Motor function evaluation device, program, and motor function evaluation method

Abstract

To provide a motor function evaluation device, a program, and a motor function evaluation method, etc. suitable for a field of assistance or the like.SOLUTION: A motor function evaluation device includes: an acquisition unit for acquiring at least one of load value information indicating the magnitude of a load attributed to a body motion of a user in a bed and gravity center information indicating transition of the gravity center position of the user attributed to the body motion on the basis of a load sensor attached to the bed for detecting the load applied to the bed; and an evaluation processing unit for evaluating the motor function of the user on the basis of the at least one of the acquired load value information and gravity center information.SELECTED DRAWING: Figure 3

Description

Technical Field

[0001] The present invention relates to an exercise function evaluation device, a program, an exercise function evaluation method, and the like.

Background Art

[0002] Conventionally, a method of performing sensing on a user using sensors provided on a bed has been known. For example, Patent Document 1 discloses a method of predicting the occurrence of a harmful state for a user of a bed based on a first sensor and a second sensor.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] To provide an exercise function evaluation device, a program, an exercise function evaluation method, etc. suitable for fields such as assistance.

Means for Solving the Problems

[0005] One aspect of the present disclosure relates to an exercise function evaluation device including an acquisition unit that is attached to a bed and acquires at least one of load value information representing the magnitude of a load caused by the body movement of a user on the bed and center-of-gravity information representing the center-of-gravity position of the user based on a load sensor that detects the load applied to the bed, and an evaluation processing unit that evaluates the exercise function of the user based on at least one of the acquired load value information and the center-of-gravity information.

[0006] Another aspect of the present disclosure relates to a program that causes a computer to function as an acquisition unit that is attached to a bed and acquires at least one of load value information representing the magnitude of a load caused by a user's body movement on the bed and center-of-gravity information representing the center-of-gravity position of the user based on a load sensor that detects the load applied to the bed, and an evaluation processing unit that evaluates the user's motor function based on at least one of the acquired load value information and the center-of-gravity information.

[0007] Still another aspect of the present disclosure relates to a motor function evaluation method that acquires at least one of load value information representing the magnitude of a load caused by a user's body movement on a bed and center-of-gravity information representing the movement history of the user's center-of-gravity position based on a load sensor that is attached to the bed and detects the load applied to the bed, and evaluates the user's motor function based on at least one of the acquired load value information and the center-of-gravity information.

Brief Description of the Drawings

[0008]

Figure 1

Figure 2

Figure 3

Figure 4

Figure 5

Figure 6

Figure 7

Figure 8A

Figure 8B

Figure 8C

Figure 9

Figure 10A

Figure 10B

Figure 11

Figure 12

Figure 13A

Figure 13B

Figure 14

Figure 15

Figure 16A

Figure 16B

Figure 17

Figure 18

Figure 19

Figure 20

Figure 21A

Figure 21B

Figure 22

Figure 23

Figure 24

Figure 25

Figure 26

Figure 27

Figure 28

Figure 29A

Figure 29B

Figure 30

Figure 31

Figure 32

Figure 33A

Figure 33B

Figure 34A

Figure 34B

Figure 35

Figure 36

Figure 37

Figure 38

Figure 39

Figure 40

Figure 41A

Figure 41B

Figure 42

Figure 43A

Figure 43B

Figure 44

Figure 45

Figure 46A

Figure 46B

Figure 47

Figure 48

Figure 49

Figure 50

Figure 51A

Figure 51B

Figure 52

Figure 53A

Figure 53B

Mode for Carrying Out the Invention

[0009] Hereinafter, the present embodiment will be described with reference to the drawings. For the drawings, the same or equivalent elements are denoted by the same reference numerals, and redundant descriptions are omitted. Note that the present embodiment described below does not unduly limit the content described in the claims. Also, not all of the configurations described in the present embodiment are essential constituent elements of the present disclosure.

[0010] 1. Example of System Configuration The information processing system 10 according to this embodiment determines the motor function of a care recipient who receives assistance (including nursing care) by an assistant. In particular, in this embodiment, the information processing system 10 includes a bed 100, and by having the care recipient use the bed 100 in daily life, the motor function is determined without the care recipient being aware of it. Here, the care recipient may be a resident of a nursing facility, a target of home care, or a patient hospitalized in a hospital. The assistant includes a care manager, a nurse, a visiting helper, etc. The assistant may also include a nurse, an occupational therapist, a physical therapist, etc. However, since the method of this embodiment evaluates the motor function of the user who uses the bed 100, the user is not limited to a care recipient. For example, the information processing system 10 may evaluate the motor function of a person (a healthy person) who does not receive assistance in order to determine the future need for assistance. Hereinafter, the information processing system 10, the bed 100 included in the information processing system 10, and the motor function evaluation device 200 will be described in detail.

[0011] FIG. 1 is a configuration example of an information processing system 10 including a motor function evaluation device 200 according to this embodiment. The information processing system 10 includes, for example, a bed 100 and a motor function evaluation device 200. However, the configuration of the information processing system 10 is not limited to the example in FIG. 1, and modified implementations such as omitting some configurations and adding other configurations are possible.

[0012] The bed 100 is a bedding used by the care recipient. Here, the bed 100 has legs 160a and a bottom 160b as movable parts 160, and may be a nursing bed capable of adjusting the height by moving the legs 160a and adjusting the angle (such as the back angle) by moving the bottom 160b. A load sensor 140 for detecting pressure is arranged on the bed 100. FIG. 1 shows an example in which load sensors 140A - 140D are arranged at four locations on the bed 100 (narrowly speaking, four locations corresponding to the four corners of the bed 100). However, the number and position of the load sensors 140 are not limited to this, and various modified implementations are possible.

[0013] The motion function evaluation device 200 is connected to the bed 100 and is a device that evaluates the motion function of the assisted person based on the output of the load sensor 140. The connection between the bed 100 and the motion function evaluation device 200 may be made wired using a cable such as USB (Universal Serial Bus), or may be made wirelessly using a method such as IEEE802.11 or Bluetooth. The motion function evaluation device 200 is, for example, a PC (Personal Computer) as shown in FIG. 1. However, the motion function evaluation device 200 is not limited to a PC, and may be a portable terminal device such as a smartphone, or may be a server system. Further, the motion function evaluation device 200 may be configured integrally with the bed 100. For example, the motion function evaluation device 200 may be incorporated in a control box that controls each part of the bed 100.

[0014] When the motion function evaluation device 200 is realized by a server system, the server system may be one server, or may include a plurality of servers. For example, the server system may include a database server and an application server. The database server may store the output of the load sensor 140 transmitted from the bed 100. The application server performs various processes based on this information. The application server executes the processes of each step described later using, for example, FIG. 4 and the like. Here, the plurality of servers may be physical servers or virtual servers. Further, when a virtual server is used, the virtual server may be provided in one physical server, or may be distributed and arranged in a plurality of physical servers. As described above, various modifications of the specific configuration of the server system in the present embodiment are possible.

[0015] FIG. 2 is a diagram showing a configuration example of the bed 100. The bed 100 includes, for example, a processing unit 110, a storage unit 120, a communication unit 130, a load sensor 140, a drive unit 150, and a movable unit 160. However, the configuration of the bed 100 is not limited to FIG. 2, and modifications such as omitting some configurations and adding other configurations are possible.

[0016] The processing unit 110 of this embodiment is composed of the following hardware. The hardware can include at least one of a circuit for processing digital signals and a circuit for processing analog signals. For example, the hardware can be composed of one or more circuit devices mounted on a circuit board or one or more circuit elements. The one or more circuit devices are, for example, an IC (Integrated Circuit), an FPGA (field-programmable gate array), etc. The one or more circuit elements are, for example, a resistor, a capacitor, etc.

[0017] Also, the processing unit 110 may be realized by the following processor. The bed 100 of this embodiment includes a memory for storing information and a processor that operates based on the information stored in the memory. The information is, for example, a program and various data, etc. The memory may be the storage unit 120 or another memory. The processor includes hardware. The processor can use various processors such as a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a DSP (Digital Signal Processor), etc. The memory may be a semiconductor memory such as SRAM (Static Random Access Memory), DRAM (Dynamic Random Access Memory), a flash memory, etc., a register, a magnetic storage device such as an HDD (Hard Disk Drive), or an optical storage device such as an optical disk device. For example, the memory stores instructions readable by a computer, and when the processor executes the instructions, the functions of the processing unit 110 are realized as processing. The instructions here may be instructions in an instruction set constituting a program or instructions for instructing operations to the hardware circuit of the processor.

[0018] For example, the processing unit 110 may be a sensor control circuit that acquires the sensor outputs of the load sensors 140 (load sensors 140A - 140D). Alternatively, in addition to acquiring the sensor outputs, the processing unit 110 may be a load calculation circuit that performs processing to obtain load value information and center-of-gravity information based on the sensor outputs. The load value information is information representing the magnitude of the load caused by the body movement of the user (care recipient) on the bed 100. The center-of-gravity information is information representing the transition of the position of the center of gravity of the load applied to the bed 100 (specifically, the center of gravity of the user using the bed 100).

[0019] The storage unit 120 is a work area of the processing unit 110 and stores various information. The storage unit 120 can be realized by various memories, and the memory may be a semiconductor memory such as SRAM, DRAM, ROM (Read Only Memory), flash memory, or may be a register, a magnetic storage device, or an optical storage device. The storage unit 120 may store, for example, sensor outputs, load value information, and center-of-gravity information. Alternatively, the storage unit 120 may store a drive program or the like for driving the drive unit 150 described later.

[0020] The communication unit 130 is an interface for performing communication via a network. When the bed 100 performs wireless communication, it includes, for example, an antenna, an RF (radio frequency) circuit, and a baseband circuit. However, as described above, the bed 100 may perform wired communication, and in that case, the communication unit 130 may include a communication interface such as a USB connector or an Ethernet connector, and a control circuit for the communication interface. The communication unit 130 may operate according to the control by the processing unit 110, or may include a processor for communication control different from the processing unit 110.

[0021] The load sensor 140 is attached to the bed 100 and detects the load applied to the bed 100. The load sensor 140 may be, for example, a piezoelectric sensor using a piezoelectric body that generates electric charge when pressure is applied, or a strain sensor that detects the deformation of a material due to pressure as a change in electrical resistance. Also, various methods are known for load sensors, including the above piezoelectric sensors and strain sensors, and these methods can be widely applied in this embodiment. Therefore, the detailed configuration of the load sensor 140 will be omitted.

[0022] The drive unit 150 is an actuator or the like that drives the movable part 160 of the bed 100. The bed 100 of this embodiment may be, for example, a nursing bed whose angle of the bottom 160b, which is the surface on which the mattress is placed, can be adjusted. For example, the bed 100 has a plurality of bottoms 160b divided into a plurality of members as the movable part 160, and the drive unit 150 adjusts the angle of the bottom 160b by changing the position and posture of at least a part of the plurality of bottoms 160b based on the control of the processing unit 110. For example, by driving the drive unit 150, control of the back angle (control of the bottom 160b on the head side) and control of the foot angle (control of the bottom 160b on the foot side) may be performed.

[0023] Also, the bed 100 may be a bed whose height of the leg part 160a can be adjusted. In this case, the drive unit 150 is an actuator or the like that drives the leg part 160a. In this way, it is possible to adjust the height of the entire bed 100 by driving the drive unit 150.

[0024] FIG. 3 is a block diagram showing a detailed configuration example of the motor function evaluation device 200. The motor function evaluation device 200 may include, for example, a processing unit 210, a storage unit 220, a communication unit 230, a display unit 240, and an operation unit 250. However, the configuration of the motor function evaluation device 200 is not limited to FIG. 3, and modified implementations such as omitting some configurations and adding other configurations are possible.

[0025] The processing unit 210 is constituted by hardware including at least one of a circuit for processing digital signals and a circuit for processing analog signals. Further, the processing unit 210 may be realized by a processor. The processor can use various processors such as a CPU, a GPU, and a DSP. The function of the processing unit 210 is realized as processing by the processor executing instructions stored in the memory of the motor function evaluation device 200.

[0026] The processing unit 210 may include an acquisition unit 211, an evaluation processing unit 212, and an output processing unit 213.

[0027] The acquisition unit 211 acquires load value information and center of gravity information based on the load sensor 140 of the bed 100. The acquisition here may be, for example, a process of acquiring the load value information and the center of gravity information calculated by the processing unit 110 of the bed 100 via wired or wireless communication. Alternatively, the acquisition here may be a process of acquiring the sensor output of the load sensor 140 from the bed 100 and obtaining the load value information and the center of gravity information based on the sensor output. In other words, in this embodiment, the process of obtaining the load value information and the center of gravity information may be executed by the processing unit 110 of the bed 100, or may be executed by the processing unit 210 (acquisition unit 211) of the motor function evaluation device 200. Further, the process of obtaining the load value information and the center of gravity information may be realized by distributed processing of the bed 100 and the motor function evaluation device 200.

[0028] In this embodiment, the process using both the load value information and the center of gravity information is not essential, and one of them may be omitted. Therefore, the acquisition unit 211 acquires at least one of the load value information and the center of gravity information.

[0029] Based on the information acquired by the acquisition unit 211, the evaluation processing unit 212 performs processing to evaluate the motor function of the assisted person. The evaluation processing here includes at least one of a physical function evaluation using load value information and a limb function evaluation using center of gravity information. Also, when an abnormality is detected in the motor function, functional recovery training may be performed on the bed 100. The evaluation of the motor function in this embodiment may include an evaluation of whether the functional recovery training is being appropriately performed (hereinafter also referred to as functional recovery training evaluation). Details of each evaluation process will be described later.

[0030] The output processing unit 213 outputs the processing result in the evaluation processing unit 212. For example, the output processing unit 213 may output the results of the physical function evaluation and the limb function evaluation as described later using FIGS. 8A - 8C, FIG. 14, etc. Also, when it is determined that functional recovery training is necessary, the output processing unit 213 may output the content (exercise menu) of the specific functional recovery training. The output here is, for example, a display on the display unit 240, but other forms of output such as output using voice may also be performed. Also, the output processing of the output processing unit 213 is not limited to the processing of outputting information to the display unit 240 etc. of the motor function evaluation device 200, and may include processing of outputting information to the display unit etc. of other devices. Other devices here are, for example, devices used by caregivers or assisted persons, and may include the terminal devices 310 - 350 described later using FIGS. 36 and 39.

[0031] The storage unit 220 is a work area of the processing unit 210 and is realized by various memories such as SRAM, DRAM, and ROM. The storage unit 220 may store the history of evaluation results such as physical function evaluation and limb function evaluation.

[0032] The communication unit 230 is an interface for performing communication via a network and includes, for example, an antenna, an RF circuit, and a baseband circuit. The communication unit 230 performs communication with the bed 100 via the network, for example. Note that the communication unit 230 may be a communication interface for performing wired communication, and various modifications of the specific communication method are possible.

[0033] The display unit 240 is an interface for displaying various information, and may be a liquid crystal display, an organic EL display, or a display of another type. The operation unit 250 is an interface for receiving user operations. The operation unit 250 may be a pointing device such as a mouse, a keyboard, or buttons provided on the motor function evaluation device 200. Further, the display unit 240 and the operation unit 250 may be a touch panel configured integrally.

[0034] As described above, the motor function evaluation device 200 according to the present embodiment includes an acquisition unit 211 and an evaluation processing unit 212. The acquisition unit 211 is attached to the bed 100, and based on the load sensor 140 that detects the load applied to the bed 100, acquires at least one of load value information representing the magnitude of the load caused by the body movement of the user on the bed 100 and gravity center information representing the transition of the gravity center position of the user caused by the body movement of the user. The evaluation processing unit 212 evaluates the motor function of the user based on at least one of the acquired load value information and gravity center information.

[0035] According to the method of the present embodiment, based on the load sensor 140 of the bed 100, the motor function of the user (care recipient) using the bed 100 can be evaluated. Therefore, the care recipient can naturally receive an objective motor function evaluation by using the bed 100 in daily life without being particularly conscious of the motor function evaluation.

