KR102212200B1 - System and method of monitoring elderly people living alone using lighting device based on IoT - Google Patents

Abstract

The present invention relates to a system for monitoring the elderly living alone using an IoT lighting device. A monitoring system according to an embodiment of the present invention includes an IoT lighting device including a lighting lamp, a motion detection unit, a CO2 sensor, and a biosignal detection unit; A health condition analysis unit that analyzes a user's health condition using motion data, CO2 concentration data, and biosignal data acquired from the IoT lighting device, and an alarm that generates an alarm command when the health condition analysis unit determines that it is an emergency situation. And a monitoring device including a generating unit and a feedback providing unit for generating a feedback command corresponding to the health condition determined by the health condition analysis unit and transmitting it to the IoT lighting device.
According to the present invention, since it is possible to check the health status in real time using the biosignal and CO2 concentration of the elderly living alone, it is possible to quickly cope with an emergency situation. In addition, even if an emergency situation occurs while the elderly living alone is sleeping, it is possible to quickly respond by checking in real time.

Description

System and method of monitoring elderly people living alone using lighting device based on IoT}

The present invention relates to a monitoring system and method capable of checking the health status of an elderly person living alone, whether or not a lonely person has died by using an IoT lighting device (such as a mood lamp or a ceiling lamp) installed in a house.

In recent years, along with the increase in single-person households, the number of lone deaths discovered after being left for a long time after death is increasing.

Accordingly, local governments at various levels are making efforts to prevent loneliness, such as having social workers and volunteers regularly visit elderly people living alone or check their health status over the phone.

However, this method has a problem in that it is difficult to quickly respond when an emergency situation occurs, and the status of the elderly living alone cannot be checked in real time due to limited manpower.

Accordingly, in recent years, research and development of a monitoring system that can automatically contact a guardian or emergency center when an emergency situation occurs and install a monitoring device in the house of the elderly living alone using information and communication technology has been actively conducted.

For example, Patent Document 1 introduces a method of determining an emergency situation using an image captured by a camera, and Patent Document 2 introduces a method of determining an emergency situation using a motion detection sensor and a CO2 sensor.

However, Patent Document 1 uses photographed images, so there is a high possibility of invasion of privacy, and it is difficult to immediately confirm when an emergency situation occurs or dies alone while sleeping.

In addition, Patent Literature 2 has a disadvantage in that it is difficult to urgently respond to an emergency situation because it is possible to determine whether a fall or lone death has been observed after monitoring the change in CO2 concentration for a long time.

Registered Patent No. 10-1357721 (announced on Feb. 5, 2014) Registered Patent No. 10-1853471 (announced on April 30, 2018)

An object of the present invention is to provide a monitoring system that can monitor the state of the elderly living alone in real time and respond immediately when an emergency situation occurs, as conceived from this background.

In addition, the purpose of this is to provide a monitoring system that can check and respond in real time even if an emergency situation occurs while sleeping.

In order to achieve this object, an aspect of the present invention is an IoT lighting device including a lighting lamp, a motion detection unit, a CO2 sensor, and a biosignal detection unit; A health condition analysis unit that analyzes a user's health condition using motion data, CO2 concentration data, and biosignal data acquired from the IoT lighting device, and an alarm that generates an alarm command when the health condition analysis unit determines that it is an emergency situation. It provides a monitoring system for the elderly living alone, including a monitoring device including a generating unit and a feedback providing unit for generating a feedback command corresponding to the health condition determined by the health condition analysis unit and transmitting it to the IoT lighting device.

In the monitoring system according to an aspect of the present invention, the bio-signal detection unit includes at least one of a Doppler radar sensor and an Impulse Radio Ultra-WideBand (IR-UWB) radar sensor, and includes a respiratory rate and a pulse rate of a monitored person. Can be detected.

In addition, in the monitoring system according to an aspect of the present invention, the health condition analysis unit determines as an emergency situation when the biological signal of the monitored person detected by the biosignal detection unit is out of the normal range, and generates an alarm command through the alarm generator. And, when the biological signal of the subject to be monitored, detected by the biological signal detection unit, falls within the normal range, it is determined as a healthy state when the CO2 concentration increases within the reference slope range, and the CO2 concentration increases to a slope smaller than the reference slope range. In this case, if it is asleep, it is determined as a healthy state, and if it is not asleep, it is determined as a healthy state, and if it is not asleep, it is determined as a healthy state. When the movement of the person to be monitored is not detected by the detection unit, it may be determined as an emergency situation and an alarm command may be generated through the alarm generating unit.

In addition, in the monitoring system according to an aspect of the present invention, the monitoring device further includes a sleep state determination unit for determining the sleep stage of the user using sound data, motion data, and bio-signals acquired from the IoT lighting device, The feedback providing unit may generate a wake-up alarm generation command only when the user's sleep stage reaches the REM sleep, non-REM sleep stage 1, or non-REM sleep stage 2 during the set alarm possible period.

