Sleep management system and sleep management method

Abstract

A sleep management system according to one embodiment of the present disclosure may comprise: a plurality of sensors (5) including at least one voice sensor (51) and at least one non-voice sensor (52) that collect data of a user; a hub device (1) that receives voice data collected by the at least one voice sensor (51) and non-voice data collected by the at least one non-voice sensor (52), obtains first processed data on the basis of processing of the voice data, and obtains second processed data on the basis of processing of the non-voice data; a user device (2) that receives the first processed data and the second processed data from the hub device (1) via wireless communication, inputs the first processed data into a first machine learning model (21) to obtain cough information of the user, and calculates a first parameter (P1) representing a correlation between the first processed data and the second processed data; a server device (3) that receives the cough information from the user device (2) via wireless communication and controls at least one home appliance (4) registered in conjunction with the user device (2) on the basis of the cough information.

Description

Sleep management system and sleep management method

[0001] The disclosed invention relates to a sleep management system and a sleep management method.

[0002] As the number of people suffering from frequent coughing increases following COVID-19, cases of sleep quality being reduced due to coughing during sleep are occurring frequently.

[0003] Sleep is essential to human health and well-being, playing a variety of roles, including helping the body recover, forming new memories, maintaining concentration, and clearing away accumulated brain waste.

[0004] Maintaining good quality sleep is very important for a healthy and smooth life.

[0005] To maintain quality sleep, demand for polysomnography, a test that detects sleep-related conditions and disorders, is growing. However, current sleep monitoring technology focuses on measuring sleep stages, sleep duration, and assessing sleep disorders such as apnea and snoring, leaving a lack of measurement and assessment of sleep-related coughing.

[0006] The disclosed invention provides a sleep management system and a sleep management method that provide a user with information about coughing during sleep by analyzing and processing data collected from various sensors.

[0007] A sleep management system according to one embodiment of the present disclosure comprises: a plurality of sensors (5) including at least one voice sensor (51) and at least one non-voice sensor (52) for collecting user data; a hub device (1) for receiving voice data collected by the at least one voice sensor (51) and non-voice data collected by the at least one non-voice sensor (52), obtaining first processed data based on processing the voice data, and obtaining second processed data based on processing the non-voice data; a user device (2) for receiving the first processed data and the second processed data from the hub device (1) via wireless communication, inputting the first processed data into a first machine learning model (21) to obtain cough information of the user, and calculating a first parameter (P1) representing a correlation between the first processed data and the second processed data; And it may include a sleep management system including a server device (3) that receives the cough information from the user device (2) through wireless communication and controls at least one home appliance (4) registered in conjunction with the user device (2) based on the cough information.

[0008] A sleep management method according to one embodiment of the present disclosure comprises: a hub device (1) receiving voice data collected by a voice sensor (51) and non-voice data collected by a non-voice sensor (52); the hub device (1) obtaining first processed data based on processing the voice data and obtaining second processed data based on processing the non-voice data; the hub device (1) transmitting the first processed data and the second processed data to a user device (2) via wireless communication; the user device (2) inputting the first processed data received from the hub device (1) into a first machine learning model (21) to obtain cough information of the user; the user device (2) calculating a first parameter (P1) indicating a correlation between the first processed data and the second processed data; the sub device (3) receiving the cough information from the user device (2); And the sub-device (3) may include controlling at least one home appliance (4) registered in conjunction with the user device (2) based on the cough information.

[0009] According to one aspect of the disclosed invention, a person's sleep state can be accurately measured in daily life without attaching various sensors to the body.

[0010] According to one aspect of the disclosed invention, since analysis of a person's sleep state is performed at a user device, invasion of an individual's privacy can be prevented.

[0011] According to one aspect of the disclosed invention, since data processing is performed by a plurality of devices, the level of data processing load that each device must bear can be reduced.

[0012] According to one aspect of the disclosed invention, convenience in health management can be provided by providing the user with various information about coughing occurring during sleep.

[0013] According to one aspect of the disclosed invention, a user's disease can be diagnosed or prevented early by warning the user if a disease is suspected based on a coughing sound that the user makes while sleeping.

[0014] According to one aspect of the disclosed invention, even if the voice sensor stops collecting voice data due to privacy invasion, cough information can be provided to the user based on non-voice data, thereby preventing invasion of an individual's privacy.

[0015] According to one aspect of the disclosed invention, it is possible to induce a user to have good quality sleep.

[0016] The effects that can be obtained from the present disclosure are not limited to the effects mentioned above, and other effects that are not mentioned can be clearly understood by a person having ordinary skill in the art to which the present disclosure belongs from the description below.

[0017] FIG. 1 illustrates an example of a network of a sleep management system according to one embodiment.

[0018] FIG. 2 schematically illustrates an example of the structure of a sleep management system according to one embodiment.

[0019] FIG. 3 illustrates an example of a control block diagram of a sleep management system according to one embodiment.

[0020] FIGS. 4 and 5 illustrate examples of multiple sensors of a sleep management system according to one embodiment.

[0021] FIG. 6 illustrates an example of a flowchart of a sleep management method according to one embodiment.

[0022] FIG. 7 is a diagram illustrating a process for processing data collected from multiple sensors of a sleep management system according to one embodiment.

[0023] Figures 8, 9, 10, and 11 illustrate a flowchart of a sleep management method according to one embodiment.

[0024] FIG. 12 illustrates an example of sleep state information including cough information derived by a sleep management system according to one embodiment.

[0025] Figure 13 is a drawing illustrating an example of a predetermined operation performed by a home appliance to relieve a user's cough.

[0026] Figure 14 is a drawing illustrating an example of a predetermined action performed by a smart bed to relieve a user's cough.

[0027] Figure 15 is a drawing illustrating an example of a predetermined action performed by a smart pillow to relieve a user's cough.

[0028] It should be understood that the various embodiments and terms used in this document are not intended to limit the technical features described in this document to specific embodiments, but rather to include various modifications, equivalents, or substitutes of the embodiments.

[0029] In connection with the description of the drawings, similar reference numerals may be used for similar or related components.

[0030] The singular form of a noun corresponding to an item may include one or more of said items, unless the relevant context clearly indicates otherwise.

[0031] In this document, each of the phrases "A or B", "at least one of A and B", "at least one of A or B", "A, B, or C", "at least one of A, B, and C", and "at least one of A, B, or C" may include any one of the items listed together in that phrase, or all possible combinations thereof.

[0032] The term “and / or” includes any combination of a plurality of related described elements or any one of a plurality of related described elements.

[0033] For example, a phrase such as "A, B, and / or C" may include any one of the items listed in that phrase, or all possible combinations of them.

[0034] Terms such as "first," "second," or "first" or "second" may be used simply to distinguish one component from another and do not qualify the components in any other respect (e.g., importance or order).

[0035] When a component (e.g., a first component) is referred to as being "coupled" or "connected" to another component (e.g., a second component), with or without the terms "functionally" or "communicatively," it means that the component can be connected to the other component directly (e.g., wired), wirelessly, or through a third component.

[0036] The terms “include” or “have” are intended to specify the presence of a feature, number, step, operation, component, part or combination thereof described in this document, but do not preclude the presence or addition of one or more other features, numbers, steps, operations, components, parts or combinations thereof.

[0037] When a component is said to be “connected,” “coupled,” “supported,” or “in contact with” another component, this includes not only cases where the components are directly connected, coupled, supported, or in contact, but also cases where the components are indirectly connected, coupled, supported, or in contact through a third component.

[0038] When we say that a component is "on" another component, this includes not only cases where the component is in contact with the other component, but also cases where there is another component between the two components.

[0039] Below, a sleep management system according to various embodiments is specifically described with reference to the attached drawings.

[0040] FIG. 1 illustrates an example of a network of a sleep management system according to one embodiment.

[0041] Referring to FIG. 1, a sleep management system according to one embodiment may include a hub device (1), a user device (2), a server device (3), and / or a home appliance (4).

[0042] The hub device (1) may include a communication module capable of communicating with a user device (2), a server device (3), and / or a home appliance (4), at least one processor for processing data, and at least one memory storing a program for controlling the operation of the hub device (1).

[0043] The hub device (1) can obtain processed data based on processing data collected from multiple sensors. In one embodiment, the hub device (1) can process data collected from multiple sensors using a machine learning model.

[0044] In one embodiment, the hub device (1) can transmit processing data to the user device (2). For example, the hub device (1) can transmit processing data to the user device (2) through direct communication without going through the server device (3).

[0045] The home appliance (4) may include various types of electronic products. For example, the home appliance (4) may include at least one of an air conditioner (41), a humidifier (42), a dehumidifier (43), an air purifier (44), a furniture control device included in a smart bed (45), and a furniture control device included in a smart pillow (46). The aforementioned home appliances are merely examples, and therefore, in addition to the aforementioned home appliances, various types of electronic products such as displays, lighting devices, automatic curtain opening / closing devices, and speakers may also be included in the home appliance (4).

[0046] The home appliance (4) can be remotely controlled by the server device (3).

[0047] The furniture control device included in a smart bed (45) or smart pillow (46) may include an air cell, an actuator, and / or a vibration element capable of transmitting vibrations to a user lying or sitting on the furniture by changing the structure of the furniture, which may change the user's posture. For example, the furniture control device included in a smart bed (45), a recliner chair, and / or a recliner sofa with a recliner function may include an actuator capable of controlling the reclining angle.

[0048] The lighting device may include a light source whose light intensity and / or color is controllable.

[0049] The automatic curtain opening device may include an actuator for automatically opening or closing the curtain.

[0050] The server device (3) may include a communication module capable of communicating with the hub device (1), the user device (2), and / or the home appliance (4).

