JP2023017638A - Control device, control method, and control program - Google Patents

Abstract

To control bedding and a bedroom environment using motion information indicating a motion of a person estimated by using electric characteristics of the bedding including a flexible material having conductivity.SOLUTION: A control device (1) detects, in a detection unit, electric characteristics between a plurality of detection points in a bed (2) including a flexible material having conductivity whose electric characteristics change according to a change in an applied pressure. An estimation unit (5) estimates a motion of a person from the electric characteristics of the bed (2) using a learning model (51). A control unit (7) controls at least one of the bed (2) and a bedroom environment (8) using the motion information indicating the estimated motion of the person.SELECTED DRAWING: Figure 1

Description

The present disclosure relates to control devices, control methods, and control programs.

2. Description of the Related Art Conventionally, in order to identify the posture of a person on bedding, a change in the shape of the bedding is detected, and the result of the detection is used to estimate the posture of the person. In terms of detecting a shape change that occurs in bedding, it is difficult to detect the deformation of the bedding without disturbing the deformation of the bedding. Moreover, since strain sensors used for detecting deformation of a rigid body such as metal deformation are difficult to use for bedding, a special detection device is required to detect deformation of bedding. For example, there is known a technique of measuring the displacement and vibration of an object with a camera, obtaining a deformed image, and extracting the amount of deformation (see, for example, Patent Document 1). Also known is a technique related to a flexible tactile sensor that estimates the amount of deformation from the amount of light transmission (see Patent Document 2, for example).

In addition, in terms of estimating the sleep state of a person sleeping in various postures, vibrations caused by the heartbeat and breathing of the sleeper are detected by sensors such as piezoelectric elements, and the sleep state of the sleeper is estimated based on the detected vibrations. A technique for estimation is known (see, for example, Patent Document 3).

International Publication No. 2017-029905 JP 2013-101096 A JP 2009-297455 A

However, in the aspect of detecting shape changes occurring in bedding, when detecting the amount of deformation such as displacement of an object using a camera and image analysis technique, the system including the camera and image analysis etc. becomes large-scale, and the apparatus This is not preferable because it causes an increase in the size of the device. In addition, the optical method using a camera cannot measure hidden portions that are not captured by the camera. Therefore, there is room for improvement in detecting deformation of bedding.

Further, in terms of estimating the sleeping state, when using vibration detected by a sensor such as a piezoelectric element, the sensor itself may inhibit deformation of the bedding. In addition, there is a possibility that vibration detection cannot take into consideration the sleep state caused by the deformation of bedding, and there is room for improvement in estimating the sleep state. In particular, there is room for improvement in estimating the motion of a person sleeping on bedding. Also, it is conceivable to control the bedding and bedroom environment using motion information indicating the estimated motion of a person, but the techniques described in Patent Documents 1 to 3 do not consider this at all.

The present disclosure provides a control device that can control bedding and a bedroom environment using motion information that indicates the movement of a person, which is estimated using the electrical properties of bedding that includes a conductive flexible material. An object is to provide a method and a control program.

In order to achieve the above object, the first aspect is
A detection unit for detecting electrical characteristics between a plurality of predetermined detection points on the soft material of bedding provided with a flexible material that is conductive and whose electrical characteristics change according to changes in applied pressure. and,
Using time-series electrical characteristics when pressure is applied to the flexible material and motion information indicating the movement of a person applying pressure to the flexible material as learning data, and using the time-series electrical characteristics as input, The time-series electrical characteristics detected by the detection unit are input to a learning model trained to output the motion information, and motion information indicating the motion of a person corresponding to the input time-series electrical characteristics. an estimating unit for estimating
a control unit that controls at least one of the bedding and a bedroom environment, which is the environment of the bedroom in which the bedding is installed, using the motion information estimated by the estimation unit;
is a control device including

A second aspect is the control device of the first aspect,
The bedding is a bed including a mattress,
The control unit controls at least one of the angle of the bed and the bedroom environment using the motion information estimated by the estimation unit.

A third aspect is the control device of the second aspect,
The bedroom environment includes at least one of brightness, sound, and room temperature in the bedroom.

A fourth aspect is the control device of any one aspect of the first aspect to the third aspect,
The learning model is trained to output, as the movement information, information indicating changes in the posture of the person corresponding to the detected electrical characteristics,
The control unit controls at least one of the bedding and the bedroom environment using the information indicating the change in posture estimated by the estimation unit.

A fifth aspect is the control device according to any one aspect of the first aspect to the fourth aspect,
The learning model is trained to output, as the movement information, information indicating a change in a person's respiratory state corresponding to the detected electrical characteristics,
The control unit controls at least one of the bedding and the bedroom environment using the information indicating the change in the respiratory state estimated by the estimation unit.

A sixth aspect is the control device of any one aspect of the first to fifth aspects,
The movement of the person includes movement in the sleeping state of the person.

A seventh aspect is the control device according to any one aspect of the first aspect to the sixth aspect,
the electrical property is volume resistance;
The flexible material is a urethane material having a structure having at least one of fibrous and mesh-like skeletons, or having a structure in which a plurality of fine air bubbles are scattered inside, and at least a portion of the urethane material being electrically conductive.

An eighth aspect is the control device according to any one aspect of the first aspect to the seventh aspect,
The learning model includes a model generated by learning using a network by reservoir computing using the flexible material as a reservoir and using the reservoir.

The ninth aspect is
the computer
A detection unit for detecting electrical characteristics between a plurality of predetermined detection points on the soft material of bedding provided with a flexible material that is conductive and whose electrical characteristics change according to changes in applied pressure. obtaining the electrical properties from
Using time-series electrical characteristics when pressure is applied to the flexible material and motion information indicating the movement of a person applying pressure to the flexible material as learning data, and using the time-series electrical characteristics as input, The time-series electrical characteristics detected by the detection unit are input to a learning model trained to output the motion information, and motion information indicating the motion of a person corresponding to the input time-series electrical characteristics. , and
The control method uses the estimated motion information to control at least one of the bedding and a bedroom environment in which the bedding is installed.

