JPH10257204A - Remote daily behavior confirmation device and system - Google Patents

Abstract

PROBLEM TO BE SOLVED: To provide a remote daily behavior confirmation device that monitors the health of a resident and ensures the safety, where it is not required to carry a transmitter by the resident at all times, any operation of the device and a discrimination method based on a statistical index is adopted. SOLUTION: The remote behavior confirmation device is made up of a plurality of human body sensors 2 placed in a house 4 and a resident monitor 1 that obtains indices such as a transition matrix and a distribution function to discriminate behaviors of residents from sensed data, compares present indices with a plurality of past indices, discriminate it 'unusual' when prescribed conditions are not satisfied, and reports it to a center via a modem 3. Furthermore, a center equipment 6 receives the notice, processes and displays it.

Description

DETAILED DESCRIPTION OF THE INVENTION

[0001]

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to a living activity remote confirmation device and a living activity remote confirmation system, and more particularly to detecting the living activity of a solitary elderly person in order to ensure the safety and physical health of the elderly person. The present invention relates to a living activity remote confirmation device and a living activity remote confirmation system for estimating a health condition and a life accident and promptly reporting an emergency.

[0002]

2. Description of the Related Art Heretofore, services for the purpose of ensuring the safety of a solitary elderly by various means have been provided by the government or a company. In the conventional method, for example, a solitary elderly person always carries a radio transmitter, and in an emergency, makes a report by operating the switch of the radio transmitter by himself, and reports the report to an administrative organization or its contractor (individual and group). It is based on a service center set in advance or its intermediary receiving and responding.

[0003]

In the conventional service, it is necessary to reduce the size and weight of the transmitter in order to carry the radio transmitter at all times. There are problems such as occurrence of a failure due to the above, and instability of the receiving operation due to insufficient transmission output. Also, when a sudden accident occurs to the elderly,
There is a defect in the system that operation by one's own power cannot always be expected, and furthermore, there is a problem in that the old man does not function sufficiently due to psychological restrictions such as hesitation to withdraw the switch and reluctance.

[0004] In addition, the determination of the health of the elderly and whether or not they are safe can be made by (a) fire alarms, gas leak detectors, etc., which can be determined by whether or not there is an input from a sensor, (b) ) As determined by comparing the data measured by the sensor with the preset data, such as blood pressure, (c) The number of times of use of the toilet per day has been significantly reduced from the number of times of use in the past several days In some cases, it can be determined by comparing with past statistical data that it is determined that the elderly person may have a movement disorder. However, the determination method of (c) has not been conventionally used, and there has been a problem that a "change" in the living behavior of the monitored resident cannot be accurately detected.

[0005] An object of the present invention is to remove the restriction that an elderly person must carry a transmitter at all times, to eliminate the intentional operation of equipment by the elderly person, and to determine the above (c) which is not conventionally used. It is an object of the present invention to provide a living activity remote confirmation device and a living activity remote confirmation system that enable the health and safety of residents to be ensured simply by living a daily life naturally by combining the method with a conventional determination method. .

[0006]

SUMMARY OF THE INVENTION A living activity remote confirmation apparatus according to the present invention is connected to a plurality of sensor means for detecting the presence of a person in a house to be monitored and around the house, and a home monitor processing means. An index for determining the living behavior of the resident is obtained from the information output means and the data detected by the plurality of sensor means, and a current index is compared with a past index to satisfy a predetermined condition. If not, it is characterized by including a home monitor processing means for judging "not normal" and outputting information "not normal" to the information output means. Further, the living activity remote confirmation system of the present invention includes a communication control device connected to a public communication network as information output means, and transmits the “unusual” information to a remote center device. It comprises a confirmation device and a center device for receiving and displaying information transmitted from the living activity remote confirmation device.

The living activity remote confirmation apparatus of the present invention obtains an index for determining the living activity of the resident from data detected by a plurality of sensor means, and compares a current index with a plurality of past indices. Then, it is determined whether or not “it is not normal”. Therefore, the “change” in the living behavior of the monitored residents
Can be accurately detected and reported.

