Methods, programs, and information processing devices that computers use to obtain indicators representing the stability of sleep patterns.

Abstract

To acquire an index indicating stability of a sleep pattern.SOLUTION: A computer-executed method for acquiring an index indicating stability of a sleep pattern comprising the steps of: acquiring biological information of a subject; acquiring a sleep index from the acquired biological information; and acquiring stability of a sleep pattern of the subject. The sleep index includes: a first time when sleep of a first depth appears; and a second time when sleep of a depth shallower than the first depth appears. The step of acquiring the stability of the sleep pattern includes a step of acquiring at least one of time lengths of the first time and the second time which appear during a first period of a prescribed length when the subject lies on a bed within a day, and acquiring an index indicating the stability of the sleep pattern of the subject by using a variation degree of the acquired one of the time lengths for respective days of a plurality of days.SELECTED DRAWING: Figure 9

Description

[Technical Field]

[0001] The present disclosure relates to information processing, and more specifically to a technique for acquiring an index representing stability of a sleep pattern. [Background Art]

[0002] Techniques for evaluating sleep quality have been proposed. For example, Japanese Unexamined Patent Publication No. 2013-99507 (Patent Document 1) calculates a subject's sleep evaluation score, performs logistic regression analysis on the sleep evaluation score to calculate a sleep disorder discrimination probability, and calculates the subject's sleep index based on the sleep disorder discrimination probability. This sleep evaluation score is obtained from a plurality of types of predetermined items extracted based on polysomnography (PSG) measurement data, including at least an item related to sleep depth, an item related to sleep rhythm, and an item related to mid-sleep awakening. It is obtained by multiplying the principal component coefficient of the sleep evaluation score obtained for the predetermined items by the sleep determination data corresponding to the predetermined items calculated from the subject's biological signals (see the abstract). [Prior Art Documents] [Patent Documents]

[0003] [Patent Document 1] Japanese Unexamined Patent Publication No. 2013-99507 [Summary of the Invention] [Problem to be Solved by the Invention]

[0004] As an index related to sleep, there is a demand for acquiring an index that reflects the stability of a sleep pattern. Patent Document 1 proposes a sleep evaluation score based on the discrimination probability of sleep disorder calculated from the sleep evaluation score as an indicator of sleep quality, but does not disclose a technique for acquiring an index that reflects the stability of a sleep pattern. Therefore, the technique of Patent Document 1 cannot meet the demand described above.

[0005] This disclosure is made in light of the above-mentioned background, and in one aspect, its purpose is to provide a technology for obtaining an index that represents the stability of sleep patterns. [Means for solving the problem]

[0006] A computer method relating to this disclosure for obtaining an index representing the stability of a sleep pattern comprises the steps of: obtaining biometric information of a subject; obtaining a sleep index from the obtained biometric information; and obtaining the stability of the subject's sleep pattern, wherein the sleep index includes a first hour in which a first depth of sleep occurs and a second hour in which lighter sleep than the first depth occurs, and the step of obtaining the stability of the sleep pattern obtains the length of at least one of the first hour or the second hour occurring in a first period of a predetermined length in which the subject is lying down during the day, for each of multiple days During the same time period in the aforementioned first period The process includes a step of obtaining an index representing the stability of the subject's sleep pattern, using the degree of variation in the length of the obtained one of the time periods.

[0007] In the method described above, the period from when the subject gets into bed until when they get up includes a period of lying down, and the period of lying down includes multiple first periods, and the step of obtaining the stability of the sleep pattern further includes, for each first period, obtaining the length of at least one of the first hour or second hour that occurs in that first period, for each of the multiple days During the aforementioned first period in the same time zone The method includes the steps of obtaining the degree of variation in the length of the one of the acquired periods, and obtaining an index representing the stability of the subject's sleep pattern using the statistics of the degree of variation obtained for each of the multiple first periods.

[0008] In the method described above, the statistic includes the average of the degree of variability obtained for each of the multiple first periods.

[0009] The method described above further includes a step of evaluating the cognitive function of a subject based on the correlation between an assessment value of a person's cognitive function and an index representing the stability of that person's sleep pattern, using an index representing the stability of the sleep pattern obtained for the subject.

[0010] The method described above further includes a step of obtaining the correlation, the step of obtaining the correlation includes a step of training a learning model, which takes an index representing the stability of sleep patterns as input and an evaluation value of cognitive function as output, to learn the correlation.

[0011] The method described above further comprises the step of generating an object for each subject to visualize the time-series changes in the values ​​indicated by an index representing the stability of the subject's sleep pattern.

[0012] The program relating to this disclosure causes a computer to execute the method described above. The information processing device relating to this disclosure comprises a memory storing the above-mentioned program and a processor that executes the program. [Effects of the Invention]

[0013] According to one embodiment, an index reflecting the stability of sleep patterns can be obtained.

[0014] The above and other objects, features, aspects and advantages of this invention will become apparent from the following detailed description relating to this invention, which will be understood in conjunction with the accompanying drawings. [Brief explanation of the drawing]

[0015] [Figure 1] This is a diagram showing an example of the configuration of the monitoring system 100. [Figure 2] This is a block diagram outlining the configuration of the monitoring system 100. [Figure 3] This diagram shows a schematic representation of the monitoring system 100 using the sensor box 119. [Figure 4]It is a block diagram showing the hardware configuration of the computer system 400. [Figure 5] It is a block diagram showing the functional configuration of the apparatus 600 according to the present embodiment. [Figure 6] It is a diagram conceptually illustrating an aspect of data storage in the storage unit 620. [Figure 7] It is a diagram showing event contents 626 indicated by event information 622 for each day of one week for a certain resident. [Figure 8] It is a diagram schematically showing a procedure for acquiring sleep stability of a certain resident. [Figure 9] It is a diagram schematically explaining acquisition and application of a stability index for a certain resident. [Figure 10] It is a flowchart showing an example of processing according to the present embodiment. [Figure 11] It is a flowchart showing an example of processing according to the present embodiment. [Figure 12] It is a flowchart showing an example of processing according to the present embodiment. DETAILED DESCRIPTION OF THE INVENTION

[0016] Hereinafter, embodiments of the present invention will be described with reference to the drawings. In the following description, identical components are denoted by identical reference numerals. Their names and functions are also identical. Therefore, detailed description thereof will not be repeated.

[0017] The system or apparatus described below is applied to scenes used in nursing care facilities, hospital facilities and other facilities capable of continuously accommodating care recipients or patients. Note that application targets are not limited to such residents of facilities as care recipients or patients, and can be broadly applied to people who do not correspond to care recipients or patients.