The tenth aspect is
to the computer,
A detection unit for detecting electrical characteristics between a plurality of predetermined detection points on the soft material of bedding provided with a flexible material that is conductive and whose electrical characteristics change according to changes in applied pressure. obtaining the electrical properties from
Using time-series electrical characteristics when pressure is applied to the flexible material and motion information indicating the movement of a person applying pressure to the flexible material as learning data, and using the time-series electrical characteristics as input, The time-series electrical characteristics detected by the detection unit are input to a learning model trained to output the motion information, and motion information indicating the motion of a person corresponding to the input time-series electrical characteristics. , and
A control program for executing a process of controlling at least one of the bedding and a bedroom environment in which the bedding is installed, using the estimated movement information.

According to the present disclosure, it is possible to control the bedding and the bedroom environment using motion information indicating the movement of a person, which is estimated using the electrical properties of the bedding provided with a flexible material having conductivity. have an effect.

It is a figure which shows an example of a structure of the control apparatus which concerns on embodiment. It is a figure which shows an example of a structure of the bed used as control object. It is a figure which shows an example of the bedroom environment made into control object. It is a figure regarding the bed concerning an embodiment. FIG. 4 is a diagram relating to detection points of a conductive member according to the embodiment; FIG. 4 is a diagram related to a conductive member according to the embodiment; FIG. 4 is a diagram related to a conductive member according to the embodiment; FIG. 4 is a diagram related to a conductive member according to the embodiment; It is a figure regarding the learning process which concerns on embodiment. 6 is a flowchart illustrating an example of learning data collection processing according to the embodiment; FIG. 4 is a diagram illustrating bed-related characteristics according to an embodiment; FIG. 5 illustrates another property related to an embodiment bed; FIG. 10 illustrates yet another characteristic associated with an embodiment bed; FIG. 4 is a diagram related to learning processing in a learning processing unit according to the embodiment; 6 is a flowchart showing an example of the flow of learning processing according to the embodiment; FIG. 4 is a diagram related to learning processing in a learning processing unit according to the embodiment; It is a figure which shows an example of a structure of the control apparatus which concerns on embodiment. 6 is a flowchart showing an example of the flow of estimation/control processing according to the embodiment;

Hereinafter, embodiments for implementing the technology of the present disclosure will be described in detail with reference to the drawings.
Components and processes having the same actions and functions are given the same reference numerals throughout the drawings, and duplicate descriptions may be omitted as appropriate. In addition, the present disclosure is not limited to the following embodiments, and can be implemented with appropriate modifications within the scope of the purpose of the present disclosure. In addition, although the present disclosure mainly describes the estimation of physical quantities for members that deform nonlinearly, it goes without saying that the present disclosure can be applied to the estimation of physical quantities for members that deform linearly.

In the present disclosure, "bedding" is a concept that represents a tool used when a person sleeps, including at least a part of a flexible material that can be deformed, such as by bending, when an external force is applied. An example of bedding includes a bed that includes a mattress. An example of an external force includes pressure as a stimulus applied to bedding. "Human movement" is a concept that includes changes in the posture (sleeping posture) of a person and changes in the breathing state, which are caused by applying pressure to the flexible material while the person is sleeping on the bedding to change the flexible material. In addition, the state in which a person is sleeping includes a sleeping state such as a sleeping person at the time of going to bed.

In the present disclosure, the term “flexible material” is a concept that includes materials that are at least partially deformable such as bending when an external force is applied. It includes a structure having at least one skeleton and a structure in which a plurality of fine air bubbles are scattered. An example of an external force is pressure. Examples of structures having at least one of fibrous and mesh-like skeletons and structures in which a plurality of fine air bubbles are scattered include polymeric materials such as urethane materials. The term "flexible material to which electrical conductivity is imparted" is a concept that includes materials having electrical conductivity, materials obtained by imparting electrical conductivity to a flexible material to impart electrical conductivity, and materials in which the flexible material has electrical conductivity. including. In addition, the flexible material to which electrical conductivity is imparted has the function of changing electrical properties according to deformation. An example of a physical quantity that causes a function of changing electrical properties in response to deformation is a pressure value that indicates a stimulus due to pressure applied to a flexible material (hereinafter referred to as pressure stimulus). The flexible material deforms in response to the distribution of external forces, eg, pressure stimuli, caused by human movement. Also, an example of a physical quantity representing an electrical characteristic that changes according to deformation is an electrical resistance value. Other examples include voltage values or current values. The electrical resistance value can be regarded as the volume resistance value of the flexible material.

By imparting electrical conductivity to the flexible material, the electrical properties appear according to deformation due to pressure. That is, in a flexible material to which electrical conductivity is imparted, electrical pathways are intricately linked, and the electrical pathways expand and contract according to deformation. It may also exhibit behavior in which the electrical path is temporarily disconnected, and behavior in which a different connection than before occurs. Therefore, the flexible material behaves differently depending on the magnitude and distribution of the applied force (e.g., pressure stimulus) between positions separated by a predetermined distance (e.g., the positions of the detection points where the electrodes are arranged). indicates Therefore, the electrical properties change according to the magnitude and distribution of force (for example, pressure stimulus) applied to the flexible material. Since a conductive flexible material is used, it is not necessary to provide detection points such as electrodes at all locations where pressure is applied to the flexible material by an object such as a person. It is sufficient that detection points such as electrodes are provided at at least two arbitrary locations sandwiching the location where pressure is applied to the flexible material.

The control device of the present disclosure uses a learned learning model to estimate the motion of a person from the electrical properties of the conductive flexible material provided in the bedding, and uses motion information indicating the estimated motion of the person. , the bedding and/or a bedroom environment indicative of the bedroom environment in which the bedding is installed. A compliant material can be placed on the bedding. The learning model uses time-series electrical characteristics when pressure is applied to a conductive flexible material and motion information indicating the motion of a person applying pressure to the flexible material as learning data. The learning model receives time-series electrical characteristics as input, and is trained to output motion information indicating the motion of a person corresponding to the time-series electrical characteristics.