[0036] Also, part or all of the processing performed by the information processing system 10 of the present embodiment may be realized by a program. The processing performed by the information processing system 10 is, in a narrow sense, the processing performed by the processing unit 210 of the motor function evaluation device 200, but may be the processing executed by the processing unit 110 of the bed 100, or the processing executed in cooperation by the processing unit 210 and the processing unit 110.

[0037] The program according to this embodiment can be stored in a non-transitory information storage medium (information storage device), which is a computer-readable medium, for example. The information storage medium can be realized by, for example, an optical disk, a memory card, an HDD, or a semiconductor memory. The semiconductor memory is, for example, a ROM. The processing unit 210 and the like perform various processes of this embodiment based on the program stored in the information storage medium. That is, the information storage medium stores a program for causing a computer to function as the processing unit 210 and the like. A computer is a device including an input device, a processing unit, a storage unit, and an output unit. Specifically, the program according to this embodiment is a program for causing a computer to execute each step described later with reference to FIG. 4 and the like.

[0038] Also, the method of this embodiment can be applied to an information processing method including the following steps. The motor function evaluation method includes a step of acquiring at least one of load value information representing the magnitude of the load caused by the body movement of the user on the bed and centroid information representing the transition of the centroid position of the user caused by the body movement, based on a load sensor attached to the bed and detecting the load applied to the bed; and a step of evaluating the motor function of the user based on at least one of the acquired load value information and centroid information.

[0039] 2. Details of Processing The processing of the motor function evaluation device 200 according to this embodiment will be described. First, the overall processing including a plurality of evaluation processes will be described, and then the details of each evaluation process will be described.

[0040] Hereinafter, the movement of the care recipient on the bed 100 will be considered by dividing it into four phases: when lying in bed, when awake, when sleeping, and when getting out of bed. When lying in bed refers to the phase in which the care recipient who was outside the bed 100 lies horizontally on the mattress of the bed 100 (transitions to a lying position). When lying in bed, the care recipient first places one hand and one knee on the bed 100, and then places both hands and both knees. In that state, the care recipient moves on the bed 100 and transitions to a lying position.

[0041] The waking and sleeping phases occur after the lying-in-bed phase and represent the phases in which the care recipient assumes a lying position on the bed 100. The waking phase represents the phase in which the care recipient is in a waking state, and the sleeping phase represents the phase in which the care recipient is in a sleeping state. Note that the determination of whether the care recipient is in a waking state or a sleeping state may be performed by the movement function evaluation device 200 based on the load sensor 140 of the bed 100, or may be performed using a sensor device other than the load sensor 140. Methods for determining sleep / wakefulness are widely known, and since these methods can be widely applied in this embodiment, further detailed description thereof is omitted.

[0042] The getting-out-of-bed phase represents the phase in which the care recipient who was on the bed 100 gets off the bed 100. During the getting-out-of-bed phase, first, the care recipient moves to a state of sitting on the edge of the bed 100 with feet on the floor (hereinafter also referred to as the edge sitting position), and then gets out of the bed by moving from the edge sitting position to a standing position. In this embodiment, the getting-out-of-bed phase may be further subdivided into a plurality of phases.

[0043] For example, the getting-out-of-bed phase may include three phases: a getting-out-of-bed preparation period, a getting-out-of-bed operation period, and a getting-out-of-bed completion period. The getting-out-of-bed preparation period represents the phase until the care recipient who was on the bed 100 moves to the edge sitting position. The getting-out-of-bed operation period represents the phase in which an action of pushing back is executed to move from the edge sitting position to a standing position until the buttocks of the care recipient float from the bed 100. Note that the action of pushing back may be an action of pushing the bed with the hand, or an action of utilizing the reaction of the upper body without using the hand. Hereinafter, an example in which the care recipient pushes the bed with the hand during the getting-out-of-bed operation period will be mainly described, but the action can be appropriately replaced with other actions. The getting-out-of-bed completion period represents the phase until the buttocks of the care recipient float from the bed 100 and the body is completely separated from the bed 100.

[0044] 2.1 Flow of processing FIG. 4 is a flowchart for explaining the processing of the motor function evaluation apparatus 200. When this processing is started, first, in step S101, the processing unit 210 (narrowly, the acquisition unit 211) of the motor function evaluation apparatus 200 acquires load value information based on the load sensor 140 of the bed 100. The load value information here includes one or more load values. The load value is information representing the magnitude of the load applied to the bed 100.

[0045] For example, as shown in FIG. 1, when four load sensors 140A - 140D are provided as the load sensor 140, the acquisition unit 211 may acquire the output of each of the four load sensors 140A - 140D as the load value, or may acquire the total value of the respective outputs as the load value. As described above, the acquisition here may be a process of receiving the load value calculated by the bed 100 via the communication unit 230, or may be a process of calculating the load value based on the four sensor outputs output from the bed 100. Further, the load value is not limited to the total value or the average value, and may be other values obtained based on the sensor outputs of the plurality of load sensors 140.

[0046] For example, taking the outputs of the load sensors 140A to 140D at a given timing t as N At , N Bt , N Ct , N Dt when, the load value N(t) at the timing t is the total value of N At , N Bt , N Ct , N Dt and so on. The acquisition unit 211 measures the load value at at least one or more timings, and acquires the plurality of measured load values as load value information. The load value information may be, for example, a waveform representing the time change of the load value, as will be described later with reference to FIGS. 6 and 7. Note that, in the above, an example using the outputs of the four load sensors 140A - 140D has been described, but the load value information may be obtained based on the outputs of some of these load sensors 140, and may be, for example, the sensor output of any one of the load sensors 140.

[0047] Also in step S102, the acquisition unit 211 acquires the center-of-gravity information based on the load sensor 140 of the bed 100. For example, as will be described later with reference to FIG. 12 and the like, the acquisition unit 211 acquires a two-dimensional coordinate plane corresponding to a horizontal plane and the respective coordinate values of the four load sensors 140A-140D in the two-dimensional coordinate plane. Then, the acquisition unit 211 may obtain, as the center-of-gravity position, the coordinate values representing the center of gravity of the care recipient based on the sensor outputs of the four load sensors 140A-140D.

[0048] Also, the acquisition unit 211 obtains the center-of-gravity position at at least one or more timings, and acquires the obtained multiple center-of-gravity positions as center-of-gravity information. The center-of-gravity information may be information representing the time change of the center-of-gravity position, such as a locus described later with reference to FIG. 12. Alternatively, like the speeds v1 and v2 described later with reference to FIG. 12, the center-of-gravity information may be information representing the change speed of the center of gravity in a predetermined direction (narrowly, the right direction and the left direction).

[0049] The processes of steps S101 and S102 may be executed for a predetermined period (which may be, for example, in units of one day or a period from bedtime to waking up the next morning) including each phase such as when lying in bed, awake, sleeping, and getting out of bed. For example, the acquisition unit 211 acquires load value information and center-of-gravity information for each of when lying in bed, awake, sleeping, and getting out of bed based on the sensor output of the load sensor 140 during the predetermined period.

[0050] Note that in the processing stages of steps S101 and S102, it is not particularly determined which of when lying in bed, awake, sleeping, and getting out of bed it corresponds to, and after the completion of the target period, the determination of each phase may be performed based on features such as the waveform of the load value information and the center-of-gravity position in the center-of-gravity information. Alternatively, the determination of the phase may be executed based on information different from the load value information, such as a captured image of the care recipient or an input operation by the caregiver.

[0051] Next, in step S103, the evaluation processing unit 212 performs a physical function evaluation. The physical function evaluation includes at least one of a motor function evaluation based on load value information during lying in bed and a motor function evaluation based on load value information during getting out of bed. Details will be described later with reference to FIG. 5 and the like.

[0052] In step S104, the evaluation processing unit 212 performs a four-limb function evaluation. The four-limb function evaluation is a motor function evaluation based on the center-of-gravity information. Narrowly speaking, the four-limb function evaluation is an evaluation for each of the four limbs of the right arm, left arm, right leg, and left leg. However, the four-limb function evaluation may include evaluations related to the right and left halves of the body, evaluations related to the upper and lower halves of the body, evaluations related to frailty of the whole body, and the like. Details will be described later with reference to FIG. 11 and the like.

[0053] In step S105, the evaluation processing unit 212 determines whether a problem has been detected in the physical function evaluation or the four-limb function evaluation. The problem detection here corresponds to, for example, a case where the difference between the index value representing the motor function of the care recipient and a given determination reference value is large. Here, as will be described later, the index value may be a waveform representing the temporal change of the load value, may be the moving speed of the center-of-gravity position in a predetermined direction, or may be another index value obtained from the load value information or the center-of-gravity information.

[0054] If it is determined that there is a problem (step S105: Yes), in step S106, the evaluation processing unit 212 performs processing for functional recovery training. For example, if it is determined that there is a problem in the physical function evaluation, as will be described later as the processing of step S205 in FIG. 5, in step S103, the output processing unit 213 may present desirable training content and perform an output prompting execution. Similarly, if it is determined that there is a problem in the four-limb function evaluation, for example, in step S104, the output processing unit 213 may present desirable training content and perform an output prompting execution. In these cases, it is determined as Yes in step S105, and the functional recovery training in step S106 is executed. Note that the exercises executed in the functional recovery training are exercises that can be executed on the bed 100.

[0055] The process of step S106 may include a process in which the acquisition unit 211 acquires load value information and center of gravity information during training execution, and a process in which the evaluation processing unit 212 evaluates whether the training is being properly executed based on the load value information and the center of gravity information (functional recovery training evaluation). Details will be described later with reference to FIG. 20 and the like. Also, in step S106, both the load value information and the center of gravity information are not essential, and the acquisition of either one may be omitted. For example, the evaluation processing unit 212 determines the information to be used according to the content of the movement in the functional recovery training.

[0056] In the above, as an example of the evaluation of the motor function, three evaluations, namely, the physical function evaluation, the limb function evaluation, and the functional recovery training evaluation, have been described. However, in this embodiment, all of them are not essential, and one or two of them may be omitted. For example, the motor function evaluation device 200 may perform the physical function evaluation and the limb function evaluation without performing the functional recovery training evaluation. Also, the motor function evaluation device 200 may not perform one of the physical function evaluation and the limb function evaluation. Also, regarding the necessity of the functional recovery training, it may be determined using other methods, and the motor function evaluation device 200 of this embodiment may perform only the functional recovery training evaluation.

[0057] Also, at least one of the processes of steps S101 and S102 may be changed according to the content of the motor function evaluation to be executed. For example, when the limb function evaluation is omitted, the acquisition process of the center of gravity information in step S102 may be omitted. Also, the acquisition process of the load value information in step S101 may be omitted. In addition, in the method of this embodiment, a part of the processes described above with reference to FIG. 4 can be appropriately omitted.

[0058] 2.2 Physical Function Evaluation The physical function evaluation process shown in step S103 of FIG. 4 will be described. The acquisition unit 211 of the motor function evaluation device 200 acquires load value information during the period when the user lies in bed or gets out of bed (when lying in bed or getting out of bed), and the evaluation processing unit 212 may evaluate the motor function of the user when lying in bed or getting out of bed based on the load value information.

[0059] As described above, when in bed, after the user to be assisted places one hand and one knee on the bed 100, the user then places both hands and both knees on the bed and moves on the bed 100 in that state to transition to a lying position. That is, when in bed, since the user to be assisted mainly needs to use the arms to maintain and move the posture, the importance of the upper body motor function is relatively high. On the other hand, when getting out of bed, the user moves on the bed 100, lowers the feet to the floor to assume a sitting position, and then needs to perform a standing up motion, so the importance of the lower body motor function is relatively high. That is, when in bed and when getting out of bed, the user to be assisted needs to greatly change the posture by performing movements using the upper limbs and lower limbs. Therefore, by targeting such movements, it is possible to appropriately evaluate the motor function of the user to be assisted. In particular, when in bed or when getting out of bed, movements such as getting on and off the bed 100 and applying a large load to the bed 100 with the arms, knees, etc. occur, so a large fluctuation in the load value is predicted. Therefore, by using the load value information, it is possible to improve the evaluation accuracy of the motor function.

[0060] In the motor function evaluation device 200 of the present embodiment, the acquisition unit 211 may acquire load value information during the period when the user is in bed, and the evaluation processing unit 212 may perform a first process of evaluating the upper body motor function of the user. As described above, since movements using the arms are required when in bed, it is possible to appropriately determine the upper body motor function by using the load value information when in bed.

[0061] Alternatively, in the motor function evaluation device 200 of the present embodiment, the acquisition unit 211 may acquire load value information during the period when the user gets out of bed, and the evaluation processing unit 212 may perform a second process of evaluating the lower body motor function of the user. As described above, since movements using the lower limbs are required when getting out of bed, it is possible to appropriately determine the lower body motor function by using the load value information when getting out of bed.

[0062] In particular, the evaluation processing unit 212 of the present embodiment may perform a second process of evaluating the lower body motor function of the user based on the load value information during the pre-transfer period, which is the period when the user transitions to the sitting position. Depending on the condition of the care recipient, it may be difficult to stand up (transition to the standing position), but it is conceivable that the user can sit upright. By using the load value information during the pre-transfer period for processing, it becomes possible to evaluate the motor function of users who have difficulty standing up.

[0063] The motor function evaluation device 200 may perform both the first process and the second process, or may perform either one of them. Hereinafter, an example of performing both the first process and the second process will be described.

[0064] FIG. 5 is a flowchart for explaining the body function evaluation process shown in step S103 of FIG. 4. As a premise for this process, it is assumed that the load value information during lying in bed and the load value information during getting out of bed are acquired in step S101 of FIG. 4.

[0065] First, in step S201, the evaluation processing unit 212 evaluates the motor function during lying in bed based on the load value information during lying in bed, and determines whether there is a problem.

[0066] FIG. 6 is a graph showing the load value information of a care recipient without motor function problems (hereinafter also referred to as a healthy person). The horizontal axis in FIG. 6 represents time, and the vertical axis represents the load value. For convenience of explanation, FIG. 6 shows the load value information not only during lying in bed but also during waking, sleeping, and getting out of bed. As described above, in the present embodiment, the period of getting out of bed is further divided into a pre-transfer period, a transfer operation period, and a transfer completion period for explanation.

[0067] For example, the evaluation processing unit 212 extracts, as the load value information during lying in bed, a section that starts from a state where the load value is low and ends at a state where the load value has increased by a predetermined amount or more. The starting point corresponds to a state where the care recipient is not on the bed 100, and is a state where a load value representing the weight of bedding such as a mattress and a pillow is detected. The ending point corresponds to a state where the care recipient is on the bed 100, and is a state where a load value representing the weight of the care recipient in addition to the weight of bedding such as a mattress and a pillow is detected. Regarding specific load values, various modifications can be made, such as adjusting the offset so that the load value in a state where the weight of bedding or the like is added becomes zero.

[0068] For example, in the waking state after the transition to the lying position is completed, although a load due to the intentional body movement of the care recipient is detected, the variation range of the load is considered to be sufficiently smaller than the variation range caused by the movement during lying in bed. Therefore, the evaluation processing unit 212 can identify the load value information during lying in bed by extracting a section where the load value has increased by an amount equivalent to the weight and the variation range is a predetermined amount or more. As described above, when the start timing and end timing during lying in bed are identified using an imaging image or the like of the care recipient, the evaluation processing unit 212 may determine the information of the identified period as the load value information during lying in bed.

[0069] As shown in FIG. 6, a healthy person can smoothly execute the movements that occur during lying in bed, such as placing one hand on the bed 100, placing both hands and knees on the bed 100, and lying on the side of the bed 100, in a relatively short time. Therefore, when each movement is performed, the part in contact with the bed 100 is pressed against the bed 100 with a relatively strong force, so that the load value draws a sharp peak as shown in FIG. 6. Here, a sharp peak means that each of the rising and falling periods is short and the variation amount of the load value is large. In addition, since a healthy person can smoothly execute the operation of transitioning to the lying position, there is a characteristic that the time from the change start timing of the load value to the transition completion timing to the lying position (the length of the lying in bed phase) is relatively short.

