be learned), the more accurate the output data can be used to generate a learned model. Therefore, when generating a learned model, it is effective to use the intensity change data.

[0046] FIG. 6 is an image showing an example of the result of the wavelet transform process on the blood flow waveform data. In FIG. 6, an image generated by executing the wavelet transform process on the blood flow waveform data (raw waveform data W1) that is the source of the frequency spectrum FW1 of stage 3 shown in FIG. 3 is shown. The image is an example of intensity change data with the target intensity emphasized. Hereinafter, an image showing the intensity change data is referred to as a wavelet image.

[0047] In FIG. 6, the vertical axis represents frequency [unit: Hz], and the horizontal axis represents time [unit: min]. The shading in the wavelet image of FIG. 6 represents intensity [unit: dB]. That is, the wavelet image is data showing the intensity distribution of the frequency spectrum in a plane defined by frequency and time.

[0048] In the wavelet image of the present embodiment, the frequency band (intensity) may be represented by a color gradation. In the wavelet image, for example, a low frequency band can be represented by a cool color, and a high frequency band can be represented by a warm color. Specifically, the frequency bands may be represented by dark blue, blue, light blue, yellow-green, light yellow-green, yellow, orange, and red in ascending order. If the intensity distribution can be visually recognized in the wavelet image, the frequency bands may be represented by other colors or by grayscale. FIG. 6 shows an example of an image obtained by converting the wavelet image represented by the above colors into grayscale.

[0049] In the wavelet image of FIG. 6, in the first region AR1 that is distributed along the time axis at 0.2 Hz and in the vicinity thereof, it shows a higher intensity than the intensity in the frequency band adjacent to the first region AR1. Specifically, in the frequency band of about 0.2 Hz ± about 0.05 Hz of the first region AR1, an intensity band indicated in red is distributed along the time axis, and around the intensity band, intensity regions indicated in orange, yellow, light yellow-green, and yellow-green are distributed. In FIG. 6, a part of the intensity band indicated in red is indicated by reference numeral 101. Also, a part of the intensity regions indicated in orange, yellow, light yellow-green, and yellow-green are indicated by reference numeral 102. On the other hand, in the adjacent frequency band, mainly, intensity regions indicated in light blue, blue, and dark blue are distributed, but intensity regions indicated in red, orange, and yellow are not distributed. In FIG. 6, a part of the intensity regions indicated in light blue, blue, and dark blue are indicated by reference numeral 103.

[0050] Also, as shown in FIG. 6, in the wavelet image, a sawtooth-shaped intensity band is formed along the time axis in a frequency band higher than the frequency band of 0.2 to 0.3 Hz. In the wavelet image of FIG. 6, a sawtooth-shaped intensity band is formed in the second region AR2 (frequency band of about 0.7 Hz or higher). The second region AR2 has a lower intensity than the first region AR1 in the frequency band of about 0.9 to 1.0 Hz, and the intensity gradually decreases toward the frequency band below 0.9 Hz and the frequency band of 1.0 Hz or higher.

[0051] The above-mentioned sawtooth-shaped intensity band indicates the intensity distribution corresponding to the heartbeat. The intensity distribution becomes a band shape along the time axis in the sleeping state, and the band shape becomes a collapsed state as the sleep becomes lighter. The intensity distribution corresponding to the heartbeat is an intensity distribution that cannot be obtained by Fourier transform processing. By using the wavelet image to generate the learned model described below, a learned model that also takes into account the heartbeat can be generated.

[0052] FIG. 6 shows an example of a wavelet image in which the target intensity is emphasized, but it should be noted that even in a wavelet image in which the target intensity is not emphasized, the intensity of the first region AR1 shows a higher intensity than the intensity in the adjacent frequency band.

[0053] [[ID=eleven]] 〔Generation of Learned Model〕 In the determination of the sleep stage of the subject, a learned model (approximator) for determining the sleep stage of the subject can be used. The learned model is obtained by training a mathematical model (neural network including an input layer, a hidden layer, and an output layer) that mimics the neurons of the human nervous system so that the sleep stage of the user can be determined. The mathematical model may be any model that can generate a learned model capable of determining the sleep stage of the subject. The mathematical model may be, for example, a convolutional neural network (CNN), a recurrent neural network (RNN), or an LSTM (Long Short Term Memory).

[0054] Learning refers to adjusting the strength of connections between units, the bias of connections, etc. so that the correct calculation result is output from the output layer. In this embodiment, when learning is performed, learning data is input to the input layer. In the hidden layer, an operation based on operation data is performed on the learning data, and the operation result in the hidden layer is output as output data from the output layer. The teacher data and the output data are compared, and the operation data is adjusted so that the error is reduced. By repeatedly executing this process for each of a plurality of learning data, a learned model with adjusted operation data is generated. That is, in this embodiment, the learned model may be generated by so-called supervised learning using learning data and teacher data. The sleep estimation device 51 described later can determine the sleep stage of the subject by using the learned model generated in this way.

