JP7468350B2 - Condition monitoring device and control method for condition monitoring device - Google Patents

Description

The present disclosure relates to a condition monitoring device that monitors the safety of occupants.

Technologies for monitoring residents are known. For example, JP 2017-174012 A (Patent Document 1) proposes a monitoring system that uses IT (Information Technology) to monitor the condition of elderly people, etc. If a problem occurs with the subject, a caregiver, nurse, etc. can quickly provide assistance. An information processing device is disclosed that displays the subject's condition on a screen in real time and displays the subject's condition when an unusual event, i.e., an event, occurs.

Furthermore, Patent Publication No. 5682504 (Patent Document 2) discloses a method in which a monitoring device that collects a subject's biometric information and monitors the subject's safety irradiates the subject with microwaves, detects the subject's body movements and breathing from the Doppler-shifted reflected waves, and monitors the subject's safety from the number of body movements and breathing rates within a specified period of time.

JP 2017-174012 A Patent No. 5682504

On the other hand, the method for monitoring the safety of the subject mentioned above had the problem that it was not possible to accurately determine the subject's condition when the signal level of the subject's biometric information was low.

This disclosure has been made in consideration of the above-mentioned background, and the objective in one aspect is to provide a condition monitoring device and a condition monitoring method capable of determining the condition of a subject with high accuracy.

According to one embodiment, the condition monitoring device includes a detection unit that irradiates microwaves to the subject and detects reflected waves from the subject, an analysis unit that analyzes the reflected waves detected by the detection unit to obtain spectral data of the respiratory signal, and a judgment unit that judges the subject's state during sleep based on the spectral data of the respiratory signal.

Preferably, the judgment unit judges the state to be awake during sleep when the waveform line width of the spectral data of the respiratory signal is greater than a predetermined value, and judges the state to be restful during sleep when the waveform line width of the spectral data of the respiratory signal is equal to or less than the predetermined value.

Preferably, the spectral data of the respiratory signal has a peak value for each predetermined period. The determination unit normalizes the maximum value of the peak value for each predetermined period to a predetermined value, and determines that the subject is in an awake state during sleep when the waveform line width of the spectral data of the respiratory signal is greater than the predetermined value, and determines that the subject is in a restful state during sleep when the waveform line width of the spectral data of the respiratory signal is equal to or less than the predetermined value.

Preferably, the judgment unit generates power spectrum data of the respiratory signal, judges whether the power spectrum data is greater than or equal to a predetermined value, and judges that the subject is present if the power spectrum data is greater than or equal to the predetermined value, and judges that the subject is absent if the power spectrum data is less than the predetermined value.

Preferably, the spectral data of the respiratory signal is divided into a frequency domain showing a peak value and the other frequency domains, and the judgment unit judges the state to be awake during sleep if the ratio or difference between the power integrated value of the spectral data in the frequency domain showing the peak value and the power integrated value of the spectral data in the other frequency domains is equal to or greater than a predetermined value, and judges the state to be restful during sleep if the ratio or difference is less than the predetermined value.

According to one embodiment, the condition monitoring method includes the steps of irradiating a subject with microwaves and detecting reflected waves from the subject, analyzing the detected reflected waves to obtain spectral data of a respiratory signal, and determining the subject's sleep state based on the spectral data of the respiratory signal.

Preferably, the step of determining the subject's state during sleep determines the subject to be in an awake state during sleep when the waveform line width of the spectral data of the respiratory signal is greater than a predetermined value, and determines the subject to be in a restful state during sleep when the waveform line width of the spectral data of the respiratory signal is equal to or less than a predetermined value.

Preferably, in the step of determining the state of the subject during sleep, the spectral data of the respiratory signal has a peak value for each predetermined period. The maximum value of the peak value for each predetermined period is normalized to a predetermined value, and when the waveform line width of the spectral data of the respiratory signal is greater than the predetermined value, the subject is determined to be in an awake state during sleep, and when the waveform line width of the spectral data of the respiratory signal is equal to or less than the predetermined value, the subject is determined to be in a restful state during sleep.

