WO2019031011A1 - SLEEP STATE DETECTION DEVICE AND ASSOCIATED METHOD, AND MONITORING SYSTEM FOR SUPERVISING PERSON - Google Patents

Abstract

The present invention provides a sleep state detection device and a method therefor, and a monitored person monitoring assist system, wherein the sleep state of a subject is detected using a sleep state detection unit. Then, presence or absence of a noise source that generates noise in the sleep state that is detected by the sleep state detection unit is detected, and the sleep state detection unit is controlled according to the detection result.

Description

SLEEP STATE DETECTING APPARATUS, METHOD THEREOF, AND MONITORING SUPPORT SYSTEM

The present invention relates to a sleep state detection device and a sleep state detection method for detecting a sleep state. And this invention relates to the to-be-monitored person monitoring assistance system using this sleep state detection apparatus.

In the industry such as medical care and nursing care, there is a demand for a technique for confirming whether or not a target person such as the medical care and nursing care is sleeping well. As a technique which detects such a sleep state, there exist a technique disclosed by patent document 1 or patent document 2, for example.

The sleep depth determination apparatus disclosed in the patent document 1 determines the sleep depth of the subject by using a sensory threshold that is the minimum stimulation intensity that can be perceived by the subject in the sleep state at a predetermined sleep depth. Sleep depth determining apparatus, which applies a first stimulus having a first stimulus intensity and a second stimulus having a second stimulus intensity higher than the first stimulus intensity to the subject The subject receives the first stimulus by the stimulus applying means, a perception detecting means for detecting whether or not the subject perceives the first stimulus and the second stimulus, and the perception detecting means. The sleep depth of the subject corresponds to a sensory threshold between the first stimulation intensity and the second stimulation intensity when it is detected that it has not been perceived and that the second stimulation has been perceived. A sleep depth determination unit that determines that the sleep depth is . The stimulus applying means is a part for applying a physical stimulus to a subject, and there is a speaker for applying an auditory stimulus by sound, for example, and the stimulus intensity is changed by adjusting the sound pressure (patent document Paragraph [0023] of 1).

The sleep state management device disclosed in Patent Document 2 is a sleep state management device that manages the sleep state of the subject by the body movement of the subject, and the movement of the bedding in which the subject is sleeping And a body movement determination unit that determines the presence or absence of body movement of the subject using the detection signal from the sensor unit, the body movement determination unit using the detection signal The first period in which the period with body movement determined using body movement absence period determined as body movement absence or the body movement using the detection signal periodically occurs, and the body movement presence period continues for a predetermined time or more If at least one of the second period and the second period is present, the determination is corrected as at least one of the body movement period and the second period in the first period as a no movement period.

The sleep depth determination device disclosed in Patent Document 1 is an active type that provides stimulation to the subject, and thus there is a risk of inhibiting sleep of the subject person, but the sleep state management device disclosed in Patent Document 2 Since the passive type is a passive type that detects the movement of the bedding in which the subject is sleeping, the possibility of inhibiting the subject's sleep can be reduced, which is superior to the sleep depth determination device disclosed in Patent Document 1 in this respect. ing. However, the passive sensor may also detect a signal originating from something other than the subject (the subject) and may make an erroneous determination.

JP, 2010-200956, A JP, 2013-198654, A

The present invention is an invention made in view of the above-mentioned circumstances, and an object thereof is a sleep state detection device and a sleep state detection method capable of reducing erroneous determination, and a person to be monitored using this sleep state detection device It is providing a surveillance support system.

In order to realize the above-described object, a sleep state detection device, a sleep state detection method, and a person-to-be-monitored support system reflecting one aspect of the present invention detect a sleep state of a subject by a sleep state detection unit. Here, the presence or absence of a noise source that generates noise with respect to the sleep state detected by the sleep state detection unit is detected, and the sleep state detection unit is controlled according to the detection result.

The advantages and features provided by one or more embodiments of the invention will be better understood from the detailed description given below and the accompanying drawings. These detailed descriptions and the accompanying drawings are given by way of example only and are not intended as a definition of the limits of the present invention.

BRIEF DESCRIPTION OF THE DRAWINGS It is a figure which shows the structure of the to-be-monitored person monitoring assistance system in embodiment. It is a figure which shows the structure of the sensor apparatus in which the sleep state detection apparatus of embodiment was integrated in the said monitoring object monitoring assistance system. It is a flowchart which shows operation | movement of the said sensor apparatus in a service mode. It is a flowchart which shows operation | movement of the said sensor apparatus in the sleep state determination processing shown in FIG. It is a flowchart which shows operation | movement of the said sensor apparatus in the fall determination process shown in FIG. It is a flowchart which shows operation | movement of the said sensor apparatus in the fall determination process shown in FIG. It is a flowchart which shows operation | movement of the said sensor apparatus in the entering determination process shown in FIG. It is a flowchart which shows operation | movement of the said sensor apparatus in the bed leaving determination processing shown in FIG. It is a flowchart which shows operation | movement of the said sensor apparatus in the micro body movement abnormality determination processing shown in FIG. It is a figure which shows an example of the main screen displayed on the said terminal device. It is a figure which shows an example of the 1st setting screen displayed on the said terminal device. It is a figure which shows an example of the 2nd setting screen displayed on the said terminal device. It is a figure which shows an example of the monitoring information screen displayed on the said terminal device. It is a figure which shows another example of the monitoring information screen displayed on the said terminal device. It is a figure which shows another example of the monitoring information screen displayed on the said terminal device.

Hereinafter, an embodiment according to the present invention will be described based on the drawings. However, the scope of the invention is not limited to the disclosed embodiments. In addition, the structure which attached | subjected the same code | symbol in each figure shows that it is the same structure, and abbreviate | omits the description suitably. In the present specification, suffixes are generally indicated by reference numerals without suffixes, and individual configurations are indicated by subscripts.

The monitored person monitoring support system in the embodiment is provided corresponding to the target person, and a sensor device for determining the sleep state of the target person, and communicably connected to the sensor device, manages the sleep state received from the sensor device A central processing unit, and a terminal device communicably connected to the central processing unit and receiving and displaying the sleep state through the central processing unit, the monitored person being the person to be monitored This is a monitored person monitoring support system for supporting the monitoring of This sensor device includes the sleep state detection device in the present embodiment. The sleep state detection apparatus according to this embodiment includes a sleep state detection unit that detects a sleep state of a subject, and a noise source detection that detects the presence or absence of a noise source that generates noise with respect to the sleep state detected by the sleep state detection unit. A processing control unit that controls the sleep state detection unit according to the detection result of the noise source detection unit. Such a sleep state detection device controls the sleep state detection unit according to the detection result of the noise source detection unit, so that erroneous determination can be further reduced. And in this embodiment, from a viewpoint of monitoring a to-be-monitored person (target person) more appropriately, the said sensor apparatus is further. The predetermined action in the person to be monitored (target person) is detected, the central processing unit manages the detection result for the predetermined action received from the sensor device, and the terminal device is connected via the central processing unit To receive and display the detection result. The terminal device may be one type of device, but in the present embodiment, the terminal device is two types of devices: a fixed terminal device and a portable terminal device. The main difference between the fixed terminal device and the mobile terminal device is that while the fixed terminal device is operated in a fixed manner, the mobile terminal device is operated by being carried by a supervisor (user) such as a nurse or a caregiver, for example. These fixed terminal devices and mobile terminal devices are substantially the same.

FIG. 1 is a diagram showing a configuration of a monitored person monitoring support system in the embodiment. FIG. 2 is a diagram showing a configuration of a sensor device in which the sleep state detection device of the embodiment is incorporated in the monitored person monitoring support system.

More specifically, for example, as shown in FIG. 1, the monitored person monitoring support system MS includes one or more sensor devices SU (SU-1 to SU-4), a management server device SV, and a fixed terminal. A device SP, one or more portable terminal devices TA (TA-1 and TA-2), and a private branch exchange (PBX) CX are provided in a wired or wireless manner and in a LAN (Local Area Network). Etc. communicably connected via a network (network, communication line) NW. The network NW may be provided with relays such as repeaters, bridges and routers for relaying communication signals. In the example shown in FIG. 1, the plurality of sensor devices SU-1 to SU-4, the management server SV, the fixed terminal SP, the plurality of portable terminals TA-1 and TA-2, and the private branch exchange CX are L2 switches. Are connected communicably to each other by a wired / wireless mixed LAN (for example, a LAN according to the IEEE 802.11 standard) NW including the line concentrators (hub, HUB) LS and the access point AP. More specifically, the plurality of sensor devices SU-1 to SU-4, the management server SV, the fixed terminal SP, and the private branch exchange CX are connected to the concentrator LS, and the plurality of mobile terminals TA-1 and TA-2 are connected. Are connected to the concentrator LS via the access point AP. Then, the network NW constructs a so-called intranet by using an internet protocol group such as a transmission control protocol (TCP) and an internet protocol (IP).

The private branch exchange (line switching unit) CX is connected to the network NW, controls extension telephones such as call origination, call reception, and call between the mobile terminal devices TA, and carries out extension telephone calls between the mobile terminal devices TA, For example, it is connected to an outside telephone TL such as a fixed telephone or a mobile telephone through a public telephone network PN such as a fixed telephone network or a mobile telephone network, for example, to make, receive, and make calls between the outside telephone TL and the mobile terminal device TA. , Etc. to control the outside line telephone to carry out the outside line telephone between the outside line telephone TL and the portable terminal device TA. The private branch exchange CX is, for example, a digital exchange, an IP-PBX (Internet Protocol Private Branch eXchange), or the like.

The monitored person monitoring support system MS is disposed at an appropriate place according to the monitored person (targeted person) Ob. The monitored person (watching target person) Ob is, for example, a person who needs nursing due to illness or injury, a person who needs care due to a decrease in physical ability or the like, or a single person living alone. In particular, from the viewpoint of enabling early detection and coping, the person to be monitored Ob is a person who needs the detection when a predetermined adverse event such as an abnormal condition occurs in the person. preferable. For this reason, the person-to-be-monitored monitoring support system MS is suitably disposed in buildings such as hospitals, welfare facilities for the elderly and dwelling units according to the type of the person to be monitored Ob. In the example illustrated in FIG. 1, the monitored person monitoring support system MS is disposed in a building of a care facility provided with a plurality of living rooms RM in which a plurality of monitored persons Ob reside, and a plurality of rooms such as a nurse station. .

The sensor device SU has a communication function and the like for communicating with other devices SV, SP, and TA via the network NW, detects a predetermined event related to the monitored person Ob, and detects the detected event as the management server device SV. To the terminal apparatus SP and TA, and generates an image including a moving image and distributes the moving image to the terminal apparatus SP and TA. The predetermined event (event) preferably includes an event that requires a response. In the present embodiment, the predetermined event includes a sleep state in the monitored person Ob, a predetermined action set in the monitored person Ob, and a nurse call. Such a sensor device SU includes, for example, as shown in FIG. 2, a sensor unit 11, a sensor side sound input / output unit (SU sound input / output unit) 12, a nurse call reception operation unit 13, and a sensor side control process. A unit (SU control processing unit) 14, a sensor side communication interface unit (SU communication IF unit) 15, and a sensor side storage unit (SU storage unit) 16 are provided.

The sensor unit 11 is connected to the SU control processing unit 14, and is a device that measures predetermined amounts set in advance in the monitored person Ob under the control of the SU control processing unit 14. In the present embodiment, the sensor unit 11 is provided with a first sensor that measures a subject in order to determine the sleep state of the monitored person Ob, and in order to determine the predetermined action in the monitored person Ob And a second sensor for measuring the person.

