Control device, wake-up support system, learning device, and inference device

Abstract

To awaken a user smoothly by giving vigilance stimulation without giving a feeling of discomfort to the user while executing control to give the vigilance stimulation of a type and strength suitable for each user, solving the problem that although it is effective to give the user stimulation for urging him or her to wake up at a timing that the user's sleep is light for awakening him or her smoothly while keeping a sleep state of good quality, there is an individual difference in each user in easiness of waking up and sensitivity to vigilance stimulation, and there is a case where a feeling of discomfort is given by the vigilance stimulation depending on the user.SOLUTION: A control device of the present invention includes an acquisition part, a calculation part, and a control part. The control part executes control to increase an arousal degree when an arousal degree is low with respect to an arousal degree threshold, which is a threshold of the arousal degree for bringing a user into a state that the user wakes up from sleep.SELECTED DRAWING: Figure 2

Description

[Technical field]

[0001] The present invention relates to a wake-up assistance system. [Background technology]

[0002] In order to achieve a good quality sleep state and to wake up smoothly, it is effective to give the user a stimulus to encourage awakening when the user is in a light sleep state.

[0003] As a method of giving a user a stimulus to encourage awakening (hereinafter referred to as "awakening stimulus"), it has been proposed to immediately awaken the user by setting the radiation device to "high" if the user does not wake up even after the wake-up time has passed, or by setting the lighting to a strong white light that disturbs sleep (see, for example, Patent Document 1). [Prior art documents] [Patent documents]

[0004] [Patent Document 1] JP 2017-113454 A Summary of the Invention [Problem to be solved by the invention]

[0005] However, the ease of awakening and sensitivity to awakening stimuli vary from one user to another. For example, even if an air conditioner provides airflow to a user, some users may not be fully awakened by the scheduled wake-up time. In addition, some users may feel uncomfortable in response to awakening stimuli.

[0006] The present invention has been made to solve the above-mentioned problems, and aims to control the type and intensity of awakening stimuli to be appropriate for each user, and to wake up the user smoothly by providing the awakening stimuli without causing discomfort to the user. [Means for solving the problem]

[0007] The control device of the present invention comprises an acquisition unit that acquires a user's body movement information, breathing information, and pulse rate variability information, a calculation unit that calculates a level of alertness calculated based on the body movement information and breathing information of the user, and a level of comfort calculated based on the pulse rate variability information of the user, and a control unit that performs wake-up control, which is control to encourage the user to wake up, based on control information including the level of alertness and the comfort level. Effect of the Invention

[0008] The wake-up assistance system according to the present invention can provide a wake-up stimulus to wake up the user smoothly without causing discomfort to the user. [Brief description of the drawings]

[0009] [Figure 1] 1 is a cross-sectional side view showing a room in which a wake-up support system according to a first embodiment is installed. [Diagram 2] 1 is a functional block diagram of a wake-up assistance system according to a first embodiment. [Diagram 3] 1 is a functional block diagram of a wake-up assistance system according to a first embodiment, in which a stimulus generation device includes an air conditioner, a light generation unit, and a sound generation unit. FIG. [Figure 4] FIG. 1 is a diagram showing an example of changes in a sleep state from when a person starts sleeping until when he or she wakes up. [Diagram 5] 4 is a flowchart illustrating the operation of the wake-up assistance system according to the first embodiment. [Figure 6] 1 is a graph showing the relationship between stimulation intensity and wakefulness level A in the wake-up assistance system. [Figure 7] 10 is a flowchart illustrating the operation of the wake-up assistance system according to the second embodiment. [Figure 8] FIG. 11 is a functional block diagram of a wake-up assistance system according to a third embodiment. [Figure 9] 11 is a flowchart illustrating the operation of the wake-up assistance system according to the third embodiment. [Figure 10] FIG. 11 is a functional block diagram of a wake-up assistance system according to a fourth embodiment. [Figure 11] 13 is a flowchart illustrating the operation of the wake-up assistance system according to the fifth embodiment. [Figure 12] 13 is a flowchart illustrating the operation of the wake-up assistance system according to the sixth embodiment. [Figure 13] FIG. 13 is a functional block diagram of a wake-up assistance system according to a seventh embodiment. [Figure 14] 13 is a flowchart illustrating the operation of the wake-up assistance system according to the seventh embodiment. [Figure 15] FIG. 23 is a functional block diagram of a wake-up assistance system according to an eighth embodiment. [Figure 16] 20 is a flowchart illustrating the operation of the wake-up assistance system according to the eighth embodiment. [Figure 17] FIG. 13 is a functional block diagram of a wake-up assistance system according to a ninth embodiment. [Figure 18] 13 is a flowchart illustrating the operation of the wake-up assistance system according to the ninth embodiment. [Figure 19] FIG. 23 is a functional block diagram of a learning device according to a tenth embodiment. [Figure 20] FIG. 1 illustrates an example of a neural network. [Figure 21] 23 is a flowchart showing the operation of a learning phase according to the tenth embodiment. [Figure 22] FIG. 23 is a functional block diagram of an inference device according to a tenth embodiment. [Figure 23] 23 is a flowchart showing the operation of the utilization phase according to the tenth embodiment. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0010] Hereinafter, an embodiment of the present invention will be described with reference to the drawings. In the following drawings, the same or corresponding parts are given the same reference numerals, and the description thereof will not be repeated. In addition, in the following drawings including FIG. 1, the size relationship of each component may differ from the actual one. Furthermore, the forms of the components shown in the entire specification are merely examples, and are not limited to these descriptions.

[0011] Embodiment 1 The wake-up assistance system 1 according to the first embodiment will be described in detail below with reference to the drawings.

[0012] <Configuration of the wake-up assistance system> FIG. 1 is a cross-sectional side view showing a room in which a wake-up support system 1 according to the first embodiment is installed.

[0013] The bedroom 200 is a living space of the user. The bedroom 200 is equipped with a wake-up assistance system 1, and FIG. 1 illustrates a state in which the user is sleeping. In the example of FIG. 1, an indoor unit 41 of an air conditioner 40 is provided, and an airflow can be generated toward the user. The user is sleeping using bedding 210 provided in the bedroom 200, and a smartphone is placed on the bedding 210. The smartphone has the functions of an acquisition unit 10 and a display device 70, which will be described later.

[0014] <System configuration diagram of the wake-up assistance system> 2 is a system configuration diagram of the wake-up assistance system 1 according to the embodiment 1. The wake-up assistance system 1 shown in FIG.

[0015] The stimulus generating device 5 provides the user with an awakening stimulus. The awakening stimulus is a stimulus that is externally provided to the user in order to awaken the user from a sleeping state. As shown in FIG. 3, for example, an air conditioner 40, a light generating unit 50, and a sound generating unit 60 can be used as a means for providing the awakening stimulus. In addition, the means is not limited to these, and for example, an electric fan or a vibration generating device may also be used.

[0016] The acquisition unit 10 includes, for example, a biosensor 11. Bioinformation of the user is acquired by the biosensor 11. The acquired bioinformation includes, for example, body movement information, pulse information, pulse variability information, and respiration information.

[0017] The acquisition unit 20 can also acquire the time when the user wants to wake up (hereinafter: "scheduled wake-up time Tw") and the time when control of the stimulus generating device 5 (hereinafter: "wake-up control WC") starts (hereinafter: "operation start time Ts"). The scheduled wake-up time Tw and the operation start time Ts may be acquired by, for example, the user inputting information into a smartphone, or may be acquired by inputting information into a remote control that operates the air conditioner 40.

[0018] The calculation unit 31 calculates the awakening level A and the comfort level C based on the biological information acquired by the biological sensor 11. The awakening level A and the comfort level C will be described later.

[0019] The control unit 33 outputs a control signal based on control information OP including the awakening level A and comfort level C calculated by the calculation unit 31 and the information acquired by the acquisition unit 10. Based on this control signal, the control unit 33 controls the stimulus generation device 5.