In the following description, as the bedding, a bed including a mattress on which a sheet member (hereinafter referred to as conductive urethane) in which at least a part of a urethane member is impregnated with a conductive material is applied as a flexible material having conductivity. Explain the case. As the physical quantity for deforming the conductive urethane, a value (pressure value) representing the pressure stimulus given to the bed to which the mattress is applied is applied. The pressure values in this case are generated by movements of the person sleeping on the mattress (eg, changes in posture, changes in breathing conditions, etc.). Note that the movement of a person includes movement in a sleeping state. Also, a case where the electrical resistance value of conductive urethane is applied as a physical quantity that changes according to pressure stimulation will be described.

FIG. 1 shows an example of the configuration of the control device 1 of the present disclosure.

As shown in FIG. 1, the estimation process in the control device 1 uses a learned learning model 51 to estimate the movement of a person OP on a bed 2, which is an example of bedding, as the movement of an unknown person. Output as information. As a result, it is possible to identify the movement of a person lying on the bed 2 without using a special or large-sized device or directly measuring the deformation of a soft material such as a mattress included in the bed. Become. The learning model 51 uses the movement of the person on the bed 2 (for example, the movement corresponding value) as a label, and the electrical characteristics of the bed 2 in the movement (that is, the electrical resistance value of the conductive urethane placed on the bed 2) as an input. be learned. As an example, the learning model 51 is trained to output information indicating changes in the posture of a person sleeping on the bed 2, which corresponds to the detected electrical characteristics, as motion information. As another example, the learning model 51 is trained to output, as movement information, information indicating changes in the respiratory state of the person sleeping on the bed 2, corresponding to the detected electrical characteristics. Learning of the learning model 51 will be described later.

The control process in the control device 1 controls at least one of the bed 2 and the bedroom environment 8 using the motion information output in the estimation process. Specifically, the angle of the bed 2 is controlled. The bedroom environment 8 indicates the environment of the bedroom in which the bed 2 is installed. For example, at least one of the brightness, sound, and room temperature of the bedroom is controlled. The control device 1 includes a control section 7 .

FIG. 2 shows an example of the bed 2 to be controlled. FIG. 2(A) shows a state in which the bed 2 is flat (hereinafter referred to as a flat state). The bed 2 is rotatably connected to each of a plurality of parts, and the angle of each part is controlled using each connection point as a fulcrum. The bed 2 shown in FIG. 2 includes, as an example, a first portion 2A corresponding to the person's head, a second portion 2B corresponding to the person's waist, and a third portion 2C corresponding to the person's feet. angle is controlled. A connection point between the first portion 2A and the second portion 2B is a connection point 2E, and a connection point between the second portion 2B and the third portion 2C is a connection point 2F.

FIG. 2B shows a first state in which the first portion 2A of the bed 2 is angled upward with the connecting point 2E as a fulcrum. In this first state, breathing is easier than in the flat state of FIG. 2(A).

In FIG. 2C, each of the first portion 2A and the second portion 2B of the bed 2 is angled upward with the connection point 2E as the fulcrum, and the second portion 2C is angled downward with the connection point 2F as the fulcrum. 2 shows a second state angled at . In this second state, the load on the lower back is less than in the flat state of FIG. 2(A).

In FIG. 2(D), the second portion 2B of the bed 2 is angled upward with the connection point 2E as a fulcrum, and the third portion 2C is substantially parallel to the flat first portion 2A. 3 states are shown. In this third state, the burden on the foot is less than in the flat state of FIG. 2(A).

For example, when the respiratory state of a person is estimated to be an apnea state or a dyspnea state, breathing can be facilitated by controlling to the first state shown in FIG. 2(B). In addition, by monitoring electrical characteristics in a person's sleep state, it is possible to estimate a sign of the person's awakening. When it is estimated to be a sign of getting up, it is possible to make it easier to get up by controlling to the first state of FIG. 2(B). Further, when it is estimated that the waist of the person is greatly depressed and the burden on the waist is large, the burden on the waist can be reduced by controlling to the second state of FIG. 2(C). can. In addition, by learning how a person's legs are swollen (for example, by frequently moving their legs) and the electrical characteristics at that time, the swollen legs can be estimated from the electrical characteristics. Is possible. When it is estimated that the leg is swollen, the swelling of the leg can be reduced by controlling to the third state of FIG. 2(D). From the viewpoint of safety, it is desirable to change the angle of the bed 2 slowly, and after a certain period of time has passed, the bed 2 may be controlled to return to the flat state shown in FIG. 2(A).

Further, when the person sleeps on the bed 2, the state of the bed 2 in the wakeful state before falling asleep is the first state in FIG. 2B, the second state in FIG. 2C, or the state in FIG. As the third state of, when it is estimated that the wakeful state has transitioned to the sleeping state, even if the state is slowly changed from the first state, the second state, or the third state to the flat state of FIG. 2 (A) good.

When controlling the angle of the bed 2, for example, a data table that associates motion information with the angle of the bed 2 may be stored in advance.

FIG. 3 shows an example of a bedroom environment 8 to be controlled. Bedroom environment 8 includes, for example, at least one of brightness, sound, and room temperature in bedroom 9 . The brightness of the bedroom 9 is realized by controlling the lighting 8B. The sound in the bedroom 9 is realized by controlling the audio 8C. The room temperature of the bedroom 9 is realized by controlling the air conditioner (air conditioner) 8A.

For example, when it is estimated that a person turns over frequently (that is, the frequency of turning over is equal to or greater than a predetermined number), it is considered that the person is not in an appropriate sleeping state. In this case, the room temperature may be measured using a temperature sensor (not shown). In other words, when the measured room temperature is relatively high, it is highly likely that it will be too hot to sleep, so the air conditioner 8A is controlled to lower the room temperature. Also, if the room temperature is appropriate and the heart rate is estimated to be relatively high from the respiratory state, it is considered that the person is in a tense state for some reason. In this case, the lighting 8B is controlled to provide lighting that relaxes the state of tension, and the audio 8C is controlled to play music that alleviates the state of tension.

When controlling the bedroom environment 8, for example, a data table in which motion information is associated with the set temperature of the air conditioner 8A, the illuminance of the lighting 8B, and the background music (BGM) of the audio 8C is stored in advance. good.

Next, a configuration example of the bed 2 will be described with reference to FIG.