In the present embodiment, since the first sensor determines the sleep state of the monitored person Ob based on the respiratory state, any kind of device capable of measuring the respiration of the monitored person Ob as one of the predetermined amounts. It is good. The first sensor may be, for example, a pulsimeter or the like attached to a wrist or the like to measure a pulse, but in the present embodiment, since the respiration can be measured without contact with the monitored person Ob, the Doppler sensor 112 is used. It comprises and is constituted.

The predetermined action is, for example, in the present embodiment, an in-bed in which the monitored person Ob enters the bedding BD, an out-of-bed in which the monitored person Ob leaves the bedding BD, and a falling in which the monitored person Ob falls from the bedding BD. It includes a fall where the monitored person Ob falls outside the bedding BD, and a micromotion abnormality which is an abnormality of micromotion due to the breathing of the monitored person. The second sensor may be any device capable of determining such predetermined behavior. In the present embodiment, the predetermined behavior is divided into a first group including bed entry, bed leaving, falling and falling, and a second group including body movement abnormality, and the second sensor is the first group. A first sub-sensor for detecting a first action (in this embodiment, entering, leaving, falling and falling in the present embodiment) and a second action (in the present embodiment, micro-motion abnormality) belonging to the second group And a second sub-sensor for The first sub-sensor may be, for example, a thermographic device capable of extracting a human region from a temperature distribution, or a distance image sensor capable of extracting a human region from a distance distribution, but in this embodiment, the first sub-sensor is based on an image. Since the first action belonging to one group is determined, the camera 111 is configured to generate an image as one of the predetermined amounts. In the present embodiment, since the second sub-sensor determines the second action belonging to the second group based on the breathing state, a device capable of measuring the respiration of the person to be monitored Ob as one of the predetermined amounts. For example, the Doppler sensor 112 is comprised. That is, in the present embodiment, the Doppler sensor 112 is shared by the first sensor and the second sub sensor.

As described above, in the present embodiment, the sensor unit 11 includes the camera 111 and the Doppler sensor 112.

The camera 111 is a device that is connected to the SU control processing unit 14 and generates an image (image data) under the control of the SU control processing unit 14. The images include still images (still image data) and moving images (moving image data). The camera 111 is arranged to be able to monitor the space where the person to be monitored Ob is planning to be located (location space; room RM in the arrangement location in the example shown in FIG. 1) An image (image data) obtained by imaging and looking over the imaging target is generated, and an image (target image) of the imaging target is output to the SU control processing unit 14. Preferably, the camera 111 is scheduled to locate the head of the subject Ob in the bedding (for example, a bed or the like) BD on which the subject Ob is lying, since it is highly probable that the entire subject Ob can be imaged. It arrange | positions so that an imaging target can be imaged from the just overhead of the head preset position (usually the arrangement | positioning position of a pillow) which is preset. The sensor unit SU uses this camera 111 to obtain an image of the person to be monitored Ob, which is taken from above the person to be monitored Ob, preferably an image of the person to be monitored Ob, which is taken from directly above the planned head position.

Such a camera 111 may be a device that generates an image of visible light, but in the present embodiment, it is a digital infrared camera that generates an infrared image so as to be able to monitor the monitored person Ob even in a relatively dark state. is there. Such a digital infrared camera 111 is, for example, in the present embodiment, an imaging optical system for forming an infrared optical image of an imaging object on a predetermined imaging surface, and matching the light receiving surface with the imaging surface. And an image sensor that converts an infrared optical image of the imaging target into an electrical signal, and an image that is data representing an infrared image of the imaging target by performing image processing on an output of the image sensor An image processing unit that generates data is configured. In the present embodiment, the imaging optical system of the camera 111 is preferably a wide-angle optical system (a so-called wide-angle lens (including a fisheye lens)) having an angle of view capable of imaging the entire room RM provided.

The Doppler sensor 112 is connected to the SU control processing unit 14, and is a device that measures the movement of the body surface of the chest associated with breathing in the monitored person Ob according to the control of the SU control processing unit 14. The Doppler sensor 112 is a body movement sensor that transmits a transmission wave, receives a reflection wave of the transmission wave reflected by an object, and outputs a Doppler signal of a Doppler frequency component based on the transmission wave and the reflection wave. . When the object is moving, the frequency of the reflected wave is shifted in proportion to the moving velocity of the object by the so-called Doppler effect, so the difference between the frequency of the transmission wave and the frequency of the reflected wave (Doppler frequency component) It occurs. The Doppler sensor 112 generates a signal of this Doppler frequency component as a Doppler signal at a predetermined sampling rate, and outputs the signal to the SU control processing unit 14. When the SU control processing unit 14 receives a Doppler signal from the Doppler sensor 112, the SU control processing unit 14 stores the received Doppler signal in the SU storage unit 16 in time series. The transmission wave may be an ultrasonic wave, a microwave or the like, but in the present embodiment it is a microwave. The microwave can be transmitted through the clothes and reflected by the body surface of the monitored person Ob, so that the movement of the body surface can be detected even if the monitored person Ob wears clothes, which is preferable.

The SU sound input / output unit 12 is a circuit connected to the SU control processing unit 14 for acquiring an external sound and inputting it to the sensor unit SU, and an electric signal representing the sound according to the control of the SU control processing unit 14 It is a circuit for generating and outputting a sound according to. The SU sound input / output unit 12 is configured to include, for example, a microphone that converts acoustic vibration of sound into an electrical signal, and a speaker that converts electrical signal of sound into acoustic vibration of sound. The SU sound input / output unit 12 outputs an electrical signal representing an external sound to the SU control processing unit 14, and converts the electrical signal input from the SU control processing unit 14 into acoustic vibration of sound and outputs the acoustic vibration.

The nurse call reception operation unit 13 is connected to the SU control processing unit 14 and is a switch circuit such as a push button type switch for inputting a nurse call to the sensor device SU. The nurse call reception operation unit 13 may be connected to the SU control processing unit 14 by wire, or may be connected to the SU control processing unit 14 by short distance wireless communication such as Bluetooth (registered trademark) standard, for example.

The SU communication IF unit 15 is a communication circuit that is connected to the SU control processing unit 14 and performs communication according to the control of the SU control processing unit 14. The SU communication IF unit 15 generates the communication signal containing the data to be transferred, which is input from the SU control processing unit 14, in accordance with the communication protocol used in the network NW of the person-to-be-monitored monitoring support system MS The communication signal is transmitted to the other devices SV, SP, TA via the network NW. The SU communication IF unit 15 receives communication signals from other devices SV, SP, and TA via the network NW, extracts data from the received communication signals, and the SU control processing unit 14 can process the extracted data. The data is converted into data of the following format and output to the SU control processing unit 14. The SU communication IF unit 15 includes, for example, a communication interface circuit conforming to the IEEE 802.11 standard or the like.

The SU storage unit 16 is a circuit which is connected to the SU control processing unit 14 and stores various predetermined programs and various predetermined data according to the control of the SU control processing unit 14. The various predetermined programs include, for example, the SU control program for controlling the respective units 11 to 13, 15, and 16 of the sensor unit SU according to the functions of the respective units, and the target person based on the output of the sensor unit 11. Based on the output of the sensor unit 11, the presence or absence of a noise source that generates noise for the sleep state obtained by the sleep state processing program is detected based on the output of the sleep state processing program for obtaining the sleep state of The sleep according to the detection result of an action detection processing program (noise source determination program) that determines a predetermined action in the monitored person Ob and notifies the management server device SV, and the noise source determination program (action detection processing program) The process control program that controls the state processing program, and the nurse call reception operation unit 13 When it is attached, the management server SV is notified of that, and by using the SU sound input / output unit 12 or the like, a nurse call processing program for making a voice call with the terminal SP or TA, or generation by the camera 111 It includes a control processing program such as a streaming processing program for distributing the moving image to the terminal apparatus SP that has requested the moving image and streaming it to the TA. In the various predetermined data, each program such as a sensor device identifier (sensor ID) which is an identifier for identifying and identifying the sensor device SU of its own device, and a communication address of the management server device SV is executed. It contains the necessary data etc. above. The SU storage unit 16 includes, for example, a ROM (Read Only Memory), which is a non-volatile memory element, and an Electrically Erasable Programmable Read Only Memory (EEPROM), which is a rewritable non-volatile memory element. The SU storage unit 16 includes, for example, a random access memory (RAM) serving as a working memory of a so-called SU control processing unit 14 that stores data and the like generated during execution of the predetermined program.

The SU control processing unit 14 controls each of the units 11 to 13, 15, and 16 of the sensor unit SU according to the function of each of the units, detects a predetermined event related to the monitored person Ob, and detects the detected event. It is a circuit for notifying the management server device SV, making a voice call with the terminal devices SP and TA, and generating an image including a moving image and distributing the moving image to the terminal devices SP and TA. The SU control processing unit 14 includes, for example, a central processing unit (CPU) and peripheral circuits thereof. The SU control processing unit 14 executes the control processing program to execute a sensor-side control unit (SU control unit) 141, a sleep state processing unit 142, an action detection processing unit (noise source determination unit) 143, and a processing control unit. And 144, a nurse call processor 145 and a streaming processor 146 are functionally provided.

The SU control unit 141 controls the respective units 11 to 13, 15, and 16 of the sensor unit SU according to the functions of the respective units, and controls the entire control of the sensor unit SU.

The sleep state processing unit 142 determines the sleep state of the person to be monitored Ob based on the output of the sensor unit 11, that is, the first measurement result of the first sensor, and notifies the management server device SV of the sleep state. More specifically, based on the first measurement result of the first sensor, the sleep state processing unit 142 obtains, as the sleep state, a sleep degree that indicates the degree of the depth of the sleep of the person to be monitored Ob. In the present embodiment, the sleep state processing unit 142 obtains the sleep state based on the Doppler signal of the Doppler sensor 112 which is an example of the first sensor at predetermined time intervals set in advance. More specifically, the sleep state processing unit 142 performs, for example, fast Fourier transform (FFT) on the Doppler signal measured within a predetermined time (for example, one minute or two minutes) from the measurement time point to the past, and From the obtained spectrum, the average value of the amplitude in the frequency band corresponding to the general respiratory frequency is determined, and the determined average value is compared with the threshold for determining the sleep level (sleep level division threshold). The degree of sleep is temporarily determined as the sleep state, and the temporarily determined degree of sleep is determined as the final degree of sleep when the temporarily determined degree of sleep continues for a preset continuation determination time. Then, the sleep state processing unit 142 updates the state variable with the finally determined sleep degree. The state variable is a variable that stores the sleep degree obtained by the sleep state processing unit 142 and the predetermined action obtained by the action detection processing unit 143 described later. The sleep level classification threshold is appropriately set using, for example, a plurality of samples. In the present embodiment, since the sleep level is a low sleep level where sleep is relatively shallow and a high sleep level where sleep is relatively deep during awakening, the sleep level classification threshold is a low sleep level during these awakenings. In order to divide it into three stages of degree and high sleep degree, two first and second sleep degree division thresholds are included. Note that the sleep level classification threshold may be a plurality of three or more in order to further divide into multiple stages. The first sleep level classification threshold for distinguishing between awakening and low sleep degree is set to a value larger than the second sleep level classification threshold for distinguishing low sleep degree and high sleep degree (first sleep level classification threshold> Second sleep level classification threshold).