[0018] <System Overview> Referring to Figure 1, the overview of the monitoring system will be explained. Figure 1 is a diagram showing an example of the configuration of the monitoring system 100. An example of the people to be monitored are the residents in each room located in the living room area of ​​facility 180. In the monitoring system 100 in Figure 1, rooms 110 and 120 are located in the living room area. Room 110 is assigned to resident 111. Room 120 is assigned to resident 121.

[0019] The monitoring system 100 includes a gateway server 130, a switching device 12, an access point 140, a management server 200, a sensor box 119, various devices that communicate with the sensor box 119, and mobile terminals 161, 162, 163, and 164.

[0020] The gateway server 130 connects the internal network (intranet) of facility 180 with the external network 16 of facility 180. The external network 16 is, for example, the internet or a public telephone network. The cloud server 150, the push server 160, and the wireless base station 15 are also connected to the external network 16. The management server 200 configures a local server, such as an on-premise server, in relation to the cloud server 150.

[0021] The switching device 135 connects each device in the internal network of the facility 180 to one another. In some cases, a router or a switch may be used as the switching device 135. In the example shown in Figure 1, there are two switching devices 135, but this number is not limited to this. The internal network of the facility 180 may consist of a combination of multiple switching devices 135.

[0022] Access point 140 is used to connect mobile terminals 161 and 162 to the internal network of facility 180. In some cases, a Wi-Fi® (Wireless Fidelity) router may be used as access point 140.

[0023] The management server 200 receives event information from the sensor box 119 in the facility 180 and manages the information of residents in each room. The management server 200 also communicates with the mobile terminals 161 and 162, manages the staff holding these mobile terminals, and sends various notifications to each mobile terminal. When sending notifications to the mobile terminals 161 and 162, the management server 200 may use an external push server 160. Alternatively, an external cloud server 150 may perform some or all of the functions of the management server 200.

[0024] The sensor box 119, by coordinating with the camera and sensors built into its casing and other various sensors in the living rooms 110 and 120, acquires information about the residents 111 and 121 in the living rooms 110 and 120, respectively. This information may include images of each resident (or the living room), their body temperature, pulse, and other vital information. The sensor box 119 also transmits the acquired information about residents 111 and 121 to the management server 200 via the internal network. Details of the sensor box 119 will be described later.

[0025] Mobile terminals 161 and 162 are used by caregivers and other staff engaged in caregiving at facility 180. Staff can use mobile terminals 161 and 162 to input care records, etc. Mobile terminals 161 and 162 transmit the care records to the management server 200. In addition, if a problem occurs with residents 111 and 121, staff can receive notifications from the management server 200 using mobile terminals 161 and 162. Within facility 180, mobile terminals 161 and 162 are connected to access point 140 and communicate with the management server 200 via the internal network. In the example described herein, caregivers 141, 142, 143, and 144 each hold mobile terminals 161, 162, 163, and 164, respectively.

[0026] Mobile terminals 163 and 164 can communicate with the management server 200 from outside the facility 180 via a wireless base station 15, etc., and then via a gateway server 11. When mobile terminals 163 and 164 communicate with the management server 200 from outside the facility 180, some of the services provided from the management server 200 to mobile terminals 163 and 164 may be restricted in order to protect resident information.

[0027] Note that the number of other devices, such as mobile terminals 161, 162, access points 140, and switching equipment 135, is not limited to the numbers exemplified in Figure 1.

[0028] Each of the rooms 110 and 120 includes furniture 112, a bed 113, and a toilet 114 as part of its facilities. Door sensors 118 are installed on the doors of each of the rooms 110 and 120 to detect when the door is opened or closed. A toilet sensor 116 is installed on the door of the toilet 114 to detect when the toilet 114 is opened or closed. An odor sensor 117 is installed on the bed 113 to acquire information about the excretion of the resident 111. The resident 111 wears a vital sensor 290 that detects the resident's vital information. An example of vital information to be detected is the resident's body temperature. Another example is the resident's respiration. Yet another example is the resident's heart rate. Yet another example is two or more types of information from these. In room 110, the resident 111 can operate a care call sub-unit 115. When resident 111 operates the care call handset 115, the care call handset 115 emits a call signal, which is received by the sensor box 119. The sensor box 119 transmits the received call signal to the management server 200. The management server 200 transmits a signal to the mobile terminal 220 notifying it that it has received a call from resident 111.

[0029] The sensor box 119 incorporates sensors for detecting the behavior of objects within the living rooms 110, 120. One example of a sensor is a Doppler sensor for detecting the movement of an object. Another example is a camera. Still other examples include a care call sub-unit 115, a door sensor 118, a toilet sensor 116, an odor sensor 117, or a vital signs sensor 290. The sensor box 119 may include at least one of these sensors as its sensor.

[0030] The components of the monitoring system 100 will be described with reference to Figure 2. Figure 2 is a block diagram showing an overview of the configuration of the monitoring system 100.

[0031] [Sensor Box 119] The sensor box 119 comprises a control device 101, a ROM (Read Only Memory) 102, a RAM (Random Access Memory) 103, a communication interface 104, a camera 105, a Doppler sensor 106, a wireless communication device 107, and a storage device 108.

[0032] The control device 101 controls the sensor box 119. The control device 101 is comprised of, for example, at least one integrated circuit. The integrated circuit is comprised of, for example, at least one CPU (Central Processing Unit), MPU (Micro Processing Unit) or other processor, at least one ASIC (Application Specific Integrated Circuit), at least one FPGA (Field Programmable Gate Array), or a combination thereof.

[0033] An antenna (not shown) and the like are connected to the communication interface 104. The sensor box 119 exchanges data with external communication devices via this antenna. External communication devices include, for example, the management server 200, mobile terminals 161, 162, 163, 164 and other terminals, access point 140, cloud server 150 and other communication terminals.

[0034] In one implementation, camera 105 is a near-infrared camera. The near-infrared camera includes an IR (Infrared) illuminator that emits near-infrared light. By using a near-infrared camera, images representing the interior of rooms 110 and 120 can be captured even at night. In another implementation, camera 105 is a surveillance camera that receives only visible light. In yet another implementation, a 3D sensor or a thermographic camera may be used as camera 105. The sensor box 119 and camera 105 may be configured as an integrated unit or as a combination of separate devices. The direction in which camera 105 images corresponds to a direction in which substantially the entire area inside rooms 110 and 120 can be imaged.

[0035] The Doppler sensor 106 functions as a motion sensor. The Doppler sensor 106 emits and receives microwaves, ultrasound, and other radio waves to detect the behavior (movement) of objects (e.g., residents 111 and care staff) in the rooms 110 and 120. This allows for the detection of biological information of residents 111 and 121 in the rooms 110 and 120.

