Automated operation of adjustable bed frame

Abstract

In one aspect, a method of the present disclosure may include analyzing (e.g., by a machine learning model) data retrieved from a database, where the data includes sleep factors, the sleep factors include two or more members selected from the group consisting of a sleep law of the user, sleep stage information of the user, a preference condition of the user for the adjustable chassis, and a preference condition of the user for the furniture article. The method may further include adjusting at least one feature of the adjustable base based on an analysis of the data, where the at least one feature includes (i) a position of at least a portion of the adjustable base, thereby controlling a sleep posture of the user, and / or (ii) a rocking motion of at least a portion of the adjustable frame, thereby controlling a sleep posture of the user. Therefore, the user is helped to fall asleep or keep falling asleep.

Description

BACKGROUND

[0001] Adjusting the positioning of a furniture article (e.g., a bed arrangement) can help improve the quality of a person’s activity on the furniture (e.g., sleeping in a bed). SUMMARY

[0002] One aspect of the disclosure provides a computer-implemented method comprising: (a) analyzing data retrieved from a database associated with a user for an adjustable foundation for a bed arrangement, wherein the data comprises sleep factors comprising two or more members selected from the group consisting of: a sleep routine of the user, sleep stage information of the user, a preference condition of the user for the adjustable foundation, and a preference condition of the user for a furniture article, and (b) adjusting at least one feature of the adjustable foundation based on the analysis of the data, wherein the at least one feature comprises: (i) a position of at least a portion of the adjustable foundation, thereby controlling a sleep posture of the user, and / or (ii) a rocking motion of at least a portion of the adjustable foundation, thereby helping the user fall asleep or stay asleep.

[0003] In some embodiments, wherein the sleep factors comprise three or more members selected from the group consisting of: the sleep routine, the sleep stage information, the preference condition of the user for the adjustable foundation, and the preference condition of the user for the furniture article.

[0004] In some embodiments of any of the preceding embodiments, the two or more members comprise the sleep routine of the user. In some embodiments of any of the preceding embodiments, the two or more members comprise the sleep stage information. In some embodiments of any of the preceding embodiments, the two or more members comprise the preference condition of the user for the adjustable foundation. In some embodiments of any of the preceding embodiments, the two or more members comprise the preference condition of the user for the furniture article.

[0005] In some embodiments of any of the preceding embodiments, the at least one feature comprises the position of at least the portion of the adjustable foundation. In some embodiments, adjusting the position comprises adjusting an angle between portions of the adjustable foundation.

[0006] In some embodiments of any of the preceding embodiments, the at least one feature comprises the rocking motion. In some embodiments, the rocking motion is selected from the group consisting of: in-plane motion, head-to-toe rocking, side-to-side rocking, rotational rocking, and vertical rocking.

[0007] In some embodiments of any of the preceding embodiments, the adjustable base includes a plurality of adjustable segments disposed adjacent to one another, wherein the plurality of adjustable segments are configured to be adjusted independently of one another based on the analysis of the data in (a). In some embodiments, the plurality of adjustable segments includes two or more members selected from the group consisting of a head segment, a back segment, a leg segment, and a foot segment. In some embodiments, the plurality of adjustable segments includes a first segment for the user and a second segment for an additional user.

[0008] In some embodiments of any of the preceding embodiments, the analysis in (a) includes analyzing the sleep factor by a machine learning model. In some embodiments, the machine learning model utilizes a neural network algorithm. In some embodiments, the neural network algorithm includes a convolutional neural network algorithm.

[0009] In some embodiments of any of the preceding embodiments, the adjustment in (b) is performed upon determining a presence of the user on or near the adjustable base. In some embodiments, the method includes determining the presence of the user based on user sensing data generated by a user sensor. In some embodiments, the user sensor is coupled to the adjustable base or the article of furniture. In some embodiments, the user sensor includes one or more members selected from the group consisting of a capacitive sensor, a piezoelectric sensor, and a temperature sensor.

[0010] In some embodiments of any of the preceding embodiments, the article of furniture is (i) a mattress or mattress cover, or (ii) a pillow or pillow cover.

[0011] In some embodiments of any of the preceding embodiments, the analysis in (a) includes determining a sleep score of the user when sleeping on the article of furniture, and wherein the adjustment in (b) is based at least in part on the sleep score of a previous sleep of the user.

[0012] In some embodiments of any of the preceding embodiments, the method further includes generating or updating an adjustable base profile of the user for subsequent use by the adjustable base, wherein the adjustable base profile includes a plurality of adjustments to at least the portion of the adjustable base. In some embodiments, the adjustable base profile further includes (i) a duration of each adjustment and / or (ii) an analysis of data corresponding to each adjustment.

[0013] One aspect of the disclosure provides a system comprising: a computer processor; and a computer memory coupled to the computer processor, wherein the computer memory comprises machine executable code that, when executed by the one or more computer processors, implements the method of any preceding claim.

[0014] In some embodiments, the system further comprises the adjustable base.

[0015] In some embodiments of any of the preceding embodiments, the system further comprises the article of furniture.

[0016] One aspect of the present disclosure provides a computer-implemented method comprising: (a) analyzing, by a machine learning model, data retrieved from a database associated with a user for an adjustable base for securing an article of furniture, wherein the data comprises two or more data types selected from the group consisting of user factors, sleep factors, and environmental factors, and (b) adjusting at least one feature of the adjustable base based on the analysis of the data, wherein the at least one feature comprises: (i) a position of at least a portion of the adjustable base, thereby controlling a sleep posture of the user, and / or (ii) a rocking motion of at least a portion of the adjustable frame, thereby assisting the user in falling asleep or staying asleep.

[0017] In some embodiments, the at least one feature comprises the position of at least the portion of the adjustable base. In some embodiments, adjusting the position comprises adjusting an angle between a plurality of portions of the adjustable base.

[0018] In some embodiments, the at least one feature comprises the rocking motion. In some embodiments, the rocking motion is selected from the group consisting of in-plane motion, head-to-toe rocking, side-to-side rocking, rotational rocking, and vertical rocking.

[0019] In some embodiments of any of the preceding embodiments, the adjustable base comprises a plurality of adjustable segments disposed adjacent to one another, wherein the plurality of adjustable segments are configured to be adjusted independently of one another based on the data analysis in (a). In some embodiments, the plurality of adjustable segments comprises two or more members selected from the group consisting of a head segment, a back segment, a leg segment, and a foot segment. In some embodiments, the plurality of adjustable segments comprises a first segment for the user and a second segment for an additional user.

[0020] In some embodiments of any of the preceding embodiments, the analysis in (a) comprises analyzing the data by a machine learning model. In some embodiments, the machine learning model utilizes a neural network algorithm. In some embodiments, the neural network algorithm comprises a convolutional neural network algorithm.

[0021] In some embodiments of any of the preceding embodiments, the two or more data types include the user factor. In some embodiments, the user factor includes one or more members selected from the group consisting of the user’s physiological gender, the user’s age, the user’s health condition, the user’s exercise information, and the user’s diet information (or food consumption information).

[0022] In some embodiments of any of the preceding embodiments, the two or more data types include the sleep factor. In some embodiments, the sleep factor includes one or more members selected from the group consisting of the user’s sleep schedule, one or more biosignals of the user, sleep stage information of the user, a preference condition of the user for the adjustable base, and a preference condition of the user for the furniture article.

[0023] In some embodiments of any of the preceding embodiments, the two or more data types include the environmental factor. In some embodiments, the environmental factor includes (i) a measured value of the environmental factor or a change thereof and / or (ii) a target value of the environmental factor.

[0024] In some embodiments of any of the preceding embodiments, the analysis in (a) includes analyzing the user factor, the sleep factor, and the environmental factor.

[0025] In some embodiments of any of the preceding embodiments, the adjustment in (b) is performed upon determining a presence of the user over or near the adjustable base. In some embodiments, the method includes determining the presence of the user based on user sensing data generated by a user sensor. In some embodiments, the user sensor is coupled to the adjustable base or the furniture article. In some embodiments, the user sensor includes one or more members selected from the group consisting of a capacitive sensor, a piezoelectric sensor, and a temperature sensor.

[0026] In some embodiments of any of the preceding embodiments, the furniture article is (i) a mattress or a mattress cover, or (ii) a pillow or a pillow cover.

[0027] In some embodiments of any of the preceding embodiments, the analysis in (a) includes determining a sleep score of the user when sleeping on the furniture article, and wherein the adjustment in (b) is based at least in part on the sleep score of the user’s previous sleep.

[0028] In some embodiments of any of the preceding embodiments, the method further includes generating or updating an adjustable base profile of the user for subsequent use by the adjustable base, wherein the adjustable base profile includes a plurality of adjustments to at least the portion of the adjustable base. In some embodiments, the adjustable base profile further includes (i) a duration of each adjustment and / or (ii) an analysis of data corresponding to each adjustment.

[0029] One aspect of the disclosure provides a system comprising: a computer processor; and a computer memory coupled to the computer processor, wherein the computer memory comprises machine executable code that, when executed by the one or more computer processors, implements the method of any preceding claim.

[0030] In some embodiments, the system further comprises the adjustable base.

[0031] In some embodiments of any of the preceding embodiments, the system further comprises the article of furniture.

[0032] Another aspect of the disclosure provides a non-transitory computer readable medium comprising machine executable code that, when executed by one or more computer processors, implements any of the methods above or elsewhere herein.

[0033] Another aspect of the disclosure provides a system comprising one or more computer processors and a computer memory coupled to the one or more computer processors. The computer memory comprises machine executable code that, when executed by the one or more computer processors, implements any of the methods above or elsewhere herein.

[0034] Additional aspects and advantages of the disclosure will become apparent to those skilled in the art from the following detailed description, wherein it is shown and described illustrative embodiments of the disclosure. It is recognized that the disclosure is capable of other and different embodiments, and its several details are capable of modification in various obvious respects, all without departing from the disclosure. Accordingly, the drawings and description are to be regarded as illustrative in nature, and not as restrictive.

[0035] Incorporated by Reference

[0036] All publications, patents, and patent applications mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent, or patent application was specifically and individually indicated to be incorporated by reference. To the extent there is a contradiction between the disclosure in the incorporated publications and the specification, the specification shall control. BRIEF DESCRIPTION OF DRAWINGS

[0037] The novel features of the application are set forth with particularity in the appended claims. A better understanding of the features and advantages of the present application will be obtained by reference to the following detailed description that sets forth illustrative embodiments, in which the principles of the application are utilized, and the accompanying drawings of which:

[0038] FIG. 1 An example graphical user interface (GUI) for providing a sleep score to a user is shown.