Preferably, the spectral data of the respiratory signal is divided into a frequency domain showing a peak value and the other frequency domains. The step of determining the state of the subject during sleep includes determining the subject as being in an awake state during sleep if the ratio or difference between the power integrated value of the spectral data of the frequency domain showing the peak value and the power integrated value of the spectral data of the other frequency domains is equal to or greater than a predetermined value, and determining the subject as being in a restful state during sleep if the ratio or difference is less than the predetermined value.

In one aspect, it is possible to determine the condition of a subject with high accuracy.
The above and other objects, features, aspects and advantages of the present invention will become apparent from the following detailed description of the invention taken in conjunction with the accompanying drawings.

FIG. 1 is a diagram illustrating an example of the configuration of a monitoring system 100. FIG. 1 is a block diagram showing an outline of the configuration of a monitoring system 100. FIG. 3 is a block diagram showing the hardware configuration of a computer system 300 functioning as a cloud server 150. A diagram showing an example of a schematic device configuration of a monitoring system 100 using a sensor box 119. 11 is a diagram illustrating sensor data acquired by the sensor box 119 based on an embodiment when the subject is in a resting state during sleep. FIG. 11 is a diagram illustrating sensor data acquired by the sensor box 119 based on an embodiment when the subject is in a waking state during sleep. FIG. 11A and 11B are diagrams illustrating spectrum data of sensor data in a resting state during sleep based on an embodiment. 11A and 11B are diagrams illustrating spectrum data of sensor data in a wakeful state during sleep based on an embodiment. FIG. 1 is a diagram illustrating a method for determining a resting state during sleep based on an embodiment. 1A and 1B are diagrams illustrating a method for determining a wakefulness state during sleep based on an embodiment. FIG. 11 is a diagram illustrating power spectrum data based on the embodiment. 13A and 13B are diagrams illustrating fluctuations in the integrated power value other than near the peak value according to a modified example of the embodiment. FIG. 2 is a diagram for explaining determination of a resting state and an awake state during sleep.

Below, an embodiment of the technical concept of the present disclosure will be described with reference to the drawings. In the following description, identical parts are given the same symbols. Their names and functions are also the same. Therefore, detailed descriptions thereof will not be repeated.

[Technical Concept]
First, an outline of the technical concept disclosed in this specification will be described. In a certain aspect, a respiratory signal is measured as biological information of a subject such as a resident of a facility, and the daily condition of the subject can be accurately understood. The measurement is performed without the subject being aware that the measurement is being performed.

[Configuration of monitoring system (condition monitoring device)]
Fig. 1 is a diagram showing an example of the configuration of a monitoring system 100. The targets of monitoring are, for example, residents in each room provided in a room area 180 of a facility. In the monitoring system 100 of Fig. 1, rooms 110 and 120 are provided in the room area 180. The room 110 is assigned to a resident 111. The room 120 is assigned to a resident 121. In the example of Fig. 1, the number of rooms included in the monitoring system 100 is two, but the number is not limited to this.

In the monitoring system 100, sensor boxes 119 installed in each of the rooms 110 and 120, a management server 200 installed in the management center 130, and an access point 140 are connected via a network 190. The network 190 may include both an intranet and the Internet.

In the monitoring system 100, a mobile terminal 143 carried by a caregiver 141 and a mobile terminal 144 carried by a caregiver 142 can connect to a network 190 via an access point 140. Furthermore, the sensor box 119, the management server 200, and the access point 140 can communicate with a cloud server 150 via the network 190.

Each of the rooms 110, 120 includes as its furnishings a chest of drawers 112, a bed 113, and a toilet 114. A door sensor 118 is installed on the door of the room 110 to detect whether the door is open or closed. A toilet sensor 116 is installed on the door of the toilet 114 to detect whether the toilet 114 is open or closed. An odor sensor 117 is installed on the bed 113 to detect the odor of each resident 111, 121. In the rooms 110, 120, each of the residents 111, 121 can operate a care call handset 115.