[0070] FIG. 7 is a graph showing load value information of a care recipient with reduced motor function (hereinafter also referred to as a frail patient). Similar to FIG. 6, the horizontal axis in FIG. 7 represents time, and the vertical axis represents the load value. Since frail patients have difficulty performing each action smoothly when lying in bed compared to healthy individuals, their movements are slow. As a result, as shown in FIG. 7, in the waveform representing the load value information of frail patients, the peak becomes broad or no distinct peak is detected. A broad peak means that each of the rising and falling periods is long and the amount of variation in the load value is small. In addition, frail patients are characterized by a relatively long time from the timing of the start of the change in the load value to the timing of the completion of the transition to the lying position.

[0071] The evaluation processing unit 212 determines whether there is a problem with the motor function during lying in bed based on the differences in the waveforms of healthy individuals and frail patients shown in FIGS. 6 and 7. For example, the evaluation processing unit 212 calculates feature amounts such as the time width of the peak (the time required for rising and falling), the peak value (the amplitude value of the load at the peak), and the time from the start to the end of the lying phase based on the load value information during lying in bed, and may make the determination in step S201 based on these feature amounts. For example, a process of obtaining a first feature amount from the load value information of healthy individuals in advance, obtaining a second feature amount from the load value information of frail patients, and setting a determination threshold based on the first feature amount and the second feature amount may be executed. The determination threshold is stored in the storage unit 220. The evaluation processing unit 212 compares the feature amount of the target care recipient with the determination threshold, and determines that there is no problem if the feature amount is closer to the first feature amount than the determination threshold, and determines that there is a problem otherwise.

[0072] However, the determination process based on the load value information is not limited to the above examples. For example, a process of comparing the waveforms of the load value information of healthy individuals and the target care recipient may be performed, and if the similarity of the waveforms is equal to or greater than a predetermined value, it may be determined that there is no problem, and if it is less than the predetermined value, it may be determined that there is a problem. Also, the comparison target of the load value information may be the waveform of the load value information of frail patients.

[0073] Also, in this embodiment, a trained model for determining whether there is a problem with the target care recipient may be created by performing machine learning using the load value information of healthy individuals and the load value information of frail patients as training data. The trained model here is a model that takes load value information as input and outputs the probability of having a problem (for example, the probability of being a healthy individual). Note that the input may be the waveform of the load value information itself or a feature amount obtained from the waveform. Also, the machine learning here may be learning using a neural network, learning using SVC (support-vector machine), learning using a method developed from these methods, or learning using other methods.

[0074] Note that the evaluation processing unit 212 may perform at least one of a speed evaluation based on the time required for the change in the magnitude of the load represented by the load value information and a power evaluation based on the magnitude of the load as an evaluation of the motor function. For example, the speed evaluation is performed based on information obtained by dividing the amplitude at the peak by the rise and fall times. Alternatively, the speed evaluation may be performed based on the width of the peak (the time of at least one of the rise and fall), or may be performed based on the time required for the execution of the in-bed phase. Also, the power evaluation is performed based on the amplitude at the peak (the difference between the load value before the change starts or after the change is completed and the maximum value of the load value at the peak). In this way, the evaluation processing unit 212 obtains a speed feature amount related to the change time and a power feature amount related to the change amount of the load value based on the load value information, performs a speed evaluation based on the speed feature amount, and performs a power evaluation based on the power feature amount. Alternatively, a model that outputs a speed evaluation value and a power evaluation value may be created as a trained model. In this case, it is desirable that correct data indicating the presence or absence of a problem is given for each of speed and power for the training data.

[0075] By performing at least one of power evaluation and speed evaluation, as an evaluation of movement using load value information, it becomes possible to evaluate from the viewpoint of whether the movement is executed quickly, or from the viewpoint of whether sufficient force is applied during the movement, or both. For example, in the method of the present embodiment, when there is a problem with the motor function, it becomes possible to perform a more detailed evaluation of whether there is a problem with either speed or power. Hereinafter, an example of performing both speed evaluation and power evaluation will be described, but either one may be omitted.

[0076] For example, the evaluation processing unit 212 may evaluate whether there is a problem with speed evaluation and whether there is a problem with power evaluation based on the load value information during lying in bed. When it is determined that there is a problem in at least one of the speed evaluation and the power evaluation (step S201: No in FIG. 5), it is considered that there is a problem with the motor function of the upper body as described above. Therefore, after the evaluation processing unit 212 performs the process of turning on the flag indicating the abnormality (upper limb frailty) of the upper body in step S202, it proceeds to step S203. When it is determined that there is no problem (step S201: Yes), the process of step S202 is omitted and the process proceeds to step S203.

[0077] Also in step S203, the evaluation processing unit 212 evaluates the movement function at the time of getting out of bed based on the load value information at the time of getting out of bed, and determines whether there is a problem. The time of getting out of bed here may be, for example, the period of preparing to get out of bed. For example, the evaluation processing unit 212 may evaluate whether there is a problem with speed evaluation and whether there is a problem with power evaluation based on the load value information during the period of preparing to get out of bed. The start point of the period of preparing to get out of bed corresponds to the timing when it is detected that the variation in the load value becomes larger compared to when lying in bed (awake or asleep).

[0078] Also, in the semi-upright position, since part of the body weight is applied to the floor by touching the feet to the floor, the load value decreases to a distinguishable extent from the state where the whole body is placed on the bed 100. That is, the evaluation processing unit 212 can identify the load value information during the bed exit preparation period by identifying a section in which the amount of change in the load value is equal to or greater than a predetermined value and the load value decreases to an extent corresponding to the semi-upright position. Alternatively, in the subsequent bed exit operation period following the bed exit preparation period, since an action of applying a reaction force is executed to shift to the standing position, the load value rapidly increases. Therefore, as the end point of the bed exit preparation period, the timing immediately before (narrowly speaking) the rapid increase in the load value is detected may be used. Note that the bed exit phase here is not limited to the bed exit preparation period, and may be the bed exit operation period or the bed exit completion period. Also, the bed exit phase may be a period combining two or more of the bed exit preparation period, the bed exit operation period, and the bed exit completion period, and various modifications can be made to the specific period.

[0079] During the bed exit preparation period, the care recipient moves to the end of the bed 100 while touching the hands and knees to the mattress, and performs a movement to shift to the semi-upright position by touching the feet to the floor. Then, while a healthy person can perform the movement smoothly, a frail patient performs the movement slowly. Therefore, compared to a healthy person, the peak in the waveform of the load value information of a frail patient becomes broader, and the time from the start to the completion of the bed exit preparation period becomes longer.

[0080] Therefore, similar to the processing during lying in bed, the evaluation processing unit 212 can determine whether there is a problem with the motor function based on the difference in the waveforms between the healthy person and the frail patient shown in FIGS. 6 and 7. As described above, various modifications can be made to the specific method, such as processing for comparing a feature amount with a determination threshold value and processing using a learned model.

[0081] When it is determined that there is a problem in at least one of the speed evaluation and the power evaluation based on the load value information during the bed exit preparation period (step S203: No), as described above, it is considered that there is a problem in the lower body motor function. Therefore, after the evaluation processing unit 212 performs the process of turning on the flag indicating the abnormality (lower limb frailty) of the lower body in step S204, it proceeds to step S205. When it is determined that there is no problem (step S203: Yes), the process of step S204 is omitted and the process proceeds to step S205.

[0082] In step S205, the output processing unit 213 outputs the evaluation result of the upper body based on the load value information during bed rest and the evaluation result of the lower body based on the load value information at the time of getting out of bed. The output here is, for example, the display on the display unit 240 of the motor function evaluation device 200, but it may also be performed by other devices.

[0083] Figures 8A - 8C are examples of the display screens output in step S205. As shown in Figure 8A, the output processing unit 213 may display the evaluation result of the upper body based on the load value information during bed rest. In Figure 8A, an example is shown where the results of the speed evaluation, the power evaluation, and the comprehensive determination are each displayed as scores. The result of the comprehensive determination may be the combined result of the speed evaluation result and the power evaluation result (for example, a weighted average, etc.), or it may be an evaluation result using a feature quantity different from both the speed evaluation and the power evaluation (for example, an evaluation result based on the similarity as a whole waveform). The evaluation result here is, for example, numerical data with a full score of 100 points, but it may also be data in other forms. In the example of Figure 8A, scores of a certain value or more are obtained in all of the speed evaluation, the power evaluation, and the comprehensive determination. Therefore, it is determined that there is no problem with the upper body motor function (step S201: Yes), and the upper limb frailty flag is off.

[0084] Also, as shown in FIG. 8B, the output processing unit 213 may display an evaluation result of the lower body based on the load value information at the time of getting out of bed. Similarly in FIG. 8B, examples of displaying the results of speed evaluation, power evaluation, and comprehensive determination as scores are shown. In the example of FIG. 8B, the speed evaluation is particularly low and the score of the comprehensive determination is also low. Therefore, the lower limb frailty flag is set to on in step S204. In this case, the output processing unit 213 may output information specifying movements that may specifically cause problems. In the example of FIG. 8B, by displaying texts such as "Movements in bed have become slow" and "Movements when touching the floor with the feet are slow", it is possible for the viewed user (the care recipient or caregiver) to understand the differences from a healthy person.

[0085] Also, as shown in FIG. 8C, the output processing unit 213 may display an evaluation result based on the determination result at the time of lying in bed and the determination result at the time of getting out of bed. In FIG. 8C, the evaluation result of the upper body based on the load value information at the time of lying in bed and the evaluation result of the lower body based on the load value information at the time of getting out of bed are collectively displayed. The score here is the same as, for example, the score of the comprehensive determination in FIGS. 8A and 8B. Also, in the example of FIG. 8C, since the upper limb frailty flag is off, problems related to the upper body are not output. On the other hand, since the lower limb frailty flag is on, the output processing unit 213 outputs that there is a problem with the lower body.

[0086] Furthermore, when it is determined that there is an abnormality in the evaluation of the motor function, the output processing unit 213 may perform an output prompting training to recover the motor function. Here, since the lower limb frailty flag is on, the output processing unit 213 performs an output prompting training to recover the function of the lower body. In the example of FIG. 8C, the output processing unit 213 promotes the implementation of the function recovery training of the knee hugging movement by displaying the text "It is recommended to perform rehabilitation to speed up the knee hugging movement". Note that the output processing unit 213 is not limited to outputting text, and may perform processing to present specific movement contents using voice, still images, or moving images.

[0087] For example, information indicating either for the upper body or the lower body is associated with the exercises performed as functional recovery training, and the evaluation processing unit 212 may determine which exercise to recommend based on the on / off states of the upper limb frailty flag and the lower limb frailty flag. The output processing unit 213 outputs information prompting the exercise determined by the evaluation processing unit 212.

[0088] Alternatively, information indicating any one of insufficient speed of the upper body, insufficient power of the upper body, insufficient speed of the lower body, and insufficient power of the lower body is associated with the exercises performed as functional recovery training, and the evaluation processing unit 212 may determine the recommended exercise based on the speed evaluation and power evaluation of each of the upper body and the lower body. Further, the evaluation processing unit 212 may determine the recommended exercise based on a specific combination of scores, and various modifications of the specific processing are possible.

[0089] 2.3 Four - limb function evaluation The four - limb function evaluation process shown in step S104 of FIG. 4 will be described. The evaluation processing unit 212 evaluates the user's four - limb function based on the center - of - gravity information. At this time, since it is necessary to obtain the center - of - gravity position, the bed 100 includes a plurality of load sensors 140 arranged at different positions.

[0090] In particular, the acquisition unit 211 acquires the center - of - gravity information during the period when the user is in the lying position based on the plurality of load sensors 140, and the evaluation processing unit 212 may evaluate the motor function of the user in the lying position based on the center - of - gravity information during the period of the lying position. The lying position refers to the state in which the user is in a lying posture on the bed 100, including both the waking state and the sleeping state. By using the center - of - gravity information in the lying position, it becomes possible to divide the user's body into specific parts (for example, the right and left halves of the body, or the four limbs) and evaluate the motor function. The reason for this will be described with reference to FIGS. 9 and 10.

[0091] In the lying state, the output of the load sensor 140 varies depending on body movement, breathing, and heartbeat. When awake, body movement is conscious body movement caused by the care recipient consciously moving their body. However, even when conscious body movement occurs, if there is a disorder in the limbs, waist, etc., the care recipient will unconsciously try to cover their body, resulting in a bias in body movement in a predetermined direction. The disorders here include various disorders such as pain, paralysis, and weakness. Also, when the muscles of the whole body are weak, etc., it is considered that the overall body movement becomes gentle. Also, during sleep, conscious body movement does not occur, and unconscious body movement occurs, resulting in a bias in body movement. Therefore, in both the awake and sleep states, the user's body movement may include a bias caused by a disorder.

[0092] FIG. 9 is a schematic diagram showing a state in which the care recipient is in a lying position (in the strict sense, the supine position) on the bed 100. As described above, the right side and the left side in the present embodiment represent the directions seen from the care recipient in the supine position. In the supine position, for example, it is known that a person turns over due to the influence of blood flow or the like. Turning over is body movement, and as described above, if there is a disorder in the body, a bias will occur unconsciously in both the awake and sleep states.

[0093] For example, consider turning over from the supine position to the left lateral position where the left half of the body is down. It is known that there are three layers in the turning-over motion until the motion is completed. First, in the first layer, an operation of lifting the right shoulder is performed by moving the right arm so that the right hand comes in front of the face. In the second layer, the rotation of the body starts, and an operation of placing the right foot on the left foot is executed. In the third layer, the rotation of the body is completed, and an operation of taking balance by gently bending both knees is executed.

[0094] As described above, in the turning motion to the left lateral position, the movements mainly involve moving the right arm and the right leg. Conversely, in the turning motion from the supine position to the right lateral position, the movements mainly involve moving the left arm and the left leg. That is, the body movement (turning over) in the lying state is a movement using the four limbs, and the arms and legs mainly used differ depending on the direction of rotation. And in the turning over to the left lateral position, the center of gravity of the care recipient moves to the left compared to the supine position, and in the turning over to the right lateral position, the center of gravity of the care recipient moves to the right compared to the supine position.

[0095] Summarizing the above, the body movement in the lying state is a movement accompanied by the movement of the center of gravity, which is caused by the movement using the four limbs on the side opposite to the moving direction (rotation direction) of the center of gravity. Therefore, by using the center of gravity information in the lying position for determination, it becomes possible to appropriately determine the motor function of the four limbs.

[0096] Figures 10A and 10B are graphs showing the time change of the center of gravity position when turning over is repeated in the left - right direction. The horizontal axis of Figures 10A and 10B represents time, and the vertical axis represents the coordinate value of the center of gravity position in the left - right direction detected by the load sensor 140. The upper side of the vertical axis corresponds to the left side of the bed 100, and the lower side corresponds to the right side of the bed 100. Figure 10A is an example of the waveform of a healthy person, and Figure 10B is an example of the waveform of a care recipient with a problem in the left half of the body.

[0097] As described above, the movement of the center of gravity to the left corresponds to the turning motion to the left lateral position, and the movement to the right corresponds to the turning motion to the right lateral position. A healthy person has no problems in either the right or left half of the body. Therefore, since a healthy person can smoothly perform the turning motion in either direction, as shown in Figure 10A, the movement of the center of gravity is executed at a certain speed or more in both the right and left directions.

[0098] On the other hand, when there is a problem with the left half of the body, it becomes difficult to smoothly perform the turning motion to the right lateral position mainly using the left arm and left leg. Therefore, in this case, as shown in FIG. 10B, the moving speed of the center of gravity position to the right is slower than the moving speed of the center of gravity position to the left. The motion function evaluation device 200 of the present embodiment may perform a limb function evaluation based on the moving speed of the center of gravity position in the left-right direction as described above. Hereinafter, the specific processing flow will be described.

[0099] FIG. 11 is a flowchart for explaining the limb function evaluation process shown in step S104 of FIG. 4. As a premise of this process, it is assumed that the center of gravity information in the lying state is acquired in step S102 of FIG. 4.

