JP2023050019A - Abnormality determination system - Google Patents

Abstract

To provide an abnormality determination system that improves the accuracy of determining whether or not a subject has an abnormality.SOLUTION: An abnormality determination system 10 includes a posture detection unit (room sensor 11) that detects a posture of a subject (resident P1), and a determination unit (server 12) that determines whether or not the subject has an abnormality based on the transition speed of the posture of the subject and determines that the subject has an abnormality when the speed at which the posture of the subject shifts from the a first posture to a second posture is outside a first range.SELECTED DRAWING: Figure 1

Description

TECHNICAL FIELD The present invention relates to technology of an abnormality determination system that determines the presence or absence of an abnormality in a subject.

Conventionally, the technology of an abnormality determination system that determines the presence or absence of an abnormality in a subject is publicly known. For example, it is as described in Patent Document 1.

Patent Literature 1 describes an anomaly determination system that detects the current situation of a resident in a facility for the disabled using a sensor such as a motion sensor and displays it on the screen of a management PC in a management room. . A caregiver (facility staff) checks the presence or absence of a resident's abnormality (for example, falls) on the screen of the management PC, and if an abnormality is confirmed, the resident's room can rush to

In such an abnormality determination system, if an abnormality is erroneously detected, caregivers needlessly rush to the resident's living room.

JP 2017-16611 A

SUMMARY OF THE INVENTION The present invention has been made in view of the circumstances described above, and an object thereof is to provide an abnormality determination system capable of improving the accuracy of determination of the presence or absence of an abnormality.

The problems to be solved by the present invention are as described above, and the means for solving the problems will now be described.

That is, in claim 1, it comprises a posture detection unit that detects the posture of the subject, and a determination unit that determines whether or not the subject has an abnormality based on the posture transition speed of the subject. be.

In claim 2, the determination unit determines that the subject has an abnormality when the speed at which the subject's posture changes from the first posture to the second posture is outside the first range. It is.

In claim 3, the determination unit determines the first range by previously learning a transition speed of the posture of the subject.

In claim 4, it further comprises a location detection unit that detects the location of the subject, and the determination unit determines that, if the subject's stay time at the predetermined location is outside the second range, the subject is determined to be abnormal.

In claim 5, the determination unit determines the second range by previously learning the stay time of the subject person at a predetermined place.

In claim 6, further comprising a vital information detection unit for detecting the vital information of the subject, the determining unit determines whether or not there is an abnormality in the subject based on the vital information of the subject. be.

A seventh aspect of the present invention further comprises a storage unit that stores information about the subject's abnormality when it is determined that the subject has an abnormality.

ADVANTAGE OF THE INVENTION This invention can aim at the improvement of the determination precision of the presence or absence of abnormality.

The schematic diagram which showed the structure of the abnormality determination system which concerns on one Embodiment of this invention. 4 is a flow chart showing the contents of control by the server; The figure which showed an example of the abnormality detected by the abnormality determination system.

The configuration of the abnormality determination system 10 according to one embodiment of the present invention will be described below.

The abnormality determination system 10 according to the present embodiment determines the presence or absence of an abnormality in a person (resident P1) who resides in a facility such as a facility for the elderly, a nursing facility, or a facility for the disabled. As shown in FIG. 1, this embodiment shows an example in which an abnormality determination system 10 is provided in a facility 1 for the elderly.

A facility 1 for the elderly in which an abnormality determination system 10 is installed is provided with a plurality of living rooms 2 , and a resident P1 lives in each living room 2 . In addition, in FIG. 1, only one living room 2 is illustrated for convenience. Each living room 2 is provided with a toilet 2a. In addition, the facility for the elderly 1 is provided with a staff room 3 where the staff P2 (caregiver or the like) of the facility for the elderly 1 waits.

The abnormality determination system 10 mainly includes a room sensor 11 , a terminal 13 and a server 12 .

The living room sensor 11 acquires information about the resident P1 who is staying in the living room 2 . In this embodiment, a millimeter wave sensor using millimeter waves (electromagnetic waves in a high wave number band) propagating in a predetermined range is used as the living room sensor 11 . The living room sensor 11 is provided, for example, on the ceiling of the living room 2 so as to transmit millimeter waves downward. The millimeter wave transmitted from the living room sensor 11 is reflected by the object, and the living room sensor 11 receives this reflected wave. Based on the received reflected wave, the living room sensor 11 acquires information about the position (location) of the object such as the distance to the object, the angle, and the position of the center of gravity, the shape of the object, the movement speed of the object, and the like. can be done.