[0020] A case where the stimulus generating device 5 is composed of an air conditioner 40, a light generating unit 50, and a sound generating unit 60 will be described with reference to FIG. 3. The air conditioner 40 generates an airflow as an awakening stimulus and changes the temperature in the bedroom 200. The air conditioner 40 is composed of an indoor unit 41, a room temperature sensor 44, and an outdoor unit (not shown) connected to the indoor unit 41 via a refrigerant pipe. In the example of FIG. 1, the indoor unit 41 is placed near the ceiling of the bedroom 200. The indoor unit 41 is equipped with a louver that controls the direction of the airflow blown out into the bedroom 200. The indoor unit 41 is controlled based on a control signal output by the control unit 33.

[0021] The light generating unit 50 generates light as an awakening stimulus. The light generating unit 50 may be, for example, a ceiling light or a desk lamp. The light generating unit 50 is controlled based on a control signal output by the control unit 33.

[0022] The sound generating unit 60 generates a sound as a wake-up stimulus. For example, an alarm clock or an alarm function installed in a smartphone may be used as the sound generating unit 60. The sound generating unit 60 is controlled based on a control signal output by the control unit 33.

[0023] <Sleep explanation> FIG. 4 is a diagram showing an example of changes in a person's sleep state from when they start sleeping until they wake up. The vertical axis represents sleep depth and body movement, and the horizontal axis represents sleep time. Sleep depth is a classification of the depth of non-REM sleep into four stages from "1" to "4." The height of the vertical line representing body movement indicates the magnitude of the body movement. A tall vertical line indicates a large body movement.

[0024] As shown in Figure 4, from when a person starts sleeping until they wake up, they move to deeper sleep depths 1, 2, 3, and 4, and then move to sleep depths 3, 2, 1, and REM sleep. This sleep cycle is usually repeated about every 90 minutes. The sleep time from when a person starts sleeping until they wake up can be divided into a deep sleep section, which is the first half of the period when they sleep relatively deeply, and a light sleep section, which is the second half of the period when they sleep relatively lightly. In the first half of sleep, the sleep is deep, so the person is relatively insensitive to external stimuli such as air currents and temperature and humidity. In contrast, in the second half of sleep, the sleep becomes lighter, and the person rarely reaches sleep depths 3 and 4, and is more likely to respond to external stimuli.

[0025] <Explanation of sleep state S> As shown in Figure 4, sleep depth is classified into six stages: "awake state," "REM sleep," "sleep depth 1," "sleep depth 2," "sleep depth 3," and "sleep depth 4." Therefore, the index that classifies the user's sleep depth is defined as "sleep state S." For example, if the user is in a light and awake state, sleep state S is "awake state," and if the user is in the deepest state of sleep, sleep state S is "sleep depth 4."

[0026] Generally, the deeper the sleep, the less the body movement, the slower the pulse rate, and the shallower the breathing. Therefore, the sleep state S can be estimated by acquiring the body movement information, pulse rate information, and breathing information of the user by the biosensor 11. The sleep state S is estimated using the bioinformation acquired by the biosensor 11. In this case, the biosensor 11 is, for example, a Doppler sensor. The body movement information, pulse rate information, and breathing information of the user can be acquired by the micromotion data of the user acquired by the Doppler sensor using microwaves.

[0027] As described above, there is a correlation between the user's body movements and the sleep state S. Therefore, by acquiring the user's body movement information, information on the sleep state, such as the sleep depth and sleep cycle, can be estimated and the sleep state S can be quantified.

[0028] The biosensor 11 of the first embodiment is not limited to a Doppler sensor, and may be, for example, a surface temperature sensor. The temperature distribution data acquired by the surface temperature sensor can identify the user's position, and the user's body movement information can be acquired by comparing the time-series temperature distribution data.

[0029] Other means of the biosensor 11 may include, for example, an acceleration sensor, a visible light camera, or an infrared camera. The biosensor 11 may be provided in, for example, the air conditioner 40, or may be provided in a device separate from the air conditioner 40. Furthermore, the biosensor 11 may be used by being in contact with the body of the user.

[0030] <Explanation about Awakening Level A> When the sleep state S is "awake" or "REM sleep", it is close to the wakeful state, and the index that quantifies the wakeful state is defined as "wakefulness A". In other words, the lighter the sleep and the more wakeful the state, the higher the wakefulness A, and the deeper the sleep and the closer it is to REM sleep, the lower the wakefulness A. When the sleep state S is "awake" or "REM sleep", the wakefulness A is quantified.

[0031] In general, the deeper the sleep (the lower the alertness level A), the less the body movement, the slower the pulse rate, and the shallower the breathing. Therefore, the alertness level A can be calculated by acquiring the body movement information, pulse rate information, and breathing information of the user by the biosensor 11. The alertness level A is calculated using the bioinformation acquired by the biosensor 11. In this case, the biosensor 11 is, for example, a Doppler sensor. The body movement information, pulse rate information, and breathing information of the user can be acquired from the micromotion data of the user acquired by the Doppler sensor using microwaves.

[0032] As described above, there is a correlation between the user's body movements and the level of alertness A. Therefore, by acquiring information about the user's body movements, it is possible to estimate information about the sleep state, such as the depth of sleep and the sleep cycle, and to quantify the level of alertness A.

[0033] The biosensor 11 of the first embodiment is not limited to a Doppler sensor, and may be, for example, a surface temperature sensor. The temperature distribution data acquired by the surface temperature sensor can identify the user's position, and the user's body movement information can be acquired by comparing the time-series temperature distribution data.

[0034] Other means of the biosensor 11 may include, for example, an acceleration sensor, a visible light camera, or an infrared camera. The biosensor 11 may be provided in, for example, the air conditioner 40, or may be provided in a device separate from the air conditioner 40. Furthermore, the biosensor 11 may be used by being in contact with the body of the user.

[0035] <Explanation about Comfort Level C> An index that quantifies a user's preferences is defined as "comfort level C." In other words, when the user feels comfortable, the comfort level C is high, and when the user feels uncomfortable, the comfort level C is low. The biosensor 11 acquires pulse information and pulse variability information of the user, and the comfort level C can be calculated based on the acquired bioinformation. The comfort level C is calculated using the bioinformation acquired by the biosensor 11.

[0036] The biosensor 11 used to calculate the comfort level C is, for example, a Doppler sensor. The user's pulse information can be obtained from the micromotion data of the user acquired by the Doppler sensor using microwaves. In addition, the time series data of the acquired pulse information can be used to acquire the user's pulse variability information. Since the user's pulse and pulse variability are correlated with the comfort level C, acquiring the user's pulse information and pulse variability information can estimate information regarding the user's comfort and quantify the comfort level C.

[0037] The biosensor 11 in the present embodiment 1 is not limited to a Doppler sensor, and may be, for example, a pulse sensor or a heart rate sensor. The biosensor 11 may be provided in the air conditioner 40, or may be provided in a device separate from the air conditioner 40. Furthermore, the biosensor 11 may be used by being in contact with the body of the user.

[0038] <Explanation about control information OP> The control information OP for outputting a control signal from the control unit 33 will be described. Note that, here, a case will be described in which the stimulus generating device 5 includes an air conditioner 40, a light generating unit 50, and a sound generating unit 60. The control information OP in the present embodiment 1 includes information on the planned wake-up time Tw, the operation start time Ts, the type of awakening stimulus (hereinafter: "stimulus type"), the intensity of the awakening stimulus (hereinafter: "stimulus intensity"), and the order of the awakening stimuli (hereinafter: "stimulus order").

[0039] The scheduled wake-up time Tw and the operation start time Ts are determined based on the information acquired by the acquisition unit 10 as described above. In the period from the operation start time Ts to the scheduled wake-up time Tw (hereinafter referred to as the "control period Tp"), if the user's wake-up level A is lower than the wake-up level threshold Aw, the wake-up control WC is started.

[0040] The type of stimulation is selected from among the air conditioner 40, the light generating unit 50, and the sound generating unit 60 to be operated.