[0039] FIG. 2 A computer system programmed or otherwise configured to implement the methods provided herein is shown. DETAILED DESCRIPTION

[0040] While various embodiments of the application have been shown and described herein, it will be apparent to those skilled in the art that such embodiments are provided by way of example only. Numerous changes, substitutions and equivalents will occur to those skilled in the art without departing from the application. It is understood that various alternatives to the embodiments of the application described herein can be employed.

[0041] When the term“at least,”“greater than,” or“greater than or equal to” precedes the first numerical value of a series of two or more numerical values, the term“at least,”“greater than,” or“greater than or equal to” applies to each of the numerical values in the series of numerical values. For example, greater than or equal to 1, 2, or 3 is equivalent to greater than or equal to 1, greater than or equal to 2, or greater than or equal to 3.

[0042] When the term“at most,”“up to,”“no greater than,”“less than,” or“less than or equal to” precedes the first numerical value of a series of two or more numerical values, the term“no greater than,”“less than,” or“less than or equal to” applies to each of the numerical values in the series of numerical values. For example, less than or equal to 3, 2, or 1 is equivalent to less than or equal to 3, less than or equal to 2, or less than or equal to 1.

[0043] The terms“furniture,”“furniture article,” or“furniture piece” as used interchangeably herein generally refer to a bed, a pillow, a crib, a bassinet, a chair, a seat, a loveseat, a sofa, a divan, a headrest, a stool, a footstool, a bench, or any panel intended to be covered with fabric. The furniture article can be intended for use in a home, an office, a medical facility (e.g., a hospital), or a vehicle (such as an automobile, a truck, a boat, a bus, a train, etc.). The furniture article can be intended for use by at least one person (and / or at least one animal, such as a pet). The furniture article can be intended for use by at least about 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, or more people. The furniture article can be intended for use by at most about 10, 9, 8, 7, 6, 5, 4, 3, 2, or 1 person. In one example, the furniture article can be a bed, and the bed can include a variety of sizes including a twin bed, a longer twin bed, a full bed, a queen bed, a king bed, a super king bed, etc. In another example, the furniture article can be a baby warmer (i.e., a baby warmer) to provide heat at one or more temperatures to a baby.

[0044] The term “bed” or “bed arrangement” as used interchangeably herein can be a piece of furniture for sleeping or resting. The bed can include a mattress, a mattress protector, a pillow, and / or a covering thereof (e.g., a blanket), and / or a physical object configured to be disposed adjacent to (e.g., directly adjacent to) the mattress. One or more users can sleep or rest on and / or near a surface of the bed arrangement. The surface can be a top surface of the bed arrangement. The top surface of the bed arrangement can be flat or textured. The bed arrangement can be a mattress. The bed arrangement can be a mattress protector covering at least a portion of a surface of the mattress or at least one surface of the mattress. The bed arrangement can be a pillow. Alternatively or additionally, a user can sleep below a surface of the bed arrangement. The surface can be one or more surfaces of a covering such as, for example, a blanket. The blanket can be disposed on at least one part of the user. The bed arrangement can be a blanket. The bed arrangement can be a physical object that defines an environment (e.g., an object similar to a canopy or one or more walls that define an enclosed space that is smaller in size than a room that includes the mattress) that encloses at least a portion of the mattress. The bed arrangement can be a physical object that supports the mattress (e.g., a mattress platform, a headboard, and / or a sideboard).

[0045] The term “on” can mean that two objects (where a first object is “on” a second object) can be rotated such that the first object is above the second object relative to the ground. The two objects can be in direct or indirect contact, or can not be in contact at all.

[0046] The temperature of a piece of furniture (e.g., a bed arrangement such as a mattress, a mattress protector, a pillow, or a blanket) can be controlled (e.g., increased, decreased, or maintained). The temperature of at least a portion of the piece of furniture can be controlled. The temperature of the piece of furniture can be adjusted or maintained before, during, or after use by a user (e.g., sleeping or resting for a period of time). In one example, a bed can be pre-heated (e.g., automatically or according to a user preference) before use by a user. In some cases, the temperature of two or more portions of a piece of furniture (e.g., a bed) can be controlled separately or synchronously.

[0047] A furniture article (e.g., a bed) can use one or more sensors and / or one or more computer systems to detect sensing data (e.g., one or more biosignals) associated with a user. For example, the sensing data can be utilized to estimate or determine a state condition of the user before, during, or after use of the furniture article (e.g., determine a sleep stage, a sleep pattern, an illness, a disorder, snoring, etc. of the user). The sensors can or can not be part of the furniture article. The sensors can be part of the furniture article. The sensors can be part of a space (e.g., a room) surrounding the furniture article. The sensors can be worn by the user. Non-limiting examples of sensors can include capacitive sensors, temperature sensors, pressure sensors, piezoelectric sensors, sound sensors (e.g., microphones), accelerometers, fluid pressure sensors, etc. The sensing data can be at least partially utilized (e.g., analyzed) to determine (i) how to adjust a position of at least a portion of an adjustable bed foundation and / or (ii) how to regulate a temperature of the furniture article before, during, and after use of the furniture article by the user. In some cases, the sensors can be used to detect a property (e.g., a temperature, a movement, etc.) of the furniture article or such a property of an environment surrounding the furniture article. Sensors of a furniture article (e.g., coupled to, integrated into, embedded into, etc. the furniture article) as provided herein can detect sensing data when in contact (e.g., direct or indirect contact) with a subject or when not in contact with the subject.

[0048] A furniture article can include from about one zone to about 20 zones. In some cases, a furniture article can include at least or up to about one zone, at least or up to about two zones, at least or up to about three zones, at least or up to about four zones, at least or up to about five zones, at least or up to about six zones, at least or up to about seven zones, at least or up to about eight zones, at least or up to about nine zones, at least or up to about ten zones, at least or up to about 11 zones, at least or up to about 12 zones, at least or up to about 13 zones, at least or up to about 14 zones, at least or up to about 15 zones, at least or up to about 16 zones, at least or up to about 17 zones, at least or up to about 18 zones, at least or up to about 19 zones, or at least or up to about 20 zones. In some cases, each of the one or more zones can include a temperature control unit. In some cases, a temperature of each of the one or more zones can be independently adjusted.

[0049] In some embodiments, sensors of a furniture article can be disposed within a portion of the furniture article that corresponds to a target body part of a user, such as a head, an arm, a leg, a torso, an upper body, a lower body, etc.

[0050] The term "sleep stage" as used herein can refer to light sleep, deep sleep, or rapid eye movement ("REM") sleep. There can be two main sleep stages: non-REM sleep and REM sleep. A person can first experience non-REM sleep, and then experience a shorter period of REM sleep. In some cases, a person can experience a continuous cycle of non-REM sleep and REM sleep. Non-REM sleep can be in three stages. Each stage can last 5 to 15 minutes. A person can experience all three stages before entering REM sleep. In the first stage, a person's eyes can be closed, but the person can easily wake up. This stage can last 5 to 10 minutes. This stage can be considered light sleep. In the second stage, a person can be in light sleep. The person's heart rate can slow down, and the person's body temperature can drop. The person's body can be preparing to enter deep sleep. This stage can also be considered light sleep. The third stage can be a deep sleep stage. During this stage, a person can be harder to wake up, and if the person does wake up, the person can feel disoriented for a few minutes. During the deep stage of non-REM sleep, the body can repair and regenerate tissues, build bone and muscle, and strengthen the immune system. REM sleep can occur after a person has been asleep for 90 minutes. In some cases, a person can dream during REM sleep. The initial period of REM sleep can typically last 10 minutes. Any later periods of REM sleep can become longer, and the final period of REM sleep can last up to about an hour. During REM sleep (e.g., during the final period of REM sleep), a person's heart rate and breathing can speed up. Because the brain is more active, a person can experience high-intensity dreams during REM sleep. REM sleep can affect the learning of certain psychological skills.

[0051] A "sleep pattern" as used herein can indicate a recurrence or change in (i) one or more biosignals and / or (i) one or more sleep stages of a user of a bed. A sleep pattern can be described over a period of time (e.g., 0.5 hours, 1 hour, 2 hours, 3 hours, 4 hours, 5 hours, 6 hours, etc.) along with a count of biosignals or sleep stages. A sleep pattern can include a preferred setting of a biosignal or a sleep stage of a user. A preferred setting of a biosignal can include a type of biosignal along with a preferred value or range of values of the biosignal (e.g., a preferred body temperature or range of body temperatures of a user). A preferred setting of a sleep stage can include a type of sleep stage along with a preferred value or range of values of the sleep stage.

[0052] The user's disorder can be a sleep disorder. Non-limiting examples of sleep disorders can include sleep disorders such as insomnia, idiopathic hypersomnia (e.g., narcolepsy, idiopathic hypersomnia, recurrent hypersomnia, post-traumatic hypersomnia, menstruation-related hypersomnia), sleep breathing disorders (e.g., sleep apnea, snoring, upper airway resistance syndrome), circadian rhythm sleep disorders (e.g., delayed sleep phase disorder, advanced sleep phase disorder, non-24-hour sleep-wake disorder), parasomnias (e.g., enuresis, bruxism, night terrors, exploding head syndrome, sleep terror disorder, rapid eye movement (REM) sleep behavior disorder, dream enactment disorder), jet lag, restless leg syndrome, sleep deprivation (e.g., for days, weeks, months, etc.), and the like.

[0053] In some embodiments, the article of furniture can be a bed (e.g., a mattress or a mattress cover), and a temperature of the bed (e.g., based at least in part on the sensed data) can be controlled to help the user fall asleep, help the user wake from sleep, promote improved sleep quality, treat or improve a disorder while the user is sleeping, and the like.