[0008]

Embodiments of the present invention will be described below in detail with reference to the drawings. FIG. 1 is a block diagram showing a configuration of a living activity remote confirmation system of the present invention. The home monitor device 1 is located in the residence 4 of the solitary elderly person who is a monitored resident.
Is installed. The home monitor device 1 includes a plurality of sensors 2 and a public communication network 5 such as a telephone network via a modem 3.
It is connected to the. In addition, a plurality of home monitor devices and a center device 6 installed in a center 7 are also connected to the public communication network 5.

The home monitor device 1 detects the location of the resident in the house or around the house by the sensor 2 and performs the processing described later to determine whether or not it is “normal”. If it is determined that it is not normal, the center device 6 is called using the modem 3 and
Notify "unusual" information. In the center 7, for example, the operator reads out and displays further detailed data from the home monitor device 1, checks the display, and furthermore, when it is deemed to be abnormal, checks by telephone, visits, related persons or related organizations. Take appropriate measures such as reporting to.

FIG. 2 is a block diagram showing the configuration of the home monitor device 1. The CPU 10 is the home monitor device 1
This is a processing device such as a microprocessor that controls the entire system, and is connected to various devices via a bus 31. R
A control program is stored in the OM 11 and is stored in the RAM
Reference numeral 12 is used as a work area or a data buffer. The RAM 12 is backed up by a battery 13 so that past detection data and the like are not erased even when a power failure or the like occurs. Note that an EEPROM (flash ROM) may be used instead of using the RAM backed up by a battery.

The timer 14 has a clock function for outputting time information, and a CPU functioning after a predetermined time elapses.
, And is also backed up by the battery 13. The display 15 is, for example, a liquid crystal display panel, and the display interface circuit 1
The display is controlled by the CPU 10 through the CPU 6. Switch 1
Reference numeral 7 denotes a keypad including a plurality of switches, for example.
The CPU 10 reads on / off information via the switch interface circuit 18 having a parallel input function. The display 15 and the switch 17 are mainly used for maintenance, but can also be used for emergency calls and the like.

The modem 3 and the home monitor device 1 are connected via an RS-232C cable, which is a general interface. To further reduce the size, a modem function can be incorporated in the RS-232C interface circuit 19 of the home monitor device 1.

The thermal sensor 23 is, for example, a sensor device having intelligence, and is installed in each room or passage in a house as shown in FIG. As the thermal element, for example, a pyroelectric infrared sensor is used to detect a temperature change accompanying movement of a person. Each thermal sensor 23 is given a different address, and is connected to the network driver 22 by a single bus made of a metal cable or an optical cable. The network controller 20 drives the network driver 22 via the insulating photocoupler 21 and sequentially transmits desired addresses and commands. The thermal sensor 23 corresponding to the address returns a detection result of the sensor as a digital signal in response to the command, and the network controller 2
0 receives the digital signal and notifies the CPU 10.

The door switch 28 is a switch that is turned on / off according to the opening and closing of the door.
Is a switch that is installed under a futon, for example, and that is turned on when a predetermined pressure (load) is applied. Output signals of the door switch 28 and the sheet-like switch 30 are received by receivers 27 and 29.
And received by the photocouplers for insulation 25, 26,
The CPU 1 via the parallel interface circuit 24
Reads to 0.

In the present invention, in addition to the sensor shown in FIG. 2, various types of sensors such as a photoelectric tube, an ultrasonic sensor, a laser light reflection type sensor, and a capacitance type sensor can be used. There are various methods for connecting to the sensor. Sensors connected by cables can be further divided into several types depending on the types of signals transmitted and received. If there is intelligence on the sensor side, RS-232C, RS-422, R
A standardized communication method such as S-485 or CSMA method LAN can be used. In the case of a sensor that simply turns on and off like the door switch 28, the signal of the sensor is converted to a voltage level and read directly by the interface circuit. In the case of a sensor having a continuous signal level, the sensor signal is converted into digital data through an analog-digital converter and then read. Further, for a sensor having a built-in wireless transmitting / receiving device, wireless transmission can be performed using, for example, a specific low-power wireless transmitting / receiving device.