[0041] The stimulus intensity is a quantification of the intensity of the air speed of the airflow generated by indoor unit 41 and the temperature of bedroom 200 in the case of air conditioner 40, the luminous flux and illuminance of the light generated by light generating unit 51 in the case of light generating unit 50, and the volume and type of sound generated by sound generating unit 61 in the case of sound generating unit 60.

[0042] The stimulation order is the order in which the air conditioner 40, the light generating unit 50, and the sound generating unit 60 are operated.

[0043] Based on the information on the sleep state S, alertness A, and comfort level C calculated by the calculation unit 31, the control unit 33 calculates control information OP that makes it easy for the user's alertness A to increase and makes it difficult for the comfort level C to decrease, and outputs a control signal.

[0044] In the first embodiment, when the sleep state S of the user is lower than the threshold (close to an awake state) during the control period Tp, the control unit 33 uses the calculated control information OP to control the stimulus generation device 5.

[0045] <Description of Control Flow in the First Embodiment> The operation of the wake-up support system 1 in the present embodiment 1 will be described with reference to Fig. 5 and Fig. 6. Fig. 5 is a flowchart showing the operation of the wake-up support system 1. Fig. 6 is a graph showing the relationship between the stimulation intensity and the awakening level A in the wake-up support system 1.

[0046] In step S100 , the control unit 33 calculates control information OP based on the scheduled wake-up time Tw and the operation start time Ts acquired by the acquisition unit 10 , and the comfort level A and comfort level C calculated by the calculation unit 31 .

[0047] In step S102, if the time reaches the operation start time Ts, the process proceeds to step S104. If the time does not reach the operation start time Ts, step S102 is not executed.

[0048] Step S104 determines whether A ≤ Aw as the relationship between the arousal level A calculated by the calculation unit 31 and the arousal threshold Aw. If A ≤ Aw, the process proceeds to Step S106. If A > Aw, Step S104 is not executed.

[0049] Step S106 starts the wake-up control WC. The wake-up control WC to be executed is based on the control information OP calculated in Step S100. At this time, in the example of FIG. 6, the time has reached the operation start time Ts, and the wind speed of the air flow generated by the indoor unit 41 is increased.

[0050] Step S108 determines whether ΔA < A0 as the relationship between the arousal level increase rate ΔA and the arousal level increase rate threshold A0. Here, the arousal level increase rate ΔA is calculated as the change amount of the arousal level A per unit time. If ΔA < A0, it is determined that the arousal level A has not increased sufficiently, and the process proceeds to Step S110. If ΔA ≥ A0, it is determined that the arousal level A has increased sufficiently, and the process proceeds to Step S112.

[0051] Since it is determined in Step S108 that ΔA < A0, Step S110 changes the control information OP so as to increase the stimulation intensity or the type of stimulation, and gives an arousal stimulus to the user. Increasing the stimulation intensity includes, for example, controlling the air conditioner 40 to lower the indoor temperature of the bedroom 200 (time T1 in FIG. 6), or increasing the wind speed of the air flow generated from the indoor unit 41 (time T2 in FIG. 6). Increasing the type of stimulation includes, for example, adding the light generation unit 50 as an arousal stimulus when the wake-up scheduled time Tw approaches and it is necessary to further increase the arousal level A (time T3 in FIG. 6). If A < Aw even when the wake-up scheduled time Tw is reached, the sound generation unit 60 is added as an arousal stimulus (time Tw in FIG. 6). In the example of FIG. 6, an example of operating in the order of "air conditioner 40, light generation unit 50, sound generation unit 60" as the arousal stimulus is described, but the operating order is not limited to this.

[0052] Step S112 determines whether C < Cw as the relationship between the comfort level C and the comfort threshold Cw. If C < Cw, it is determined that the comfort level C has not reached the comfort threshold Cw, and the process proceeds to step S114. If C ≥ Cw, it is determined that the comfort level C has reached the comfort threshold Cw, and the process proceeds to step S116.

[0053] Since it is determined in step S112 that C < Cw, step S114 changes the control information OP to reduce the stimulation intensity or the type of stimulation, and gives a wake-up stimulus to the user. Reducing the stimulation intensity controls the air conditioner 40, for example, to reduce the wind speed of the air flow generated from the indoor unit 41. Reducing the type of stimulation stops the operation of any one or more of the air conditioner 40, the light generation unit 50, and the sound generation unit 60 when they are operating as wake-up stimuli.

[0054] Step S116 determines whether A > Aw as the relationship between the wakefulness level A and the wakefulness threshold Aw. If A > Aw, it is determined that the wakefulness level A has reached the wakefulness threshold Aw, and the process proceeds to step S118 to end the wake-up control WC. If A ≤ Aw, it is determined that the wakefulness level A has not reached the wakefulness threshold Aw, and the process proceeds to step S108.

[0055] Step S118 ends the wake-up control WC.

[0056] <Effects of Embodiment 1> In Embodiment 1, the biological information of the user is acquired to calculate the sleep state S, the wakefulness level A, and the comfort level C. Based on this information, appropriate control information OP is calculated to control the wake-up stimuli (for example, the air conditioner 40, the light generation unit 50, and the sound generation unit 60) for waking up the user. The sensitivity to wake-up stimuli varies from person to person, and some users may feel the wake-up stimuli unpleasant. However, in Embodiment 1, since the control information OP can be calculated so that the comfort level C does not fall below the comfort threshold Cw, the wake-up stimuli can be controlled to give the wake-up stimuli to the user without making the user feel unpleasant and wake up the user.

[0057] Embodiment 2 The following describes in detail the wake-up assistance system 1 according to the present embodiment 2. The functional block diagram is the same as that shown in FIG.

[0058] The control unit 33 according to the second embodiment prohibits execution of the wake-up control WC with the same control content as the control information OP used in the previous wake-up control WC until a predetermined period Td has elapsed since the start of the wake-up control WC. That is, the control information OP is changed every day, and the wake-up control WC is not executed based on the same control information OP for two or more days until the predetermined period Td has elapsed.

[0059] The predetermined period Td may be set by the user or may be set in advance.

[0060] The control information OP in the second embodiment includes information on a scheduled wake-up time Tw, an action start time Ts, a type of stimulation, a stimulation intensity, and a stimulation order.

[0061] <Description of Control Flow in the Second Embodiment> FIG. 7 is a flowchart showing the operation of the wake-up assistance system 1 according to the second embodiment.

[0062] In step S300, the control unit 33 calculates control information OP based on the scheduled wake-up time Tw and the operation start time Ts acquired by the acquisition unit 10, and the comfort level A and comfort level C calculated by the calculation unit 31.

[0063] In step S302, if the time reaches the operation start time Ts, the process proceeds to step S304. If the time has not reached the operation start time Ts, step S302 is not executed.

[0064] In step S304, it is determined whether or not the relationship between the awakening level A calculated by the calculation unit 31 and the awakening level threshold value Aw is A≦Aw. If A≦Aw, the process proceeds to step S306. If A≦Aw is not true, step S304 is not executed.

[0065] Step S306 determines whether the control information OP calculated in step S300 is the same as the control information OP executed during a predetermined period Td. If the same control information OP is executed, the process proceeds to step S308. If different control information OP is used, step S308 is not executed and the process proceeds to step S310.

[0066] Step S308 calculates the control information OP that has not been executed during the predetermined period Td.

[0067] Step S310 starts the wake-up control WC. The wake-up control WC to be executed is based on either the control information OP calculated in step S300 or the control information OP calculated in step S308.

[0068] Step S312 determines whether ΔA < A0 as the relationship between the arousal rate increase ΔA and the arousal rate increase threshold A0. If ΔA < A0, it is determined that the arousal level A has not increased sufficiently, and the process proceeds to step S314. If ΔA ≥ A0, it is determined that the arousal level A has increased sufficiently, and the process proceeds to step S316.

[0069] Since it is determined in step S312 that ΔA < A0, step S314 changes the control information OP to increase the stimulation intensity or the type of stimulation, and gives an arousal stimulus to the user.