[0100] Note that the lying state here may be when awake, when sleeping, or both. However, as described above, since the bias in body movement due to physical discomfort is performed unconsciously, conscious body movement may not be useful in the limb function evaluation. Therefore, the acquisition unit 211 of the present embodiment may acquire the center of gravity information during the period when the user is determined to be in the sleeping state, and the evaluation processing unit 212 may perform a limb function evaluation based on the center of gravity information. In this way, since the mixing of information caused by conscious body movement is suppressed, it is possible to improve the accuracy of the limb function evaluation.

[0101] In step S301, the evaluation processing unit 212 calculates the center of gravity velocity based on a plurality of center of gravity positions acquired in time series. The center of gravity velocity is, for example, information obtained by dividing the change in the center of gravity position between two different timings by the time difference. The two timings here are narrowly two timings that are temporally adjacent, but are not limited to this.

[0102] In step S302, the evaluation processing unit 212 performs a left-right comparison of the center-of-gravity velocity. FIG. 12 is a diagram showing changes in the center-of-gravity position in a two-dimensional coordinate plane. The horizontal axis in FIG. 12 represents the left-right direction of the bed 100. The vertical axis represents the head direction and the foot direction, with the upper part corresponding to the head direction. Also, the reference numerals 140A - 140D shown in FIG. 12 represent the positions of the load sensors 140A - 140D on the two-dimensional coordinate plane. Note that the upper right (load sensor 140A side) in FIG. 12 is referred to as the first quadrant, the upper left (load sensor 140B side) as the second quadrant, the lower left (load sensor 140D side) as the third quadrant, and the lower right (load sensor 140C side) as the fourth quadrant.

[0103] In FIG. 12, for convenience, the movement history (trajectory) of the center-of-gravity information at all times of lying in bed, waking, sleeping, and getting out of bed is shown. Here, the time of getting out of bed is, in a narrow sense, the period until the care recipient transitions to a sitting position at the edge of the bed (preparation period for getting out of bed), but it may also include the subsequent periods (movement period for getting out of bed, completion period for getting out of bed). The starting point of the trajectory shown in FIG. 12 is the position indicated by "lying in bed" in the third quadrant. When lying in bed, the care recipient enters the bed 100 from the right side of the bed 100 and assumes a lying position near the center of the bed 100, so that the center-of-gravity position moves to a position approximately in the middle between the first quadrant and the second quadrant. Thereafter, in the lying position state (waking, sleeping), the center-of-gravity position fluctuates due to factors such as turning over, breathing, and heartbeat. Thereafter, when the care recipient assumes a sitting position and stands up at the left end of the bed 100, the trajectory ends at the position indicated by "getting out of bed" in the fourth quadrant.

[0104] In step S302, the evaluation processing unit 212 may obtain the moving speed of the center-of-gravity position in the left-right direction based on, for example, the amount of change in the horizontal axis direction between two adjacent points. In the example of FIG. 12, since the positive direction of the horizontal axis is to the left, the speed on the left side is calculated as a positive value, and the speed to the right side is calculated as a negative value.

[0105] Figures 13A and 13B are graphs showing the distribution of the moving speed of the center of gravity position in the left-right direction in the example of FIG. 12. FIG. 13A represents the moving speed in the right direction, and FIG. 13B represents the moving speed in the left direction. Here, the speed is classified into four categories of "fast", "slightly fast", "slightly slow", and "slow" according to the absolute value, and for each of the leftward speed and the rightward speed, the ratio of the number of speeds classified into each category is shown. In the example of FIG. 13A, more than 3 / 4 of the rightward speeds are classified as "slow" or "slightly slow", indicating that the speed in the right direction tends to be slow as a whole. On the other hand, in the example of FIG. 13B, more than 3 / 4 of the leftward speeds are classified as "fast" or "slightly fast", indicating that the speed in the left direction tends to be fast as a whole. Although FIGS. 13A and 13B show the speed distribution, as shown in FIG. 12, the average speed v1 in the right direction and the average speed v2 in the left direction may be calculated. Here, v1 is slow and v2 is fast.

[0106] In step S303, the evaluation processing unit 212 evaluates the motor function based on the moving speed of the center of gravity position along the first direction and the moving speed of the center of gravity position along the second direction, which is the opposite direction of the first direction. As described above, for example, the first direction is one of the left-right directions, and the second direction is the other. For example, the evaluation processing unit 212 compares each of the speed v1 in the right direction and the speed v2 in the left direction with a given speed threshold. When v1 is less than or equal to the speed threshold, it is determined that there is an abnormality in the left half of the body, and when v2 is less than or equal to the speed threshold, it is determined that there is an abnormality in the right half of the body. In the example of FIGS. 12-13B, since the speed in the right direction is slow, it is determined that there is an abnormality in the left half of the body (left arm or left leg). Note that the determination here is not limited to the process of comparing each of the rightward speed v1 and the leftward speed v2 with a given speed threshold. For example, the evaluation processing unit 212 may evaluate the motor function based on the ratio of the speed v1 and the speed v2. For example, when v1 / v2 is greater than or equal to the first threshold, since the speed v2 is relatively small, it is determined that there is an abnormality in the right half of the body, and when v1 / v2 is less than or equal to the second threshold that is smaller than the first threshold, since the speed v1 is relatively small, it may be determined that there is an abnormality in the left half of the body. In addition, various modified implementations of the evaluation process of the motor function using the speeds in each direction are possible.

[0107] In step S304, the evaluation processing unit 212 determines whether a problem has been detected in the limb functions by the processing in step S303. If a problem is detected (step S304: Yes), in step S305, after the evaluation processing unit 212 turns on the limb function abnormality flag, it proceeds to step S306. If no problem is detected (step S304: No), the limb function abnormality flag remains off and it proceeds to step S306.

[0108] In step S306, the output processing unit 213 outputs the evaluation result based on the center of gravity information. The output here may be performed on the display unit 240 of the motor function evaluation device 200, or may be performed on other devices. This point is the same as the example described above in the body function evaluation process.

[0109] FIG. 14 is an example of a screen displayed in step S306. In the example of the screen shown in FIG. 14, information such as the name and weight of the care recipient is displayed. Also, on this screen, when the limb function abnormality flag is on, information specifying the content of the abnormality may be displayed. In the example of FIG. 14, the output processing unit 213 performs a process of displaying text representing the determination result of "left half body disorder". Although omitted in FIG. 14, when a problem is detected in the limb functions, a display prompting the implementation of function recovery training may be performed. For example, in addition to the information shown in FIG. 14, the output processing unit 213 may perform a display prompting the implementation of movements using the left half body.

[0110] FIG. 15 is a diagram showing changes in the center of gravity position regarding another care recipient. FIGS. 16A and 16B are graphs showing the distribution of the moving speed of the center of gravity position in the left - right direction for the care recipient, where FIG. 16A shows the distribution of the moving speed in the right direction and FIG. 16B shows the distribution of the moving speed in the left direction. In this example, as shown in FIGS. 16A and 16B, for both the right direction and the left direction, the closing ratio of "slow" and "slightly slow" is very large. Also, the average speed v3 in the right direction and the average speed v4 in the left direction are both smaller than the speed threshold.

[0111] In this case, in step S303, the evaluation processing unit 212 determines that there are abnormalities in both the left and right halves of the body, that is, the whole body is weak. FIG. 17 is an example of the screen displayed in step S306. In the screen shown in FIG. 17, as information for specifying the content of the abnormality, text representing the determination result of "The whole body looks weak" is displayed.

[0112] Moreover, above, the limb function evaluation processing based on the center of gravity information in the lying position state (awake or asleep) has been described, but the method of this embodiment is not limited to this. For example, the acquisition unit 211 may acquire the center of gravity information during the lying period (when lying in bed) in which the user transitions to the lying position state and the getting-out-of-bed period (when getting out of bed) in which the user ends the lying position state based on a plurality of load sensors 140. Then, the evaluation processing unit 212 may evaluate the motor function based on the center of gravity position during the lying period and the getting-out-of-bed period, or the moving speed of the center of gravity position. In this way, it becomes possible to more detailedly determine the limb function.

[0113] For example, in FIG. 12, the center of gravity positions at the time of lying in bed and getting out of bed are also shown. And in the example of FIG. 12, the evaluation processing unit 212 can determine that the lying in bed was performed from the right side of the bed 100 based on the fact that the locus representing the center of gravity position starts from the third quadrant. Similarly, the evaluation processing unit 212 can determine that the getting out of bed was performed from the left side of the bed 100 based on the fact that the locus representing the center of gravity position ends in the fourth quadrant.

[0114] The evaluation processing unit 212 may, for example, determine the direction used by the care recipient when lying in bed and the direction used when getting out of bed by acquiring the data of the same care recipient over a plurality of days. Then, the evaluation processing unit 212 may determine that it is abnormal when the lying in bed or getting out of bed is performed from a direction different from the normal direction.

[0115] For example, consider a case where a handrail is provided on the foot side of the bed 100, and the care recipient gets in and out of the bed while holding the handrail. In this case, when getting in and out of the bed from the right end of the bed 100, the handrail is located on the right half side of the care recipient when getting in the bed, and the handrail is located on the left half side of the care recipient when getting out of the bed. Similarly, when getting in and out of the bed from the left end of the bed 100, the direction in which the handrail is located is opposite when getting in the bed and when getting out of the bed, as seen from the care recipient.

[0116] If there is no abnormality in the limbs of the care recipient, the care recipient can perform the operations of getting in and out of the bed without any problem using either the left half or the right half of the body. Therefore, as in the normal situation, it is considered that the care recipient performs the operations of getting in and out of the bed from the direction with which the care recipient is familiar. On the other hand, for example, when an abnormality occurs in the left half of the body, the operation using the handrail located on the left side cannot be smoothly performed. As a result, for example, in order to get in and out of the bed mainly using the right half of the body, it is considered that the care recipient enters the bed 100 from the right side of the bed 100 when getting in the bed and tries to get out of the bed 100 from the left side of the bed 100 when getting out of the bed. That is, when at least one of the direction of getting in the bed and the direction of getting out of the bed is different from the normal situation, it becomes possible to detect an abnormality in the limbs by determining that direction.

[0117] FIG. 18 is an example of a screen displayed in the process of step S306 in this case. In this example, in addition to the determination based on the moving speed of the center-of-gravity position in the left-right direction in the lying-in-bed state, the direction of the bed 100 used for getting in and out of the bed is also determined based on the center-of-gravity position when getting in the bed and when getting out of the bed. Therefore, in addition to the information shown in FIG. 15, the output processing unit 213 may perform a process of displaying information indicating the direction of the bed 100 used when getting in the bed and when getting out of the bed. Further, as shown in FIG. 18, the output processing unit 213 may display text indicating that the way of getting in the bed is different from normal.

[0118] Furthermore, the above has described an example of evaluating the way of getting into and out of the bed 100 using the center of gravity positions when lying in bed and when getting out of bed (depending on whether it is the right side or the left side of the bed 100). However, the evaluation processing unit 212 may evaluate the way of getting into and out of the bed 100 from the moving speeds of the center of gravity positions when lying in bed and when getting out of bed. For example, the evaluation processing unit 212 sets the moving speed of the center of gravity position when lying in bed as the lying-in speed and the moving speed of the center of gravity position when getting out of bed as the getting-out speed. For a care recipient without abnormalities in the limbs, it is considered that the lying-in speed and the getting-out speed are executed at speeds familiar to the target care recipient. On the other hand, when abnormalities occur in the limbs, it is considered that the lying-in speed and the getting-out speed will become slow due to slow movements, or the lying-in speed and the getting-out speed will become excessively fast due to difficulty in supporting the body weight. Therefore, the evaluation processing unit 212 may determine that there is an abnormality in the limbs when at least one of the lying-in speed and the getting-out speed deviates from the normal speed.

[0119] Also, as shown in FIG. 18, the output processing unit 213 may display the body level (degree of frailty), which is an index value representing the degree of discomfort. The body level may be obtained from the moving speed of the center of gravity position in the left-right direction in the lying-in state. For example, the lower the speed, the lower the body level is evaluated. Also, compared with the case where it is determined that there is a disorder in one of the right half and the left half of the body, the body level is evaluated lower when it is determined that there is a disorder in both of them. Also, the body level may be evaluated lower when the direction during lying in bed or getting out of bed is different from normal.

[0120] Furthermore, the above has described an example of obtaining the center of gravity of the sensor outputs of the plurality of load sensors 140 as the center of gravity information in a two-dimensional coordinate plane (FIG. 12, etc.) and an example of obtaining it with the coordinate values in the left-right direction (FIGS. 10A and 10B), but the method of this embodiment is not limited to this.

[0121] For example, the evaluation processing unit 212 may determine the center of gravity position based on the ratio or difference between a part of the load values of the plurality of load sensors 140 and another part of the load values.

[0122] FIG. 19 is a graph showing the outputs of the two load sensors 140. The horizontal axis of FIG. 19 represents time, and the vertical axis represents the load value which is the output of each load sensor 140. Here, the change waveforms of the load values of the load sensor 140A arranged on the left side of the assisted person and the load sensor 140B arranged on the right side are illustrated.

[0123] In the example of FIG. 19, initially, since the output of the load sensor 140B is relatively large, the center of gravity position is biased towards the side of the load sensor 140B, that is, the right side. On the other hand, from the middle, the magnitude relationship is reversed, and the output of the load sensor 140A becomes relatively large. That is, it can be seen that the center of gravity position is moving from the state biased to the right side towards the left side.

[0124] As shown in FIG. 19, even when the center of gravity position (for example, coordinate value) is not directly calculated, it is possible to obtain the center of gravity position by comparing the outputs of the plurality of load sensors 140. Therefore, the center of gravity information in the present embodiment is not limited to the center of gravity position itself described above using FIGS. 10A, 10B, 12, etc., and may include the ratio or difference of the outputs of the plurality of load sensors 140.

[0125] 2.4 Functional recovery training evaluation As described above, in the physical function evaluation shown in step S103 of FIG. 4 and the limb function evaluation shown in step S104, the motor function of the assisted person is evaluated. And when it is determined that there is a problem with the motor function, an output for prompting functional recovery training is performed. The case where there is a problem with the motor function corresponds to, for example, the case where at least one of the upper limb frailty flag, the lower limb frailty flag, and the limb function abnormality flag is on. As described above, the output processing unit 213 may determine the exercise content to be presented based on which flag is on. For example, when the upper limb frailty flag is on, training for recovering the function of the upper body is selected, and when the lower limb frailty flag is on, training for recovering the function of the lower body is selected. Also, in the limb function evaluation, for example, the right and left sides of the body are evaluated, so training for recovering the function of the side with a lower evaluation value may be selected.

[0126] In the above description, an example was given in which the evaluation processing unit 212 independently determines the exercise content in each of the physical function evaluation and the limb function evaluation. However, the exercise content may be determined based on both the result of the physical function evaluation and the result of the limb function evaluation.

[0127] After the output for promoting the functional recovery training is performed, the acquisition unit 211 acquires at least one of the load value information and the center of gravity information during the period when the user is performing the training on the bed 100 based on the output of the output processing unit 213, and the evaluation processing unit 212 may evaluate the training based on at least one of the load value information and the center of gravity information.

[0128] The evaluation of the training here is an evaluation of whether the assisted person can realize the desired movement in the training. Alternatively, when the training is performed multiple times, it may be evaluated whether the motor function of the assisted person has recovered due to the training by determining the change in the evaluation results over time. Hereinafter, specific examples of the exercise content and the evaluation processing in the training will be described.

[0129] FIG. 20 is a specific example of an exercise executed on the bed 100 as a functional recovery training, and is a diagram showing the movement of hugging the knees. In this movement, the assisted person holds one of the knees with both hands and performs a movement of hugging the knee toward the abdomen (chest). The movement of hugging the knees is effective for the functional recovery of the lower body because it moves the legs significantly.