FIG. 3 shows the CPU 10 of the home monitor device 1.
6 is a flowchart showing the contents of a monitoring process executed by the user. This process is repeatedly executed as long as the power is turned on. In S1, it is determined whether or not there is an alarm, for example, when an emergency notification switch among the switches 17 is operated, or when an unillustrated fire sensor, gas leak sensor, or the like detects an abnormality, and the result is affirmative. In the case of, the process proceeds to S11, and the alarm information is reported to the center.

In S2, it is determined whether or not a sensor reading cycle (for example, 100 milliseconds) has elapsed since the previous execution of S3. If the result is negative, the process returns to S1, but if the result is affirmative, the process returns to S1. Move on to S3, various sensors 2
Read the values of 3, 28 and 30 in order. It should be noted that reading may be performed at optimal measurement intervals that differ depending on the type of sensor. Further, a highly urgent sensor input may be detected by an interrupt process.

In step S4, a comparison is made with the sensor value read immediately before to determine whether or not the sensor value has changed. Then, when the result is negative, the process proceeds to S6,
If the result is affirmative, the process proceeds to S5, and the information on the changed sensor value is stored in the data buffer in the RAM 12. The information to be stored includes, for example, (a) change in sensor, presence / absence of a person, or absence / presence of a person. (B) Location (number) where the sensor is installed. (C) The date and time when the sensor has changed are included. In S6, it is determined whether or not a predetermined calculation cycle (10 minutes for a “transition matrix” index described later) has elapsed since the previous time the index calculation processing after S7 was executed, and if the result is negative. Returns to S1, but if affirmative, proceeds to S7.

In S7 to S9, a normality determination process described later is performed. In brief, in S7,
An index is calculated from the sensor change data up to the present, and S8
In, a past index is calculated or a stored index is read. In S9, the present index is compared with a plurality of past indexes by a method described later. S10
In, it is determined whether or not the comparison result in S9 is “normal”. If the result is affirmative, the process returns to S1, but if negative, that is, if “normal”, the process proceeds to S11 and the center device 6 Make a report. More specifically, a call is made to the telephone number of the center device 6 registered in advance by using the modem 3, and when the center device 6 answers, digital data indicating "unusual" is transmitted to the caller information. And send it out.

FIG. 4 is a flowchart showing an example of the normality judgment processing in S7 to S10 of FIG. In this example, a “transition matrix” is used as an index. As shown in FIG. 5, the transition matrix indicates how many times a person has moved from one place to another place in the house during a predetermined period, for example, the past 24 hours from the current time. Data. The transition matrix is considered to represent the daily behavior of the resident. For example, in FIG. 5, it can be seen that the movement from the living room (A) to the kitchen (B) has been performed three times within the past 24 hours from the present, and the movement from the living room (A) to the bedroom (C) has been performed five times.

In S20, the movement source, the destination, and the movement time of the person are extracted from the sensor change information recorded in S5 of FIG. 3 to generate transition matrix data. On this occasion,
Data is divided every 24 hours, for example, within the past 24 hours, within the last 24 to 48 hours, and transition matrix data for a plurality of days is generated. In S21, the variable n is initialized to 1 and C is initialized to 0. In S22, the transition matrix data of n days ago is read from the transition matrix data for the past K days obtained in S20, and the similarity with the current (recent) transition matrix is calculated.

As a method of determining similarity, for example, several known methods such as a P-order norm (Lp norm) and a correlation coefficient (r) can be adopted. The equation for calculating the Lp norm is shown in Equation 1, and the equation for calculating the correlation coefficient r is shown in Equation 2. The matrices u and v to be compared are each a matrix of S rows and S columns.

[0023]

(Equation 1)

[0024]

(Equation 2) In the Lp norm, the closer the data is, the closer to 0, and in the case of the correlation coefficient, r takes a value between -1 and 1; for example, the closer the data is, the closer to 1.