[0070] Step S316 determines whether C < Cw as the relationship between the comfort level C and the comfort level threshold Cw. If C < Cw, it is determined that the comfort level C has not reached the comfort level threshold Cw, and the process proceeds to step S318. If C ≥ Cw, it is determined that the comfort level C has reached the comfort level threshold Cw, and the process proceeds to step S320.

[0071] Since it is determined in step S316 that C < Cw, step S318 changes the control information OP to reduce the stimulation intensity or the type of stimulation, and gives an arousal stimulus to the user.

[0072] In step S320, it is determined whether the relationship between the awakening level A and the awakening level threshold Aw is A>Aw. If A>Aw, it is determined that the awakening level A has reached the awakening level threshold Aw, and the process proceeds to step S322 to end the wake-up control WC. If A>Aw is not true, it is determined that the awakening level A has not reached the awakening level threshold Aw, and the process proceeds to step S312.

[0073] In step S322, the wake-up control WC ends.

[0074] <Effects of the Second Embodiment> In the second embodiment, since the wake-up control WC is not executed using the same control information OP in the predetermined period Td, the awakening stimulus can be given to the user by different control information OP for each day. This prevents the user from becoming accustomed to the awakening stimulus and becoming less likely to wake up, and effectively increases the awakening level A of the user, waking him / her up.

[0075] Embodiment 3 The wake-up assistance system 1 according to the third embodiment will be described in detail below.

[0076] 8 is a functional block diagram of the wake-up assistance system 1 according to the embodiment 3. Compared to the embodiment 1, an evaluation information acquisition means 14 and a control method information acquisition means 15 are added to the acquisition unit 10 of the control device 2. Note that both the evaluation information acquisition means 14 and the control method information acquisition means 15 may be included, or only one of them may be included.

[0077] The evaluation information acquisition means 14 acquires evaluation information by a user inputting the evaluation information. The evaluation information is the state of awakening and discomfort that the user subjectively feels, which is manually input by the user himself / herself. The evaluation information to be input may be, for example, a numerical value input into an input field, or may be input in text using a chatbot or the like. In addition, as the evaluation information acquisition means 14, for example, the user may input the evaluation information into a smartphone, or may input the evaluation information by operating a remote control of the air conditioner 40. The evaluation information acquired by the evaluation information acquisition means 14 is input to the control unit 33 to calculate the control information OP.

[0078] The control method information acquisition means 15 acquires control method information by the user inputting the control method information. The control method information refers to a pattern of wake-up control WC based on a combination of a stimulus type, a stimulus intensity, and a stimulus order. That is, the user manually inputs the control method information desired by the user into the control method information acquisition means 15. The input control method information may be, for example, a selective input of a stimulus type, a stimulus intensity, and a stimulus order. In addition, as a means for inputting the control method information, for example, the user may input the control method information into a smartphone, or may input the control method information by operating a remote control of the air conditioner 40. The control method information acquired by the control method information acquisition means 15 is input to the control unit 33 to calculate the control information OP.

[0079] <Operation of the Third Embodiment> Fig. 9 is a flowchart showing the operation of the wake-up assistance system 1 according to the embodiment 3. The flowchart in Fig. 9 shows the operation in the case where the acquisition unit 10 has both the evaluation information acquisition means 14 and the control method information acquisition means 15.

[0080] In step S400, the control unit 33 calculates control information OP based on the scheduled wake-up time Tw, operation start time Ts, evaluation information, control method information acquired by the acquisition unit 10, and the comfort level A and comfort level C calculated by the calculation unit 31.

[0081] If the time reaches the operation start time Ts, step S402 proceeds to step S404. If the time has not reached the operation start time Ts, step S402 is not executed.

[0082] Step S404 determines whether A ≤ Aw as the relationship between the wakefulness A calculated by the calculation unit 31 and the wakefulness threshold Aw. If A ≤ Aw, step S404 proceeds to step S406. If A > Aw, step S404 is not executed.

[0083] Step S406 starts the wake-up control WC. The wake-up control WC to be executed is based on the control information OP calculated in step S400.

[0084] Step S408 determines whether ΔA < A0 as the relationship between the wakefulness increase rate ΔA and the wakefulness increase rate threshold A0. If ΔA < A0, it is determined that the wakefulness A has not increased sufficiently, and step S408 proceeds to step S410. If ΔA ≥ A0, it is determined that the wakefulness A has increased sufficiently, and step S408 proceeds to step S412.

[0085] Since it is determined in step S410 that ΔA < A0, the control information OP is changed to increase the stimulation intensity or the type of stimulation, and a wake-up stimulus is given to the user.

[0086] Step S412 determines whether C < Cw as the relationship between the comfort level C and the comfort level threshold Cw. If C < Cw, it is determined that the comfort level C has not reached the comfort level threshold Cw, and step S412 proceeds to step S414. If C ≥ Cw, it is determined that the comfort level C has reached the comfort level threshold Cw, and step S412 proceeds to step S416.

[0087] Since it is determined in step S414 that C < Cw, the control information OP is changed to reduce the stimulation intensity or the type of stimulation, and a wake-up stimulus is given to the user.

[0088] In step S416, it is determined whether the relationship between the awakening level A and the awakening level threshold Aw is A>Aw. If A>Aw, it is determined that the awakening level A has reached the awakening level threshold Aw, and the process proceeds to step S418 to end the wake-up control WC. If A>Aw is not true, it is determined that the awakening level A has not reached the awakening level threshold Aw, and the process proceeds to step S408.

[0089] In step S418, the wake-up control WC ends.

[0090] In step S420, the user inputs evaluation information to the evaluation information acquiring means 14, and inputs the control method information to the control method information acquiring means 15. The evaluation information input by the user to the evaluation information acquiring means 14 may be a qualitative input of the wakefulness state that the user himself / herself subjectively feels, or may be a quantitative input of the wakefulness level A and comfort level C that the user himself / herself subjectively feels.

[0091] <Advantages of the Third Embodiment> In the third embodiment, the user himself / herself can specify the evaluation information of the wakefulness state and the desired control method information. By using the evaluation information and control method information input by the user in addition to the information of the estimated wakefulness level A and comfort level C, it is possible to calculate the control information OP suitable for the user when the next wake-up control WC is executed.

[0092] Embodiment 4 The wake-up assistance system 1 according to the fourth embodiment will be described in detail below.

[0093] 10 is a functional block diagram of a wake-up assistance system 1 according to the fourth embodiment. A display device 70 is added to the configuration of the first embodiment. The display device 70 has at least one of an awakening level display unit 71, a comfort level display unit 72, and a control information display unit 73.

[0094] The awakening level display unit 71 displays the awakening level A calculated by the calculation unit 31, allowing the user to visually recognize the data of the awakening level A. The data of the awakening level A may be quantified and displayed quantitatively, or may be displayed qualitatively in text. In addition, as a display means for the awakening level A, for example, it may be displayed on a smartphone or a display, or it may be displayed on the operation screen of the remote control of the air conditioner 40.

[0095] The comfort level display unit 72 displays the comfort level C calculated by the calculation unit 31, allowing the user to visually confirm the data of the comfort level C. The data of the comfort level C may be quantified and displayed quantitatively, or may be displayed qualitatively in text. Furthermore, as a means for displaying the comfort level C, for example, it may be displayed on a smartphone or display, or it may be displayed on the operation screen of the remote control of the air conditioner 40.

[0096] The control information display unit 73 makes it possible to visually confirm the data of the control method information described in the third embodiment. The data of the control method information may be digitized and displayed quantitatively, or may be displayed qualitatively in text. Furthermore, as a means for displaying the control method information, for example, it may be displayed on a smartphone or a display, or it may be displayed on the operation screen of the remote control of the air conditioner 40.

[0097] <Advantages of the Fourth Embodiment> In the fourth embodiment, the calculation results of the awakening level A and the comfort level C, or the control method information can be presented to the user. This allows the user to objectively grasp his / her own awakening level and comfort. In addition, the user can use the grasped results of the awakening level A and the comfort level C as reference information and specify appropriate control method information by himself / herself.