[0130] When the movement of hugging the knees is executed, the evaluation processing unit 212 evaluates the training based on the sensor output of the load sensors 140 (load sensors 140C and 140D) arranged on the foot side of the bed 100.

[0131] Figures 21A and 21B are graphs showing the sensor outputs of the load sensors 140 when the knee hugging motion is properly executed. In Figures 21A and 21B, the horizontal axis represents time, and the vertical axis represents the load value which is the sensor output. As shown in Figure 21A, the sensor outputs of the load sensors 140A and 140B arranged on the head side of the bed 100 have little variation. That is, when performing the knee hugging motion which is a lower body movement, the load sensors 140 on the head side may not be suitable for the evaluation of the training.

[0132] On the other hand, as shown in Figure 21B, the sensor outputs of the load sensors 140 arranged on the foot side of the bed 100 have large variations. Here, an example with large variations in the sensor output of the load sensor 140D arranged on the right side of the bed 100 is shown assuming the knee hugging motion of the right knee. However, when performing the knee hugging motion of the left knee, the variations in the sensor output of the load sensor 140C arranged on the left side of the bed 100 will become large. Note that the knee hugging motion may be performed on both the left and right sides.

[0133] For example, the evaluation processing unit 212 may acquire the load value information when the care recipient is performing the knee hugging motion, and obtain the similarity between the load value information and the waveform shown in Figure 21B. If the similarity is equal to or greater than a predetermined threshold, the training is determined to be appropriate, and if it is less than the predetermined threshold, the training is determined to be inappropriate. Note that various modifications such as using a learned model for the evaluation process are possible, which is the same as in the physical function evaluation.

[0134] According to the method of this embodiment, when a problem with the motor function is discovered during daily life using the bed 100, it is possible to promote the functional recovery training that can be executed on the bed 100 and appropriately evaluate the effects of the functional recovery training and the like. Therefore, when the evaluation of the training is low, it is possible to prompt the caregiver to take appropriate measures such as recommending other exercises or dispatching a physical therapist to ensure the proper execution of the exercises.

[0135] Abdominal muscle exercises may also be performed as functional recovery training. FIG. 22 is a diagram showing changes in the center of gravity position when abdominal muscle exercises are appropriately performed. In FIG. 22, the vertical and horizontal axes of the graph are the same as those in FIG. 12 and the like. As shown in FIG. 22, in the abdominal muscle exercise, since the movement of raising the upper body is performed, the center of gravity position changes in the vertical direction. The amount of movement of the center of gravity position here is significantly larger than the amount of movement in the vertical direction due to turning over, breathing, heartbeat, etc., to an identifiable extent.

[0136] Therefore, the evaluation processing unit 212 acquires, for example, the center of gravity information when the care recipient is performing abdominal muscle exercises, and performs evaluation processing based on the moving direction and moving distance of the center of gravity position. For example, the evaluation processing unit 212 may perform processing of comparing the amount of change in the vertical direction of the center of gravity information with a reference change amount that is the amount of change in the vertical direction in FIG. 22. If the amount of change is close to the reference change amount, the training is determined to be appropriate, and if the deviation between the amount of change and the reference change amount is more than a predetermined value, the training is determined to be inappropriate. In addition, determination based on other feature amounts such as the ratio of the speed and acceleration of the center of gravity position may be performed, and various modifications are possible for the specific method of evaluating functional recovery training.

[0137] 3. Variations Hereinafter, several variations will be described.

[0138] 3.1 Fall Detection Conventionally, it has been known that an incident occurs in which the care recipient falls from or slips off the bed 100. Both falling and slipping off here mean that the care recipient accidentally falls from the bed 100. Falling corresponds to the case of falling vigorously, and slipping off corresponds to the case of gradually falling over time.

[0139] The movement function evaluation device 200 of the present embodiment may detect at least one of the fall of the assisted person from the bed 100 and the slipping down based on the sensor output of the load sensor 140. In particular, the acquisition unit 211 acquires load value information during the period when the user gets out of bed, and the evaluation processing unit 212 detects at least one of the fall of the user from the bed 100 and the slipping down based on the load value information. Since falling and slipping down are considered a kind of movement of the user away from the bed 100, it is assumed that the load value decreases. That is, by using the load value information at the time of getting out of bed, it becomes possible to accurately detect falling and slipping down. Hereinafter, an example of determining both falling and slipping down will be described, but either one may be omitted.

[0140] Figures 23 - 25 are examples of graphs representing load value information at the time of getting out of bed. The horizontal axis of Figures 23 - 25 represents time, and the vertical axis represents the load value. In Figure 23, the time of getting out of bed is divided into three periods: the pre-getting-out-of-bed preparation period, the getting-out-of-bed movement period, and the getting-out-of-bed completion period. Each period is as described above. Also, in Figures 24 and 25, examples are assumed where the actions of shifting to the sitting position and applying a reaction are not clearly executed. Therefore, in Figures 24 and 25, only the getting-out-of-bed completion period when the body moves away from the bed 100 is illustrated.

[0141] Figure 23 is a diagram showing a waveform (hereinafter also referred to as a normal waveform) when getting out of bed is performed normally without falling or slipping down. In this case, the assisted person first shifts to the sitting position during the pre-getting-out-of-bed preparation period, and then performs an action of getting up by pushing the bed 100 with the hand or using the reaction of the upper body by bending forward during the getting-out-of-bed movement period. As a result, the normal waveform increases rapidly during the getting-out-of-bed movement period. Furthermore, when the getting-up action continues normally, the buttocks of the assisted person begin to lift off the bed 100, so the load applied to the bed 100 during the getting-out-of-bed completion period decreases rapidly. That is, in the normal waveform, a sharp peak appears in the waveform during the getting-out-of-bed movement period. Then, when getting out of bed is completed, the assisted person performs an action of releasing the hand from the bed 100, so the normal waveform also has a peak during the getting-out-of-bed completion period.

[0142] FIG. 24 is a diagram showing waveforms (hereinafter also referred to as fall waveforms) when a fall occurs. In a situation where a fall occurs, it is considered that the assisted person cannot maintain a sitting position on the edge of the bed and falls from the bed 100, or even if the assisted person can assume a sitting position on the edge of the bed, the posture is unstable and the assisted person cannot perform an action of pushing the bed 100 with the hand to stand up. Therefore, as shown in FIG. 24, in the fall waveform, the load value corresponding to the sitting position on the edge of the bed does not decrease, and no distinct peak corresponding to the action of pushing back appears (while the preparation period for getting out of bed and the getting-out-of-bed operation period do not clearly appear), and the load value rapidly decreases. Also, when a fall occurs, a part of the assisted person's body (for example, the head, etc.) may collide with the bed 100. In this case, due to the collision, it is also conceivable that the value fluctuates finely during the decrease in the load value, as shown in FIG. 24 for example. Also, since the assisted person cannot complete the standing-up action by releasing the hand from the bed 100 during a fall, it is assumed that no distinct peak will be detected during the completion period of getting out of bed. Note that FIG. 24 shows an example in which body movement due to delirium or the like is detected before the start of the preparation period for getting out of bed, but such body movement does not necessarily appear in all fall waveforms.

[0143] As can be seen from FIGS. 23 and 24, the fall waveform has differences compared with the normal waveform in that no peak appears at the time of getting out of bed, fine fluctuations in the load value occur during the decrease in the value, and no distinct peak appears during the completion period of getting out of bed.

[0144] FIG. 25 is a diagram showing waveforms when slipping-off occurs (hereinafter also referred to as slipping-off waveforms). In a situation where slipping-off occurs, for example, first, one side of the body of the care recipient drops off the bed 100, and the care recipient gradually drops off the bed 100 toward the other side of the body without being able to regain an upright posture. Naturally, since it is unlikely that the care recipient can shift to a sitting position and push the bed 100 with their hand, as shown in FIG. 25, the slipping-off waveform starts to decrease without a clear peak appearing at the time of getting out of bed. And in the case of slipping-off, since the entire body does not drop off the bed 100 in a short time, the decrease in the load value becomes relatively gentle. Therefore, as shown in FIG. 25, for example, even after it is determined that the load value has fallen below a predetermined threshold value and the getting-out-of-bed completion period has started, it is conceivable that the load value gradually decreases due to the continued slipping-off of the body.

[0145] As can be seen from FIGS. 23 and 25, the slipping-off waveform has differences compared to the normal waveform in that no peak appears at the time of getting out of bed and the decrease in the load value is not steep (it takes a relatively long time to fall below the predetermined threshold value). Also, as can be seen from FIGS. 24 and 25, the slipping-off waveform has a difference compared to the falling waveform in that the decrease in the load value is not steep.

[0146] The evaluation processing unit 212 of the present embodiment may determine whether it corresponds to normal, falling, or slipping-off based on the differences between the normal waveform, the falling waveform, and the slipping-off waveform. For example, the evaluation processing unit 212 may obtain, as feature quantities, the peak during the above-described getting-out-of-bed preparation period, the length of time until the load value decreases to a predetermined value or less, etc., and determine falling or slipping-off based on the feature quantities. Also, the fact that various modified implementations such as using machine learning are possible is the same as in the case of body function evaluation.

[0147] Also, although the fall determination using the load value information at the time of getting out of bed has been described above, the method of the present embodiment is not limited to this. For example, the acquisition unit 211 may acquire the center-of-gravity information at the time of getting out of bed, and the evaluation processing unit 212 may perform a fall determination based on the change speed of the center-of-gravity position at the time of getting out of bed represented by the center-of-gravity information.

[0148] FIG. 26 is a diagram showing changes in the center-of-gravity position in a two-dimensional coordinate plane, and the axes and load sensors 140A-140D are the same as those in FIG. 12. As shown in FIG. 26, the evaluation processing unit 212 may obtain the moving speed v5 of the center-of-gravity position based on the center-of-gravity position at the time of getting out of bed. If v5 is equal to or greater than a predetermined threshold value, it means that the care recipient gets out of the bed vigorously when getting out of bed. However, since the user in this embodiment is assumed to be a care recipient staying in a nursing facility, etc., there is a high probability that getting out of bed will be done carefully. Specifically, as described above, it is considered that a series of operations of shifting to a sitting position, holding onto the bed 100, standing up, and releasing the hand from the bed 100 are sequentially and carefully executed. That is, if the moving speed v5 of the center-of-gravity position at the time of getting out of bed is excessively large, there is a possibility of an unintended getting out of bed, that is, a fall. Therefore, the evaluation processing unit 212 may obtain the moving speed of the center-of-gravity position at the time of getting out of bed, and determine that it is a fall when the moving speed is equal to or greater than a given threshold value.

[0149] 3.2 Respiratory movement The acquisition unit 211 acquires the center-of-gravity information during the period (awake or asleep) when the user is in a lying position based on the plurality of load sensors 140, and the evaluation processing unit 212 may evaluate whether the user is performing abdominal breathing or thoracic breathing based on the change amount of the center-of-gravity position. In this way, it becomes possible to evaluate the breathing method of the user.

[0150] Abdominal breathing is a breathing method that expands the lungs using the diaphragm, and thoracic breathing is a breathing method that expands the lungs by expanding the ribs with the muscles around the lungs. Thus, since different parts are used in abdominal breathing and thoracic breathing, it is important to use a breathing method according to the situation. For example, since the trunk is exercised in abdominal breathing, abdominal breathing is effective for improving posture and the like. In this embodiment, since the breathing method can be naturally determined only by breathing on the bed 100, it becomes possible to encourage the appropriate breathing for the care recipient.

[0151] FIG. 27 is a flowchart for explaining the process of determining respiration. It is assumed that load value information and center of gravity information in the lying position (awake or asleep) have been acquired as a prerequisite for this process.

[0152] First, a respiration determination is performed to determine whether the variation in the load value detected by the load sensor 140 is caused by respiration. FIG. 28 is a graph showing the change in the load value when respiration is performed. The horizontal axis in FIG. 28 represents time, and the vertical axis represents the amount of change in the load value. As shown in FIG. 28, when respiration is performed, the load value varies significantly at the timing of inhaling and exhaling. Since such characteristics are almost common in abdominal respiration and thoracic respiration, the evaluation processing unit 212 may perform the respiration determination based on whether the load value information changes in the same way as in FIG. 28.

[0153] Specifically, in step S401, the evaluation processing unit 212 determines whether the variation frequency of the load value is 0.2 - 0.33 Hz. The value here is based on the average respiration rate of adults (12 - 20 times per minute), and the threshold value may be changed based on attributes such as age and medical history.

[0154] In step S402, the evaluation processing unit 212 determines whether the variation in the load value continues for a certain period of time or more. Since respiration is continuously performed, if the variation in the load value is caused by respiration, it is considered that the variation continues. It should be noted that during sleep, respiration may become shallow or stop. In that case, the variation in the load value becomes small. From this, the evaluation processing unit 212 monitors the respiration stop during sleep, and the output processing unit 213 may output an alert when an abnormality including respiration stop is detected.

[0155] When the fluctuation frequency of the load value is outside the above range (step S401: No), or when the fluctuation of the load value ends in less than a certain period of time (step S402: No), the fluctuation of the load value is considered to be due to factors other than breathing, and the processing after step S403 is not performed and the processing shown in FIG. 27 ends. Here, an example of performing breathing determination based on load value information has been shown, but breathing determination may be performed using other information such as a captured image. In this case, it is not essential for the acquisition unit 211 to acquire load value information.

[0156] When the fluctuation frequency of the load value is within the above range (step S401: Yes) and the fluctuation continues for a certain period of time or more (step S402: Yes), the evaluation processing unit 212 determines the breathing method based on the center of gravity information. Specifically, in step S403, the evaluation processing unit 212 determines the amount of movement of the center of gravity position.

[0157] FIG. 29A is a diagram showing an example of the movement of the center of gravity position when abdominal breathing is performed, and FIG. 29B is a diagram showing an example of the movement of the center of gravity position when thoracic breathing is performed. The vertical axis, horizontal axis, and load sensor 140 in FIGS. 29A and 29B are the same as those in FIG. 12. As can be seen from the comparison between FIG. 29A and FIG. 29B, in abdominal breathing, the center of gravity position changes greatly in the vertical direction, while in thoracic breathing, the amount of movement of the center of gravity position is small.

[0158] Therefore, in step S403, the evaluation processing unit 212 may determine whether the amount of movement of the center of gravity position is equal to or greater than a predetermined threshold value. When the amount of movement is equal to or greater than the threshold value (step S403: Yes), in step S404, the evaluation processing unit 212 determines that it is abdominal breathing. When the amount of movement is less than the threshold value (step S403: No), in step S405, the evaluation processing unit 212 determines that it is thoracic breathing.

[0159] Note that FIGS. 29A and 29B are examples of the movement of the center of gravity. For example, when the initial value or offset is changed, the movement amount of thoracic breathing may increase and the movement amount of abdominal breathing may decrease. However, even in this case, since there is a difference in the movement amount of the center of gravity according to the breathing method, the evaluation processing unit 212 can distinguish between abdominal breathing and thoracic breathing based on the movement amount.

[0160] In step S406, the evaluation processing unit 212 may perform evaluation processing on the breathing content. For example, the evaluation processing unit 212 may calculate a breathing score representing the preference of the breathing content. For example, since abdominal breathing is considered preferable in the lying state, the evaluation processing unit 212 may increase the breathing score when it is determined to be abdominal breathing (step S404) compared to when it is determined to be thoracic breathing (step S405). Further, the evaluation processing unit 212 may determine the speed of breathing. For example, when the evaluation processing unit 212 determines the fluctuation frequency of the load value caused by breathing in step S401, the closer the value is to the center of the range of 0.2 Hz to 0.33 Hz, the higher the breathing score is determined, and the farther away from the center of the range, the lower the breathing score is determined. Further, the evaluation processing unit 212 may determine the depth of breathing based on the amplitude of the load value and determine the breathing score based on the depth. Further, the evaluation processing unit 212 may perform evaluation processing separately for inhalation and exhalation with respect to the speed and depth of breathing.