As described above, when the sleep state (the sleep level in the present embodiment) is obtained, the sleep state processing unit 142 stores event information (event information) representing the contents of a predetermined event (event) related to the monitored person Ob. The SU communication IF unit 15 notifies the management server SV of a communication signal (first event notification communication signal) for notifying the event. More specifically, the sleep state processing unit 142 transmits, via the SU communication IF unit 15, the first event notification communication signal containing the sensor ID of its own device and the event information representing the contents of the event via the management server SV Send to In the present embodiment, the event information is one or more of sleep level (awakening, low sleep level, high sleep level), bed entry, bed leaving, falling, falling, body movement abnormality and nurse call (NC). Here, the sleep state processing unit 142 stores the obtained sleep degree (during awakening, low sleep degree, high sleep degree) in the first event notification communication signal as the event information. When the sleep state processing unit 142 determines the degree of sleep, the sleep state processing unit 142 may cause the camera 111 to generate an image, and the image may be further contained in the first event notification communication signal. The image may be at least one of a still image and a moving image.

The sleep state processing unit 142 may further obtain the reliability indicating the degree of reliability of the sleep degree and notify the management server SV of the reliability. In this case, for example, the sleep state processing unit 142 obtains the duration of the obtained sleep degree, and compares the duration of the obtained sleep degree with a threshold (reliability classification threshold) for determining the reliability. To determine the degree of confidence. For example, the reliability classification threshold is appropriately set to one or more using a plurality of samples. For example, the reliability classification threshold may be a single value for discriminating whether the reliability is relatively high or the reliability is relatively low, or, for example, the reliability may be trusted. In order to divide into three stages of relatively high reliability, medium reliability with relatively moderate reliability, and low reliability with relatively low reliability, with all two values You may be there.

The action detection processing unit (noise source determination unit) 143 detects the presence or absence of a noise source that generates noise for the sleep state obtained by the sleep state processing unit 142 based on the output of the sensor unit 11. Based on the predetermined action in the person to be monitored Ob is determined and notified to the management server SV.

More specifically, in the present embodiment, for example, in the present embodiment, the noise source is a person other than the target person (monitored person) Ob, an animal other than a person, a television screen, a curtain and a string The presence or absence of a noise source includes at least one of a string extending from the lighting device for turning on and off the provided lighting device, and whether there is such a noise source in the room RM of the person to be monitored Ob The noise source determination unit (action detection processing unit) 143 detects the presence or absence of a noise source (noise source determination) based on the image (target image) generated by the camera 111 of the sensor unit 11. To determine the presence or absence of a noise source. More specifically, the noise source determination unit 143 extracts a moving body area from the target image generated by the camera of the sensor unit 11 by, for example, a background subtraction method, and when the extracted moving body area is one, the noise source If there is more than one moving body area extracted, it is determined that there is a noise source, and the detection result is notified (outputted) to the processing control unit 144. In the present embodiment, one body movement area extracted from the target image is regarded as a person area of the person to be monitored Ob, and a plurality of body movement areas extracted from the target image is regarded as including a noise source. .

In the detection of the predetermined behavior, in the present embodiment, the predetermined behavior is, as described above, admission, leaving, falling, falling, and anomalous body movement, and these entering, leaving, falling, and falling are The movement of the body is detected based on the output of the camera 111 (target image), and the micro movement abnormality is detected based on the output of the Doppler sensor 112 (Doppler signal).

More specifically, the behavior detection processing unit (noise source determination unit) 143 determines as follows: entering, leaving, falling, falling, body movement abnormality. In the following description, various thresholds and continuation determination times are appropriately set from a plurality of samples, stored in advance in the storage unit 16 as one of the various data, and the bedding BD in the target image is arranged The existing area (the area where the bedding BD is located) is stored in advance in the storage unit 16 as one of the various data.

In the determination of admission, the action detection processing unit 143 determines that the moving object region extracted as a human region by the background subtraction method from the target image acquired from the camera 111 this time is the bed when the previous state variable is "bed up". If the area completely overlaps with the area where the BD is located (if the person area (body movement area) is completely within the area where the bedding BD is located), it is provisionally determined to be the bed, and the duration of the complete overlapping state is the bed If the continuation determination time is exceeded and continues, it is finally determined that there is an entrance, and the entrance is detected. Then, the action detection processing unit 143 updates the state variable with “in bed”. The admission continuation determination time is a threshold value for ultimately determining that the bed, which is temporarily determined by completely overlapping the extracted person area and the location area of the bedding BD, is the bed.

In the determination of leaving, the action detection processing unit 143 extracts the state variable of the previous time from the target image acquired from the camera 111, which is one of the state variables of the last time “in bed” and “in awakening”. If the moving area is out of the area of the bedding BD is more than the bed leaving determination threshold, it is temporarily determined to be bed leaving, and the duration of the over coming area of the bed exceeding the bed leaving determining threshold is determined to be the bed continuation determining time If it exceeds, it is finally determined that there is bed departure, and the bed departure is detected. And action detection processing part 143 updates the above-mentioned state variable by "Being out of bed". The bed leaving determination threshold is a threshold for determining whether or not bed leaving is determined according to the size of the protruding area. The bed leaving continuation determination time is a threshold value for finally determining that bed leaving which has been tentatively determined by comparing the protruding area with the bed leaving determination threshold is bed leaving.

In the fall determination, the action detection processing unit 143 determines that the size of the head region in the moving object region extracted as the human region from the target image acquired from the camera 111 at this time is equal to or less than the lying posture determination threshold, If the rate of change of the size is equal to or greater than the fall determination speed threshold and the person area is within the fall determination area set around the area where the bedding BD is located, it is determined that there is a fall and the fall To detect The lying posture determination threshold is a threshold for determining whether or not the size of the head region in the lying posture is. The fall determination speed threshold is a threshold for determining whether or not a fall is caused by the change speed of the size of the head region.

In the fall determination, the action detection processing unit 143 determines that the size of the head region in the moving body region extracted as the human region from the target image acquired from the camera 111 at this time is equal to or less than the lying posture determination threshold, It is determined that there is a fall and the fall is detected if the rate of change of the size of the object is greater than or equal to the fall determination speed threshold and the person area is in the area excluding the bedding BD and the fall determination area. Do. The fall determination speed threshold value is a threshold value for determining whether or not it is a fall according to the change speed of the size of the head region.

In the micro movement abnormality, the action detection processing unit 143 determines the micro movement abnormality based on the Doppler signal of the Doppler sensor 112. More specifically, like the sleep state processing unit 142, the action detection processing unit 143 performs, for example, fast Fourier transform (FFT) on the Doppler signal measured within a predetermined time from the measurement time point to the past. From the obtained spectrum, an average value of amplitudes in a frequency band corresponding to a general respiration frequency is determined, and the determined average value and a threshold for determining whether or not there is an abnormality in the body movement (microbody Motion abnormality determination threshold), and if the average value obtained is equal to or less than the above-mentioned body movement abnormality determination threshold, it is temporarily determined that there is a body movement abnormality, and the above average value is less than the above-mentioned body movement abnormality determination threshold If the continuation time of a certain state continues beyond the time period for determination of abnormal movement of microbes, the micromotion abnormality is finally determined to be present, and the microbeal movement abnormality is detected. The micro movement abnormality determination threshold is set to a value smaller than the second sleep degree division threshold (second sleep degree division threshold> micro movement abnormality determination threshold). In order that the micro movement abnormality continuation determination time may finally determine that the micro movement abnormality temporarily determined by comparing the average value thus determined and the micro movement abnormality determination threshold is a micro movement abnormality. Is the threshold of

As described above, when the predetermined action is detected, the action detection processing unit 143 accommodates one or more of bed entry, bed leaving, falling, falling, and body movement abnormality as the sensor ID of the own device and the event information. The first event notification communication signal is transmitted to the management server SV via the SU communication IF unit 15. In addition, when the action detection processing unit 143 detects any of the entering, leaving, falling and falling, the first image is notified of the target image used in detecting the entering, leaving, falling and falling. It may be further accommodated in the communication signal, and if a body movement abnormality is detected, the camera 111 may be caused to generate an image, and this image may be further accommodated in the first event notification communication signal. The image may be at least one of a still image and a moving image.

Note that a third sensor dedicated to measuring a predetermined amount of noise used to detect a noise source by the noise source determination unit (action detection processing unit) 143 is provided in the sensor device SU, and the noise source is The determination unit (action detection processing unit) 143 may determine the presence or absence of the noise source based on the third measurement result of the third sensor, but in the present embodiment, as described above, the camera 111 is the noise source It is used for both the detection of the presence or absence of and the detection of the predetermined action.

The process control unit 144 controls the sleep state processing unit 142 in accordance with the detection result of the noise source determination unit (action detection processing unit) 143. More specifically, in the present embodiment, the process control unit 144 controls whether or not the sleep state processing unit 142 is to execute detection according to the detection result of the noise source determination unit 143. More specifically, for example, when the detection result of the noise source determination unit 143 indicates no noise source, the processing control unit 144 causes the sleep state processing unit 142 to perform detection, and If the detection result indicates that there is a noise source, the sleep state processing unit 142 is not made to execute detection.

When the nurse call reception operation unit 13 receives a nurse call, the nurse call processing unit 145 notifies the management server apparatus SV of a first event notification communication signal that accommodates this as another example of the predetermined event. By using the SU sound input / output unit 12 or the like, voice communication is performed with the terminal devices SP and TA. More specifically, when the nurse call reception operation unit 13 is operated for input, the nurse call processing unit 145 performs SU communication of the first event notification communication signal containing the nurse call as the sensor ID of the own device and the event information. It transmits to the management server apparatus SV via the IF unit 15. Then, the nurse call processing unit 145 uses the SU sound input / output unit 12 or the like to make a voice call, for example, by using Voice over Internet Protocol (VoIP) with the terminal devices SP and TA.

When there is a request for distribution of a moving image from the fixed terminal apparatus SP or the portable terminal apparatus TA via the communication IF unit 3, the SU streaming processing unit 146 sends the requested fixed terminal apparatus SP or the portable terminal apparatus TA , And distributes a moving image (for example, a live moving image) generated by the camera 11 through the SU communication IF unit 15 by streaming reproduction.

Four first to fourth sensor devices SU-1 to SU-4 provided corresponding to the monitored person Ob are shown in FIG. 1 as an example, and the first sensor device SU-1 is shown. Is disposed in the room RM-1 (not shown) of Mr. A's Ob-1 who is one of the monitored persons Ob, and the second sensor device SU-2 is Mr. B's Ob- who is one of the monitored persons Ob. The third sensor device SU-3 is disposed in a living room RM-2 (not shown) of 2 and is disposed in a living room RM-3 (not shown) of Mr. C's Ob-3 who is one of the monitored persons Ob. The fourth sensor device SU-4 is disposed in a living room RM-4 (not shown) of Mr. D's Ob-4 who is one of the monitored persons Ob.

In the sensor device SU having such a configuration, the sensor unit 11, the sleep state processing unit 142, the behavior detection processing unit (noise source determination unit) 143, and the processing control unit 144 constitute an example of a sleep state detection device, The Doppler sensor 112 and the sleep state processing unit 142 of the sensor unit 11 are an example of a sleep state detection unit that detects the sleep state of the target person (monitored person) Ob, and the camera 111 and the noise source determination unit of the sensor unit 11 Reference numeral 143 denotes an example of a noise source detection unit that detects the presence or absence of a noise source that generates noise with respect to the sleep state detected by the sleep state detection unit.