[0054] The terms "biological signal" and "bio signal" can be used interchangeably. Examples of biological signals can include cardiac signals (e.g., heart rate variability (HRV), heart rate (e.g., resting heart rate), time elapsed between two successive R-wave peaks (RR interval), or sounds), respiration (breathing) signals (e.g., respiration rate or sounds), motion, temperature, movement, perspiration, sounds, neural activity, blood oxygen (e.g., measured by direct or indirect contact with the user's skin), and the like. The article of furniture (e.g., a bed) can be capable of detecting one or more biological signals of a user. For example, the sensed data obtained by the sensors can include ballistocardiogram (BCG) data or similar data, or electrocardiogram (ECG) data or similar data. The article of furniture can be capable of adjusting a property of the article of furniture (e.g., a temperature or movement of the article of furniture, such as a vibration, a geometric configuration, and the like) to control (e.g., increase, decrease, or maintain) a biological signal of a user of the article of furniture.

[0055] The terms“real time” or“real-time” as used interchangeably herein generally refer to an event (e.g., an operation, a process, a method, a technique, a calculation, an analysis, an optimization, etc.) that is performed using recently obtained (e.g., collected or received) data. Examples of events can include, but are not limited to, analyzing sensing data (e.g., one or more biosignals), adjusting a state of a furniture article, etc. In some cases, a real-time event can be performed almost immediately or within a sufficiently short time span, such as, for example, within at least 0.0001 milliseconds, 0.0005 milliseconds, 0.001 milliseconds, 0.005 milliseconds, 0.01 milliseconds, 0.05 milliseconds, 0.1 milliseconds, 0.5 milliseconds, 1 milliseconds, 5 milliseconds, 0.01 seconds, 0.05 seconds, 0.1 seconds, 0.5 seconds, 1 seconds, or longer. In some cases, a real-time event can be performed almost immediately or within a sufficiently short time span, such as, for example, within at least 1 second, 0.5 seconds, 0.1 seconds, 0.05 seconds, 0.01 seconds, 5 milliseconds, 1 milliseconds, 0.5 milliseconds, 0.1 milliseconds, 0.05 milliseconds, 0.01 milliseconds, 0.005 milliseconds, 0.001 milliseconds, 0.0005 milliseconds, 0.0001 milliseconds, or less.

[0056] System for controlling an adjustable base and method thereof

[0057] Various aspects of the present disclosure provide systems and methods thereof for adjusting one or more features of an adjustable base (or adjustable bed frame as used interchangeably herein) to secure a user of a furniture article as provided herein. In some embodiments, the one or more features of the adjustable base can include a position of at least a portion of the adjustable base, thereby controlling a sleep posture of the user when on the furniture article. In some embodiments, the one or more features of the adjustable base can include a rocking motion of at least a portion of the adjustable base, thereby helping the user fall asleep or stay asleep when on the furniture article. In some embodiments, the one or more features of the adjustable base can include a rocking motion of at least a portion of the adjustable base to help wake up a user sleeping on the furniture article.

[0058] In some embodiments, the adjustment of the one or more features of the adjustable base can be performed (e.g., automatically performed without requiring any active control by the user) before, during, and / or after the user uses the adjustable base and / or the furniture article. For example, the adjustable base can secure a mattress for the user to sleep on, and the adjustment of the one or more features of the adjustable base can be performed before, during, and / or after the user sleeps on the mattress (or a mattress cover disposed on the mattress).

[0059] In some embodiments, the adjustment of one or more features of the adjustable base can be performed prior to the user sitting on the article of furniture (e.g., a mattress), for example, based on an analysis (e.g., via a machine learning model) of past data retrieved from a database. The past data can be sensor data previously detected (e.g., by one or more sensors of the adjustable base and / or the article of furniture) and stored during one or more previous uses of the article of furniture by the user (e.g., the user’s sleep the previous night or nights). Alternatively or additionally, the past data can be different data provided by the user (e.g., data unrelated to sleep), or data retrieved from a database of a user device other than the adjustable base or the article of furniture (e.g., a mobile phone, a tablet computer, a smart watch, etc.).

[0060] In some embodiments, the adjustment of one or more features of the adjustable base can be performed after the user sits on the article of furniture (e.g., a mattress or a mattress cover), for example, based on an analysis (e.g., via a machine learning model) of past data retrieved from a database as provided herein and / or sensed data detected during the user’s current use of the adjustable base or the article of furniture (e.g., the current sleep).

[0061] In some embodiments, the adjustment of one or more features of the adjustable base can be performed based on an assessment of the user’s presence on or near the adjustable base. The assessment of the user’s presence can include determining that the user is located on or near the adjustable base. Alternatively, the assessment of the user’s presence can include determining that the user is not located on or near the adjustable base. This assessment can be performed based on sensed data generated by one or more sensors of the adjustable base or the article of furniture. For example, this sensor(s) can be disposed within the adjustable base, the mattress, and / or the mattress cover. Alternatively, this assessment can be performed based on sensed data generated by (i) one or more environmental sensors disposed near the adjustable base and / or (ii) a user device (e.g., a mobile phone, a tablet computer, a smart watch, etc.) as provided herein.

[0062] One or more factors for controlling operation of an adjustable base

[0063] In some embodiments, the operation of the adjustable base (e.g., automatically adjusting (i) the position of at least a portion of the adjustable base, thereby controlling the user’s sleep posture and / or (ii) the rocking motion of at least a portion of the adjustable frame, thereby helping the user fall asleep or stay asleep) can be controlled based on user factors, sleep factors, environmental factors, combinations thereof, and / or an analysis thereof. The user factors, sleep factors, and / or environmental factors can be collected prior to and / or during the user’s use of the article of furniture and stored in a database.

[0064] Operation of the adjustable base can be controlled based on user factors and optionally based on sleep factors and / or environmental factors. Operation of the adjustable base can be controlled based on sleep factors and optionally based on user factors and / or environmental factors. Operation of the adjustable base can be controlled based on environmental factors and optionally based on user factors and / or sleep factors.

[0065] In some embodiments, user factors, sleep factors, and / or environmental factors can be provided by a user via a portal, such as a graphical user interface (GUI) of a user application on a user device (e.g., a computer, a mobile phone, a smart watch, smart glasses, etc.) that is operably coupled to a computer processor as provided herein.

[0066] In some embodiments, user factors, sleep factors, and / or environmental factors (i) can not be provided by a user personally via a portal, and (ii) can be collected via one or more sensors that are operably coupled to the article of furniture or the article of furniture environment. Such sensor(s) as provided herein can include, for example, a capacitive sensor, a temperature sensor, a pressure sensor, a piezoelectric sensor, a sound sensor (e.g., a microphone), an accelerometer, a liquid pressure sensor, etc. The one or more sensors can be provided as part of the article of furniture or as a separate device from the article of furniture. For example, the article of furniture can be a bed device, and the one or more sensors can be provided as part of (i) a headboard, (ii) a side panel or side wall, (iii) a platform for securing a mattress, (iv) a canopy structure for defining a small environment (e.g., an enclosed structure) around the bed device and smaller than the size of a room, or a combination thereof. Alternatively or additionally, the one or more sensors can be provided as part of the adjustable base.

[0067] In some embodiments, any information or data associated with user factors, sleep factors, and / or environmental factors can be stored in and retrieved from a database (e.g., a cloud database) in digital communication with a computer processor as provided herein.

[0068] In some embodiments, a computer processor can utilize one or more AI models (e.g., machine learning models as provided herein) to control (e.g., automatically control) operation of the adjustable base, or make decisions that control operation of the adjustable base as provided herein. For example, one or more algorithms can be utilized to control operation (e.g., generate operational parameters such as output levels or modes, operational times, etc.) of one or more environmental modulators as provided herein.

[0069] In some embodiments, this factor (e.g., a user factor, a sleep factor, and / or an environmental factor) can be (i) a current factor collected, measured, and / or analyzed during a current use of the furniture article, (ii) a past factor collected, measured, and / or analyzed from one or more past uses of the furniture article by the user, (iii) a desired factor for the current use of the furniture article, e.g., provided by the user via the GUI, and / or (iv) a target factor for the current use of the furniture article, e.g., based on an analysis of the current factor and / or the past factor as provided herein. In some past uses, the one or more past uses can include at least or at most about 1 past use, 2 past uses, 3 past uses, 4 past uses, 5 past uses, 6 past uses, 7 past uses, 8 past uses, 9 past uses, 10 past uses, 15 past uses, 20 past uses, 30 past uses, 40 past uses, 50 past uses, 60 past uses, 70 past uses, 80 past uses, 90 past uses, or 100 past uses. In some cases, the multiple past uses (e.g., 3 past uses) can or can not be consecutive uses. In some past uses, the one or more past uses can include at least or at most about 1 day in the past, 2 days in the past, 3 days in the past, 4 days in the past, 5 days in the past, 6 days in the past, 7 days in the past, 8 days in the past, 9 days in the past, 10 days in the past, 15 days in the past, 20 days in the past, 30 days in the past, 40 days in the past, 50 days in the past, 60 days in the past, 70 days in the past, 80 days in the past, 90 days in the past, 4 months in the past, 5 months in the past, 6 months in the past, 7 months in the past, 8 months in the past, 9 months in the past, 10 months in the past, 11 months in the past, or 12 months in the past. In some cases, the past factor can be raw data or processed data thereof (e.g., average, conditional average, weighted average, arithmetic mean, geometric mean, harmonic mean, etc.). For example, the past factor can be an average sleep time or sleep latency or usage of the bed arrangement over the past three days by the user.

[0070] In some embodiments, the user factor, the sleep factor, and / or the environmental factor can be based on factual information associated with the user, e.g., based on (i) information or data provided by the user (e.g., via a GUI) and / or (ii) information or data measured by one or more sensors as provided herein, where such information or data is obtained during a current use or a previous use of the furniture article. For example, the user factor can include a desired sleep time (or duration) for the current use of the bed arrangement as provided by the user. In another example, the sleep factor can be based on a current biosignal level (e.g., heart rate) or a sleep stage (e.g., REM sleep or deep sleep) of the user measured / determined while the user is sleeping. In some embodiments, the user factor, the sleep factor, and / or the environmental factor can be based on a target value thereof, e.g., generated by the computer processor. For example, the user factor can include a sleep time (or duration) of the user for one or more previous uses of the bed arrangement. In another example, the sleep factor can be based on a target biosignal level (e.g., a target heart rate generated based on past historical data) or a target sleep stage (e.g., REM sleep or deep sleep) of the user.