[0161] Also in step S406, the output processing unit 213 may output the result of the breathing evaluation. FIG. 30 is an example of the result screen of the breathing evaluation displayed in step S406. As shown in FIG. 30, in the result screen of the breathing evaluation, in addition to attribute information such as body weight, a breathing score may be displayed. Also, as shown in FIG. 30, information for improving the breathing content may be displayed. In the example of FIG. 30, since the text "There is a tendency to exhale slightly faster" is displayed, it is possible to prompt the care recipient to adjust the speed of breathing.

[0162] Also, it is known that abdominal breathing can relax the body because the parasympathetic nervous system becomes dominant when performing abdominal breathing. Therefore, abdominal breathing may be recommended as the breathing method before sleep onset. Accordingly, the evaluation processing unit 212 may perform a determination regarding breathing before sleep onset. FIG. 31 is a flowchart for explaining the processing executed before sleep onset. In step S501, the evaluation processing unit 212 determines whether the current time has passed the scheduled bedtime of the care recipient. If the current time has not passed the scheduled bedtime (step S501: No), it is considered that the probability of sleep occurring from now on is low, that is, the necessity of recommending abdominal breathing is low. Therefore, the processing after step S502 is omitted.

[0163] If the current time has passed the scheduled bedtime (step S501: Yes), in step S502, the output processing unit 213 outputs information recommending the execution of abdominal breathing to the care recipient. The processing in step S502 may be a display process using a display existing around the bed 100, or may be an audio output process.

[0164] In step S503, the evaluation processing unit 212 evaluates the abdominal breathing. Specifically, in step S503, the processing of steps S401 - S406 shown in FIG. 27 may be executed. As a result, a breathing score and advice for improving breathing are output.

[0165] In step S504, the evaluation processing unit 212 determines whether the care recipient has transitioned to the sleep state. The determination in step S504 may be executed based on the sensor output of the load sensor 140, or may be executed using other devices. Devices for determining the sleep state are known, such as smartphones and wristwatch-type devices, and in this embodiment, they can be widely applied.

[0166] When it is determined that the assisted person is not in a sleeping state (i.e., in an awake state), the motor function evaluation device 200 returns to step S502 and continues the process. That is, the motor function evaluation device 200 outputs a recommendation for abdominal breathing, evaluates the breathing, and outputs the evaluation result. When it is determined that the assisted person is in a sleeping state, the process shown in FIG. 31 ends.

[0167] 3.3 Coughing Judgment At night, the parasympathetic nerve is dominant, so the bronchi narrow as the body relaxes. Therefore, coughing may increase depending on the physical condition of the assisted person.

[0168] Therefore, the acquisition unit 211 acquires the load value information and the center of gravity information during the period when the user is in a sleeping state, and the evaluation processing unit 212 may determine whether the cause of the user's body movement is coughing or turning over based on the magnitude of the load and the change amount of the center of gravity position of the user in the left-right direction. In this way, it becomes possible to accurately determine the number of coughs during sleep. For example, even if the assistance of the assisted person is performed during the day, the number of coughs may decrease during the day because the sympathetic nerve is dominant. Therefore, it is difficult for the caregiver to notice the poor physical condition of the assisted person. In that regard, since the motor function evaluation device 200 of the present embodiment can appropriately detect coughing during sleep, it becomes possible to prompt the caregiver to take appropriate measures according to the physical condition of the assisted person.

[0169] FIG. 32 is a flowchart for explaining the process of determining coughing. As a premise of this process, it is assumed that the acquisition unit 211 has acquired the load value information and the center of gravity information during sleep.

[0170] First, in steps S601 and S602, the evaluation processing unit 212 initializes to 0 a variable n representing the number of times of turning over detection and a variable s representing the number of times of coughing detection.

[0171] In step S603, the evaluation processing unit 212 determines whether or not the load value has changed by a predetermined threshold value or more based on the load value information.

[0172] FIG. 33A is an example of load value information when a turning-over occurs, and FIG. 33B is an example of load value information when a cough occurs. The horizontal axis in FIGS. 33A and 33B represents time, and the vertical axis represents the load value. As shown in FIGS. 33A and 33B, in both the case of turning-over and coughing, fluctuations in the load value occur, and the amount of fluctuation is considered to be larger than that caused by other factors occurring during sleep. Other factors here correspond to heartbeat and breathing.

[0173] When the amount of fluctuation of the load value is less than the threshold value (step S603: No), it is considered that neither coughing nor turning-over has occurred. Therefore, the evaluation processing unit 212 skips the processing of steps S604 - S606 described later and proceeds to step S607. When the amount of fluctuation of the load value is equal to or greater than the threshold value (step S603: Yes), it is considered that either coughing or turning-over has occurred. Therefore, the evaluation processing unit 212 executes processing to distinguish between them.

[0174] FIG. 34A is an example of center-of-gravity information when a turning-over occurs, and FIG. 34B is an example of center-of-gravity information when a cough occurs. The vertical axis, horizontal axis, and load sensor 140 in FIGS. 34A and 34B are the same as those in FIG. 12. As shown in FIG. 34A, when a turning-over occurs, the center-of-gravity position changes in the left-right direction. This is the same as the example described above with reference to FIGS. 10A and 10B. On the other hand, as shown in FIG. 34B, when a cough occurs, the change in the center-of-gravity position is relatively small.

[0175] Therefore, in step S604, the evaluation processing unit 212 determines whether the center-of-gravity position has changed by a certain amount or more in the left-right direction. When the center-of-gravity position has changed by a certain amount or more (step S604: Yes), it is considered that a turning-over has occurred. Therefore, in step S605, the evaluation processing unit 212 increments a variable n representing the number of occurrences of turning-over. Note that in step S605, processing may be executed to count right-side turning-overs and left-side turning-overs separately based on the change direction of the center-of-gravity position. When the change in the center-of-gravity position is less than a certain amount (step S604: No), it is considered that a cough has occurred. Therefore, in step S606, the evaluation processing unit 212 increments a variable s representing the number of occurrences of coughing.

[0176] After the process of step S606, or when it is determined as No in step S603, in step S607, the evaluation processing unit 212 determines whether the assisted person has gotten out of bed. For example, the evaluation processing unit 212 may determine whether the load value represented by the load value information has become equal to or less than a predetermined threshold value. When it is determined that the assisted person has not gotten out of bed (step S607: No), the process returns to step S603 and the count processing of turning over and coughing continues. When it is determined that the assisted person has gotten out of bed (step S607: Yes), the process shown in FIG. 32 ends. The output processing unit 213 may output the variable n and the variable s at that time. The variable n represents the number of times of turning over, and the variable s represents the number of times of coughing.

[0177] Also, when the occurrence of coughing is detected, the evaluation processing unit 212 may perform a process of estimating the cause thereof. FIG. 35 is a flowchart for explaining the cause evaluation process of coughing. First, in step S701, the evaluation processing unit 212 determines whether coughing has occurred. The process of step S701 may be a determination of whether the variable s has been incremented, or may be a determination of whether the variable s has exceeded a given threshold value. When it is determined that coughing has not occurred (step S701: No), the processes of steps S702 - S704 described later are omitted.

[0178] When coughing has occurred (step S701: Yes), in step S702, the evaluation processing unit 212 determines whether the body temperature of the assisted person is equal to or higher than a certain level. The body temperature measurement in the process of step S702 may be performed using a thermometer, or may be performed using thermography. For example, the motor function evaluation device 200 receives the measurement result from a thermometer or an imaging device via a network.

[0179] When the body temperature is equal to or higher than a certain level (Step S702: Yes), in Step S703, the evaluation processing unit 212 determines that the cause of the cough is fever. When the body temperature is lower than a certain level (Step S702: No), in Step S704, the evaluation processing unit 212 determines that the cause of the cough is asthma or pneumonia.

[0180] In Step S705, the evaluation processing unit 212 determines whether the care recipient has gotten out of bed. If it is determined that the care recipient has not gotten out of bed (Step S705: No), the process returns to Step S701 and the processing continues. If it is determined that the care recipient has gotten out of bed (Step S705: Yes), the processing shown in FIG. 35 ends.

[0181] 3.4 Incident Prediction Falls of the care recipient can be a factor that reduces the QOL of the elderly. Falls here are not limited to falling from the bed 100, but widely include falls and drops in other scenarios such as in the toilet, cafeteria, and when transferring to a wheelchair. However, it is not easy to estimate to what extent the risk of falls and drops is for the care recipient. For example, skilled caregivers used to judge based on tacit knowledge.

[0182] Therefore, in this embodiment, based on the processing result of the motor function evaluation device 200, a process of estimating the risk related to incidents such as falls and drops (hereinafter also referred to as incident risk) may be performed. As described above, in the motor function evaluation device 200, the motor function of the care recipient is evaluated based on the sensor output of the load sensor 140. Since the level of motor function is related to the ease of falling, it becomes possible to appropriately evaluate the incident risk by using the evaluation result of the motor function evaluation device 200.

[0183] FIG. 36 is a diagram showing an example of an information processing system 10 including a motor function evaluation device 200. In FIG. 36, care recipients a, b, and c are exemplified as care recipients. Care recipient a lives in nursing facility A and uses, for example, a bed 100 arranged in a room of nursing facility A. Care recipient b lives in nursing facility B and uses a bed 100 arranged in a room of nursing facility B. Care recipient c receives care at home and uses, for example, a bed 100 arranged in his / her own room.

[0184] The bed 100 is connected to a motor function evaluation device 200, which is a server system, via a network such as the Internet. The motor function evaluation device 200 performs various processes described above based on measurement data output from the bed 100 to obtain, for example, a physical function evaluation result and a limb function evaluation result. Note that the measurement data may be sensor output or load value information or center of gravity information. Thereby, the server system can collect evaluation results of the motor functions of a plurality of care recipients.

[0185] Alternatively, devices such as PCs may be arranged in each of nursing facility A, nursing facility B, and the patient's home separately from the server system, and the devices may operate as the motor function evaluation device 200. In this case, the devices such as PCs perform physical function evaluation and limb function evaluation, and the server system acquires the evaluation results via a network. Also in this case, the server system can collect evaluation results of the motor functions of a plurality of care recipients.

[0186] The server system may also acquire incident information representing details of the incident when an incident occurs. The incident information is input, for example, by a care staff member of a nursing facility. For example, when an incident occurs to care recipient a, care staff member A who works at nursing facility A and is in charge of care recipient a inputs the incident information using a terminal device 310 such as a provided smartphone. The terminal device 310 transmits the input incident information to the server system.

[0187] FIG. 38 is an example of incident information to be collected. As shown in FIG. 38, the incident information includes information such as the target person (the person to be assisted) of the incident, the discoverer of the incident (the caregiver), the location of occurrence, classification, cause, countermeasures, etc.

[0188] The server system that has acquired the incident information creates training data for learning based on the evaluation result of the target person's motor function. For example, when the incident information in FIG. 38 is acquired, the server system acquires the evaluation result of the motor function of care recipient a from the storage unit. The content of the evaluation result can be variously modified. For example, as described above with reference to FIG. 18, it may include a determination result such as left-sided motor impairment or information at the body level. Then, the server system creates training data by associating the evaluation result of the motor function with the incident information. For example, the input of the model used for machine learning is the evaluation result of the motor function, and the output is information indicating that a fall has occurred. Note that the output here may also be expressed as the correct label in machine learning. The correct label here is information indicating, for example, that the probability of falling is 100%.

[0189] The server system acquires a large number of similar training data and performs machine learning based on the training data. Note that the training data may include data to which information indicating that no fall has occurred is attached as the correct label. The learned model generated by such machine learning becomes a model that outputs numerical data representing the probability of falling when receiving the evaluation result of the motor function as the input.

[0190] Therefore, when the evaluation result of the motor function of the care recipient b is obtained, by inputting the evaluation result into the learned model, it becomes possible to estimate the probability (incident risk) of an incident such as a fall occurring to the care recipient b. For example, the estimation result of the incident risk of the care recipient b is notified to the terminal device 330 used by the caregiver B, who is the responsible caregiver. This makes it possible to notify the incident risk to caregivers, facility staff, etc. The same applies to the care recipient c. For example, the incident risk is notified to the terminal device 320 used by the family members who live together or separately. This makes it possible to notify the incident risk to the family members of the care recipient.

[0191] Note that, above, an example of a model using simple input and output has been described, but the method of this embodiment is not limited to this. For example, the information on the causes and countermeasures included in the incident information shown in FIG. 37 may be used for machine learning. In this case, as the learned model, it is possible to create a model that outputs information such as the cause of the predicted incident and effective countermeasures for preventing the incident.

[0192] Also, the input of the model is not limited to the evaluation result of the motor function. For example, as the input, information on the daily rhythm based on the determination result of sleep / wakefulness, the number and occurrence times of getting in and out of bed, the time required for getting in and out of bed, etc. may be included. Also, the input may include attribute information such as the height, weight, age, gender, medication information, and disease information of the care recipient. Also, the input is not limited to simple weight and may include body composition information such as muscle mass and skeletal muscle ratio. In particular, the muscle mass here may include the limb muscle mass. Furthermore, the input may include acceleration data measured during daily life (activities outside the bed 100), and for example, information such as the number of steps, walking style, and activity amount obtained based on the acceleration data may be included.

[0193] FIG. 38 is an example of a notification screen for incident risks, and is an example of a screen displayed on a terminal device (such as terminal devices 310-330) used by, for example, the family members or caregivers of the care recipient. As shown in FIG. 38, the notification screen for incident risks includes the name of the target care recipient, information on body weight, the evaluation result of motor function, and the specific content of the incident risk. As shown in FIG. 38, the evaluation result of motor function includes a determination result such as right-sided limb dysfunction and the physical level. The specific content of the incident risk includes at least one of the fall risk information representing the probability of occurrence of a fall and the drop risk information representing the probability of occurrence of a fall. Here, as the fall risk information and the drop risk information, numerical values representing probabilities, specific frequencies, and information such as the occurrence status of incidents regarding care recipients with similar motor functions are displayed. Also, on the notification screen for incident risks, as shown in FIG. 38, countermeasure information representing recommended countermeasures may be displayed.

[0194] 3.5 Exercise Guidance Bedridden elderly people may have a reversed day-night life, such as falling asleep during the day. Also, due to the difficulty in feeling social connections, there is a possibility of feeling lonely or becoming a shut-in. Therefore, in this embodiment, exercise guidance via a network may be performed.

[0195] FIG. 39 is a diagram showing an example of the information processing system 10 including the motor function evaluation device 200. In the information processing system 10 shown in FIG. 39, examples of users include an instructor who guides exercise, and care recipients b and c who are care recipients. The fact that care recipients b and c use the bed 100 and can transmit measurement data to the server system is the same as in FIG. 36. Also, in the example of FIG. 39, the instructor also uses the bed 100 to perform exercise in order to show a model to the care recipient. Therefore, measurement data regarding the instructor is also transmitted to the server system.

[0196] Furthermore, the information processing system 10 shown in FIG. 39 includes a camera 360 that images an instructor. The video information captured by the camera may be transmitted to the terminal device 340 of the care recipient b and the terminal device 350 of the care recipient c via the server system. By displaying the video of the instructor on the terminal devices 340 and 350 of the care recipients, the care recipients can perform movements in accordance with the movements of the instructor. Also, the video of the care recipient may be transmitted to the instructor's terminal device (not shown in FIG. 39). In this case, the instructor can also provide guidance to the care recipient in real time while checking the situation of the care recipient. As a result, since the care recipient can perform functional recovery training while communicating with the instructor, it is possible to make the care recipient feel a social connection.

[0197] Furthermore, the motion function evaluation device 200, which is a server system, evaluates the functional recovery training of each care recipient based on a comparison process between the load value information and the center of gravity information of the care recipient and the load value information and the center of gravity information of the instructor. Specifically, the evaluation processing unit 212 determines that the functional recovery training is being appropriately executed as the load value information of the care recipient is closer to the load value information of the instructor. The same applies to the center of gravity information. Also, as described above with reference to FIGS. 20-22, it may be determined whether to use the load value information or the center of gravity information based on the specific exercise content. In this way, similar to the example described above, an objective evaluation of the functional recovery training becomes possible. For example, the evaluation result may be transmitted to the instructor's terminal device, and the instructor may provide specific feedback.