As shown in FIG. 4 , the bed 2 according to the present embodiment is constructed by placing a conductive urethane 22 on a mattress 21 . A bed 2 composed of a mattress 21 on which a conductive urethane 22 is placed is connected to an electrical characteristic detection section 76 (FIG. 5), which is an example of a detection section. The conductive urethane 22 may be arranged on at least a part of the mattress 21 as shown in FIG. 4, and may be arranged inside or outside. Specifically, the entire interior of the mattress 21 may be made of the conductive urethane 22, as shown by the AA cross section of the bed as a bed cross section 2-1. In addition, as shown in the bed section 2-2, the conductive urethane 22 may be formed on the person side (front side) inside the mattress 21, and as shown in the bed section 2-3, the inside of the mattress 21 The conductive urethane 22 may be formed on the opposite side (rear side) to the person side. Furthermore, as shown in bed section 2-4, conductive urethane 22 may be formed near the center of the interior of mattress 21. FIG.

In addition, as shown in bed cross section 2-5, conductive urethane 22 may be arranged outside the person side (surface side) of mattress 21, and as shown in bed cross section 2-6, the conductive urethane 22 may be placed opposite to the person side. A conductive urethane 22 may be arranged on the outside of the side (rear side). When the conductive urethane 22 is arranged outside the mattress 21, the conductive urethane 22 and the mattress 21 may be simply laminated, or the conductive urethane 22 and the mattress 21 may be integrated by adhesion or the like. Even if the conductive urethane 22 is arranged outside the mattress 21, the flexibility of the mattress 21 is not hindered because the conductive urethane 22 is a conductive urethane member.

In order to simplify the explanation, an example in which the bedding is formed by arranging the conductive urethane 22 on the outside of the mattress 21 on the person side (surface side) will be explained (bed section 2-5).

In this embodiment, as shown in FIG. 5, signals from a plurality of (two in FIG. 5) detection points 75 arranged at a distance are used to determine the electrical properties (that is, the electrical resistance value) of the conductive urethane 22. A certain volume resistance value) can be detected. In the example shown in FIG. 5, a first detection set #1 is shown for detecting electrical resistance values from signals from a plurality of detection points 75 arranged diagonally with a distance on the conductive urethane 22. there is The arrangement of the plurality of detection points 75 is not limited to the positions shown in FIG. The electrical characteristics of the conductive urethane 22 can be obtained by connecting an electrical characteristics detector 76 for detecting electrical characteristics (that is, a volume resistance value, which is an electrical resistance value) to the detection point 75 and using the output thereof.

The electric resistance value detected in the bed 2 composed of the mattress 21 provided with the conductive urethane 22 described above is determined by the deformation of the conductive urethane 22 when the bed 2 is subjected to pressure stimulation. changes before and after being Therefore, the electrical resistance value changes before and after the movement of the person accompanied by pressure stimulation on the bed 2 . Therefore, detection of time-series electrical resistance values, that is, detection of changes in electrical resistance values from a state in which pressure stimulation is not applied to the bed 2 (for example, detection of electrical resistance values exceeding a predetermined threshold value). , it becomes possible to detect the movement of a person with respect to the bed 2 . Specifically, the movement of the person with respect to the bed 2 includes a contact state because it accompanies the pressure stimulation due to the contact of the person with the bed 2 . Therefore, by arranging the conductive urethane 22 on the bed 2, it is possible to detect the contact of a person with the bed 2. FIG. Moreover, even if any one of the position, distribution, and magnitude of the pressure stimulus applied to the bed 2 changes, the electric resistance value also changes. Therefore, it is not impossible to detect the contact state including the contact position of the person with respect to the bed 2 from the electrical resistance value that changes in time series.

In order to improve the detection accuracy of the electrical characteristics of the conductive urethane 22, more detection points than the two detection points shown in FIG. 5 may be used.

As an example, the conductive urethane 22 may be formed by arranging one or more rows of a plurality of conductive urethane pieces each having a detection point, and the electrical characteristics may be detected for each of the plurality of conductive urethane pieces. good. For example, the conductive urethane pieces 23 shown in FIG. 6 may be arranged to form the conductive urethane 22 (FIGS. 7 and 8). The example shown in FIG. 6 includes a first detection set #1 that detects an electrical resistance value from a signal from a detection point 75A arranged diagonally with a distance therebetween, and another detection set #1 arranged diagonally. A second detection set #2 is shown which detects the electrical resistance value from the signal from point 75B. In the example shown in FIG. 7, the conductive urethane pieces 23 (FIG. 6) are arranged (4×1) in the longitudinal direction of the mattress 21 to form the conductive urethane 22, and the first detection set # 1 to 8 detection sets #8 are shown. Furthermore, in the example shown in FIG. 8, the conductive urethane pieces 23 (FIG. 6) each adopt the first detection set #1 and are arranged (4×2) in the longitudinal direction and width direction of the mattress 21 to form conductive The urethane 22 is shown to be configured to configure the first detection set #1 to the eighth detection set #8.

As another example, the detection range on the conductive urethane 22 may be divided, a detection point may be provided for each divided detection range, and the electrical characteristics may be detected for each detection range. For example, a region corresponding to the size of the conductive urethane piece 23 shown in FIGS. What is necessary is just to detect an electrical characteristic.

As shown in FIG. 1 , the control device 1 includes an estimator 5 . Time-series input data 4 representing the magnitude of electrical resistance (electrical resistance value) in the conductive urethane 22 is input to the estimation unit 5 . The input data 4 corresponds to a person's movement 3 representing the movement of a person on the bed 2 . The estimation unit 5 also outputs output data 6 representing physical quantities (motion corresponding values) indicating the motion of the person on the bed 2 as an estimation result. Note that the estimation unit 5 includes a learning model 51 that has been trained.

The learning model 51 learns to derive movement information (output data 6) indicating the movement of the person on the bed from the electrical resistance (input data 4) of the conductive urethane 22 that changes due to pressure stimulation according to the movement 3 of the person. It is a model that has completed The learning model 51 is, for example, a model that defines a trained neural network, and is expressed as a set of information on weights (strengths) of connections between nodes (neurons) that make up the neural network.