[0071] In some embodiments, the user factor can include one or more members including a physiological gender of the user, an age of the user, a health condition of the user, exercise information of the user, diet information (or food consumption information) of the user, and / or a combination thereof. In some cases, the algorithm can utilize (e.g., analyze) multiple members of the user factor and / or multiple subtypes of each member of the user factor. The algorithm can be trained to assign equal importance weight or different importance weight to the multiple members and / or the multiple subtypes (e.g., a difference in importance between two different members and / or between multiple subtypes is at least or at most about 1%, 2%, 5%, 10%, 20%, 30%, 40%, 50%, 60%, 70%, 80%, 90%, 95%, or 99%).

[0072] In some embodiments, the health condition of the user can be a health status of the user, which can be a general classification such as, for example, “normal” (or “healthy”) or “abnormal” (or “unhealthy”). In some embodiments, the health condition of the user can be a physical health condition (e.g., a cold, a fever, fatigue, menopause, a disease type, etc.) or a mental health condition (e.g., stress, anxiety, etc.).

[0073] In some embodiments, the user's health condition can be objective. For example, the health condition can be provided in the user's own verbal or written description, which can be analyzed via one or more computer algorithms, such as, for example, a natural language processing (NLP) algorithm and / or a convolutional neural network (CNN) algorithm for image processing. In some embodiments, the user's health condition can be based on a conclusion provided by a healthcare provider (e.g., a doctor) to a computer processor. In some embodiments, the user's health condition can be determined based on, for example, sensed data (e.g., biosignals) measured by one or more sensors as provided herein when the user uses the furniture article during current or past use of the furniture article.

[0074] In some embodiments, the user's exercise information and / or diet information can be objective. For example, the exercise information and / or diet information can be provided in the user's own verbal or written description, which can be analyzed via one or more computer algorithms as provided herein (e.g., NLP, CNN, etc.). In some embodiments, the exercise information and / or diet information can be retrieved from a database associated with a user device as provided herein, such as a smartwatch that includes one or more sensors to track the user's movement or exercise during or prior to the user's use of the furniture article. Non-limiting examples of exercise information can include duration and / or frequency of walking, running, swimming, basketball, baseball, hockey, tennis, gymnastics, standing. Non-limiting examples of diet information can include type of food consumed by the user (e.g., basic food, pre-packaged meal, home-cooked meal, fruit, vegetable, etc.), amount of food consumed by the user, frequency of food consumed by the user, and / or time of day when food is consumed.

[0075] In some embodiments, the sleep factors can include one or more members including sleep regularity, one or more biosignals of the user (e.g., biometrics), sleep stage information of the user, preferred conditions of the bed device by the user during sleep, and / or combinations thereof. In some cases, the algorithm can utilize (e.g., analyze) multiple members of the sleep factors and / or multiple subtypes of each member of the sleep factors. The algorithm can be trained to assign equal importance weight or different importance weight to the multiple members and / or the multiple subtypes (e.g., difference in importance between two different members and / or between multiple subtypes is at least or at most about 1%, 2%, 5%, 10%, 20%, 30%, 40%, 50%, 60%, 70%, 80%, 90%, 95%, or 99%).

[0076] In some embodiments, the sleep factor can include a sleep regularity. The sleep regularity can include one or more members including a bedtime, a sleep time, a sleep latency, a wake-up time, and combinations thereof. In some cases, the bedtime can be a time at which the user begins to use the bed arrangement, such as a time at which the user gets into bed. In some cases, the sleep time can be a time at which the user transitions from being awake to being asleep, for example, a time at which the user first enters light sleep in a particular day while in bed. For example, based on analysis of sensed data from one or more sensors (e.g., heart rate data from a pressure sensor such as a piezoelectric sensor), the time of entering light sleep can be determined. In some cases, the sleep latency can be a duration between the bedtime and the sleep onset. In some cases, the wake-up time can be a time at which the user transitions from being asleep (e.g., in one or more sleep stages) to being awake. Alternatively, the wake-up time can be a predetermined alarm time (e.g., determined by the user or the computer processor).

[0077] In some embodiments, the sleep factor can include one or more biosignals (as provided herein) of the user, or an analysis thereof. In some cases, the one or more biosignals can include sensed data collected during or in the current use of the article of furniture (e.g., the bed arrangement). For example, the sensed data can be measured or collected substantially in real-time. Alternatively or additionally, the sensed data can be collected during the current use and at least or at most about 5 minutes, 10 minutes, 15 minutes, 20 minutes, 30 minutes, 40 minutes, 50 minutes, 60 minutes, 70 minutes, 80 minutes, 90 minutes, 100 minutes, 110 minutes, 120 minutes, 3 hours, 4 hours, 5 hours, 6 hours, 7 hours, or 8 hours before the computer processor uses the sensed data (e.g., processes or analyzes the sensed data). In some cases, the sleep factor can include an analysis of the one or more biosignals. The sleep factor can be based on whether the current sensed data of the biosignals of the user is within or outside of a predetermined range (e.g., mean or normal range) of the past sensed data of the biosignals of the user. For example, the biosignals can be a heart rate (e.g., resting heart rate, HRV), and the sleep factor can be whether the current heart rate of the user is within a predetermined range of the heart rate. In another example, the biosignals can be a respiration rate, and the sleep factor can be whether the current respiration rate of the user is within a predetermined range of the respiration rate (e.g., between about 12 and about 20 breaths per minute).

[0078] In some embodiments, the sleep factor can include one or more sleep stage information (as provided herein) of the user, or an analysis thereof. In some cases, the sleep factor can include one or more information about a sleep stage, such as a start time of the sleep stage, a duration of the sleep stage, a frequency of the sleep stage (e.g., within a current sleep, or a daily average of multiple previous sleeps), etc. In some cases, the computer processor can determine whether the start time of the sleep stage is at least or at most about 5 minutes, 10 minutes, 15 minutes, 20 minutes, 30 minutes, 40 minutes, 50 minutes, 60 minutes, 70 minutes, 80 minutes, 90 minutes, 100 minutes, 110 minutes, or 120 minutes earlier or later than a reference time. Non-limiting examples of the reference time can include a predetermined time determined by the computer processor; one or more sleep schedule information, such as a bedtime, a sleep time, etc.; a start of a previous sleep stage, etc.

[0079] In some cases, the sleep stage information can include a current sleep stage of the user, e.g., determined in substantially real-time. In some cases, the sleep stage information can include a past sleep stage. The past sleep stage can be from a current sleep night of the user and / or from a past sleep night of the user. For example, the sleep factor can be which type of sleep stage the user was in immediately prior to the current sleep stage.

[0080] In some cases, the sleep stage information can include an amount or total duration of a particular sleep stage (e.g., deep sleep, REM sleep) that the user needs or is suspected to need during the current sleep / night. The amount or total duration of the particular sleep stage can be provided by the user, or can be determined by the computer processor, by one or more AI models (e.g., machine learning models) as provided herein, based on past sleep of the user or past sleep stage information data of past use of the bed device. For example, the amount or total duration of the particular sleep stage can be based on an amount or total duration of the same particular sleep stage experienced by the user during a sleep of a previous night (or a sleep of previous nights). The amount or total duration of the particular sleep stage that the user needs (e.g., determined by the computer processor) can be at least or at most about 1%, 5%, 10%, 15%, 20%, 30%, 40%, 50%, 60%, 70%, 80%, 90%, 100%, 110%, 120%, 150%, 200%, 250%, 300%, 400%, or 500% more than a sleep of a previous night (or an average or median of multiple previous sleeps); or can be at least or at most about 1%, 5%, 10%, 15%, 20%, 30%, 40%, 50%, 60%, 70%, 80%, 90%, 100%, 110%, 120%, 150%, 200%, 250%, 300%, 400%, or 500% less than a sleep of a previous night (or an average or median of multiple previous sleeps).

[0081] In some cases, the sleep stage information can include a sleep stage pattern (or trend) for the user’s current night’s sleep (e.g., so far) and / or for one or more previous nights’ sleep. The subject can experience at least one cycle of multiple different sleep stages, such as experiencing light sleep, deep sleep, and REM sleep in succession. The subject can experience multiple cycles of different sleep stages, each cycle including two or more members of light sleep, deep sleep, and / or REM sleep. In some cases, the pattern of sleep stages can include a proportion of the total duration of a particular sleep stage (e.g., deep sleep or REM sleep) relative to the total duration of the sleep, and / or relative to the total duration of different sleep stages (e.g., total duration of deep sleep vs. total duration of REM sleep). For example, the computer processor can determine that the proportion of the total duration of a particular sleep stage for the current night needs to increase (or decrease) by at least or at most about 1%, 5%, 10%, 15%, 20%, 30%, 40%, 50%, 60%, 70%, 80%, 90%, 100%, 110%, 120%, 150%, 200%, 250%, 300%, 400%, or 500% compared to one or more past nights. In some cases, the pattern of sleep stages can include a number of occurrences of a particular sleep stage within multiple cycles per night. For example, the computer processor can determine that the number of occurrences of a particular sleep stage for the current night needs to increase (or decrease) by at least or at most about 1x, about 2x, about 3x, about 4x, or about 5x compared to one or more past nights. In some cases, the pattern of sleep stages can include a number of cycles per night. For example, the computer processor can determine that the number of cycles for the current night needs to increase (or decrease) by at least or at most about 1 cycle, 2 cycles, 3 cycles, 4 cycles, or 5 cycles compared to one or more past nights. In some cases, the sleep stage information can include a sleep pattern for the user, as provided herein.

[0082] In some embodiments, the sleep factors can include one or more target conditions of the bed arrangement of the user, e.g., at a particular time during sleep. The target conditions can be predetermined by the user (e.g., via a GUI). The target conditions can be predetermined by the computer processor, e.g., a predetermined schedule of target conditions for the night. Non-limiting examples of target conditions can include a target temperature of the bed arrangement (e.g., regulated by a temperature controller coupled or in fluid communication with the bed arrangement, such as via one or more fluid channels within the bed arrangement), a target temperature of the bed arrangement environment (e.g., regulated by an HVAC system), a configuration or angle of the bed arrangement (e.g., incline or decline of an adjustable bed arrangement), etc. In some embodiments, the one or more target conditions of the bed arrangement can include one or more target features of a fixed bed arrangement of the adjustable base, such as (i) a target position of at least a portion of the adjustable base (e.g., predetermined by the user) and / or (ii) a target rocking motion of at least a portion of the adjustable base (e.g., predetermined by the user).