The sensor box 119 has a built-in sensor for detecting the behavior of objects in the rooms 110 and 120. One example of a sensor is a Doppler sensor for detecting the movement of objects. Another example is a camera. The sensor box 119 may include both a Doppler sensor and a camera as sensors.

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.

[Sensor box 119]
The sensor box 119 includes a control device 101, a read only memory (ROM) 102, a random access memory (RAM) 103, a communication interface 104, a camera 105, a Doppler sensor 106, a wireless communication device 107, and a storage device 108.

The control device 101 controls the sensor box 119. The control device 101 is, for example, configured with at least one integrated circuit. The integrated circuit is, for example, configured with 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 of these.

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 the antenna. The external communication devices include, for example, the management server 200, mobile terminals 143 and 144 and other terminals, the access point 140, the cloud server 150, and other communication terminals.

In one implementation, the camera 105 is a near-infrared camera. The near-infrared camera includes an IR (Infrared) projector that projects near-infrared light. By using the near-infrared camera, an image showing the interior of the rooms 110 and 120 can be captured even at night. In another implementation, the camera 105 is a surveillance camera that receives only visible light. In still another implementation, a 3D sensor or a thermography camera may be used as the camera 105. The sensor box 119 and the camera 105 may be configured as an integrated unit or may be configured as separate units.

The Doppler sensor 106 is, for example, a microwave Doppler sensor that emits and receives radio waves to detect the behavior (movement) of objects in the rooms 110 and 120. This allows the biometric information of the residents 111 and 121 in the rooms 110 and 120 to be detected. In one example, the Doppler sensor 106 emits microwaves in the 24 GHz band toward the beds 113 in each room 110 and 120, and receives the reflected waves reflected by the residents 111 and 121. The reflected waves are Doppler shifted by the movements of the residents 111 and 121. The Doppler sensor 106 can detect the breathing state and heart rate of the residents 111 and 121 from the reflected waves.

The wireless communication device 107 receives signals from the care call handset 240, door sensor 118, toilet sensor 116, and odor sensor 117, and transmits the signals to the control device 101. For example, the care call handset 240 has a care call button 241. When the button is operated, the care call handset 240 transmits a signal indicating that the operation has been performed to the wireless communication device 107. The door sensor 118, toilet sensor 116, and odor sensor 117 transmit their respective detection results to the wireless communication device 107.

The storage device 108 is, for example, a recording medium such as a fixed storage device such as a flash memory or a hard disk, or an external storage device. The storage device 108 stores the programs executed by the control device 101 and various data used to execute the programs. The various data may include behavioral information of the residents 111, 121.

At least one of the above programs and data may be stored in a storage device other than storage device 108 (for example, a storage area of control device 101 (for example, cache memory, etc.), ROM 102, RAM 103, external device (for example, management server 200 or mobile terminals 143, 144, etc.)) as long as the storage device is accessible by control device 101.

[Mobile terminals 143, 144]
The mobile terminals 143 and 144 include 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 one aspect, the mobile terminals 143 and 144 are realized as, for example, a smartphone, a tablet terminal, a wristwatch-type terminal, or other wearable device.

The control device 221 controls the mobile terminals 143 and 144. The control device 221 is, for example, configured with at least one integrated circuit. The integrated circuit is, for example, configured with at least one CPU, at least one ASIC, at least one FPGA, or a combination thereof.

An antenna (not shown) and the like are connected to the communication interface 224. The mobile terminals 143 and 144 exchange data with external communication devices via the antenna and the access point 140. The external communication devices include, for example, the sensor box 119 and the management server 200.

The display 226 is realized, for example, by a liquid crystal display, an organic EL (Electro Luminescence) display, or the like. The input device 229 is realized, for example, by a touch sensor provided on the display 226. The touch sensor receives a touch operation on the mobile terminals 143, 144, and outputs a signal corresponding to the touch operation to the control device 221.