In another aspect of the present invention, the IoT lighting apparatus includes the steps of acquiring motion data and bio-signal data of a subject to be monitored, and CO2 concentration data of a monitoring area; Transmitting, by the IoT lighting device, the motion data, biometric signal data, and CO2 concentration data to a monitoring device; Determining, by the monitoring device, whether there is an emergency situation using the operation data, biometric signal data, and CO2 concentration data; If it is determined as an emergency situation, it includes generating an alarm command, and in the step of determining whether there is an emergency situation, if the biological signal of the person to be monitored detected by the biological signal detection unit is out of the normal range, it is determined as an emergency situation. If the biological signal of the monitored person detected by the signal detection unit falls within the normal range, it is determined as a healthy state if the CO2 concentration increases within the reference slope range, and if the CO2 concentration increases to a slope smaller than the reference slope range, sleep If it is in a state of health, if it is not in a sleeping state, it is determined as a state of health, and if it is not in a sleep state, it is determined as a health state. If the CO2 concentration increases with a slope that is less than the standard slope range, but not in a sleeping state or in a ventilated state, the motion detection unit monitors It can be judged as an emergency situation if the movement of the vehicle is not detected.

According to the present invention, since it is possible to check the health status in real time by using the bio-signals of the elderly living alone and the CO2 concentration, it is possible to quickly cope with an emergency situation. In addition, even if an emergency situation occurs while the elderly living alone is sleeping, it is possible to quickly respond by checking in real time.

1 is a configuration diagram of a monitoring system according to an embodiment of the present invention
2 is a block diagram of an IoT lighting device according to an embodiment of the present invention
3 is a block diagram of a monitoring device according to an embodiment of the present invention
4 is a diagram illustrating various increasing patterns of CO2
5 is a flow chart showing a method for monitoring the elderly living alone according to an embodiment of the present invention
6 is a flow chart showing a sleep monitoring method according to an embodiment of the present invention

Hereinafter, preferred embodiments of the present invention will be described in detail with reference to the drawings.

For reference, in the present specification, when one element is connected, combined, or communicated with another element, not only the case of direct connection, coupling, or communication with another element, but also another element in the middle This includes cases of indirect connection, association, or communication over and over.

In addition, when a certain part includes a certain component, it means that other components may be further included rather than excluding other components unless specifically stated to the contrary.

As illustrated in FIG. 1, the system for monitoring an elderly living alone according to an embodiment of the present invention includes at least one Internet of Things (IoT) lighting device 100 and an IoT lighting device 100 installed in an indoor room in which the elderly living alone reside. An emergency from the gateway 200, which communicates with the IoT lighting device 100 through the gateway 200, the gateway 200 and the communication network 300, and the monitoring device 400 It may include a guardian terminal 600 carried by a predetermined guardian to receive a call.

The IoT lighting device 100 may wirelessly communicate with a door sensor 500 installed on a front door, a door, and a bathroom door. The door sensor 500 includes a contact type or non-contact type sensor that can determine whether the door is in an open state or a closed state.

The detection result of the door sensor 500 may be used as an important factor in the process of determining the state of the elderly living alone, as illustrated in FIG. 5.

In addition, the IoT lighting device 100 may wirelessly communicate with a portable terminal (not shown in the drawing) such as a smartphone, tablet, or wearable device of a resident of the home.

IoT lighting device 100, as illustrated in the block diagram of FIG. 2, the processor 110, the memory 120, the communication unit 130, the lighting control unit 140, the lighting lamp 142, the motion detection unit 150 , CO ₂ sensor 160, bio-signal detection unit 170, sound output unit 180, may include a bus 190, and the like.

The processor 110 executes a computer program stored in the memory 120 to perform a predetermined operation or data processing. For example, the processor 110 transmits motion data, CO ₂ concentration, bio signal data, etc. detected by the motion detection unit 150, the CO ₂ sensor 160, and the biosignal detection unit 170 to the monitoring device 400, and , In response to the feedback command received from the monitoring device 400, the lighting control unit 140, the sound output unit 180, and the like may be controlled.

The memory 120 may store a computer program for the operation of the IoT lighting device 100. The computer program is a set of instructions executed by the processor 110 and may include an operating system, middleware, an application, or an application programming interface (API).

The memory 120 may include non-volatile memory (eg, flash memory, etc.) and volatile memory (eg, random access memory (RAM)) The computer program may be stored in the non-volatile memory and loaded into the volatile memory to be executed. .

In addition, the memory 120 can store data or commands generated by the processor 110, the communication unit 130, the lighting control unit 140, the motion detection unit 150, the CO ₂ sensor 160, the biosignal detection unit 170, etc. have.

The communication unit 130 may support wireless communication or wired communication. The type of wireless communication is not particularly limited, for example, Wi-Fi, Zigbee, Z-Wave, Bluetooth, Near Field Communication (NFC), mobile communication, RF communication It may include at least one of.