[0098] Embodiment 5. The wake-up assistance system 1 according to the fifth embodiment will be described in detail below with reference to a flowchart. The functional block diagram is as shown in FIG.

[0099] <Description of Control Flow in the Fifth Embodiment> The operation of the wake-up support system 1 in the fifth embodiment will be described with reference to FIG. 11. FIG. 11 is a flowchart showing the operation of the wake-up support system 1 according to the fifth embodiment.

[0100] In step S500, control information OP is calculated based on the scheduled wake-up time Tw acquired by the acquisition unit 10, the operation start time Ts, the comfort level A calculated by the calculation unit 31, and the comfort level C.

[0101] In step S502, when the time reaches the operation start time Ts, the process proceeds to step S504. If the time has not reached the operation start time Ts, step S502 is not executed.

[0102] In step S504, it is determined whether A ≤ Aw as the relationship between the arousal level A calculated by the calculation unit 31 and the arousal threshold Aw. If A ≤ Aw, the process proceeds to step S506. If A > Aw, step S504 is not executed.

[0103] In step S506, wake-up control WC is started. The wake-up control WC to be executed is based on the control information OP calculated in step S500.

[0104] In step S508, it is determined whether ΔA < A0 as the relationship between the arousal level increase rate ΔA and the arousal level increase rate threshold A0. If ΔA < A0, it is determined that the arousal level A has not increased sufficiently, and the process proceeds to step S510. If ΔA ≥ A0, it is determined that the arousal level A has increased sufficiently, and the process proceeds to step S512.

[0105] In step S510, since it is determined in step S508 that ΔA < A0, the control information OP is changed so as to increase the stimulation intensity or increase the stimulation type, and an arousal stimulus is given to the user.

[0106] Step S512 determines whether C < Cw as the relationship between the comfort level C and the comfort threshold Cw. If C < Cw, it is determined that the comfort level C has not reached the comfort threshold Cw, and the process proceeds to step S514. If C ≥ Cw, it is determined that the comfort level C has reached the comfort threshold Cw, and the process proceeds to step S516.

[0107] Since it is determined in step S512 that C < Cw, the air conditioner 40 is controlled to reduce the wind speed of the airflow generated from the indoor unit 41, or the air conditioner 40 is stopped.

[0108] Step S516 determines whether A > Aw as the relationship between the arousal level A and the arousal threshold Aw. If A > Aw, it is determined that the arousal level A has reached the arousal threshold Aw, and the process proceeds to step S518 to end the wake-up control WC. If A ≤ Aw, it is determined that the arousal level A has not reached the arousal threshold Aw, and the process proceeds to step S508.

[0109] Step S518 ends the wake-up control WC.

[0110] <Effect of Embodiment 5> In Embodiment 5, when the comfort level C of the user is lower than the comfort threshold Cw, the air conditioner 40 is controlled to weaken the wind speed of the airflow generated from the indoor unit 41, or the air conditioner 40 is stopped. Since the airflow of the indoor unit 41 is an arousal stimulus with high responsiveness, the comfort level C of the user can be efficiently improved by weakening the airflow.

[0111] Embodiment 6. Hereinafter, the wake-up support system 1 according to Embodiment 6 will be described in detail based on the flowchart. The functional block diagram is the same as that shown in FIG. 2 and is the same as in Embodiment 1.

[0112] <Explanation of the Control Flow in Embodiment 6> The operation of the waking-up support system 1 in the sixth embodiment will be described with reference to FIG. 12. FIG. 12 is a flowchart showing the operation of the waking-up support system 1 according to the sixth embodiment.

[0113] In step S600, it is determined whether the scheduled waking-up time Tw is earlier than normal. If the scheduled waking-up time Tw is earlier than normal, the process proceeds to step S602. If it is not determined that the scheduled waking-up time Tw is earlier than normal, the process proceeds to step S604.

[0114] In step S602, control information OP with a higher stimulation intensity than normal is calculated.

[0115] In step S604, control information OP with a stimulation intensity equivalent to normal is calculated.

[0116] In step S606, when the time reaches the operation start time Ts, the process proceeds to step S608. If the time has not reached the operation start time Ts, step S606 is not executed.

[0117] In step S608, it is determined whether A ≤ Aw as the relationship between the wakefulness A calculated by the calculation unit 31 and the wakefulness threshold Aw. If A ≤ Aw, the process proceeds to step S610. If A > Aw, step S608 is not executed.

[0118] In step S610, waking-up control WC is started. The waking-up control WC to be executed is based on the control information OP calculated in step S602 or step S604.

[0119] In step S612, it is determined whether ΔA < A0 as the relationship between the wakefulness increase rate ΔA and the wakefulness increase rate threshold A0. If ΔA < A0, it is determined that the wakefulness A has not increased sufficiently, and the process proceeds to step S614. If ΔA ≥ A0, it is determined that the wakefulness A has increased sufficiently, and the process proceeds to step S616.

[0120] Since it is determined in step S612 that ΔA < A0, control information OP is changed to increase the stimulation intensity or the type of stimulation, and an awakening stimulus is given to the user.

[0121] In step S616, it is determined whether C < Cw as the relationship between the comfort level C and the comfort threshold Cw. If C < Cw, it is determined that the comfort level C has not reached the comfort threshold Cw, and the process proceeds to step S618. If C ≥ Cw, it is determined that the comfort level C has reached the comfort threshold Cw, and the process proceeds to step S620.

[0122] Since it is determined in step S616 that C < Cw, control information OP is changed to reduce the stimulation intensity or the type of stimulation, and an awakening stimulus is given to the user.

[0123] In step S620, it is determined whether A > Aw as the relationship between the arousal level A and the arousal threshold Aw. If A > Aw, it is determined that the arousal level A has reached the arousal threshold Aw, and the process proceeds to step S622 to end the wake-up control WC. If A ≤ Aw, it is determined that the arousal level A has not reached the arousal threshold Aw, and the process proceeds to step S612.

[0124] Step S622 ends the wake-up control WC.

[0125] <Effect of the Sixth Embodiment> In the sixth embodiment, when the wake-up scheduled time Tw is earlier than normal, an awakening stimulus can be given to the user using control information OP with a stimulation intensity higher than normal. Thereby, even when it is difficult to wake up because the wake-up scheduled time Tw is earlier than normal, the user can be effectively awakened.

[0126] Embodiment 7. Hereinafter, the wake-up support system 1 according to the seventh embodiment will be described in detail with reference to the drawings.

[0127] 13 is a functional block diagram of the wake-up support system 1 according to the seventh embodiment. The wake-up support system 1 has a number of people information acquisition means 18 in the acquisition unit 10. The other configurations are the same as those of the wake-up support system 1 according to the first embodiment.

[0128] The number of people information acquisition means 18 detects people inside the bedroom 200 and acquires the number of people inside the bedroom 200. As a means for detecting people, for example, a human presence sensor may be used to acquire the number of people. Alternatively, an infrared sensor may be used to acquire a thermal image of the interior of the bedroom 200 and the number of people may be acquired based on the thermal image data. The acquired data on the number of people is input to the control unit 33 and used to calculate the control information OP.

[0129] <Description of Control Flow in the Seventh Embodiment> The operation of the wake-up support system 1 in the seventh embodiment will be described with reference to Fig. 14. Fig. 14 is a flowchart showing the operation of the wake-up support system 1 according to the seventh embodiment.

[0130] In step S700, the control information OP is calculated based on the scheduled wake-up time Tw and the operation start time Ts acquired by the acquisition unit 10, and the comfort level A and the comfort level C calculated by the calculation unit 31.

[0131] In step S702, if the time reaches the operation start time Ts, the process proceeds to step S704. If the time has not reached the operation start time Ts, step S702 is not executed.

[0132] In step S704, it is determined whether or not the relationship between the awakening level A calculated by the calculation unit 31 and the awakening level threshold value Aw is A≦Aw. If A≦Aw, the process proceeds to step S706. If A≦Aw is not true, step S704 is not executed.