The storage device 228 may be realized, for example, by a flash memory, a hard disk or other fixed storage device, or a removable data recording medium.

[Management Server 200]
The management server 200 includes an analysis unit 202 and a determination unit 204 .

The analysis unit 202 and the determination unit 204 are realized by the CPU executing a program stored in the memory. The analysis unit 202 reads out the sensor data stored in the hard disk 5 of the cloud server 150 and obtains spectral data of the respiratory signal.

The judgment unit 204 judges the subject's condition, etc. based on the spectrum data of the respiratory signal.

[Cloud Server Configuration]
The configuration of cloud server 150 will be described with reference to Fig. 3. Fig. 3 is a block diagram showing the hardware configuration of a computer system 300 that functions as cloud server 150.

Computer system 300 includes, as its main components, a CPU 1 which executes programs, a mouse 2 and keyboard 3 which receive instructions input by the user of computer system 300, a RAM 4 which volatilely stores data generated by execution of the programs by CPU 1 or data input via mouse 2 or keyboard 3, a hard disk 5 which non-volatilely stores data, an optical disk drive 6, a communications interface (I/F) 7, and a monitor 8. The components are interconnected by a data bus. A CD-ROM 9 or other optical disk is loaded into optical disk drive 6.

Processing in computer system 300 is realized by each piece of hardware and software executed by CPU 1. Such software may be pre-stored on hard disk 5. The software may also be stored on CD-ROM 9 or other recording medium and distributed as a computer program. Alternatively, the software may be provided as a downloadable application program by an information provider connected to the Internet. Such software is read from the recording medium by optical disk drive 6 or other reading device, or downloaded via communication interface 7, and then temporarily stored on hard disk 5. The software is read from hard disk 5 by CPU 1 and stored in RAM 4 in the form of an executable program. CPU 1 executes the program.

Each of the components constituting computer system 300 shown in FIG. 3 is general. Therefore, one of the essential parts of the technical idea of the present disclosure can be said to be software stored in RAM 4, hard disk 5, CD-ROM 9 or other recording medium, or software that can be downloaded via a network. The recording medium may include a non-transitory computer-readable data recording medium. Note that the operation of each piece of hardware in computer system 300 is well known, so a detailed description will not be repeated.

Note that recording media are not limited to CD-ROMs, FDs (Flexible Disks), and hard disks, but may also include media that carry programs in a fixed manner, such as magnetic tapes, cassette tapes, optical disks (MOs (Magnetic Optical Discs)/MDs (Mini Discs)/DVDs (Digital Versatile Discs)), 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 memories.

The term "program" here refers not only to programs that can be executed directly by the CPU, but also to programs in source program format, compressed programs, encrypted programs, etc.

[Device configuration of monitoring system 100]
The monitoring using the monitoring system 100 will be described with reference to Fig. 4. Fig. 4 is a diagram showing an example of a schematic device configuration of the monitoring system 100 using a sensor box 119.

The monitoring system 100 is used to monitor occupants 111, 121 and other occupants who are the targets of monitoring (surveys). As shown in Figure 4, a sensor box 119 is attached to the ceiling of the living room 110. Similar sensor boxes 119 are attached to the other living rooms.

Range 410 represents the detection range of sensor box 119. If sensor box 119 has the aforementioned Doppler sensor, the Doppler sensor detects human behavior occurring within range 410. If sensor box 119 has a camera as a sensor, the camera captures images within range 410.

The sensor box 119 is installed, for example, in a nursing home, a medical facility, a home, etc. In the example of Fig. 4, the sensor box 119 is attached to the ceiling, and the resident 111 and the bed 113 are photographed from the ceiling. The location where the sensor box 119 is attached is not limited to the ceiling, and it may be attached to a side wall of the room 110.