In addition, the communication unit 130 may provide a communication interface between the IoT lighting apparatus 100 and other electronic devices according to an embodiment of the present invention. Other electronic devices capable of communicating with the IoT lighting device 100 may include a gateway 200, another IoT lighting device 100, other types of IoT devices, and home network devices.

In addition, as described above, the IoT lighting apparatus 100 may wirelessly communicate with various door sensors 500 installed in the house, and may wirelessly communicate with portable terminals such as smartphones, tablets, and wearable devices.

The lighting lamp 142 is preferably an LED, but is not limited thereto. In addition, the lighting lamp 142 is preferably capable of expressing two or more colors, such as a color LED, but is not limited thereto.

The lighting control unit 140 turns on or off the lighting 142 in response to a control signal transmitted from the processor 110, changes the lighting color of the lighting 142, or controls dimming. It plays a role of adjusting the brightness through.

The lighting control unit 140 may variously change the color of the lighting lamp 142 according to the health status of the elderly living alone or the degree of pollution of indoor air. As an example, if the biological signal data (heart rate, respiration rate, body temperature, etc.) is in a normal range, it is illuminated in blue, when it is out of the normal range by the first set value, it is illuminated in yellow, and when it is outside the normal range by the second setting value, it is illuminated in red. Can express color.

As another example, when the concentration of CO ₂ detected by the CO ₂ sensor 160 is less than 1,000 ppm, for example, blue color, 1,000 to 2,000 ppm, yellow, and 2,000 ppm or more, the illumination color may be expressed in red.

The motion detection unit 150 is for detecting a motion of a subject to be monitored within a surveillance area, and may include an infrared sensor.

In addition, the motion detection unit 150 is for detecting a posture as well as a movement of a person to be monitored, and may include a camera having an image sensor. The camera may be a general camera or an infrared camera. Instead of installing the motion detection unit 150 in the IoT lighting device 100, it is possible to analyze the motion and posture of the person to be monitored using an image captured by a CCTV installed in the house.

Information, images, images, etc. detected by the motion detection unit 150 may be transmitted to the monitoring device 400.

The biosignal detection unit 170 is for detecting the biosignal of the person to be monitored in the monitoring area, for example, Doppler capable of detecting biosignals such as respiration rate and heart rate in a non-contact manner in a state separated from the body of the person to be monitored. It may include at least one of a (Doppler) radar sensor and an Impulse Radio Ultra-WideBand (IR-UWB) radar sensor.

The Doppler radar sensor uses the Doppler effect in which the frequency of the reflected signal varies depending on the speed of the object when a microwave signal is reflected off a moving object. In particular, when an object reciprocates a certain displacement, the frequency of the reflected signal remains the same, but the respiration rate, heart rate, etc. can be detected from the movement of the human body or the heart by using the characteristic that the phase changes periodically.

The IR-UWB radar sensor uses a broadband signal, which is more resistant to noise than the Doppler radar sensor, and has excellent resolution for detecting minute movements of objects. The IR-UWB radar sensor detects the surrounding situation by transmitting an impulse signal having a duration of several nano-several picoseconds while having a broadband characteristic and receiving the reflected signal.

Meanwhile, the biosignal detection unit 170 may determine the body temperature of the person to be monitored by analyzing the infrared image image acquired by the motion detection unit 150. At this time, it is also possible to determine whether the body temperature of the person to be monitored is in the normal range, whether it is lower than normal, or higher than normal.

Information such as respiration rate, heart rate, body temperature, etc. detected by the biological signal detection unit 170 may be used by the person to be monitored to monitor his or her sleep status, or to notify a guardian or other person in case of an emergency. It can also be used for purposes.

As an example, the biological signal detector 170 may transmit and store data such as respiratory rate, heart rate, and body temperature of the monitored person acquired during sleep to a portable terminal of the monitored person. In this way, the monitored person can check his or her status information while sleeping through the portable terminal after waking up.

As another example, the biological signal detection unit 170 continuously monitors the breathing rate, heart rate, body temperature, etc. of the monitored person, and generates an emergency alarm through the sound output unit 180 when at least one detection value falls below the reference value. It is also possible to send an emergency call to the registered guardian terminal 600, emergency rescue center, etc.

The sound output unit 180 includes a speaker that outputs a predetermined sound in response to a control signal transmitted from the processor 110. The output sound may be a notification message, a warning message, a warning sound, music, or other sounds.

Without installing the sound output unit 180 in the IoT lighting device 100, a Bluetooth speaker installed in the house may be used as a sound output means.

The bus 190 may be a circuit that connects the above-described components to each other and transmits an electrical signal.

Although not shown in the drawing, the IoT lighting apparatus 100 includes a power supply, and the power supply may include a battery, or may be connected to an external AC power or DC power supply.

