WO2017183527A1

WO2017183527A1 - Subject monitoring device and method, and subject monitoring system

Info

Publication number: WO2017183527A1
Application number: PCT/JP2017/014919
Authority: WO
Inventors: 将積　直樹
Original assignee: コニカミノルタ株式会社
Priority date: 2016-04-19
Filing date: 2017-04-12
Publication date: 2017-10-26
Also published as: JPWO2017183527A1; JP7151480B2

Abstract

A subject monitoring device, subject monitoring method, and subject monitoring system according to the present invention: sense a prescribed event which relates to excretion by a subject who is a subject to be monitored, and derive a first excretion probability; measure a prescribed vital sign of the subject in time series, and derive a second excretion probability; on the basis of the first and second excretion probabilities, derive a final excretion probability of the subject; and issue a notification to the outside.

Description

Monitored person monitoring device, method and monitored person monitoring system

The present invention relates to a monitored person monitoring apparatus, a monitored person monitoring method, and a monitored person monitoring system for monitoring a monitored person as a monitoring target.

Japan (Japan) is an aging society, more specifically the ratio of population over 65 years old to the total population due to the improvement of living standards accompanying the post-war high economic growth, improvement of sanitary environment and improvement of medical standards, etc. It is a super-aging society with an aging rate exceeding 21%. In 2005, the total population was about 126.5 million, while the elderly population over the age of 65 was about 25.56 million. In 2020, the total population was about 124.11 million. There is also a prediction that the elderly population will be about 34.56 million. In such an aging society, nurses who need nursing or nursing care due to illness, injury, elderly age, etc., or those who need nursing care (such as those who require nursing care) are those who need nursing in a normal society that is not an aging society. This is expected to increase more than Japan, for example, is a society with a declining birthrate with a total fertility rate of 1.43 in 2013. For this reason, elderly care has been taking place in which elderly nurses, etc., are cared for by an elderly family (spouse, child, brother).

Employees requiring nursing care, etc. enter hospitals and facilities for welfare for the elderly (Japanese elderly law short-term entrance facilities, nursing homes for the elderly and special nursing homes for the elderly, etc.) and receive nursing and care. In such a facility, a situation in which a nurse or the like needs to be injured or fallen out of the bed, for example, by falling from the bed or falling while walking can occur. It is necessary to respond to such a situation as quickly as possible. Moreover, if such a situation is left unattended, it may develop into a more serious situation. For this reason, in the facility, nurses and caregivers regularly check their safety and state by patrol.

However, the increase in the number of nurses etc. cannot keep up with the increase in the number of nurses required, and the nursing industry and the care industry are chronically short of manpower. Furthermore, since the number of nurses, caregivers and the like is reduced in the semi-night shift and night shift hours compared to the day shift hours, the work load per person increases, and thus the work load is required to be reduced. In addition, the situation of the elderly care is not an exception in the facility, and it is often seen that elderly nurses and the like care for elderly nurses and the like. In general, physical strength declines when older, so the burden of nursing care becomes heavier than young nurses, etc., even if they are healthy, and their movements and judgments are also delayed.

In order to reduce the labor shortage and the burden on nurses, a technology that complements nursing work and nursing care work is required. For this reason, in recent years, monitored person monitoring techniques for monitoring a monitored person to be monitored, such as a care recipient, have been researched and developed.

As one of such techniques, for example, a safety management system disclosed in Patent Document 1 includes a central control device installed in a base station, a room connected to the central control device in a wired or wireless manner, and a separate room from the base station. A safety management system comprising a nurse call terminal installed in the at least one sensor attached to the bed in the other room for detecting that the care recipient is about to leave the bed An infrared CCD camera whose output is connected to the nurse call terminal and wired or wirelessly connected to the central control device and controlled by an input from the central control device. The central control unit is provided with means for displaying an image captured by the infrared CCD camera. That.

On the other hand, in terms of safety confirmation, a single person living alone is the same as the care recipient and the like and is a subject to be monitored.

By the way, the above-mentioned monitored person such as a nursing person has a risk of falling when he / she walks out of bed to perform excretion, for example, and may be injured if he / she falls. . For this reason, when a monitored person walks, a monitoring person such as a nurse or a caregiver often accompanies. In particular, when the monitored person is elderly, there is a high risk of falling when walking, and there is also a risk of falling or falling when leaving or getting in.

In the safety management system disclosed in Patent Document 1, the care recipient's action is automatically nursed when the care receiver (an example of the person being monitored) starts to move away from the bed. Since it can be grasped at the center, a nurse (an example of a supervisor) can run under the cared person. However, since the monitored person has already left the floor and walked when he rushed, there was a possibility that the attendance of the monitored person would not be in time for the falling of the monitored person.

JP 2000-105885 A

The present invention is an invention made in view of the above-described circumstances, and its object is to monitor a monitored person and a monitored person that can support advance rushing by predicting the excretion probability and notifying the monitoring person It is a method and to provide a monitored person monitoring system.

The monitored person monitoring apparatus, the monitored person monitoring method, and the monitored person monitoring system according to the present invention obtain a first excretion probability by detecting a predetermined event related to excretion of the monitored person who is a monitoring target, A second excretion probability is obtained by measuring a predetermined time-series biological signal in the monitored person, and the final excretion probability of the monitored person is obtained based on the first and second excretion probabilities and notified to the outside. . For this reason, the monitored person monitoring apparatus, the monitored person monitoring method, and the monitored person monitoring system according to the present invention can support advance rushing by predicting the excretion probability and notifying the monitoring person.

The above and other objects, features and advantages of the present invention will become apparent from the following detailed description and the accompanying drawings.

It is a figure which shows the structure of the to-be-monitored person monitoring system in embodiment. It is a figure which shows the structure of the sensor apparatus in the said to-be-monitored person monitoring system. It is a figure for demonstrating the arrangement | positioning aspect of the said sensor apparatus. It is a figure which shows the structure of the Doppler sensor part in the said sensor apparatus. It is a figure which shows the structure of the excretion event process part in the said sensor apparatus. It is a figure for demonstrating each detection of a bed leaving and entering a floor in the said sensor apparatus. It is a figure which shows the structure of the biosignal processing part in the said sensor apparatus. It is a figure which shows an example of a Doppler signal in the case of detecting a body movement, and its power spectrum. It is a figure which shows an example of a Doppler signal in the case of detecting respiration and its power spectrum. It is a figure which shows an example of a sensor noise signal and its power spectrum. It is a flowchart which shows the operation | movement which creates the excretion prediction model in the said sensor apparatus, and notifies a final excretion probability. It is a flowchart which shows the operation | movement which estimates and notifies the excretion in the said sensor apparatus.

Hereinafter, an embodiment according to the present invention will be described with reference to the drawings. In addition, the structure which attached | subjected the same code | symbol in each figure shows that it is the same structure, The description is abbreviate | omitted suitably. In this specification, when referring generically, it shows with the reference symbol which abbreviate | omitted the suffix, and when referring to an individual structure, it shows with the reference symbol which attached the suffix.

The monitored person monitoring system in the embodiment monitors a monitored person (watched person) Ob that is a monitored object (watched object) to be monitored (watched), and communicates with the terminal device and the terminal device. And a monitored person monitoring device for monitoring the monitored person Ob. In the present embodiment, the monitored person monitoring apparatus measures an excretion event detecting unit that detects a predetermined event related to excretion of the monitored person who is a monitoring target, and a time-series predetermined biological signal in the monitored person. A first excretion probability calculation unit that obtains, as a first excretion probability, a probability per unit time that the monitored person excretes based on a detection result of the excretion event detection unit; A second excretion probability calculating unit that obtains, as a second excretion probability, a probability per unit time that the monitored person excretes based on a measurement result of the biological signal measuring unit; and the first and second excretion probability calculations A final excretion probability calculating unit that obtains a probability per unit time that the monitored person excretes as a final excretion probability based on the first and second excretion probabilities determined by the unit; and the final excretion probability Calculated in the calculation unit And a notification processing unit for notifying the final excretion probability to the outside. Furthermore, in the present embodiment, the monitored person monitoring device includes a determination unit that determines whether or not the final excretion probability obtained by the final excretion probability calculation unit exceeds a predetermined threshold, and the notification process When the determination unit determines that the final excretion probability calculated by the final excretion probability calculation unit exceeds a predetermined threshold, the unit notifies the outside to that effect. The monitored person monitoring device may output a message indicating that the excretion probability or final excretion probability has exceeded a predetermined threshold to an output device provided in the own device. The terminal device is notified through a management server device that manages the entire supervisory monitoring system. In addition, although the said terminal device may be one type of apparatus, in this embodiment, the said terminal device is two types of apparatuses, a fixed terminal device and a portable terminal device. The main difference between these fixed terminal devices and portable terminal devices is that the fixed terminal device is fixedly operated, while the portable terminal device is operated by being carried by a supervisor (user) such as a nurse or a caregiver. The fixed terminal device and the mobile terminal device are substantially the same.