[0055] Learning data is data that serves as an example for generating a learned model. The learning data may be a frequency spectrum generated from blood flow waveform data. In this embodiment, a wavelet image is used. As the wavelet image, one in which the target intensity is emphasized or one in which the target intensity is not emphasized may be used. The learning data may be one whose behavior is different between waking and sleeping, or one whose behavior changes according to the depth of sleep. The learning data may be various types of data (e.g., frequency spectra of blood flow waveform data showing different waveforms from each other).

[0056] Teacher data is data with correct labels associated with learning data. For example, for frequency spectra as learning data, data in which the sleep stage of a person who has acquired blood flow waveform data is associated as a correct label may be used as teacher data. As described above, the sleep stage of the subject may be specified based on electroencephalogram data detected by an electroencephalograph. As the correct label, a code indicating each sleep stage may be used. Alternatively, as the correct label, a code indicating the correct answer for a specific sleep stage (e.g., stage 2 or 3) may be used, and a code indicating an incorrect answer for other sleep stages may also be used. In the present embodiment, as an example of teacher data, data associated as a correct label with a wavelet image (a wavelet image specified as stage 2 or 3 based on electroencephalogram data) known to correspond to stage 2 or 3 may be used.

[0057] Calculation data is data related to calculations for generating a learned model, including an arithmetic expression, variables of the arithmetic expression (e.g., bias and weight), and data such as an activation function. The bias and weight define the strength of the connection between each unit. By adjusting the bias and weight, the accuracy of the learned model can be improved. As a method for adjusting the calculation data, for example, the error backpropagation method and the gradient descent method may be adopted.

[0058] 〔Embodiment 1〕 Next, an example of a sleep estimation system 1 capable of determining the sleep stage of a subject, constructed based on the above principle, will be described. The sleep estimation system 1 of the present embodiment may be a system capable of determining the sleep stage of a subject using the above learned model.

[0059] <Sleep stage estimation system> FIG. 1 is a block diagram showing a schematic configuration example of the sleep estimation system 1 according to Embodiment 1. As shown in FIG. 1, the sleep estimation system 1 includes an accelerometer 2, a blood flow meter 3, and a mobile terminal 5. In the mobile terminal 5, a sleep estimation device 51 that determines the sleep stage of a subject is constructed by executing, for example, an application capable of determining the sleep stage of the subject as a part of the function of a control unit that comprehensively controls each member of the mobile terminal 5.

[0060] <Accelerometer> The accelerometer 2 is a sensor that can detect the acceleration generated by the movement of the subject. The accelerometer 2 may transmit the detected acceleration as acceleration data to the sleep estimation device 51 via wireless or wired communication. The accelerometer 2 is attached to a part of the subject's body, such as the head or finger. As the accelerometer 2, for example, a known sensor such as a frequency change type, a piezoelectric type, a piezoresistive type, or a capacitance type may be used.

[0061] <Blood flow meter> The blood flow meter 3 may be the blood flow meter described in the above principle. The blood flow meter 3 may be, for example, a laser Doppler blood flow meter. In the present embodiment, the blood flow meter 3 may transmit the raw waveform data W1 as blood flow waveform data to the sleep estimation device 51. The blood flow meter 3 may transmit the processed waveform data W2 to the sleep estimation device 51 instead of the raw waveform data W1. The blood flow meter 3 may not generate the processed waveform data W2, and the sleep estimation device 51 may generate the processed waveform data W2. The blood flow meter 3 is attached to a part of the subject's body, such as the ear, finger, wrist, arm, forehead, nose, or neck.

[0062] <Mobile terminal> The mobile terminal 5 may be any terminal capable of data communication with at least the accelerometer 2 and the blood flow meter 3. The mobile terminal 5 may be, for example, a smartphone or a tablet. The mobile terminal 5 is constructed with the sleep estimation device 51 and is provided with a storage unit 52 and a notification unit 53.

[0063] The storage unit 52 can store programs and data used by the control unit (particularly the sleep estimation device 51). The storage unit 52 can store, for example, the learned model generated as described above and a threshold value for determining whether the subject is stationary.

[0064] The notification unit 53 can notify various information to the surroundings of the mobile terminal 5 (e.g., the subject). In the present embodiment, the notification unit 53 can notify various information according to a notification instruction from the sleep estimation device 51. The notification unit 53 may be at least any one of a sound output device that outputs sound, a vibration device that vibrates the mobile terminal 5, and a display device that displays an image.

[0065] (Sleep Estimation Device) The sleep estimation device 51 can determine the sleep stage of a subject wearing the accelerometer 2 and the blood flow meter 3. The sleep estimation device 51 may include a second acquisition unit 11, a second determination unit 12, a first acquisition unit 13 (acquisition unit), a generation unit 14, a first determination unit 15 (determination unit), and a notification unit 16.

[0066] The second acquisition unit 11 can acquire acceleration data from the accelerometer 2. The second determination unit 12 can determine whether the subject is stationary based on the acceleration data acquired by the second acquisition unit 11. For example, the second determination unit 12 may determine that the subject is stationary when the acceleration indicated by the acceleration data is less than the threshold value stored in the storage unit 52. The second determination unit 12 may transmit the determination result data to the generation unit 14.