The server 12 performs various processes based on the detection result of the living room sensor 11 . The server 12 is configured by, for example, a virtual server (cloud server) provided on the cloud. The server 12 includes an arithmetic processing unit such as a CPU, a storage unit such as a RAM and a ROM, and the like. Based on the information from the room sensor 11, the server 12 can determine whether or not the resident P1 has an abnormality. Also, the server 12 can transmit and receive various information to and from a terminal 13, which will be described later.

The terminal 13 is capable of displaying various information. The terminal 13 is carried by a person who should know whether or not the resident P1 has an abnormality. In this embodiment, it is assumed that the staff member P2 of the facility for the elderly 1 possesses the terminal 13 . The terminal 13 is configured by, for example, a device (for example, a smart phone, a tablet terminal, etc.) that can be carried by the staff member P2. The terminal 13 can notify the staff member P2 of information from the server 12, which will be described later, by an appropriate method (display on a liquid crystal screen, voice, etc.).

By using the abnormality determination system 10 configured as described above, it is possible to determine whether or not the resident P1 has an abnormality. Further, when the abnormality determination system 10 determines that the resident P1 has an abnormality, the abnormality determination system 10 can notify the staff member P2 to that effect. As a result, the staff P2 can promptly take appropriate measures such as rushing to the living room 2 of the resident P1.

By repeatedly executing the control flow shown in FIG. 2, the server 12 can determine whether or not there is an abnormality in the resident P1 and notify the staff member P2. A series of processes by the abnormality determination system 10 will be specifically described below.

In step S<b>101 , the server 12 determines whether or not there is only one person in the living room 2 based on the information from the living room sensor 11 .

Here, the server 12 can determine the room occupancy information of the living room 2 (how many people are in the living room 2) based on the information from the living room sensor 11 . Specifically, the server 12 can determine the presence or absence of people in the room and the number of people from various information (distance, moving speed, etc.) of objects in the room 2 acquired by the room sensor 11 .

When the server 12 determines that there is only one person in the living room 2, the process proceeds to step S102. On the other hand, when the server 12 determines that there is not one person in the living room 2 (no one is in the room, or two or more people are in the room), the process proceeds to step S107. When it is detected that two or more people are in the living room 2 in this way, there is a high possibility that the resident P1 and the staff member P2 are in the living room 2. The determination of abnormality in S104 is not performed.

If there is only one person in the living room 2, the person is likely to be the resident P1 of the living room 2. In the following description, it is assumed that the person determined to be in the room alone in step S101 is the resident P1.

In step S102, the server 12 determines whether the posture of the resident P1 in the living room 2 is lying down.

Here, the server 12 can determine the posture of the resident P1 based on information from the living room sensor 11 . Specifically, the server 12 determines which of the three postures of the resident P1, lying down, sitting on the edge, and standing, from various types of information about the resident P1 acquired by the living room sensor 11. can judge. Note that the categories of postures determined by the server 12 are not limited to the three types described above, and can be arbitrarily set.

When the server 12 determines that the posture of the resident P1 in the living room 2 is lying down, the process proceeds to step S103. On the other hand, when the server 12 determines that the posture of the resident P1 in the living room 2 is not lying down, the process proceeds to step S107.

In step S103, the server 12 determines that the transition speed when the resident P1 transitions from the previous posture (posture other than the lying position) to the lying position determined in step S102 is outside a predetermined range (first range). It is determined whether or not.

Specifically, the server 12 determines whether or not the transition speed of the resident P1 from the previous posture to the lying position is 5 m/s or more (for convenience, this determination condition is hereinafter referred to as “condition 1”). do. Here, it is generally known that the speed at which a person falls is 5 m/s or more. Therefore, in the present embodiment, it is presumed that the resident P1 has fallen down when the transition speed of the resident P1 to the lying position is 5 m/s or more. The reference value (5 m/s) for estimating overturning can be arbitrarily changed.

Furthermore, in step S103, the server 12 determines that the transition time T1 from the previous posture of the resident P1 to the lying position is 1/2 or less, or twice or more than the normal transition time T2 (for convenience, this determination is condition is referred to as "condition 2"). Here, the normal transition time T2 is the transition time when the resident P1 is in a normal state (especially when no abnormality has occurred) and is shifted to the lying position. The server 12 sets the transition time T2 by learning in advance the transition time of the posture of the resident P1 in normal times. For example, the server 12 can set the average value of the transition time of the posture of the resident P1 in the most recent month as the transition time T2.