[0051] The server device (3) may include at least one processor capable of processing data received from the hub device (1), the user device (2), and / or the home appliance (4), and at least one memory capable of storing a program for processing the data or the processed data. The server device (3) may be implemented as various computing devices such as a workstation, a cloud, a data drive, a data station, etc. The server device (3) may be implemented as one or more servers that are physically or logically separated based on functions, detailed configurations of functions, or data, and may transmit and receive data through communication between each server and process the transmitted and received data.

[0052] The server device (3) can store and / or manage user accounts, register hub devices (1), user devices (2), and / or home appliances (4) by linking them to user accounts, and perform functions of managing or controlling the registered hub devices (1) and home appliances (4). For example, a user can access the server device (3) through the user device (2) and create a user account. The user account can be identified by an ID and password set by the user. The user can access the server device (3) through the user device (2) and manage the user account. The server device (3) can register hub devices (1), user devices (2), and / or home appliances (4) to the user account according to a set procedure. For example, the server device (3) can link identification information (e.g., serial number or MAC address, etc.) of the hub device (1) to the user account, thereby registering, managing, and controlling the hub device (1). Likewise, the server device (3) can register and control the user device (2) and home appliance (4) to the user account.

[0053] The server device (3) can receive various information from the hub device (1), user device (2), and / or home appliance (4) registered to the user account.

[0054] For example, the server device (3) may include a first server and a second server. The first server may create and / or manage user account information, and register and / or manage information of the hub device (1), the user device (2), and / or the home appliance (4) in the user account information. The second server may receive registration information of the user device (2) and the home appliance (4) from the first server, and control the user device (2) and / or the home appliance (4).

[0055] As another example, the second server may perform the management function of the hub device (1) and home appliance (4) registered in the first server on behalf of the first server.

[0056] The number of server devices (3) is not limited thereto, and the server devices (3) may include multiple servers for performing the same operation and / or different operations.

[0057] The user device (2) may include a communication module capable of communicating with a hub device (1), a server device (3), and / or a home appliance (4). The user device (2) may include a user interface for receiving user input or outputting information to the user. The user device (2) may include at least one processor for controlling the operation of the user device (2) and at least one memory for storing a program for controlling the operation of the user device (2).

[0058] The user device (2) may be carried by the user or placed in the user's home or office, etc. The user device (2) may include, but is not limited to, a personal computer, a terminal, a mobile phone, a smart phone, a handheld device, a wearable device, a display device, etc.

[0059] The memory of the user device (2) may store a program, i.e., an application, that can process data received from the hub device (1). The application may be sold installed on the user device (2) or downloaded and installed from an external server.

[0060] A user can access a server device (3) by executing an application installed on a user device (2), create a user account, and perform communication with the server device (3) based on the logged-in user account to register a hub device (1) and / or a home appliance (4).

[0061] For example, if the home appliance (4) is operated so that it can be connected to the server device (3) according to the procedure guided by the application installed on the user device (2), the server device (3) can register the home appliance (4) to the user account by registering the identification information (e.g., serial number or MAC address) of the home appliance (4) to the corresponding user account, thereby registering the home appliance (4). The home appliance (4) can also be registered to the user account in the same manner. It goes without saying that the information required to register a device such as a home appliance (4), home appliance (4), etc. to a user account may include other information that can identify the device in addition to the serial number or MAC address of the device.

[0062] The user device (2) can receive various information from the server device (3) or from the hub device (1) or home appliance (4) registered directly to the user account.

[0063] A network can include both wired and wireless networks. Wired networks include cable networks or telephone networks, while wireless networks can include any network that transmits and receives signals via radio waves. Wired and wireless networks can be interconnected.

[0064] A network may include a wide area network (WAN) such as the Internet, a local area network (LAN) formed around an access point (AP), and a short-range wireless network that does not use an access point (AP). Short-range wireless networks may include, but are not limited to, Bluetooth (IEEE 802.15.1), Zigbee (IEEE 802.15.4), Wi-Fi Direct, Near Field Communication (NFC), Z-Wave, etc.

[0065] An access point (AP) can connect a hub device (1), a user device (2), and / or a home appliance (4) to a wide area network (WAN) to which a server device (3) is connected. The hub device (1), the user device (2), and / or the home appliance (4) can be connected to the server device (3) via the wide area network (WAN).

[0066] The access point (AP) communicates with a hub device (1), a user device (2), and / or a home appliance (4) using wireless communication such as Wi-Fi (IEEE 802.11), Bluetooth (IEEE 802.15.1), or Zigbee (IEEE 802.15.4), and can connect to a wide area network (WAN) using wired communication, but the wireless communication method of the access point (AP) is not limited to this.

[0067] In one embodiment, the hub device (1) can communicate with the user device (2) via a short-range wireless network that does not go through an access point (AP).

[0068] For example, the hub device (1) may be connected to the user device (2) via a short-range wireless network (e.g., Wi-Fi Direct, Bluetooth, NFC). As another example, the hub device (1) may be connected to the user device (2) via a wide area network (WAN) using a long-range wireless network (e.g., a cellular communication module).

[0069]

[0070] FIG. 2 schematically illustrates an example of the structure of a sleep management system according to one embodiment.

[0071] FIG. 3 illustrates an example of a control block diagram of a sleep management system according to one embodiment.

[0072] Referring to FIGS. 2 and 3, the hub device (1) can receive data collected from a plurality of sensors (5).

[0073] The plurality of sensors (5) may include sensors for collecting user data. Some of the plurality of sensors (5) may be included in a smart sensor device. The smart sensor device may include a smartphone, a smart watch (6), a smart ring, etc. included in the user device (2).

[0074] Each of the plurality of sensors (5) can collect user data and transmit the collected user data to the hub device (1).

[0075] In one embodiment, the user's data may include data related to the user's sleep.

[0076] Data related to the user's sleep may include pressure data for measuring pressure changes corresponding to changes in the user's posture, displacement data corresponding to body displacement that changes according to the user's breathing, oxygen saturation data corresponding to the user's oxygen saturation, electrocardiogram data corresponding to the user's electrocardiogram, acceleration data corresponding to acceleration that changes according to the user's movement, and / or eye-movement data corresponding to the movement of the user's eyes.

[0077] The plurality of sensors (5) may include at least one voice sensor (51) for collecting user voice data and at least one non-voice sensor (52) for collecting user non-voice data.

[0078] At least one non-voice sensor (52) may include a pressure sensor (52a) for collecting pressure data for measuring pressure changes corresponding to changes in the user's posture, a UWB sensor (52b) for measuring displacement data corresponding to displacement of the body that changes according to the user's breathing, a radar sensor (52c) for collecting eye-movement data corresponding to movements of the user's eyes, an acceleration sensor (52d) for collecting acceleration data corresponding to acceleration that changes according to movements of the user, an oxygen saturation sensor for collecting oxygen saturation data corresponding to oxygen saturation of the user, and / or an electrocardiogram sensor for collecting electrocardiogram data corresponding to the user's electrocardiogram.

[0079] Data collected from multiple sensors (5) can be transmitted to the hub device (1).

[0080] In one embodiment, data collected by at least one sensor among a plurality of sensors (5) can be transmitted to the hub device (1) via wired communication, and data collected by the remaining sensors can be transmitted to the hub device (1) via wireless communication.

[0081] Accordingly, the hub device (1) can be connected to at least one of the plurality of sensors (5) by wire and connected to the remaining sensors wirelessly.

[0082] In one embodiment, data collected from multiple sensors (5) can be transmitted to a hub device (1) via wired communication.

[0083] In one embodiment, the hub device (1) may include at least one processor (110) storing a program for processing data collected from a plurality of sensors (5), and at least one processor (110) capable of processing data collected from a plurality of sensors (5) based on the program stored in the at least one processor (120).

[0084] At least one processor (120) can store a machine learning model for processing data collected from multiple sensors (5).

[0085] In one embodiment, the machine learning model may be a machine learning model for feature extraction that extracts features of data when data collected from a plurality of sensors (5) is input, and outputs processed data including the extracted features.

[0086] Features of data may include elements that a machine learning model extracts from the data to perform classification or prediction.

[0087] In one embodiment, the machine learning model may be a machine learning model for determining sleep stages, which outputs processed data including data on the user's sleep stage when data collected from a plurality of sensors (5) is input.

[0088] At least one processor (110) can obtain first processing data based on processing voice data collected from a voice sensor (51).

[0089] The first processed data may include feature data extracted from the voice data and / or data on sleep stages extracted from the voice data. The capacity of the first processed data may be smaller than that of the first data.

[0090] At least one processor (110) can obtain second processed data based on processing non-voice data collected from a non-voice sensor (52).

[0091] The second processed data may include feature data extracted from the non-voice data and / or data regarding sleep stages extracted from the non-voice data. The size of the second processed data may be smaller than that of the non-voice data.

[0092] According to the present disclosure, by first processing data in a hub device (1) and then transmitting it to a user device (2), the amount of data processing that the user device (2) must bear can be reduced.

[0093] The hub device (1) may include a communication unit (130) including a wired communication module for performing wired communication with a plurality of sensors (5), and / or a wireless communication module for performing wireless communication with a user device (2), a server device (3), and / or a home appliance.

[0094] The hub device (1) may include a printed circuit board including at least one processor (110), at least one processor (120), and a communication unit (130). At least some of the plurality of sensors (5) may be connected to the printed circuit board by wires.

[0095] The hub device (1) may include a housing covering a printed circuit board.

[0096] The hub device (1) is likely to be installed in a location where user operation is difficult. Accordingly, in one embodiment, the hub device (1) may not include a user interface device (input / output device).