[0067] The first acquisition unit 13 can acquire blood flow waveform data (raw waveform data W1) from the blood flow meter 3. The generation unit 14 can generate a frequency spectrum of the blood flow waveform data by performing frequency analysis processing on the blood flow waveform data acquired by the first acquisition unit 13. The first determination unit 15 can determine the sleep stage of the subject based on the frequency spectrum generated by the generation unit 14. In other words, the first determination unit 15 can determine the transition of the depth of sleep of the subject based on the frequency spectrum.

[0068] In this embodiment, the generation unit 14 can generate a wavelet image by executing wavelet transform processing in which the target intensity is relatively emphasized compared to other frequency bands as frequency analysis processing. The wavelet image is processing data indicating the result of time-frequency analysis processing of blood flow waveform data. The first determination unit 15 can determine the sleep stage of the subject based on the wavelet image generated by the generation unit 14.

[0069] In this embodiment, when the first determination unit 15 determines that the characteristic waveform Sh is included in the frequency band of 0.2 to 0.3 Hz of the frequency spectrum, it can be determined that the sleep stage of the subject is stage 2 or 3. In this case, the first determination unit 15 may determine that the sleep stage of the subject has transitioned from stage 1 to stage 2 or 3. On the other hand, when the first determination unit 15 determines that the characteristic waveform Sh is not included in the frequency band of 0.2 to 0.3 Hz, it can be determined that the sleep stage of the subject is a sleep stage other than stage 2 or 3. After the first determination unit 15 determines that the subject is in the sleep stage of stage 2 or 3, when it determines that the characteristic waveform Sh is not included in the frequency band of 0.2 to 0.3 Hz, it may be determined that the sleep stage of the subject has transitioned from stage 2 or 3 to stage 1. The determination of whether or not the characteristic waveform Sh is included can also be performed, for example, by determining whether or not the first intensity is greater than the second intensity by a predetermined value or more.

[0070] In this embodiment, the first determination unit 15 may execute the determination of the sleep stage of the subject by using a learned model. In this case, the first determination unit 15 can output the determination result of the sleep stage of the subject from the output layer of the learned model by providing the wavelet image generated by the generation unit 14 as input data to the input layer of the learned model.

[0071] As described above, the learned model is generated using, as an example of teacher data, data associated as correct labels with wavelet images known to correspond to stage 2 or 3. Therefore, the first determination unit 15 can determine that the sleep stage of the subject is stage 2 or 3, or that the subject has transitioned from stage 1 to stage 2 or 3, by providing the wavelet image generated by the generation unit 14 to the learned model. When the first determination unit 15 provides the learned model with a frequency spectrum including a waveform Sh characteristic in a frequency band of particularly 0.2 to 0.3 Hz, there is a possibility that it can accurately determine that the sleep stage of the subject is stage 2 or 3.

[0072] Here, when estimating the sleep stage using the blood flow waveform data, the sleep estimation device may not be able to determine whether the subject is asleep only based on the blood flow waveform data. For example, in the case of a subject with stable blood flow even during wakefulness, there may be no significant difference between the blood flow waveform data during wakefulness and the blood flow waveform data during sleep, and in this case, the sleep estimation device may not be able to determine whether the subject is asleep. In the present embodiment, when the second determination unit 12 determines that the subject is stationary, the generation unit 14 executes frequency analysis processing on the blood flow waveform data, so that the determination process by the first determination unit 15 can be executed in a state where it is highly likely that the subject is asleep.

[0073] The notification unit 16 can execute notification processing based on the determination result of the first determination unit 15. The notification unit 16 may transmit a notification instruction according to the notification processing to the notification unit 53. Thereby, the notification unit 53 can notify information according to the notification processing to the surroundings of the mobile terminal 5. The notification unit 16 may include a first notification unit 161 and a second notification unit 162.

[0074] The first notification unit 161 can execute the first notification process after a predetermined time has elapsed since the transition from stage 1 to stage 2 or 3 is detected by the first determination unit 15 as the above notification process. The first notification process is a notification process associated with the detection of the transition, and may be, for example, an alarm process for prompting the subject to wake up, or a process for notifying the detection of the transition. The predetermined time may be appropriately set by experiment, for example, according to the purpose of the notification. In this embodiment, the predetermined time may be set to a time when the subject is presumed to be likely to wake up when measured from the time of the transition from stage 1 to stage 2 or 3. By the first notification process, for example, the subject can wake up at a good waking timing after falling asleep. The first notification unit 161 may execute the first notification process when the first determination unit 15 detects a transition from stage 1 to stage 2 or 3.