Thus, in the present embodiment, when the transition time T1 is significantly shorter or longer (the transition speed is significantly faster or slower) than the normal transition time T2, the resident P1 intends It is presumed that he fell without doing anything. For example, when transition time T1 is half or less of transition time T2, resident P1 may stumble and fall. Moreover, when the transition time T1 is twice or more the transition time T2, there is a possibility that the physical condition of the resident P1 deteriorated and he fell while suffering.

When the server 12 determines that the above condition 1 or condition 2 is satisfied, the process proceeds to step S105. On the other hand, when the server 12 determines that neither the condition 1 nor the condition 2 is satisfied, the process proceeds to step S104.

In step S104, the server 12 determines whether or not the residence time t1 of the resident P1 at the predetermined place is outside the predetermined range (second range).

Specifically, the server 12 determines whether or not the time (staying time t1) that the resident P1 stays in a place other than the bed is twice or more the usual staying time t2 at the place. . For example, the server 12 determines whether or not the resident P1 stays in the restroom 2a for a time longer than twice the usual staying time t2. Here, the usual staying time t2 is the time during which the resident P1 is expected to stay at the place in normal times. The server 12 sets the stay time t2 by learning in advance the stay time of the resident P1 at each place during normal times.

The server 12 can determine the location of the resident P1 based on the information from the living room sensor 11 . For example, when the living room sensor 11 cannot detect the resident P1 near the toilet 2a, it can be determined that the resident P1 has entered the toilet 2a. The server 12 can also determine where the resident P1 is in the living room 2 (on the bed, on the floor, by the window, etc.) in addition to the restroom 2a. The server 12 learns in advance the length of stay of the resident P1 at these various locations, and sets the length of stay t2 at each location. For example, the server 12 can set the average value of the staying time at each place of the resident P1 in the last month as the staying time t2 at each place.

As described above, in this embodiment, when the stay time t1 is significantly longer than the stay time t2 in normal times, it is presumed that some kind of abnormality has occurred in the resident P1. For example, if the residence time t1 of the resident P1 in the toilet 2a is long, the resident P1 may be in poor physical condition or fall over in the toilet 2a. In addition, when the residence time t1 at a position where the resident P1 does not usually stop in the living room 2 is long, there is a possibility that the resident is in poor physical condition at that position. Further, if the determination of overturning based on the posture of resident P1 is omitted in step S103, the overturning can also be detected by the determination of step S104.

If the resident P1 is staying in bed for a long time, there is a high possibility that the resident P1 is simply sleeping. are excluded.

When the server 12 determines that the stay time t1 of the resident P1 in places other than the bed is twice or more the usual stay time t2, the process proceeds to step S105. On the other hand, when the server 12 determines that the stay time t1 of the resident P1 in places other than the bed is less than twice the usual stay time t2, the process proceeds to step S107.

In step S105, the server 12 determines that an abnormality has occurred in the resident P1. Further, the server 12 notifies the resident P1 that an abnormality has occurred. Specifically, the server 12 issues a predetermined alert using the terminal 13 . The alert can contain various information. For example, as an alert, information identifying the resident P1 (name of the resident P1, number of the living room 2, etc.), a place where an abnormality is thought to have occurred (distinction between the toilet 2a, the inside of the living room 2, etc.), details of the abnormality (falling (see step S103), the possibility of poor physical condition due to a long stay (see step S104), etc.). As the alert, display of various information on the liquid crystal screen of the terminal 13, notification by voice, or the like can be used.

The staff P2 who received the alert from the terminal 13 can grasp that some kind of abnormality has occurred in the resident P1. Also, the staff member P2 can quickly rush to the resident P1 based on various information notified as an alert.

After performing the process of step S105, the server 12 proceeds to step S106.

In step S106, the server 12 stores the information regarding the abnormality of the resident P1 in the storage unit. By storing the information about the abnormality in this way, the information can be utilized for nursing records and the like. The server 12 terminates this control flow after performing the process of step S106.

On the other hand, in step S107 after moving from step S101, step S102, and step S104, the server 12 determines whether the vital information of resident P1 is abnormal. In this embodiment, the pulse rate and respiration rate are used as the vital information for determination.