[0083] In some embodiments, the environmental factors can include one or more members including temperature (e.g., which can or can not be the same as the temperature of the bed arrangement itself), air quality, humidity, pressure, oxygen level, nitrogen level, noise, light (e.g., brightness, darkness, specific wavelengths of light), combinations thereof, and / or changes thereof. In some cases, a change in an environmental factor can be determined by comparing at least two environmental factor data (e.g., in terms of data collection time) that are at least or at most about 1 minute, 2 minutes, 3 minutes, 4 minutes, 5 minutes, 6 minutes, 7 minutes, 8 minutes, 9 minutes, 10 minutes, 15 minutes, 20 minutes, 30 minutes, 40 minutes, 50 minutes, 60 minutes, 70 minutes, 80 minutes, 90 minutes, 100 minutes, 120 minutes, 2.5 hours, 3 hours, 4 hours, 5 hours, 6 hours, 7 hours, 8 hours, 12 hours, 16 hours, 24 hours, 36 hours, 48 hours, 3 days, 4 days, 5 days, 6 days, or 7 days apart. In some cases, the environmental factor can be a target environmental factor, e.g., predetermined by the user (e.g., via a GUI) or predetermined by the computer processor, e.g., a predetermined schedule of operation of the adjustable base for the night. In some cases, the environmental factor can be a degree of difference (or similarity) between a current measurement of the environmental factor (e.g., a substantially real-time measurement) and a target value of the environmental factor for that time, e.g., whether the current measurement of the environmental factor is greater than (or less than) the target value by at least or at most about 1%, 2%, 5%, 10%, 20%, 30%, 40%, 50%, 60%, 70%, 80%, 90%, 95%, or 99%. In some cases, the system can include or be operably coupled to (i) one or more environmental sensors configured to detect this environmental factor and / or (ii) a database (e.g., a cloud database) including information associated with this environmental factor.

[0084] Additional details

[0085] In some embodiments, data provided by a user or collected by a processor (e.g., from a database or from one or more sensors as provided herein) can be processed by a computer processor, e.g., to perform (e.g., automatically via a computer processor) any one or more methods as provided herein, such as controlling operation of an adjustable base.

[0086] Non-limiting examples of data processing operations can include filtering, linear filtering, non-linear filtering, folding, grouping, energy calculation, low pass filtering, band pass filtering, high pass filtering, median filtering, rank filtering, quartile filtering, percentile filtering, mode filtering, finite impulse response (FIR) filtering, infinite impulse response (IIR) filtering, moving average (MA) filtering, autoregressive (AR) filtering, autoregressive moving average (ARMA) filtering, selective filtering, adaptive filtering, interpolation, decimation, sub-sampling, up-sampling, re-sampling, time correction, time base correction, phase correction, amplitude correction, phase clean-up, amplitude clean-up, matched filtering, enhancement, recovery, de-noising, smoothing, signal conditioning, enhancement, recovery, spectral analysis, linear transformation, non-linear transformation, inverse transformation, frequency transformation, inverse frequency transformation, Fourier transformation (FT), discrete time FT (DTFT), discrete FT (DFT), fast FT (FFT), wavelet transformation, Laplace transformation, Hilbert transformation, Hadamard transformation, trigonometric transformation, sinusoidal transformation, cosinusoidal transformation, discrete cosine transformation (DCT), power-of-two transformation, sparse transformation, graph-based transformation, graph signal processing, fast transformation, transformation with zero padding, circular padding, padding, zero padding, feature extraction, decomposition, projection, orthogonal projection, non-orthogonal projection, overcomplete projection, eigen decomposition, singular value decomposition (SVD), principal component analysis (PCA), independent component analysis (ICA), grouping, ranking, thresholding, soft thresholding, hard thresholding, clipping, soft clipping, first derivative, second derivative, higher order derivative, convolution, multiplication, division, addition, subtraction, integration, maximization, minimization, least mean square error, recursive least square, constrained least square, batch least square, least absolute error, least mean square deviation, least absolute deviation, local maximization, local minimization, cost function optimization, neural network, recognition, labeling, training, clustering, machine learning, supervised learning, unsupervised learning, semi-supervised learning, self-supervision, comparison to another TSCI, similarity score calculation, quantization, vector quantization, matching pursuit, compression, encryption, encoding, storage, transmission, normalization, time normalization, frequency domain normalization, classification, clustering, labeling, tagging, learning, detection, estimation, learning network, mapping, remapping, spreading, storing, retrieving, transmitting, receiving, representing, merging, combining, partitioning, tracking, monitoring, matched filtering, Kalman filtering, particle filter, interpolation, extrapolation, histogram estimation, importance sampling, Monte Carlo sampling, compressive sensing, representing, merging, combining, partitioning, scrambling, error protection, forward error correction, not performing any operation, time-varying processing, conditional averaging, weighted averaging, arithmetic mean, geometric mean, harmonic mean, selected frequency averaging, antenna link averaging, logical operation, permutation, combination, ranking, AND, OR, XOR, union, intersection, vector addition, vector subtraction, vector multiplication, and vector division.

[0087] In some cases, one or more of the data processing operations provided herein can be performed via one or more machine learning models (e.g., one or more trained classifiers). In some cases, one or more of the data processing operations provided herein can be performed by a computer processor without utilizing a machine learning model.

[0088] In some cases, more than one model can be used in parallel, such as in an ensemble model. In some cases, more than one model can be used, where some of the models are pre-trained. In some cases, more than one model can take more than one type of input data (e.g., image data, audio data, tabular data, textual data). In some cases, a model that takes more than one type of data can be a multi-modal artificial intelligence model (e.g., a large language model, a diffusion model).

[0089] In some embodiments, a system as provided herein can include at least one sensor operably coupled to the article of furniture. The at least one sensor can be attached to the article of furniture, can be part of the article of furniture (e.g., disposed and concealed in an interior portion of the article of furniture), or disposed proximate or adjacent to the article of furniture. The at least one sensor can be configured to detect sensing data associated with a user of the article of furniture. The sensing data can be associated with or indicative of a biological signal of the user. The sensing data can include single biological signal data or multiple biological signal data. The sensing data can include a single type of biological signal (e.g., sound, vibration, temperature, etc.) or multiple different types of biological signals (e.g., sound and vibration, sound and temperature, vibration and temperature, etc.). Alternatively or additionally, any of the sensors as provided herein can be coupled to an adjustable base.

[0090] In some embodiments, the system can include a controller (e.g., a computer processor) configured to adjust a condition / operation of the article of furniture, adjustable base, or other device (e.g., one or more environmental modulators, one or more speakers, one or more coverings, one or more light sources, etc.) based at least in part on data (such as, for example, user factors, sleep factors, environmental factors, etc.). The controller can be configured to generate a decision to adjust the condition / operation of the article of furniture, adjustable base, or other device (e.g., generate a control signal to adjust the condition / operation) substantially in real-time or shortly after the at least one sensor detects or generates the sensed data. In some cases, a duration or time difference (e.g., a short time span) between a time at which the controller makes the decision and a time at which the at least one sensor detects or generates the sensed data can be at least or at most about 1 second, at least or at most about 2 seconds, at least or at most about 5 seconds, at least or at most about 10 seconds, at least or at most about 20 seconds, at least or at most about 30 seconds, at least or at most about 1 minute, at least or at most about 2 minutes, at least or at most about 5 minutes, at least or at most about 10 minutes, at least or at most about 15 minutes, at least or at most about 20 minutes, at least or at most about 25 minutes, at least or at most about 30 minutes, at least or at most about 40 minutes, at least or at most about 50 minutes, at least or at most about 60 minutes, at least or at most about 1.5 hours, or at least or at most about 2 hours. Alternatively, the decision for the controller to adjust the condition / operation of the article of furniture, adjustable base, or other device and the at least one sensor to detect the sensed data can not and need not occur in real-time or within a short time span of each other, as described herein.

[0091] In some embodiments, upon determining that the user can be experiencing a target human condition (e.g., a disease such as heart disease, or a target sleep condition such as snoring, sleep apnea, etc.), the controller can make a decision to adjust the condition / operation of the article of furniture, adjustable base, or other device, for example, to treat or improve this undesirable condition of the user.

[0092] In some embodiments, the human condition can be a desirable condition. In some embodiments, the human condition can be an undesirable condition. In some cases, the undesirable condition can include a sleep disorder as provided herein.

[0093] In some embodiments, the controller can utilize at least one classifier (e.g., at least or at most about 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, or more classifiers) to make decisions as provided herein, e.g., to analyze user factors, sleep factors, and / or environmental factors, etc. The classifier can be configured to receive inputs including at least user factors, sleep factors, and / or environmental factors, and provide outputs including, but not limited to, instructions for controlling operation of one or more environmental modulators, one or more speakers, one or more coverings, one or more light sources, etc.

[0094] In some embodiments, the controller can be configured to determine (e.g., via use of at least one classifier and based on detected user signals) (i) a number of users (e.g., one or two users) that are currently present on or near the article of furniture (e.g., on top of the bed arrangement), (ii) an approximate or substantially precise location of each user relative to the article of furniture (e.g., on the left side of the bed arrangement, on the right side of the bed arrangement, etc.), and / or (iii) an identity of each user, wherein the identity is based on information about the user that was previously stored in a database.

[0095] In some embodiments, the article of furniture or adjustable foundation can be associated with a user profile of a user that is stored in a database (e.g., a cloud database). The user profile can be accessible (e.g., readable, editable, etc.) by the controller as provided herein. The user can access (e.g., read, edit, etc.) the user profile via a graphical user interface (GUI) of a user application installed on a user device. As described herein, the user profile can include one or more adjustment profiles for the article of furniture, adjustable foundation, or conditions of the user’s environment. The user profile can include any additional information about the user including, but not limited to, biological sex, age, height, weight, medical history, family history, family member identity, genetic information, blood information, information about additional articles of furniture for the same user or other users (e.g., other members of a group as provided herein), etc. The additional information can be provided by the user. The additional information can be retrieved from another database associated with the user (e.g., a database associated with the user’s smartwatch, a database associated with the user’s genetic analysis, such as 23andMe, etc.).