The monitoring system 100 detects danger to the resident 111 based on a series of images (i.e., video) obtained from the camera 105. As an example, detectable dangers include the resident 111 falling over, or the resident 111 being in a dangerous location (e.g., a bed rail, etc.).

When the monitoring system 100 detects that the resident 111 is in danger, it notifies the caregivers 141, 143, etc. As an example of a notification method, the monitoring system 100 notifies the mobile terminals 143, 144 of the caregivers 141, 142 of the danger of the resident 111. When the mobile terminals 143, 144 receive the notification, they notify the caregivers 141, 142 of the danger of the resident 111 by a message, sound, vibration, etc. This allows the caregivers 141, 142 to immediately know that the resident 111 is in danger and to rush to the resident 111's side quickly.

Although Fig. 4 shows an example in which the monitoring system 100 includes one sensor box 119, the monitoring system 100 may include multiple sensor boxes 119. Also, Fig. 4 shows an example in which the monitoring system 100 includes multiple mobile terminals 143, 144, but the monitoring system 100 can also be realized with a single mobile terminal.

In this example, the communication interface 104 of the sensor box 119 transmits the sensor data acquired by the Doppler sensor 106 to the cloud server 150.

The cloud server 150 stores the data in a hard disk 5, for example.
The management server 200 reads out the sensor data stored in the hard disk 5 of the cloud server 150 and executes a predetermined process. In this example, the state of the subject is determined.

Specifically, it determines whether the subject is awake or at rest during sleep, and whether the subject is present or absent.

The management server 200 notifies the caregiver of the subject's condition as necessary.
[Sensor data]
FIG. 5 is a diagram illustrating sensor data acquired by sensor box 119 based on the embodiment when the subject is in a resting state during sleep.

As shown in Figure 5, the Doppler sensor detects reflected microwave waves. For example, when a subject is resting in bed while sleeping, there is little movement other than breathing. Therefore, reflected waves that correspond to breathing movements are detected as small amplitude signals at a constant cycle.

Figure 6 is a diagram illustrating sensor data acquired by the sensor box 119 based on an embodiment when the subject is in an awake state during sleep.

For example, when a subject is awake while sleeping in bed, movements other than breathing are large. Therefore, the reflected waves corresponding to movements other than breathing, such as turning over in bed, are large, and the subject's movements produce large amplitudes in the signal waveform.

Figure 7 is a diagram illustrating spectral data of sensor data when in a resting state during sleep based on an embodiment.

In Figure 7, the analysis unit 202 of the management server 200 reads out the sensor data of Figure 5 stored in the hard disk 5 of the cloud server 150 and obtains spectral data of the respiratory signal.

The horizontal axis represents the respiratory rate (breathing/min), and the vertical axis represents the signal strength.
When the patient is in a resting state during sleep, a substantially constant period is detected in accordance with the breathing motion. In this example, a case is shown in which a peak value of the sensor data is detected at 19 breaths/min.

Figure 8 is a diagram illustrating spectral data of sensor data when in an awake state during sleep based on an embodiment.

In Figure 8, the analysis unit 202 of the management server 200 reads out and analyzes the sensor data of Figure 6 stored in the hard disk 5 of the cloud server 150, and obtains spectral data of the respiratory signal.

The horizontal axis represents respiratory rate (breathing/min) and the vertical axis represents signal strength.
In the case of a wakeful state during sleep, multiple peak waveforms are detected in accordance with other movements in addition to breathing. The highest peak value corresponds to a breathing rate (breathing/min) of 13 breaths/min.

As shown in Figures 7 and 8, the signal strength differs between the resting state during sleep and the awake state. The signal strength is greater in the resting state during sleep than in the awake state. This is because the maximum value differs depending on the distance between the subject and the sensor box 119 and the direction of movement. Therefore, it may be difficult to determine the awake state because the signal strength in the awake state is smaller than that in the resting state during sleep.