In addition, the IoT lighting apparatus 100 may include input means such as buttons, keypads, and touch screens for the user to input commands or change settings.

Alternatively, a portable terminal such as a user's smartphone may be used as an input means. In this case, when a user command is input through a dedicated application running on the portable terminal, the input command is the communication unit of the IoT lighting device 100 in the portable terminal. After being transmitted to 130, it may be executed by the processor 110.

In addition, the IoT lighting apparatus 100 may include one or more microphones for detecting sound generated indoors. When multiple microphones are used, a microphone sensitive to a high frequency band and a microphone sensitive to a low frequency band may be used together.

The IoT lighting device 100 or the monitoring device 400 may include a function of distinguishing whose voice is the voice of two or more persons when voices are simultaneously input. To this end, it is desirable to collect voice characteristics of each person in advance and store the speech characteristic values through voiceprint analysis and statistical analysis, or to learn the speech analysis method through machine learning.

In addition, the IoT lighting apparatus 100 may include a voice input means for converting a voice input through a microphone into an input.

The gateway 200 and the communication network 300 are for relaying communication between the IoT lighting device 100 installed in the home and the monitoring device 400 installed outside, and whether wired or wireless, the type of communication protocol, etc. are not particularly limited.

The monitoring device 400 may include a processor 410, a memory 420, a database 430, a communication unit 440, a bus 490, and the like, as illustrated in the block diagram of FIG. 3.

The processor 410 executes a computer program stored in the memory 420 to perform a predetermined operation or data processing.

The memory 420 may store a computer program for operating the monitoring device 400. The computer program is a set of instructions executed by the processor 410 and may include an operating system, middleware, an application, or an application programming interface (API).

Applications stored in the memory 420 and executed by the processor 410 include, for example, a health condition analysis unit 450, a sleep condition analysis unit 460, an alarm generator 470, a feedback providing unit 480, etc. It may include.

At least one of the health condition analysis unit 450, the sleep condition analysis unit 460, the alarm generation unit 470, and the feedback providing unit 480 may be implemented as firmware or hardware.

The health condition analysis unit 450 analyzes and determines the health condition of the user using biosignal data, CO2 concentration data, motion information, etc. of the subject to be monitored received from the IoT lighting device 100.

The health state analysis unit 450 may determine whether or not the biological signal information (respiration rate, heart rate, body temperature, etc.) of the monitored person is in a normal state by comparing with a preset reference value.

In addition, the health condition analysis unit 450 may infer whether the monitored person has a disease or the type of disease by applying a statistical estimation method or a machine learning estimation method based on various bio-signal information and CO2 concentration detected from the monitoring target. .

In addition, the health state analysis unit 450 may infer the state of the monitored person by analyzing the pattern of changes in the CO2 concentration. For example, by collecting data such as the area of the surveillance area, the degree of movement of the monitored person, respiration rate, and CO2 concentration for a long time in advance, a statistical estimation method or machine learning estimation method is applied, based on the change pattern of the CO2 concentration detected indoors. It is possible to estimate the condition of the subject to be monitored.

For example, as illustrated in FIG. 4, when the concentration of CO2 increases within the first slope range, it is a normal state, and when the concentration of CO2 increases rapidly to the second slope range larger than the first slope range, exercise or movement It can be estimated as a state, and if the CO2 concentration increases very rapidly in the third slope range, which is larger than the second slope range, it can be assumed that food is burned or a fire situation.

In addition, if the CO2 concentration gradually increases to the fourth slope range, which is smaller than the first slope range, a sleep or loss of consciousness occurs. If the CO2 concentration does not change, it is a state of loneliness, and if the CO2 concentration decreases, the window or front door is closed. It can be assumed that it is open and ventilated.

Even in a state in which the monitored person loses his mind due to a fall, etc., biosignal data such as pulse rate, respiration rate, body temperature, etc. may be detected in the normal range.According to an embodiment of the present invention, a change pattern of CO2 concentration and movement information of the monitored person By utilizing, it is possible to confirm that the person being monitored is in a state of distraction, and through this, it is possible to respond to an emergency such as sending an emergency call to the guardian terminal 600.

The sleep state analysis unit 460 determines the sleep stage, sleep level, etc. of the subject to be monitored in real time or periodically using posture information, biosignal information, and motion information of the subject to be monitored received from the IoT lighting device 100. .

In general, sleep consists of rapid eye movement (REM) sleep and non-REM sleep alternately, and REM sleep accounts for 20-25% of total sleep, and non-REM sleep accounts for 75-80%. In addition, non-REM sleep is divided into four stages, and it is known that the characteristics of brain waves are different for each stage. For example, theta activity (3.5-7.5Hz) appears in the first stage of sleep, the theta wave, sleep spindle, and sharp waveform K complex appear in the second stage of sleep, and the third stage It is known that a delta wave with a large amplitude (delta activity: 3.5Hz or less) appears on the surface of the water, and the delta wave increases by more than 50% in the fourth stage of sleep. It is known that theta waves appear sporadically in the REM sleep stage.