In step S23, it is determined whether or not the value indicating the similarity indicates that the similarity is equal to or greater than a predetermined threshold value.
The process proceeds to S24 when it is determined that “there is no similarity”. In S24, 1 is added to C. In S25, 1 is added to n, and in S26, it is determined whether or not n is larger than a predetermined value K. If the determination result is negative, the process returns to S22,
If affirmative, the process proceeds to S27. In S27,
It is determined whether the value of C, that is, the number of days determined to be “not similar” is greater than a preset value A. If the value is greater than the determination threshold A, it is determined that “it is not normal”.

With the above configuration and operation, for example, the daily behavior of a solitary elderly person is monitored, and when the detected behavior pattern is different from the normal behavior pattern, this change is reliably detected and reported to the center. It can be performed.

Next, other indices will be described. FIG.
FIG. 4 is an explanatory diagram showing an example of data of a “distribution function”. The distribution function is obtained by calculating the sum of the number of times a person has passed per unit time from the present time to the past 24 hours. The distribution function is considered to represent activity. In the example of FIG. 6, one hour before the present, one person passes through the living room (A), zero times in the kitchen (B), zero times in the bedroom (C), and zero times in the washroom (D). From 1 hour to 2 hours before, living room (A) once, kitchen (B) three times, bedroom (C) twice,
It can be seen that a person has passed the washroom (D) twice. As for the distribution function, similarly to the transition matrix, it is possible to calculate the number of past days every 24 hours and compare the current index with the past index to determine whether the distribution function is normal. As in the case of the transition matrix, an N-order norm, a correlation coefficient, and the like can be adopted as the comparison method.

FIG. 8 is an explanatory diagram showing a display example of "in-home moving distance" which is another index. The amount of movement in the house can be obtained from the above-mentioned transition matrix and the distance between the places where the sensors are installed. The distance traveled per day indicates whether the elderly alone are active. The amount of movement (distance) may gradually decrease due to a decrease in athletic ability or mental instability. By accumulating data on the amount of movement in the house, grasp changes in the health condition of the elderly person over a long period of time. Can be. Since the moving distance in the house is greatly reduced on the day when the user goes out of the house as compared to the day when he / she is at home, the fact that the user has gone out is detected by a sensor at the entrance or the like and is referred to at the time of determination. If a short moving day continues for a predetermined number of consecutive days, it is determined that "normal".

The "stay time" which is another index is the time spent staying at a specific place in the house. For places where the purpose of use is limited, such as toilets and baths, the stay time is roughly determined. Some types of sensors, such as pyroelectric infrared sensors, can detect the presence or absence of a person and whether they are moving. If you stay in the toilet for more than an hour and do not move, you can definitely consider it an abnormal situation. Therefore,
Set a maximum stay time for each location in advance,
If it exceeds this, it is determined that "it is not normal". These indicators are measured unknowingly by the elderly.

In the home monitor device 1, only one index may be employed, but a plurality of indices may be calculated at appropriate intervals, and it may be determined whether or not each index is normal. For example, “transition matrix” and “distribution function” are every 10 minutes, the amount of movement is every 24 hours, and “stay time” is 1
The index is calculated at minute intervals, and the judgment is performed.

Next, the function of the center device 6 and a data display method will be described. As the hardware of the center device 6, for example, a general-purpose personal computer or workstation can be used, and a program realizes a communication function, data collection, processing function, display function, and the like. The center device 6 that has received the message from the home monitor device 1 displays information such as caller information and the content of the report to the operator, and also displays various current and past index data or sensor change information from the home monitor device 1. The data is read, processed, and displayed and output on a CRT display or a printer.