In an embodiment, a process is performed to normalize the maximum value of the peak signal strength for each specified period to 1. This normalizes the maximum peak value to 1 during periods of different signal strength, making it easier to compare the waveform shapes in a resting state and an awake state.

Figure 9 is a diagram explaining a method for determining a restful state during sleep based on an embodiment. This is mainly processing in the determination unit 204.

As shown in FIG. 9, the vertical axis represents the state in which the maximum peak value of the signal strength is normalized to 1. Then, the waveform line width near the peak value of the spectrum data is detected, and it is determined whether the waveform line width is equal to or smaller than a predetermined value. When the waveform line width is narrower than the predetermined value, as in this example, it is possible to determine that the subject is in a restful state during sleep.

FIG. 10 is a diagram illustrating a method for determining a wakefulness state during sleep based on an embodiment.
10, the vertical axis indicates a state in which the maximum peak value of the signal strength is normalized to 1. Then, the waveform line width near the peak value of the spectrum data is detected, and it is determined whether the waveform line width is equal to or smaller than a predetermined value. If the waveform line width is wider than the predetermined value as in this example, it is possible to determine that the subject is in a wakeful state during sleep.

In this example, the case where the signal line width is detected at a position where the signal strength is 2.00E-01 has been described, but this is not a limitation and detection may be performed at other positions. Also, the predetermined value that serves as the threshold value may be changed depending on the position of the signal strength to be detected.

Therefore, it is possible to determine whether a person is in a restful or awake state during sleep by acquiring the spectral data and analyzing the waveform shape.

Furthermore, with this method, even if the signal level of the subject's biometric information is low, it is possible to accurately determine the subject's condition by comparing and judging the signal strength after normalizing its peak value to 1.

FIG. 11 is a diagram illustrating power spectrum data based on the embodiment.
In FIG. 11, the determining unit 204 of the management server 200 generates power spectrum data based on the spectrum data of the sensor data.

Specifically, it is the sum of the powers in a predetermined range including the peak value of the sensor data.
For example, in the case of Fig. 7, when a peak value of 19 times/min is detected as the spectrum data of the sensor data, the sum of the power in the range of four times before and after (15 to 23 times/min) is calculated as the predetermined range. In this case, for example, 5.8E+11 is calculated.

In the case of Figure 8, for example, when a peak value of 13 times/minute is detected as spectrum data of the sensor data, the sum of the power of the range of four times before and after (9 to 17 times/minute) is calculated as a predetermined range. In this case, for example, 4.4E+11 is calculated.

The power spectrum data makes it possible to confirm the presence/absence of the subject.

Specifically, the judgment unit 204 can set a threshold value of, for example, 1E+10, and judge power spectrum data greater than the threshold value to indicate the presence of the subject (presence) and judge power spectrum data below the threshold value to indicate the absence of the subject (absence).

In time periods when the power spectrum data is equal to or greater than the threshold value of 1E+10, the subject is present, and in other cases the subject is not present, so the data for that time period (absent) can be ignored.

(Modification)
In a variation of the embodiment, a different method for determining whether the patient is in a restful or awake state during sleep is described.

Specifically, the determination is made based on a comparison between the power of a specified range including the peak value of the spectral data of the sensor data and the power of an area outside the specified range.

As an example, for the spectrum data described in Figure 7, the power integrated value calculated near the peak value in a restful state during sleep (a range of 15 to 23 beats/min, 4 beats before and after) is 1.862.

Moreover, the total power integrated value (0 to 35 times/min) is calculated to be 1.956.
For power integrated values other than those near the peak value, the power integrated value near the peak value is subtracted from the total power integrated value.

The power integration value outside the peak value is 1.956 - 1.862 = 0.0094. In other words, there are almost no signals corresponding to movements other than breathing, and the breathing signal accounts for the majority.

Therefore, it can be seen that the majority of the total power integration value is occupied by the area near the peak value.