[0075] The second notification unit 162 can execute the second notification process after a predetermined time has elapsed since the transition from stage 2 or 3 to stage 1 is detected by the first determination unit 15 as the above notification process. The second notification process is a notification process associated with the detection of the transition, and may be, for example, an alarm process for prompting the subject to wake up, or a process for notifying the detection of the transition. The predetermined time may be appropriately set by experiment, for example, according to the purpose of the notification. In this embodiment, the predetermined time may be set to a time when the subject is presumed to be likely to wake up when measured from the time of the transition from stage 2 or 3 to stage 1. By the second notification process, for example, the subject can wake up at a good waking timing after falling asleep. The second notification unit 162 may execute the second notification process when the first determination unit 15 detects a transition from stage 2 or 3 to stage 1.

[0076] 〔Flow of the process〕 FIG. 7 is a flowchart showing an example of the flow of the process (sleep estimation method) by the sleep estimation device 51. When the sleep estimation device 51 determines the sleep stage of the subject, after the blood flow meter 3 is attached to the subject, the blood flow meter 3 may start detecting blood flow waveform data.

[0077] As shown in FIG. 7, in the sleep estimation device 51, the first acquisition unit 13 can acquire blood flow waveform data from the blood flow meter 3 (S1: first acquisition step, acquisition step). The generation unit 14 can generate a frequency spectrum of the blood flow waveform data by performing frequency analysis processing on the blood flow waveform data. In the present embodiment, the generation unit 14 can generate a wavelet image with enhanced target intensity by performing wavelet transform processing on the blood flow waveform data (S2: generation step). The first determination unit 15 can determine the sleep stage of the subject based on the frequency spectrum. In the present embodiment, the first determination unit 15 can determine the sleep stage of the subject by inputting the wavelet image with enhanced target intensity into the learned model (S3) (S4: first determination step, determination step).

[0078] Based on the determination result of the sleep stage, the first determination unit 15 can determine whether a transition has occurred from stage 1 to stage 2 or 3 (S5). When the first determination unit 15 determines that a transition has occurred from stage 1 to stage 2 or 3 (YES in S5), the first notification unit 161 can determine whether a predetermined time has elapsed since that determination (S6). When the first notification unit 161 determines that a predetermined time has elapsed (YES in S6), as the first notification process, for example, it can execute an alarm process for causing the alarm sound to be notified from the notification unit 53 (S7). The notification unit 53 can notify the alarm sound in response to a notification instruction from the first notification unit 161.

[0079] If NO in S5, the process may return to the process of S1. If NO in S6, the process of S6 may be repeated. Also, in S5, when the first determination unit 15 determines that a transition has occurred from stage 2 or 3 to stage 1, the second notification unit 162 may execute the second notification process, for example, after a predetermined time has elapsed.

[0080] [Problems in the Prior Art and Effects of the Sleep Estimation Device According to the Present Disclosure] Patent Document 1 discloses a method for detecting non-REM sleep including the following steps 1 to 4. · Step 1: A step of generating time-series data of the heartbeat intervals of the subject. · Step 2: Set a window of a predetermined time length that moves along the time axis of the time-series data, and for each of a plurality of determination time points on the time axis, perform spectral analysis on the time-series data within the window containing it. · Step 3: Calculate the concentration degree of the power of the high-frequency component of the heart rate fluctuation from the spectrum of each window. · Based on the calculated concentration degree, determine whether it is non-REM sleep.

[0081] In the above method, as the detection device for the time-series data in Step 1, for example, a plethysmograph or an electrocardiograph is used.

[0082] However, handling an electroencephalograph and acquiring electroencephalograms require advanced specialized knowledge. Also, attaching an electroencephalograph is complicated. Therefore, it is difficult for the subject to easily acquire electroencephalograms and to easily grasp their own sleep stages.

[0083] Also, as described above, the inventor has found that when a significant intensity change is recognized in the frequency band of 0.2 to 0.3 Hz in the frequency spectrum of the blood flow waveform data, the subject is likely to be in the sleep stage of Stage 2 or 3.

[0084] The sleep estimation device 51 of the present disclosure can determine the sleep stage of the subject using blood flow waveform data. Handling a blood flow meter and acquiring blood flow waveform data do not require as much advanced specialized knowledge as an electroencephalograph. Also, attaching a blood flow meter is easier than an electroencephalograph. That is, since the sleep estimation device 51 can acquire the blood flow waveform data of the subject relatively easily, it can determine the sleep stage of the subject relatively easily. Also, according to the sleep estimation device 51, the subject can easily grasp their own sleep stage.

[0085] In addition, when the sleep estimation device 51 of the present disclosure obtains a frequency spectrum having the above-mentioned significant intensity change not recognized in the electrocardiogram waveform data, it can be determined that the sleep stage of the subject is stage 2 or stage 3. Therefore, the sleep estimation device 51 can increase the possibility of accurately estimating that the sleep stage of the subject is stage 2 or stage 3.

[0086] 〔Embodiment 2〕 Another embodiment of the present disclosure will be described below. For convenience of explanation, members having the same functions as those described in the above embodiment are denoted by the same reference numerals, and the description thereof will not be repeated. FIG. 8 is a block diagram showing a schematic configuration example of the sleep estimation system 1A according to Embodiment 2.