The management server SV has a communication function of communicating with the other devices SU, TA, and SP via the network NW, and receives the notification of the predetermined event from the sensor device SU by the first event notification communication signal. Manages information (monitoring information) related to monitoring of the observer Ob, and notifies (predicts, notifies, transmits) the predetermined event to a predetermined terminal apparatus SP and TA with a second event notification communication signal, and executes a client In the embodiment, the data is provided to the client according to the request of the terminal device (SP, TA, etc.) to manage the entire monitored person monitoring support system MS. In the present embodiment, the monitoring information includes, for example, a sensor ID of the sensor device SU that is a transmission source of the first event notification communication signal, the predetermined event (sleeping state (sleeping degree obtained by the sensor device SU) These are the type of predetermined action detected by the device SU, the nurse call received by the sensor device SU), the image of the monitored person Ob, the time when the notification is received (notification time), etc. It is associated and stored (recorded, managed). The monitoring information is accommodated in the second event notification communication signal. The second event notification communication signal may be transmitted, for example, by broadcast communication (broadcast or multicast), or, for example, one or more associated with the sensor device SU that is the transmission source of the first event notification communication signal. May be sent to the terminal device SP, TA. Such a management server SV can be configured, for example, by a computer with a communication function.

The fixed terminal device SP includes a communication function of communicating with other devices SU, SV, and TA via the network NW, a display function of displaying predetermined information, and an input function of inputting predetermined instructions and data. Monitored by, for example, inputting predetermined instructions and data given to the management server SV and the portable terminal TA, displaying the monitoring information obtained by the sensor SU by notification from the management server SV, etc. The device functions as a user interface (UI) of the person monitoring support system MS. Such fixed terminal apparatus SP can be configured, for example, by a computer with a communication function.

The portable terminal device TA has a communication function of communicating with other devices SV, SP, SU via the network NW, a display function of displaying predetermined information, an input function of inputting predetermined instructions and data, and a voice call. A call function to be performed is provided, and predetermined instructions and data given to the management server device SV and the sensor device SU are input, or the monitoring information obtained by the sensor device SU is displayed by notification from the management server device SV, It is a device for answering or calling a nurse call by voice communication with the sensor unit SU. Such a portable terminal device TA can be configured by, for example, a portable communication terminal device such as a so-called tablet computer, a smartphone, or a mobile phone.

Next, the operation of this embodiment will be described. FIG. 3 is a flow chart showing the operation of the sensor device in the service mode. FIG. 4 is a flowchart showing the operation of the sensor device in the sleep state determination process shown in FIG. FIG. 5 is a flowchart showing an operation of the sensor device in the fall determination process shown in FIG. FIG. 6 is a flowchart showing the operation of the sensor device in the falling determination process shown in FIG. FIG. 7 is a flowchart showing the operation of the sensor device in the bed entering determination process shown in FIG. FIG. 8 is a flowchart showing the operation of the sensor device in the bed leaving determination process shown in FIG. FIG. 9 is a flow chart showing the operation of the sensor device in the micro movement abnormality determination process shown in FIG. FIG. 10 is a diagram showing an example of a main screen displayed on the terminal device. FIG. 11 is a diagram showing an example of a first setting screen displayed on the terminal device. FIG. 12 is a diagram showing an example of a second setting screen displayed on the terminal device. FIG. 13 is a diagram showing an example of a monitoring information screen displayed on the terminal device. FIG. 14 is a view showing another example of the monitoring information screen displayed on the terminal device. FIG. 15 is a diagram showing still another example of the monitoring information screen displayed on the terminal device. FIG. 13A, FIG. 14A and FIG. 15A are each a diagram showing a monitoring information screen displaying the contents of an event as text, and FIG. 13B, FIG. 14B and FIG. It is a figure which shows an information screen.

In the person-to-be-monitored person monitoring support system MS configured as described above, when the power is turned on, each of the devices SU, SV, SP, and TA performs initialization of necessary parts and starts its operation. In the sensor unit SU, the SU control processing unit 14 includes the SU control unit 141, the sleep state processing unit 142, the behavior detection processing unit (noise source determination unit) 143, the processing control unit 144, and the nurse by executing the control processing program. The call processing unit 145 and the streaming processing unit 146 are functionally configured.

When the power is turned on and the operation is started, the terminal device SP, TA, for example, the fixed terminal device SP accepts a log-in operation by a supervisor (user) such as a nurse or a caregiver. In the login operation, an ID or the like of a user name or the like of the monitor is input and stored in the storage unit. When the fixed terminal device SP logs in to the monitored person monitoring support system MS by the login operation, the fixed terminal device SP displays a main screen on the display unit.

The main screen is a screen for receiving the operation mode of the fixed terminal device SP. For example, as shown in FIG. 11, the main screen 21 includes a “service mode” button 211 and a “setting mode” button 212. The “service mode” button 211 is a button for requesting a service mode for monitoring the monitored person Ob as the operation mode of the fixed terminal device SP, and an instruction to operate the fixed terminal device SP in the service mode (instruction, command ) Is a button for inputting. The “setting mode” button 212 is a button for requesting a setting mode for setting a predetermined parameter defined in advance as an operation mode of the fixed terminal apparatus SP, and instructs the fixed terminal apparatus SP to operate in the setting mode. It is a button for inputting.

When displaying the main screen 21 as described above, when receiving an input operation from the input unit of the fixed terminal device SP, the fixed terminal device SP receives the input operation received by the control processing unit as “service mode It is determined whether it is an input operation of the “” button 211 or an input operation of the “setting mode” button 212.

As a result of the determination, when the received input operation is an input operation of the “service mode” button 211, the fixed terminal device SP starts operation in the service mode so as to monitor the monitored person Ob. The input operation is, for example, an operation in which the cursor is moved onto the “service mode” button 211 by the movement of the mouse and the mouse is left-clicked.

On the other hand, as a result of the determination, when the received input operation is an input operation of the “setting mode” button 212, the fixed terminal device SP starts operation in the setting mode so as to set the predetermined parameter. .

In the setting mode, as described above, when the input operation of the “setting mode” button 212 is received, the fixed terminal device SP displays a setting screen on the display unit. In the present embodiment, authentication is performed using an ID such as a user name, and only the authorized user (the setter) can enter the setting mode.

The setting screen is a screen for inputting and setting the predetermined parameter. In the present embodiment, the predetermined parameter is a setting value used to appropriately determine the predetermined event, and for example, an imaging condition for extracting a monitored person Ob from an image, and the determination Threshold (determination threshold) or the like. More specifically, in the present embodiment, the predetermined parameters are a frame rate, a brightness level, a ceiling height, and an area where the bedding BD is located. The setting screen comprises two first and second setting screens in the present embodiment. The first setting screen inputs (determines) a person to be monitored Ob (sensor device SU) to be a target of parameter setting, and mainly the numerical parameters (the frame rate in the present embodiment) among the predetermined parameters. , Brightness level and ceiling height) are input and set. The second setting screen is a screen for inputting and setting other parameters (in the present embodiment, the location area of the bedding BD) other than numerical parameters among the predetermined parameters.

More specifically, when the input operation of the “setting mode” button 212 is received from the input unit, the fixed terminal device SP causes the control processing unit to display the first setting screen on the display unit 4.

For example, as shown in FIG. 12, this first setting screen 22 is for inputting and setting a frame rate and a monitor person's name input setting area 221 for inputting and setting the name of the monitoree Ob. Frame rate input setting area 222, a brightness level input setting area 223 for inputting and setting a brightness level, a ceiling height input setting area 224 for inputting and setting a ceiling height, An area setting button 225 and a "return to main screen" button 226 are provided. Each of the input setting areas 221 to 224 includes an input field for parameter values, and an “update” button for storing and setting parameters based on the parameter values input to the input fields. The “area setting” button 225 is a button for requesting the second setting screen, and is a button for inputting an instruction to cause the fixed terminal apparatus SP to display the second setting screen. The “return to main screen” button 226 is a button for requesting the main screen 21, and is a button for inputting an instruction to cause the fixed terminal apparatus SP to display the main screen 21. The “return to main screen” button 226 is also a button for setting each parameter value stored as a parameter in the storage unit to the sensor unit SU via the management server unit SV.

In the example shown in FIG. 11, “Mr. A”, “15 fps”, “5” and “2.4 m” are input in the input fields in the input setting areas 221 to 224, respectively. When the "update" button in the monitored person name input setting area 221 is operated, the control processing unit of the fixed terminal device SP sets the target of parameter setting to "Mr. A", and the storage unit of the fixed terminal device SP Is stored in Note that the sensor device SU that monitors “person A” or its sensor ID may be input and set as a parameter setting target. When the “update” button in the frame rate input setting area 222 is input, the control processing unit of the fixed terminal device SP sets the frame rate to “15 fps” and is stored in the storage unit of the fixed terminal device SP. In the present embodiment, since the sensor unit SU performs the event detection operation every frame or every few frames, setting the frame rate defines the execution interval of the event detection operation. When the “update” button in the brightness level input setting area 223 is input, the control processing unit of the fixed terminal device SP sets the brightness level to “5”, and is stored in the storage unit of the fixed terminal device SP. Ru. If the target image captured by the sensor unit SU is too dark or too bright, it becomes difficult to extract the person area of the person to be monitored Ob from the target image, and it becomes difficult to identify a person. By setting the brightness level, a target image can be generated with a proper exposure, the person area can be extracted more appropriately, and the person can be more appropriately identified. When the “update” button in the ceiling height input setting area 224 is input, the control processing unit of the fixed terminal device SP sets the ceiling height to “2.4 m”, and the storage unit of the fixed terminal device SP is It is memorized. When the sensor unit SU is disposed on a ceiling with a standard ceiling height (for example, 2.4 m or the like), the recumbent posture determination threshold value or the like in the case where the sensor unit SU is disposed is stored in advance in the sensor unit SU as a default value. By setting the ceiling height, the recumbent posture determination threshold of the default value is corrected, and the corrected recumbent posture determination threshold is used for the detection of the predetermined action described above. By setting the ceiling height, the lying posture determination threshold can be adjusted in accordance with the situation of the sensor device SU actually installed.

When the input operation of the “area setting” button 225 is received, the fixed terminal device SP displays the second setting screen on its display unit.

For example, as shown in FIG. 12, the second setting screen 23 includes a target image display area 231 for displaying a target image, an “update” button 232, and a “return” button 233. In the target image display area 231, the camera 111 of the sensor device SU for monitoring the monitored person Ob having the name of the monitored person Ob inputted in the monitored person name input setting area 221 of the first setting screen 22. The generated target image is displayed. The “update” button 232 is a button for requesting setting of parameters in the area input from the input unit while referring to the target image displayed in the target image display area 231. The “return” button 233 is a button for requesting the first setting screen 22, and is a button for inputting an instruction to cause the fixed terminal apparatus SP to display the first setting screen 22.

In the second setting screen 23 as described above, when the second setting screen 23 is displayed, the fixed terminal device SP waits for the input of the location area of the bedding BD. When the user inputs four vertices of the location area of the bedding BD from the input unit and performs an input operation of the "update" button 232, the control processing unit of the fixed terminal apparatus SP causes each of the four vertices of the location area of the bedding BD. The pixel position is input, stored in the storage unit, and the location area of the bedding BD is set. FIG. 12 illustrates how the user inputs the four vertices of the location area of the bedding BD.

Then, when the “Return” button 233 is operated, the first setting screen 22 is displayed on the display unit 4. Furthermore, when the “Return to main screen” button 226 is operated, the main screen 21 is displayed. At this time, the fixed terminal device SP manages each parameter value stored as a parameter in its storage unit as a management server device The sensor unit SU transmits the parameter values to the sensor unit SU via the SV, and stores and sets the received parameter values in the SU storage unit 16 of the own unit SU. As a result, each value of the predetermined parameter is set in the sensor unit SU.

On the other hand, when the input operation of the “service mode” button 211 is received on the main screen 21 described above, the fixed terminal device SP operates in the service mode, and the monitored person monitoring support system MS operates as follows. Monitors the monitored person Ob.

In the monitoring of the monitored person Ob, the sensor device SU detects the sleep state of the monitored person Ob by operating as follows for each frame or every several frames, and detects the sleeping state of the monitored person Ob. A predetermined operation is detected, and the presence or absence of acceptance of a nurse call is determined.