[0096] In some embodiments, the controller can be configured to calculate a score indicative of a quality of a user’s use of the article of furniture or adjustable foundation based at least in part on analyzing the user factors, sleep factors, and / or environmental factors. For example, after use, the user can provide feedback or input via a GUI associated with the controller about how the user viewed the manner of use, and the controller can utilize this information to calculate the score. In some embodiments, the article of furniture can be a bed arrangement, and the controller can be configured to calculate a sleep score indicative of a quality of sleep of the user while sleeping on the bed arrangement.

[0097] In some embodiments, the sleep score computed by the controller can be related to a threshold (or benchmark) sleep score. The threshold sleep score can be based on aggregated sleep scores and / or sensing data from a population of users (e.g., at least about 10, 50, 100, 500, 1,000, 5,000, 10,000, 20,000, 50,000, or more users) collected over the course of days, weeks, months, or years (e.g., at least or at most about 1 year, at least or at most about 2 years, at least or at most about 3 years, at least or at most about 4 years, at least or at most about 5 years, etc.). Alternatively, in some embodiments, the sleep score computed by the controller can be more individualized, and the threshold sleep score can be based on aggregated sleep scores and / or sensing data from a particular user collected (e.g., long-term collected) over the course of days, weeks, months, or years (e.g., at least or at most about 1 year, at least or at most about 2 years, at least or at most about 3 years, at least or at most about 4 years, at least or at most about 5 years, etc.).

[0098] In some embodiments, the score (e.g., sleep score) as provided herein can be a rating. The rating can be a numerical rating, a letter rating, an alphanumeric rating, a percentage, a graphical system, etc. In some cases, the rating can be provided based on a scale, where a higher rating can be associated with a better user experience (e.g., better sleep quality) than a lower rating. In some cases, the rating can be based on a scale of 0 (0%) to 100% rating, where a higher percentage value indicates a better user experience (e.g., better sleep quality). The rating can be at least about 0%, 1%, 2%, 3%, 4%, 5%, 6%, 7%, 8%, 9%, 10%, 20%, 30%, 40%, 50%, 60%, 70%, 80%, 90%, 99%, or more. The rating can be at most about 100%, 90%, 80%, 70%, 60%, 50%, 40%, 30%, 20%, 10%, 9%, 8%, 6%, 5%, 4%, 3%, 2%, 1%, or less. In some cases, the rating can be based on another numerical scale, such as a scale of 0 to 10 (e.g., in order of positive impact 0, 1, 2, 3, 4, 5, 6, 7, 8, 9, and 10). In some cases, the rating can be based on a graphical scale, such as, for example, a scale of 1 to 5 stars (e.g., in order of positive impact 1, 2, 3, 4, and 5 stars). In some cases, the rating can be a letter rating system, such as, for example, one or more of D-, D, D+, C-, C, C+, B-, B, B+, A-, A, and A+.

[0099] In some embodiments, the computed sleep score and / or raw data of a user of the article of furniture can be compared to benchmark data (e.g., computed sleep scores, raw data thereof, analyses thereof, such as averages, etc.) of a plurality of users of the same article of furniture. The plurality of users can include at least about 10, at least about 50, at least about 100, at least about 500, at least about 1,000, at least about 5,000, at least about 10,000, or more users. The benchmark data can be collected over a period of time, such as at least about 1 year, at least about 2 years, at least about 3 years, at least about 4 years, at least about 5 years, or more. The benchmark data can include data collected over the past 1 year, 2 years, 3 years, 4 years, 5 years, or more. For example, the comparison can indicate that the user of the article of furniture has a higher or lower sleep score compared to other users of the same article of furniture. In some embodiments, the sleep score of the user of the article of furniture can be compared to benchmark data (e.g., average sleep score) of the user’s previous use of the article of furniture. For example, the comparison can indicate that the user of the article of furniture has a higher or lower sleep score compared to the user’s previous use of the article of furniture. Alternatively or additionally, the benchmark data can be individualized benchmark data of the user (e.g., not indicative of any other individual). The individualized benchmark data can include a target or value of the user, or a value (e.g., average) from a previous night or nights. Alternatively or additionally, the benchmark data can be a threshold value (e.g., global threshold value) that is applicable to a plurality of users.

[0100] In one example, the sleep score and / or raw data indicative of sleep regularity can be compared to individualized benchmark of the user. In another example, the sleep score and / or raw data indicative of sleep quality can be compared to a population benchmark. In another example, the sleep score and / or raw data indicative of total sleep time can be compared to a threshold value (e.g., about 8 hours as a target threshold value for total sleep time per night).

[0101] FIG. 1An example graphical user interface (GUI) is illustratively shown displaying information about a user's sleep score ("sleep health score") for a selected day or date (Friday or "F"). The sleep score can be provided in the form of one or more ratings, such as a numerical score (e.g., 88 out of 100) or a textual description (e.g., good). The GUI can provide one or more factors used to determine the sleep score, such as sleep quality ("quality"), the user's sleep routine ("habits"), and total sleep time ("sleep time"). Each of the factors can be provided with its own analysis or score (e.g., determined by a classifier) so that the user sees, for example, possible reasons why their sleep score is higher or lower than expected. In some cases, the GUI can allow the user to select at least one of the one or more factors on the GUI to trigger the GUI to display more detailed information about the selected factor. For example, as shown in FIG. 1 the sleep quality factor can be selected to prompt the GUI to display an overall progression of the user's sleep stages for the selected night (e.g., a color schematic representing different sleep stages, the x-axis representing time, and the y-axis representing the user's biosignal or a biosignal of the bed or environment detected during sleep).

[0102] Another aspect of the present disclosure provides a system comprising one or more computer processors and computer memory coupled to the one or more computer processors. The computer memory comprises machine executable code that, when executed by the one or more computer processors, implements any of the methods above or elsewhere herein, such as, for example, one or more operations of a sensor unit as provided herein.

[0103] Artificial intelligence, machine learning, and algorithms

[0104] In some embodiments, any decision or action of a controller (or computer processor, used interchangeably herein) as provided herein can be decided (or generated) by analyzing data based on one or more computer-implemented models (e.g., AI models, such as ML models) or computer algorithms.

[0105] In some embodiments, the computer-implemented model is a classifier as provided herein, which can be used to process (e.g., analyze) one or more of the user factors, sleep factors, and / or environmental factors.

[0106] In some embodiments, the classifier can be trained based on past data associated with the subject or a group of subjects. The past data can include one or more of (i) to (vi) as provided herein. The past data can include data collected within at least or at most about 1 day, 2 days, 3 days, 4 days, 5 days, 6 days, 7 days, 8 days, 9 days, 10 days, 11 days, 12 days, 13 days, 14 days, 3 weeks, 4 weeks, 5 weeks, 6 weeks, 7 weeks, 8 weeks, 9 weeks, 10 weeks, 11 weeks, 12 weeks, 4 months, 5 months, 6 months, 7 months, 8 months, 9 months, 10 months, 11 months, 12 months, 15 months, 18 months, 21 months, or 24 months prior to using the classifier to determine any action or operation as provided herein. In some cases, the classifier can be continuously trained using new data including one or more of (i) to (vi). The frequency of the continuous training (or updating) of the classifier can be at least once a day, once a week (or multiple weeks), once a month (or multiple months), once a year (or multiple years), etc.

[0107] In some embodiments, the classifier can be trained based on data not provided by the user or not collected by the sensors as provided herein. In some embodiments, the classifier can be trained on reference data. In some cases, the reference data can include clinical data collected from a group of individuals (e.g., thermography data and analysis thereof from experimental or clinical studies). In some cases, the reference data can be artificial data not collected from any particular individual. For example, the reference data can include predicted or hypothetical data for one or more biosignals (e.g., used as pseudo ground truth data). In some cases, the reference data can be used as ground truth data.

[0108] In some embodiments, a classifier as provided herein can be trained by applying a computer algorithm (e.g., a deep learning algorithm, a clustering algorithm, a forest-based model, a regression model, a classifier model, etc.) to control data as disclosed herein as a training data set. Non-limiting examples of training paradigms that include computer algorithms for training a classifier can include supervised learning, unsupervised learning, semi-supervised learning, reinforcement learning, self-learning, feature learning, anomaly detection, association rules, etc. In some cases, a classifier can be trained by using one or more learning models on this training data set. Non-limiting examples of learning models or model architectures can include artificial neural networks (e.g., convolutional neural networks (CNNs), recurrent neural networks (RNNs), long short-term models (LSTMs), encoder-decoders, support vector machines (SVMs), generative adversarial networks (GANs), diffusion models, transformers, graph neural networks (GNNs), large language models, U-net architecture neural networks, etc.), backpropagation, boosting, decision trees, support vector machines, regression analysis, Bayesian networks, Markov models, hidden Markov models, simulated annealing, genetic algorithms, kernel estimators, conditional random fields, random forests, ensembles of classifiers, minimum complexity machines (MCMs), probabilistic approximate correct learning (PACT), etc.

[0109] In some embodiments, a classifier can continue to be trained by applying a computer algorithm to control data as well as any new input data as a training data set (e.g., current sensed data detected and generated substantially in real-time or within a short time span as provided herein).

[0110] In some embodiments, a computer-implemented model (e.g., for determining a physiological condition of a subject) can be an unsupervised, semi-supervised, or self-supervised model, a fully supervised model. Models such as these can not require the output of the model to be used as an output for downstream applications or modeling, whereas other embodiments can. Non-limiting approaches include transformer models, BERT models, ERNIE models, autoencoders, variational autoencoders, generative adversarial networks, ladder networks, Siamese networks.

[0111] In some embodiments, a computer-implemented model (e.g., for determining a physiological condition of a subject) can be a generative model. Non-limiting examples can include variational autoencoders, encoders, deconvolutional encoders, generative adversarial networks, transformer models.

[0112] In some embodiments, the computer-implemented model (e.g., for determining a physiological condition of a subject) can be a multi-modal artificial intelligence model. Examples of such models include any model that employs different types or modalities of features, such as but not limited to: image, video, text, sensor, spatial, tabular, genetic, clinical, temporal, discrete, or continuous. Non-limiting examples of such methods include large language models (LLMs), diffusion models, generative pre-trained transformer models.

[0113] In some embodiments, pre-trained models can be used alone or with other models or algorithms for various purposes. Machine learning models can be untrained and subsequently trained to optimize for a task or tasks. In some cases, they can use labeled data. In some cases, they can use unlabeled data. In some cases, they can use partially labeled data. In some cases, they can use data for which labels are generated by a machine learning model that can be the same model as the one being trained or can be a different model, and the labels can be generated during training or outside of model training. On the other hand, pre-trained models are models for which training has already been completed. Models can be trained multiple times. In some cases, models are continuously trained and copies of the parameters at different points in time are used as trained versions of the model. In some cases, models can alternate between training and use (inference, classification, regression, etc.).