[0087] In the sleep estimation system 1 according to Embodiment 1, the mobile terminal 5 can acquire blood flow waveform data from the blood flow meter 3 attached to the subject, for example, by wireless communication. Then, the sleep estimation device 51 constructed in the mobile terminal 5 can determine the sleep stage of the subject based on the blood flow waveform data.

[0088] On the other hand, as shown in FIG. 8, in the sleep estimation system 1A according to Embodiment 2, the blood flow meter 3 may be provided in the wearable device 20. In addition, in the wearable device 20, the sleep estimation device 51 may be constructed as a part of the function of the control unit that comprehensively controls each member of the wearable device 20. That is, in the sleep estimation system 1A, the sleep estimation device 51 may be mounted on the wearable device 20 together with the blood flow meter 3. Therefore, it is possible to execute the acquisition process of the blood flow waveform data and the determination process of the sleep stage based on the blood flow waveform data with one device. In addition, various devices or components required when performing wireless or wired communication between two devices become unnecessary. The wearable device 20 may be worn at a position similar to the position where the blood flow meter 3 is worn on the subject.

[0089] 〔Modification〕 As described above, the invention according to the present disclosure has been described based on the drawings and examples. However, the invention according to the present disclosure is not limited to the above-described embodiments. That is, the invention according to the present disclosure can be variously modified within the scope shown in the present disclosure, and embodiments obtained by appropriately combining the technical means disclosed in different embodiments are also included in the technical scope of the invention according to the present disclosure. In other words, it should be noted that those skilled in the art can easily make various modifications or corrections based on the present disclosure. Also, note that these modifications or corrections are included in the scope of the present disclosure.

[0090] (Modification Example of Frequency Analysis Processing) For example, the generation unit 14 may generate a wavelet transform image by performing wavelet transform processing on the blood flow waveform data, and it is not always necessary to perform wavelet transform processing so that the target intensity is emphasized.

[0091] Further, the generation unit 14 may perform time-frequency analysis processing other than wavelet transform processing on the blood flow waveform data. The generation unit 14 may perform, for example, short-time Fourier transform processing on the blood flow waveform data. The short-time Fourier transform processing performs Fourier transform processing on each of a plurality of waveform data cut out along the time axis using a window function. In this case, the generation unit 14 may generate an image (intensity change data) similar to the wavelet image as processing data by performing short-time Fourier transform processing in which the target intensity is relatively emphasized compared to other frequency bands.

[0092] Further, the generation unit 14 may perform processing other than time-frequency analysis processing as frequency analysis processing. The generation unit 14 may perform, for example, Fourier transform processing. When the generation unit 14 performs Fourier transform processing, for example, the frequency spectra FW1 or FW2 shown in FIG. 3 can be generated. Also, the generation unit 14 may generate a frequency spectrum (waveform) as shown in FIG. 3 by performing short-time Fourier transform processing.

[0093] In this way, the generation unit 14 can generate various frequency spectra. Therefore, the first determination unit 15 can determine the sleep stage of the subject by inputting the various frequency spectra into the learned model. However, the learned model is generated using frequency spectra of the same type as the frequency spectra generated by the generation unit 14 as learning data and teacher data.

[0094] (Modification example of the determination process of the first determination unit) The learned model may not be stored in the storage unit 52 of the mobile terminal 5 or the wearable device 20. That is, the sleep estimation system 1 or 1A may not perform the determination of the sleep stage of the subject using the learned model.

[0095] For example, when the first determination unit 15 determines that the first intensity is greater than or equal to a predetermined value more than the second intensity in the frequency spectrum generated by the generation unit 14, it may determine that the sleep stage of the subject is stage 2 or 3. Instead of the learned model, a predetermined value may be stored in the storage unit 52.

[0096] In addition, when the first determination unit 15 determines the sleep stage of the subject using the frequency spectrum FW1, if a characteristic waveform Sh can be extracted in the frequency band of 0.2 to 0.3 Hz, it may be determined that the sleep stage of the subject is stage 2 or 3. In this case, instead of the learned model, a reference waveform capable of extracting the characteristic waveform Sh in the frequency spectrum FW1 may be stored in the storage unit 52. When the first determination unit 15 determines that there is a waveform that matches the reference waveform in the frequency band of 0.2 to 0.3 Hz of the frequency spectrum FW1, it may be determined that the characteristic waveform Sh can be extracted in the frequency band. The first determination unit 15 may determine that there is a waveform that matches the reference waveform in the frequency band of 0.2 to 0.3 Hz when the degree of coincidence between the waveform included in the frequency band of 0.2 to 0.3 Hz and the reference waveform is equal to or higher than a threshold value set by an experiment, for example. In addition, the first determination unit 15 may determine whether the characteristic waveform Sh is included in the frequency band of 0.2 to 0.3 Hz based on other indicators (e.g., the degree of change in the slope of the waveform). Further, the same determination as that for the frequency spectrum FW1 may be performed for the frequency spectrum FW2.