[0097] In order to prepare for the case where the hub device (1) is installed in a place where the user can easily operate it, in one embodiment, the hub device (1) may include a user interface device (input / output device).

[0098] In one embodiment, a user can operate a user interface device provided on the hub device (1) to connect the hub device (1) to an access point (AP).

[0099] In one embodiment, a user can activate the communication unit (130) of the hub device (1) by operating a user interface device provided on the hub device (1).

[0100] In one embodiment, a user can turn on the power of the hub device (1) by operating a user interface device provided on the hub device (1).

[0101] At least one processor (110) can control multiple sensors (5).

[0102] For example, at least one processor (110) can control at least one wired sensor among a plurality of sensors (5).

[0103] At least one processor (110) can wake up at least one wired sensor among a plurality of sensors (5) based on the satisfaction of a sensor wake-up condition.

[0104] Waking up a sensor may include activating the sensor.

[0105] At least one processor (110) may switch at least one wired sensor among the plurality of sensors (5) to a standby state based on the satisfaction of a sensor standby condition. Switching the sensor to a standby state may include deactivating the sensor or operating it in a low-power mode.

[0106] The user device (2) can receive data acquired by the hub device (1) from the hub device (1) via wireless communication.

[0107] The data acquired by the hub device (1) may include processed data obtained by processing data collected from a plurality of sensors (5).

[0108] In one embodiment, the user device (2) may include at least one memory (220) storing a program for processing data received from the hub device (1), and at least one processor (210) capable of processing data received from the hub device (1) based on the program stored in the at least one memory (220).

[0109] At least one memory (220) can store a machine learning model for processing data received from the hub device (1).

[0110] At least one memory (220) can store a sleep management application that can be downloaded from an external server. The sleep-related application can be a downloadable app, and at least some of the sleep-related application can be temporarily stored or temporarily created on a device-readable storage medium, such as a memory of a manufacturer's server, an application store server, or a relay server.

[0111] A sleep management application may include a machine learning model. The machine learning model included in the sleep management application may be updated by an external server.

[0112] In one embodiment, the user device (2) may include a communication unit (230) including at least one communication module for establishing communication with a smart sensor device including at least some of a hub device (1), a server device (3), a home appliance (4), and / or a plurality of sensors (5).

[0113] The user device (2) can receive processing data from the hub device (1) through the communication unit (230).

[0114] In one embodiment, at least one processor (210) may establish communication between the communication unit (130) of the hub device (1) and the communication unit (230) of the user device (2) in response to the communication unit (230) (e.g., a short-range wireless communication module) being activated.

[0115] In one embodiment, at least one processor (210) can control the user interface (240) to provide feedback requesting activation of the communication unit (230) in response to the sleep management application being executed while the communication unit (230) (e.g., a short-range wireless communication module) is not activated.

[0116] At least one processor (210) can wirelessly receive data from the hub device (1) via a communication unit (230) (e.g., a short-range wireless communication module).

[0117] At least one processor (210) can process data received from the hub device (1) using a machine learning model stored in at least one memory (220).

[0118] Data received from the hub device (1) may include first processing data and / or second processing data.

[0119] At least one processor (210) can input first processing data and / or second processing data into a machine learning model stored in at least one memory (220) to obtain sleep state information related to the user's sleep state.

[0120] Sleep state information related to the user's sleep state may include at least one of information about the user's coughing during sleep, information about the user's sleep stage, information about the user's stress index, or information about the user's sleep disorder.

[0121] The machine learning model stored in at least one memory (220) may be a machine learning model for determining a user's sleep state, which outputs sleep state information related to the user's sleep state when first processing data and / or second processing data are input.

[0122] At least one processor (210) can input first processing data and / or second processing data into a machine learning model and store the acquired sleep state information in at least one memory (220).

[0123] In one embodiment, at least one processor (210) may generate sleep summary information based on sleep state information accumulated and stored in at least one memory (220). At least one processor (210) may control a user interface (240) to output sensory information corresponding to the sleep summary information based on a predetermined condition being satisfied (e.g., receiving a user input for confirming the sleep summary information).

[0124] At least one processor (210) can control the communication unit (230) to transmit the acquired sleep state information by inputting the first processing data and / or the second processing data into the machine learning model to the server device (3).

[0125] The communication unit (230) may include a first communication module for establishing communication with the hub device (1) and a second communication module for establishing communication with the server device (3). Accordingly, the communication unit (230) may perform communication with the hub device (1) via the first communication method while simultaneously performing communication with the server device (3) via the second communication method.

[0126] According to one embodiment of the present disclosure, data collected from a plurality of sensors (5) is primarily processed by a hub device (1) and secondarily processed by a user device (2), and then sleep state information is obtained, and the sleep state information can be transmitted to a server device (3) in real time.

[0127] According to one embodiment of the present disclosure, data collected from a plurality of sensors (5) related to the user's private life may not be directly transmitted to the server device (3).

[0128] The user device (2) may include a user interface (240) for communication with the user.

[0129] According to various embodiments, it is also possible for the hub device (1) to primarily process data collected from multiple sensors (5), and then secondarily process the primarily processed data to obtain sleep state information.

[0130] According to various embodiments, it is also possible for the hub device (1) to primarily process data collected from a plurality of sensors (5), transmit the primarily processed data to a server, and then acquire sleep state information after the server secondarily processes the primarily processed data.

[0131] According to various embodiments, it is also possible for the hub device (1) to transmit data collected from a plurality of sensors (5) to the user device (2), the user device (2) to primarily process the data received from the hub device (1), and to secondarily process the primarily processed data and then obtain sleep state information.

[0132] According to various embodiments, it is also possible for the hub device (1) to transmit data collected from a plurality of sensors (5) to the server device (3), the server device (3) to primarily process the data received from the hub device (1), and to secondarily process the primarily processed data and then obtain sleep state information.

[0133] The user interface (240) can obtain user input. The user interface (240) can provide various information regarding the operation of the user device (2). The user interface (240) can include an input interface and an output interface.

[0134] The input interface can convert sensory information received from the user into electrical signals. The electrical signals can correspond to user input. The user input can include various commands. The input interface can transmit electrical signals (voltage or current) corresponding to the user input to at least one processor (210).

[0135] The input interface may include various input devices capable of converting tactile information into electrical signals. For example, the input interface may be provided as a physical button or a touchscreen. The input interface may also include a microphone capable of converting auditory information into electrical signals.

[0136] The input interface can receive user input to run a sleep management application.

[0137] The output interface can output information related to the operation of the user device (2). The output interface can display information input by the user or information provided to the user on various screens. The output interface can display information related to the operation of the user device (2) in the form of at least an image or text. For example, the output interface can output the interface of a sleep management application. In addition, the output interface can display a graphical user interface (GUI) that enables control of the user device (2). That is, the output interface can display a user interface element (UI element), such as an icon.

[0138] The output interface can output an interface corresponding to a sleep management application.

[0139] For example, the output interface may include a liquid crystal display panel (LCD Panel), a light emitting diode panel (LED Panel), an organic light emitting diode panel (OLED Panel), or a micro LED panel. The output interface may include a touch display that also functions as an input device.

[0140] The output interface and input interface may be provided as separate devices or as a single device (e.g., a touch display).

[0141] The server device (3) can receive data acquired by the user device (2) from the user device (2) via wireless communication.

[0142] The data acquired by the user device (2) may include the sleep state information described above.

[0143] In one embodiment, the server device (3) may include at least one memory (320) storing a program for processing sleep state information received from the user device (2), and at least one processor (310) capable of processing sleep state information received from the user device (2) based on the program stored in the at least one memory (320).

[0144] At least one memory (320) can store sleep state information received from the user device (2).

[0145] At least one memory (320) can store a program for generating sleep summary information based on sleep state information received from the user device (2).

[0146] At least one processor (310) can generate sleep summary information based on sleep state information accumulated and stored in at least one memory (320).

[0147] At least one memory (320) can store a program for controlling a home appliance (4) based on sleep state information received from a user device (2).

[0148] At least one processor (310) can control the home appliance (4) based on sleep state information received from the user device (2).

[0149] According to various embodiments, a program for generating sleep summary information based on sleep state information and a program for controlling a home appliance (4) based on sleep state information may be stored on different servers.

[0150] For example, a first server included in the server device (3) can store a program for generating sleep summary information based on sleep state information, and a second server included in the server device (3) can store a program for controlling a home appliance (4) based on sleep state information.

[0151] At least one memory (320) can store sleep summary information generated based on sleep state information.

[0152] In one embodiment, the server device (3) may include a communication unit (330) including at least one communication module for establishing communication with a smart sensor device including at least some of a hub device (1), a user device (2), a home appliance (4), and / or a plurality of sensors (5).

[0153] The server device (3) can receive sleep status information from the user device (2) through the communication unit (330).

[0154] The server device (3) can transmit a control command to the home appliance (4) through the communication unit (330).

[0155] The server device (3) can transmit sleep summary information to the user device (2) through the communication unit (330).

[0156] According to one embodiment of the present disclosure, the user's sleep can be managed in various ways as the server device (3) performs various operations based on sleep state information.

[0157] FIGS. 4 and 5 illustrate examples of multiple sensors of a sleep management system according to one embodiment.

[0158] Referring to FIGS. 4 and 5, in one embodiment, at least one voice sensor (51) among a plurality of sensors (5) may be installed in furniture (10). Additionally, at least one voice sensor (51) may be provided in a smart sensor device such as a smart watch (6).

[0159] In one embodiment, at least one non-audio sensor (52) of the plurality of sensors (5) may be installed on the furniture (10). The at least one non-audio sensor (52) may include a pressure sensor (52a), a UWB sensor (52b), a radar sensor (52c), and / or an acceleration sensor (52d).