The learning model 51 is generated by learning processing of the learning processing unit 52 shown in FIG. The learning processing unit 52 performs learning processing using the electrical characteristics (input data 4) of the conductive urethane 22 that change due to the pressure stimulation caused by the movement 3 of the person. That is, a large amount of data obtained by measuring the electrical resistance of the conductive urethane 22 in chronological order using the human movement 3 as a label is used as learning data. Specifically, the learning data includes a large amount of sets of input data including electrical resistance values (input data 4) and information indicating human movement 3 corresponding to the input data (output data 6). . Here, time-series information is associated with each of the electrical resistance values (input data 4) of the conductive urethane 22 by adding information indicating the measurement time. In this case, information indicating the time of measurement may be added to the set of time-series electrical resistance values of the conductive urethane 22 to associate the time-series information with the time period determined as the human movement 3 .

Next, the learning processing section 52 will be described.
In the learning process performed by the learning processing unit 52, the bed 2 configured by the mattress 21 on which the conductive urethane 22 is arranged is applied as a detection unit, and the movement 3 of the person and the electrical resistance value ( Input data 4) is used as learning data. For example, the person OP is instructed to perform a predetermined movement on the bed 2, and the electrical resistance value at that time is detected and associated with the movement as learning data. Movements include, for example, movement from lying on one's back to left and right sideways, movement from left and right sideways to one's back, changes from lying on one's back to lying down (or from lying down to one's back) (that is, rolling over), and from a respiratory state to an apnea state ( or a change from an apnea state to a respiratory state) are applied. Also, the electrical characteristics (that is, the volume resistance value, which is the electrical resistance value) can be detected by connecting the electrical characteristics detection section 76 (FIG. 5) to the detection point 75 .

Specifically, the learning processing unit 52 can be configured including a computer including a CPU (not shown), and executes learning data collection processing and learning processing. FIG. 10 shows an example of learning data collection processing executed by a CPU (not shown). In step S100, the learning processing unit 52 instructs the person OP to move on the bed 2 (conductive urethane 22), and in step S102, acquires in time series electrical resistance values that change due to pressure stimulation according to the motion. In the next step S104, motion 3 is assigned as a label to the acquired time-series electrical resistance values and stored. The learning processing unit 52 continues until the set of the human movement 3 and the electrical resistance value of the conductive urethane 22 reaches a predetermined number or a predetermined time (in step S106, negative until an affirmative determination is made). decision) and repeat the above process. As a result, the learning processing unit 52 can acquire and store the electrical resistance value of the conductive urethane 22 in time series for each movement of the person. A set of electrical resistance values of the urethane 22 serves as learning data.

By the way, the movement of the person OP depends at least in part on changes and maintenance of physical quantities such as the relative positional relationship of each part of the person OP with respect to the bed 2, the distribution of pressure stimulation by each part, the magnitude, and the frequency. Identifiable. Therefore, some of these time-series physical quantities are considered to include features indicating the movement of the person OP. In this embodiment, by using the conductive urethane 22, it is possible to detect the electrical characteristics (volume resistance) reflecting these physical quantities in chronological order.

FIG. 11 shows an example of electrical characteristics of the bed 2 composed of the mattress 21 on which the conductive urethane 22 is arranged. FIG. 11 shows each electrical contact of conductive urethane 22 in which a plurality of conductive urethane pieces 23 (FIG. 6) employing diagonal detection set #1 are arrayed (4×2) in the longitudinal direction and width direction on mattress 21 . characterize. FIG. 11(A) shows the result of detection of electrical characteristics by the detection set #1. Similarly, FIG. 11(B) is detection set #2, FIG. 11(C) is detection set #3, FIG. 11(D) is detection set #4, FIG. 11(E) is detection set #5, and FIG. F) shows detection results for detection set #6, FIG. 11G shows detection results for detection set #7, and FIG. 11H shows detection results for detection set #8.

In the example of FIG. 11, the characteristics of the electrical characteristics (electrical resistance value) of the conductive urethane 22 that change due to the person OP rolling over on the conductive urethane 22 are shown. 11(A) to 11(H) show the behavior when the person OP rolls over at intervals of 10 seconds, and the electrical resistance values of the conductive urethane 22 obtained by the first detection sets #1 to #8 are shown. Time characteristics are shown.

As shown in FIG. 11, the electrical characteristics of each detection set change according to the behavior of the person OP, and the behavior of turning over is reflected. It can be confirmed that it is possible to estimate the behavior of a person tossing and turning from the values. That is, even if there are various tossing-and-turning behaviors, by using the learning model 51 that has been learned for each, it is possible to separate the results regarding the tossing-and-turning behavior of the person, and it is possible to determine the tossing-and-turning behavior of the person. Become.

Further, for example, a pressure stimulus is generated by sinking of the waist of the person OP (that is, movement of the waist). In this case, the body pressure distribution of the mattress 21 can be estimated from the change in the electrical resistance of the conductive urethane 22 . Thereby, it becomes possible to provide the mattress 21 that can appropriately disperse the body pressure.

FIG. 12 shows electrical characteristics (electrical resistance values) of the conductive urethane 22 that change depending on the breathing state of the person OP with respect to the conductive urethane 22 .

The electrical characteristic (electrical resistance value) in the detection set corresponding to the chest of the person OP, that is, the electrical characteristic (electrical resistance value) that changes according to the respiratory state of the person is referred to as the "original waveform". Next, this "original waveform" is normalized by dividing it by the average value of electrical resistance values. This waveform is called a "normalized waveform". Next, the difference between the original waveform and the normalized waveform is calculated to eliminate the offset. This waveform is called a "difference waveform". Next, the waveform obtained by convoluting and accumulating the difference waveform and the sine wave and squaring it is calculated as the respiratory cycle component. This waveform is called a respiratory cycle component waveform, and is shown in FIG. 12 as an example. In this respiratory cycle component waveform, the closer the periodicity, the larger the respiratory cycle component. In other words, it is considered that there is a high possibility that an interval with a small respiratory cycle component is in an apnea state.

In this way, by using the learning model 51 that has learned the respiratory state of the person OP, the respiratory state during sleep can be calculated from the electrical resistance value that changes in time series according to the deformation of the conductive urethane 22 corresponding to the chest position of the person. can also be estimated. Therefore, for example, it is also possible to determine an apnea state during sleep.