As a display example, the transition matrix shown in FIG.
In addition to the distribution function shown in FIG. 6 and the moving amount in the house shown in FIG.
A transition diagram by time for displaying transition (moving) state according to time as shown in FIG. 7, an action trajectory diagram as shown in FIG. 9, and a histogram showing distribution functions as shown in FIG. Can be selected and displayed. The action trajectory diagram in FIG. 9 is a diagram in which the sensor numbers that detect a person in the floor plan are inverted and displayed as time elapses, and, for example, a one-day action trajectory is displayed in about 10 seconds. In FIG. 9, square frames 40 and 41 numbered 1 to 8 indicate the positions of the sensors, and indicate that a person is present at the position of the frame 41 where the display color is inverted. . In the center 7, the operator can process various data as necessary and display it, thereby making it easier for the elderly to act.
In addition, it is possible to accurately grasp, and it is possible to accurately determine whether or not it is normal. Note that the center device 6 may have a function of calling the in-home monitor device 1 at an arbitrary time or sequentially at a predetermined cycle, and reading out the behavior information of the elderly person. Alternatively, the home monitor device 1 may periodically call the center device 6, transfer the measurement data, calculate the index in the center device 6, and determine the “normality”.

[0033]

According to the present invention, since there is no need for the elderly to consciously operate the equipment, an alarm can be promptly issued without any trouble even if any abnormality occurs in the elderly. In addition, since daily life behavior patterns are accumulated, there is also an effect that "changes" in life behavior can be accurately detected.

[Brief description of the drawings]

FIG. 1 is a block diagram illustrating a configuration example of a living activity remote confirmation system of the present invention.

FIG. 2 is a block diagram showing a configuration of a home monitor device 1;

FIG. 3 is a flowchart showing the contents of a monitor process executed by a CPU 10;

FIG. 4 is a flowchart illustrating an example of a normality determination process in S9 to S12.

FIG. 5 is an explanatory diagram showing an example of data of a transition matrix.

FIG. 6 is an explanatory diagram illustrating a data example of a distribution function.

FIG. 7 is an explanatory diagram showing a display example of a transition diagram by time.

FIG. 8 is an explanatory diagram showing a display example of a home movement amount.

FIG. 9 is an explanatory diagram showing a display example of an action locus diagram.

FIG. 10 is an explanatory diagram illustrating a display example of a histogram of a distribution function.

[Explanation of symbols]

1: home monitor device, 2: sensor, 3: modem, 4
... monitor house, 5 ... public communication network, 6 ... center equipment,
7 ... Center

 ────────────────────────────────────────────────── ─── Continuation of the front page (72) Inventor Kozo Ichida 6-7 Shimogamo Yakkocho, Sakyo-ku, Kyoto-shi, Kyoto

Claims (6)

[Claims] 1. A plurality of sensors installed in and around a house to be monitored for detecting the presence of a person, information output means connected to a home monitor processing means, and a plurality of sensors detected by the plurality of sensor means. An index for determining the living behavior of the resident is obtained from the data obtained, the current index is compared with the past index, and if the predetermined condition is not satisfied, it is determined that “it is not normal”, A home-activity monitor for outputting information indicating "unusual" to the information output means; 2. The at-home monitor processing means determines whether or not the moving direction and the number of times of movement between the plurality of sensor means are similar to the same type of data in the past plural days, and if not, determines whether they are similar. The living activity remote confirmation device according to claim 1, wherein it is determined that "it is not normal". 3. The at-home monitor processing means obtains a histogram of the sum of the number of times of detection of a person per unit time by the plurality of sensor means, compares the histogram with similar data in the past, and determines whether or not they are similar. The living activity remote confirmation device according to claim 1, wherein it is determined that "not normal" if they are not similar. 4. The home monitor processing means obtains a moving distance of the resident per unit time of the resident from the moving direction and the number of times of movement between the plurality of sensor means and a distance between the sensor means, and obtains past similar data. 2. The remote living activity confirmation apparatus according to claim 1, wherein, when the predetermined condition is not satisfied, it is determined that the condition is not normal. 5. The home monitor processing means measures the time the resident is staying at the place by a sensor means installed at a specific place in the house, and when the stay time exceeds a preset time, The living activity remote confirmation device according to claim 1, wherein it is determined that "it is not normal". 6. The remote confirmation of living activity according to claim 1, wherein said information output means includes a communication control device connected to a public communication network, and transmits "unusual" information to a remote center device. A living activity remote confirmation system comprising: a device; and a center device for receiving and displaying information transmitted from the living activity remote confirmation device.