[0160] At least some of the plurality of sensors (5) may be provided on furniture (10) on which a user can sit or lie.

[0161] Furniture (10) on which a user can sit or lie down may include, for example, a bed, a chair, and / or a sofa, but of course, any type of furniture on which a user can sit or lie down may be adopted as furniture (10) according to one embodiment without limitation.

[0162] In one embodiment, furniture (10), such as a bed, chair, and / or sofa, may include an actuator that can change the user's posture by changing its structure and / or a vibration element that can transmit vibration to the user.

[0163] The pressure sensor (52a) may include a piezoelectric element that generates an electrical signal corresponding to a displacement caused by pressure.

[0164] The pressure sensor (52a) can be installed at a location where it can measure the pressure generated by the user's body (e.g., whole body) depending on whether the user is lying down or sitting.

[0165] For example, if the furniture (10) corresponds to a bed, the pressure sensor (52a) may be installed on the mattress, which is the part where pressure is generated by the user's body. The mattress may have a flat polygonal or circular shape, and may include a cover that forms the exterior and has a receiving space, and a pad that is installed in the receiving space of the cover and on which the pressure sensor (52a) is placed. The mattress may be placed on the floor, a chair, a sofa, or a bed.

[0166] The mattress may further include springs and / or sponges. The springs and / or sponges may be provided in the accommodation space of the cover.

[0167] The structure (e.g., length, arrangement, etc.) of the pressure sensor (52a) may be changed depending on the size of the mattress.

[0168] As another example, if the furniture (10) corresponds to a chair, the pressure sensor (52a) may be provided in the seating part, backrest part, headrest, and / or leg part where pressure is generated by the user's body.

[0169] The seating portion may include a portion that the user's buttocks close, the backrest portion may include a portion that the user's back closes, the headrest may include a portion that the user's head closes, and the leg portion may include a portion that the user's legs close.

[0170] The location of the pressure sensor (52a) is not limited to the examples shown in FIGS. 4 and 5, and the first sensor (51) can be installed in various locations capable of measuring the pressure generated by the body of a user lying or sitting on the furniture (10).

[0171] The pressure sensor (52a) can measure the pressure generated by a user lying or sitting on the furniture (10). For example, the pressure sensor (52a) can measure the pressure distribution generated by a user lying or sitting on the furniture (10). The pressure sensor (52a) can obtain pressure data corresponding to the pressure generated by a user lying or sitting on the furniture (10).

[0172] The UWB sensor (52b) may include a UWB signal emitting unit that transmits an ultra-wideband signal (UWB signal) and a UWB signal receiving unit that receives a UWB signal reflected by the user's body.

[0173] The UWB sensor (52b) may have a detection area directed toward the body (e.g., torso) of a user lying or sitting on the furniture (10). The UWB sensor (52b) may have a detection area capable of detecting body displacement due to the user's breathing. The UWB sensor (52b) may be provided on a frame of the furniture (10) to have a detection area directed toward the body (e.g., torso) of the user, but the location of the UWB sensor (52b) is not limited thereto.

[0174] For example, the UWB sensor (52b) may have a detection area directed toward a part of the body of a user lying or sitting on furniture (10).

[0175] For example, if the furniture (10) corresponds to a bed, the UWB sensor (52b) may have a detection area directed toward the central area of ​​the bed.

[0176] As another example, if the furniture (10) corresponds to a chair, the UWB sensor (52b) may have a detection area facing the backrest of the chair.

[0177] The UWB sensor (52b) can transmit an ultra-wideband signal (UWB signal) toward the user's body and receive a UWB signal reflected from the user's body.

[0178] The UWB sensor (52b) can measure the displacement of the user's body based on the UWB signal reflected from the user's body. For example, the UWB sensor (52b) can measure the displacement of the user's body based on the time of flight (ToF; Time of Fight) of the UWB signal. As another example, the UWB sensor (52b) can measure the displacement of the user's body based on the change in the wavelength (and frequency) of the UWB signal by utilizing the Doppler effect.

[0179] That is, the UWB sensor (52b) can obtain displacement data corresponding to the displacement of the body that changes according to the user's breathing.

[0180] The radar sensor (52c) may include a radar sensor. The radar sensor (52c) may include a radar signal irradiation unit that transmits a radar signal (e.g., mmWave signal, millimeter wave wave) and a radar signal reception unit that receives a radar signal (e.g., mmWave signal) reflected from the user's body.

[0181] The frequency band (e.g., 28 GHz) of the radar signal output from the radar sensor (52c) may be higher than the frequency band (e.g., 6.0 to 8.8 GHz) of the UWB signal output from the UWB sensor (52b).

[0182] The frequency bandwidth of the radar signal output from the radar sensor (52c) may be narrower than the frequency bandwidth of the UWB signal output from the UWB sensor (52b).

[0183] The radar sensor (52c) may have a detection area directed toward the body (e.g., face) of a user lying or sitting on the furniture (10). The radar sensor (52c) may have a detection area capable of detecting the movement of the user's eyes. The radar sensor (52c) may be provided on a frame of the furniture (10) to have a detection area directed toward the body (e.g., torso) of the user, but the location of the radar sensor (52c) is not limited thereto.

[0184] The radar sensor (52c) may have a detection area directed toward a part of the body of a user lying or sitting on the furniture (10).

[0185] For example, if the furniture (10) corresponds to a bed, the radar sensor (52c) may have a detection area directed toward the head area of ​​the bed.

[0186] As another example, if the furniture (10) corresponds to a chair, the radar sensor (52c) may have a detection area directed toward the headrest of the chair.

[0187] The radar sensor (52c) can transmit a radar signal (mmWave signal, millimeter wave wave) toward the user's body and receive a mmWave signal reflected from the user's body.

[0188] The radar sensor (52c) can measure the movement of the user's eyes based on mmWave reflected from the user's eyes.

[0189] That is, the radar sensor (52c) can obtain eye-movement data corresponding to the movement of the user's eyes.

[0190] The oxygen saturation sensor and / or the electrocardiogram sensor may include a light source that irradiates light and a light receiving unit that receives light reflected from the user's body.

[0191] The oxygen saturation sensor and / or the electrocardiogram sensor may have a sensing area facing the body of a user lying or sitting on the furniture (10).

[0192] The oxygen saturation sensor and / or the electrocardiogram sensor may be provided in a wearable smart sensor device (e.g., a smart watch, a smart ring, etc.) by the user.

[0193] The oxygen saturation sensor and / or electrocardiogram sensor may operate non-invasively, shining light toward a portion of the user's body (e.g., the wrist) and receiving light reflected from the user's body.

[0194] The oxygen saturation sensor and / or the electrocardiogram sensor can measure the oxygen saturation in the user's blood or the user's electrocardiogram based on the intensity of light reflected from the user's body.

[0195] Some of the light directed at a part of the body is absorbed by blood vessels, and depending on the absorption rate of the light or the pattern of the absorbed light, the oxygen saturation in the user's blood or the user's electrocardiogram can be measured.

[0196] The acceleration sensor (52d) may include a MEMS sensor, a 3-axis acceleration sensor, and / or a 6-axis acceleration sensor.

[0197] According to various embodiments, the acceleration sensor (52d) may be provided in a wearable smart sensor device (e.g., a smart watch, a smart ring, etc.) by a user, similar to an oxygen saturation sensor and / or an electrocardiogram sensor.

[0198] In one embodiment, the acceleration sensor (52d) may be installed on furniture (10).

[0199] The acceleration sensor (52d) can obtain acceleration data corresponding to the user's body movement.

[0200] The hub device (1) may be installed on furniture (10) or installed in a location adjacent to the furniture (10) and may be connected to some of the plurality of sensors (5) via a wire. In addition, the hub device (1) may perform wireless communication with a smart sensor device (e.g., a wearable device) worn by a user.

[0201] FIG. 6 illustrates an example of a flowchart of a sleep management method according to one embodiment.

[0202] FIG. 7 is a diagram illustrating a process for processing data collected from multiple sensors of a sleep management system according to one embodiment.

[0203] Referring to FIGS. 6 and 7, the hub device (1) can collect data from a plurality of sensors (5) (S1).

[0204] When multiple sensors (5) are maintained in an activated state, the power consumption supplied to the multiple sensors (5) may be high. Maintaining the multiple sensors (5) in an activated state may include maintaining a state in which the multiple sensors (5) are capable of acquiring sensor data by being supplied with power.

[0205] In one embodiment, the hub device (1) can keep at least some of the plurality of sensors (5) in a deactivated state, but can switch the plurality of sensors (5) to an activated state based on the satisfaction of a predetermined condition.

[0206] For example, the hub device (1) can determine whether a user is present in the furniture (10) based on processing data collected from multiple sensors (5). The presence of a user in the furniture (10) may include the user lying down or sitting on the furniture (10).

[0207] The hub device (1) can switch multiple sensors (5) to a standby state based on the determination that there is no user in the furniture (10).

[0208] For example, the hub device (1) can deactivate the remaining sensors except for the voice sensor (51) and operate the voice sensor (51) in a low power mode. Deactivating the sensor may include cutting off power supplied to the sensor.

[0209] Operating the sensor in a low power mode may involve setting the sensor's operating cycle (e.g., data collection cycle) to a longer period.

[0210] The hub device (1) can determine whether a user is present in the furniture (10) based on processing data collected by a sensor (e.g., a voice sensor (51)) operating in a low power mode among a plurality of sensors (5).

[0211] The hub device (1) can wake up multiple sensors (5) based on the determination that a user is present in the furniture (10).

[0212] A plurality of sensors (5) can transmit collected data to the hub device (1) based on activation.