FIG. 1 is a diagram illustrating a configuration of a monitored person monitoring system according to the embodiment. FIG. 2 is a diagram showing a configuration of a sensor device in the monitored person monitoring system. FIG. 3 is a view for explaining an arrangement mode of the sensor device. FIG. 4 is a diagram illustrating a configuration of a Doppler sensor unit in the sensor device. FIG. 5 is a diagram illustrating a configuration of an excretion event processing unit in the sensor device. FIG. 6 is a diagram for explaining detection of getting out and entering the sensor device. 6A is a diagram for explaining detection of getting out of the bed, and FIG. 6B is a diagram for explaining detection of entering the floor. FIG. 7 is a diagram illustrating a configuration of a biological signal processing unit in the sensor device. FIG. 8 is a diagram illustrating an example of a Doppler signal and its power spectrum when body movement is detected. FIG. 9 is a diagram illustrating an example of a Doppler signal and its power spectrum when breathing is detected. FIG. 10 is a diagram illustrating an example of a sensor noise signal and its power spectrum. 8A, FIG. 9A, and FIG. 10A show Doppler signals in time space, the horizontal axis is time, and the vertical axis is output value (signal level, amplitude). 8B, FIG. 9B, and FIG. 10B show Doppler signals (power spectrum) in the frequency space, the horizontal axis is frequency, and the vertical axis is the power of each frequency component (amplitude of each frequency component). is there.

More specifically, the monitored person monitoring system MS in the embodiment includes, for example, as shown in FIG. 1, one or a plurality of sensor devices SU (SU-1 to SU-4), a management server device SV, A fixed terminal device SP, one or a plurality of portable terminal devices TA (TA-1, TA-2), and a private branch exchange (PBX) CX, which are wired or wireless, LAN (Local) It is connected to be communicable via a network (network, communication line) NW such as Area Network. The network NW may be provided with repeaters such as repeaters, bridges, and routers that relay communication signals. In the example shown in FIG. 1, the plurality of sensor devices SU-1 to SU-4, the management server device SV, the fixed terminal device SP, the plurality of portable terminal devices TA-1, TA-2, and the private branch exchange CX include an L2 switch. Are connected to each other by a wired / wireless LAN (for example, a LAN in accordance with the IEEE 802.11 standard) NW including the LS and the access point AP. More specifically, the plurality of sensor devices SU-1 to SU-4, the management server device SV, the fixed terminal device SP, and the private branch exchange CX are connected to the line concentrator LS, and the plurality of portable terminal devices TA-1, TA-2. Is connected to the line concentrator LS via the access point AP. The network NW constitutes a so-called intranet by using Internet protocol groups such as TCP (Transmission control protocol) and IP (Internet protocol).

The monitored person monitoring system MS is arranged at an appropriate place according to the monitored person Ob. The monitored person (person to be watched) 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, a single person living alone, or the like. In particular, from the viewpoint of enabling early detection and early action, the monitored person Ob may be a person who needs the detection when a predetermined inconvenient event such as an abnormal state occurs in the person. preferable. For this reason, the monitored person monitoring system MS is suitably arranged in a building such as a hospital, a welfare facility for the elderly, and a dwelling unit according to the type of the monitored person Ob. In the example illustrated in FIG. 1, the monitored person monitoring system MS is disposed in a building of a care facility that includes a plurality of living rooms RM in which a plurality of monitored persons Ob live and a plurality of living rooms such as a nurse station.

The sensor device SU has, for example, a communication function that communicates with other devices SV, SP, and TA via the network NW, monitors the monitored person Ob, and excretes the monitored person Ob. Is determined as the final excretion probability, notified to the outside, and when it is determined that the final excretion probability has exceeded a predetermined threshold value, the fact is notified to the outside. In the present embodiment, as described above, the sensor device SU notifies the terminal devices SP and TA via the monitoring server device SV. FIG. 1 shows four first to fourth sensor devices SU-1 to SU-4 as an example, and the first sensor device SU-1 is one of the monitored persons Ob. The second sensor device SU-2 is arranged in a room RM-2 (not shown) of Mr. B Ob-2 who is one of the monitored persons Ob. The third sensor device SU-3 is disposed in the room RM-3 (not shown) of Mr. C Ob-3, one of the monitored subjects Ob, and the fourth sensor device SU-4 It is arranged in the room RM-4 (not shown) of Mr. D Ob-4, one of the monitored persons Ob. Such a sensor device SU will be described in more detail later.

The management server device SV has a communication function for communicating with other devices SU, TA, SP via the network NW, and the final excretion probability or the final excretion probability exceeds a predetermined threshold value from the sensor device SU. If it is determined that it has been determined (excretion notice information), the final excretion probability and the excretion notice information are stored and recorded in association with the monitored person Ob, and the final excretion probability or The excretion notice information is notified (reported, notified, transmitted) to a predetermined terminal device SP, TA corresponding to the monitored person Ob, and data in response to a request from a client (terminal device SP, TA, etc. in this embodiment) Is provided to the client and manages the monitored person monitoring system MS as a whole.

More specifically, the management server device SV stores a notification destination correspondence and a communication address correspondence in advance. The notification destination correspondence relationship is a correspondence relationship between the notification source sensor device SU (sensor ID) and the notification destination terminal devices SP and TA (terminal ID). The communication address correspondence is a correspondence between each device SU, SP, TA (each ID) and its communication address. The sensor ID (sensor device identifier) is an identifier for identifying and identifying the sensor device SU. The terminal ID (terminal device identifier) is an identifier for identifying and identifying the terminal devices SP and TA. First, when the management server device SV receives a communication signal (first final excretion probability notification communication signal) that accommodates the final excretion probability, the notification source (transmission source) in the received first final excretion probability notification communication signal ) And the data such as the final excretion probability contained in the received first final excretion probability notification communication signal are stored (recorded) in association with each other. Then, the management server device SV identifies the notification destination terminal devices SP and TA corresponding to the notification source sensor device SU in the received first final excretion probability notification communication signal from the notification destination correspondence relationship, and this notification A communication signal (second final excretion probability notification communication signal) containing the sensor ID of the sensor device SU of the notification source (transmission source) and the final excretion probability is transmitted to the terminal devices SP and TA. Send. Further, when the management server device SV receives a communication signal (first excretion notice notification communication signal) containing the excretion notice information, the sensor device of the notification source (transmission source) in the received first excretion notice notification communication signal The SU (sensor ID) and the data such as the excretion notice information stored in the received first excretion notice notification communication signal are stored (recorded) in association with each other. Then, the management server device SV identifies the notification destination terminal devices SP and TA corresponding to the notification source sensor device SU in the received first excretion notice notification communication signal from the notification destination correspondence relationship, and this notification destination To the terminal devices SP and TA, a communication signal (second excretion notice notification communication signal) containing the sensor ID of the sensor device SU of the notification source (transmission source) and the excretion notice information is transmitted. The communication address is obtained from the communication address correspondence relationship.

Such a management server device SV can be configured by a computer with a communication function, for example.

The fixed terminal device SP includes a communication function for communicating with other devices SU, SV, TA via the network NW, a display function for displaying predetermined information, an input function for inputting predetermined instructions and data, and the like. Input predetermined instructions and data to be given to the management server device SV, the sensor device SU and the portable terminal device TA, display the final excretion probability obtained by the sensor device SU, and excretion obtained by the sensor device SU It is a device that functions as a user interface (UI) of the monitored person monitoring system MS by outputting the advance notice information or the like. Such a fixed terminal device SP can be configured by, for example, a computer with a communication function.

The mobile terminal device TA has a communication function for communicating with other devices SV, SP, SU via the network NW, a display function for displaying predetermined information, an input function for inputting predetermined instructions and data, and a voice call. It has a calling function to perform, and inputs a predetermined instruction or data to be given to the management server device SV or the sensor device SU, or displays a final excretion probability obtained by the sensor device SU by a notification from the management server device SV Or a device that functions as a user interface (UI) of the monitored person monitoring system MS by, for example, outputting excretion notice information obtained by the sensor device SU by a notification from the management server device SV. Such a portable terminal device TA can be configured by a portable communication terminal device such as a so-called tablet computer, a smartphone, or a mobile phone.

Next, the sensor device SU will be described in more detail. For example, as shown in FIG. 2, the sensor device SU includes an excretion event sensor unit 11, a biological signal sensor unit 12, a control processing unit 13, a storage unit 14, and a communication interface unit (communication IF unit) 15. With.

The communication IF unit 15 is a communication circuit that is connected to the control processing unit 13 and performs communication according to the control of the control processing unit 13. The communication IF unit 15 generates a communication signal containing data to be transferred input from the control processing unit 13 according to the communication protocol used in the network NW of the monitored person monitoring system MS, and generates the generated communication signal. It transmits to other devices SV, SP, TA via the network NW. The communication IF unit 15 receives a communication signal from another device SV, SP, TA via the network NW, extracts data from the received communication signal, and a format in which the control processing unit 13 can process the extracted data. And output to the control processing unit 13. The communication IF unit 15 includes, for example, a communication interface circuit that complies with the IEEE 802.11 standard or the like.

The excretion event sensor unit 11 is connected to the control processing unit 13, and acquires data for detecting a predetermined event related to the excretion of the monitored person Ob according to the control of the control processing unit 13. In the present embodiment, the predetermined event related to the excretion of the monitored person Ob is a bed leaving the monitored person from the bedding. In order to detect the bed leaving without contact, the excretion event sensor unit 11 performs control processing. The imaging unit 11 is connected to the unit 13 and generates an image (image data) by imaging according to the control of the control processing unit 13. An imaging unit 11 (an excretion event sensor unit and an imaging unit use the same reference numerals for convenience) as an example of the excretion event sensor unit 11 together with the biological signal sensor unit 12 as shown in FIG. A space where the person Ob is scheduled to be located (location space, in the example shown in FIG. 1, the room RM of the arrangement location) is arranged on the ceiling surface CE, for example, so that the location space can be imaged from above. Then, an image (image data) overlooking the imaging target is generated, and the imaging target image (target image) is output to the control processing unit 13. Preferably, since there is a high probability that the entire monitored person Ob can be imaged, the imaging unit 11 is expected to be located at the head of the monitored person Ob in a bedding (such as a bed) BD on which the monitored person Ob lies. It is arranged so that the imaging target can be imaged from directly above the preset planned head position (usually the pillow arrangement position).

