KR102330328B1 - Monitoring Method for the Old and the Weak Care - Google Patents

Abstract

A monitoring method for the care of the elderly according to the present invention includes the steps of: detecting a reflected wave of a radio signal reflected from an object to obtain location information of the object; and generating an event when the object does not move during a threshold time proportional to the location information weight set differently according to location information.

Description

Monitoring Method for the Old and the Weak Care

The present invention relates to a monitoring method for the care of the elderly, and more particularly, to a method capable of monitoring the health abnormality of the elderly.

As the size of the family decreases and the aging society enters, the number of elderly and infirm living alone without a guardian is increasing. Since the elderly living alone are left vulnerable to health problems and emergencies, countermeasures are being taken.

As Closed Circuit Television (hereinafter referred to as CCTV) develops and spreads, a method of using CCTV installed in a living space to monitor the health status of the elderly has been proposed. A method of monitoring the elderly based on video, such as CCTV, significantly infringes on the privacy of the monitoring target. In addition, the monitoring method using image capturing has a limit in the monitoring target area because a shadow area is generated due to an obstacle. In addition, since a situation may occur in which image capturing is impossible due to ambient illuminance or light reflection, the monitoring method using image capturing has a disadvantage in that it cannot continuously monitor an object.

A method of monitoring the elderly using a voice signal other than video recording has been proposed, but even when using a voice signal, the problem of invasion of privacy of the monitored person is still not solved. In addition, the method using the voice signal has a problem in that accuracy is low because it has severe noise due to ambient noise, and it is impossible to cope with the case where the subject to be monitored falls silently.

Recently, a method of monitoring the health status of the elderly and weak using portable devices such as smart phones and wearable devices has been proposed. The portable device may cause inconvenience to the monitoring target, and the monitoring target has a disadvantage in that the portable device needs to be continuously supplied with power.

SUMMARY OF THE INVENTION The present invention aims to solve the above and other problems.

An object of the present invention is to provide a monitoring method for the care of the elderly that can minimize the invasion of privacy of the subject to be monitored.

Another object of the present invention is to provide a method for continuously and accurately monitoring the health status of the elderly and infirm while eliminating the shadow area.

In addition, in order to practice the present invention, it is to provide a monitoring method for the care of the elderly that can reduce the discomfort of the subject to be monitored.

In order to achieve the above technical problem, the monitoring method for the care of the elderly according to the present invention includes the steps of detecting a reflected wave of a radio signal reflected from an object to obtain location information of the object, and monitoring the amount of change in location information to determine the object over time and generating an event when the object does not move for a critical time proportional to a weight of location information set differently according to location information.

Since the present invention does not use image capture or audio signals in the process of monitoring the object, it is possible to minimize the invasion of privacy of the object.

In addition, since the present invention does not use image capturing, it is possible to solve the problem of difficult to monitor the state of the object due to the ambient illuminance and light reflection of the monitoring target. Since the present invention does not use a voice signal, it is possible to solve the problem that it is difficult to monitor the state of the object due to the surrounding noise. In addition, because the chirp radar method is used, the object can be monitored without being affected by obstacles. As a result, the present invention can monitor an object without being affected by an obstructive element and without a shadow area.

In addition, since the object does not need to attach or hold an additional device to the body in order to practice the present invention, the object may not feel discomfort.

1 is a view showing a monitoring system for health care according to the present invention.
2 is a view showing a monitoring method for care for the elderly according to the present invention.
3 is a diagram illustrating an embodiment of a Tx1 signal transmitted by a first transmitter.
4 is a diagram illustrating a Tx1 signal and an Rx1 signal.
5 is a diagram illustrating an example of a change in a first separation distance according to time.
6 and 7 are diagrams for explaining an embodiment in which the location information calculating unit calculates location information.
8 is a diagram illustrating the configuration of an artificial intelligence device belonging to an event determining unit.
9 is a diagram illustrating an embodiment in which a biometric information analysis unit analyzes biometric information.

Since the technology to be described below may have various changes and may have various embodiments, specific embodiments will be illustrated in the drawings and described in detail. However, this is not intended to limit the technology described below to specific embodiments, and it should be understood to include all changes, equivalents, or substitutes included in the spirit and scope of the technology described below.

Terms such as first, second, A, and B may be used to describe various components, but the components are not limited by the above terms, and only for the purpose of distinguishing one component from other components. used only as For example, a first component may be named as a second component, and similarly, a second component may also be referred to as a first component without departing from the scope of the technology to be described below. and/or includes a combination of a plurality of related listed items or any of a plurality of related listed items.

In terms of the terms used herein, the singular expression should be understood to include a plural expression unless the context clearly dictates otherwise, and terms such as "comprises" refer to the described feature, number, step, operation, and element. , parts or combinations thereof are to be understood, but not to exclude the possibility of the presence or addition of one or more other features or numbers, step operation components, parts or combinations thereof.

Prior to a detailed description of the drawings, it is intended to clarify that the classification of the constituent parts in the present specification is merely a division according to the main function that each constituent unit is responsible for. That is, two or more components to be described below may be combined into one component, or one component may be divided into two or more for each more subdivided function. In addition, each of the constituent units to be described below may additionally perform some or all of the functions of other constituent units in addition to the main function it is responsible for. Of course, it may be carried out by being dedicated to it.