[0036] More specifically, the Doppler sensor 106 is connected to the control device 101 and measures the movement of the chest surface of the resident 111 in accordance with the control of the control device 101. The Doppler sensor 106 transmits microwaves or ultrasound (hereinafter also referred to as "transmitted waves"), receives microwaves or ultrasound reflected by an object (i.e., "reflected waves"), and outputs a Doppler signal of Doppler frequency components based on the transmitted waves and reflected waves. When an object is moving, the frequency of the reflected waves shifts in proportion to the speed at which the object is moving due to the so-called Doppler effect. As a result, a difference (Doppler frequency component) is created between the frequency of the transmitted waves and the frequency of the reflected waves. The Doppler sensor 106 generates this Doppler frequency component signal as a Doppler signal at a predetermined sampling rate and outputs the Doppler signal to the control device 101. When the control device 101 receives a Doppler signal from the Doppler sensor 106, it stores the received Doppler signal in time series in the memory device 108. Furthermore, when microwaves are used as the transmitting wave, these microwaves penetrate clothing and reflect off the body surface of the resident 111. Therefore, even if the resident 111 is wearing clothes, body movement can be detected.

[0037] In one example, each Doppler sensor 106 emits microwaves in the 24GHz band towards the beds 113 in each room 110, 120, and receives the reflected waves reflected by the residents 111, 121, etc. The reflected waves are Doppler-shifted due to the movements of the residents 111, 121. From these reflected waves, the Doppler sensor 106 can detect the respiratory status and heart rate of the residents 111, 121.

[0038] The wireless communication device 107 receives signals from the care call sub-unit 115, door sensor 118, toilet sensor 116, odor sensor 117, and vital sensor 290, and transmits these signals to the control device 101. The care call sub-unit 115 is equipped with a care call button 241. When the care call button 241 is operated, the care call sub-unit 115 transmits a signal (e.g., a call signal) indicating that the operation has been performed. The transmitted signal is received by the wireless communication device 107. When the door sensor 118, toilet sensor 116, odor sensor 117, and vital sensor 290 transmit their respective detection results, the transmitted signals are also received by the wireless communication device 107.

[0039] The storage device 108 is, for example, a fixed storage device such as flash memory or a hard disk, or a recording medium such as an external storage device. The storage device 108 stores the program executed by the control device 101, and various data used for the execution of the program. The various data may include behavioral information of the residents 111 and 121. Details of the behavioral information will be described later.

[0040] At least one of the above programs and data may be stored in a storage device other than storage device 108 (for example, the storage area of ​​the control device 101 (e.g., cache memory), ROM 102, RAM 103, or external devices (e.g., management server 200 or mobile terminals 161, 162, 163, 164, etc.)) as long as it is a storage device accessible by the control device 101.

[0041] [Detection of sleep and wakefulness] In this embodiment, sleep includes "sleeping" and "waking." "Waking" includes "waking up in the middle of the night." A person's sleep state can be determined from their body movements. In this embodiment, the body movements of residents 111 and 121 are detected based on the Doppler signal output from the Doppler sensor 106. Specifically, the control device 101 focuses on the fact that the amplitude of the Doppler signal represents the amount of change in the chest and abdomen movement associated with the heartbeat and breathing of residents 111 and 121 who are in the bed (bedding) 113, i.e., body movements, and detects the sleep state of residents 111 and 121 who are in the bed (bedding) 113.

[0042] More specifically, the control device 101 performs a Fast Fourier Transform (FFT) on the Doppler signals measured within a predetermined time period from the time of measurement, and from the spectrum obtained by this FFT, it calculates the average amplitude in the frequency band corresponding to the frequency of typical respiration. The control device 101 compares the calculated average value with a threshold for determining sleep or wakefulness. If the comparison result indicates that the calculated average value is less than or equal to the threshold, it determines that the person is "sleeping" during that time period. If the average value exceeds the threshold, it determines that the person is "awake" during that time period. In addition, the control device 101 performs a Fast Fourier Transform (FFT) on the Doppler signals measured within a predetermined time period from the time of measurement, and from the spectrum obtained by this FFT, it calculates the average amplitude in the frequency band corresponding to the frequency of typical heartbeats. The control device 101 compares the obtained average value with a threshold for determining sleep or wakefulness. If the obtained average value is less than or equal to the threshold, the control device determines that the person is "sleeping" during that time. If the average value exceeds the threshold, the control device determines that the person is "awake" during that time.

[0043] Furthermore, in this embodiment, "deep sleep" can be classified as "sleep," while "light sleep" and "middle-of-the-night awakenings" can be classified as "awakenings."

[0044] [Activity Information] Next, the behavioral information in this embodiment will be explained. The behavioral information is, for example, information indicating that residents 111 and 121 have performed a predetermined action. In one example, the predetermined action includes "getting into bed," which indicates that residents 111 and 121 have entered the bed (bedding) 113 to go to sleep at night, etc.; "getting up," which indicates that residents 111 and 121 have gotten up in the bed (bedding) 113 after "getting into bed"; and "leaving bed," which indicates that residents 111 and 121 have left the bed (bedding) 113. "Leaving bed" includes "outside bed," which indicates that residents 111 and 121 are in a place in the living room 110 and 120 other than the bed (bedding) 113, and "absence," which indicates that residents 111 and 121 have left the living room 110 and 120.

[0045] In one embodiment, the control device 101 generates activity information for residents 111 and 121 associated with each room 110 and 120 based on images captured by cameras 105 installed in each room 110 and 120. For example, the control device 101 detects partial images of residents 111 and 121's heads from the images and detects information on residents 111 and 121's "entering bed," "getting up," "leaving bed," "out of bed," and "absence" based on the time change in the size of these detected partial images of residents 111 and 121's heads. A specific example of activity information generation will be described in more detail below.

[0046] First, the storage device 108 stores the location area of ​​each bed 113 in the living rooms 110 and 120, a first threshold Th1, and a second threshold Th2. The first threshold Th1 is a value used to distinguish the size of the resident's head between when they are lying down and when they are sitting, within the location area of ​​the bed 113. The second threshold Th2 is a value used to distinguish whether the resident is standing, based on the size of their head, within the living rooms 110 and 120, excluding the location area of ​​the bed 113.