[0097] (Modification example of the sleep estimation system 1 or 1A) The acceleration generated by the movement of the subject is detected by the accelerometer 2, and the sleep estimation device 51 does not have to determine the sleep state of the subject based on the acceleration. In this case, the sleep estimation system 1 or 1A does not include the accelerometer 2, and the sleep estimation device 51 does not have to include the second acquisition unit 11 and the second determination unit 12.

[0098] 〔Example of realization by software〕 The control block of the sleep estimation device 51 may be realized by a logic circuit (hardware) formed in an integrated circuit (IC chip) or the like, or may be realized by software.

[0099] In the latter case, the sleep estimation device 51 includes a computer that executes instructions of a program, which is software for realizing each function. This computer includes, for example, at least one processor (control device) and at least one computer-readable recording medium that stores the above program. Then, in the above computer, when the above processor reads and executes the above program from the above recording medium, the object of the present disclosure is achieved. As the above processor, for example, a CPU (Central Processing Unit) can be used. As the above recording medium, a "non-transitory tangible medium", for example, in addition to a ROM (Read Only Memory) and the like, a tape, a disk, a card, a semiconductor memory, a programmable logic circuit, etc. can be used. Further, it may further include a RAM (Random Access Memory) for expanding the above program. Further, the above program may be supplied to the above computer via any transmission medium (communication network, broadcast wave, etc.) capable of transmitting the program. Note that one aspect of the present disclosure can also be realized in the form of a data signal embedded in a carrier wave, in which the above program is embodied by electronic transmission.

[0100] 〔Expression Example of the Present Disclosure〕 Further, one aspect of the present disclosure may be expressed as follows.

[0101] A sleep estimation device according to one aspect of the present disclosure includes a first acquisition unit that acquires blood flow data indicating the blood flow of a subject, a generation unit that generates a frequency spectrum of the blood flow data by performing frequency analysis processing on the blood flow data, and a first determination unit that determines the sleep stage of the subject based on the frequency spectrum.

[0102] Furthermore, a sleep estimation device according to an aspect of the present disclosure includes an acquisition unit that acquires blood flow data indicating the blood flow of a subject, and a generation unit that generates processing data indicating the result of time-frequency analysis processing of the blood flow data by performing a wavelet transform process or a short-time Fourier transform process in which the intensity in a predetermined frequency band is relatively emphasized compared to other frequency bands on the blood flow data, and a determination unit that determines the sleep stage of the subject based on the processing data.

[0103] Furthermore, a sleep estimation method according to an aspect of the present disclosure includes a first acquisition step of acquiring blood flow data indicating the blood flow of a subject, a generation step of generating a frequency spectrum of the blood flow data by performing frequency analysis processing on the blood flow data, and a first determination step of determining the sleep stage of the subject based on the frequency spectrum.

[0104] Furthermore, a sleep estimation method according to an aspect of the present disclosure includes an acquisition step of acquiring blood flow data indicating the blood flow of a subject, a generation step of generating processing data indicating the result of time-frequency analysis processing of the blood flow data by performing a wavelet transform process or a short-time Fourier transform process in which the intensity in a predetermined frequency band is relatively emphasized compared to other frequency bands on the blood flow data, and a determination step of determining the sleep stage of the subject based on the processing data.

[0105] Furthermore, a sleep estimation system according to an aspect of the present disclosure includes a first acquisition unit that acquires blood flow data indicating the blood flow of a subject, a generation unit that generates a frequency spectrum of the blood flow data by performing frequency analysis processing on the blood flow data, and a first determination unit that determines the sleep stage of the subject based on the frequency spectrum. When the sleep stages in non-REM sleep are set as stage 1, 2, and 3 in order from a lighter sleep stage, the first determination unit determines that the sleep stage of the subject has transitioned from stage 1 to stage 2 or 3 when a first intensity, which is the maximum intensity in a first range of a part of a region including a frequency band of 0.2 Hz or more and 0.3 Hz or less, as the frequency spectrum, is greater than a second intensity in a second range of a part of the region outside the first range.

[0106] Furthermore, the sleep estimation system according to an aspect of the present disclosure may include a first notification unit that executes a first notification process when it is determined by the first determination unit that the transition from stage 1 to stage 2 or 3 has occurred, or after a predetermined time has elapsed since it was determined that the transition from stage 1 to stage 2 or 3 has occurred.

[0107] Furthermore, in the sleep estimation system according to an aspect of the present disclosure, the frequency spectrum generated by the generation unit when the first determination unit determines that the sleep stage of the subject has transitioned from stage 1 to stage 2 or 3 may include a broad upwardly convex waveform centered on the first intensity in the frequency band.