FIG. 13 shows the characteristics of the electrical characteristics (electrical resistance) of the conductive urethane 22 that change with changes in the posture of the person with respect to the conductive urethane 22 . FIGS. 13(A) to 13(H) show the first detection sets #1 to # of the behavior when the posture of the person is changed in the order of supine, left lateral, right lateral, left lateral, and supine. 8 shows the time characteristic of the electrical resistance value of the conductive urethane 22 according to .

As shown in FIG. 13, the electrical characteristics of each detection set change according to the behavior of the person OP, and the behavior of the posture change is reflected. It can be confirmed that the behavior of a person's posture change can be estimated from the resistance value. That is, even if there are various posture change behaviors, by using a learning model in which each is learned, the results related to the posture change behavior of the person can be separated, and the posture change behavior of the person can be discriminated. It becomes possible.

Therefore, when the person OP changes the movement according to the instructed movement, the pressure stimulation to the bed 2 changes, and by acquiring the electrical characteristics corresponding to the change in the pressure stimulation in time series, It becomes possible to associate and store time-series electrical characteristics. A set of the time-series electrical characteristics and the motion corresponding value indicating the instructed motion becomes learning data.

In addition, the movement mentioned above includes the movement in the sleep state of people, such as a sleeping person. Sleep states include, for example, so-called REM sleep, non-REM sleep, light sleep, and deep sleep. These states involve at least one of a resting state with a posture in which motion is stable for a given time, and an active state with multiple postures and motions. Therefore, in the same way as the movement of the person OP described above, the sleep state includes changes in physical quantities such as the relative positional relationship of each part of the person OP with respect to the bed 2, the distribution, magnitude, and frequency of pressure stimulation by each part. It is identifiable by at least part of such as maintenance and Therefore, it is thought that some of the time-series physical quantities include features indicating motion in the sleep state, and by using the conductive urethane 22, electrical characteristics (volume resistance) that reflect these physical quantities in the sleep state can be obtained. It is possible to detect in chronological order. It should be noted that whether a person is in a sleeping state or in an awake state can be determined using a physical quantity characteristically appearing in either the sleeping state or the awake state. An example of a physical quantity that characteristically appears in a sleep state is a physical quantity that indicates that a change in posture is equal to or less than a threshold for a period of time that exceeds a predetermined period of time. Further, by further inputting data indicating whether the state is a sleep state or an awake state, it is possible to set whether the detected electrical characteristic corresponds to either the sleep state or the awake state.

Next, an example of the learning data described above is shown in a table. Table 1 is an example of data in which time-series electrical resistance value data (r) and respiratory state values are associated with each other as learning data relating to changes in respiratory state. Table 2 is an example of data in which time-series electrical resistance value data (R) and sleep state values are associated with each other as learning data related to sleep state changes. Table 3 is an example of data in which a set of characteristic data (J) indicating time-series electrical resistance values detected in each detection set shown in FIG. 13 described above and motion corresponding values are associated with each other. Any characteristic data (J) included in this set includes a posture change feature, that is, a feature pattern. All characteristic data (J) are used as learning data. For example, a plurality of characteristic data (J) and motion corresponding values detected on the bed 2 are used as learning data.

Next, learning processing in the learning processing section 52 will be described. FIG. 14 is a diagram showing functions of a CPU (not shown) of the learning processing unit 52 in learning processing.
A CPU (not shown) of the learning processing unit 52 includes functional units of the generator 54 and the calculator 56 . The generator 54 has a function of generating an output in consideration of the sequential relationship of the electrical resistance values obtained in time series as an input.

In addition, the learning processing unit 52 holds, as data for learning, a large number of sets of the above-mentioned input data 4 (electrical resistance value) and output data 6, which is the movement 3 of the person applying the pressure stimulus to the conductive urethane 22. are doing.

The generator 54 includes an input layer 540, an intermediate layer 542, and an output layer 544 to form a known neural network (NN). Since the neural network itself is a known technology, detailed description is omitted, but the intermediate layer 542 includes a large number of node groups (neuron groups) having inter-node connections and feedback connections. Data from the input layer 540 is input to the intermediate layer 542 , and data resulting from the operation of the intermediate layer 542 is output to the output layer 544 .

The generator 54 is a neural network that generates the generated output data 6A representing the movement of the person from the inputted input data 4 (electrical resistance). The generated output data 6A is data obtained by estimating the motion of a person whose conductive urethane 22 is given a pressure stimulus from the input data 4 (electrical resistance). The generator 54 generates generated output data representing a state close to human movement from the input data 4 (electrical resistance) input in chronological order. The generator 54 learns using a large number of input data 4 (electrical resistance) so that it can generate generated output data 6A that approximates the movement of a person given a pressure stimulus to the bed 2, that is, the conductive urethane 22. Become. In another aspect, the electrical characteristics, which are the input data 4 input in time series, are regarded as patterns, and by learning the patterns, the bed 2, that is, the conductive urethane 22, is subjected to a pressure stimulus, and the movement is similar to that of a person. It becomes possible to generate the generated output data 6A.

The calculator 56 is a calculator that compares the generated output data 6A with the output data 6 of the learning data and calculates the error of the comparison result. The learning processing unit 52 inputs the generated output data 6A and the output data 6 of the learning data to the calculator 56 . In response to this, the calculator 56 calculates the error between the generated output data 6A and the output data 6 of the learning data, and outputs a signal indicating the calculation result.

The learning processing unit 52 performs learning of the generator 54 that tunes the weight parameter of the connection between nodes based on the error calculated by the calculator 56 . Specifically, the weight parameter of the connection between the nodes of the input layer 540 and the hidden layer 542 in the generator 54, the weight parameter of the connection between the nodes in the hidden layer 542, and the node of the hidden layer 542 and the output layer 544 Each of the weight parameters of the connections between is fed back to the generator 54 using techniques such as gradient descent and error backpropagation. That is, with the output data 6 of the learning data as a target, the connections between all nodes are optimized so as to minimize the error between the generated output data 6A and the output data 6 of the learning data.

The learning model 51 is generated by learning processing of the learning processing unit 52 . The learning model 51 is expressed as a set of information of weight parameters (weights or strengths) of connections between nodes as a result of learning by the learning processing unit 52 .