[0047] The control device 101 extracts motion regions from the target image as the regions of residents 111 and 121, for example, by background subtraction or frame subtraction. The control device 101 further extracts the head regions (partial images) of residents 111 and 121 from the extracted motion regions, for example, by circular or elliptical Hough transforms, by pattern matching using a pre-prepared head model, and by using thresholds derived by a neural network trained for head detection. The control device 101 detects "entering bed" and "getting up" from the position and size of the extracted head regions within the region of the people. If the position of the head is not extracted, the control device 101 detects "leaving bed".

[0048] The control device 101 may determine that the action "getting up" has occurred if it detects that the position of the head extracted as described above is within the area where the bed 113 is located, and that the size of the head extracted as described above has changed from the size of a supine position to the size of a sitting position by using the first threshold Th1, or if it detects that the size of the head extracted as described above has changed from the size of a sitting position to the size of a supine position by using the first threshold Th1.

[0049] The control device 101 may determine that the behavior "getting out of bed" has occurred when the extracted head position moves from within the bed 113's location area to outside the bed 113's location area, and by applying a second threshold Th2 to the extracted head size, it detects that the head has changed from a certain size to the size of a standing posture.

[0050] The control device 101 may determine that the action "out of bed" has occurred when it detects that the extracted head position has moved from within the bed 113's location area to outside the bed 113's location area. The control device 101 may also determine that the action "out of bed" has occurred when it detects that the extracted head position has moved from within the bed 113's location area to outside the bed 113's location area to the door sensor.

[0051] As described above, in one specific example, the control device 101 of the sensor box 119 generates behavioral information for residents 111 and 121. In other monitoring systems 100, other elements (for example, a cloud server 150) besides the control device 101 may generate behavioral information for residents 111 and 121 using images from the rooms 110 and 120.

[0052] [Mobile device 220] The mobile terminal 220 includes a control device 221, a ROM 222, a RAM 223, a communication interface 224, a display 226, a storage device 228, and an input device 229. In some cases, the mobile terminals 161, 162, 163, and 164 are implemented as, for example, smartphones, tablet devices, smartwatches, or other wearable devices.

[0053] The control device 221 controls the mobile terminals 161, 162, 163, and 164. The control device 221 is comprised of, for example, at least one integrated circuit. The integrated circuit is comprised of, for example, at least one CPU, at least one ASIC, at least one FPGA, or a combination thereof.

[0054] An antenna (not shown) and other devices are connected to the communication interface 224. Mobile terminals 161, 162, 163, and 164 exchange data with external communication devices via the antenna and access point 140. External communication devices include, for example, a sensor box 119 and a management server 200.

[0055] The display 226 is implemented by, for example, an organic EL (Electro-Luminescence) display, a liquid crystal display, etc. The input device 229 is implemented by, for example, a touch sensor provided on the display 226. The touch sensor receives touch operations on the mobile terminals 161, 162, 163, and 164 and outputs a signal corresponding to the touch operation to the control device 221.

[0056] The storage device 228 can be implemented, for example, by flash memory, a hard disk or other fixed storage device, or a removable data recording medium.

[0057] In a given scenario, the control device 101 identifies getting into bed, getting up, and leaving bed, for example, as follows. The area in the target image where the bed 113 is located (the area where the bed 113 is located) is pre-stored in the ROM 102 as one of the various data. In addition, each threshold and the continuation judgment time are appropriately set from multiple samples and are pre-stored in the ROM 102 as one of the various data.

[0058] [Coming to bed] In determining whether a person has entered the bed, the control device 101 provisionally determines that a person has entered the bed if the previous state variable (a variable that stores the behavior determination result) was "out of bed," and the person region extracted from the target image acquired from the camera 105, for example by background subtraction, completely overlaps with the location area of ​​the bed 113 (i.e., the person region is completely within the location area of ​​the bed 113). If the duration of this complete overlap exceeds the bed entry continuation determination time, the control device 101 ultimately determines that a person has entered the bed and detects that a person has entered the bed. The control device 101 updates the state variable to "in bed." The bed entry continuation determination time is used as a threshold for determining whether a person has entered the bed, which was provisionally determined by the complete overlap between the extracted person region and the location area of ​​the bed 113, is actually in bed.

[0059] [Lying down] "Lying down" refers to a supine position in which the resident (person under monitoring) is lying on the bed 113. For example, the control device 101 detects "lying down" as information about the resident's behavior when the area occupied by the resident in the image is included in the area of ​​the bed 113 and the amount of movement of the resident is less than or equal to a predetermined amount. During the period in which "lying down" is detected, the control device 101 determines whether the resident is "sleeping" or "awake" as described above.

[0060] [Wake up] In determining whether a person has woken up, the control device 101 provisionally determines that the person has woken up if the previous state variable was "lying down" and the area of ​​the person extracted from the target image acquired from the camera 105 this time extends beyond the area where the bed 113 is located, and the area is greater than or equal to the wake-up determination threshold but less than the bed-getting-out determination threshold. The control device 101 finally determines that the person has woken up and detects the wake-up if the duration of the state in which the area is greater than or equal to the wake-up determination threshold but less than the bed-getting-out determination threshold exceeds the wake-up-continuation determination time. The control device 101 updates the state variable to "woke up". The wake-up determination threshold is used to determine whether or not the person has woken up based on the size of the area. The bed-getting-out determination threshold is used to determine whether or not the person has gotten out of bed based on the size of the area. The bed-getting-out determination threshold is set to a value greater than the wake-up determination threshold. The wake-up-continuation determination time is used as a threshold to finally determine that the person has woken up, based on the wake-up determination provisionally made by comparing the area with the wake-up determination threshold.

[0061] [Getting out of bed] In determining whether a person has left bed, the control device 101 provisionally determines that a person has left bed if the previous state variable was either "in bed" or "out of bed," and the area of ​​the person extracted from the target image acquired from the camera 105 this time extends beyond the area where the bed 113 is located and is greater than or equal to the bed-leaving determination threshold. The control device 101 finally determines that a person has left bed and detects that a person has left bed if the duration of the state in which the area is greater than or equal to the bed-leaving determination threshold exceeds the bed-leaving duration determination time. The control device 101 updates the state variable to "out of bed." The bed-leaving duration determination time is used as a threshold to finally determine that a person has left bed, which was provisionally determined by comparing the area with the bed-leaving determination threshold.

[0062] In this embodiment, for example, when a resident goes to sleep, their actions transition in the following order: getting out of bed → getting into bed → lying down → getting up → getting out of bed. During this transition of actions, the control device 101 detects the "sleep" and "wakefulness" described above during the period when lying down is detected from getting into bed until getting up is detected.