Such an imaging unit 11 may be a device that generates an image of visible light, but in the present embodiment, it is a device that generates an infrared image so that the monitored person Ob can be monitored even in a relatively dark place. . For example, in this embodiment, the imaging unit 11 has an imaging optical system that forms an infrared optical image of an imaging target on a predetermined imaging surface, and a light receiving surface that matches the imaging surface. An image sensor that is arranged and converts an infrared optical image in the imaging target into an electrical signal, and image data that represents an infrared image in the imaging target by performing image processing on the output of the image sensor It is a digital infrared camera provided with the image processing part etc. which produce | generate. In the present embodiment, the imaging optical system of the imaging unit 11 is preferably a wide-angle optical system (so-called wide-angle lens (including a fisheye lens)) having an angle of view that can image the entire living room RM in which the imaging unit 11 is disposed. .

The biological signal sensor unit 12 is connected to the control processing unit 13 and acquires data for measuring a biological signal according to the control of the control processing unit 13. In the present embodiment, the biological signal sensor unit 12 includes a Doppler sensor unit 12 that is connected to the control processing unit 13 and that is controlled by the control processing unit 13 in order to perform measurement without contact. The Doppler sensor unit 12 (the biosignal sensor unit and the Doppler sensor unit use the same reference numerals for the sake of convenience) as an example of the biological signal sensor unit 12 transmits a transmission wave and reflects the transmission wave reflected by the object. A sensor that receives a reflected wave and outputs a Doppler signal having a Doppler frequency component based on the transmitted wave and the reflected wave. When the object is moving, the frequency of the reflected wave is shifted in proportion to the moving speed of the object due to the so-called Doppler effect. Arise. The Doppler sensor unit 12 generates a Doppler frequency component signal as a Doppler signal and outputs it. The transmission wave may be an ultrasonic wave, a microwave, or the like. In the present embodiment, the transmission wave is a microwave of 2.4 GHz to 24 GHz. Since microwaves can be transmitted through clothing and reflected from the body surface of the living body, the movement of the body surface can be detected even when the living body is wearing clothes, which is preferable. The Doppler sensor unit 12 is arranged as described above, for example, so as to transmit the transmission wave to the location space and receive the reflected wave from the space. The Doppler signal of the Doppler frequency component is output from the Doppler sensor unit 12 to the control processing unit 13.

More specifically, the Doppler sensor unit 12 includes, for example, a transmission unit 121, a transmission antenna 122, a reception antenna 123, a reception unit 124, and an analog / digital conversion unit (AD) as illustrated in FIG. Conversion unit) 125.

The transmission unit 121 is a circuit that generates a transmission wave of an electrical signal corresponding to a microwave, and includes a microwave oscillation circuit including a Gunn diode, an amplification circuit, and the like. The transmission antenna 122 is an antenna that is connected to the transmission unit 121, converts the transmission wave of the electric signal generated by the transmission unit 121 into a transmission wave of the microwave, and radiates the transmission wave of the microwave to the location space. . The transmission antenna 122 radiates a microwave transmission wave with a predetermined directivity characteristic (half-width of main lobe and transmission direction).

The receiving antenna 123 is an antenna that acquires a microwave from the location space and converts the microwave into an electric signal. The reception unit 124 is a circuit that is connected to the reception antenna 123 and generates a Doppler signal having a Doppler frequency component by signal processing from the electrical signal output from the reception antenna 123 and the transmission wave of the electrical signal. The receiving unit 124 may be a circuit that generates a 1-channel Doppler signal. However, in this embodiment, in order to detect with higher accuracy, for example, a quadrature phase detector is provided, and an I channel and a Q channel are provided. This is a circuit for generating two-channel Doppler signals (I channel data I (t) and Q channel data Q (t)). In the two-channel receiver 124, the Doppler frequency component Doppler signal Dp (t) is a complex signal of I (t) + i × Q (t) (Dp (t) = I (t) + i × Q ( t), i is an imaginary unit, i ² = −1). The AD conversion unit 125 is a circuit that is connected to the reception unit 124 and converts an analog Doppler signal into a digital Doppler signal by sampling and digitizing the analog Doppler signal at a predetermined sampling interval. The AD conversion unit 125 is connected to the control processing unit 13 and outputs the AD converted digital Doppler signals (I channel data I (t) and Q channel data Q (t)) to the control processing unit 13. In the example illustrated in FIG. 4, the AD conversion unit 125 is provided in the Doppler sensor unit 12, but may be provided in the control processing unit 13 instead.

The storage unit 14 is a circuit that is connected to the control processing unit 13 and stores various predetermined programs and various predetermined data under the control of the control processing unit 13. The various predetermined programs include, for example, an SU control program that controls each unit of the sensor device SU according to the function of each unit, and an output of the excretion event sensor unit (imaging unit in the present embodiment) 11. Based on the output of the excretion event processing program for executing a process for detecting a predetermined event related to the excretion of the monitored person Ob and the output of the biological signal sensor unit (Doppler sensor unit in this embodiment) 12, the biological signal of the monitored person Ob The first excretion that determines the probability per unit time that the monitored person Ob excites as the first excretion probability based on the detection result of the biological signal processing program that executes the process of extracting the excretion event and the excretion event processing program Probability per unit time that the monitored object Ob excretes based on the measurement result of the probability calculation program or the biological signal processing program When the second excretion probability calculation program obtained as the second excretion probability, a clock program for measuring time, or the event (in this embodiment, getting out of bed) is detected by the excretion event processing program, the current time is calculated from the clock program. The excretion time is acquired as the excretion time, and the acquired excretion time is associated with the monitored person Ob and recorded in the excretion time storage unit 141 described later, or the time series extracted by the biological signal processing program A predetermined biological signal is recorded in a biological signal storage unit 142 described later in association with the monitored person Ob, and the first and second excretion probability calculation programs obtained by the first and second excretion probability calculation programs. 2 Based on the excretion probability, the final excretion is determined as a final excretion probability that the monitored person Ob excretes. A probability calculation program, a notification processing program for notifying the final excretion probability calculated by the final excretion probability calculation program to the outside, or a final excretion probability determined by the final excretion probability calculation program exceeds a predetermined threshold A control processing program such as a determination program for determining whether or not has been included is included. The various kinds of predetermined data include data necessary for executing each program such as the sensor ID of the own device and the communication address of the management server device SV. The storage unit 14 includes, for example, a ROM (Read Only Memory) that is a nonvolatile storage element, an EEPROM (Electrically Erasable Programmable Read Only Memory) that is a rewritable nonvolatile storage element, and the like. The storage unit 14 includes a RAM (Random Access Memory) that serves as a working memory of a so-called control processing unit 13 that stores data generated during execution of the predetermined program. The storage unit 14 functionally includes an excretion time storage unit 141, a biological signal storage unit 142, a first excretion prediction model storage unit 143, and a second excretion prediction model storage unit 145.

The excretion time storage unit 141 stores the excretion time, which is the excretion time, in association with the monitored person Ob. The biological signal storage unit 142 stores the biological signal in association with the monitored person Ob. The first excretion prediction model storage unit 143 stores the first excretion prediction model generated as described later in association with the monitored person Ob. The second excretion prediction model storage unit 144 stores the second excretion prediction model generated as described later in association with the monitored person Ob.

The control processing unit 13 controls each unit of the sensor device SU according to the function of each unit, monitors the monitored person Ob, and excretes the monitored person Ob (for example, 15 minutes and 30 minutes). , 60 minutes, etc.) is determined as the final excretion probability, notified to the outside, and when it is determined that the final excretion probability has exceeded a predetermined threshold, that fact is notified to the outside It is a circuit for. The control processing unit 13 includes, for example, a CPU (Central Processing Unit) and its peripheral circuits. When the control processing program is executed, the control processing unit 13 includes a control unit 130, an excretion event processing unit 131, a biological signal processing unit 132, a first excretion probability calculating unit 133, a second excretion probability calculating unit 134, a clock Unit 135, excretion time recording processing unit 136, biological signal recording processing unit 137, final excretion probability calculating unit 138, determination unit 139, and notification processing unit 140.

The control unit 130 controls each unit of the sensor device SU according to the function of each unit, and controls the entire sensor device SU.

The excretion event processing unit 131 executes a process of detecting a predetermined event related to excretion of the monitored person Ob based on the output of the excretion event sensor unit (imaging unit in the present embodiment) 11. The predetermined event related to excretion may be excretion itself, but in the present embodiment, as described above, the person being monitored is getting out of bed. A monitored person who receives nursing or care by a nurse or a caregiver has a high possibility of going to the toilet for excretion as it is when leaving the bed. In particular, leaving at night is highly likely to be accompanied by excretion. In the present embodiment, as described above, bed leaving is detected without contact. For this reason, in order to detect bed leaving from an image (target image) generated by the imaging unit 11 which is an example of the excretion event sensor unit 11, the excretion event processing unit 131 is illustrated in FIG. As described above, the moving object detection unit 1311 and the behavior determination unit 1312 are functionally provided.

The moving object detection unit 1311 receives the target image generated by the imaging unit 11, and extracts a moving object region in the target image as a person region of the monitored person Ob based on the input target image. It is. More specifically, the moving object detection unit 1311 extracts a moving object region from the target image by, for example, a background difference method or a frame difference method. The moving object detection unit 1311 outputs the extracted moving object region to the action determination unit 1312.