Here, the server 12 can determine the vital information (pulse rate and respiration rate) of the resident P1 based on the information from the living room sensor 11 . Specifically, the server 12 can determine the pulse rate and respiration rate of the resident P1 from minute movements of the resident P1 (body surface movements due to pulse and respiration) acquired by the living room sensor 11. .

The server 12 determines whether the pulse rate and breathing rate of the resident P1 are abnormal based on predetermined criteria. For example, the server 12 determines that the pulse rate of the resident P1 is abnormal when the pulse rate of the resident P1 is 120 beats/minute or more or less than 50 beats/minute. Further, for example, the server 12 determines that the breathing rate of the resident P1 is abnormal when the breathing rate of the resident P1 is less than 10 times/minute or 30 times/minute or more. Note that the reference values for determining abnormalities in the pulse rate and respiration rate are not limited to those described above, and can be arbitrarily changed. For example, it is possible to learn the vital information of the resident P1 during normal times, and set an individual reference value for each resident P1 based on the learning result.

When the server 12 determines that the vital information of the resident P1 is abnormal (at least one of the pulse rate and the respiratory rate is abnormal), the process proceeds to step S105. On the other hand, when the server 12 determines that there is no abnormality in the vital information of the resident P1, the control flow ends.

In this way, the server 12, when the posture of the resident P1 is not lying down (NO in step S102), or when no abnormality is detected in the processing of steps S103 and S104, the final Regularly check vital signs. This makes it possible to detect an abnormality of the resident P1 that could not be detected by the above process. It should be noted that even when a plurality of persons are present in the living room 2 (NO in step S101), it is determined in step S105 whether or not there is an abnormality in the vital information.

An example of an abnormality detected by the above control flow will be described below with reference to FIG.

As in Example 1 shown in FIG. 3, in the living room 2, when the resident P1 moves from a state of walking at a transition speed of 5 m / s or more (standing position) to a state of lying on the floor (lying position) ( YES in step S102, YES in step S103), the server 12 determines that an abnormality has occurred in resident P1 (step S105).

Further, as in Example 2 shown in FIG. 3, when the resident P1 stays in the toilet 2a for a time longer than twice the usual staying time t2 (YES in step S104), the server 12 asks the resident P1 to It is determined that an abnormality has occurred (step S105).

As described above, by repeatedly executing the control flow shown in FIG. 2, the server 12 can detect an abnormality of the resident P1 and promptly notify the staff member P2 of the abnormality.

As described above, the abnormality determination system 10 according to the present embodiment
a posture detection unit (living room sensor 11) that detects the posture of the target person (resident P1);
a determination unit (server 12) that determines whether or not the subject has an abnormality based on the posture transition speed of the subject;
is provided.
By configuring in this way, it is possible to improve the accuracy of determining the presence or absence of an abnormality. That is, since the presence or absence of an abnormality can be determined based on the posture transition speed, it is possible to prevent erroneous detection of an abnormality when the subject intentionally changes the posture at a normal transition speed. can be done.

Further, the determination unit
If the speed at which the subject's posture transitions from the first posture (posture other than lying position) to the second posture (recumbing position) is outside the first range (YES in step S103), It is determined that there is an abnormality.
By configuring in this way, it is possible to objectively determine an abnormality based on a predetermined criterion (first range).

Further, the determination unit
The first range is determined by previously learning the transition speed of the posture of the subject.
By configuring in this way, it is possible to determine the reference (first range) according to the subject, so that it is possible to improve the accuracy of determining the presence or absence of abnormality.

In addition, the abnormality determination system 10
further comprising a location detection unit (living room sensor 11) for detecting the location of the subject;
The determination unit is
If the subject's staying time at the predetermined place is outside the second range (YES in step S104), it is determined that the subject has an abnormality.
By configuring in this way, an abnormality can be determined according to the stay time. For example, when the subject stays for a long time in a place where he should not stay for a long time, it can be determined that the subject has an abnormality.

Further, the determination unit
The second range is determined by previously learning the stay time of the subject person at the predetermined place.
By configuring in this way, it is possible to determine the reference (second range) according to the subject, so it is possible to improve the accuracy of determining the presence or absence of abnormality.