[0063] When the control device 101 detects a predetermined action from the resident's actions, it sends an event notification signal via the communication interface 104 to the management server 200, which includes event information representing the content of a predetermined event related to the resident. More specifically, the control device 101 sends an event notification signal via the communication interface 104 to the management server 200, which includes the sensor ID of the sensor box 119, event information representing the content of the event, and the target image captured when the action was detected.

[0064] In one embodiment, the event information includes one or more identifiers from among getting into bed, lying down, getting up, leaving bed, out of bed, and absence, and information about the time each was detected. Here, the control device 101 includes in the event information for the period during which lying down is detected identifiers representing the "sleep" and "wakeful" states detected during that period, and information about the time when the state was detected in association with the identifier. It may also include images taken at that time in association with the "sleep" and "wakeful" states. Such images included in the event information may include at least one of still images and videos. In one embodiment, the images included in the event information are distributed by the management server 200 to users (e.g., caregivers, administrators, doctors, or other staff) upon request and displayed on a display where these users can view the images. Such a display includes, for example, the display 226 of a mobile terminal 220.

[0065] [Overview of monitoring] Referring to Figure 3, we will now explain the monitoring system 100. Figure 3 is a schematic diagram of the monitoring system 100 using the sensor box 119.

[0066] The monitoring system 100 is used to monitor residents 111, 121 and other residents who are the subjects of monitoring (subject to surveillance). A sensor box 119 is installed on the ceiling of room 110. Sensor boxes 119 are similarly installed in the other rooms.

[0067] Range 31 represents the detection range by the sensor box 119. If the sensor box 119 has the aforementioned Doppler sensor, the Doppler sensor detects human behavior occurring within range 31. If the sensor box 119 has a camera as a sensor, the camera can capture images of at least within range 31.

[0068] The sensor box 119 is installed, for example, in nursing homes, medical facilities, or homes. In the example shown in Figure 3, the sensor box 119 is mounted on the ceiling and photographs the resident 111 and the bed 113 from above. The mounting location of the sensor box 119 is not limited to the ceiling; it may also be mounted on the side wall of the living room 110.

[0069] The monitoring system 100 detects dangers to the resident 111 based on a series of images (i.e., video) obtained from the camera 105. For example, detectable dangers include the resident 111 falling or the resident 111 being in a dangerous area (for example, a bed rail).

[0070] The monitoring system 100 notifies caregivers 141, 142, etc., of the event information detected regarding resident 111. As an example of notification method, the monitoring system 100 notifies caregivers 141, 142's mobile terminals 161, 162 of resident 111's event information. Upon receiving the notification, the mobile terminals 161, 162 notify caregivers 141, 142 with a message, voice, vibration, etc., representing the event information of the notification. This allows caregivers 141, 142 to understand resident 111's behavior.

[0071] Furthermore, the monitoring system 100 can also notify the mobile terminals 163, 164 of caregivers 143, 144 who are outside the facility via the wireless base station 15 of the event information.

[0072] Figure 3 shows an example where the monitoring system 100 has one sensor box 119, but in other scenarios, the monitoring system 100 may have multiple sensor boxes 119. Also, Figure 3 shows an example where the monitoring system 100 has multiple mobile terminals 161, 162, but in other scenarios, the monitoring system 100 can be implemented with just one mobile terminal.

[0073] [Computer system configuration] Referring to Figure 4, the configuration of a computer system 400, which is one embodiment of an information processing device, will be described. Figure 4 is a block diagram showing the hardware configuration of the computer system 400. The computer system 400 is an example of an information processing device that functions as a gateway server 130, a cloud server 150, a push server 160, or a management server 200.

[0074] The computer system 400 includes, as its main components, a CPU 1 for executing programs, a mouse 2 and a keyboard 3 for receiving input instructions from the user of the computer system 400, RAM 4 for volatilely storing data generated by the execution of programs by the CPU 1 or data input via the mouse 2 or keyboard 3, a hard disk 5 for non-volatilely storing data, an optical disc drive 6, a communication interface (I / F) 7, and a monitor 8. Each component is connected to the others by a data bus. A CD-ROM 9 or other optical disc is mounted in the optical disc drive 6.

[0075] Processing in the computer system 400 is realized by each piece of hardware and software executed by the CPU 1. Such software may be pre-stored on the hard disk 5. Alternatively, the software may be stored on a CD-ROM 9 or other recording medium and distributed as a computer program. Or, the software may be provided as a downloadable application program by an information provider connected to the so-called Internet. Such software is read from the recording medium by an optical disc drive 6 or other reading device, or downloaded via a communication interface 7, and then temporarily stored on the hard disk 5. The CPU 1 reads the software from the hard disk 5 and stores it in RAM 4 in the form of an executable program. The CPU 1 then executes the program.

[0076] The components of the computer system 400 shown in Figure 4 are common. Therefore, one of the essential parts of the technical concept relating to this disclosure is the software stored in the RAM 4, hard disk 5, CD-ROM 9, and other recording media, or software that can be downloaded via a network. The recording media may include non-temporary, computer-readable data recording media. Since the operation of each piece of hardware in the computer system 400 is well known, a detailed explanation will not be repeated.

[0077] Furthermore, the recording medium is not limited to CD-ROMs, FDs (Flexible Disks), hard disks, and SSDs (Solid State Drives), but may also include magnetic tapes, cassette tapes, optical discs (MO (Magnetic Optical Disc) / MD (Mini Disc) / DVD (Digital Versatile Disc)), IC (Integrated Circuit) cards (including memory cards), optical cards, mask ROMs, EPROMs (Electronically Programmable Read-Only Memory), EEPROMs (Electronically Erasable Programmable Read-Only Memory), flash ROMs, and other semiconductor memory media that permanently store programs.

[0078] The term "program" as used here includes not only programs that can be directly executed by the CPU, but also programs in source code format, compressed programs, encrypted programs, and so on.

[0079] Referring to Figure 5, an example of a configuration for realizing a device 600 that acquires sleep pattern stability will be described. Figure 5 is a block diagram showing the configuration of the functions of the device 600 according to this embodiment. The device 600 is realized by a well-known computer device (information processing device) equipped with communication functions and data processing functions. In this embodiment, the device 600 can be implemented, for example, in the computer system 400 or the mobile terminal 220 in Figure 4. The device 600 uses the given data to generate recommendations for care plans and rehabilitation programs tailored to each resident. In this embodiment, the recommendations include sleep indicators for each resident who is a subject, indicators representing the stability of sleep patterns, and indicators for evaluating cognitive function, and recommendations based on these.