In these sleep stages, REM sleep and non-REM sleep stages 1 to 2 are divided into shallow sleep, and non-REM sleep stages 3 to 4 can be divided into deep sleep.In general, waking up in a shallow sleep stage will not only wake up quickly, but also reduce fatigue. It is known that waking up in the deep sleep stage not only makes it difficult to get up, but also increases fatigue.

The sleep phase may be determined directly by detecting the brain waves of a sleeping person, or may be determined indirectly using other biometric signals that can be measured in a non-contact manner.

In order to directly detect EEG, an EEG sensor must be attached to the subject, and the detection result of the EEG sensor must be transmitted to the IoT lighting apparatus 100 by wired or wireless communication. Of course, if there is a sensor that can accurately measure brain waves in a non-contact method, it is desirable to use it.

There are statistical estimation methods and machine learning estimation methods for indirectly determining brain waves without measuring them directly.

To apply a statistical estimation method, data such as brain waves, other biological signals (respiration rate, heart rate, body temperature, etc.), posture information, and torsional frequency of the person being monitored while sleeping should be collected for a long period of time and then analyzed for correlation through statistical analysis. . Statistical analysis data may be stored in the DB 430.

Therefore, the monitoring device 400 receives biosignal data such as posture, respiration rate, heart rate, and body temperature of the monitored person detected by the IoT lighting device 100, and then extracts brain waves having a high correlation therewith, and sleeps based on this. You can estimate the steps. The user's sleep level (eg, high, medium, low) can also be estimated by statistically processing the user's experience data on the quality of sleep (eg, slept well, normal, overworked, not slept, etc.).

In order to apply the machine learning estimation method, a learning process that improves the accuracy of output values such as sleep stage and sleep level must be performed using a machine learning algorithm.

The kind of machine learning algorithm is not particularly limited. As an example, machine learning for sleep analysis may be performed using algorithms such as Support Vector Machine (SVM), K-Nearest Neighbor (KNN), and Random Forest. As another example, a machine for sleep analysis using deep learning algorithms based on artificial neural networks (ANNs) such as DNN (Deep Neural Network), CNN (convolutional Neural Network), and RNN (Recurrent Neural Network). You can also run.

The artificial neural network (ANN) of the deep learning algorithm has one or more hidden layers between the input layer and the output layer, and learning through the deep learning algorithm is a node (neuron) of an arbitrary first layer and a second layer. This is the process of optimizing the weights ([W]1...[W]n) given between nodes (neurons) of.

The deep learning algorithm applies the gradient reduction method, etc., based on the error between the output value of the output node and the target value at each learning cycle or at a set cycle, and each weight ([W]1...[W]n ), the accuracy of the output value can be continuously improved.

In an embodiment of the present invention, posture data, respiratory rate data, heart rate data, body temperature data, sound data, etc. received from the IoT lighting device 100 are input to each input node of the input layer, and the output node of the output layer is input. The sleep stage and sleep level corresponding to the information can be output.

The alarm generating unit 470 transmits an alarm to the guardian terminal 600, a portable terminal of the person to be monitored, a control server, an emergency center, etc., when the health condition analysis unit 450 determines that it is an emergency situation.

The alarm generator 470 may send an alarm to the IoT lighting device 100, in this case, the IoT lighting device 100 outputs a predetermined alarm sound after receiving the alarm or turns on the lighting lamp 142 in emergency mode. can do. This has the advantage of being able to respond to an emergency by being able to recognize an emergency situation in the neighboring house of the elderly living alone.

The feedback providing unit 480 may generate various feedback commands according to the determination result of the health condition analysis unit 450 and transmit them to the IoT lighting apparatus 100.

As described above, the feedback command may change the lighting color according to the health condition, may output a predetermined voice, or may be other.

In addition, the feedback providing unit 480 may generate a feedback command based on the determination result of the sleep state analysis unit 460.

For example, the feedback providing unit 480 may determine whether a weather alarm condition is satisfied, and if it is satisfied, may transmit a weather alarm generation command to the IoT lighting apparatus 100. As described above, if the monitored person's sleep status is monitored in real time or periodically, and the wake-up alarm is generated only during the REM sleep or non-REM sleep stage 1~2, the monitored person can get up more easily and feel less tired after waking up. Satisfaction with the use of the IoT lighting device 100 may be greatly improved.

To do this, an alarm available period (eg, 06:30 to 07:30) must be set in advance through the IoT lighting device 100. The set alarm available period is transmitted to the monitoring device 400 and stored, and the feedback providing unit 480 acquires sleep stage information from the sleep state analysis unit 460 for a set period to determine whether a wake-up alarm has occurred, and the alarm condition is set. When satisfied, an alarm command is transmitted to the IoT lighting device 100.