[0108] Furthermore, a sleep estimation system according to one aspect of the present disclosure includes a first acquisition unit that acquires blood flow data indicating the blood flow of a subject, a generation unit that generates a frequency spectrum of the blood flow data by performing frequency analysis processing on the blood flow data, and a first determination unit that determines the sleep stage of the subject based on the frequency spectrum. When the sleep stages in non-REM sleep are stage 1, stage 2, and stage 3 in order from the lighter sleep stage, the generation unit generates intensity change data indicating the change over time of the intensity in each frequency band within a predetermined time as the frequency spectrum by performing time-frequency analysis processing as the frequency analysis processing. The first determination unit uses, as teacher data, the intensity change data including a frequency spectrum having a predetermined shape in a frequency band of 0.2 Hz or more and 0.3 Hz or less, which is specified as corresponding to stage 2 or 3 based on biological information different from the blood flow data, and is learned by a learned model. When the intensity change data including the frequency spectrum having the predetermined shape generated by the generation unit is given to the learned model, it is determined that the sleep stage of the subject has transitioned from stage 1 to stage 2 or 3.

[0109] Furthermore, a sleep estimation system according to one aspect of the present disclosure includes a first acquisition unit that acquires blood flow data indicating the blood flow of a subject, a generation unit that generates a frequency spectrum of the blood flow data by performing frequency analysis processing on the blood flow data, and a first determination unit that determines that the sleep stage of the subject has transitioned from stage 1 to stage 2 or 3 when it is determined that the frequency spectrum has a predetermined shape in a frequency band of 0.2 Hz or more and 0.3 Hz or less. The sleep estimation system also includes a second acquisition unit that acquires acceleration data indicating the acceleration caused by the movement of the subject, and a second determination unit that determines whether the subject is stationary based on the acceleration data. The generation unit performs the frequency analysis processing when the second determination unit determines that the subject is stationary.

[0110] Furthermore, a sleep estimation system according to one aspect of the present disclosure includes an acquisition unit that acquires blood flow data indicating the blood flow of a subject, and performs a process of relatively emphasizing the intensity in a frequency band of 0.2 Hz or more and 0.3 Hz or less with respect to the blood flow data than other frequency bands, thereby generating processing data indicating the result of time-frequency analysis processing of the blood flow data. A generation unit, and a determination unit that determines the sleep stage of the subject based on the processing data. The generation unit generates intensity change data indicating a change over time of the intensity in each frequency band within a predetermined time as the processing data. When the sleep stages in non-REM sleep are stage 1, 2, and 3 in order from the lighter sleep stage, the determination unit is based on biological information different from the blood flow data. When the intensity change data including a frequency spectrum having a predetermined shape in a frequency band of 0.2 Hz or more and 0.3 Hz or less, which is specified as corresponding to stage 2 or 3, is given to a learned model learned using the data as teacher data, it is determined that the sleep stage of the subject has transitioned from stage 1 to stage 2 or 3.

[0111] Furthermore, in a sleep estimation system according to one aspect of the present disclosure, the generation unit may generate the processing data by performing a wavelet transform process or a short-time Fourier transform process as the process of emphasizing.

[0112] Furthermore, in a sleep estimation system according to one aspect of the present disclosure, the biological information may be electroencephalogram data detected by an electroencephalograph.

[0113] Furthermore, in a sleep estimation system according to one aspect of the present disclosure, the predetermined shape may be a broad waveform convex upward.

[0114] Furthermore, a sleep estimation system according to one aspect of the present disclosure may include a blood flow meter that detects the blood flow data by receiving scattered light generated by irradiating light on the blood vessels of the subject.

[0115] Furthermore, a sleep estimation system according to an aspect of the present disclosure may include a wearable device including a blood flow meter that detects the blood flow data by receiving scattered light generated by irradiating light onto a blood vessel of the subject.

[0116] Furthermore, a sleep estimation method according to an aspect of the present disclosure includes: a first acquisition step of acquiring blood flow data indicating the blood flow of a subject; a generation step of generating a frequency spectrum of the blood flow data by performing frequency analysis processing on the blood flow data; and a first determination step of determining a sleep stage of the subject based on the frequency spectrum. When the sleep stages in non-REM sleep are stages 1, 2, and 3 in order from a lighter sleep stage, in the first determination step, as the frequency spectrum, when a first intensity that is the maximum intensity in a first range of a part of a region including a frequency band of 0.2 Hz or more and 0.3 Hz or less is greater than a second intensity in a second range of a part of the region outside the first range, it is determined that the sleep stage of the subject has transitioned from the stage 1 to the stage 2 or 3.

[0117] Furthermore, a sleep estimation method according to an aspect of the present disclosure includes an acquisition step of acquiring blood flow data indicating the blood flow of a subject, and performing a process of relatively emphasizing the intensity in a frequency band of 0.2 Hz or more and 0.3 Hz or less with respect to the blood flow data than other frequency bands, thereby generating processing data indicating the result of time-frequency analysis processing of the blood flow data. A generation step, and a determination step of determining a sleep stage of the subject based on the processing data. In the generation step, as the processing data, intensity change data indicating a change over time of the intensity in each frequency band within a predetermined time is generated. When the sleep stages in non-REM sleep are stage 1, 2, and 3 in order from a lighter sleep stage, in the determination step, based on biological information different from the blood flow data, it is specified as corresponding to stage 2 or 3. When the intensity change data including the frequency spectrum having a predetermined shape in the frequency band of 0.2 to 0.3 Hz is given to the learned model learned using the intensity change data as teacher data, it is determined that the sleep stage of the subject has transitioned from stage 1 to stage 2 or 3.