The behavior determination unit 1312 detects the bed leaving by determining the behavior of the monitored person Ob based on the moving body region input from the moving body detection unit 1311, here, the presence or absence of the bed leaving. More specifically, in order to determine the presence or absence of getting out of the bed, first, the storage unit 14 stores in advance the location area of the bedding BD as one of the various predetermined data. Then, as shown in FIG. 6A, the behavior determination unit 1312 leaves the bed when the moving body region MOb input from the moving body detection unit 1311 changes in time from within the region where the bedding BD is located to outside the region where the bedding BD is located. Judge that there is, and detect getting out of bed. When the behavior determination unit 1312 detects getting out of bed, the behavior determination unit 1312 outputs the detection result to the excretion time recording processing unit 136. In addition, the action determination unit 1312 may be a precondition for determining the prior detection of entering the floor as getting out of bed. In this case, as shown in FIG. 6B, the behavior determination unit 1312, when the moving body region MOb input from the moving body detection unit 1311 changes in time from outside the region where the bedding BD is located to inside the region where the bedding BD is located. It is determined that there is an entry, and the entry is detected. Note that when the imaging unit 11 captures an image of the bedding BD obliquely from above or the like, the moving body region MOb and the bedding BD may overlap even if the monitored person Ob is getting out of bed. For this reason, when determining whether to leave the floor or to enter the floor, the temporal change in the area of the overlapping region where the moving body region MOb and the location area of the bedding BD overlap, or the ratio of the area of the overlapping region to the area of the moving body region MOb Time changes may be taken into account.

The biological signal processing unit 132 performs a process of extracting the biological signal of the monitored person Ob based on the output of the biological signal sensor unit (Doppler sensor unit in this embodiment) 12. More specifically, such a biological signal processing unit 132 functionally includes a signal cutout unit 1321 and a frequency analysis unit 1322 as shown in FIG.

The signal extraction unit 1321 receives a Doppler signal from the Doppler sensor unit 12. Since the Doppler signal input from the Doppler sensor unit 12 is a temporally continuous signal, the signal clipping unit 1321 performs the fast Fourier transform in the frequency analysis unit 1322 in the next stage. The Doppler signal input from is cut out with a predetermined time length and output to the frequency analysis unit 1322. The cutout method may be a cutout method in which the Doppler signal input from the Doppler sensor unit 12 is divided by a predetermined time length so that there is no overlapping portion between the cutout Doppler signals before and after the cutout. In order to improve the time resolution, the cut-out method is to divide by a predetermined time length so that the Doppler signals before and after the cut-out have overlapping portions.

The frequency analysis unit 1322 converts the time-space Doppler signal input from the signal cutout unit 1321 into a frequency-space Doppler signal (power spectrum). The frequency analysis unit 1322 outputs the Doppler signal in the frequency space to the biological signal recording processing unit 137. For the conversion from the time space to the frequency space, known conventional means are used. For example, a fast Fourier transform method (FFT (Fast Fourier Transform) method), a discrete Fourier transform method (DFT (Discrete Fourier Transform) method), A discrete cosine transform method (DCT (Discrete Cosine Transform) method), a wavelet transform method, or the like is used.

In the present embodiment, the frequency analysis unit 1322 converts the Doppler signal in the time space into a Doppler signal in the frequency space by a short-time Fourier transform method (STFT (Short-Time Fourier Transform) method) which is a known technique. In this STFT method, a time-space Doppler signal input from the Doppler sensor unit 12 is cut out by a signal cutout unit 1321 by a so-called window function for a predetermined time Doppler signal, and the Doppler signal of this predetermined time is output by a frequency analysis unit 1322. Fourier transform is performed to generate a Doppler signal (power spectrum) in the frequency space. Actually, since the Doppler signal is continuously input from the Doppler sensor unit 12 at the sampling interval of the AD conversion unit 125, the signal clipping unit 1321 and the frequency analysis unit 1322 are input from the Doppler sensor unit 12. The window functions are acted on while shifting the window functions in time, and each of them is Fourier transformed.

The Doppler sensor unit 12 can obtain Doppler signals due to various movements of the monitored person Ob, such as body movements and breathing movements, for example, so that the time-space Doppler signals and the frequency-space Doppler signals correspond to the Doppler signals. Have a profile.

For example, the body movement such as walking and turning over is a non-periodic movement with a relatively large movement because the movement of the slowly moving trunk and the movement of the limb moving fast are mixed. The Doppler signal corresponding to the body movement in which each part of the body performs various movements is a relatively wideband signal having a relatively large signal strength. In time space, for example, as shown in FIG. As shown in FIG. 8B, in the frequency space, the target amplitude is a relatively flat (flat) profile having no peak in a specific frequency component.

Also, for example, the movement of the breath appears as a vertical movement of the chest and becomes a periodic movement with a relatively small movement. In rest breathing, it is generally about 12 to 25 times / minute, and the chest moves up and down at about 0.2 Hz to 0.4 Hz. Such a Doppler signal corresponding to the movement of breathing is a relatively narrow band signal having a relatively small signal intensity. In time space, for example, as shown in FIG. The signal is a signal whose amplitude changes regularly, and in the frequency space, as shown in FIG. 9B, a profile has a peak at a specific frequency component (about 0.3 Hz in the example shown in FIG. 9B).

Further, when there is no moving object in the measurement target range of the Doppler sensor unit 12 due to absence of the monitored person Ob (including the case where the monitored person Ob stops breathing), sensor noise is generated from the Doppler sensor unit 12. Is output. This sensor noise is so-called thermal noise and becomes white noise. In the time space, for example, as shown in FIG. 10A, the sensor noise is a flat signal whose amplitude is relatively small and does not change much with time. In the frequency space, As shown in FIG. 10B, the profile is a relatively flat (flat) profile having no peak at a specific frequency component.

Referring back to FIG. 2, the clock unit 135 measures time. The clock unit 135 also has a calendar function for measuring the date.

The excretion time recording processing unit 136 acquires the current time (year / month / day) from the clock unit 135 as the excretion time when the excretion event processing unit 131 detects the event (the bed is regarded as excretion in the present embodiment). The acquired excretion time is recorded in the excretion time storage unit 141 in association with the monitored person Ob. The fact that the event (leaving from bed, excretion) occurred by recording the excretion time is also recorded in the excretion time storage unit 141.

The biological signal recording processing unit 137 receives a predetermined time-series biological signal measured by the biological signal sensor unit 12, in this embodiment, the Doppler signal in the frequency space obtained by the biological signal processing unit 132. Are recorded in the biological signal storage unit 142 in association with each other.

The first excretion probability calculating unit 133 obtains, as the first excretion probability, a predetermined per unit time probability that the monitored person Ob excretes based on the detection result of the excretion event processing unit 131. More specifically, the first excretion probability calculation unit 133 includes a plurality of sub time zones (first sub time zones) generated by dividing a predetermined time zone by a predetermined time length (first time length). The first excretion prediction model is generated by obtaining the first excretion probability based on the excretion time stored in the excretion time storage unit 141. The predetermined time zone may be arbitrary according to the excretion monitoring time zone, for example, a time zone of 24 hours a day, a time zone from 20 o'clock at night to 6 o'clock, and midnight to 4 o'clock. It is the time zone until the time. The predetermined time length may be any appropriate time length, such as 10 minutes, 15 minutes, and 30 minutes. In one example, 24 hours a day are divided every 15 minutes from 0:00, and 96 (= 4 × 24) sub-time zones are generated. Then, the sensor device SU is operated over a predetermined period, for example, one week, and the excretion time is stored in the excretion time storage unit 141. As a result, for example, when the excretion time is stored in the excretion time storage unit 141 in the sub time zone from 2 o'clock to 2:15, 5 times out of 7 days, the sub time from 2 o'clock to 2:15 The first excretion probability in the time zone is calculated as (excretion detection frequency) / (observation frequency) = 5 times / 7 days (7 times) = about 71%. Such calculation is performed for each of the 96 sub-time zones, and each first excretion probability is obtained for each of the 96 sub-time zones, and 96 of the sub-time zones and the first excretion probability is obtained. Each group is the first excretion prediction model.

Then, the first excretion probability calculating unit 133 stores the generated first excretion prediction model in the first excretion prediction model storage unit 143 in association with the monitored person Ob.

The second excretion probability calculating unit 134 obtains, as the second excretion probability, a predetermined probability per unit time that the monitored subject Ob excretes based on the processing result of the biological signal processing unit 132. More specifically, the second excretion probability calculation unit 134 uses the time-series predetermined biological signal stored in the biological signal storage unit as learning data to determine the second excretion prediction model. Is generated by learning. More specifically, a predetermined feature amount is generated as learning data for each of a plurality of second sub time periods generated by dividing the predetermined time period by a predetermined second time length. The predetermined second time length may be any appropriate time length, and may be the same as or different from the predetermined first time length. The predetermined feature amount is, for example, a plurality of Dopplers in a frequency space obtained in the small time period for each of a plurality of small time periods generated by dividing the second sub time period by a predetermined third time length. The average power Pave, the maximum power Pmax, the minimum power Pmin, the variance Pvar, the average breathing rate Bave, the maximum breathing rate Bmax, the minimum breathing rate Bmin, and the variance Bvar obtained from the signal. Therefore, the predetermined feature amount includes eight of the average power Pave, the maximum power Pmax, the minimum power Pmin, its variance Pvar, the average breath rate Bave, the maximum breath rate Bmax, the minimum breath rate Bmin, and its variance Bvar. The number is multiplied by the number of time zones. For example, the second sub-time zone of 30 minutes is divided into six first to sixth sub-time zones every 5 minutes, and for each of these first to sixth sub-time zones, the frequency obtained in the small time zone. The average power Pave, the maximum power Pmax, the minimum power Pmin, the variance Pvar, the average breathing rate Bave, the maximum breathing rate Bmax, the minimum breathing rate Bmin, and the variance Bvar obtained from a plurality of Doppler signals in space are obtained. 48 (= 8 × 6) in total. The power can be obtained by integrating the power spectrum, and the respiration rate can be obtained by counting the number of peaks per minute.