[0198] 3.6 Bed Angle and Height Adjustment As described above with reference to FIG. 2, the bed 100 of the present embodiment may include a movable part 160 and a drive part 150 that drives the movable part 160. The bed 100 is a nursing bed capable of adjusting, for example, the back angle of the bottom 160b and the height of the entire bed 100.

[0199] In this embodiment, the height of the bed 100 may be controlled based on the load value information at the time of getting out of bed. FIG. 40 is a flowchart for explaining the height adjustment process of the bed 100. In step S801, the motor function evaluation device 200 detects getting out of bed. As described above, the getting-out-of-bed determination may be executed based on the load value information or other information.

[0200] In step S802, the acquisition unit 211 acquires the load value information at the time of getting out of bed. The load value information is, as in the above-described example, a waveform representing the temporal change of the load value, and includes, for example, the load value information for each of the getting-out-of-bed preparation period, the getting-out-of-bed operation period, and the getting-out-of-bed completion period.

[0201] In step S803, the evaluation processing unit 212 determines whether there is a problem with the waveform that is the load value information at the time of getting out of bed. FIG. 41A is a diagram showing the load value information when the height of the bed is appropriate, and FIG. 41B is a diagram showing the load value information when the height of the bed is too low.

[0202] In either waveform, since the care recipient performs an action of standing up by putting hands on the bed 100 from the sitting position or an action using the reaction of the upper body, a peak is detected during the getting-out-of-bed operation period. However, when the height of the bed 100 is excessively low, the action for standing up cannot be executed smoothly compared to the case where the height is appropriate. As a result, the waveform shown in FIG. 41B has a broader peak and a relatively smaller load value at the peak apex compared to the waveform shown in FIG. 41A. The evaluation processing unit 212 determines whether there is a problem based on which of the waveforms shown in FIG. 41A and FIG. 41B the waveform corresponding to the load value information acquired in step S802 is closer to.

[0203] If there is no problem with the waveform of the load value information, it is considered that the height of the bed 100 is appropriate in the current state. Therefore, the height adjustment of the bed 100 shown in FIG. 40 is completed. If there is a problem with the waveform of the load value information, it is considered that the height of the bed 100 is not appropriate. Therefore, the evaluation processing unit 212 executes the height adjustment of the bed 100. Basically, when the height is not appropriate, control is executed to increase the height of the bed 100.

[0204] However, in step S804, before raising the bed 100, the evaluation processing unit 212 determines whether the current height of the bed 100 is equal to or greater than a given threshold value. This is, for example, in consideration of the possibility that when the person to be assisted is severely frail, the waveform of the load value information may deviate from an appropriate waveform due to the low motor function of the person to be assisted. In this case, even if the bed 100 is raised, no improvement in the rising operation can be seen, so there is a possibility that the bed 100 will be too high.

[0205] Therefore, on the condition that the bed 100 is not at a height equal to or greater than a predetermined value (step S804: No), in step S805, the evaluation processing unit 212 executes the process of raising the bed 100. For example, the evaluation processing unit 212 outputs an instruction to increase the height of the bed 100 to the processing unit 110 of the bed 100 via the communication unit 230.

[0206] Also, in step S806, the output processing unit 213 outputs an output prompting the person to be assisted to re-execute the operation of getting out of bed (rising) from the bed 100. The output here may be executed using the display unit 240 of the motor function evaluation device 200, or may be executed using the display unit of the smartphone of the person to be assisted or the caregiver. After step S806, the process returns to step S801 and the process continues. That is, when the person to be assisted performs the getting-out-of-bed operation again, acquisition and determination of the load value information are executed, and the height of the bed 100 is adjusted as necessary.

[0207] Also, although there is a problem with the waveform of the load value information, if the height of the bed 100 has already reached or exceeded the threshold value (step S804: Yes), as described above, it is considered that the waveform of the load value information deviates from the normal waveform due to factors other than the height of the bed 100. Therefore, in this case, the evaluation processing unit 212 does not execute the process of raising the bed 100. Also, if the current height is maintained, the bed 100 is already too high, and the risk of falling or the like may increase. Therefore, the evaluation processing unit 212 may perform a transition process to the low bed mode in which the height of the bed 100 is set to a predetermined value or less in step S807. For example, the evaluation processing unit 212 outputs a transition instruction to the low bed mode to the processing unit 110 of the bed 100 via the communication unit 230.

[0208] Also, in the present embodiment, the back angle of the bed 100 may be controlled based on the load value information at the time of rising. Rising, for example, corresponds to a part of getting out of bed, and represents an operation from a state of leaning against the bottom 160b of the bed 100 to raising the upper body and shifting to the semi-upright sitting position. Here, the rising operation may include an operation such as getting up while holding the bed 100 or an operation after shifting to the semi-upright sitting position.

[0209] FIG. 42 is a flowchart for explaining the angle adjustment process of the bed 100. In step S901, the motor function evaluation device 200 detects the rising of the assisted person. The rising determination may be executed based on the load value information or may be executed based on other information such as a captured image.

[0210] In step S902, the acquisition unit 211 acquires the load value information at the time of rising. The load value information is a waveform representing the time-series change of the load value as in the above-described example, and includes, for example, the load value information for each of the getting-out-of-bed preparation period, the getting-out-of-bed operation period, and the getting-out-of-bed completion period. In step S903, the evaluation processing unit 212 determines whether there is a problem with the waveform that is the load value information at the time of rising. FIG. 43A is a diagram showing the load value information when the back angle of the bed 100 is appropriate, and FIG. 43B is a diagram showing the load value information when the back angle is too low.

[0211] In both waveforms, since the assisted person tries to shift from the lying position to the semi-upright position, fluctuations in the load value can be observed during the getting-out-of-bed preparation period. However, when the back angle is not appropriate, compared to the case where the back angle is appropriate, it takes a longer time to shift to the semi-upright position because the person cannot smoothly perform the rising motion. As a result, the waveform shown in FIG. 43B has a longer time until the shift to the semi-upright position (the length of the getting-out-of-bed preparation period) and a relatively smaller amplitude of the waveform during the shift compared to the waveform shown in FIG. 43A. The evaluation processing unit 212 determines whether there is a problem based on which of the waveforms shown in FIG. 43A and FIG. 43B the waveform corresponding to the load value information obtained in step S902 is closer to.

[0212] When there is no problem with the waveform of the load value information, it is considered that the current back angle of the bed 100 is appropriate. Therefore, the angle adjustment of the bed 100 shown in FIG. 42 is completed. When there is a problem with the waveform of the load value information, it is considered that the back angle of the bed 100 is not appropriate. Therefore, the evaluation processing unit 212 executes the angle adjustment of the bed 100. Basically, when the angle is not appropriate, control is executed to make it easier to get up by raising the back angle of the bed 100.

[0213] However, in step S904, the evaluation processing unit 212 determines whether the current back angle is equal to or greater than a given threshold before raising the back angle of the bed 100. This is because, for example, it is known that turning over becomes difficult if the back angle is raised too much.

[0214] Therefore, the evaluation processing unit 212 executes the process of raising the back angle of the bed 100 in step S905 on the condition that the back angle of the bed 100 is not equal to or greater than the predetermined value (step S904: No). For example, the evaluation processing unit 212 outputs an instruction to raise the back angle of the bed 100 to the processing unit 110 of the bed 100 via the communication unit 230.

[0215] Also in step S906, the output processing unit 213 outputs an instruction to prompt the assisted person to re - execute the action of getting up from the bed 100. After step S906, the process returns to step S901 and continues. That is, when the assisted person performs the getting - up action again, the acquisition and determination of the load value information are executed, and the angle of the bed 100 is adjusted as necessary.

[0216] Also, although there is a problem with the waveform of the load value information, if the back angle of the bed 100 has already reached or exceeded the threshold value (step S904: Yes), as described above, increasing the back angle further may make it difficult to turn over. Therefore, in this case, the evaluation processing unit 212 does not execute the process of increasing the back angle. For example, the evaluation processing unit 212 may perform a process of maintaining the back angle when it is determined as Yes in step S904. Alternatively, the evaluation processing unit 212 may perform a process of adjusting the back angle to the value when it was determined that the sleep state was the best based on the determination result of the assisted person's past sleep state.

[0217] In the above description, an example using the load value information at the time of standing up or getting up has been described, but the center - of - gravity information may be used instead of the load value information. For example, the evaluation processing unit 212 may determine whether the height and back angle of the bed 100 are appropriate based on the moving speed of the center - of - gravity position.

[0218] Also, the height adjustment of the bed 100 is not limited to being executed when getting out of bed. For example, the evaluation processing unit 212 may execute the height adjustment of the bed 100 based on the load value information or the center - of - gravity information during lying in bed.

[0219] In the above, examples of adjusting the height of the entire bed 100 and the back angle have been described, but control of other movable parts 160 may also be executed. For example, the evaluation processing unit 212 may adjust the foot angle by controlling the position and posture of the bottom 160b on the user's foot side based on at least one of the load value information and the center - of - gravity information. Also, the back angle and the foot angle may be controlled independently or in combination.

[0220] 3.7 Processing related to the use of handrails Also, in the above-described physical function evaluation, the evaluation processing unit 212 may perform processing related to the use of the handrail. FIG. 44 is a diagram showing an example of a handrail 400 provided on the bed 100. As shown in FIG. 44, the handrail 400 is installed, for example, on the side surface of the bed 100. A care recipient with reduced motor function can reduce the risk of falling or the like by performing operations while gripping the handrail 400 when lying in bed or getting out of bed.

[0221] The handrail 400 in the present embodiment may include a sensor that detects whether or not the care recipient is using the handrail 400. For example, the handrail 400 includes a contact portion 410 that is a portion gripped by the care recipient and a support column portion 420 that supports the contact portion 410. And the contact portion 410 may include a touch sensor that detects contact. Alternatively, the support column portion 420 may include a load sensor. Also, the handrail 400 may include both a touch sensor and a load sensor.

[0222] FIG. 45 is a flowchart for explaining the processing related to the use of the handrail in the evaluation processing unit 212. This processing may be executed in combination with the above-described physical function evaluation processing using, for example, FIG. 5. First, in step S1001, the evaluation processing unit 212 acquires sensor information from the handrail 400. The sensor information here may be the output of a touch sensor provided in the contact portion 410, the output of a load sensor provided in the support column portion 420, or both.

[0223] In step S1002, the evaluation processing unit 212 determines whether the assisted person is using the handrail 400. When using the handrail 400, the assisted person grips the contact portion 410 and performs an operation of applying body weight to the handrail 400. Therefore, when the touch sensor detects the contact of the assisted person (narrowly speaking, the hand of the assisted person), the evaluation processing unit 212 determines that the handrail 400 is being used. Alternatively, when the load sensor detects that a load equal to or greater than a predetermined value is applied to the support portion 420, the evaluation processing unit 212 determines that the handrail 400 is being used. The evaluation processing unit 212 may also perform both of these determinations.

[0224] When it is determined that the handrail 400 is being used (step S1002: Yes), in step S1003, the evaluation processing unit 212 sets on a handrail flag, which is a flag indicating that the handrail 400 is being used. It is assumed that the handrail flag is set to off as an initial value.

[0225] After the processing of step S1003, or when it is determined in step S1002 that the handrail is not being used (step S1002: No), in step S1004, the output processing unit 213 performs a display process based on the handrail flag. Note that step S1004 may be performed as part of the processing of step 205 in FIG. 5.

[0226] FIGs. 46A and 46B are examples of the screens displayed in step S1004. The screens shown in FIGS. 46A and 46B may be displayed on the display unit 240 of the motor function evaluation apparatus 200, or may be displayed on the display unit of another apparatus, in the same manner as FIGS. 8A to 8B.

[0227] FIG. 46A is an example of a screen displayed when the handrail flag is on. In this case, the output processing unit 213 outputs information indicating that the respective determination results of the speed evaluation and the power evaluation, and the comprehensive determination, were obtained by using the handrail 400. For example, in FIG. 46A, the score at the time of getting out of bed is illustrated, and here, in addition to the scores representing the results of each evaluation, the text "stood up using the handrail" is displayed. In this way, it is possible to clearly show the user who views FIG. 46A that the target score is the result obtained with the assistance of the handrail 400.

[0228] Further, the output processing unit 213 may output a comparison result with the case where the same care recipient does not use the handrail 400. For example, assume that the evaluation processing unit 212 obtains a first score when not using the handrail 400 and a second score when using the handrail 400 for each of the speed evaluation, the power evaluation, and the comprehensive determination. In this case, the evaluation processing unit 212 may obtain the amount of increase in the score by using the handrail 400 by obtaining the difference between the first score and the second score. The output processing unit 213 performs processing to display the amount of increase. In the example of FIG. 46A, the output processing unit 213 displays the amount of increase in each of the speed evaluation, the power evaluation, and the comprehensive determination as the effect of using the handrail 400.

[0229] Further, as described above with reference to FIGS. 8B and 8C, when it is determined that the motor function is low, the output processing unit 213 may output the problematic movement, the recommended functional recovery training, etc. In addition to these, when it is determined that the motor function is low and the handrail flag is off, the output processing unit 213 may perform output recommending the use of the handrail 400.

[0230] FIG. 46B is an example of a screen recommending the use of the handrail 400. In the example of FIG. 46B, in addition to the information shown in FIG. 8B, a comment "Using the handrail may improve the rising motion when getting out of bed" is displayed. In this way, for a care recipient who cannot smoothly perform the motion when getting out of bed due to a decline in motor function, it is possible to recommend using the handrail 400.

[0231] Further, the evaluation processing unit 212 may perform machine learning that takes load value information or the like as input and outputs the amount of score increase by the handrail 400 described above using FIG. 46A. In this way, by inputting the load value information or the like of the target care recipient, it is possible to create a learned model for estimating the amount of score increase when the care recipient uses the handrail 400. For example, the evaluation processing unit 212 may determine whether the use of the handrail 400 is effective for the target care recipient based on the learned model. When it is determined that the use of the handrail 400 is effective, the output processing unit 213 may perform an output recommending the use of the handrail 400 as shown in FIG. 46B.

[0232] 3.8 Visualization of Living Situation Also, in the method of the present embodiment, the body movement of the care recipient on the bed 100 can be measured during periods including when lying in bed, sleeping, waking up, and getting out of bed. Therefore, by using the load value information and the center of gravity information of the present embodiment, it becomes possible to estimate the living situation of the care recipient on the bed 100.

[0233] FIG. 47 is a waveform showing the transition of load value information over a predetermined period. As described above, during sleep when unconscious body movement occurs, the variation range (amplitude) of the load value information is smaller than when waking up when conscious body movement occurs. Also, among the waking states, the variation range of the load value information differs to a distinguishable extent between the state of being at rest and the state of performing clear movements such as functional recovery training. Also, when the care recipient is in a sitting position, since a part of the body weight is applied to the floor by touching the feet to the floor, the value of the load value decreases.

[0234] Therefore, when the load value information shown in FIG. 47 is acquired, as indicated by the upper arrow, the state of the care recipient can be estimated. When the sitting position is adopted, since the care recipient places their buttocks on one of the left or right ends of the bed 100, the state where the center of gravity position is biased to one of the left or right continues. Therefore, whether the care recipient is in the sitting position or not may be determined based on the center of gravity information.

[0235] The output processing unit 213 may output the determination result of the state (phase) of the care recipient on the bed 100 shown in FIG. 47 to the terminal devices of the family members or caregivers of the care recipient as the living situation. In this way, even if the caregiver or the like is not watching the care recipient closely, it becomes possible to appropriately let the caregiver or the like grasp the situation of the care recipient on the bed 100.