[0213] The voice sensor (51) can transmit voice data to the hub device (1), and the non-voice sensor (52) can transmit non-voice data to the hub device (1).

[0214] In one embodiment, at least some of the plurality of sensors (5) can transmit sensor data to the hub device (1) via wired communication, and some of the remaining sensors (5) can transmit sensor data to the hub device (1) via wireless communication.

[0215] The hub device (1) can primarily process data collected from multiple sensors (5) (S2). That is, the primary processing of the data can be performed by the processor (110) of the hub device (1). For this purpose, the hub device (1) can be equipped with a machine learning model.

[0216] Data collected from multiple sensors (5) can be processed by a machine learning model mounted on the hub device (1).

[0217] The processor (110) of the hub device (1) can obtain first processing data based on processing voice data collected by the voice sensor (51). In addition, the processor (110) of the hub device (1) can obtain second processing data based on processing non-voice data collected by the non-voice sensor (52).

[0218] The machine learning model mounted on the hub device (1) can be pre-trained to extract features from voice data collected by the voice sensor (51).

[0219] The machine learning model mounted on the hub device (1) can be pre-trained to extract features from pressure data collected by the pressure sensor (52a). The machine learning model mounted on the hub device (1) can be pre-trained to extract features from displacement data collected by the UWB sensor (52b). The machine learning model mounted on the hub device (1) can be pre-trained to extract features from eye movement data collected by the radar sensor (52c). The machine learning model mounted on the hub device (1) can be pre-trained to extract features from acceleration data collected by the acceleration sensor (52d). The machine learning model mounted on the hub device (1) can be pre-trained to extract features from oxygen saturation data and / or electrocardiogram data collected by the oxygen saturation sensor and / or the electrocardiogram sensor.

[0220] The machine learning model mounted on the hub device (1) can use voice data collected by the voice sensor (51) as input data and output first processed data as output data. The voice data may include sound wave signals collected by the voice sensor (51).

[0221] The first processing data may be a sound signal collected from a voice sensor (51) processed and expressed as a plurality of sound parameters. Here, the sound parameters may include frequency, amplitude, phase, wavelength, and / or sound pressure.

[0222] As another example, the first processed data may include information about the user's posture, respiration rate, and heart rate inferred from the first data. As another example, the first processed data may include information about the user's cough, sleep stage, stress index, or sleep disorder inferred from the voice data.

[0223] The machine learning model mounted on the hub device (1) can use non-voice data collected by the non-voice sensor (52) as input data and output second processing data as output data.

[0224] Secondary processed data may include, for example, information about respiration rate and heart rate, information about eye movements, oxygen saturation, electrocardiogram (ECG) information, and / or movement information inferred from non-speech data. As another example, second processed data may include information about the user's sleep stage, information about the user's stress index, or information about the user's sleep disorders inferred from second data.

[0225] According to the present disclosure, the hub device (1) primarily processes data collected from a plurality of sensors (5), thereby enabling data collected from a plurality of sensors (5) to be transmitted to a user device (2) even in a communication method with a low data transmission capacity.

[0226] The hub device (1) can process data collected from multiple sensors (5) and transmit the processed data to the user device (2) (S3).

[0227] The hub device (1) can transmit processing data to the user device (2) via wireless communication. In one embodiment, the communication unit (130) of the hub device (1) can include a first communication module for receiving data collected from some of the plurality of sensors (5) via a first wireless communication method, and a second communication module for transmitting the processing data to the user device (2) via a second wireless communication method.

[0228] The first wireless communication method and the second wireless communication method may be the same or different from each other.

[0229] According to one embodiment of the present disclosure, a hub device (1) has both a first communication module for receiving data from some of a plurality of sensors (5) and a second communication module for communicating with a user device (2), so that it can communicate with a plurality of sensors (5) and a user device (2) at the same time.

[0230] The user device (2) can process processing data received from the hub device (1) (S4).

[0231] To this end, the user device (2) may be equipped with at least one machine learning model (20). The at least one machine learning model (20) equipped in the user device (2) may include a first machine learning model (21), a second machine learning model (22), and / or a third machine learning model (23).

[0232] Processing data received from the hub device (1) can be processed by a machine learning model (20) installed in the user device (2).

[0233] The machine learning model (20) mounted on the user device (2) may include an artificial neural network (deep neural network) model having multiple layers (e.g., an input layer, a hidden layer, and an output layer). The machine learning model (20) mounted on the user device (2) may be configured as a perceptron structure having a structure that receives multiple signals as input and outputs one signal. The machine learning model (20) mounted on the user device (2) may be trained for the purpose of estimating the user's sleep state based on processing data processed by the hub device (1).

[0234] The machine learning model (20) mounted on the user device (2) can use the processed data output from the hub device (1) as input data to output cough information related to the user's cough during sleep as output data.

[0235] The user's cough information may include a second parameter (P2) corresponding to the timing of the cough, the cough period, and / or the cough sound.

[0236] The first machine learning model (21) can output the user's cough information as output data by using the first processing data as input data. That is, the user device (2) can obtain the user's cough information by inputting the first processing data, which is the processed voice data collected from the voice sensor (51), into the first machine learning model (21).

[0237] The processor (210) of the user device (2) can calculate a first parameter (P1) indicating a correlation between the first processing data and the second processing data based on the first processing data and the second processing data.

[0238] The second machine learning model (22) can use the first parameter (P1) as input data to utilize it as a learning parameter. The second machine learning model (22) can output the user's cough information as output data by using the first parameter (P1) and the second processing data as input data. That is, the user device (2) can obtain the user's cough information by inputting the first parameter (P1) indicating the correlation between the first processing data and the second processing data and the second processing data, which is the second processing data processed by the non-voice data collected from the non-voice sensor (52), into the second machine learning model (22).

[0239] Accordingly, the user device (2) can obtain the user's cough information using only the second processing data, which is the result of processing non-voice data, through the second machine learning model (22), without voice data, by using the first parameter (P1) indicating the correlation between the first processing data and the second processing data. A specific method for this will be described later.

[0240] If a user wants to disable the voice sensor for privacy reasons, the non-voice sensor alone can still obtain the user's cough information, which is effective in protecting the user's privacy.

[0241] As described above, the cough information output from the second machine learning model (22) may include a second parameter (P2) corresponding to the cough sound. The second parameter (P2) may be a plurality of acoustic parameters corresponding to the cough sound. Accordingly, the second parameter (P2) may include the frequency, amplitude, phase, wavelength, and / or sound pressure of an acoustic signal corresponding to the cough sound.

[0242] The second parameter (P2) included in the cough information output from the second machine learning model (22) can be transferred to the third machine learning model (23). The third machine learning model (23) can use the second parameter (P2) as input data to utilize it as a learning parameter.

[0243] The third machine learning model (23) can output the type of cough sound related to the user's coughing during sleep as output data by using the second parameter (P2) as input data. That is, the user device (2) can input the second parameter (P2) corresponding to the cough sound into the third machine learning model (23) to obtain the type of cough sound, which is a type of cough information of the user.

[0244] The type of cough sound can vary depending on the surrounding environment. In other words, changes in the surrounding environment may cause changes in the cough sound.

[0245] For example, cough types can include dry and disease-related coughs. Dry coughs can be caused by dry environments or dust. Therefore, dry coughs may be less likely to be associated with disease. Dry coughs can be called "dry coughs."

[0246] A cough of this type, which suggests a disease, can be caused by conditions such as bronchitis, asthma, pneumonia, chronic obstructive pulmonary disease, and pulmonary fibrosis. Therefore, it can be significantly different from a dry cough.

[0247] According to the present disclosure, since voice data and non-voice data are primarily processed by the hub device (1) and the output data is secondarily input into the machine learning model (20) installed in the user device (2) to output the user's cough information, the user's cough information can be accurately estimated. That is, according to the present disclosure, a large amount of data can be processed in stages to accurately estimate the user's cough information.

[0248] The user device (2) can transmit cough information to the server device (3) (S5).

[0249] According to the present disclosure, instead of direct data related to the user's private life being transmitted to the server device (3), only the user's cough information is transmitted to the server device (3), thereby making it easier to obtain the user's consent for data collection.

[0250] The server device (3) can generate a control command for controlling the home appliance (4) based on the cough information (S6). At this time, the home appliance (4) can include at least one home appliance (4) registered in conjunction with the user device (2). The server device (3) can store and / or manage user accounts and register the user device (2) and the home appliance (4) by linking them to the user account.

[0251] At least one home appliance (4) registered in conjunction with the user device (2) may include a home appliance (4) registered to the user account to which the user device (2) is registered.

[0252] The server device (3) can transmit a control command to control the home appliance (4) to the home appliance (4) (S7).

[0253] According to various embodiments, the process (S6) of generating a control command for controlling the home appliance (4) based on cough information and the process of transmitting the control command for controlling the home appliance (4) to the home appliance (4) can of course also be performed by the user device (2).

[0254] The home appliance (4) can perform a predetermined operation corresponding to a control command received from the server device (3) (S8). A specific embodiment of the home appliance (4) in which the server device (3) controls the home appliance (4) based on cough information and performs a predetermined operation in response thereto will be described in detail later with reference to FIGS. 13 to 15.

[0255] The machine learning model stored in the user device (2) can be updated by an external server.

[0256]

[0257] Figures 8, 9, 10, and 11 illustrate a flowchart of a sleep management method according to one embodiment.