In FIG. 3, first, the sensor unit SU causes the SU control processing unit 14 to acquire an image of one frame as a target image from the camera 111 of the sensor unit 11 (S1).

Subsequently, the sensor device SU causes the behavior detection processing unit (noise source determination unit) 143 of the SU control processing unit 14 to extract a moving subject region from the target image acquired from the camera 111 in process S1 (S2) ).

Subsequently, the sensor device SU causes the timing detection unit (action detection processing unit) 143 to determine whether there is a noise source that generates noise with respect to the sleep state detected by the sleep state processing unit 142 (S3). More specifically, in the present embodiment, the noise source determination unit 143 determines the number of body motion areas extracted in the process S2. As a result of this determination, the noise source determination unit 143 determines that there is no noise source if the number of moving object areas extracted is one (No, No), and notifies the processing control unit 144 of the detection result. Next, process S4 is performed. On the other hand, as a result of the determination, the noise source determination unit 143 determines that there is a noise source when there are a plurality of extracted moving body regions (Yes, Yes), and notifies the processing control unit 144 of this detection result. Then, the process S5 is performed. When it is determined that there is a noise source (Yes, Yes), the noise source determination unit 143 may execute processing S5 next without notifying the processing control unit 144 of the detection result.

In the process S4, the sensor device SU controls the sleep state processing unit 142 by the process control unit 144 of the SU control processing unit 14.

More specifically, when the result of the noise source determination unit 143 indicates that there is no noise source from the noise source determination unit (action detection processing unit) 143, the process control unit 144 detects the sleep state processing unit 142. Next, processing S10 is executed, and from the noise source determination unit (action detection processing unit) 143, if the result of the noise source determination unit 143 is that there is a noise source, the sleep state Next, processing S10 is performed without the processing unit 142 performing detection.

In this sleep state process, in FIG. 4, first, the sleep state processing unit 142 determines whether the determination condition of the sleep state is satisfied based on the Doppler signal of the Doppler sensor 112 (S41). More specifically, the sleep state processing unit 142 first acquires, from the SU storage unit 16, a Doppler signal measured within a predetermined time, for example, one minute, from the present time to the past. Subsequently, the sleep state processing unit 142 performs, for example, fast Fourier transform (FFT) on the acquired one-minute Doppler signal. Subsequently, the sleep state processing unit 142 obtains an average value of amplitudes in a frequency band corresponding to a general respiration frequency from the spectrum obtained by the FFT. Subsequently, the sleep state processing unit 142 compares the calculated average value with the sleep level division threshold, and in the present embodiment, the first and second sleep level division thresholds respectively. As a result of this comparison, when the average value thus obtained exceeds the first sleep level classification threshold, the sleep state processing unit 142 temporarily determines that the awakening state is in progress, and the average value exceeds the first sleep level classification threshold. If the duration of the current state exceeds the predetermined duration determination time (presence duration during awakening determination), the tentatively determined duration of awakening is determined as the final sleep degree (Yes), Next, process S42 is performed. As a result of the comparison, the sleep state processing unit 142 provisionally obtains the low sleepiness degree, when the calculated average value is less than the first sleepiness degree division threshold and exceeds the second sleepiness degree division threshold. The duration of the state in which the average value is less than the first sleep level category threshold and exceeds the second sleep level category threshold exceeds a predetermined continuation determination time (low sleep continuation determination time) set in advance. In this case, the temporarily determined low sleep level is determined as the final sleep level (Yes), and then the process S42 is executed. As a result of the comparison, when the average value is equal to or less than the second sleep level division threshold, the sleep state processing unit 142 temporarily determines the high sleep degree, and the average value is equal to or less than the second sleep level division threshold. If the duration of a certain state exceeds a predetermined duration determination time (continuity determination time during high sleep), the temporarily obtained high sleep degree is determined as the final sleep degree (Yes) Then, the process S42 is executed. Then, as a result of the comparison, in the case other than this as a result of the comparison, the sleep state processing unit 142 provisionally determines the sleep state (No), and ends the present sleep state processing.

In the process S42, the sleep state processing unit 142 determines that the sleep state has been determined and the sleep state has been obtained. Sleep state detection presence information (for example, a sleep state detection flag indicating presence or absence of sleep state detection is “0” 1) is stored in the SU storage unit 16 and the state variable is updated with “sleeping degree (any of awakening, low sleep degree, high sleep degree)” (state variable 「“ sleeping degree ” ), End this sleep state processing.

Returning to FIG. 3, in the process S5, the sensor device SU causes the behavior detection processing unit 143 of the control processing unit 14 to perform a fall determination process based on the moving object region extracted in the process S2.

More specifically, in this fall determination processing, first, the true person area of the person to be monitored (target person) Ob is specified from a plurality of moving body areas. For example, the action detection processing unit 143 determines whether or not each of a plurality of moving object regions has a head region, and sets the moving object region having the head region as a true person region of the monitored person (target person) Ob. If there is no moving object region having a head region and if there are a plurality of moving object regions having a head region, the present processing is terminated as an error. Then, in FIG. 5, first, the action detection processing unit 143 determines whether or not the fall determination condition is satisfied based on the person area extracted and specified in the process S2 as described above (S51). More specifically, the action detection processing unit 143 determines that the size of the head region of the person region extracted from the target image in the process S2 and specified as described above is equal to or less than the lying posture determination threshold, It is determined that there is a fall if the change speed of the size of the area is equal to or more than the fall judgment speed threshold and the person area is within the fall judgment area set around the area where the bedding BD is located (Yes Then, the process S52 is executed, and in the other cases, it is determined that there is no fall (No), and the present fall determination process is ended. Here, the extraction of the head region is performed by, for example, circular or elliptical Hough transform from the person region, for example, pattern matching using a prepared head model (template), for example, head extraction It is extracted by the neural network learned for the purpose. In the process S52, the action detection processing unit 143 stores SU storage information (for example, the fall flag indicating the presence or absence of a fall is changed from "0" to "1") by determining the occurrence of a fall and indicating the presence of a fall. The part 16 is stored, and the main fall determination process is ended.

Returning to FIG. 3, in the processing S6 following the processing S5, the sensor device SU executes the fall determination processing based on the person area extracted and specified as described above by the action detection processing unit 143. .

More specifically, in this fall determination process, first, in FIG. 6, whether the action detection processing unit 143 satisfies the fall determination condition based on the person area extracted and specified as described above in the process S2 It is determined whether or not it is (S61). More specifically, the action detection processing unit 143 determines that the size of the head region of the person region extracted from the target image in the process S2 and specified as described above is equal to or less than the lying posture determination threshold, If the change speed of the size of the area is equal to or more than the fall determination speed threshold and the human area is in the area excluding the area where the bedding BD is located and the fall determination area, it is determined that there is a fall (Yes); Next, processing S62 is executed, and in the other cases, it is determined that there is no fall (No), and the present fall determination processing is ended. In the process S62, the action detection processing unit 143 stores the SU presence information (for example, the fall flag indicating the presence or absence of a fall is changed from "0" to "1") by determining the occurrence of a fall and representing the presence of a fall. It memorizes in section 16, ends this falling decision processing.

Returning to FIG. 3, in the processing S7 following the processing S6, the sensor device SU executes the entrance determination processing based on the person area extracted and identified as described above in the processing S2 by the action detection processing unit 143 Do.

More specifically, in this entering determination process, in FIG. 7, the action detection processing unit 143 first determines whether the state variable (previous state variable) is (S71). As a result of this determination, when the state variable is not “bedding off” (No), the behavior detection processing unit 143 ends the main entrance determination processing. On the other hand, as a result of the determination, if the state variable is “bedding off” (Yes), the action detection processing unit 143 next executes processing S72. In the process S72, the action detection processing unit 143 determines whether or not the determination condition of admission is satisfied based on the person area extracted and specified as described above in the process S2. More specifically, when the behavior detection processing unit 143 completely overlaps the location area of the bedding BD this time, the feature area extracted from the target image in the process S2 and specified as described above (the above-mentioned person area is completely If it is in the area where the bedding BD is located), it is tentatively determined to be in bed, and if the continuation time of the complete superposition state continues beyond the in-bed continuation determination time, it is finally determined to be in-bed presence (Yes) Next, the process S73 is executed, and in the case other than this, it is determined that there is no bed entry (No), and the present bed entry determination process is ended. In the process S73, the behavior detection processing unit 143 determines the occurrence of the entrance and the presence information indicating the presence of the entrance (for example, the entrance flag indicating the presence or absence of the entrance is changed from "0" to "1"). Is stored in the SU storage unit 16). Subsequently, the behavior detection processing unit 143 updates the state variable with “in-bed” (state variable 「“ in-bed ”) (S74), and ends the main-in-bed determination processing.

Returning to FIG. 3, in process S8 following the process S7, the sensor device SU executes the bed leaving determination process based on the person area extracted and identified as described above in the process S2 by the action detection processing unit 143. .

More specifically, in the bed leaving determination process, in FIG. 8, the action detection processing unit 143 first determines whether the state variable (previous state variable) is (S81). As a result of this determination, when the state variable is neither “in bed” nor “in awakening” (No), the behavior detection processing unit 143 ends the current leaving determination process. On the other hand, as a result of the determination, if the state variable is any one of “in bed” and “awake” (Yes), the action detection processing unit 143 next executes a process S82. In the process S82, the action detection processing unit 143 determines whether or not the determination condition for bed departure is satisfied based on the person area extracted and specified as described above in the process S2. More specifically, the action detection processing unit 143 detects that the person area extracted from the target image in the process S2 and identified as described above is out of the area of the bedding BD at this time is equal to or more than the bed departure determination threshold. In this case, temporary determination is made that the bed has left, and if the continuation time of the overhang region in the state of being equal to or greater than the bed separation determination threshold exceeds the bed up determination time, final determination is made as bed release (Yes). S83 is executed, and in the other cases except this, it is determined that there is no bed leaving (No), and the present bed leaving determination processing is ended. In the process S83, the behavior detection processing unit 143 determines the occurrence of bed departure and stores the presence of bed leaving information (for example, the bed leaving flag indicating presence or absence of bed leaving is changed from "0" to "1") in the SU memory. Store in section 16 Subsequently, the behavior detection processing unit 143 updates the state variable with "bedding" (state variable 「" beading ") (S84), and ends the bed leaving determination processing.

Returning to FIG. 3, in the processing S9 following the above-described processing S8, the sensor device SU causes the behavior detection processing unit 143 to execute micro movement abnormality determination processing based on the Doppler signal of the Doppler sensor 112 in the sensor unit 11.

More specifically, in this micro movement abnormality determination process, in FIG. 9, first, the action detection processing unit 143 determines whether or not the micro movement abnormality determination condition is satisfied based on the Doppler signal of the Doppler sensor 112. It determines (S91). More specifically, the action detection processing unit 143 first acquires, from the SU storage unit 16, a Doppler signal measured within a predetermined time, for example, within one minute, from the present time to the past. Subsequently, the behavior detection processing unit 143 performs, for example, fast Fourier transform (FFT) on the acquired one-minute Doppler signal. Subsequently, the behavior detection processing unit 143 obtains an average value of amplitudes in a frequency band corresponding to a general respiration frequency from the spectrum obtained by the FFT. Subsequently, the action detection processing unit 143 compares the calculated average value with the above-mentioned body movement abnormality determination threshold, and if the obtained average value is equal to or less than the above-mentioned body movement abnormality determination threshold, the body movement abnormality If the duration of the state where the average value is equal to or less than the micro movement abnormality determination threshold is tentatively determined and continues beyond the micro movement abnormality continuation determination time, the micro movement abnormality is determined to be present. A determination is made (Yes), and then the process S92 is executed, and in the other cases, it is determined that there is no micro movement abnormality (No), and the micro movement abnormality determination process is ended. In the process S92, the action detection processing unit 143 determines micro body movement abnormality occurrence and indicates micro body movement abnormality presence information indicating presence of micro body movement abnormality (for example, a micro body movement abnormality flag indicating presence or absence of micro body movement abnormality “0” is changed to “1” to be stored in the SU storage unit 16, and the micro movement abnormality determination process is ended.