[0133] In step S706, it is determined whether or not two or more people are present in the bedroom 200. If two or more people are present, the process proceeds to step S708. If two or more people are not present, the process proceeds to step S710.

[0134] In step S708, the control unit 33 calculates control information OP for operating only the air conditioner 40.

[0135] Step S710 starts the waking control WC. The waking control WC to be executed is based on the control information OP calculated in step S700 or step S708.

[0136] In step S712, it is determined whether ΔA < A0 as the relationship between the arousal level increase rate ΔA and the arousal level increase rate threshold A0. If ΔA < A0, it is determined that the arousal level A has not increased sufficiently, and the process proceeds to step S714. If ΔA ≥ A0, it is determined that the arousal level A has increased sufficiently, and the process proceeds to step S716.

[0137] Since it is determined in step S712 that ΔA < A0, in step S714, the control information OP is changed so as to increase the stimulation intensity or increase the stimulation type, and an arousal stimulus is given to the user.

[0138] In step S716, it is determined whether C < Cw as the relationship between the comfort level C and the comfort level threshold Cw. If C < Cw, it is determined that the comfort level C has not reached the comfort level threshold Cw, and the process proceeds to step S718. If C ≥ Cw, it is determined that the comfort level C has reached the comfort level threshold Cw, and the process proceeds to step S720.

[0139] Since it is determined in step S716 that C < Cw, in step S718, the control information OP is changed so as to reduce the stimulation intensity or reduce the stimulation type, and an arousal stimulus is given to the user.

[0140] In step S720, it is determined whether A > Aw as the relationship between the arousal level A and the arousal level threshold Aw. If A > Aw, it is determined that the arousal level A has reached the arousal level threshold Aw, and the process proceeds to step S722 to end the waking control WC. If A ≤ Aw, it is determined that the arousal level A has not reached the arousal level threshold Aw, and the process proceeds to step S712.

[0141] In step S722, the wake-up control WC ends.

[0142] <Effects of the Seventh Embodiment> In the seventh embodiment, when multiple people are present inside bedroom 200, the airflow generated from indoor unit 41 of air conditioner 40 is preferentially selected as the awakening stimulus. Compared to the light generated from light generating unit 51 and the sound generated from sound generating unit 61, the airflow generated from indoor unit 41 can provide an awakening stimulus to the user from a limited range. In other words, by selecting the airflow generated from indoor unit 41 as the awakening stimulus, the awakening stimulus can be provided only to the user to be awakened, without providing the awakening stimulus to people in the room other than the user to be awakened.

[0143] Embodiment 8 The wake-up assistance system 1 according to the eighth embodiment will be described in detail below with reference to the drawings.

[0144] 15 is a functional block diagram of the wake-up support system 1 according to the embodiment 8. The wake-up support system 1 has a weather information acquisition means 16 in the acquisition unit 10. The other configuration is the same as that of the wake-up support system 1 according to the embodiment 1.

[0145] The weather information acquisition means 16 acquires weather information. As the weather information, for example, the weather (sunny, cloudy, rainy, snowy), temperature, and humidity are acquired. As the weather information acquisition means, for example, weather forecast information may be acquired by a communication means, or the temperature and humidity may be measured and acquired. The acquired weather information is input to the control unit 33 and used for calculating the control information OP.

[0146] <Description of Control Flow in the Eighth Embodiment> The operation of the wake-up support system 1 in the eighth embodiment will be described with reference to Fig. 16. Fig. 16 is a flowchart showing the operation of the wake-up support system 1 according to the eighth embodiment.

[0147] Step S800 calculates control information OP based on the scheduled wake-up time Tw and the operation start time Ts acquired by the acquisition unit 10, the arousal level A and comfort level C calculated by the calculation unit 31, and the weather information acquired by the weather information acquisition means 16.

[0148] If the time reaches the operation start time Ts, step S800 proceeds to step S804. If the time has not reached the operation start time Ts, step S800 is not executed.

[0149] Step S804 determines whether A ≤ Aw based on the relationship between the arousal level A calculated by the calculation unit 31 and the arousal level threshold Aw. If A ≤ Aw, step S804 proceeds to step S806. If A > Aw, step S804 is not executed.

[0150] Step S806 starts the wake-up control WC. The wake-up control WC to be executed is based on the control information OP calculated in step S800.

[0151] Step S808 determines whether ΔA < A0 based on the relationship between the arousal level increase rate ΔA and the arousal level increase rate threshold A0. If ΔA < A0, it is determined that the arousal level A has not increased sufficiently, and step S808 proceeds to step S810. If ΔA ≥ A0, it is determined that the arousal level A has increased sufficiently, and step S808 proceeds to step S812.

[0152] Since it is determined in step S808 that ΔA < A0, step S810 changes the control information OP to increase the stimulation intensity or the type of stimulation, and gives an arousal stimulus to the user.

[0153] Step S812 determines whether C < Cw based on the relationship between the comfort level C and the comfort level threshold Cw. If C < Cw, it is determined that the comfort level C has not reached the comfort level threshold Cw, and step S812 proceeds to step S814. If C ≥ Cw, it is determined that the comfort level C has reached the comfort level threshold Cw, and step S812 proceeds to step S816.

[0154] Since it is determined in step S812 that C < Cw, control information OP is changed so as to reduce the stimulation intensity or the type of stimulation, and an awakening stimulus is given to the user.

[0155] Step S816 determines whether A > Aw as the relationship between the arousal level A and the arousal threshold Aw. If A > Aw, it is determined that the arousal level A has reached the arousal threshold Aw, and the process proceeds to step S818 to end the wake-up control WC. If A > Aw is not satisfied, it is determined that the arousal level A has not reached the arousal threshold Aw, and the process proceeds to step S808.

[0156] Step S818 ends the wake-up control WC.

[0157] <Effect of Embodiment 8 of the Present Invention> In Embodiment 8 of the present invention, appropriate control information OP can be calculated according to the weather. As a specific example, for example, when giving an awakening stimulus to a user who is not good at waking up on a rainy day, the intensity of the light generation unit 50 can be increased on a rainy day to give an awakening stimulus, thereby increasing the arousal level A of the user. In this way, by inputting the weather information acquired by the weather information acquisition means 16 into the control unit 33, appropriate control information OP can be calculated according to the weather information, and the stimulation generation device 5 can be controlled.

[0158] Embodiment 9. Hereinafter, the wake-up support system 1 according to Embodiment 9 of the present invention will be described in detail with reference to the drawings.

[0159] FIG. 17 is a functional block diagram of the wake-up support system 1 according to Embodiment 9 of the present invention. The wake-up support system 1 has curtain opening / closing information acquisition means 17 in the acquisition unit 10. Other configurations are the same as those of the wake-up support system 1 according to Embodiment 1.

[0160] The curtain opening / closing information acquisition means 17 determines whether the curtains installed on the windows of the bedroom 200 are open or not, and acquires the curtain opening / closing information. As the means for acquiring the curtain opening / closing information, for example, a proximity sensor may be used to determine the opening / closing state of the curtains. Alternatively, an infrared sensor may be used to acquire a thermal image of the curtains and the window to determine the opening / closing state of the curtains. In this case, the infrared sensor may be provided in the air conditioner 40, or may be provided separately from the air conditioner 40. The acquired curtain opening / closing information is input to the control unit 33 and used to calculate the control information OP.

[0161] <Description of Control Flow in the Ninth Embodiment> The operation of the wake-up support system 1 in the ninth embodiment will be described with reference to Fig. 18. Fig. 18 is a flowchart showing the operation of the wake-up support system 1 according to the ninth embodiment.

[0162] Step 900 calculates control information OP based on the planned wake-up time Tw and operation start time Ts acquired by the acquisition unit 10, the alertness level A and comfort level C calculated by the calculation unit 31, and the curtain opening / closing information acquired by the curtain opening / closing information acquisition means 17.