[0258] Referring to FIG. 8, at least one voice sensor (51) among the plurality of sensors (5) can collect voice data and transmit it to the hub device (1), and at least one non-voice sensor (52) among the plurality of sensors (5) can collect non-voice data and transmit it to the hub device (1). (810)

[0259] The hub device (1) can process voice data received from a voice sensor (51) and non-voice data received from a non-voice sensor (52) to obtain first processing data and second processing data. (820)

[0260] Afterwards, the hub device (1) can transmit the acquired first processing data and the acquired second processing data to the user device (2). (830)

[0261] The user device (2) can obtain the user's cough information as output data by inputting the first processing data received from the hub device (1) into the first machine learning model (21). (840) The user device (2) can transmit the obtained user's cough information to the server device (3). (850)

[0262] The server device (3) can transmit a control command to the home appliance (4) to control at least one home appliance (4) based on cough information received from the user device (2). (860)

[0263] Referring to FIG. 9, after the first processing data and the second processing data are transmitted to the user device (2) according to step 830 of FIG. 8, the processor (210) of the user device (2) can calculate a first parameter (P1) indicating a correlation between the first processing data and the second processing data, and the memory (220) of the user device (2) can store the calculated first parameter (P1). (910)

[0264] The user device (2) can obtain the user's cough information by inputting the first parameter (P1) and the second processing data into the second machine learning module (22). (920)

[0265] Afterwards, according to step 850 of FIG. 8, the user device (2) can transmit the acquired user's cough information to the server device (3).

[0266] Referring to FIG. 10, the hub device (1) can block the collection of voice data from the voice sensor (51). (1010) For example, the user device (2) can control the hub device to stop collecting voice data based on receiving a command from the user to stop collecting voice data from the voice sensor. This has the effect of protecting the user's privacy.

[0267] When the collection of voice data is blocked as above, the hub device (1) can only obtain non-voice data collected from the non-voice sensor (52). (1020)

[0268] The hub device (1) can obtain second processing data based on the acquired non-voice data processed. (1030) The hub device (1) can transmit only the second processing data to the user device (2) without the first processing data. (1040)

[0269] Afterwards, according to step 920 of FIG. 9 again, the user device (2) can obtain cough information by inputting the stored first parameter (P1) and the received second processing data into the second machine learning module (22).

[0270] Referring to FIG. 11, after step 840 of FIG. 8, the user device (2) can input the second parameter (P2) corresponding to the cough sound included in the user's cough information as input data to the third machine learning model (23). (1110)

[0271] The third machine learning model (23) can output the type of cough sound related to the user's coughing during sleep as output data using the second parameter (P2) as input data. That is, the user device (2) can determine the type of cough sound based on the second parameter (P2) corresponding to the cough sound (1120).

[0272] The user device (2) can identify whether the type of cough sound is a suspected disease type. (1130) The user device (2) can provide the user with a warning alarm about the suspected disease type based on the identification of the type of cough sound as a suspected disease type. (1140)

[0273] This has the potential to encourage users to receive early diagnosis of diseases. Therefore, it can provide users with the ability to manage their health by diagnosing or preventing diseases early.

[0274] Human sleep stages can be divided into wakefulness stages, rapid eye movement (REM) stages, and non-rapid eye movement (NREM) stages.

[0275] The awakening stage corresponds to the stage in which a person is awake.

[0276] REM sleep is a rapid eye movement sleep stage, a shallow sleep similar to being awake, and is a stage of sleep characterized by rapid eye movement.

[0277] In adults, REM sleep typically accounts for approximately 20–25% of total sleep, occurring approximately 90–120 minutes per night.

[0278] During REM sleep, the brain's neural activity is quite similar to that of awake states. However, because the body is in a relaxed state, it is involuntary. For this reason, REM sleep is also called paradoxical sleep, meaning that brain waves are not suppressed during REM sleep.

[0279] Non-REM sleep is a non-rapid eye movement sleep stage, and unlike REM sleep, there is almost no eye movement during non-REM sleep.

[0280] During non-REM sleep, dreams are rare, and muscle movements are not inhibited as in REM sleep. Those who do not properly progress through the sleep stages become trapped in non-REM sleep, and the lack of muscle inhibition can lead to sleep disorders (e.g., sleepwalking).

[0281] Non-REM sleep stages can be divided into stage 1 (stage N1), stage 2 (stage N2), stage 3 (stage N3), and stage 4 (stage N4). Within non-REM sleep stages, stages 1 (stage N1) and 2 (stage N2) can be divided into light sleep stages, while stages 3 (stage N3) and 4 (stage N4) can be divided into deep sleep stages.

[0282] As another example, non-REM sleep stages may be divided into stage 1 (stage N1), stage 2 (stage N2), and stage 3 (stage N3).

[0283] During non-REM sleep, brain wave activity gradually slows and physiological functions decline. During non-REM sleep, brain tissue and epithelial cells regenerate, body energy is restored, and hormones for skeletal growth, protein synthesis, and tissue regeneration are secreted.

[0284] Stage N1 is the most liminal stage of sleep, marking the body's gradual transition into sleep. Stage N1 occurs before deep sleep and represents a state of non-deep sleep.

[0285] Stage N2 is a transition from borderline sleep to a deeper sleep. Brainwave patterns shift from slightly slower beta waves to slower theta waves, and eye movements cease, but intermittent rapid eye movements are absent.

[0286] Stage N3 is the initial stage of deep sleep, where brainwave patterns shift to delta waves, muscle tone is relaxed, and physical movement is minimal. Snoring may occur during Stage N3.

[0287] Stage N4 is a deep sleep from which awakening is extremely difficult. During stage N4, growth hormone secretion increases, which supports skeletal growth, protein synthesis, and tissue regeneration. Symptoms such as sleepwalking and enuresis may also occur.

[0288] Typically, when a person falls asleep, the first sleep cycle begins. In this first sleep cycle, the person enters non-REM sleep from the wakeful stage, then moves through stages N1, N2, N3, and N4, and then returns to N3, N2, N1, and REM sleep.

[0289] Afterwards, in the second sleep cycle, we go through stages N1, N2, N3, N4, and then return to stages N3 and N2.

[0290] Afterwards, in the third sleep cycle, we go through stage N3 and then return to stage N2, stage N1, and REM sleep.

[0291] Afterwards, in the fourth sleep cycle, we go through stage N1 and N2 sleep, and then enter stage N1 and REM sleep again.

[0292] After that, the person goes through the N1 stage, N2 stage, and REM sleep stage and wakes up naturally.

[0293] If a person wakes up during stage N4 sleep, they may feel groggy and not feel like they've slept. Therefore, it's recommended that people wake up during stage N1 or REM sleep.

[0294]

[0295] FIG. 12 illustrates an example of sleep state information including cough information derived by a sleep management system according to one embodiment.

[0296] Sleep status information can be derived in real time by a sleep management system.

[0297] Referring to FIG. 12, sleep state information derived by a sleep management system according to one embodiment may include information about sleep stages, information about oxygen saturation, information about sleep disorders, information about stress index, information about respiratory rate, information about movement, information about heart rate, information about body pressure, and / or information about coughing.

[0298] According to various embodiments, the user device (2) may output sleep state information through an output interface (e.g., a display).

[0299] Information about sleep stages may include information about the user's current sleep stage and / or information about the user's sleep stages over time.

[0300] Information about the user's current sleep stage may include information about whether the user's current sleep stage corresponds to a wake stage, a REM sleep stage, or stage 1, stage 2, stage 3, or stage 3 of non-REM sleep.

[0301] Information about the user's sleep stages over time may include information about changes in sleep stages from a time point preset by the user using the user device (2), a time point when the user lies down or sits on furniture (10) to fall asleep, a time point when the user falls asleep, and / or a time point when the user runs the sleep management application to the present time point.

[0302] When information about the user's sleep stage over time is output by the user device (2), the information about the user's sleep stage over time can be displayed in the form of a graph, and the x-axis of the graph can represent time and the y-axis can represent the user's sleep stage.

[0303] Information about oxygen saturation may include information about the user's current oxygen saturation and / or information about the user's oxygen saturation over time.

[0304] When information regarding oxygen saturation is output by the user device (2), the numerical value of the oxygen saturation may be output in the form of a percentage. Additionally, when information regarding oxygen saturation is output by the user device (2), whether the user's oxygen saturation is normal according to medical standards may be displayed.

[0305] Information about sleep disorders may include information about the current user's sleep disorders and / or information about sleep disorders that have developed over time.

[0306] Sleep disorders may include information on breathing-related sleep disorders, such as apnea and hypopnea. Information on breathing-related sleep disorders, such as apnea and hypopnea, may include the Apnea Hypopnea Index (AHI).

[0307] When information on sleep disorders related to breathing is output by the user device (2), the Apnea Hypopnea Index (AHI) may be output, and whether the user's Apnea Hypopnea Index is normal according to medical standards may be displayed.

[0308] Information about the user's stress level may include information about the user's stress level. When information about the user's stress level is output by the user device (2), the user's stress level may be output numerically or in the form of comparative terms (e.g., "high," "medium," "low"), and whether the user's stress level is normal according to medical standards may be indicated.

[0309] Information about respiration rate may include information about the user's current respiration rate and / or information about the user's respiration rate over time.

[0310] When information about the current respiratory rate is output by the user device (2), the user's respiratory rate can be output numerically, and whether the user's respiratory rate is normal according to medical standards can be displayed.

[0311] When information about the user's breathing rate over time is output by the user device (2), the information about the user's breathing rate over time can be displayed in the form of a graph, and the x-axis of the graph can represent time and the y-axis can represent the user's breathing rate.

[0312] Information about movement may include information about the degree of movement of the user, and / or information about the degree of movement of the user over time.

[0313] When information about the current degree of movement is output by the user device (2), the degree of the user's movement may be output numerically or in the form of comparative words (e.g., high, medium, low).