FIG. 15 shows an example of the flow of learning processing. In step S110, the learning processing unit 52 acquires input data 4 (electrical resistance) labeled with information indicating the movement of the person OP, which is learning data obtained as a result of chronological measurement. In step S112, the learning processing unit 52 generates the learning model 51 using learning data obtained as a result of time-series measurement. That is, a set of information on weight parameters (weights or strengths) of connections between nodes is obtained as a result of learning using a large amount of learning data as described above. Then, in step S114, data expressed as a set of information on weight parameters (weights or strengths) of connections between nodes of learning results is stored as a learning model 51. FIG.

Note that the generator 54 may use a recursive neural network having a function of generating an output in consideration of the context of time-series inputs, or may use another method.

In the control device 1, the learned generator 54 (that is, data expressed as a set of weight parameter information of connections between nodes of learning results) generated by the above-described method is used as a learning model 51. use. By using the sufficiently learned learning model 51, it is possible to identify the movement of a person from the time-series electrical resistance values of the bed 2, that is, the conductive urethane 22. FIG.

Note that the processing by the learning processing unit 52 is executed by, for example, an external learning model generation device (not shown) different from the control device 1 . The control device 1 includes an estimator 5 and a controller 7 . The output data 6, which is information indicating motion 3, is an example of motion information of the present disclosure.

By the way, as described above, the conductive urethane 22 exhibits behaviors such as expansion and contraction, expansion and contraction, temporary disconnection, and new connection of the electrical paths according to deformation, and the electrical paths are linked in a complicated manner. As a result, it behaves with different electrical properties in response to an applied force (eg, pressure stimulus). This allows the conductive urethane 22 to be treated as a reservoir that stores data regarding deformation of the conductive urethane 22 . That is, the control device 1 can apply the conductive urethane 22 to a network model (hereinafter referred to as PRCN) called physical reservoir computing (PRC). Since PRC and PRCN are known techniques, detailed description thereof will be omitted.

FIG. 16 shows an example of the learning processing unit 52 that learns by treating the bed 2 containing the conductive urethane 22 as a reservoir that stores data relating to deformation of the bed 2 containing the conductive urethane 22 . The conductive urethane 22 becomes an electrical characteristic (electrical resistance value) according to each of various pressure stimuli, and functions as an input layer for inputting the electrical resistance value. act as a layer. Since the conductive urethane 22 outputs different electrical characteristics (input data 4) according to the pressure stimulus given by the movement 3 of the person, in the estimation layer, the pressure stimulus given from the electrical resistance value of the conductive urethane 22 3 (the shape of the flexible material) can be estimated. Therefore, in the learning process, the estimation layer should be learned.

The control device 1 described above can be realized, for example, by causing a computer to execute a program having the functions described above.

FIG. 17 shows an example of a configuration in which a computer is included as an execution device that executes processing for realizing various functions of the control device 1 .

A computer functioning as the control device 1 has a computer main body 100 shown in FIG. The computer main body 100 includes a CPU 102 , a RAM 104 such as a volatile memory, a ROM 106 , an auxiliary storage device 108 such as a hard disk drive (HDD), and an input/output interface (I/O) 110 . These CPU 102, RAM 104, ROM 106, auxiliary storage device 108, and input/output I/O 110 are connected via a bus 112 so as to exchange data and commands with each other. The input/output I/O 110 is also connected to a communication unit 114, which is a communication interface (communication I/F) for communicating with an external device, and an operation display unit 116 such as a display and a keyboard. The communication unit 114 has a function of acquiring the input data 4 (electrical resistance) with the bed 2 including the conductive urethane 22 . That is, the communication unit 114 includes the bed 2 on which the conductive urethane 22 is arranged, which is a detection unit, and input data 4 (electrical resistance) from the electrical characteristic detection unit 76 connected to the detection point 75 in the conductive urethane 22. can be obtained.

The auxiliary storage device 108 stores a control program 108P for causing the computer main body 100 to function as the control device 1, which is an example of the control device of the present disclosure. The CPU 102 reads the control program 108P from the auxiliary storage device 108, develops it in the RAM 104, and executes processing. Thereby, the computer main body 100 that has executed the control program 108P operates as the control device 1, which is an example of the control device of the present disclosure.

The auxiliary storage device 108 stores a learning model 108M including the learning model 51 and data 108D including various data. The control program 108P may be provided by a recording medium such as a CD-ROM.

Next, the estimation/control processing in the control device 1 implemented by a computer will be described.

FIG. 18 shows an example of the flow of estimation/control processing by the control program 108P executed in the computer main body 100. As shown in FIG.
The estimation/control processing shown in FIG. 18 is executed by the CPU 102 when the computer main body 100 is powered on. That is, the CPU 102 reads out the control program 108P from the auxiliary storage device 108, develops it in the RAM 104, and executes the process.

First, in step S200, the CPU 102 reads out the learning model 51 from the learning model 108M of the auxiliary storage device 108 and develops it in the RAM 104, thereby acquiring the learning model 51. FIG. Specifically, a network model (see FIGS. 14 and 16), which is a connection between nodes based on weight parameters expressed as the learning model 51, is developed in the RAM 104. FIG. Therefore, a learning model 51 is constructed in which connections between nodes are realized by weight parameters.

Next, in step S202, the CPU 102 transmits the unknown input data 4 (electrical resistance), which is the target for estimating the shape of the flexible material due to the pressure stimulation applied to the conductive urethane 22, via the communication unit 114 in time series. to get to.

Next, in step S204, CPU 102 estimates output data 6 (unknown motion) corresponding to input data 4 (electrical resistance) obtained in step S202, using learning model 51 obtained in step S200.

Next, in step S206, CPU 102 outputs output data 6 (movement of a person) as a result of estimation to auxiliary storage device 108. FIG.

Then, in step S208, the CPU 102 uses the output data 6 resulting from the estimation to control the bed 2 and the bedroom environment 8, and ends this processing routine. For example, as shown in FIG. 2 above, the angle of the bed 2 may be controlled, and as shown in FIG. You can control one

Note that the estimation/control processing illustrated in FIG. 18 is an example of processing executed by the control method of the present disclosure.