When an alarm command is received, the IoT lighting device 100 may generate a wake-up alarm through the sound output unit 180 and control the lighting control unit 140 to turn on the lighting 142. When turning on the lighting lamp 142, it is preferable to increase the brightness step by step through dimming control.

If the REM sleep or non-REM sleep stage 1~2 does not reach during the set alarm available period, a wake-up alarm can be generated at the end of the set period.

Meanwhile, the feedback providing unit 480 may transmit a white noise generation command to the IoT lighting apparatus 100 when it is determined that the user is unable to sleep and is turning. The IoT lighting device 100 may output white noise, such as rain or water, through the sound output unit 180 in response thereto.

Hereinafter, a method for monitoring the elderly living alone according to an embodiment of the present invention will be described with reference to FIG. 5.

First, the IoT lighting apparatus 100 according to an embodiment of the present invention starts monitoring and first determines whether or not there is an elderly person living alone in the area to be monitored.

The monitoring target area is an area in which data can be collected using the motion detection unit 150, CO2 sensor 160, and the biosignal detection unit 170 of the IoT lighting device 100, and is used in a door or partition such as a room, living room, and bathroom. It is preferable that the area is partitioned from another space, but is not limited thereto.

Whether the elderly living alone enters can be determined using, for example, a door sensor 500 of a front door and an IoT lighting device 100 of a living room. That is, after the front door is opened, if movement is detected in the IoT lighting device 100 in the living room and the CO2 concentration increases, it can be determined that the person to be monitored has entered the house. Conversely, if the front door is opened after motion is detected by the IoT lighting device 100 in the living room and there is no change in the CO2 concentration, it can be determined that the person to be monitored has gone out.

However, the method of determining whether or not the person subject to surveillance is admitted is not particularly limited and may be determined in any other way. For example, it is possible to determine whether to enter the room using a separate entrance sensor. (ST11)

When it is confirmed that the person to be monitored is in the house, the processor 110 of the IoT lighting device 100 performs the motion data detected by the motion detector 150, the CO2 concentration data detected by the CO2 sensor 160, and the biosignal detector 170 ), the biosignal data such as heart rate, respiration rate, body temperature, etc. acquired from the communication unit 130 are transmitted in real time or periodically to the monitoring device 400 through the communication unit 130.

Subsequently, the health condition analysis unit 450 of the monitoring device 400 determines whether the biometric signal data received from the IoT lighting device 100 falls within the normal range. (ST12)

In the above ST12, when it is determined that the biometric signal data received from the IoT lighting device 100 does not fall within the normal range, the alarm generator 470 of the monitoring device 400 transmits an alarm message to the guardian terminal 600, etc. do. For example, if biosignal data is not detected from the IoT lighting device 100 at all, the health condition analysis unit 450 may determine that the person to be monitored is lonely and generate an alarm. (ST17)

If in ST12, it is determined that the biosignal data received from the IoT lighting device 100 falls within the normal range, the health condition analysis unit 450 of the monitoring device 400 increases the CO2 concentration increase or decrease within the reference range. Judge whether or not.

If the increase or decrease pattern of the CO2 concentration is within the normal slope range, the health condition analysis unit 450 may determine that the monitored person's biosignal is normal and the CO2 concentration pattern is also normal, so that the health status analysis unit 450 is in a healthy state. For example, in FIG. 4, if the concentration of CO2 increases within the first and second slope ranges, it can be considered to be within the normal slope range. (ST13)

If the increase/decrease pattern of the CO2 concentration in ST13 is within the normal slope range, the health condition analysis unit 450 determines that the monitored person is in a healthy condition, and it is preferable to perform step ST12 again.

If it is determined in ST13 that the increase/decrease pattern of the CO2 concentration increases within a slope range smaller than the normal slope range, the health condition analysis unit 450 determines whether the monitored person is sleeping. This is because the pattern of increasing and decreasing the concentration of CO2 due to shallow breathing during sleep differs from that of awakening.

Whether sleep is in progress may be determined through the analysis result of the sleep state analysis unit 460. As described above, the sleep state analysis unit 460 may estimate an EEG having a high correlation by using the biological signal information of the person to be monitored and estimate the sleep stage based on this. In addition, the sleep state analysis unit 460 uses a statistical estimation method or a machine learning estimation method based on the biosignal data of the person to be monitored, the attitude data of the person to be monitored detected through the motion detection unit 150, and voice data collected through a microphone. It can be applied to determine whether the person being monitored sleeps.

When it is determined that the monitored person is sleeping, the health condition analysis unit 450 may determine that the monitored person is in a healthy condition. (ST14)

If it is determined that the person is sleeping in ST14, it is preferable that the health state analysis unit 450 determines that the person to be monitored is in a health state and performs step ST12 again.