Returning to FIG. 3, next, the sensor device SU determines whether or not notification of a predetermined event is necessary by the SU control processing unit 14 (S10). More specifically, the sensor unit SU causes the sleep state processing unit 142 of the SU control processing unit 14 to store the sleep state detection information in the SU storage unit 16 or the SU storage unit using the action detection processing unit 143 of the SU control processing unit 14. For example, it is determined whether the result of the fall presence information, the fall presence information, etc. is stored in 16, and if the result is stored in the SU storage unit 16, the SU control processing unit 14 If it is determined that the notification is necessary (Yes) and then the process S11 is executed, the present process is terminated. If the result is not stored in the SU storage unit 16, the SU control processing unit is performed. 14 determines that the notification is unnecessary (No), and ends the present process.

In this process S11, the sensor device SU uses the SU control processing unit 14 to notify the predetermined terminal devices SP and TA of the resultant event, the first event notification communication signal containing the result as the event information. Is sent to the management server SV. In one specific example, in the case where the bed presence information is stored in the SU storage unit 16, the SU control processing unit 14 determines the sensor ID of its own device, the "bed" as the event information, and the determination of the bed. The first event notification communication signal containing the used target image is transmitted to the management server SV via the SU communication IF unit 15.

Then, while executing each of the processes S1 to S11 as described above, the sensor device SU determines whether the nurse call processing unit 145 of the SU control processing unit 14 receives a nurse call or not. And, upon receiving a nurse call, the sensor device SU transmits a first event notification communication signal containing the received nurse call as the event information in order to notify acceptance of the nurse call to a predetermined terminal device SP or TA. Is sent to the management server SV.

When the management server device SV receives the first event notification communication signal from the sensor device SU via the network NW, each sensor ID, event information, and other information contained in the first event notification communication signal is the sensor ID. Are stored (recorded) as monitoring information of the monitored person Ob monitored by the sensor device SU. That is, the management server device SV stores the sensor ID, the event information, and other information contained in the first event notification communication signal in association with each other. Then, the management server device SV transmits a second event notification communication signal to the terminal devices SP and TA of the notification destination corresponding to the sensor device SU of the transmission source (notification source) in the received first event notification communication signal.

When the fixed terminal apparatus SP and the portable terminal apparatus TA receive the second event notification communication signal from the management server apparatus SV via the network NW, the sensor ID, the event information, etc. contained in the second event notification communication signal Each piece of information is stored (recorded) as monitoring information of the monitored person Ob monitored by the sensor device SU having the sensor ID, and the monitoring information is displayed. For example, in the case where the sensor device SU detects “being awake” and this “awake” is notified by the second event notification communication signal, the terminal devices SP and TA display the event information shown in FIG. 13A as text. The monitored information screen 31a is displayed. Alternatively, a monitoring information screen 31b in which the event information shown in FIG. 13B is displayed by an icon is displayed on the terminal devices SP and TA. Further, for example, when the sensor device SU detects the “low sleep level” and this “low sleep level” is notified by the second event notification communication signal, the terminal apparatus SP, TA receives the event information shown in FIG. 14A. The monitoring information screen 31a displayed in text is displayed. Alternatively, a monitoring information screen 31b in which event information shown in FIG. 14B is displayed by an icon is displayed on the terminal devices SP and TA. For example, in the case where the sensor apparatus SU detects the "high sleep level" and this "high sleep level" is notified by the second event notification communication signal, the terminal apparatus SP, TA receives the event information shown in FIG. 14A. The monitoring information screen 31a displayed in text is displayed. Alternatively, a monitoring information screen 31b in which event information shown in FIG. 14B is displayed by an icon is displayed on the terminal devices SP and TA.

As described above, in the monitored person monitoring support system MS according to the present embodiment, and the sleep state detection device and the sleep state detection method incorporated in the sensor device SU, the detection result of the noise source detection unit is the present embodiment. Then, according to the result of the noise source determination unit (action detection processing unit) 143, the sleep state detection unit, that is, the sleep state processing unit 142 in the present embodiment, is controlled. In the state, while the sleep state processing unit 142 determines the sleep state of the target person (monitored person) Ob, in a state unsuitable for detection of the sleep state with a noise source, the sleep state processing unit 142 sleeps the target person Ob Since it becomes possible to control so as not to determine the state, the above-mentioned person-to-be-monitored monitoring support system MS, the sleep state detection device and the sleep state detection method can reduce erroneous determinations more. That.

The above-described person-to-be-monitored monitoring support system MS, the sleep state detection device, and the sleep state detection method, for example, cause the sleep state processing unit 142 to execute detection in a state suitable for detection of a sleep state without noise sources By controlling the sleep state processing unit 142 so as to cause the sleep state processing unit 142 to not perform detection or the like in a state unsuitable for the detection of the sleep state with a noise source, erroneous determination can be further reduced. .

In the above-described embodiment, the processing control unit 144 causes the sleep state processing unit 142 to respond to the detection result of the noise source detection unit, or according to the result of the noise source determination unit (action detection processing unit) 143 in this embodiment. Although whether or not to execute detection is controlled, the processing control unit 144 detects the noise source detection unit as in each of the following modifications, and in each of the modifications, a noise source determination unit (action detection processing unit) The sleep state processing unit 142 may be controlled according to the result of 143.

In the first modified embodiment, the process control unit 144 controls whether to output the sleep state detected by the sleep state processing unit 142 according to the result of the noise source determination unit 143. In the first modified embodiment, although the sleep state processing is executed by the sleep state processing unit 142, by controlling the output of the result, an effect equivalent to the effect obtained by the control of the execution can be obtained. More specifically, in the process S4, when the result of the noise source determination unit 143 indicates that there is no noise source from the noise source determination unit 143, the process control unit 144 causes the sleep state processing unit 142 to If the output of the obtained sleep degree is performed, while the result of the noise source determination unit 143 indicates that there is a noise source from the noise source determination unit 143, the sleep state processing unit 142 determines the calculated sleep degree Exit without output. Such a monitored person monitoring support system MS, a sleep state detection device, and a sleep state detection method, for example, have no noise source, and the sleep state obtained by the sleep state processing unit 142 in a state suitable for detecting a sleep state. The sleep state processing unit 142 is controlled to output or not output the sleep state obtained by the sleep state processing unit 142 in a state unsuitable for the detection of the sleep state with noise source and the like. Thus, erroneous determinations can be further reduced.

In the second modification, the process control unit 144 controls whether the sleep state detected by the sleep state processing unit 142 is to be assisted by the result of the noise source determination unit 143 according to the result of the noise source determination unit 143. Do. More specifically, in the process S4, in the process S4, the process control unit 144 receives from the noise source determination unit 143 the result of the noise source determination unit 143 when there is no noise source. If the result of the noise source determination unit 143 from the noise source determination unit 143 indicates that there is a noise source, the sleep state processing unit 142 outputs the obtained sleep degree as it is. Additional information is added to the sleep degree detected by the state processing unit 142 to indicate that the sleep degree is determined to be unsuitable for detection of a sleep state such as "low accuracy" or "low reliability". Such a monitored person monitoring support system MS, a sleep state detection device, and a sleep state detection method, for example, have no noise source, and the sleep state detected by the sleep state processing unit 142 in a state suitable for detection of the sleep state. Conversely, there is a noise source, and information indicating that the sleep state detected by the sleep state processing unit 142 is unsuitable for detection of the sleep state is information indicating that the state is unsuitable for detection of the sleep state. Since it becomes possible to assist the sleep state obtained by the sleep state processing unit 142 with the result of the noise source determination unit 143 or the like, such as adding or the like, erroneous determination can be further reduced.

In the third modified embodiment, the sleep state processing unit 142 measures the sleep degree representing the degree of the depth of the sleep of the subject person (monitored person) Ob with the preset sleep degree determination threshold value and the first measurement of the first sensor. The processing control unit 144 changes the sleep condition determination threshold according to the result of the noise source determination unit 143 as the control, by comparing the result with the result. In the above-described embodiment, the first and second sleep level classification thresholds correspond to an example of the sleep level determination threshold, the Doppler sensor 112 corresponds to an example of the first sensor, and more specifically, the processing In S4, when the result of the noise source determination unit 143 indicates that there is a noise source from the noise source determination unit 143, the process control unit 144 sets the first and second sleep level classification thresholds to a low sleep level or a high sleep level. The sensor unit SU is set so as to change it to a value that is difficult to determine the degree of sleep, so that the degree of low sleep and the degree of high sleep can not be substantially determined. On the other hand, when the result of the noise source determination unit 143 indicates that there is no noise source from the noise source determination unit 143, the process control unit 144 sets the first and second sleep level classification thresholds to low sleep or high sleep. The sensor unit SU is set such that it is changed to a value that is easy to be determined, and the low sleep degree and the high sleep degree can be substantially easily found. Such a monitored person monitoring support system MS, a sleep state detection device, and a sleep state detection method, for example, have a noise source, and in the case of a state suitable for detecting a sleep state Changing the state judgment threshold or changing the sleep state judgment threshold to a value for which it is difficult to obtain the sleep state when the state of the noise is not suitable for detection of the sleep state. Since this becomes possible, it is possible to further reduce the erroneous determination.

In addition, preferably, the sleep state processing unit 142 uses the learning model of one of a plurality of different learning models machine-learned to obtain a sleep state based on the first measurement result of the first sensor. The processing control unit 144 determines, as the control, the sleep state processing unit 142 from among the plurality of learning models according to the result of the noise source determination unit 143. The learning model used in may be changed (selected). In addition, preferably, the sleep state processing unit 142 uses the algorithm of one of a plurality of different algorithms for determining the sleep state to obtain the target person (monitored person) Ob based on the first measurement result of the first sensor. The processing control unit 144 changes (selects) the algorithm used by the sleep state processing unit 142 from among the plurality of algorithms according to the result of the noise source determination unit 143 as the control. It is good.

In the fourth modified embodiment, the sleep state processing unit 142 determines, in advance, the sleep degree indicating the degree of the depth of the sleep of the subject person (monitored person) Ob at predetermined time intervals set in advance. Temporarily determined as the sleep state by comparing the threshold value and the first measurement result of the first sensor, and the tentatively determined sleep degree is temporarily determined when the continuation determination time set in advance is continued. The sleep degree is determined as the final sleep degree, and the process control unit 144 changes the continuation determination time according to the result of the noise source determination unit 143 as the control. In the above-described embodiment, the first and second sleep level classification thresholds correspond to an example of the sleep level determination threshold, the Doppler sensor 112 corresponds to an example of the first sensor, and the awakening determination time during awake time is low. The continuous determination time during sleep and the continuous determination time during high sleep correspond to an example of the continuous determination time. More specifically, in the process S4, when the result of the noise source determination unit 143 indicates that there is a noise source from the noise source determination unit 143, the process control unit 144 determines that the awakening continuation determination time is low. Change the continuous judgment time during sleep and the continuous judgment time during high sleep to values that are difficult to be judged during awakening or low sleep or high sleep, thereby substantially awakening or low sleep or high sleep The sensor unit SU is set so as not to be required. On the other hand, when the result of the noise source determination unit 143 indicates that there is no noise source from the noise source determination unit 143, the process control unit 144 determines that the awakening continuation determination time, the low sleep continuation determination time, and the high sleep The sensor apparatus SU is configured to change the continuation determination time to a value that makes it easy to determine the awakening degree and the low sleep degree and the high sleepiness degree, thereby substantially obtaining the awakening degree and the low sleepiness and the high sleep degree. Is set. Such a monitored person monitoring support system MS, a sleep state detection device, and a sleep state detection method continue, for example, to a value that makes it easy to obtain a sleep state when there is no noise source and is a state suitable for detecting a sleep state. Since it is possible to change the determination time or to change the determination time to a value for which it is difficult to determine the sleep state when the determination time is changed, or conversely, when the sleep state is not suitable for detecting the sleep state. False positives can be reduced.