[0163] In step S902, if the time reaches the operation start time Ts, the process proceeds to step S904. If the time has not reached the operation start time Ts, step S902 is not executed.

[0164] In step S904, it is determined whether or not the relationship between the awakening level A calculated by the calculation unit 31 and the awakening level threshold value Aw is A≦Aw. If A≦Aw, the process proceeds to step S906. If A≦Aw is not true, step S904 is not executed.

[0165] In step S906, the wake-up control WC is started. The wake-up control WC to be executed is based on the control information OP calculated in step S900.

[0166] Step S908 determines whether ΔA < A0, where ΔA is the arousal rate increase and A0 is the arousal rate increase threshold. If ΔA < A0, it is determined that the arousal level A has not increased sufficiently, and the process proceeds to step S910. If ΔA ≥ A0, it is determined that the arousal level A has increased sufficiently, and the process proceeds to step S912.

[0167] Since it is determined in step S908 that ΔA < A0, step S910 changes the control information OP to increase the stimulation intensity or the type of stimulation, and gives an arousal stimulus to the user.

[0168] Step S912 determines whether C < Cw, where C is the comfort level and Cw is the comfort level threshold. If C < Cw, it is determined that the comfort level C has not reached the comfort level threshold Cw, and the process proceeds to step S914. If C ≥ Cw, it is determined that the comfort level C has reached the comfort level threshold Cw, and the process proceeds to step S916.

[0169] Since it is determined in step S912 that C < Cw, step S914 changes the control information OP to reduce the stimulation intensity or the type of stimulation, and gives an arousal stimulus to the user.

[0170] Step S916 determines whether A > Aw, where A is the arousal level and Aw is the arousal level threshold. If A > Aw, it is determined that the arousal level A has reached the arousal level threshold Aw, and the process proceeds to step S918 to end the wake-up control WC. If A ≤ Aw, it is determined that the arousal level A has not reached the arousal level threshold Aw, and the process proceeds to step S908.

[0171] Step S918 ends the wake-up control WC.

[0172] <Effects of the Ninth Embodiment> In the ninth embodiment, appropriate control information OP can be calculated in accordance with the curtain opening / closing information. As a specific example, when providing an awakening stimulus to a user who has difficulty waking up in a dark environment with the curtains closed in the bedroom 200, the intensity of the light generating unit 50 can be increased to provide the awakening stimulus when the curtains are closed, thereby increasing the awakening level A of the user. In this way, by inputting the curtain opening / closing information acquired by the curtain opening / closing information acquiring means 17 to the control unit 33, appropriate control information OP can be calculated in accordance with the curtain opening / closing information, and the stimulus generating device 5 can be controlled.

[0173] Embodiment 10 The learning device 100 and the inference device 110 according to the tenth embodiment will be described in detail below with reference to the drawings.

[0174] <Configuration of the learning device (learning phase)> 19 is a configuration diagram of a learning device 100 according to the present embodiment 10. The learning device 100 includes a learning data acquiring unit 101, a model generating unit 102, and a trained model storage unit 105.

[0175] The learning data acquiring unit 101 acquires the awakening level A calculated by the calculating unit 31, the comfort level C calculated by the calculating unit 31, and the control information OP calculated by the control unit 33 as learning data.

[0176] The model generation unit 102 learns the control information OP based on learning data created based on a combination of the awakening level A, comfort level C, and control information OP output from the learning data acquisition unit 101. That is, a learned model is generated that infers optimal control information OP from the awakening level A and comfort level C of the wake-up assistance system 1. Here, the learning data is data in which the awakening level A, comfort level C, and control information OP are associated with each other.

[0177] The learning device 100 and the inference device 110 are used to learn the control information OP of the wake-up assistance system 1, but may be devices connected to the wake-up assistance system 1 via a network and separate from the wake-up assistance system 1. The learning device 100 and the inference device 110 may be built into the wake-up assistance system 1. Furthermore, the learning device 100 and the inference device 110 may exist on a cloud server.

[0178] The learning algorithm used by the model generation unit 102 may be a known algorithm such as supervised learning, unsupervised learning, reinforcement learning, etc. As an example, a case where a neural network is applied will be described.

[0179] The model generation unit 102 learns the control information OP by so-called supervised learning, for example, according to a neural network model. Here, supervised learning refers to a method of providing a set of input and result (label) data to the learning device 100, learning features of the learning data, and inferring the result from the input.

[0180] A neural network is composed of an input layer consisting of multiple neurons, an intermediate layer (hidden layer) consisting of multiple neurons, and an output layer consisting of multiple neurons. The intermediate layer may be one layer, or two or more layers.

[0181] For example, in a three-layered neural network as shown in Figure 20, when multiple inputs are input to the input layer (X1-X3), the values ​​are multiplied by weight W1 (w11-w16) and input to the intermediate layer (Y1-Y2), and the result is further multiplied by weight W2 (w21-w26) and output from the output layer (Z1-Z3). This output result changes depending on the values ​​of weights W1 and W2.

[0182] In this embodiment 10, the neural network learns the control information OP by so-called supervised learning according to learning data created based on a combination of the alertness level A, comfort level C, and control information OP acquired by the learning data acquisition unit 101.

[0183] That is, the neural network learns by inputting the alertness level A and the comfort level C to the input layer and adjusting the weights W1 and W2 so that the results output from the output layer approach the control information OP.

[0184] The model generation unit 102 executes the above-described learning to generate and output a trained model.

[0185] The trained model storage unit 105 stores the trained model output from the model generation unit 102.

[0186] Next, the learning process of the learning device 100 will be described with reference to Fig. 21. Fig. 21 is a flowchart showing the learning process of the learning device 100.

[0187] In step S1000, the learning data acquisition unit 101 acquires the awakening level A, the comfort level C, and the control information OP. Note that, although the awakening level A, the comfort level C, and the control information OP are acquired simultaneously, it is sufficient if the awakening level A, the comfort level C, and the control information OP are input in association with each other, and the data on the awakening level A, the comfort level C, and the control information OP may be acquired at different times.

[0188] In step S1002, the model generation unit 102 learns the control information OP by so-called supervised learning in accordance with learning data created based on a combination of the alertness level A, the comfort level C, and the control information OP acquired by the learning data acquisition unit 101, and generates a learned model.

[0189] In step S1004, the trained model storage unit 105 stores the trained model generated by the model generation unit 102.

[0190] <Construction of inference device (utilization phase)> 22 is a configuration diagram of an inference device 110 according to the present embodiment 10. The inference device 110 includes a data acquisition unit 111 and an inference unit 112.

[0191] The data acquiring unit 111 acquires the awakening level A calculated by the calculating unit 31 and the comfort level C calculated by the calculating unit 31.

[0192] The inference unit 112 infers the control information OP obtained by using the trained model. That is, by inputting the awakening level A and the comfort level C acquired by the data acquisition unit 111 to this trained model, the inference unit 112 can output the control information OP inferred from the awakening level A and the comfort level C.

[0193] In this embodiment 10, the control information OP is output using a trained model trained by the model generation unit 102 of the wake-up assistance system 1. However, it is also possible to obtain a trained model from an external source, such as another wake-up assistance system 1, and output the control information OP based on this trained model.

[0194] Next, the process for obtaining the control information OP using the inference device 110 will be described with reference to FIG.

[0195] In step S1100, the data acquiring unit 111 acquires the awakening level A and the comfort level C.

[0196] In step S1102, the inference unit 112 inputs the awakening level A and the comfort level C to the learned model stored in the learned model storage unit 105, and obtains control information OP.

[0197] In step S1104, the inference unit 112 outputs the control information OP obtained from the trained model to the wake-up assistance system 1.

[0198] In step S1106, the wake-up support system 1 uses the output control information OP to instruct and control the stimulus generation device 5. This makes it possible to provide the user with an appropriate awakening stimulus according to the awakening level A and comfort level C of the user.