[0114] In some embodiments, computer-implemented models (e.g., for determining a physiological condition of a subject) can be trained using a transfer learning approach. In such embodiments, the computer-implemented model can first be trained on multiple data related only to the desired task of the model by data modality, where the multiple training data can contain information related to the desired task of the model in some form. The computer-implemented model can then be used on multiple different data specific to the desired task. Examples of such training approaches can include, in a non-limiting manner, training a model for disease detection by infrared data by first training the model on data collected by sensors in various environments (e.g., outdoors, indoors, inside a car, different climates); then, the approach would train the model a second time on infrared data specific to disease detection while preserving the training parameters in the first training step. Benefits of such training approaches can be one or both of: (1) they can allow the model to learn a larger modal distribution of inputs into the model; and (2) they can allow the model to be trained using a smaller dataset specific to the desired task without suffering from undergeneralization.

[0115] In some embodiments, the computer-implemented model (e.g., for determining a physiological condition of a subject) can utilize user input. The user input is not limited to the input methods of one or more devices disclosed herein, and can include, but is not limited to, a smartphone, a computer, a web interface, a user’s own device, a third-party device, a third-party application. In some cases, the device can include a graphical user interface (GUI) configured to allow the user to provide input. The user input can be a result of a prompt for the input method. The user input can be from a source such as, but not limited to, a user of the device disclosed herein, or can be from another user, such as a friend, family member, doctor, or any type of professional. For example, the input can include how the user’s sleep quality was (e.g., or how the user perceives the sleep quality of one or more nights in the past) or how the user perceives the user’s health condition.

[0116] In some embodiments, the computer-implemented method (e.g., for determining a physiological condition of a subject) can use data collected about the environment or other contextual information that is not specific to the user. Examples of such data sources can include, but are not limited to, the daylight cycle, the time of year, the home temperature, the humidity, the air quality, general stressors (e.g., news reports), noise levels, allergen levels, indoor light levels, home traffic levels, etc.

[0117] In some embodiments, the computer-implemented model (e.g., for determining a physiological condition of a subject) can access data provided by other devices, such as, but not limited to, smart home devices. Examples of such devices can include, but are not limited to, a thermostat, a humidity sensor, a light, a device connected to the internet of things, a device connected through the z-wave protocol, a device connected through the matter protocol, a device connected by the zigbee protocol, a physically connected device, a device connected through the internet connection, a device on a mesh network, a window controller, a sunshade controller, a blind controller, a doorbell, a security camera, a door lock, a door sensor, a window sensor, a plug. In some cases, the computer-implemented model can interact with a smart home application, such as Phillips Hue, SmartThings, Google Nest, SmartHome Manager.

[0118] In some embodiments, the computer-implemented model (e.g., for determining a physiological condition of a subject) can access information available on the internet. Examples of such information include, but are not limited to, social media data, internet usage data, purchasing habits.

[0119] Computer system

[0120] The present disclosure provides a computer system programmed to implement the methods of the present disclosure.FIG. 2 A computer system 1101 is shown, programmed or otherwise configured to direct the operation of systems of the present disclosure, such as an adjustable base. The computer system 1101 can be an electronic device of a user or a computer system remotely located with respect to the electronic device. The electronic device can be a mobile electronic device.

[0121] The computer system 1101 includes a central processing unit (CPU, also "processor" and "computer processor" herein) 1105, which can be a single core or multi core processor, or a plurality of processors for parallel processing. Computer system 1101 also includes memory or memory location 1110 (e.g., random access memory, read only memory, flash memory), electronic storage unit 1115 (e.g., hard disk), communication interface 1120 (e.g., network adapter) for communicating with one or more other systems, and peripheral devices 1125, such as cache, other memory, data storage, or electronic display adapters. Memory 1110, storage unit 1115, interface 1120, and peripheral devices 1125 are in communication with the CPU 1105 through a communication bus (solid lines), such as a motherboard. The storage unit 1115 can be a data storage unit (or data repository) for storing data. The computer system 1101 can be operatively coupled to a computer network (‘network’) 1130 by means of the communication interface 1120. The network 1130 can be the Internet, an internet and / or an extranet, or an intranet and / or extranet that in turn can include a network, such as the Internet. In some cases, the network 1130 is a telecommunication and / or data network. The network 1130 can include one or more computer servers that can implement a distributed computing methodology, such as cloud computing. In some cases, the network 1130 can implement a peer-to-peer network, which can enable devices coupled to the computer system 1101 to behave as a client or a server.

[0122] The CPU 1105 can execute a sequence of machine-readable instructions, which can be embodied in a program or software. The instructions can be stored in a memory location, such as the memory 1110. The instructions, when executed by the CPU 1105, can cause the CPU 1105 to perform

[0123] The CPU 1105 can be a part of a circuit, such as an integrated circuit. One or more other components of the system 1101 can be included in the circuit. In some cases, the circuit is an application specific integrated circuit (ASIC).

[0124] Storage unit 1115 may store files, such as drivers, libraries, and saved programs. Storage unit 1115 may store user data, such as user preferences and user programs. In some cases, computer system 1101 may include one or more additional data storage units external to computer system 1101, such as those located on a remote server communicating with computer system 1101 via an intranet or the Internet.

[0125] Computer system 1101 can communicate with one or more remote computer systems via network 1130. For example, computer system 1101 can communicate with a user's remote computer system. Examples of remote computer systems include personal computers (e.g., portable PCs), laptops, or tablet PCs (e.g., tablet PCs). iPad GalaxyTab), telephone, smartphone (e.g., iPhone, Android-enabled devices (or personal digital assistant). Users can access computer system 1101 via network 1130.

[0126] The methods described herein can be implemented by machine-executable code (e.g., a computer processor) stored at an electronic storage location (e.g., memory 1110 or electronic storage unit 1115) in computer system 1101. The machine-executable or machine-readable code can be provided in software form. During use, this code can be executed by processor 1105. In some cases, code can be retrieved from storage unit 1115 and stored on memory 1110 for easy access by processor 1105. In some cases, electronic storage unit 1115 can be excluded, and machine-executable instructions can be stored on memory 1110.

[0127] The code can be pre-compiled and configured for use with a machine having a processor suitable for executing the code, or it can be compiled during runtime. The code can be provided in a programming language, which can be selected to enable the code to be executed in a pre-compiled or just-in-time (JIT) compiled manner.

[0128] Aspects of the systems and methods provided herein, such as computer system 1101, can be implemented in programming. Various aspects of the technology can be thought of as “products” or “articles of manufacture” typically in the form of machine (or processor) executable code and / or associated data that is carried on or embodied in a type of machine readable medium. Machine-executable code can be stored on an electronic storage unit, such as memory (e.g., read-only memory, random-access memory, flash memory) or a hard disk. “Storage” type media can include any or all of the tangible memory of the computers, processors or the like, or associated modules thereof, such as various semiconductor memories, tape drives, disk drives and the like, which can provide non-transitory storage at any time for the software programming. All or portions of the software can at times be communicated by an applicable medium to or from a network connecting computer(s) or processor(s) operating thereon. Such communications, for example, can enable loading of the software from one computer or processor into another computer or processor. Thus, another type of media that can bear the software elements includes optical, electrical and electromagnetic waves such as used in wired and optical fiber

[0129] Accordingly, a machine readable medium, such as a computer-readable medium, can take many forms, including but not limited to, a tangible storage medium, a carrier wave medium or physical transmission medium. Non-volatile storage media include, for example, optical or magnetic disks, such as any of the storage devices in any computer(s) or the like which might be used to implement the databases, etc. shown in the drawings. Volatile storage media include dynamic memory, such as the main memory of such a computer platform. Tangible transmission media include, for example, coaxial cables, copper wire and fiber optics, including the wires that comprise a bus within a computer system. Carrier wave transmission media can take the form of electric or electromagnetic signals, or acoustic or light waves such as those generated during radio frequency (RF) and infrared (IR) data communications. Common forms of computer-readable media therefore include for example: a floppy disk, a flexible disk, a hard disk, magnetic tape, any other magnetic medium, a CD-ROM, DVD or DVD-ROM, any other optical medium, punch cards, paper tape, any other physical storage medium that can be used to store or transfer programming code means and / or data, and any medium that can be used to carry or store desired programming code means and / or data in a form readable by a computer.

[0130] The computer system 1101 can include or communicate with an electronic display 1135 that includes a user interface (UI) 1140 for providing. Examples of UIs include, without limitation, graphical user interfaces (GUIs) and web-based user interfaces.

[0131] The methods and systems of this disclosure can be implemented by one or more algorithms. The algorithms can be implemented in software when executed by the central processing unit 1105. For example, the algorithms can assist in comparing the sensing data and control data provided herein.

[0132] Examples

[0133] Example 1: Controlling an adjustable base of a furniture article

[0134] The systems and methods of this disclosure can be used to adjust at least one feature of an adjustable base of a furniture article. In some embodiments, the position of at least a portion of the adjustable base can be adjusted, thereby controlling the sleep posture of a user. In some embodiments, a rocking motion of at least a portion of the adjustable frame can be initiated or adjusted, thereby assisting a user in falling asleep or staying asleep.

[0135] In some embodiments, the adjustment of at least one feature of the adjustable base can be based on data analysis.

[0136] In some embodiments, the data can include a relative proportion of different sleep stages during the night (e.g., a percentage of deep sleep, a percentage of REM sleep, a percentage of light sleep, etc.), a sleep regularity of the user (e.g., whether the user consistently retires and wakes up over the course of days, weeks, or months), and / or a total sleep time of the user (e.g., a total sleep time of the previous night, or an average over the previous nights). In some embodiments, the data can be analyzed to generate a sleep score, and one or more features of the adjustable base provided herein can be performed (e.g., by the user or automatically by a computer processor) based on the sleep score.