From the viewpoint of detecting the sleep state with higher accuracy, the process control unit 144 receives no noise source as a result of the noise source determination unit 143 from the noise source determination unit 143. The awakening continuation determination time, the low sleep continuation determination time and the high sleep continuation determination time are respectively determined from the noise source determination unit 143 and the arousal when the result of the noise source determination unit 143 indicates that there is a noise source. It may be changed to a value longer than the duration of the medium continuation determination time, the low sleep continuation determination time, and the high sleep continuation determination time.

In the fifth modified embodiment, the first sensor includes a plurality of sub-sensors that measure a subject person (monitored person) Ob, and the sleep state processing unit 142 selects one of the plurality of sub sensors in the first sensor. Based on the sub-measurement result of the sub-sensor, the sleep state of the subject Ob is determined, and the processing control unit 144 performs, as the control, a sleep state processing unit from among the plurality of sub-sensors according to the result of the noise source determination unit 143 Change the sub-sensors used at 142. Preferably, the plurality of sub-sensors may be disparate different sensors. More specifically, for example, the first sensor is placed between the non-contact type Doppler sensor 112 described above, the bedding BD and the subject person (monitored person) Ob to detect the weight of a person If the result of the noise source determination unit 143 indicates that there is a noise source from the noise source determination unit 143, the process control unit 144 uses the sub sensor used by the sleep state processing unit 142. It changes to the said mat | matte sensor, and makes the sleep state process part 142 obtain | require the sleeping state of object person Ob based on the output of the said mat | matte sensor. For example, Japanese Patent Application Laid-Open No. 2013-198654, Japanese Patent Application Laid-Open No. 2014-223174, etc. disclose a method of obtaining a sleep state using such a mat sensor. Further, for example, a sleep meter Sleep scan SL-504 (manufactured by Tanita) or a sleep meter HSL-101 (manufactured by Omron) may be used as a sub-sensor. On the other hand, when the result of the noise source determination unit 143 indicates that there is no noise source from the noise source determination unit 143, the process control unit 144 changes the sub sensor used in the sleep state processing unit 142 to the Doppler sensor 112, Based on the output of the Doppler sensor 112, the sleep state processing unit 142 obtains the sleep state of the subject Ob. In such a monitored person monitoring support system MS, the sleep state detection device, and the sleep state detection method, among the plurality of sub sensors, the sub sensor used in the sleep state processing unit 142 is selected according to the detection result of the noise source determination unit. Since the change is made, it is possible to select an appropriate sub-sensor to be used by the sleep state processing unit 142 according to the result of the noise source determination unit 143 from among the plurality of sub sensors, so that erroneous determination can be further reduced.

In the sixth variation, the sleep state processing unit 142 Fourier-transforms the Doppler signal measured by the Doppler sensor 112 within a predetermined time set in advance, and copes with the respiratory frequency from the spectrum obtained by the Fourier transformation. The average value of the amplitude in the frequency band to be obtained is determined, and the sleep state of the target person (monitored person) Ob is determined based on the determined average value, and the processing control unit 144 determines the result of the noise source determination unit 143 as the control. The bandwidth of the frequency band is changed accordingly. More specifically, for example, in the process S4, when the result of the noise source determination unit 143 from the noise source determination unit 143 indicates that there is a noise source, the bandwidth of the frequency band is The sensor device SU is set so as to measure the movement of the body surface of the chest accompanying breathing in the subject Ob more reliably. On the other hand, when the result of the noise source determination unit 143 is that there is no noise source from the noise source determination unit 143, the process control unit 144 relatively narrows the bandwidth of the frequency band, thereby The sensor unit SU is set to more accurately measure the movement of the body surface of the chest associated with respiration in the person Ob ((the bandwidth when the result of the noise source determination unit 143 indicates the presence of a noise source) > (The bandwidth in the case where the result of the noise source determination unit 143 is no noise source)). Such a monitored person monitoring support system MS, the sleep state detecting device, and the sleep state detecting method change the bandwidth of the frequency band according to the result of the noise source determining unit 143, so that erroneous determination can be further reduced.

In the seventh modified embodiment, as shown by the broken line in FIG. 2, the sensor unit SU functionally further includes a clock unit 147 for clocking the date and time in the SU control processing unit 14, and at least a sleep time zone The SU storage unit 16 is further provided with a schedule information storage unit 161 that stores schedule information representing the schedule of the target person Ob included in association with the target person (monitored person) Ob, and the processing control unit 144 From the schedule information storage unit 161, the current time is acquired from the current time, and the schedule of the extracted target person Ob and the result of the noise source determination unit 143 are extracted from the schedule information storage unit 161. Control the sleep state processing unit 142. For example, when the schedule of the subject Ob corresponding to the current time is a sleep time zone, the process control unit 144 receives the result of the noise source determination unit 143 from the noise source determination unit 143, If there is no noise source, the first and second sleep level classification thresholds are changed to values that are more easily determined as the low sleep level and the high sleep level than the default value. Such a monitored person monitoring support system MS, the sleep state detecting device, and the sleep state detecting method control the sleep state processing unit 142 according to the schedule of the target person Ob and the detection result of the noise source determination unit 143. It is possible to take account of the person Ob's schedule and to reduce false positives more.

In the above-described embodiment and the respective variations thereof, the sensor used in the sleep state processing unit 142 is a narrow measurement range sensor having a predetermined first measurement range set in advance, and the noise source determination unit 143 The sensor used may be a wide measurement range sensor having a second measurement range wider than the first measurement range. Such a narrow measurement range sensor is, for example, the Doppler sensor 112 described above. The wide measurement range sensor is, for example, the above-described camera 111, and also, for example, a thermographic apparatus capable of extracting a human region from a temperature distribution. The narrow measurement range sensor and the wide measurement range sensor are not limited to these, and the second measurement range may be wider than the first measurement range. In such a monitored person monitoring support system MS, the sleep state detecting device and the sleep state detecting method, since the sleep state detecting unit includes the narrow measurement range sensor, the target person can be measured locally locally and noise Since the source detection unit includes the wide measurement range sensor, the surroundings of the subject can be measured widely.

Moreover, in the above-mentioned embodiment and its each modification, although the presence or absence of a noise source was determined by the number of objects of a moving body area | region, you may determine as follows. For example, a predetermined determination area (for example, the location area of the bedding BD) set in advance is stored in the storage unit 16, and the noise source determination unit 143 extracts a moving body area from the target image generated by the camera 111. If there is one extracted moving object region and the entire extracted moving object region is within the judgment region, it is judged that there is no noise source, and there is one extracted moving object region and the extracted moving object region When it is outside the judgment area, it is judged that there is a noise source, and even when there are a plurality of extracted moving object areas, it is judged that there is a noise source.

Although the present specification discloses various aspects of the technology as described above, the main technologies are summarized below.

A sleep state detection device according to one aspect includes a sleep state detection unit that detects a sleep state of a subject, and a noise source detection that detects the presence or absence of a noise source that generates noise with respect to the sleep state detected by the sleep state detection unit. A processing control unit that controls the sleep state detection unit according to the detection result of the noise source detection unit. Preferably, in the above-described sleep state detection device, the sleep state detection unit determines a sleep state of the subject based on a first sensor that measures the subject and a first measurement result of the first sensor. And a processing unit. Preferably, in the above-described sleep state detection device, the first sensor is a Doppler sensor that measures movement of a body surface of a chest associated with breathing in the subject. Preferably, in the above-described sleep state detection device, the sleep state processing unit obtains a sleep degree representing the degree of depth of sleep of the subject as the sleep state. Preferably, in the above-described sleep state detection device, the sleep state processing unit obtains a sleep degree representing the degree of sleep depth of the subject and a reliability degree representing the degree of reliability with respect to the sleep degree. Preferably, in the above-described sleep state detection device, the noise source detection unit is configured to measure the noise source based on a third measurement result of measuring a predetermined amount set in advance and a third measurement result of the third sensor. And a noise source determination unit that determines presence or absence. Preferably, in the above-described sleep state detection device, the third sensor is a camera that generates an image of the subject. Preferably, in the above-described sleep state detection device, the noise source is a person other than the subject, an animal except a person, a screen of a television, a curtain and a string (for example, the lighting device for turning on and off a lighting device) At least one of the extending strings). Preferably, in the above-described sleep state detection device, the noise source determination unit extracts a moving object region from the image generated by the camera, and there is no noise source when the extracted moving object region is one. If there are a plurality of moving body regions extracted, it is determined that there is a noise source. Preferably, the above-described sleep state detection apparatus further includes a storage unit that stores a predetermined determination area set in advance, the noise source determination unit extracts a moving body area from the image generated by the camera, and the extraction If there is one moving object region and the whole extracted moving object region is within the judgment region, it is judged that there is no noise source, and there is one extracted moving object region and the extracted moving object region is If it is outside the determination area, it is determined that there is a noise source, and if there are multiple moving object areas extracted, it is also determined that there is a noise source.

Since such a sleep state detection device controls the sleep state detection unit according to the detection result of the noise source detection unit, for example, in a state suitable for detection of a sleep state without a noise source, the sleep state detection unit Since it is possible to control so that the sleep state detection unit does not seek the sleep state of the subject in a state unsuitable for detecting the sleep state while there is a noise source while the sleep state of the subject person is determined, The state detection device can further reduce erroneous determinations.

In another aspect, in the above-described sleep state detection device, the processing control unit controls whether to cause the sleep state detection unit to execute detection in accordance with the detection result of the noise source detection unit.

Such a sleep state detection apparatus, for example, causes a sleep state detection unit to execute detection in a state suitable for detection of a sleep state without a noise source or, conversely, unsuitable for detection of a sleep state having a noise source. By controlling the sleep state detection unit so as to cause the sleep state detection unit to not perform detection or the like in an abnormal state, it is possible to further reduce the erroneous determination.

In another aspect, in the above-described sleep state detection device, whether the processing control unit outputs the sleep state detected by the sleep state detection unit according to the detection result of the noise source detection unit. Control.

Such a sleep state detection device outputs, for example, the sleep state obtained by the sleep state detection unit in a state suitable for detection of a sleep state without a noise source, or conversely, a sleep state with a noise source By controlling the sleep state processing unit so that the sleep state obtained by the sleep state detection unit is not output or the like in a state unsuitable for the detection of false detection can be further reduced.

In another aspect, in the above-described sleep state detection device, the processing control unit is configured to control the sleep state detected by the sleep state detection unit according to the detection result of the noise source detection unit. Control whether or not to assist with the detection result.

Such a sleep state detection apparatus outputs, for example, the sleep state obtained by the sleep state detection unit as it is in a state suitable for detection of a sleep state without a noise source or, conversely, sleep with a noise source It is determined by the sleep state detection unit such that information indicating that the state is unsuitable for the detection of the sleep state is added to the sleep state determined by the sleep state detection unit in a state unsuitable for the detection of the state. Since it becomes possible to assist the sleep state determined by the detection result of the noise source detection unit, it is possible to further reduce the erroneous determination.