In addition, the abnormality determination system 10
further comprising a vital information detection unit (living room sensor 11) for detecting the subject's vital information,
The determination unit is
Based on the vital information of the subject, the presence or absence of abnormality of the subject is determined (step S107).
By configuring in this way, an abnormality can be determined based on the vital information. In particular, when no abnormality is detected in the posture or the length of stay as in the present embodiment, it is possible to prevent omission of abnormality detection by determining the presence or absence of abnormality based on vital information.

In addition, the abnormality determination system 10
It further comprises a storage unit (server 12) for storing information about the subject's abnormality when it is determined that the subject has an abnormality.
By configuring in this way, it is possible to utilize the information about the abnormality for nursing care records and the like.

The living room sensor 11 according to this embodiment is an embodiment of the posture detection unit, the location detection unit, and the vital information detection unit according to the present invention.
Also, the server 12 according to this embodiment is an embodiment of the determination unit and the storage unit according to the present invention.

Although the embodiments of the present invention have been described above, the present invention is not limited to the above embodiments, and can be appropriately modified within the scope of the technical ideas of the invention described in the claims. .

For example, in the present embodiment, an example in which the abnormality determination system 10 is provided in the elderly facility 1 is shown, but the present invention is not limited to this, and can be applied to various facilities. In addition, the configuration of the living room 2 shown in this embodiment is an example, and for example, a living room 2 not equipped with a toilet 2a, or a living room 2 equipped with other private rooms (bathroom, dressing room, washroom, etc.) There may be.

Further, in the present embodiment, the living room sensor 11 (millimeter wave sensor) was exemplified as an example of the attitude detection unit, the location detection unit, and the vital information detection unit, but the present invention is not limited to this, and various other detection means can be used. It is possible to detect the posture etc. of the target person. It is also possible to detect the subject's posture, location, vital information, and the like using different detection means. For example, it is possible to detect vital information and the like using detection means (wearable device) that can be worn by the subject.

In addition, in the present embodiment, the server 12 (cloud server) is used as an example of the determination unit, but the present invention is not limited to this, and the determination unit can be configured in various other ways. For example, it is possible to use an on-premises server provided in the elderly facility 1 as the determination unit.

Further, the specific content (see steps S103, S104, and S107) described as the criteria for determining abnormality in the present embodiment is an example, and the present invention is not limited to this. Numerical values can be changed arbitrarily.

Also, the control flow (see FIG. 2) described in this embodiment is an example, and can be arbitrarily changed. For example, it is possible to change the order of steps S103 and S104. It is also possible to configure not to execute any of the processes of steps S103, S104, and S107.

In addition, in the present embodiment, when the posture of the resident P1 is lying down (YES in step S102), an abnormality is detected according to the posture and the length of stay (steps S103 and S104). The posture for detecting an abnormality is not limited to the lying position, and it is also possible to detect an abnormality in various other postures.

Further, in the present embodiment, an example is shown in which it is determined that the resident P1 has entered the toilet 2a when the room sensor 11 provided in the living room 2 cannot detect the resident P1. It is also possible to provide a living room sensor 11 to detect the resident P1.

In addition, in the present embodiment, an example of judging abnormalities using pulse rate and respiration rate as vital information was shown, but vital information is not limited to this, and various other information (blood pressure, body movement, autonomic nervous system, etc.) etc.) can also be used.

10 Abnormality Determination System 11 Room Sensor 12 Server 13 Terminal

Claims (7)

a posture detection unit that detects the posture of a subject;
a determination unit that determines the presence or absence of an abnormality in the subject based on the transition speed of the posture of the subject;
Abnormality determination system. The determination unit is
If the speed at which the subject's posture shifts from the first posture to the second posture is outside the first range, it is determined that the subject has an abnormality.
The abnormality determination system according to claim 1. The determination unit is
determining the first range by learning in advance the transition speed of the posture of the subject;
The abnormality determination system according to claim 2. further comprising a location detection unit that detects the location of the subject;
The determination unit is
If the subject's stay time at the predetermined place is outside the second range, it is determined that the subject has an abnormality;
The abnormality determination system according to any one of claims 1 to 3. The determination unit is
Determining the second range by learning in advance the length of stay of the subject at a predetermined place,
The abnormality determination system according to claim 4. further comprising a vital information detection unit that detects the vital information of the subject;
The determination unit is
Determining whether the subject has an abnormality based on the subject's vital information,
The abnormality determination system according to any one of claims 1 to 5. Further comprising a storage unit that stores information about the abnormality of the subject when it is determined that the subject has an abnormality,
The abnormality determination system according to any one of claims 1 to 6.

Images