For the spectral data of the sensor data described in Figure 8, the power integrated value calculated near the peak value of the wakefulness state during sleep (a range of 9 to 17 times/min, 4 times before and after) is 4.382.

Moreover, the total integrated power value (0 to 35 times/min) is calculated to be 8.922.
For power integrated values other than those near the peak value, the power integrated value near the peak value is subtracted from the total power integrated value.

The power integrated value outside the peak value is 8.922 - 4.382 = 4.54. Therefore, about half of the total power integrated value is the area near the peak value, and about the other half is the other area. Therefore, it also contains many signals that correspond to movements other than breathing.

Figure 12 is a diagram illustrating the fluctuation of the power accumulation value other than near the peak value according to a modified example of the embodiment. The determination unit 204 generates data on the fluctuation of the power accumulation value according to the above method.

As shown in FIG. 12, a case where it varies with time is shown.
The dotted lines indicate the average value for every 10 minutes.

As an example, in this example, the judgment unit 204 sets the threshold to 1 and judges whether the person is in an awake state or a resting state during sleep based on whether the average value is the threshold ("1") or not.

Note that the sleeping state is judged if the subject is present in the room. Therefore, the judgment is made while the subject is present in the room, and no judgment is made if the subject is absent.

In FIG. 12, as an example, the cases where the person is present and absent are shown, and the sleeping state is judged when the person is present. This is mainly processing in the judgment unit 204.

FIG. 13 is a diagram for explaining the determination of the resting state and the awake state during sleep.
With reference to Fig. 13, it is determined whether the power integrated value in Fig. 12 is equal to or less than a threshold value ("1") If it is equal to or less than the threshold value ("1"), it is determined to be in a resting state, and if it exceeds the threshold value ("1"), it is determined to be in an awake state.

Based on the result of the judgment, it is possible to grasp the state of the subject during sleep. In other words, if the period of rest during sleep is long, it is possible to judge that the sleep state is good. For example, it is possible to judge whether the sleep state is good or not based on whether the rest state during sleep is secured for a predetermined period or more.

On the other hand, if the period of wakefulness during sleep is long, it can be determined that the sleep state is poor.

For example, it is possible to determine whether or not a person is in a poor sleep state based on whether or not a state of wakefulness during sleep continues for a predetermined period of time or longer.

This enables highly accurate analysis of the subject's sleep state.
In this example, a method has been described in which the power integrated value other than near the peak value is calculated for the spectral data of the sensor data to determine whether the user is in a restful state or an awake state during sleep. However, it is of course possible to adopt other methods.

Specifically, the ratio between the power integrated value near the peak value and the power integrated value other than near the peak value may be calculated. When the subject is in a restful state during sleep, the power integrated value other than near the peak value will be small, so the ratio will be 0. On the other hand, when the subject is in an awake state during sleep, the power integrated value other than near the peak value will be large, so the ratio will approach 1.

Therefore, by calculating the ratio between the power integrated value near the peak value and the power integrated value other than near the peak value, the resting state or awake state during sleep can be determined by comparing it with a predetermined threshold value.

The method according to the modified example of this embodiment is based on a comparison of the power in a specified range including the peak value of the spectral data with the power in an area outside the specified range, making it possible to grasp the subject's condition with high accuracy even when the signal level of the subject's biometric information is low.

In this example, the case where the management server 200 has an analysis unit 202 and a judgment unit 204 has been described, but this is not limited to the above, and it is of course also possible to provide the sensor box 119 with these functions to form a single status monitoring device.

The embodiments disclosed herein should be considered to be illustrative and not restrictive in all respects. The scope of the present invention is indicated by the claims, not by the above description, and is intended to include all modifications within the meaning and scope of the claims.

This technology can be applied to information collected in hospitals, nursing homes, care facilities and other facilities.