Then, the sensor device SU is operated for a predetermined period, for example, one week, and stores the Doppler signal in the frequency space in the biological signal storage unit 142. On the other hand, a supervisor such as a nurse or a caregiver assigns data indicating the presence or absence of excretion to each of the plurality of second sub-periods from a nursing record, a care record, etc., and stores it via the terminal devices SP and TA. Store in part 14. Then, the second excretion probability calculation unit 134 obtains each feature amount for each second sub-time zone for one week from the Doppler signal in the frequency space thus obtained, and stores the feature amount in these feature amounts. The supervised learning data is generated in association with the presence or absence of excretion stored in the memory, and the second excretion prediction model for obtaining the second excretion probability is generated by, for example, logistic regression analysis using the generated learning data .

Then, the second excretion probability calculating unit 134 stores the generated second excretion prediction model in the second excretion prediction model storage unit 144 in association with the monitored person Ob.

The final excretion probability calculating unit 138 is based on the first and second excretion probabilities calculated by the first and second excretion

probability calculating units

133 and 134, and the monitored person Ob excretes per predetermined unit time. The probability is obtained as the final excretion probability. The final excretion probability calculation unit 138 outputs the obtained final excretion probability to the determination unit 139 and the notification processing unit 140, respectively. More specifically, the final excretion probability calculating unit 138 uses the first excretion probability obtained from the first excretion prediction model and the second excretion prediction model for each of the plurality of sub time periods (first sub time periods). The final excretion probability is obtained by multiplying the obtained second excretion probability. When obtaining the second excretion probability from the second excretion prediction model, the feature amounts (average power Pave, maximum power Pmax, minimum power Pmin, and the like obtained from the Doppler signal of the frequency space acquired in the sub time zone are calculated. Variance Pvar, average respiration rate Bave, maximum respiration rate Bmax, minimum respiration rate Bmin, and its variance Bvar) are used. When the predetermined time zone is 24 hours a day and the data collection period is a plurality of days (the number of observations is a plurality of times), the frequency space acquired in the sub time zone (the first sub time zone) Since there are a plurality of feature amounts obtained from the Doppler signal, any one of the plurality of feature amounts, an average value of the plurality of feature amounts, or a median value of the plurality of feature amounts is obtained. It is used when determining the second excretion probability from the second excretion prediction model. For this reason, it is preferable that the 1st sub time slot | zone and the 2nd sub time slot | zone correspond.

The determination unit 139 determines whether or not the final excretion probability obtained by the final excretion probability calculation unit 138 exceeds a predetermined threshold th. As a result of the determination, when the final excretion probability does not exceed the predetermined threshold th, the determination unit 139 does nothing and the final excretion probability exceeds the predetermined threshold th. The determination unit 139 outputs to the notification processing unit 140 that the final excretion probability has exceeded a predetermined threshold th.

The notification processing unit 140 notifies the final excretion probability obtained by the final excretion probability calculating unit 138 to the outside. In the present embodiment, the notification processing unit 140 transmits the final excretion probability obtained by the final excretion probability calculating unit 138 to the predetermined terminal devices SP and TA via the management server device SV by the communication IF unit 15. More specifically, the notification processing unit 140 sends a communication signal (first final excretion probability notification communication signal) containing the sensor ID of its own device and the final excretion probability obtained by the final excretion probability calculating unit 138. The data is transmitted to the management server device SV by the communication IF unit 15. The management server device SV that has received the first final excretion probability notification communication signal searches for the terminal ID of the notification destination corresponding to the sensor ID accommodated therein, and to the terminal devices SP and TA having the searched terminal ID, The sensor ID accommodated in the received final excretion probability notification communication signal and the communication signal (second final excretion probability notification communication signal) accommodating the final excretion probability are transmitted. The management server device SV may transmit the sensor ID stored in the received final excretion probability notification communication signal and the communication signal containing the final excretion probability by broadcast communication.

When the determination unit 139 inputs that the final excretion probability exceeds a predetermined threshold th, the notification processing unit 140 externally indicates that the final excretion probability exceeds the predetermined threshold th. To notify. In the present embodiment, the notification processing unit 140 transmits the fact that the final excretion probability has exceeded a predetermined threshold th to the predetermined terminal devices SP and TA by the communication IF unit 15 via the management server device SV. More specifically, the notification processing unit 140 includes a communication signal (first excretion notice) containing its own sensor ID and excretion notice information indicating that the final excretion probability exceeds a predetermined threshold th. Notification communication signal) is transmitted to the management server device SV by the communication IF unit 15. The management server device SV that has received this first excretion notice communication signal searches for the terminal ID of the notification destination corresponding to the sensor ID accommodated therein, and sends this to the terminal devices SP and TA having the searched terminal ID. A communication signal (first excretion notice notification communication signal) containing the sensor ID and excretion notice information contained in the received first excretion notice notification communication signal is transmitted.

In the present embodiment, the excretion event sensor unit 11 and the excretion event processing unit 131 correspond to an example of an excretion event detection unit that detects a predetermined event related to excretion of the monitored person, and the biosignal sensor unit 12 and the biosignal processing. The unit 132 corresponds to an example of a biological signal measurement unit that measures a predetermined time-series biological signal in the monitored person.

Next, the operation of this embodiment will be described. FIG. 11 is a flowchart showing an operation of creating an excretion prediction model in the sensor device and notifying the final excretion probability. FIG. 12 is a flowchart showing an operation of predicting and notifying excretion in the sensor device.

In the monitored person monitoring system MS having the above-described configuration, each device SU, SV, SP, TA performs initialization of each necessary part and starts its operation when the power is turned on. In the sensor device SU, by executing the control processing program, the control processing unit 13 includes the control unit 130, the excretion event processing unit 131, the biological signal processing unit 132, the first excretion probability calculating unit 133, and the second excretion probability calculating unit. 134, a clock unit 135, an excretion time recording processing unit 136, a biological signal recording processing unit 137, a final excretion probability calculating unit 138, a determination unit 139, and a notification processing unit 140 are functionally configured.

In the monitored person monitoring system MS in the present embodiment, an initial mode for creating the first and second excretion prediction models and notifying the final excretion probability, and an excretion notice mode for performing the excretion notice using the final excretion probability There is. Hereinafter, these will be described sequentially.

(Initial mode)
In the initial mode, in FIG. 11, first, the sensor device SU acquires and stores each data by the control processing unit 13 (S11). More specifically, the sensor device SU acquires an image from the imaging unit 11 as an example of the excretion event sensor unit 11, and the excretion event processing unit 131 performs the above-described event (book) based on the image (target image). In the embodiment, when the above event is detected, the excretion time recording processing unit 136 acquires the current time as the excretion time from the clock unit 135, and stores the acquired excretion time in the excretion time storage unit 141. To do. The sensor device SU acquires a Doppler signal from the Doppler sensor unit 12 as an example of the biological signal sensor unit 12, generates a Doppler signal in the frequency space by the biological signal processing unit 132, and generates the generated Doppler signal in the frequency space. This is stored in the biological signal storage unit 142. At this time, a monitor such as a nurse or a caregiver assigns data indicating the presence or absence of excretion to each of the plurality of second sub-periods from a nursing record or a care record, and the terminal devices SP, TA Is stored in the storage unit 14.

Next, the sensor device SU determines whether or not a preset data collection period (for example, 1 week, 10 days, 2 weeks, etc.) has ended since the start of acquisition of each data by the control processing unit 13 ( S12). If the result of this determination is that the data collection period has not ended (No), the sensor device SU returns the process to step S11 by the control processing unit 13, while the data collection period has ended ( In Yes), the sensor device SU performs the next processing S13 by the control processing unit 13. That is, each data is collected and stored until the data collection period ends.

In the process S13, the sensor device SU generates a first excretion prediction model by using each data acquired and stored in the process S11 and the process S12 by the first excretion probability calculation unit 133 of the control processing unit 13. The generated first excretion prediction model is stored in the first excretion prediction model storage unit 143.

Next, the sensor device SU generates a second excretion prediction model by using each data acquired and stored in the processing S11 and the processing S12 by the second excretion probability calculation unit 134 of the control processing unit 13, The generated second excretion prediction model is stored in the second excretion prediction model storage unit 144 (S14).

Next, the sensor device SU uses the final excretion probability calculating unit 138 of the control processing unit 13 based on the first and second excretion probabilities obtained by the first and second excretion

probability calculating units

133 and 134 to The probability per unit time that the monitor Ob excretes is obtained as the final excretion probability (S16).

Next, the sensor device SU notifies the final excretion probability obtained in step S15 to the outside by the notification processing unit 139 of the control processing unit 13 (S17), and ends the process. In the present embodiment, the notification processing unit 139 transmits the first final excretion probability notification communication signal containing the sensor ID and the final excretion probability to the management server device SV via the communication IF unit 15. The management server device SV that has received the first final excretion probability notification communication signal searches for the terminal ID of the notification destination corresponding to the sensor ID accommodated therein, and to the terminal devices SP and TA having the searched terminal ID, The sensor terminal ID contained in the received first final excretion probability notification communication signal and the second final excretion probability notification communication signal containing the final excretion probability are transmitted. The terminal devices SP and TA that have received the second final excretion probability notification communication signal display the final excretion probability accommodated in the received second final excretion probability notification communication signal in association with the monitored person Ob. To do. For example, the final excretion probabilities are displayed sequentially for each first sub-time period. That is, the first excretion prediction model is displayed. Note that the correspondence between the sensor ID and the name of the monitored person Ob is stored in advance in the terminal devices SP and TA.