Explanation of Signs

[0118] 1, 1A Sleep Estimation System 3 Blood Flow Meter 11 Second Acquisition Unit 12 Second Determination Unit 13 First Acquisition Unit (Acquisition Unit) 14 Generation Unit 15 First Determination Unit (Determination Unit) 20 Wearable Device 51 Sleep Estimation Device 161 First Notification Unit 162 Second Notification Unit

Claims

1. A determination unit that determines the sleep stage of the subject based on the frequency spectrum of the blood flow data of the subject, When the sleep stages in non-REM sleep are stage 1, 2, and 3 in order from the lighter sleep stage, When at least the frequency spectrum includes a predetermined shape in a region including a frequency band of 0.2 Hz or more and 0.3 Hz or less, the determination unit determines that the sleep stage of the subject has transitioned from stage 1 to stage 2 or 3, The predetermined shape included in the region is a convex upward waveform shape including a first intensity that is the maximum intensity in the region, a sleep estimation system.

2. The determination unit determines that the predetermined shape is included when the first intensity in a first range of a part of the frequency band in the frequency spectrum is greater than a second intensity in a second range outside the first range. The sleep estimation system according to claim 1.

3. A first notification unit that executes a first notification process when it is determined by the determination unit that the transition has occurred from stage 1 to stage 2 or 3, or after a predetermined time has elapsed since it was determined that the transition has occurred from stage 1 to stage 2 or 3. The sleep estimation system according to claim 1 or 2.

4. A blood flow meter that detects the blood flow data by receiving scattered light generated by irradiating light on the blood vessels of the subject. The sleep estimation system according to any one of claims 1 to 3.

5. A wearable device including a blood flow meter that detects the blood flow data by receiving scattered light generated by irradiating light on the blood vessels of the subject. The sleep estimation system according to any one of claims 1 to 3.

6. A determination unit that determines the sleep stage of the subject based on the frequency spectrum of the blood flow data of the subject, When the sleep stages in non-REM sleep are stage 1, 2, and 3 in order from the lighter sleep stage, When the frequency spectrum of the blood flow data is given to a learned model that has been learned using, as teacher data, a frequency spectrum having a predetermined shape in a region including a frequency band of 0.2 Hz or more and 0.3 Hz or less, which is specified as corresponding to stage 2 or 3 based on biological information different from the blood flow data, the determination unit determines whether the sleep stage of the subject has transitioned from stage 1 to stage 2 or 3. The predetermined shape included in the region is a convex upward waveform shape including a first intensity that is the maximum intensity in the region. The biological information is electroencephalogram data detected by an electroencephalograph, and it is a sleep estimation system.

7. When it is determined by the determination unit that a transition has occurred from the stage 1 to the stage 2 or 3, or after a predetermined time has elapsed since it is determined that a transition has occurred from the stage 1 to the stage 2 or 3, a first notification unit that executes a first notification process is provided. The sleep estimation system according to claim 6.

8. A blood flow meter that detects the blood flow data by receiving scattered light generated by irradiating light on the blood vessels of the subject, and the sleep estimation system according to claim 6 or 7.

9. A wearable device including a blood flow meter that detects the blood flow data by receiving scattered light generated by irradiating light on the blood vessels of the subject, and the sleep estimation system according to claim 6 or 7.

10. A sleep estimation method executed in a sleep estimation system, including a determination step in which a determination unit included in the sleep estimation system determines a sleep stage of the subject based on a frequency spectrum of blood flow data of the subject. When the sleep stages in non-REM sleep are set as stages 1, 2, and 3 in order from a lighter sleep stage, in the determination step, when at least the frequency spectrum includes a predetermined shape in a region including a frequency band of 0.2 Hz or more and 0.3 Hz or less, it is determined that the sleep stage of the subject has transitioned from the stage 1 to the stage 2 or 3. The predetermined shape included in the region is a convex upward waveform shape including a first intensity that is the maximum intensity in the region. The sleep estimation method.

11. A sleep estimation method executed in a sleep estimation system, including a determination step in which a determination unit included in the sleep estimation system determines a sleep stage of the subject based on a frequency spectrum of blood flow data of the subject. When the sleep stages in non-REM sleep are set as stages 1, 2, and 3 in order from a lighter sleep stage, In the determination step, when the frequency spectrum of the blood flow data is given to a learned model that has been trained using, as teacher data, a frequency spectrum having a predetermined shape in a frequency band of 0.2 Hz or more and 0.3 Hz or less, which is specified as corresponding to the stage 2 or 3 based on biological information different from the blood flow data, it is determined whether the sleep stage of the subject has transitioned from the stage 1 to the stage 2 or 3. The predetermined shape included in the region is a convex upward waveform shape including a first intensity that is the maximum intensity in the region. The biological information is electroencephalogram data detected by an electroencephalograph, and it is a sleep estimation method.

Images