[0080] The device 600 comprises a signal input unit 610, a storage unit 620, a data processing unit 630, and an output unit 640. The data processing unit 630 includes an index acquisition unit 631, a stability acquisition unit 632, a cognitive function evaluation unit 634, and a recommendation generation unit 636. The output unit 640 includes a recommendation storage unit 641 and a recommendation display unit 642. The index acquisition unit 631 includes an index calculation unit 650. The stability acquisition unit 632 includes a stability calculation unit 633.

[0081] The signal input unit 610 receives signals from an external source to the device 600. The signal input unit 610 is implemented by a LAN (Local Area Network) interface card, a WiFi (Wireless Fidelity) module, or other input interface device. The signals received by the signal input unit 610 include event communication signals containing the event information described above. The signal input unit 610 extracts event information from the received signals by performing analog-to-digital (AD) conversion or the like.

[0082] The storage unit 620 stores data and information input to the device 600, as well as data generated by the data processing unit 630. The storage unit 620 is implemented using RAM or other volatile recording media, or a hard disk, SSD or other non-volatile data recording media.

[0083] The data processing unit 630 uses the data and information provided to the device 600 to generate (obtain) recommendations tailored to each resident.

[0084] [Sleep index] More specifically, in the data processing unit 630, the index acquisition unit 631 acquires the sleep index of each resident from event information obtained by observing each resident. Acquiring the sleep index from event information may include calculating the sleep index using the event information.

[0085] The "sleep index" indicates a predetermined type of time calculated from the resident's event information. More specifically, this predetermined type of time includes the time spent "sleeping" and "waking" periods, as well as the time spent out of bed, within the period in which bed rest is detected during the day. The device 600 calculates the time spent "sleeping" and "waking" periods, as well as the time spent out of bed, for example, in minutes.

[0086] [An indicator representing the stability of sleep patterns] Furthermore, the stability acquisition unit 632 uses the sleep indicators acquired for each resident to acquire an index representing the stability of the resident's sleep pattern (hereinafter also referred to as the "stability index").

[0087] The "stability index" is obtained by the device 600 executing a predetermined calculation algorithm based on sleep indicators acquired for a particular resident. In this embodiment, the "stability index" represents the degree to which "sleep" time appears (is detected) regularly during a resident's sleep period, and the degree to which the distribution of "sleep" time is constant. The "stability index" is a non-negative value. For example, a smaller value of the "stability index" indicates that the resident's sleep pattern is stable, meaning that "sleep" time appears regularly to a higher degree. Conversely, a larger value of the "stability index" indicates that the resident's sleep pattern is unstable, meaning that there is variability, the appearance of "sleep" time is irregular, and the length of time is also irregular.

[0088] [Assessment of cognitive function] In the experiment, the inventor administered the MMSE (Mini Mental State Examination) to each of several subjects to evaluate their cognitive function, and also obtained the aforementioned "stability index" for each subject. It is known that a higher score on the MMSE indicates higher cognitive function, while a lower score indicates lower cognitive function. As a result of this experiment, the inventor found that there is a negative correlation between the "stability index" and the cognitive function evaluation value (score). More specifically, the inventor found that the higher the value of the "stability index," the lower the cognitive function evaluation value (score). This experimental result was found to be consistent with the medical evaluation that "people with unstable sleep are more prone to cognitive decline than people with stable sleep."

[0089] From these experiments, the inventors also found that, even without administering cognitive function tests such as the MMSE to the residents, the "stability index" obtained for the residents can be used as a significant indicator for evaluating the residents' cognitive function.

[0090] The cognitive function evaluation unit 634 evaluates the cognitive function of a resident based on the "stability index" value obtained for that resident. Specifically, the cognitive function evaluation unit 634 uses the learning model 635 that the device 600 has learned through machine learning. At this learning stage, the device 600 configures the learning model 635 as a model (regression model) that has learned the correlation between multiple input parameters, including the values ​​of the stability index 624 for each of multiple subjects, and a predetermined medical cognitive function evaluation scale that shows the evaluation results regarding the degree of cognitive function (degree of decline, etc.) for each of the multiple subjects. By obtaining the learning model, it is possible to obtain the correlation between the evaluation value of a person's (subject's) cognitive function and that person's "stability index". In this embodiment, for example, MMSE is used as such a cognitive function evaluation scale. Therefore, the learning model 635 is configured as a model that takes multiple parameters, including the value of the stability index 624, as input and outputs a value corresponding to a predetermined medical cognitive function evaluation scale. The input parameters of such a learning model 635 may include gender, age, etc.

[0091] Furthermore, the cognitive function assessment unit 634 may be configured to obtain a value corresponding to a predetermined medical cognitive function assessment scale that corresponds to the stability index 624, using a rule base that has been generated in advance based on correlation, regardless of the learning model.

[0092] The cognitive function assessment unit 634 outputs a value corresponding to a predetermined medical cognitive function assessment scale obtained using a learning model 635 or a rule-based system for the resident's stability index 624, as the cognitive function assessment result 625 of the resident.

[0093] The output unit 640, acting as a recommendation storage unit 641, outputs recommendations generated by the recommendation generation unit 636. For example, recommendations obtained for a particular resident (such as sleep indicators, stability indicators, and cognitive function assessments) are stored in the memory unit 620. The output unit 640 also acts as a recommendation display unit 642, outputting recommendations for a particular resident. For example, the recommendations are transferred to the mobile terminal 220 so that they are displayed on the display 226.

[0094] [Data structure] Referring to Figure 6, the data structure of the storage unit 620 of the device 600 will be described. Figure 6 is a conceptual diagram showing one mode of data storage in the storage unit 620.

[0095] As shown in Figure 6, the memory unit 620 stores, for each resident, a resident ID 621 that identifies the resident, event information 622, a sleep index 623 obtained from the event information 622, a stability index 624 obtained from the sleep index 623, and a cognitive function evaluation result 625 obtained from the stability index 624. The resident ID 621 is obtained, for example, by converting the ID of the sensor box 119 included in the corresponding event information 622 according to a predetermined rule.

[0096] In Figure 6, multiple event information 622 may be stored for a particular resident. In this case, the device 600 manages the multiple event information 622 in the memory unit 620 in a time series according to the time the information was acquired. When event information 622 is managed in a time series, multiple sleep indices 623, stability indices 624, and cognitive function evaluation results 625 are also acquired from the multiple event information 622. The device 600 also manages these acquired multiple sleep indices 623, multiple stability indices 624, and multiple cognitive function evaluation results 625 in a time series, similar to the event information 622.

[0097] Using this time-series managed data, the output unit 640 of the device 600 can output information representing the changes over time in the sleep index 623, the changes over time in the stability index 624, and the changes over time in the cognitive function evaluation results 625.