In the initial mode, the monitored person monitoring system MS operates in this way.

(Excretion notice mode)
In the excretion notice mode, each data is acquired and recorded by a process similar to the process S11 shown in FIG. 11 at a predetermined time interval (sampling interval) set in advance, while each process shown in FIG. 12 is preset. It is repeatedly executed at a predetermined time interval (for example, 1 second).

In FIG. 12, first, the sensor device SU acquires the current time from the clock unit 135 by the first and second excretion

probability calculation units

133 and 134 of the control processing unit 13 (S21).

Next, the sensor device SU uses the first excretion probability calculation unit 133 to obtain the first excretion probability corresponding to the current time from the first excretion prediction model (S22).

Next, the sensor device SU uses the second excretion probability calculation unit 134 to obtain the second excretion probability corresponding to the current time from the second excretion prediction model (S23). For example, the second excretion probability calculation unit 134 calculates feature amounts (described above) from a plurality of Doppler signals in the frequency space stored in the biological signal storage unit 142 from the current time to a time that is traced back in the past by the second time length. In the example, the average power Pave, the maximum power Pmax, the minimum power Pmin, the variance Pvar, the average breathing rate Bave, the maximum breathing rate Bmax, the minimum breathing rate Bmin, and the variance Bvar are obtained in total 48), and the obtained feature amount Is used in the second excretion prediction model to determine the second excretion probability.

Next, the sensor device SU obtains a final excretion probability based on the first excretion probability obtained in the process S22 and the second excretion probability obtained in the process S23 by the final excretion probability calculating unit 138 (S25). For example, the final excretion probability calculating unit 138 obtains the final excretion probability by multiplying the first excretion probability obtained in step S22 and the second excretion probability obtained in step S23.

Next, the sensor device SU determines whether or not the final excretion probability obtained by the final excretion probability calculation unit 138 in the process S25 exceeds a predetermined threshold th by the determination unit 139 (S26). As a result of this determination, if the final excretion probability does not exceed the predetermined threshold th, the sensor device SU ends the current process, while the final excretion probability exceeds the predetermined threshold th. If it exceeds, the sensor apparatus SU ends the current process after executing the next process S27.

In this process S27, the sensor device SU notifies the outside that the final excretion probability has exceeded a predetermined threshold th by the notification processing unit 140. In this embodiment, the notification processing unit 139 transmits the first excretion notice notification communication signal containing the sensor ID and the excretion notice information to the management server device SV through the communication IF unit 15. The management server device SV that has received the first excretion notice notification communication signal searches the terminal ID of the notification destination corresponding to the sensor ID accommodated therein, and sends this to the terminal devices SP and TA having the searched terminal ID. A second excretion notice notification communication signal containing the sensor ID and excretion notice information contained in the received first excretion notice notification signal is transmitted. The terminal devices SP and TA that have received the second excretion notice notification communication signal sound a predetermined warning sound. In place of or in addition to the warning sound, the terminal devices SP and TA may display a message indicating the excretion notice in association with the monitored person Ob. Further, the terminal devices SP and TA may output a predetermined vibration instead of or in addition to the warning sound, or in addition to or in addition to the display.

In the excretion notice mode, the monitored person monitoring system MS operates in this way.

As described above, the monitored person monitoring system MS, the sensor apparatus SU which is an example of the monitored person monitoring apparatus, and the monitored person monitoring method implemented therein are the first excretion of the monitored person Ob. The probability is obtained, the second excretion probability of the monitored person Ob is obtained, and the final excretion probability of the monitored person Ob is obtained based on the first and second excretion probabilities and notified to the outside. Therefore, since the monitor can predict the excretion by referring to the final excretion probability of the monitored person Ob, the monitored person monitoring system MS, the sensor device SU, and the monitored person monitoring method are rushed in advance. Can support. Therefore, the risk of falling of the monitored person Ob can be reduced.

Since the monitored person monitoring system MS, the sensor device SU, and the monitored person monitoring method obtain the final excretion probability based on the first and second excretion probabilities obtained by two methods, more accurate. The excretion probability can be obtained.

Especially in the case of elderly people who live in facilities, the time of meals and bedtime are determined to some extent and have periodicity in order to have a stable life. Accordingly, the timing of excretion and the bed movement for that purpose have periodicity. Also, before excretion, there is some body movement such as unconsciously feeling uncomfortable, becoming sleepless and increasing the number of turns. In particular, this tendency tends to appear during nighttime sleeping. The monitored person monitoring system MS, the sensor device SU, and the monitored person monitoring method obtain the first excretion probability based on the detection result of the excretion event processing unit 131, and the second based on the processing result of the biological signal processing unit 132. Since the excretion probability is obtained and these are integrated to obtain the final excretion probability, the excretion probability can be obtained with high accuracy.

For elderly people who are excreted in diapers 24 hours a day when they are bedridden, exchanging diapers after excretion is a heavy work burden for nurses and caregivers. Therefore, there is a desire to know the timing of changing diapers before excretion. For example, Japanese Patent Application Laid-Open No. 2001-161732 discloses a device for detecting the timing of changing diapers. However, since the device is installed in the diaper, it is necessary for the elderly to feel uncomfortable or to change it every time the diaper is changed. Convenience is not good. However, the monitored person monitoring system MS, the sensor device SU, and the monitored person monitoring method do not require a separate device in the diaper and are easy to use.

The monitored person monitoring system MS, the sensor device SU, and the monitored person monitoring method perform a predetermined notification to the outside when the final excretion probability exceeds a predetermined threshold th. For this reason, by referring to this notification, the monitor can recognize that the monitored person Ob is near excretion. And since the supervisor can run under the monitored person Ob before the monitored person Ob actually leaves, the risk of falling can be reduced.

The monitored person monitoring system MS, the sensor device SU, and the monitored person monitoring method can easily detect the event by regarding getting out of bed as the event.

Since the monitored person monitoring system MS, the sensor device SU, and the monitored person monitoring method detect getting out of bed from the image, it is possible to detect the getting-off of the monitored person Ob without contacting the monitored person Ob and thus the event.

In the monitored person monitoring system MS, the sensor device SU, and the monitored person monitoring method, the biological signal of the monitored person Ob is measured by the Doppler sensor unit 12, so that the biological signal can be measured without contact with the monitored person Ob. .

In the above-described embodiment, when there is an actual excretion in the monitored person Ob during the excretion notice mode, a monitor such as a nurse or a caregiver can set the excretion time and the terminal device SP, TA. Data indicating the presence or absence of excretion is input and transmitted to the sensor device SU via the management server device SV. The sensor device SU stores data representing the excretion time and presence / absence of excretion received from the terminal devices SP and TA via the management server device SV in the storage unit 14. Then, the sensor device SU adds the data obtained during the execution of the excretion notice mode to each data of the initial mode at every predetermined time interval or according to an instruction from a monitor or the like, and creates the first excretion prediction model. Recalculate, update the learning data by adding the data obtained during the implementation of the excretion notice mode to each data in the initial mode, and re-learn and update the second excretion prediction model with this updated learning data. Also good. This can further improve the accuracy of the first and second excretion prediction models.

In such a case, the sensor device SU as an example of the monitored person monitoring device described above further includes an excretion receiving unit that receives an input of the excretion time, and the biological signal storage unit 142 further receives the excretion receiving unit. The excretion time is recorded in the excretion time storage unit 141 in association with the monitored person Ob, and the learning data is generated by dividing the predetermined time zone by a predetermined second time length. The first excretion probability calculating unit 133 regenerates the first excretion prediction model based on the excretion time stored in the excretion time storage unit 141 and includes the second excretion probability calculation unit 134. Generates excretion presence / absence data indicating the presence / absence of excretion for each of the plurality of second sub-periods based on the excretion time stored in the excretion time storage unit 141, and the generation Supervised learning data is generated by adding the excretion data to each data corresponding to each of the plurality of second sub-time zones in the learning data, and the second supervised learning data is used to generate the second supervised learning data. Regenerate the excretion prediction model by re-learning. In the present embodiment, the excretion time is input to the terminal device SP, TA by a monitor such as a nurse or a caregiver, and is input from the terminal device SP, TA to the sensor device SU via the management server device SV. The communication IF unit 15 corresponds to an example of an excretion receiving unit that receives an input of excretion time. The sensor device SU is further connected to the control processing unit 13 as necessary, for example, an input unit for inputting various commands, various data, and the like, and various commands and various data input by the input unit. An output unit may be further provided, and the excretion time may be input from the input unit.