As described above, according to the present disclosure, the movement of a person is estimated from the input data 4 (electrical resistance) that changes according to the pressure stimulus applied to the conductive urethane 22 by the movement 3 of the person. , the estimation results can be used to control the bed 2 and bedroom environment 8 . In other words, it is possible to estimate the motion of an unknown person and control the bed and bedroom environment using the estimation results without using a special device or a large-sized device or directly measuring the deformation of a flexible material. It becomes possible.

In addition, the electrical characteristics of each detection set change due to changes in the posture and respiratory condition of the person OP, and the electrical characteristics (time-series electrical resistance) reflect changes in posture and respiratory condition. It is possible to estimate a person's posture change and breathing condition change from the electrical resistance value that changes in time series in the urethane 22, and to control the bed and bedroom environment. That is, even with various posture changes and respiratory state changes, by using the learning model described above, it is possible to identify changes in the posture and respiratory state of the person. can be estimated and used to control the bed and bedroom environment.

In addition, when estimating the movement in the sleep state, by detecting the electrical characteristics (volume resistance) reflecting the physical quantity in the sleep state in time series, for example, so-called REM sleep state and non-REM sleep state, light sleep States and deep sleep states, resting states, and active states with multiple postures and movements can be estimated and used to control bed and bedroom environments. In addition, the estimated change in the posture of a person appropriately corresponds to the sleeping phase of a person, such as a sleeping person, and can be used to estimate the sleeping phase of a sleeping person and control the bed and bedroom environment. .

In the control device 1 using the learning model 51 learned by the above-described learning process, by inputting the electrical characteristics of the conductive urethane 22 in various unknown changes in posture and changes in respiratory state, the posture of the corresponding person can be calculated. It was confirmed that it is possible to estimate the changes in

As described above, in the present disclosure, the case of applying conductive urethane as an example of the flexible material has been described, but the flexible material is of course not limited to conductive urethane.

Moreover, the technical scope of the present disclosure is not limited to the scope described in the above embodiments. Various changes or improvements can be made to the above-described embodiments without departing from the scope of the invention, and forms with such changes or improvements are also included in the technical scope of the present disclosure.

Further, in the above embodiment, a case has been described in which the estimation process, the learning process, and the control process are realized by a software configuration using a process using flowcharts, but the invention is not limited to this. It is good also as a form implement|achieved by a structure.

Also, part of the control device, for example, a neural network such as a learning model, may be configured as a hardware circuit.

1 control device 2 bed 3 movement 4 input data 5 estimation unit 6 output data 6A generated output data 7 control unit 8 bedroom environment 9 bedroom 21 mattress 22 conductive urethane 23 conductive urethane piece 51 learning model 52 learning processing unit 54 generator 56 Arithmetic unit 75 Detection point 76 Electrical characteristic detector

Claims (10)

A detection unit for detecting electrical characteristics between a plurality of predetermined detection points on the soft material of bedding provided with a flexible material that is conductive and whose electrical characteristics change according to changes in applied pressure. and,
Using time-series electrical characteristics when pressure is applied to the flexible material and motion information indicating the movement of a person applying pressure to the flexible material as learning data, and using the time-series electrical characteristics as input, The time-series electrical characteristics detected by the detection unit are input to a learning model trained to output the motion information, and motion information indicating the motion of a person corresponding to the input time-series electrical characteristics. an estimating unit for estimating
a control unit that controls at least one of the bedding and a bedroom environment, which is the environment of the bedroom in which the bedding is installed, using the motion information estimated by the estimation unit;
Control device including. The bedding is a bed including a mattress,
The control device according to claim 1, wherein the control unit controls at least one of the angle of the bed and the bedroom environment using the motion information estimated by the estimation unit. 3. The control device of claim 2, wherein the bedroom environment includes at least one of brightness, sound, and room temperature in the bedroom. The learning model is trained to output, as the movement information, information indicating changes in the posture of the person corresponding to the detected electrical characteristics,
The control unit controls at least one of the bedding and the bedroom environment using the information indicating the change in posture estimated by the estimation unit. Control device. The learning model is trained to output, as the movement information, information indicating a change in a person's respiratory state corresponding to the detected electrical characteristics,
The control unit controls at least one of the bedding and the bedroom environment using the information indicating the change in the respiratory state estimated by the estimation unit. controller. The control device according to any one of claims 1 to 5, wherein the movement of the person includes movement of the person in a sleeping state. the electrical property is volume resistance;
The flexible material is a urethane material having a structure having at least one of fibrous and mesh-like skeletons, or having a structure in which a plurality of fine air bubbles are scattered inside, and at least a portion of the urethane material being electrically conductive. The control device according to any one of claims 1 to 6. The control according to any one of claims 1 to 7, wherein the learning model includes a model generated by learning using a network based on reservoir computing using the flexible material as a reservoir. Device. the computer
A detection unit for detecting electrical characteristics between a plurality of predetermined detection points on the soft material of bedding provided with a flexible material that is conductive and whose electrical characteristics change according to changes in applied pressure. obtaining the electrical properties from
Using time-series electrical characteristics when pressure is applied to the flexible material and motion information indicating the movement of a person applying pressure to the flexible material as learning data, and using the time-series electrical characteristics as input, The time-series electrical characteristics detected by the detection unit are input to a learning model trained to output the motion information, and motion information indicating the motion of a person corresponding to the input time-series electrical characteristics. , and
A control method for controlling at least one of the bedding and a bedroom environment in which the bedding is installed, using the estimated motion information. to the computer,
A detection unit for detecting electrical characteristics between a plurality of predetermined detection points on the soft material of bedding provided with a flexible material that is conductive and whose electrical characteristics change according to changes in applied pressure. obtaining the electrical properties from
Using time-series electrical characteristics when pressure is applied to the flexible material and motion information indicating the movement of a person applying pressure to the flexible material as learning data, and using the time-series electrical characteristics as input, The time-series electrical characteristics detected by the detection unit are input to a learning model trained to output the motion information, and motion information indicating the motion of a person corresponding to the input time-series electrical characteristics. , and
A control program for executing a process of controlling at least one of the bedding and a bedroom environment in which the bedding is installed, using the estimated movement information.

Images