[0098] [Example of calculating sleep indicators and stability indicators] Referring to Figure 7, the event content 626 contained in event information 622 will be explained. Figure 7 is a diagram showing the event content 626 indicated by event information 622 for each day of a week for a certain resident. The event content is classified as "sleep" 630, "awake" 631, "out of bed" 634 ("out of bed" 632, "absence" 633) detected during a resident's day.

[0099] The device 600 uses the data classified in this way to extract the time for each classified item for each day, and calculates a sleep index 623 from the time for each extracted item.

[0100] The procedure for obtaining the stability index will be explained with reference to Figure 8. Figure 8 is a schematic diagram showing the procedure for obtaining the sleep stability of a resident. When obtaining the stability of a resident's nighttime sleep, the device 600 divides the time period 36 during which nighttime lying down is detected (for example, 3 hours and 45 minutes from 0:00 to 3:45 in Figure 8) into 15-minute units 37, and calculates the "sleep" time 38 (in minutes) for each unit 37. In Figure 8, for example, the device 600 calculates the "sleep" time 38 for each unit 37 within each day of a week, and calculates the standard deviation SD (SD) for each unit 37 for the week (i.e., 7 units) of "sleep" time 38. The device 600 calculates the mean as a statistic of the standard deviation SD for each unit 37, and sets the mean as the stability index 624.

[0101] In this way, the device 600 divides a predetermined length of time during the day, more preferably at night, during which lying down is detected (hereinafter also referred to as nighttime lying down time), into predetermined length periods of time (for example, 10-minute units), and calculates a "sleep duration" representing the length of "sleep" time included in each divided unit. For each day, the device 600 calculates the degree of variation (distribution) of the "sleep duration" within the day as a standard deviation of 40. For a predetermined specified period (for example, one week), the device 600 calculates the average of the standard deviations of 40 calculated for each day of the specified period, and sets the average value as a "stability index" 624 representing the degree of variation of the "sleep duration" during the specified period.

[0102] In Figure 8, time zone 36 is defined as nighttime bedtime, but time zone 36 is not limited to nighttime. Any portion of the 24-hour period during the day in which bedtime is detected between "going to bed" and "getting up" may be included, even if it includes midnight (12:00 AM). Furthermore, the length of time zone 36 is not limited to 3 hours and 45 minutes; it may be shorter or longer than this time. Also, the unit time 37 is not limited to 15 minutes; it may be 10 minutes, 30 minutes, 1 hour, etc. In addition, the specified period for calculating the standard deviation (SD) is one week, but it is not limited to one week; it may be one month or one year.

[0103] Furthermore, while the mean was set as the standard deviation (SD) statistic for the stability index 624, the statistic is not limited to the mean; for example, the median may also be used.

[0104] [Calculation and Application of Sleep Stability] The acquisition and application of sleep stability will be explained with reference to Figures 9 to 12. Figure 9 is a schematic diagram illustrating the acquisition and application of a stability index for a certain resident. Figures 10, 11, and 12 are flowcharts of an example of the process according to this embodiment.

[0105] For a certain resident 121, the control device 101 collects a Doppler signal from the Doppler sensor 106 (step S1 in Figure 9). The control device 101 collects the Doppler signal (step T1 in Figure 10), detects the duration of "sleep" and "wakefulness" from the collected Doppler signal, and transfers event information 622, which includes the detection results as event content 626, to the device 600. The device 600 stores the event information 622 from the control device 101 in the storage unit 620, and as an index calculation unit 650, accesses (searches) the event information 622 stored in the storage unit 620, calculates a sleep index 623 from the accessed event information 622 (step S2 in Figure 9, step T2 in Figure 10), and stores the sleep index 623 in the storage unit 620 (step T3). The device 600 obtains sleep indicators 623 by batch processing event information 622, which contains, for example, event details 626 for one day, once a day. The memory unit 620 stores sleep indicators 623 for multiple days for a particular resident.

[0106] The device 600, acting as a stability calculation unit 633, calculates a stability index using the sleep index 623 (step S3 in Figure 9). Specifically, the device 600 receives a user input to specify a period for calculating the stability index (step Q1 in Figure 11). The device 600 searches the memory unit 620 based on the specified period and obtains the sleep index 623 for each day corresponding to that period (step Q2). The device 600, acting as a stability acquisition unit 632, calculates a stability index using the sleep index 623 for each day (step Q3) and stores it in the memory unit 620 (step Q4).

[0107] The device 600, acting as a cognitive function evaluation unit 634, evaluates the cognitive function of the resident (step S4 in Figure 9). Specifically, the device 600 obtains a sleep stability index for a given resident by searching the memory unit 620 (step SR1 in Figure 12). The device 600 compares the value indicated by the stability index with a threshold, and based on the comparison result, obtains the cognitive function evaluation result 625 for the resident (step R2) and stores it in the memory unit 620 (step R3).

[0108] The device 600, as a recommendation generation unit 636, generates recommendations using the stability index 624. For example, the device 600 generates a recommendation that includes visualization data 18, such as a graph, for an object that visualizes the time-series changes in the value of the stability index 624 acquired over a predetermined period for a particular resident (step S5a). Alternatively, for example, the device 600 calculates the amount of change in the stability index 624 over a predetermined period retrospectively from the present (i.e., when the latest stability index 624 was acquired) and, if it determines that the amount of change exceeds a threshold, generates a message 165 recommending that the resident's sleep be monitored (step S5b). For example, the device 600 recommends that another system analyze the cognitive function evaluation results 625 for a particular resident (step S5c). Such other systems include, for example, a hospital system operated by a physician.

[0109] [Differentiation] The device 600 may acquire a "stability index" based on "wakefulness." Specifically, since the sleep period consists of "sleep" and "wakefulness," the device 600 may acquire a "stability index" for "sleep" by acquiring the degree to which "wakefulness" appears (is detected) regularly instead of "sleep." Alternatively, the device may detect the degree of "sleep" and "wakefulness" separately and acquire a "stability index" using both detected degrees.

[0110] The control device 101 acquired "sleep" and "wakefulness" from body movement, which is an example of biological information based on Doppler signals. However, instead of such body movement, biological information may be acquired from biological information measured by a biological information measuring device that includes a vital sensor 290. For example, it is known that body temperature and heart rate decrease when sleep is deep and increase when awake. "Sleep" and "wakefulness" may be detected based on such changes in biological information such as body temperature and heart rate. Alternatively, "sleep" and "wakefulness" may be detected by combining body temperature or pulse rate with body movement.