Further, in the above-described embodiment, the final excretion probability is obtained based on the first and second excretion probabilities, but the final excretion probability may be further obtained based on the third excretion probability. In such a case, in the sensor device SU as an example of the monitored person monitoring device described above, as shown by a broken line in FIG. 2, the third excretion prediction model in which the excretion probability increases as time elapses from the excretion time. A third excretion probability calculating unit 21 for obtaining three excretion probabilities is further provided functionally in the control processing unit 13, and a final excretion probability calculating unit 138 is obtained by each of the first to third excretion

probability calculating units

133, 134, and 21, respectively. The final excretion probability is obtained based on the obtained first to third excretion probabilities. More specifically, for example, the final excretion probability calculation unit 138 multiplies the first to third excretion probabilities obtained by the first to third excretion

probability calculation units

133, 134, and 21, respectively, thereby multiplying the final excretion probability. Find the excretion probability. The memory | storage part 14 is further equipped with the 3rd excretion prediction model memory | storage part 22 which memorize | stores a 3rd excretion prediction model functionally, as shown with a broken line in FIG. In the flowchart shown in FIG. 11, a process S15 for generating a third excretion prediction model and storing it in the third excretion prediction model storage unit 22 is further added between the process S14 and the process S16, as indicated by a broken line. . In the flowchart shown in FIG. 12, a process S24 for obtaining a third excretion probability is further added between the processes S23 and S25 as shown by a broken line. The third excretion prediction model may be a table or a function expression generated by using a plurality of samples in advance, or may be a learning model generated by using learning data. According to this, since the final excretion probability is obtained based on the third excretion probability in addition to the first and second excretion probabilities, the final excretion probability with higher accuracy can be obtained.

In the above-described embodiment, the excretion event sensor unit 11 includes the imaging unit 11, and the excretion event processing unit 131 detects the bed leaving as excretion, but the excretion event detection unit is not limited thereto. For example, a leaving mat disposed in an area around the bedding or a place where the user leaves the bed may be used. The bed leaving mat is provided with, for example, a pressure-sensitive sensor, and the monitored person Ob detects the bed leaving the monitored person Ob when the monitored person Ob rides on the bed leaving mat. In addition, for example, a seating sensor that detects seating may be used. The seating sensor includes, for example, a pressure sensor, and when the monitored person Ob rides on the seating sensor, the seating of the monitored person Ob is detected by the pressure sensor. In the case of using this seating sensor, it is possible to cope with the risk of walking to bed after excretion. Such a floor mat or seating sensor is connected to the control processing unit 13 of the sensor device SU so as to be communicable by wire or wirelessly.

In the above-described embodiment, the feature amounts are the average power Pave, the maximum power Pmax, the minimum power Pmin, the variance Pvar, the average respiratory rate Bave, the maximum respiratory rate Bmax, the minimum respiratory rate Bmin, and the variance Bvar. However, the present invention is not limited to this. For example, in addition to these, the amount of intake water and the amount of meals may be used. In such a case, in the sensor device SU as an example of the monitored person monitoring device described above, preferably, an intake water reception unit that receives an input of an intake water amount associated with an intake time, and the intake water reception unit An intake water storage unit that stores the intake water amount associated with the received intake time in association with the monitored person Ob, and the learning data includes the predetermined time zone for a predetermined second time period. Data is provided for each of the plurality of second sub-periods generated by dividing by the length, and the second excretion probability calculation unit 134 corresponds to the intake time stored in the intake water storage unit in the learning data. Learning the second excretion prediction model by adding the intake water amount associated with the intake time to the data of the second sub-time period and using the added learning data Therefore, to produce. In the sensor device SU as an example of the monitored person monitoring device described above, preferably, a meal amount receiving unit that receives an input of a meal amount associated with a meal time, and the meal received by the meal amount receiving unit A meal amount storage unit that stores a meal amount associated with time in association with the monitored person Ob, and the learning data is obtained by dividing the predetermined time period by a predetermined second time length. Each of the plurality of generated second sub-time zones includes data, and the second excretion probability calculating unit 134 is a second sub-time zone corresponding to the meal time stored in the meal amount storage unit in the learning data. The second excretion prediction model is generated by learning by adding the amount of meal associated with the meal time to the data and using the added learning data. In the sensor device SU as an example of the monitored person monitoring device described above, preferably, a water intake receiving unit that receives an input of an intake water amount associated with the intake time, and a meal amount associated with the meal time The intake amount storage unit that receives the input of the intake amount, the intake amount storage unit that stores the intake amount of water associated with the intake time, which is received by the intake amount reception unit, in association with the monitored person Ob, and the meal amount A meal amount storage unit that is received by the reception unit and stores a meal amount associated with a meal time in association with the monitored person Ob, and the learning data includes the predetermined time period in a predetermined number of times; Data is provided for each of the plurality of second sub-periods generated by dividing by a two-hour length, and the second excretion probability calculation unit 134 stores the intake water storage unit in the learning data. The intake water amount associated with the intake time is added to the data of the second sub time period corresponding to the remembered intake time, and the meal time corresponding to the meal time stored in the meal amount storage unit in the learning data is added. The second excretion prediction model is generated by learning by adding the amount of meal associated with the meal time to the data of the second sub-time period and using the added learning data.

The intake water amount associated with the intake time and the meal amount associated with the meal time are input to the terminal devices SP and TA by a monitor such as a nurse or a caregiver, and the terminal devices SP and TA To the sensor device SU via the management server device SV. The communication IF unit 15 corresponds to an example of an intake water reception unit, and also corresponds to an example of a meal amount reception unit. As shown by a broken line in FIG. 2, the storage unit 14 further includes a water intake storage unit 31 and a meal amount storage unit 32 in terms of function.

In the above-described embodiment, the final excretion probability is notified to the outside in the process S17 of the initial mode. In addition, the sensor device SU has the predetermined excretion probability set to a predetermined threshold th. It may be determined whether or not it has been exceeded, and the determination result may be notified to the outside. When displaying the final excretion probability, the final excretion probability is displayed in a different display mode depending on whether or not the predetermined threshold th is exceeded. For example, the final excretion probability exceeding the predetermined threshold th is displayed in red or yellow, and the final excretion probability not exceeding the predetermined threshold th is displayed in blue or green.

Further, in the above-described embodiment, in the process S27 of the excretion notice mode, the fact that the final excretion probability has exceeded a predetermined threshold th is notified to the outside. In addition, the sensor device SU The final excretion probability may also be notified to the outside. Then, when displaying that the final excretion probability exceeds a predetermined threshold th, the final excretion probability is displayed.

In the above-described embodiment, the monitored person monitoring device is configured by the sensor device SU, but may be configured by the sensor device SU and the management server device SV. In such a case, in one example, the sensor device SU includes the excretion event sensor unit 11 and the biological signal sensor unit 12, and the management server device SV includes the excretion event processing unit 131, the biological signal processing unit 132, and the first excretion probability calculation. Unit 133, second excretion probability calculating unit 134, clock unit 135, excretion time recording processing unit 136, biological signal recording processing unit 137, final excretion probability calculating unit 138, determination unit 139, notification processing unit 140, excretion time storage unit 141 The biological signal storage unit 142, the first excretion prediction model storage unit 143, and the first excretion prediction model storage unit 144 are configured.

This specification discloses various modes of technology as described above, and the main technologies are summarized below.

A monitored person monitoring apparatus according to one aspect includes an excretion event detecting unit that detects a predetermined event related to excretion of a monitored person that is a monitoring target, and a living body that measures a time-series predetermined biological signal in the monitored person. A first excretion probability calculating unit that obtains, as a first excretion probability, a probability per unit time that the monitored person excretes based on a detection result of the signal measurement unit, the excretion event detection unit, and the biological signal A second excretion probability calculation unit that obtains a probability per unit time that the monitored person excretes as a second excretion probability based on the measurement result of the measurement unit; and the first and second excretion probability calculation units A final excretion probability calculating unit that obtains a probability per unit time that the monitored person excretes as a final excretion probability based on the obtained first and second excretion probabilities; and the final excretion probability calculating unit Sought in And a notification processing unit for notifying a final specific excretion probability to the outside. Preferably, in the above-mentioned monitored person monitoring device, when the event is detected by the clock unit that performs timing, the excretion time storage unit that stores the excretion time that is the time of excretion, and the excretion event detection unit An excretion time recording processing unit that acquires the current time from the clock unit as the excretion time, and records the acquired excretion time in the excretion time storage unit in association with the monitored person; A biological signal storage unit that stores a biological signal of the biological signal, and a biological signal recording processing unit that records a predetermined time-series biological signal measured by the biological signal measurement unit in the biological signal storage unit in association with the monitored person The first excretion probability calculating unit further includes a plurality of sub time zones (first sub time zones) generated by dividing a predetermined time zone by a predetermined time length (first time length). , At the time of excretion A first excretion prediction model is generated by obtaining the first excretion probability based on the excretion time stored in the storage unit, and the second excretion probability calculation unit is a time series stored in the biological signal storage unit. By using a predetermined biological signal as learning data, a second excretion prediction model for obtaining the second excretion probability is generated by learning, and the final excretion probability calculating unit is configured by each of the first and second excretion probability calculating units. The final excretion probability is obtained based on the first and second excretion probabilities obtained from the generated first and second excretion prediction models, respectively. Preferably, the above-described monitored person monitoring device further includes an excretion receiving unit that receives an input of the excretion time, and the biological signal storage unit further outputs the excretion time received by the excretion receiving unit to the monitored person. In association with the excretion time storage unit, the learning data includes data for each of a plurality of second sub time periods generated by dividing the predetermined time period by a predetermined second time length, The first excretion probability calculation unit regenerates the first excretion prediction model based on the excretion time stored in the excretion time storage unit, and the second excretion probability calculation unit stores in the excretion time storage unit. Based on the excretion time generated, excretion presence / absence data representing the presence / absence of excretion is generated for each of the plurality of second sub time periods, and the generated excretion presence / absence data is Supervised generates learning data by adding to each data corresponding to each of the plurality of bands second sub time regenerates by relearning the second excretion prediction model by using supervised learning data to said generating. Preferably, in the above-described monitored person monitoring apparatus, an intake water reception unit that receives an input of an intake water amount associated with an intake time, and an intake water that is received by the intake water reception unit and that is associated with an intake time An intake water storage unit that stores the amount in association with the monitored person, and the learning data is generated by dividing the predetermined time period by a predetermined second time length. Data is provided for each time zone, and the second excretion probability calculation unit adds the second sub-time zone data corresponding to the intake time stored in the intake water storage unit in the learning data to the intake time. The second excretion prediction model is generated by learning by adding the associated intake water amount and using the added learning data. Preferably, in the above-described monitored person monitoring device, a meal amount receiving unit that receives an input of a meal amount associated with a meal time, and a meal amount associated with the meal time received by the meal amount reception unit A meal amount storage unit that stores the data in association with the monitored person Ob, and the learning data includes a plurality of second sub-times generated by dividing the predetermined time period by a predetermined second time length. Data is provided for each band, and the second excretion probability calculation unit corresponds to the meal time in the second sub-time data corresponding to the meal time stored in the meal amount storage unit in the learning data. The added excretion amount is added and the second excretion prediction model is generated by learning by using the added learning data. Preferably, in the above-described monitored person monitoring apparatus, an intake water reception unit that receives an input of an intake water amount associated with intake time, and a meal amount reception unit that receives an input of a meal amount associated with meal time The intake water storage unit that is received by the intake water reception unit and that stores the intake water amount associated with the intake time in association with the monitored person Ob, and the meal time that is received by the meal amount reception unit A meal amount storage unit that stores the associated meal amount in association with the monitored person Ob, and the learning data is generated by dividing the predetermined time period by a predetermined second time length. Each of the plurality of second sub-periods includes data, and the second excretion probability calculating unit includes a second sub-corresponding to the intake time stored in the intake water storage unit in the learning data. The intake water amount associated with the intake time is added to the data of the interval, and the meal is added to the data of the second sub time zone corresponding to the meal time stored in the meal amount storage unit in the learning data. The second excretion prediction model is generated by learning by adding a meal amount associated with time and using the added learning data.