[0314] When information about the degree of movement over time is output by the user device (2), the information about the degree of movement of the user over time can be displayed in the form of a graph, and the x-axis of the graph can represent time and the y-axis can represent the degree of movement of the user.

[0315] Information about heart rate may include information about the user's current heart rate and / or information about the user's heart rate over time.

[0316] When information about the current heart rate is output by the user device (2), the user's heart rate can be output numerically, and whether the user's heart rate is normal according to medical standards can be displayed.

[0317] When information about the user's heart rate over time is output by the user device (2), the information about the user's heart rate over time can be displayed in the form of a graph, and the x-axis of the graph can represent time and the y-axis can represent a pulse corresponding to the user's heartbeat.

[0318] Information about body pressure may include information about the user's body posture. This information may include whether the user is lying flat, lying on their left side, lying on their right side, lying prone, or sitting.

[0319] When information about body pressure is output by the user device (2), a term indicating the user's posture may be used, and a pressure distribution table based on the furniture (10) on which the user is lying or sitting may be output.

[0320] Information about a cough may include the cough period, cough volume, and / or cough sound type. When information about a current cough is output by the user device (2), the cough period and cough sound volume may be numerically output, and whether the cough type is a suspected disease type according to medical criteria may be indicated.

[0321]

[0322] The hub device (1) can wake up multiple sensors (5) based on the satisfaction of a predetermined condition.

[0323] For example, the hub device (1) can wake up multiple sensors (5) based on determining that a user is present in the furniture (10).

[0324] As another example, the user device (2) may transmit a sleep management start request to the hub device (1) based on receiving a user input corresponding to the start of sleep, and the hub device (1) may wake up a plurality of sensors (5) based on receiving the sleep management start request through the user device (2).

[0325] As another example, the user device (2) can receive information about the expected sleep time from the user and transmit it to the hub device (1). The hub device (1) can wake up multiple sensors (5) based on reaching the expected sleep time.

[0326] The server device (3) can determine whether the current time corresponds to sleep time.

[0327] For example, a user can preset a sleep time via the user device (2). The sleep time can be set as a time range or by time. For example, the user can set the sleep time to "10:00 PM - 11:00 PM" or "10:00 PM."

[0328] The server device (3) can determine that the current time corresponds to the sleep time if the current time corresponds to the sleep time set by the user.

[0329] As another example, when a user inputs a command corresponding to the start of sleep through the user device (2), the server device (3) can determine that the current time corresponds to the sleep time.

[0330] A command corresponding to the start of sleep can be received via the user interface (240) of the user device (2). For example, the command corresponding to the start of sleep can be received by the user device (2) via touch input and / or voice input.

[0331] According to various embodiments, when a user inputs an automatic sleep management request through the user device (2), the server device (3) may determine that the current time corresponds to sleep time based on the satisfaction of a predetermined condition. In one embodiment, the server device (3) may determine whether the current time corresponds to sleep time based on the result information. For example, the server device (3) may determine that the current time corresponds to sleep time if the user maintains a predetermined posture (e.g., lying down or prone) for a predetermined period of time.

[0332] If the current time corresponds to sleep time, the server device (3) can control the home appliance (4) based on sleep status information including cough information received from the user device (2).

[0333] In one embodiment, the server device (3) can control at least one home appliance (4) to perform a predetermined operation to alleviate the user's cough based on the current time corresponding to the sleep time and the user's cough cycle being shorter than a predetermined time.

[0334] Figure 13 is a drawing illustrating an example of a predetermined operation performed by a home appliance to relieve a user's cough.

[0335] Referring to FIG. 13, the server device (3) can control the air conditioner (41) to perform a predetermined operation to relieve the user's cough.

[0336] For example, the server device (3) can control the air conditioner (41) to increase the ambient temperature based on the user's cough information. That is, the server device (3) can increase the set temperature of the air conditioner (41) or stop the air conditioner (41) from operating.

[0337] Additionally, the server device (3) can control the humidifier (42) to perform a predetermined operation to relieve the user's cough.

[0338] For example, the server device (3) can control the humidifier (42) to increase the relative humidity based on the user's cough information. That is, the server device (3) can operate the humidifier (42). In addition, the server device (3) can increase the set humidity of the operating humidifier (42) or increase the operating intensity of the operating humidifier (42).

[0339] Additionally, the server device (3) can control the dehumidifier (43) to perform a predetermined operation to relieve the user's cough.

[0340] For example, the server device (3) can control the dehumidifier (43) to increase the relative humidity based on the user's cough information. That is, the server device (3) can reduce the set humidity of the dehumidifier (43), stop the operation of the operating dehumidifier (43), or reduce the operating intensity of the operating dehumidifier (43).

[0341] Additionally, the server device (3) can control the air purifier (44) to perform a predetermined operation to relieve the user's cough.

[0342] For example, the server device (3) can control the air purifier (44) to improve air quality based on the user's cough information. That is, the server device (3) can operate the air purifier. In addition, the server device (3) can increase the operating intensity of the air purifier (44) while it is in operation.

[0343]

[0344] Figure 14 is a drawing illustrating an example of a predetermined action performed by a smart bed to relieve a user's cough.

[0345] Referring to FIGS. 13 and 14, the server device (3) can control the smart bed (45) to perform a predetermined operation to relieve the user's cough.

[0346] For example, the server device (3) can control the smart bed (45) so that the user's head is in a higher position than the torso and legs to expand the airway based on the user's cough information.

[0347] That is, the server device (3) can control the smart bed (45) so that the user's upper body is raised at a first angle (θ1) that is predetermined. Specifically, the server device (3) can control the furniture control device (45a) included in the smart bed (45) so that a part of the smart bed (45) corresponding to the user's upper body forms a first angle (θ1) that is predetermined with respect to the ground.

[0348] The furniture control device (45a) included in the smart bed (45) may include a vibration element capable of transmitting vibration to a user lying on the smart bed (45) and / or an actuator capable of changing the user's posture by changing the structure of the smart bed (45).

[0349] Figure 15 is a drawing illustrating an example of a predetermined action performed by a smart pillow to relieve a user's cough.

[0350] Referring to FIGS. 13 and 15, the server device (3) can control the smart pillow (46) to perform a predetermined operation to relieve the user's cough.

[0351] For example, the server device (3) can control the smart pillow (46) to expand the airway based on the user's cough information. That is, the server device (3) can control the smart pillow (46) to turn the user's head (H). Specifically, the server device (3) can control the furniture control device (47) included in the smart pillow (46) so that the direction in which the face faces deviates from the vertical direction by a predetermined second angle (θ2).

[0352] The furniture control device (47) included in the smart pillow (46) may include a vibration element capable of transmitting vibration to a user sleeping on the smart pillow (46), an actuator capable of changing the user's posture by changing the structure of the smart pillow (46), and / or an air cell (47).

[0353] Referring to FIG. 15, the air cell (47) included in the smart pillow (46) may include a plurality of air cells. The plurality of air cells may include a first air cell (47a), a second air cell (47b), a third air cell (47c), a fourth air cell (47d), and a fifth air cell (47e). The number of the plurality of air cells is not limited according to FIG. 15.

[0354] The server device (3) can control the volume of a portion of the plurality of air cells included in the smart pillow (46) to increase in order to expand the user's airway by turning the user's head (H).

[0355] For example, the server device (3) can control the smart pillow (46) to increase the volume of the first air cell (47a) and the second air cell (47b) to turn the user's head (H) to the right.

[0356] In addition, the server device (3) can adjust the size of the second angle (θ2) that is predetermined by adjusting the size of the increase in the volume of each of the plurality of air cells.

[0357] In addition, in order to form a natural incline of the smart pillow (46) as shown in FIG. 15 to allow the user's head (H) to turn, the server device (3) can control the smart pillow (46) so that the size by which the volume of the first air cell (47a) increases is greater than the size by which the volume of the second air cell (47b) increases.

[0358] The operations of the server device (3) described with reference to FIGS. 13 to 15 can be performed repeatedly according to a predetermined cycle.

[0359] According to various embodiments, the operations described with reference to FIGS. 13 to 15 may also be performed by the user device (2). For example, the user device (2) may control the home appliance (4) based on sleep state information including cough information.

[0360] According to one aspect of the disclosed invention, a person's sleep state can be accurately measured in daily life without attaching various sensors to the body.

[0361] According to one aspect of the disclosed invention, since analysis of a person's sleep state is performed at a user device, invasion of an individual's privacy can be prevented.

[0362] According to one aspect of the disclosed invention, since data processing is performed by a plurality of devices, the level of data processing load that each device must bear can be reduced.

[0363] According to one aspect of the disclosed invention, convenience in health management can be provided by providing the user with various information about coughing occurring during sleep.

[0364] According to one aspect of the disclosed invention, a user's disease can be diagnosed or prevented early by warning the user if a disease is suspected based on a coughing sound that the user makes while sleeping.

[0365] According to one aspect of the disclosed invention, even if the voice sensor stops collecting voice data due to privacy invasion, cough information can be provided to the user based on non-voice data, thereby preventing invasion of an individual's privacy.

[0366] According to one aspect of the disclosed invention, it is possible to induce a user to have good quality sleep.

[0367] A sleep management system according to one embodiment of the present disclosure comprises: a plurality of sensors (5) including at least one voice sensor (51) and at least one non-voice sensor (52) for collecting user data; a hub device (1) for receiving voice data collected by the at least one voice sensor (51) and non-voice data collected by the at least one non-voice sensor (52), obtaining first processed data based on processing the voice data, and obtaining second processed data based on processing the non-voice data; a user device (2) for receiving the first processed data and the second processed data from the hub device (1) via wireless communication, inputting the first processed data into a first machine learning model (21) to obtain cough information of the user, and calculating a first parameter (P1) representing a correlation between the first processed data and the second processed data; And it may include a sleep management system including a server device (3) that receives the cough information from the user device (2) through wireless communication and controls at least one home appliance (4) registered in conjunction with the user device (2) based on the cough information.