[0199] In the tenth embodiment, the case where supervised learning is applied to the learning algorithm used by the model generating unit 102 has been described, but the present invention is not limited to this. As for the learning algorithm, reinforcement learning, unsupervised learning, semi-supervised learning, or the like can also be applied in addition to supervised learning.

[0200] The model generation unit 102 may learn the control information OP according to learning data created for multiple wake-up support systems 1. The model generation unit 102 may acquire learning data from multiple wake-up support systems 1 used in the same area, or may learn the control information OP using learning data collected from multiple wake-up support systems 1 operating independently in different areas. It is also possible to add or remove a wake-up support system 1 that collects learning data from the target midway. Furthermore, the learning device 100 that has learned the control information OP for a certain wake-up support system 1 may be applied to another wake-up support system 1, and the control information OP for the other wake-up support system 1 may be re-learned and updated.

[0201] In addition, the learning algorithm used in the model generation unit 102 may be deep learning, which learns to extract the features themselves, or machine learning may be performed according to other known methods, such as genetic programming, functional logic programming, and support vector machines.

[0202] <Advantages of the Tenth Embodiment> In the tenth embodiment, by learning the relationship between the user's awakening level A, comfort level C, and control information OP, it is possible to provide the user with an awakening stimulus suited to the user. [Explanation of symbols]

[0203] 1 Wake-up assistance system, 2 Control device, 5 Stimulus generation device, 10 Acquisition unit, 11 Biometric sensor, 12 Scheduled wake-up time acquisition means, 13 Operation start time acquisition means, 14 Evaluation information acquisition means, 15 Control method information acquisition means, 16 Weather information acquisition means, 17 Curtain opening / closing information acquisition means, 18 Number of people information acquisition means, 31 Calculation unit, 33 Control unit, 40 Air conditioner, 41 Indoor unit, 44 Room temperature sensor, 50 Light generation unit, 60 Sound generation unit, 70 Display device, 71 Arousal level display unit, 72 Comfort level display unit, 73 Operation information display unit, 100 Learning device, 101 Learning data acquisition unit, 102 Model generation unit, 105 Learned model storage unit, 110 Inference device, 111 Data acquisition unit, 112 Inference unit, 200 bedroom, 210 bedding, Ts operation start time, Tw scheduled wake-up time, Tp control period, S sleep state, A alertness, Aw alertness threshold, ΔA alertness rise rate, A0 alertness rise rate threshold, C comfort level, Cw comfort level threshold, OP control information, WC wake-up control, Td predetermined period

Claims

1. an acquisition unit that acquires first biometric information of a user and second biometric information different from the first biometric information; a calculation unit that calculates a wakefulness level, which is calculated based on first biological information of the user and is an index indicating a wakefulness level of the user, and a comfort level, which is calculated based on second biological information of the user and is an index indicating a comfort level of the user; A control unit that performs wake-up control, which is control that prompts the user to wake up, based on control information including the wakefulness level and the comfort level. Control device.

2. The control unit increases the level of awakening when the level of awakening is lower than a threshold level of awakening that is a threshold level of the level of awakening for the user to wake up from sleep. The control device according to claim 1 .

3. The control unit increases the comfort level when the comfort level is lower than a comfort level threshold value that is a threshold value of the comfort level specified by the user. The control device according to claim 1 .

4. The first biological information acquired by the acquisition unit includes body movement information of the user. The control device according to claim 1 .

5. The first biological information acquired by the acquisition unit includes respiratory information of the user. The control device according to claim 1 .

6. The first biological information acquired by the acquisition unit includes pulse information of the user. The control device according to claim 1 .

7. The second biological information acquired by the acquisition unit includes pulse information of the user. The control device according to claim 1 .

8. The second biological information acquired by the acquisition unit includes pulse variability information of the user. The control device according to claim 1 .

9. The acquisition unit further acquires an operation start time for starting the wake-up control, the control information includes the operation start time, The control unit starts the wake-up control when the time reaches the operation start time. The control device according to any one of claims 1 to 8.

10. The control unit prohibits execution of a control that is the same as the wake-up control until a predetermined period has elapsed since starting the wake-up control. The control device according to any one of claims 1 to 8.

11. The acquisition unit further acquires subjective evaluation information of the user, the control information includes the evaluation information, The control unit performs the wake-up control based on the control information. The control device according to any one of claims 1 to 8.

12. The acquisition unit further acquires control method information desired by the user, The control information includes the control method information, The control unit performs the wake-up control based on the control information. The control device according to any one of claims 1 to 8.

13. The acquisition unit further acquires control method information desired by the user, The control information includes the control method information, The control unit performs the wake-up control based on the control information. The control device according to claim 11.

14. The acquisition unit further acquires weather information, the control information includes the weather information, The control unit performs the wake-up control based on the control information. The control device according to any one of claims 1 to 8.

15. The acquisition unit further acquires curtain opening / closing information, the control information includes opening / closing information of the curtain, The control unit performs the wake-up control based on the control information. The control device according to any one of claims 1 to 8.

16. The acquisition unit further acquires a planned wake-up time of the user, the control information includes the scheduled wake-up time, The control unit performs the wake-up control such that the wake-up level at the scheduled wake-up time is equal to or higher than the wake-up level threshold. The control device according to claim 2.

17. The wakefulness threshold is set when the user's sleep state is one of REM sleep and wakefulness. The control device according to claim 2.

18. A control device according to any one of claims 1 to 2 or claims 4 to 8; A stimulus generating device that provides a stimulus to the user to encourage them to wake up. Wake-up assistance system.

19. The control device according to claim 3 ; A stimulus generating device that provides a stimulus to the user to encourage them to wake up. Wake-up assistance system.

20. The device further includes a display device having at least one of an awakening level display unit for displaying the awakening level and a comfort level display unit for displaying the comfort level. The wake-up assistance system according to claim 18.

21. The device further includes a display device having at least one of an awakening level display unit for displaying the awakening level and a comfort level display unit for displaying the comfort level. The wake-up assistance system according to claim 19.

22. The stimulus generating device has at least one of an air conditioner that generates an air flow, a light generating unit that generates light, and a sound generating unit that generates sound. The wake-up assistance system according to claim 18.

23. The stimulus generating device has at least one of an air conditioner that generates an air flow, a light generating unit that generates light, and a sound generating unit that generates sound. The wake-up assistance system according to claim 19.

24. The control unit controls the stimulus generation device to reduce intensity or stop operation when the comfort level is equal to or lower than the comfort level threshold. The wake-up assistance system according to claim 19.

25. The control unit performs control to reduce the wind speed of the airflow generated by the air conditioner or to stop the operation when the comfort level is equal to or lower than the comfort level threshold value. The wake-up assistance system according to claim 19.

26. The stimulus generating device has at least one air conditioner that generates an air flow, The acquisition unit further acquires information on the number of people in the room, The control information includes the number of people information, The control unit operates only the air conditioner when there are two or more occupants. The wake-up assistance system according to claim 18.

27. The control unit controls at least one of the type of operation of the stimulus generation device, the sequence of operation of the stimulus generation device, and the intensity of the stimulus generated by the stimulus generation device. The wake-up assistance system according to claim 18.

28. a wakefulness level that is calculated based on the first biological information of the user and is an index indicating a wakefulness level of the user; a comfort level that is calculated based on second biometric information of the user that is different from the first biometric information and is an index indicating a degree of comfort of the user; and a learning data acquisition unit that acquires learning data including an operating condition for controlling to prompt the user to wake up; A model generation unit that generates a trained model for inferring the operating condition based on the awakening level and the comfort level using the learning data. Learning device.

29. a wakefulness level that is calculated based on the first biological information of the user and is an index indicating a wakefulness level of the user; a data acquisition unit that acquires a comfort level, the comfort level being an index indicating a degree of comfort of the user, the comfort level being calculated based on second biometric information of the user different from the first biometric information; and an inference unit that uses a trained model for inferring an operating condition for controlling to prompt the user to wake up from the awakening level and the comfort level, and outputs the operating condition from the awakening level and the comfort level acquired by the data acquisition unit. Reasoning device.

Images