On the other hand, if the monitored person is not sleeping in the above ST14, the monitored person may be in an abnormal state or may be ventilating with a window open. Therefore, the health condition analysis unit 450 needs to perform an additional analysis through the following process.

That is, it is necessary to check the time and period when the window or front door is opened through the door sensor 500 installed on a window or a front door, and determine whether ventilation has been performed through this. However, if the door is opened for a very short period of time, it is not considered to have been ventilated, so it is necessary to set a reference value for determining whether to ventilate through a preliminary experiment. (ST15)

If the ST15 determines that there is ventilation, the increase/decrease pattern of the CO2 concentration due to the ventilation is outside the normal slope range, and there is a possibility that the person to be monitored has gone out while the door is open. It is preferable to perform it again from step ST11 of determining.

If it is determined that there is no ventilation in ST15, there is a possibility that an emergency situation has occurred to the monitored person because the increase/decrease pattern of the CO2 concentration is outside the normal slope range even though there is no ventilation.

In this case, for accurate determination, the degree of movement and the movement distance of the user are determined by using the movement data detected through the movement detection unit 150. (ST16)

If the degree of movement is out of the set value, it can be seen that the user does not stay in the surveillance area for a long time and moves frequently, so that the person to be monitored can be determined as a health state. However, in this case, since there is a possibility that the subject to be monitored has gone out, the health condition analysis unit 450 is preferably performed again from step ST11, which determines whether the subject to be monitored is in the house.

When there is no motion or very weakly detected in ST16, the health condition analysis unit 450 may generate an alarm by determining that the monitored person is unconscious or unable to move. (ST17)

Next, a sleep monitoring method according to an embodiment of the present invention will be described with reference to FIG. 6.

First, the operation mode of the IoT lighting device 100 is switched to a sleep monitoring mode. The operation mode of the IoT lighting apparatus 100 may be switched to the sleep monitoring mode by inputting a mode switching command by the user, or may be automatically switched to the sleep monitoring mode when the mode switching condition is satisfied. For example, at a set time (e.g., 23:00), it is switched to the sleep monitoring mode, or when the light 142 is turned off, it is switched to the sleep monitoring mode, or the light 142 is turned off after the set time so that it is switched to the sleep monitoring mode. Can be set.

When the IoT lighting device 100 is switched to the sleep monitoring mode, the processor 110 stores posture data, heart rate data, respiration rate data, sound data, etc. acquired from the motion detection unit 150, the biometric signal detection unit 170, and the like. It transmits in real time or periodically to the monitoring device 400 through the communication unit 130. (ST31)

The sleep state analysis unit 460 of the monitoring device 400 determines whether the user has fallen asleep or is turning by using the data received from the IoT lighting device 100. For example, after operating in the sleep monitoring mode, if the frequency of turning over a set period of time exceeds the reference value, it may be determined as a step of turning over without falling asleep. (ST32)

When the sleep state analysis unit 460 determines that the tossing step is performed, the feedback providing unit 480 transmits a white noise generation command to the IoT lighting device 100, and the IoT lighting device 100 responds with the sound of rain, water, and library. White noise such as sound is output. (ST33)

The sleep state analysis unit 460 may determine whether the state is in apnea after the tossing determination step. The sleep state analysis unit 460 may determine whether or not to breathe by using the breathing data acquired through the biosignal detection unit 170 and/or sound data detected by the microphone. (ST34)

If the sleep state analysis unit 460 determines that the apnea stage is in the apnea phase, the feedback providing unit 480 transmits a warning feedback generation command to the IoT lighting device 100, and the IoT lighting device 100 may output a warning sound in response thereto. have. If the sleep condition analysis unit 460 determines that it is an emergency situation, the IoT lighting device 100 not only outputs a warning sound, but also turns on the lighting lamp 142, outputs a warning sound to the IoT lighting apparatus 100 in another bedroom, and turns on the lighting lamp 142. I can turn it on. (ST35)

Meanwhile, the feedback providing unit 480 checks whether or not the wake-up time set by the user has arrived, and if the wake-up time has not arrived, repeats the above process and determines whether the wake-up time is satisfied or not.

Weather conditions can be specific sleep stages. That is, the feedback providing unit 480 may determine that the wake-up condition is satisfied if the user's sleep stage is, for example, REM sleep, non-REM sleep stage 1, or non-REM sleep stage 2, for example. However, since it is not limited thereto, only the REM sleep stage may be set as a weather condition, or the REM sleep or non-REM sleep stage 1 may be set as the weather condition.

At this time, as described above, in the case of two or more sleeping in one bedroom, the sleeping stages of each person can be checked and determined as satisfying the weather conditions only when the sleeping stages of all people satisfy the set conditions. (ST36, ST37)

When it is determined that the weather condition is satisfied, the feedback providing unit 480 transmits a weather alarm generation command to the IoT lighting device 100, and the IoT lighting device 100 outputs a weather alarm set in response thereto. (ST38)

In the above, a preferred embodiment of the present invention has been described, but the present invention is not limited to the above-described embodiment and may be modified and implemented in various forms.