100 System, 101, 221 Control device, 106 Doppler sensor, 107 Wireless communication device, 108 Storage device, 109 Door, 110, 120 Room, 111, 121, 910, 920, 930, 950 Resident, 112 Chest of drawers, 113 Bed, 114 Toilet, 115 Care call handset, 116 Toilet sensor, 117 Sensor, 118 Door sensor, 119 Sensor box, 130 Management center, 140 Access point, 141, 142 Caregiver, 143, 144 Mobile terminal, 150 Cloud server, 190 Network, 200 Management server, 226 Display, 229 Input device, 241 Care call button, 290 Vital sensor, 300 Computer system.

Claims (4)

A detection unit that irradiates a subject with microwaves and detects reflected waves from the subject;
an analysis unit that analyzes the reflected wave detected by the detection unit to obtain spectral data of a respiratory signal;
a determination unit for determining a sleep state of the subject based on the spectral data of the respiratory signal,
The spectral data of the respiratory signal is divided into a frequency domain showing a peak value and a frequency domain other than the peak value,
The determination unit is
If the difference between the power integrated value of the spectrum data of the entire frequency domain and the power integrated value of the spectrum data of the frequency domain showing the peak value is less than a predetermined value, the state is determined to be a resting state during sleep;
The state monitoring device determines that the subject is in a wakeful state during sleep when a difference between a power integrated value of the spectral data of the entire frequency domain and a power integrated value of the spectral data of the frequency domain showing the peak value is equal to or greater than a predetermined value. A detection unit that irradiates a subject with microwaves and detects reflected waves from the subject;
an analysis unit that analyzes the reflected wave detected by the detection unit to obtain spectral data of a respiratory signal;
a determination unit for determining a sleep state of the subject based on the spectral data of the respiratory signal,
The spectral data of the respiratory signal is divided into a frequency domain showing a peak value and a frequency domain other than the peak value,
The determination unit is
When a ratio of a power integrated value of the spectrum data of the frequency domain showing the peak value to a power integrated value of the spectrum data of the other frequency domain does not exceed a predetermined threshold , the subject is determined to be in a resting state during sleep;
The state monitoring device determines that the state is a wakeful state during sleep when a ratio of a power integrated value of the spectral data of the frequency domain showing the peak value to a power integrated value of the spectral data of the other frequency domain exceeds the predetermined threshold value . A control method for a condition monitoring device including a sensor and a controller, comprising:
The sensor includes a step of irradiating a subject with microwaves and detecting a reflected wave reflected from the subject;
The controller analyzes the detected reflected waves to obtain spectral data of the respiratory signal;
and determining a sleep state of the subject based on the spectral data of the respiratory signal.
The spectral data of the respiratory signal is divided into a frequency domain showing a peak value and a frequency domain other than the peak value,
The step of determining a state of the subject during sleep includes:
determining that the subject is in a resting state during sleep when a difference between a power integrated value of the spectrum data of the entire frequency domain and a power integrated value of the spectrum data of the frequency domain showing the peak value is less than a predetermined value;
and determining that the state is awake when the difference between the power integrated value of the spectral data of the entire frequency domain and the power integrated value of the spectral data of the frequency domain showing the peak value is equal to or greater than a predetermined value. A control method for a condition monitoring device including a sensor and a controller, comprising:
The sensor includes a step of irradiating a subject with microwaves and detecting a reflected wave reflected from the subject;
The controller analyzes the detected reflected waves to obtain spectral data of the respiratory signal;
and determining a sleep state of the subject based on the spectral data of the respiratory signal.
The spectral data of the respiratory signal is divided into a frequency domain showing a peak value and a frequency domain other than the peak value,
The step of determining a state of the subject during sleep includes:
determining that the subject is in a resting state during sleep when a ratio of a power integrated value of the spectrum data of the frequency domain showing the peak value to a power integrated value of the spectrum data of the other frequency domain does not exceed a predetermined threshold value ;
and determining that the state is awake during sleep when a ratio of a power integrated value of the spectral data of the frequency domain showing the peak value to a power integrated value of the spectral data of the other frequency domain exceeds the predetermined threshold .

Images