[0137] In some embodiments, the data can include (1) sleep factors (e.g., a relative proportion of different sleep stages during the night, a sleep regularity of the user, a total sleep time of the user, a biological signal of the user, etc.), (2) environmental factors (e.g., one or more conditions of an environment of the adjustable base or furniture article), and / or (3) user factors (e.g., age, biological sex, health conditions, etc.). In some embodiments, the data can be analyzed to generate a sleep score, and one or more features of the adjustable base provided herein can be performed (e.g., by the user or automatically by a computer processor) based on the sleep score.

[0138] The systems and methods of the present disclosure can be combined with or modified by additional systems including articles of furniture (e.g., bed devices) and methods of use thereof. For example, systems and methods of detecting biological signals or physiological conditions (e.g., sleep disorders) of a user of an article of furniture, regulating a temperature or configuration of the article of furniture, regulating biological signals or physiological conditions (e.g., sleep disorders) of a user on the article of furniture, and regulating operation of other devices operably coupled to the article of furniture are described in U.S. Patent Publication No. 2015 / 0351556 (“BED DEVICE SYSTEM AND METHODS”), U.S. Patent Publication No. 2016 / 0128488 (“APPARATUS AND METHODS FOR HEATING OR COOLING A BED BASED ON HUMAN BIOLOGICAL SIGNALS”), U.S. Patent Publication No. 2017 / 0135882 (“ADJUSTABLE BEDFRAME AND OPERATING METHODS FOR HEALTH MONITORING”), U.S. Patent Publication No. 2017 / 0135632 (“DETECTING SLEEPING DISORDERS”), U.S. Patent Publication No. 2020 / 0405998 (“SLEEP POD”), and U.S. Patent Publication No. 2021 / 0315389 (“SYSTEMS AND METHODS FOR REGULATING A TEMPERATURE OF AN ARTICLE OF FURNITURE”), each of which is incorporated by reference herein in its entirety.

[0139] While preferred embodiments of the application have been shown and described herein, it will be apparent to those skilled in the art that many changes, modifications, and substitutions can be made thereto without departing from the application. The description and illustration of the embodiments herein are not meant to be limiting to the application. Although the application has been described with reference to the above explanation, it is not intended to be limited to the examples described herein. It is therefore expressly intended that the application be limited only as set forth in the claims.

Claims

1. A computer-implemented method comprising: (a) analyzing data retrieved from a database associated with a user of an adjustable base for a fixed bed apparatus, wherein the data comprises sleep factors including two or more members selected from the group consisting of a sleep routine of the user, sleep stage information of the user, a preference condition of the user for the adjustable base, and a preference condition of the user for a furniture article, and (b) adjusting at least one feature of the adjustable base based on the analysis of the data, wherein the at least one feature comprises: (i) a position of at least a portion of the adjustable base, thereby controlling a sleep posture of the user, and / or (ii) a rocking motion of at least a portion of the adjustable frame, thereby assisting the user in falling asleep or remaining asleep.

2. The method of claim 1, wherein the sleep factors comprise three or more members selected from the group consisting of the sleep routine, the sleep stage information, the preference condition of the user for the adjustable base, and the preference condition of the user for the furniture article.

3. The method of any of the preceding claims, wherein the two or more members include the sleep routine of the user.

4. The method of any of the preceding claims, wherein the two or more members include the sleep stage information.

5. The method of any of the preceding claims, wherein the two or more members include the preference condition of the user for the adjustable base.

6. The method of any of the preceding claims, wherein the two or more members include the preference condition of the user for the furniture article.

7. The method of any of the preceding claims, wherein the at least one feature comprises the position of at least the portion of the adjustable base.

8. The method of claim 7, wherein adjusting the position comprises adjusting an angle between portions of the adjustable base.

9. The method of any of the preceding claims, wherein the at least one feature comprises the rocking motion.

10. The method of claim 9, wherein the rocking motion is selected from the group consisting of in-plane motion, longitudinal rocking, side-to-side rocking, rotational rocking, and vertical rocking.

11. The method of any of the preceding claims, wherein the adjustable base comprises a plurality of adjustable segments disposed adjacent to one another, wherein the plurality of adjustable segments are configured to be adjusted independently of one another based on the data analysis in (a).

12. The method of claim 11, wherein the plurality of adjustable segments comprises two or more members selected from the group consisting of a head segment, a back segment, a leg segment, and a foot segment.

13. The method of claim 11, wherein the plurality of adjustable segments comprises a first segment for the user and a second segment for an additional user.

14. The method of any of the preceding claims, wherein the analysis in (a) comprises analyzing the sleep factors by a machine learning model.

15. The method of claim 14, wherein the machine learning model utilizes a neural network algorithm.

16. The method of claim 15, wherein the neural network algorithm comprises a convolutional neural network algorithm.

17. The method of any of the preceding claims, wherein the adjustment in (b) is performed upon determining the presence of the user on or near the adjustable foundation.

18. The method of claim 17, comprising determining the presence of the user based on user sensing data generated by a user sensor.

19. The method of claim 18, wherein the user sensor is coupled to the adjustable foundation or the article of furniture.

20. The method of claim 18, wherein the user sensor comprises one or more members selected from the group consisting of a capacitive sensor, a piezoelectric sensor, and a temperature sensor.

21. The method of any of the preceding claims, wherein the article of furniture is (i) a mattress or mattress cover, or (ii) a pillow or pillow cover.

22. The method of any of the preceding claims, wherein the analysis in (a) comprises determining a sleep score of the user when sleeping on the article of furniture, and wherein the adjustment in (b) is based at least in part on a sleep score of a previous sleep of the user.

23. The method of any of the preceding claims, further comprising generating or updating an adjustable foundation profile of the user for subsequent use by the adjustable foundation, wherein the adjustable foundation profile comprises a plurality of adjustments to at least the portion of the adjustable foundation.

24. The method of claim 23, wherein the adjustable foundation profile further comprises (i) a duration of each adjustment and / or (ii) the analysis of data corresponding to each adjustment.

25. A system comprising: a computer processor; and a computer memory coupled to the computer processor, wherein the computer memory comprises machine executable code that, when executed by the one or more computer processors, implements the method of any of the preceding claims.

26. The system of claim 25, further comprising the adjustable foundation.

27. The system of any of the preceding claims, further comprising the article of furniture.

28. A computer-implemented method comprising: (a) analyzing, by a machine learning model, data retrieved from a database associated with a user of an adjustable foundation for securing an article of furniture, wherein the data comprises two or more data types selected from the group consisting of user factors, sleep factors, and environmental factors; and (b) adjusting at least one feature of the adjustable foundation based on the analysis of the data, wherein the at least one feature comprises: (i) a position of at least a portion of the adjustable foundation, thereby controlling a sleep posture of the user, and / or (ii) a rocking motion of at least a portion of the adjustable frame, thereby assisting the user in falling asleep or staying asleep. ​ 29. The method of claim 28, wherein the at least one characteristic comprises a position of at least the portion of the adjustable base.

30. The method of claim 29, wherein adjusting the position comprises adjusting an angle between portions of the adjustable base.

31. The method of claim 28, wherein the at least one characteristic comprises the rocking motion.

32. The method of claim 31, wherein the rocking motion is selected from the group consisting of in-plane motion, longitudinal rocking, side-to-side rocking, rotational rocking, and vertical rocking.

33. The method of any of the preceding claims, wherein the adjustable base comprises a plurality of adjustable segments disposed adjacent to one another, wherein the plurality of adjustable segments are configured to be adjusted independently of one another based on the data analysis in (a).

34. The method of claim 33, wherein the plurality of adjustable segments comprises two or more members selected from the group consisting of a head segment, a back segment, a leg segment, and a foot segment.

35. The method of claim 33, wherein the plurality of adjustable segments comprises a first segment for the user and a second segment for an additional user.

36. The method of any of the preceding claims, wherein the analysis in (a) comprises analyzing the data by a machine learning model.

37. The method of claim 36, wherein the machine learning model utilizes a neural network algorithm.

38. The method of claim 37, wherein the neural network algorithm comprises a convolutional neural network algorithm.

39. The method of any of the preceding claims, wherein the two or more data types comprise the user factors.

40. The method of claim 39, wherein the user factors comprise one or more members selected from the group consisting of a physiological gender of the user, an age of the user, a health condition of the user, exercise information of the user, and diet information (or food consumption information) of the user.

41. The method of any of the preceding claims, wherein the two or more data types comprise the sleep factors.

42. The method of claim 41, wherein the sleep factors comprise one or more members selected from the group consisting of a sleep routine of the user, one or more biosignals of the user, sleep stage information of the user, a preference condition of the user for the adjustable base, and a preference condition of the user for the furniture article.

43. The method of any of the preceding claims, wherein the two or more data types comprise the environmental factors.

44. The method of claim 43, wherein the environmental factors comprise (i) measured values of the environmental factors or changes thereof and / or (ii) target values of the environmental factors.

45. The method of any of the preceding claims, wherein the analysis in (a) comprises analyzing the user factors, the sleep factors, and the environmental factors.

46. The method of any of the preceding claims, wherein the adjustment in (b) is performed upon determining the presence of the user above or near the adjustable foundation.

47. The method of claim 46, comprising determining the presence of the user based on user sensing data generated by a user sensor.

48. The method of claim 47, wherein the user sensor is coupled to the adjustable foundation or the article of furniture.

49. The method of claim 47, wherein the user sensor comprises one or more members selected from the group consisting of a capacitive sensor, a piezoelectric sensor, and a temperature sensor.

50. The method of any of the preceding claims, wherein the article of furniture is (i) a mattress or mattress cover, or (ii) a pillow or pillow cover.

51. The method of any of the preceding claims, wherein the analysis in (a) comprises determining a sleep score of the user when sleeping on the article of furniture, and wherein the adjustment in (b) is based at least in part on the sleep score of the user’s previous sleep.

52. The method of any of the preceding claims, further comprising generating or updating an adjustable foundation profile of the user for subsequent use by the adjustable foundation, wherein the adjustable foundation profile comprises a plurality of adjustments to at least the portion of the adjustable foundation.

53. The method of claim 52, wherein the adjustable foundation profile further comprises (i) a duration of each adjustment and / or (ii) an analysis of data corresponding to each adjustment.

54. A system comprising: a computer processor; and a computer memory coupled to the computer processor, wherein the computer memory comprises machine executable code that, when executed by the one or more computer processors, implements the method of any of the preceding claims.

55. The system of claim 54, further comprising the adjustable foundation.

56. The system of any of the preceding claims, further comprising the article of furniture.

Images