[0236] Further, the evaluation processing unit 212 may calculate the energy consumption based on the living situation of the care recipient on the bed 100. FIG. 48 is an example of a screen for displaying the calculated energy consumption. For example, here, the state of the care recipient is divided into four categories: sitting position, movement, sleep, and wakefulness. As described above, the evaluation processing unit 212 acquires the activity time, which is the time determined to be in each state. Also, for each state, information representing the activity intensity in that state is associated. Here, an example is shown in which METs, which represents how many times the resting state, is used as the activity intensity, but other indicators may be used as the activity intensity. The evaluation processing unit 212 calculates the amount of energy consumed in that state based on the activity intensity and activity time of the state. As a process for calculating the energy consumption, for example, it may be obtained by an equation such as energy consumption (kcal) = METs × body weight (kg) × activity time × 1.05. Also, various methods using energy consumption are known, and in this embodiment, they can be widely applied.

[0237] When the consumption energy is calculated and output, when the assisted person is made to exercise (function recovery training in a narrow sense), the result of the exercise is manifested as an increase in the consumption energy. Therefore, it becomes possible to improve the motivation of the assisted person for exercise. Also, based on the consumption energy, a process of estimating a standard amount of food intake may be executed.

[0238] Also, the living situation here may be information representing the transition of the posture taken by an assisted person who has been in the bed 100 for a predetermined period or more. FIG. 49 is another waveform representing the transition of the load value information in a predetermined period. As shown in FIG. 49, the state representing the living situation may be a state representing a posture such as a lying position or a semi-upright position. Whether it is a lying position may be determined based on whether the change in the load value information is within a certain range. This is because when in a lying position, the range in which the body can move is narrower compared to other postures such as a sitting position, and the fluctuation of the load value is relatively small. However, the evaluation processing unit 212 may use a device capable of measuring the distribution of the load value on the bed 100 and determine whether it is a lying position based on the distribution of the load value. In a lying position, since the contact area on the bed 100 is wider compared to other postures, it is considered that the load value is distributed over a relatively wide range.

[0239] Also, as described above, the evaluation processing unit 212 may determine sleep and wakefulness. For example, as shown in FIG. 49, the evaluation processing unit 212 may process the lying position during sleep and the lying position during wakefulness as different states.

[0240] The output processing unit 213 outputs information representing the posture of the assisted person on the bed 100 based on the determination result of the evaluation processing unit 212. FIG. 50 is an example of the information output by the output processing unit 213. As shown in FIG. 50, the output processing unit 213 may output a graph representing the ratio of the time taken in each posture. In this way, it becomes possible to let an assistant or the like determine whether the assisted person has not been in a lying position all the time on the bed 100. For example, when the time ratio of the lying position is a predetermined value or more, the output processing unit 213 may perform an output prompting a change in posture to a sitting position or getting out of bed.

[0241] For example, it is known that if a person remains in a sedentary state for a long time for the treatment of diseases or injuries, there is a possibility of developing disuse syndrome, which can cause a significant decline in physical ability and have an adverse effect on the mental state. According to the method of this embodiment, since it is possible to prompt attention when the lying position state continues for a long time, it becomes possible to suppress disuse syndrome and the like.

[0242] 3.9 Correction processing based on the firmness of the mat As described above, the evaluation processing unit 212 may execute various processes based on the waveform of the load value information itself or the feature amount obtained from the waveform of the load value information. However, when a member that absorbs impact is used together with the bed 100, the load value information may change according to the characteristics of the member. The member here is, for example, a mat laid between the bed 100 and the floor. However, the member may be a mattress placed on the bottom 160b of the bed 100, or other members. Hereinafter, an example of the mat will be described.

[0243] For example, consider the sitting-down motion of a user in a standing position shifting to a sitting position on the bed 100. Here, the sitting-down motion is similar to the falling motion of an object. Specifically, the sitting-down motion can be considered as the motion of an object with a mass proportional to the weight of the care recipient falling from a height proportional to the height of the care recipient. Also, the fact that the sitting-down motion can be considered as a falling motion is regardless of whether the care recipient is a healthy person or a frail patient. Since the sitting-down motion is a motion with energy caused by height and weight in this way, the contributions of height and weight are large. Therefore, when the fluctuations in the height and weight of the care recipient are small, it is expected that the fluctuations in the load value information when the sitting-down motion is performed are also small. However, in reality, even if the fluctuations in height and weight are small, the load value information may fluctuate according to the firmness of the mat.

[0244] Figures 51A and 51B are examples of load value information when the same assisted person performs a sitting-down movement from a standing position to a sitting position (seated position). Figure 51A is an example of load value information when the mat is hard, and Figure 51B is an example of load value information when the mat is soft. The horizontal axis of Figures 51A and 51B represents time, and the vertical axis represents the load value.

[0245] As shown in Figure 51A, when the mat is hard, the load value at the peak is relatively large. Also, when the mat is hard, the variation in the load value due to the impact of sitting down subsides in a relatively short time. Hereinafter, the peak value of the load value in the sitting-down movement will be referred to as the sitting peak. Also, the period during which the load value varies due to sitting down (the period from the start of hip contact to when the load value stabilizes) will be referred to as the sitting time. In contrast, as shown in Figure 51B, when the mat is soft, compared to when the mat is hard, the value of the sitting peak becomes smaller and the sitting time becomes longer.

[0246] As described above with reference to Figures 6 and 7, etc., since the waveform of the load value information is information used for the determination of the motor function, it may not be preferable for it to change due to factors other than the motor function such as the hardness of the mat. Therefore, the evaluation processing unit 212 may execute correction processing for suppressing the influence of the hardness of the mat on the load value information.

[0247] Figure 52 is a flowchart for explaining the correction processing of the load value information. When this processing is started, in step S1101, the evaluation processing unit 212 acquires information on the height and weight of the assisted person. For example, the evaluation processing unit 212 may receive an input operation by the assisted person or the caregiver, or may perform processing to acquire information on the height and weight of the assisted person from a care system used in a care facility or the like.

[0248] In step S1102, the output processing unit 213 outputs information instructing the assisted person to take a seat. FIG. 53A is an example of the screen output in step S1102. As shown in FIG. 53A, for example, the output processing unit 213 may display text such as "Please sit on the bed while stretching your back as much as possible without using the handrail." In this way, even when the assisted person is different, or when the assisted person is the same but the execution timing of the correction process is different, it becomes easier to execute the same movement, so that the accuracy of the correction process can be improved. Also, as described above, since the point that the sitting movement can be regarded as a falling movement is common to healthy persons and frail patients, it is possible to suppress the influence of the difference in motor function on the correction process.

[0249] In step S1103, the evaluation processing unit 212 acquires load value information when the assisted person executes a sitting movement based on the sitting instruction, and performs waveform analysis of the load value information. For example, as waveform analysis, the evaluation processing unit 212 performs a process of acquiring values of a sitting peak, a sitting time, and an area obtained by integrating the waveform at the sitting time. In FIGS. 51A and 51B, the sitting peak corresponds to h, the sitting time corresponds to t, and the area corresponds to S.

[0250] Then, in step S1103, the evaluation processing unit 212 obtains a correction value for correcting the waveform of the load value information based on the sitting peak, the sitting time, and the area. For example, the evaluation processing unit 212 may perform a process of correcting the respective values of the sitting peak and the sitting time while maintaining the area. In this case, the storage unit 220 may store a reference ratio that is the ratio of the sitting peak to the sitting time when using a mat of a reference firmness. The evaluation processing unit 212 obtains the values of the corrected sitting peak and the sitting time such that the ratio of the corrected sitting peak and the sitting time is close to the reference ratio (for example, the difference value is equal to or less than the threshold value), and the change amount of the area is equal to or less than a predetermined value. In this way, regardless of the firmness of the mat actually used, it becomes possible to match the waveform of the load value information to the case of using a mat of a reference firmness. Note that the content of the correction process based on the sitting peak, the sitting time, and the area is not limited to the above example, and various modifications can be made.

[0251] Also, in step S1103, the evaluation processing unit 212 may perform weight correction processing. As described above, the sitting motion can be considered as a falling motion in which an object with a weight proportional to the body weight falls from a height proportional to the body height. Therefore, the momentum immediately before sitting on the bed 100 is a value that depends on the body height and weight, and it is assumed that the area, which is information corresponding to the impulse, is also a value that depends on the body height and weight. However, since the body weight changes according to situations such as diet, exercise, and illness, it is also possible that the weight obtained in step S1101 is not an appropriate value. Therefore, the evaluation processing unit 212 may correct the weight value based on the area value. For example, the evaluation processing unit 212 may obtain the corrected weight based on the condition that the area is proportional to the product of the body height and weight. Note that the weight correction processing is not limited to the above example, and various modifications can be made. Also, the weight correction processing may be omitted.

[0252] In step S1104, the output processing unit 213 outputs the corrected value and performs a process of accepting an approval / non-approval operation by the user. FIG. 53B is an example of a screen output in step S1104. As shown in FIG. 53B, for example, the output processing unit 213 may present the corrected values for each of the weight, sitting time, and sitting peak. Further, the output processing unit 213 may display inquiry text such as "Do you want to correct with this value?" and "Yes" and "No" buttons for receiving user input.

[0253] When "Yes" is selected on the screen shown in FIG. 53B, the evaluation processing unit 212 determines that the result of the waveform analysis has been approved (step S1104: Yes). Therefore, in step S1105, the evaluation processing unit 212 corrects the load value information using the correction value obtained in step S1103. Each process such as the exercise function determination may be executed using the load value information after the correction process. In this way, it becomes possible to execute the determination process of the exercise function using the load value information with high accuracy.

[0254] When "No" is selected on the screen shown in FIG. 53B, the evaluation processing unit 212 determines that the result of the waveform analysis has not been approved (step S1104: No). In this case, the process returns to step S1102 and the process continues.

[0255] In the above, an example of executing the correction process based on the load value information in the sitting motion has been described, but the present invention is not limited to this. For example, the evaluation processing unit 212 may receive a user input for selecting the firmness of the mat, and correct the load value information according to the received firmness. The harder the mat is compared to the standard, the correction process of increasing the sitting peak and shortening the sitting time is executed. Further, the output processing unit 213 may output an instruction to the user to place an object of a predetermined weight on the bed 100. The evaluation processing unit 212 obtains correction information based on the load value information when the object is placed on the bed 100, and corrects the load value information of the care recipient based on the correction information. In this way, since the load value information for obtaining the correction information does not depend on the height and weight of the care recipient, it is possible to easily execute the correction process of the load value information. In addition, various modifications are possible for the specific content of the correction process for suppressing the influence of members such as mats.

[0256] Although the present embodiment has been described in detail as above, those skilled in the art will easily understand that many modifications can be made without substantially departing from the novel matters and effects of the present embodiment. Therefore, all such modified examples are intended to be included in the scope of the present disclosure. For example, in the specification or drawings, a term described at least once together with a broader or synonymous different term can be replaced with the different term at any place in the specification or drawings. Also, all combinations of the present embodiment and the modified examples are included in the scope of the present disclosure. Further, the configurations and operations of the bed, the motion function evaluation device, the information processing system, etc. are not limited to those described in the present embodiment, and various modifications can be made.

Explanation of Signs

[0257] 10... Information processing system, 100... Bed, 110... Processing unit, 120... Memory unit, 130... Communication unit, 140, 140A - 140D... Load sensor, 150... Driving unit, 160... Movable part, 160a... Leg part, 160b... Bottom, 200... Motor function evaluation device, 210... Processing unit, 211... Acquisition unit, 212... Evaluation processing unit, 213... Output processing unit, 220... Memory unit, 230... Communication unit, 240... Display unit, 250... Operation unit, 310 - 350... Terminal device, 360... Camera, 400... Handrail, 410... Contact part, 420... Support part, v1 - v5... Moving speed of the center of gravity position

Claims

1. An acquisition unit that is attached to a bed and acquires at least one of load value information representing the magnitude of a load caused by the body movement of a user on the bed and center-of-gravity information representing the transition of the center-of-gravity position of the user caused by the body movement, based on a load sensor that detects the load applied to the bed; An evaluation processing unit that evaluates the motor function of the user based on at least one of the acquired load value information and the center-of-gravity information; A motor function evaluation device including the above.

2. In Claim 1, the acquisition unit acquires the load value information during a period when the user lies in bed or gets out of bed, and the evaluation processing unit is a motor function evaluation device that evaluates the motor function of the user when lying in bed or getting out of bed based on the load value information.

3. In Claim 2, when the acquisition unit acquires the load value information during a period when the user lies in bed, the evaluation processing unit performs a first process of evaluating the motor function of the upper body of the user, and when the acquisition unit acquires the load value information during a period when the user gets out of bed, the evaluation processing unit performs a second process of evaluating the motor function of the lower body of the user, is a motor function evaluation device that performs at least one of the above.

4. In Claim 3, when the evaluation processing unit performs the second process, the acquisition unit acquires the load value information during a bed getting-out preparation period, which is a period until the user transitions to a sitting position during the period of getting out of bed, and the evaluation processing unit is a motor function evaluation device that evaluates the motor function of the lower body of the user based on the load value information during the bed getting-out preparation period.

5. In Claim 2, the evaluation processing unit is a motor function evaluation device that executes at least one of an evaluation of speed based on the time required for the change in the load represented by the load value information and an evaluation of power based on the magnitude of the load, as an evaluation of the motor function.

6. In Claim 2, the acquisition unit acquires the load value information during a period when the user gets out of bed, and the evaluation processing unit is a motor function evaluation device that detects at least one of the user's fall from the bed and slipping off.

7. In Claim 1, the acquisition unit acquires the center-of-gravity information during a period when the user is in a lying position, based on a plurality of the load sensors, and the evaluation processing unit is a motor function evaluation device that evaluates the motor function of the user in the lying position based on the center-of-gravity information.

8. In claim 7, the acquisition unit is a motor function evaluation device that acquires the center-of-gravity information during the period in which the user is determined to be in a sleeping state.

9. In claim 7, the evaluation processing unit is a motor function evaluation device that evaluates the motor function based on the moving speed of the center-of-gravity position along a first direction and the moving speed of the center-of-gravity position along a second direction that is the opposite direction of the first direction.

10. In claim 7, the acquisition unit acquires the center-of-gravity information during the lying period in which the user transitions to the lying position and during the getting-out-of-bed period in which the user ends the lying position based on a plurality of the load sensors, the evaluation processing unit is a motor function evaluation device that evaluates the motor function based on the center-of-gravity position or the moving speed of the center-of-gravity position during the lying period and the getting-out-of-bed period.

11. In any one of claims 1 to 10, when it is determined that there is an abnormality in the evaluation of the motor function, the motor function evaluation device further includes an output processing unit that performs an output for prompting training for recovering the motor function.

12. In claim 11, the acquisition unit acquires at least one of the load value information and the center-of-gravity information during the period in which the user is performing the training on the bed based on the output of the output processing unit, the evaluation processing unit is a motor function evaluation device that evaluates the training based on at least one of the load value information and the center-of-gravity information.

13. In any one of claims 1 to 10, the acquisition unit acquires the center-of-gravity information during the period in which the user is in the lying position based on a plurality of the load sensors, the evaluation processing unit is a motor function evaluation device that evaluates whether the user is performing abdominal breathing or thoracic breathing based on the amount of change in the center-of-gravity position.

14. In any one of claims 1 to 10, the acquisition unit acquires the load value information and the center-of-gravity information during the period in which the user is in the sleeping state, the evaluation processing unit is a motor function evaluation device that determines whether the cause of the body movement is coughing or turning over based on the magnitude of the load and the amount of change in the center-of-gravity position of the user in the left-right direction.

15. Based on a load sensor attached to the bed and detecting the load applied to the bed, an acquisition unit that acquires at least one of load value information representing the magnitude of the load caused by the body movement of the user on the bed and center of gravity information representing the transition of the center of gravity position of the user caused by the body movement. As an evaluation processing unit that evaluates the motor function of the user based on at least one of the acquired load value information and the center of gravity information. A program that causes a computer to function.

16. Based on a load sensor attached to the bed and detecting the load applied to the bed, it acquires at least one of load value information representing the magnitude of the load caused by the body movement of the user on the bed and center of gravity information representing the transition of the center of gravity position of the user caused by the body movement. Evaluates the motor function of the user based on at least one of the acquired load value information and the center of gravity information. Motor function evaluation method.

Images