In another aspect, in the above-described sleep state detection device, the sleep state detection unit determines a sleep state of the subject based on a first sensor that measures the subject and a first measurement result of the first sensor. And a sleep state processing unit for determining a sleep degree indicating the degree of depth of the subject's sleep, the sleep degree determination threshold set in advance, and the first measurement result of the first sensor. The processing control unit changes the sleep state determination threshold according to the detection result of the noise source detection unit as the control.

Such a sleep state detection device, for example, changes the sleep state determination threshold to a value for which the sleep state can be easily determined when there is no noise source and is a state suitable for detection of the sleep state, and conversely, noise In the case where there is a source and the state is unsuitable for detecting the sleep state, it is possible to change the sleep state determination threshold to a value for which it is difficult to determine the sleep state, and hence erroneous determination can be further reduced.

In another aspect, in the above-described sleep state detection device, the sleep state detection unit determines a sleep state of the subject based on a first sensor that measures the subject and a first measurement result of the first sensor. And a sleep state processing unit for obtaining a sleep level indicating the degree of the depth of the subject's sleep at a predetermined time interval set in advance, and the sleep level determination threshold set in advance. Temporarily determined as the sleep state by comparing with the first measurement result of the first sensor, and the temporarily determined sleep degree continues for a predetermined continuation determination time, the temporarily determined sleep degree The degree is determined as the final degree of sleep, and the processing control unit changes the continuation determination time according to the detection result of the noise source detection unit as the control.

Such a sleep state detection device is, for example, in the case where there is no noise source and is a state suitable for detection of a sleep state, the continuation determination time is changed to a value for which sleep state can be easily obtained. Since it is possible to change the continuation determination time or the like to a value for which it is difficult to determine the sleep state when there is an inappropriate state for detecting the sleep state, erroneous determination can be further reduced.

In another aspect, in the above-described sleep state detection device, the sleep state detection unit determines a sleep state of the subject based on a first sensor that measures the subject and a first measurement result of the first sensor. The first sensor includes a plurality of sub-sensors for measuring the subject, and the sleep-state processing unit is a sub-sensor of any one of the plurality of sub-sensors in the first sensor. The sleep state of the subject is determined based on the measurement result, and the process control unit determines, as the control, the sleep state processing unit from among the plurality of sub-sensors according to the detection result of the noise source detection unit. Change the sub-sensors used. Preferably, in the above-described sleep state detection device, the plurality of sub-sensors are different types of mutually different sensors.

Since such a sleep state detection device changes the sub sensor used in the sleep state processing unit among the plurality of sub sensors according to the detection result of the noise source detection unit, the noise among the plurality of sub sensors Since it becomes possible to select an appropriate sub-sensor used in the sleep state processing unit according to the detection result of the source detection unit, it is possible to further reduce the erroneous determination.

In another aspect, in the above-described sleep state detection device, the sleep state detection unit is a Doppler sensor that measures movement of a body surface of a chest accompanied by breathing in the subject, and a Doppler signal of the Doppler sensor. And a sleep state processing unit for determining a sleep state of the subject based on the Fourier transform of the Doppler signal measured by the Doppler sensor within a predetermined time set in advance. The average value of the amplitude in the frequency band corresponding to the respiratory frequency is determined from the spectrum obtained by the conversion, and the sleep state of the subject is determined based on the determined average value, and the processing control unit determines the control as: The bandwidth of the frequency band is changed according to the detection result of the noise source detection unit.

Such a sleep state detection device changes the bandwidth of the frequency band in accordance with the detection result of the noise source detection unit, so that erroneous determination can be further reduced.

In another aspect, in the above-described sleep state detection device, the target person is associated with schedule information representing a schedule of the subject including at least a clock unit for clocking a date, a year, a minute, and a sleep time zone. And a schedule information storage unit for storing the current information, and the processing control unit acquires the current time from the clock unit and extracts the schedule of the subject corresponding to the acquired current time from the schedule information storage unit. And controlling the sleep state detection unit according to the extracted target person's schedule and the detection result of the noise source detection unit.

Since such a sleep state detection device controls the sleep state detection unit according to the schedule of the subject and the detection result of the noise source detection unit, the schedule of the subject can be taken into consideration, and erroneous determination can be further reduced. .

In another aspect, in the above-described sleep state detection device, the sleep state detection unit is a narrow measurement range sensor having a predetermined first measurement range, and the target person based on a measurement result of the narrow measurement range sensor. And the noise source detection unit based on the measurement result of the wide measurement range sensor having the second measurement range wider than the first measurement range, and the wide measurement range sensor. And a noise source determination processing unit that determines the presence or absence of the noise source.

In such a sleep state detection device, since the sleep state detection unit includes the narrow measurement range sensor, the target person can be measured locally and locally, and the noise source detection unit includes the wide measurement range sensor. People's surroundings can be measured widely.

A sleep state detection method according to another aspect includes a sleep state detection step of detecting a sleep state of a subject, and a noise of detecting the presence or absence of a noise source generating noise with respect to the sleep state detected in the sleep state detection step. And a process control process of controlling the sleep state detection process according to the detection result of the noise source detection process.

Since such a sleep state detection method controls the sleep state detection step according to the detection result of the noise source detection step, for example, in a state suitable for detection of a sleep state without a noise source, the sleep state detection step Since it is possible to control so as not to find the sleep state of the subject in the sleep state detection step in the sleep state detection step while it is determined that the sleep state of the subject is determined while the sleep state is not suitable for detecting the sleep state. The state detection method can further reduce erroneous determinations.

The monitored person monitoring support system according to another aspect is provided corresponding to a target person, and a sensor device for determining a sleep state of the target person, and sleep that is communicably connected to the sensor device and received from the sensor device A central processing unit for managing the state; and a terminal device communicably connected to the central processing unit and receiving and displaying the sleep state via the central processing unit, the target person being the monitored person A monitored person monitoring support system for supporting monitoring of a monitored person, wherein the sensor device includes any one of the above-described sleep state detecting devices.

According to this, it is possible to provide a person-to-be-monitored support system using any of the above-described sleep state detection devices. Such a person-to-be-monitored support system uses any one of the above-described sleep state detection devices, so that it is possible to further reduce erroneous determinations.

This application is based on Japanese Patent Application No. 2017-155072 filed on Aug. 10, 2017, the contents of which are included in the present application.

Although embodiments of the present invention have been illustrated and described in detail, it is merely illustrative and not restrictive. The scope of the present invention should be interpreted by the terms of the appended claims.

While the present invention has been properly and sufficiently described above through the embodiments with reference to the drawings in order to express the present invention, those skilled in the art can easily change and / or improve the above embodiments. It should be recognized that it is possible. Therefore, unless a change or improvement implemented by a person skilled in the art is at a level that deviates from the scope of the claims set forth in the claims, the change or the improvement is the scope of the rights of the claim It is interpreted as being included in

According to the present invention, it is possible to provide a sleep state detection device and a sleep state detection method for detecting a sleep state, and a monitored person monitoring support system using this sleep state detection device.

Claims (12)

A sleep state detection unit that detects the sleep state of the subject;
A noise source detection unit that detects the presence or absence of a noise source that generates noise with respect to the sleep state detected by the sleep state detection unit;
A processing control unit that controls the sleep state detection unit according to the detection result of the noise source detection unit;
Sleep condition detection device. The process control unit controls whether or not the sleep state detection unit is to execute detection in accordance with the detection result of the noise source detection unit.
The sleep state detection device according to claim 1. The process control unit controls whether or not to output the sleep state detected by the sleep state detection unit according to the detection result of the noise source detection unit.
The sleep state detection device according to claim 1. The processing control unit controls whether or not the sleep state detected by the sleep state detection unit is assisted by the detection result of the noise source detection unit according to the detection result of the noise source detection unit.
The sleep state detection device according to claim 1. The sleep state detection unit includes a first sensor that measures a subject, and a sleep state processing unit that determines a sleep state of the subject based on a first measurement result of the first sensor.
The sleep state processing unit sets the sleep degree representing the degree of the depth of sleep of the subject as the sleep state by comparing the sleep degree determination threshold set in advance with the first measurement result of the first sensor. Ask for
The process control unit changes the sleep condition determination threshold according to the detection result of the noise source detection unit as the control.
The sleep state detection device according to claim 1. The sleep state detection unit includes a first sensor that measures a subject, and a sleep state processing unit that determines a sleep state of the subject based on a first measurement result of the first sensor.
The sleep state processing unit is configured to determine a sleep degree representing a degree of depth of sleep of the subject at a predetermined time interval set in advance, a sleep degree determination threshold set in advance, and a first measurement result of the first sensor And the temporally determined sleep degree is determined as the final sleep degree when the provisionally determined sleep degree is continuing for a preset continuation determination time. And
The process control unit changes the continuation determination time according to the detection result of the noise source detection unit as the control.
The sleep state detection device according to claim 1. The sleep state detection unit includes a first sensor that measures a subject, and a sleep state processing unit that determines a sleep state of the subject based on a first measurement result of the first sensor.
The first sensor includes a plurality of sub-sensors that measure a subject,
The sleep state processing unit determines a sleep state of the subject based on a sub measurement result of any one of a plurality of sub sensors in the first sensor;
The processing control unit changes, as the control, a sub-sensor used in the sleep state processing unit among the plurality of sub-sensors according to the detection result of the noise source detection unit.
The sleep state detection device according to claim 1. The sleep state detection unit is a Doppler sensor that measures the movement of the body surface of the chest associated with breathing in the subject, and a sleep state processing unit that obtains the sleep state of the subject based on the Doppler signal of the Doppler sensor Equipped with
The sleep state processing unit performs Fourier transform on the Doppler signal measured by the Doppler sensor within a predetermined time set in advance, and the spectrum obtained by the Fourier transform has an amplitude in a frequency band corresponding to a frequency of respiration. Determining an average value and determining a sleep state of the subject based on the determined average value;
The process control unit changes the bandwidth of the frequency band according to the detection result of the noise source detection unit as the control.
The sleep state detection device according to claim 1. Clock part which measures date and time, and
A schedule information storage unit which stores schedule information representing at least a schedule of the subject including a time zone of sleep in association with the subject;
The process control unit acquires the current time from the clock unit, extracts the schedule of the subject corresponding to the acquired current time from the schedule information storage unit, and the schedule of the extracted subject and Controlling the sleep state detection unit according to the detection result of the noise source detection unit;
The sleep state detection device according to any one of claims 1 to 8. The sleep state detection unit includes a narrow measurement range sensor having a predetermined first measurement range, and a sleep state processing unit that obtains the sleep state of the subject based on the measurement result of the narrow measurement range sensor.
The noise source detection processing unit determines the presence or absence of the noise source based on measurement results of a wide measurement range sensor having a second measurement range wider than the first measurement range, and the wide measurement range sensor. With
The sleep state detection device according to any one of claims 1 to 9. A sleep state detection step of detecting a sleep state of a subject;
A noise source detection step of detecting the presence or absence of a noise source generating noise with respect to the sleep state detected in the sleep state detection step;
Processing control step of controlling the sleep state detection step according to the detection result of the noise source detection step;
Sleep state detection method. A sensor device provided corresponding to a subject, for determining a sleep state of the subject, a central processing unit communicably connected to the sensor device, and managing a sleep state received from the sensor device, and the central processing unit A monitoring target for supporting the monitoring of the person to be monitored, the terminal being communicably connected to and receiving the sleep state via the central processing unit and displaying the sleep state; A support system,
The sensor device includes the sleep state detection device according to any one of claims 1 to 10.
Monitored person monitoring support system.

Images