[0111] [Note] The embodiment described above includes the following technical concept. (Composition 1) A method performed by a computer to obtain an indicator representing the stability of sleep patterns, The aforementioned method, Step (T2) involves acquiring the subject's biometric information, Step (T2) of obtaining sleep indicators from the acquired biological information, The process includes a step (Q3) of obtaining the stability of the subject's sleep pattern, The aforementioned sleep index includes the first hour in which sleep of first depth (630) occurs and the second hour in which sleep of shallower depth than the first hour (631) occurs. The step of obtaining the stability of the aforementioned sleep pattern is: A method comprising the steps of obtaining the length (38) of at least one of the first or second hours that occurs during a first period of a predetermined length (e.g., 15 minutes in Figure 8) in which the subject is lying down during the day, and obtaining an index representing the stability of the subject's sleep pattern using the degree of variability (40) of the length of said first hour obtained for each day over multiple days (e.g., one week in Figure 8). (Configuration 2) The period from when the subject gets into bed until when they get up includes the period of lying down. The period of bed rest includes a plurality of the aforementioned first periods, The step of obtaining stability in the aforementioned sleep pattern further includes: For each of the aforementioned multiple first periods, the steps include obtaining the length of at least one of the first or second hours that occurs in the first period, and obtaining the degree of variation (40) of the length of that one hour obtained for each day of the multiple days, The method according to configuration 1, comprising the step of obtaining an index representing the stability of the subject's sleep pattern using the statistic (624) of the degree of variation obtained for each of the plurality of first periods. (Composition 3) The method according to configuration 2, wherein the statistic includes the average of the degree of variation obtained for each of the plurality of first periods. (Composition 4) The method according to any one of configurations 1 to 3, further comprising the step of evaluating the cognitive function of a subject from the indicator representing the stability of the sleep pattern obtained for the subject, based on the correlation between the evaluation value of the person's cognitive function and the indicator representing the stability of the person's sleep pattern. (Composition 5) The step of obtaining the aforementioned correlation is further provided, The step of obtaining the aforementioned correlation is: The method according to configuration 4, comprising the step of causing a learning model, which takes an index representing the stability of the sleep pattern as input and an evaluation value of the cognitive function as output, to learn the correlation. (Composition 6) The method according to any one of configurations 1 to 5, further comprising the step of generating an object for visualizing the time-series changes in the values ​​indicated by an index representing the stability of the subject's sleep pattern. (Composition 7) A program that causes a computer to perform one of the methods described in configuration 1 to 6. (Composition 8) Memory containing the program described in Configuration 7, An information processing device comprising a processor that executes the aforementioned program.

[0112] The embodiments disclosed herein should be considered in all respects to be illustrative and not restrictive. The scope of the present invention is indicated by the claims rather than by the foregoing description, and all modifications within the meaning and scope equivalent to the claims are intended to be included. [Explanation of symbols]

[0113] 2 Mouse, 3 Keyboard, 4,103,223 RAM, 5 Hard disk, 6 Optical disk drive, 7,104,224 Communication interface, 8 Monitor, 9,102,222 ROM, 11,130 Gateway server, 12,135 Switching device, 15 Wireless base station, 16 External network, 18 Visualization data, 31 Range, 36 Time zone, 37 Unit time, 38 Hours, 40 SD Standard Deviation, 100 System, 101,221 Control device, 105 Camera, 106 Doppler sensor, 107 Wireless communication device, 108,228 Storage device, 110,120 Living room, 111,121,ID621 Resident, 112 Furniture, 113 Bed, 114 Toilet, 115 Care call handset, 116 Toilet sensor, 117, ID sensor, 118 Door sensor, 119 Sensor box, 140 Access point, 141, 142, 143, 144 Caregiver, 150 Cloud server, 160 Push server, 161, 162, 163, 164, 220 Mobile terminal, 165 Message, 180 Facility, 200 Management server, 226 Display, 229 Input device, 241 Care call button, 290 Vital sensor, 400 Computer system, 600 Device, 610 Signal input unit, 620 Memory unit, 622 Event information, 623 Sleep index, 624 Stability index, 625 Evaluation result, 626 Event content, 630 Data processing unit, 631 Index acquisition unit, 632 Stability acquisition unit, 633 Stability calculation unit, 634 Cognitive function evaluation unit, 635 Learning model, 636 Recommendation generation unit, 640 Output unit, 641 Recommendation storage unit, 642 Recommendation display unit, 650 Indicator calculation unit.

Claims

1. A method performed by a computer to obtain an indicator representing the stability of sleep patterns, The aforementioned method, Steps to acquire the subject's biometric information, A step of obtaining sleep indicators from the acquired biological information, The process includes a step of obtaining the stability of the subject's sleep pattern, The aforementioned sleep index includes the first hour in which sleep of a first depth occurs and the second hour in which sleep lighter than the first depth occurs. The step of obtaining the stability of the aforementioned sleep pattern is: A method comprising the steps of obtaining the length of at least one of the first hour or the second hour that occurs during a first period of a predetermined length in which the subject is lying down during the day, and obtaining an index representing the stability of the subject's sleep pattern using the degree of variation in the length of the one of the hours obtained during the first period at the same time on each of multiple days.

2. The period from when the subject gets into bed until when they get up includes the period of lying down. The period of lying down includes a plurality of the first periods, The step of obtaining stability in the aforementioned sleep pattern further includes: For each of the aforementioned multiple first periods, the steps include obtaining the length of at least one of the first or second hours that occurs within the first period, and obtaining the degree of variation in the length of that one hour obtained within the first period at the same time on each of the multiple days, The method according to claim 1, further comprising the step of obtaining an index representing the stability of the subject's sleep pattern using a statistical measure of the degree of variation obtained for each of the plurality of first periods.

3. The method according to claim 2, wherein the statistic includes the average of the degree of variation obtained for each of the plurality of first periods.

4. The method according to claim 1 or 2, further comprising the step of evaluating the cognitive function of a subject from an index representing the stability of the sleep pattern obtained for the subject, based on the correlation between an evaluation value of the person's cognitive function and an index representing the stability of the person's sleep pattern.

5. The step of obtaining the aforementioned correlation is further provided, The step of obtaining the aforementioned correlation is: The method according to claim 4, further comprising the step of causing a learning model, which takes an index representing the stability of the sleep pattern as input and an evaluation value of the cognitive function as output, to learn the correlation.

6. The method according to claim 1 or 2, further comprising the step of generating an object for visualizing the time-series changes in the values ​​indicated by an index representing the stability of the subject's sleep pattern.

7. A program that causes a computer to perform the method according to claim 1 or 2.

8. A memory containing the program described in claim 7, An information processing device comprising a processor that executes the aforementioned program.

Images