Such a monitored person monitoring device obtains the first excretion probability of the monitored person, obtains the second excretion probability of the monitored person, and based on the first and second excretion probabilities, the final of the monitored person. To determine the probability of excretion and notify the outside. Therefore, since the monitor can predict the excretion by referring to the final excretion probability of the monitored person, the monitored person monitoring apparatus can support advance rushing. Since the monitored person monitoring device obtains the final excretion probability based on the first and second excretion probabilities obtained by two methods, the excretion probability with higher accuracy can be obtained.

In another aspect, in the above-described monitored person monitoring apparatus, a determination unit that determines whether or not a final excretion probability obtained by the final excretion probability calculation unit exceeds a predetermined threshold, and the notification processing unit When it is determined by the determination unit that the final excretion probability obtained by the final excretion probability calculation unit has exceeded a predetermined threshold, a predetermined notification is given to the outside.

Such a monitored person monitoring device makes a predetermined notification to the outside when the final excretion probability exceeds a predetermined threshold value set in advance. Therefore, by referring to this notification, the monitor can recognize that the monitored person is nearing excretion.

In another aspect, in the above-described monitored person monitoring apparatus, the excretion event detecting unit includes a bed leaving detection unit that detects the bed leaving the bed person as the event.

Such a monitored person monitoring apparatus can easily detect the event by regarding the bed leaving as the event.

In another aspect, in the above-described monitored person monitoring apparatus, the bed leaving detection unit is configured to pick up an image to generate an image, and to detect the bed leaving based on the image generated by the image pickup unit. A part.

Since such a monitored person monitoring apparatus detects a bed leaving from an image, it is possible to detect the floor of the monitored person and thus the event without contact with the monitored person.

In another aspect, in the above-described monitored person monitoring device, the biological signal measurement unit includes a Doppler sensor.

Since such a monitored person monitoring apparatus measures a biological signal of the monitored person with a Doppler sensor, the biological signal can be measured without contact with the monitored person.

In another aspect, the above-described monitored person monitoring apparatus further includes a third excretion probability calculation unit that obtains a third excretion probability from a third excretion prediction model in which the excretion probability increases as time elapses from the excretion time. The final excretion probability calculating unit obtains the final excretion probability based on the first to third excretion probabilities obtained by the first to third excretion probability calculating units, respectively.

Such a monitored person monitoring apparatus obtains the final excretion probability based on the third excretion probability in addition to the first and second excretion probabilities, and thus obtains a more accurate final excretion probability. be able to.

According to another aspect of the monitored person monitoring method, an excretion event detecting step of detecting a predetermined event related to excretion of a monitored person who is a monitoring target, and measuring a time-series predetermined biological signal in the monitored person A first excretion probability calculating step of obtaining a probability per unit time as a first excretion probability that the monitored person excretes based on the detection result of the excretion event detection step; A second excretion probability calculation step of obtaining a probability per unit time that the monitored person excretes as a second excretion probability based on a measurement result of the biological signal measurement unit; and the first and second excretion probability calculations A final excretion probability calculating step for determining a final excretion probability as a final excretion probability that the monitored person excretes based on the first and second excretion probabilities determined in the process; and the final excretion And a notification step of notifying the final excretion probability calculated at a rate calculation step to the outside.

Such a monitored person monitoring method obtains the first excretion probability of the monitored person, obtains the 22nd excretion probability of the monitored person, and based on the first and second excretion probabilities, the final of the monitored person is obtained. To determine the probability of excretion and notify the outside. Therefore, since the monitor can predict the excretion by referring to the final excretion probability of the monitored person, the monitored person monitoring method can support advance rushing. The monitored person monitoring method obtains the final excretion probability based on the first and second excretion probabilities obtained by two methods, so that the excretion probability with higher accuracy can be obtained.

A monitored person monitoring system according to another aspect includes a terminal device and a monitored person monitoring device that is communicably connected to the terminal device and monitors a monitored person that is a monitoring target. The monitored person monitoring device is any one of the above-described monitored person monitoring devices.

Since such a monitored person monitoring system uses any of the above-described monitored person monitoring devices, it is possible to support advance rushing by predicting the excretion probability and notifying the monitoring person.

This application is based on Japanese Patent Application No. 2016-83279 filed on April 19, 2016, the contents of which are included in this application.

In order to express the present invention, the present invention has been properly and fully described through the embodiments with reference to the drawings. However, those skilled in the art can easily change and / or improve the above-described embodiments. It should be recognized that this is possible. Therefore, unless the modifications or improvements implemented by those skilled in the art are at a level that departs from the scope of the claims recited in the claims, the modifications or improvements are not covered by the claims. To be construed as inclusive.

According to the present invention, a monitored person monitoring apparatus, a monitored person monitoring method, and a monitored person monitoring system can be provided.

Claims

An excretion event detection unit for detecting a predetermined event related to excretion of a monitored person to be monitored;
A biological signal measuring unit for measuring a predetermined biological signal in time series in the monitored person;
A first excretion probability calculation unit that obtains, as a first excretion probability, a probability per unit time that the monitored person excretes based on a detection result of the excretion event detection unit;
A second excretion probability calculating unit that obtains, as a second excretion probability, a probability per unit time that the monitored person excretes based on the measurement result of the biological signal measuring unit;
Based on the first and second excretion probabilities obtained by the first and second excretion probability calculating units, final excretion is obtained by determining a probability per unit time that the monitored person excretes as a final excretion probability. A probability calculator,
A notification processing unit for notifying the final excretion probability determined by the final excretion probability calculating unit to the outside,
Monitored person monitoring device.
A determination unit for determining whether or not the final excretion probability obtained by the final excretion probability calculation unit exceeds a predetermined threshold;
The notification processing unit, when it is determined by the determination unit that the final excretion probability calculated by the final excretion probability calculation unit exceeds a predetermined threshold, to give a predetermined notification to the outside,
The monitored person monitoring apparatus according to claim 1.
The excretion event detection unit includes a bed leaving detection unit that detects the bed leaving the bedding from the bedding as the event.
The monitored person monitoring apparatus according to claim 1 or 2.
The bed leaving detection unit includes an image pickup unit that picks up an image and generates an image, and a detection unit that detects the bed removal based on the image generated by the image pickup unit.
The monitored person monitoring apparatus according to claim 3.
The biological signal measurement unit includes a Doppler sensor,
The monitored person monitoring apparatus according to any one of claims 1 to 3.
A third excretion probability calculating unit for obtaining a third excretion probability from a third excretion prediction model in which the excretion probability increases as time elapses from the excretion time;
The final excretion probability calculating unit obtains the final excretion probability based on the first to third excretion probabilities obtained by the first to third excretion probability calculating units,
The monitored person monitoring apparatus according to any one of claims 1 to 5.
An excretion event detection step for detecting a predetermined event related to excretion of the monitored person to be monitored;
A biological signal measuring step of measuring a predetermined biological signal in time series in the monitored person;
A first excretion probability calculating step of obtaining a probability per unit time as a first excretion probability that the monitored person excretes based on a detection result of the excretion event detection step;
A second excretion probability calculating step of obtaining, as a second excretion probability, a probability per unit time that the monitored person excretes based on the measurement result of the biological signal measurement unit;
Based on the first and second excretion probabilities obtained in the first and second excretion probability calculation steps, final excretion is obtained as a final excretion probability that the monitored person excretes the predetermined unit time. A probability calculation process;
A notification processing step of notifying the final excretion probability determined in the final excretion probability calculation step to the outside,
Monitored person monitoring method.
A monitored person monitoring system comprising a terminal device and a monitored person monitoring device connected to the terminal device so as to be communicable and monitoring a monitored person to be monitored,
The monitored person monitoring apparatus is the monitored person monitoring apparatus according to any one of claims 1 to 6.
Monitored person monitoring system.