For example, although FIG. 1 shows that the monitoring device 400 is an external server, it is not limited thereto.

Accordingly, at least one of the programs executed in the monitoring device 400 may be installed and executed directly in the IoT lighting device 100 or may be installed and executed in another IoT device in the home. In addition, it may be installed and executed on a portable terminal such as a user's smart phone capable of communicating with the IoT lighting device 100 or a user's premises computer.

As described above, the present invention may be variously modified or modified in a specific application process, and if the modified or modified embodiment includes the technical idea of the present invention disclosed in the claims to be described later, it is natural that it belongs to the scope of the present invention. Will do.

100: IoT lighting device 110: Processor 120: Memory
130: communication unit 140: lighting control unit 142: lighting
150: motion detection unit 160: CO2 sensor 170: biological signal detection unit
180: sound output unit 190: bus 200: gateway (G/W)
300: communication network 400: monitoring device 410: processor
420: memory 430: DB 440: communication unit
450: health condition analysis unit 460: sleep condition analysis unit 470: alarm generation unit
480: feedback providing unit 490: bus 500: guardian terminal

Claims (5)

IoT lighting device having a lighting lamp, a motion detection unit, a CO2 sensor, and a biosignal detection unit;
A door sensor that is installed on a window or door to check whether it is opened or closed and transmits opening/closing information to the IoT lighting device;
A health condition analysis unit that analyzes the user's health condition using motion data, CO2 concentration data, and bio-signal data acquired from the IoT lighting device, and acoustic data, motion data, and bio-signal data acquired from the IoT lighting device. Using a sleep state determination unit to determine whether the user is sleeping and the sleep stage, an alarm generation unit that generates an alarm command when the health state analysis unit determines that it is an emergency situation, and the health state or the health state determined by the health state analysis unit Monitoring device having a feedback providing unit for generating a feedback command corresponding to the sleep state determined by the sleep state determination unit and transmitting it to the IoT lighting device
It includes, the health state analysis unit,
When the biological signal of the monitored person detected by the biological signal detection unit of the IoT lighting device is out of the normal range, it is determined as an emergency situation and an alarm command is generated through the alarm generator,
When the biological signal of the person to be monitored detected by the biological signal detection unit falls within the normal range,
If the CO2 concentration increases within the standard slope range, it is judged as a healthy state,
If the CO2 concentration increases to a slope smaller than the standard slope range, it is determined as a health state if it is asleep, and if it is not asleep, a health state if it is confirmed as a ventilation state by information from the door sensor received from the IoT lighting device. Judged by
If the CO2 concentration increases with a slope smaller than the standard slope range, but is neither sleeping nor ventilated, it is determined as an emergency situation when the motion detection unit of the IoT lighting device does not detect the movement of the person to be monitored and the alarm generating unit A monitoring system for the elderly living alone, characterized in that generating an alarm command through The method of claim 1,
The bio-signal detection unit includes at least one of a Doppler radar sensor and an Impulse Radio Ultra-WideBand (IR-UWB) radar sensor, and detects a respiratory rate and a pulse rate of a monitored person. delete The method of claim 1,
The sleep state determination unit checks the frequency of the user turning over for a set time,
The feedback providing unit transmits a white noise generation command to the IoT lighting device when the user's turning frequency is more than a reference value, while the user's sleep stage reaches REM sleep, non-REM sleep stage 1, or non-REM sleep stage 2 during a set alarm possible period. A monitoring system for the elderly living alone, characterized in that it generates a wake-up alarm command for only one case An IoT lighting device including a motion detector, a CO2 sensor, and a biosignal detector, acquiring motion data and biosignal data of a person to be monitored, and CO2 concentration data of the monitoring area;
Transmitting, by the IoT lighting device, the motion data, biometric signal data, and CO2 concentration data to a monitoring device;
Determining, by the monitoring device, whether there is an emergency situation using the operation data, biometric signal data, and CO2 concentration data;
Step of generating an alarm command when it is judged as an emergency situation
Including,
In the step of determining whether there is an emergency,
If the biological signal of the monitored person detected by the IoT lighting device is out of the normal range, it is determined as an emergency situation,
When the biological signal of the person to be monitored falls within the normal range,
If the CO2 concentration increases within the standard slope range, it is judged as a healthy state,
If the CO2 concentration increases with a slope smaller than the standard slope range, it is determined as a healthy state if it is asleep, and if it is not asleep, a healthy state if it is confirmed as a ventilation state by information from the door sensor received from the IoT lighting device. Judged by
Monitoring the elderly living alone, characterized in that when the CO2 concentration increases with a slope smaller than the reference slope range, but is neither sleeping nor ventilated, it is determined as an emergency situation when the movement of the monitored person is not detected by the IoT lighting device. Way

Images