[0368] The user device (2) can obtain the user's cough information by inputting the first parameter (P1) and the second processing data produced into the second machine learning model (22).

[0369] The user device (2) can control the hub device (1) to stop collecting the voice data based on receiving a command from the user to stop collecting the voice data from the voice sensor (51).

[0370] The user device (2) can store the first parameter (P1) calculated above and, based on receiving a command from the user to stop collecting the voice data from the voice sensor (51), input the stored first parameter (P1) and the second processing data into the second machine learning module (22) to obtain the cough information.

[0371] The cough information of the user may include at least one of a coughing time, a coughing cycle, and a second parameter (P2) corresponding to a coughing sound.

[0372] The user device (2) can determine the type of cough sound by inputting the second parameter (P2) into the third machine learning model (23).

[0373] The user device (2) can provide the user with a warning alarm regarding the suspected disease type based on whether the type of cough sound is determined to be a suspected disease type.

[0374] The server device (3) can control at least one home appliance (4) to perform a predetermined operation to alleviate the cough based on the fact that the cough cycle is shorter than a predetermined time.

[0375] The at least one home appliance (4) includes an air conditioner (41), and the server device (3) can control the air conditioner (41) to increase the ambient temperature based on the cough information of the user.

[0376] The at least one home appliance includes an air conditioner (41), and the server device (2) can stop the operation of the air conditioner (41) based on the cough information of the user.

[0377] The at least one home appliance (4) includes a humidifier (42), and the server device (3) can operate the humidifier (42) to increase the relative humidity or increase the operating intensity of the humidifier (42) while it is in operation, based on the cough information of the user.

[0378] The at least one home appliance (4) includes a dehumidifier (43), and the server device (3) can stop the operation of the dehumidifier (43) or reduce the operating intensity of the dehumidifier (43) while it is in operation, based on the cough information of the user, so as to increase the relative humidity.

[0379] The at least one home appliance (4) includes an air purifier (44), and the server device (3) can operate the air purifier (44) or increase the operating intensity of the air purifier (44) in operation based on the cough information of the user.

[0380] The at least one home appliance (4) includes a smart bed (45), and the server device (3) can control the smart bed (45) so that the user's upper body is raised to a predetermined first angle based on the user's cough information.

[0381] The at least one home appliance (4) includes a smart pillow (46), and the server device (3) can control the smart pillow (46) based on the cough information of the user so that the direction in which the user's face faces deviates from the vertical direction by a second angle that is predetermined.

[0382] A sleep management method according to one embodiment of the present disclosure comprises: a hub device (1) receiving voice data collected by a voice sensor (51) and non-voice data collected by a non-voice sensor (52); the hub device (1) obtaining first processed data based on processing the voice data and obtaining second processed data based on processing the non-voice data; the hub device (1) transmitting the first processed data and the second processed data to a user device (2) via wireless communication; the user device (2) inputting the first processed data received from the hub device (1) into a first machine learning model (21) to obtain cough information of the user; the user device (2) calculating a first parameter (P1) indicating a correlation between the first processed data and the second processed data; the sub device (3) receiving the cough information from the user device (2); And the sub-device (3) may include controlling at least one home appliance (4) registered in conjunction with the user device (2) based on the cough information.

[0383] The above sleep management method may further include the user device (2) inputting the calculated parameters and the second processing data into a second machine learning model (22) to obtain cough information of the user.

[0384] The sleep management method further comprises: controlling the hub device (1) to stop collecting the voice data based on the user device (2) receiving a command from the user to stop collecting the voice data from the voice sensor (51);

[0385] The sleep management method may further include: the user device (2) storing the calculated first parameter (P1); and, based on receiving a command from the user to stop collecting the voice data from the voice sensor (51), inputting the stored first parameter (P1) and the second processing data into a second machine learning module (22) to obtain the cough information.

[0386] The cough information of the user may include at least one of the timing of coughing, the period of coughing, and a second parameter (P2) corresponding to the cough sound, and the sleep management method may further include the user device (2) inputting the second parameter (P2) into a third machine learning model (23) to determine the type of the cough sound.

[0387] Meanwhile, the disclosed embodiments may be implemented in the form of a recording medium storing computer-executable instructions. The instructions may be stored in the form of program code, and when executed by a processor, may generate program modules to perform the operations of the disclosed embodiments. The recording medium may be implemented as a computer-readable recording medium.

[0388] Computer-readable storage media include all types of storage media that store instructions that can be deciphered by a computer. Examples include read-only memory (ROM), random access memory (RAM), magnetic tape, magnetic disks, flash memory, and optical data storage devices.

[0389] Additionally, a computer-readable recording medium may be provided in the form of a non-transitory storage medium. Here, the term "non-transitory storage medium" simply means a tangible device that does not contain signals (e.g., electromagnetic waves). This term does not distinguish between cases where data is permanently stored in the storage medium and cases where data is temporarily stored. For example, a "non-transitory storage medium" may include a buffer in which data is temporarily stored.

[0390] According to one embodiment, the method according to various embodiments disclosed in the present document may be provided as included in a computer program product. The computer program product may be traded as a product between a seller and a buyer. The computer program product may be distributed in the form of a machine-readable recording medium (e.g., compact disc read only memory (CD-ROM)), or may be distributed online (e.g., downloaded or uploaded) via an application store (e.g., Play Store™) or directly between two user devices (e.g., smartphones). In the case of online distribution, at least a portion of the computer program product (e.g., a downloadable app) may be temporarily stored or temporarily generated on a machine-readable recording medium, such as the memory of a manufacturer's server, an application store's server, or an intermediary server.

[0391] The above illustrates and describes specific embodiments. However, the invention is not limited to the above-described embodiments, and those skilled in the art will readily appreciate that various modifications and implementations can be made without departing from the spirit and scope of the invention as set forth in the claims below.

Claims

1. A plurality of sensors (5) including at least one voice sensor (51) and at least one non-voice sensor (52) for collecting user data; A hub device (1) that receives voice data collected by at least one voice sensor (51) and non-voice data collected by at least one non-voice sensor (52), obtains first processed data based on processing the voice data, and obtains second processed data based on processing the non-voice data; A user device (2) that receives the first processing data and the second processing data from the hub device (1) via wireless communication, inputs the first processing data into a first machine learning model (21) to obtain cough information of the user, and calculates a first parameter (P1) representing a correlation between the first processing data and the second processing data; and A sleep management system including a server device (3) that receives the cough information from the user device (2) via wireless communication and controls at least one home appliance (4) registered in conjunction with the user device (2) based on the cough information.

2. In paragraph 1, The above user device (2) is, A sleep management system that obtains cough information of the user by inputting the first parameter (P1) and the second processing data produced above into a second machine learning model (22).

3. In paragraph 1, The above user device (2) is, A sleep management system that controls the hub device (1) to stop collecting the voice data based on receiving a command from the user to stop collecting the voice data from the voice sensor (51).

4. In paragraph 1, The above user device (2) is, Store the first parameter (P1) calculated above, A sleep management system that obtains the cough information by inputting the stored first parameter (P1) and the second processing data into a second machine learning module (22) based on receiving a command from the user to stop collecting the voice data from the voice sensor (51).

5. In paragraph 1, The cough information of the above user is: A sleep management system comprising at least one of a coughing point, a coughing period and a second parameter (P2) corresponding to a coughing sound.

6. In paragraph 5, The above user device (2) is, A sleep management system that determines the type of cough sound by inputting the second parameter (P2) into a third machine learning model (23).

7. In paragraph 6, The above user device (2) is, A sleep management system that provides a warning alarm for the suspected disease type to the user based on the type of cough sound being determined as the suspected disease type.

8. In paragraph 5, The above server device (3) is, A sleep management system that controls at least one home appliance (4) to perform a predetermined operation to alleviate the cough based on the fact that the cough cycle is shorter than a predetermined time.

9. In paragraph 1, At least one of the above home appliances (4) includes an air conditioner (41), The above server device (3) is, A sleep management system that controls the air conditioner (41) to increase the ambient temperature based on the cough information of the user.

10. In paragraph 1, At least one of the above home appliances comprises an air conditioner (41), The above server device (2) is, A sleep management system that stops the operation of the air conditioner (41) based on the cough information of the user.

11. In paragraph 1, At least one of the above home appliances (4) comprises a humidifier (42), The above server device (3) is, A sleep management system that operates the humidifier (42) to increase the relative humidity or increases the operating intensity of the humidifier (42) while it is in operation based on the cough information of the user.

12. In paragraph 1, At least one of the above home appliances (4) includes a dehumidifier (43), The above server device (3) is, A sleep management system that stops the operation of the dehumidifier (43) or reduces the operating intensity of the dehumidifier (43) while it is in operation based on the cough information of the user.

13. In paragraph 1, At least one of the above home appliances (4) includes an air purifier (44), The above server device (3) is, A sleep management system that operates the air purifier (44) or increases the operating intensity of the air purifier (44) in operation based on the cough information of the user.

14. In paragraph 1, At least one of the above home appliances (4) comprises a smart bed (45), The above server device (3) is, A sleep management system that controls the smart bed (45) so that the user's upper body is raised to a predetermined first angle based on the user's cough information.

15. In paragraph 1, At least one of the above home appliances (4) comprises a smart pillow (46), The above server device (3) is, A sleep management system that controls the smart pillow (46) so that the direction in which the user's face faces deviates from the vertical direction by a second angle determined in advance based on the cough information of the user.

Images