In addition, in performing the method or the method of operation, each process constituting the method may occur differently from the specified order unless a specific order is clearly described in context. That is, each process may occur in the same order as specified, may be performed substantially simultaneously, or may be performed in the reverse order.

Monitoring system for healthcare

1 is a view showing a monitoring system for health care according to the present invention.

Referring to FIG. 1 , the monitoring system for health care according to the present invention includes first and second wireless signal transceivers 110 and 120 and a signal analysis unit 200 .

The first radio signal transceiver 110 includes a first transmitter 111 and a first receiver 112 , and the second radio signal transceiver 120 includes a second transmitter 121 and a second receiver 122 . do. The first transmitter 111 transmits a Tx1 signal, and the first receiver 112 receives an Rx1 signal in which the Tx1 signal is reflected from the object 10 . Similarly, the second transmitter 121 transmits a Tx2 signal, and the second receiver 122 receives an Rx2 signal in which the Tx2 signal is reflected from the object 10 .

Tx (Transmission) represents a transmission signal, and Rx (Reception) represents a received signal.

That is, the Tx 1 signal and the Tx 2 signal respectively indicate the transmission signal 1 and the transmission signal 2, and Rx 1 and Rx 2 indicate the reception signal 1 and the reception signal 2, respectively.

The signal analysis unit 200 includes a signal processing unit 210 , a location information calculation unit 220 , an event determination unit 230 , and a biometric information analysis unit 240 .

The signal processing unit 210 includes an amplifier for amplifying the Tx signals Tx1 and Tx2 and the Rx signals Rx1 and Rx2 and a digital signal processing unit for extracting an effective signal from the signals amplified by the amplifying unit. signal process). The amplifying unit may use a low noise amplifier (LNA).

The location information calculating unit 220 calculates the separation distance between the first wireless signal transceiver 110 and the object 10 based on the Tx1 signal and the Rx1 signal from the signal processing unit 210, and based on the Tx2 signal and the Rx2 signal to calculate the separation distance between the second wireless signal transceiver 120 and the object 10 . In the present specification, the object 10 refers to a natural person, and in particular refers to an elderly person subject to monitoring.

In addition, the location information calculator 220 calculates location information Pxy of the object 10 based on the separation distance between the object 10 and the first and second wireless signal transceivers 110 and 120 . The location information Pxy refers to two-dimensional coordinates indicating the location of the object 10 within the monitoring target area.

The event determiner 230 receives the location information Pxy from the location information calculator 220 and determines whether an event occurs according to the amount of change in the location information Pxy.

In particular, the event determiner 230 determines whether an event occurs in consideration of weights set differently according to the location information Pxy and meta information. The event may be generated when the location of the monitored object 10 based on the location information Pxy stays in one place for a predetermined time.

The biometric information analysis unit 240 interprets the biometric information of the object 10 when an event occurs. The biometric information of the object 10 is acquired based on specific frequencies of the Rx signals Rx1 and Rx2, and the presence or absence of abnormalities in the acquired biometric information is analyzed. The biometric information acquired by the event determiner 230 may be a heart rate or the like. The biometric information analysis unit 240 may take a relief action according to the analyzed body information. Relief measures may include an operation of calling a relief organization, and in this case, the body information obtained by the event determining unit 230 may be transmitted to the relief organization.

Monitoring methods for the care of the elderly

2 is a view showing a monitoring method for care for the elderly according to the present invention.

With reference to FIGS. 1 and 2 , the monitoring method for the care of the elderly according to the present invention will be described in detail as follows.

In the first step (S210), the location information calculator 220 acquires the location information (Pxy) of the object 10 based on the reflected wave of the radio signal.

In order to obtain the location information (Pxy) of the object 10, the location information calculating unit 220 is a separation distance between the first wireless signal transceiver 110 and the object 10 and the second wireless signal transceiver 120 and the object (10) Calculate the distance between them.

First, a method of calculating the separation distance between the first wireless signal transceiver 110 and the object 10 will be described as follows.

The first radio signal transceiver 110 transmits a Tx1 signal and receives Rx1 signals in order to calculate a separation distance from the object 10 . 3 is a diagram illustrating an embodiment of a Tx1 signal transmitted by a first transmitter, and FIG. 4 is a diagram illustrating a Tx1 signal and Rx1 signals received by the first receiver.

3 and 4 , the first transmitter 111 may transmit a chirp signal whose frequency varies according to time as a Tx1 signal. Like the Tx1 signal, the Rx1 signals received by the first receiver 112 have different frequencies according to time, which is the same as the delayed Tx1 signal. Since the Tx1 signal is reflected by various objects having different distances from each other, the first receiver 112 may receive a plurality of Rx1 signals as shown in FIG. 4 . Since the frequency of the Tx1 signal and the Rx1 signal varies according to time, the frequency of the Rx1 signal received at a specific point in time can be determined at which point in time the Tx1 signal is delayed.

Similarly, the second transmitter 121 transmits the Tx2 signal, and the second receiver 122 receives the Rx2 signal.

The signal processing unit 210 receives the Tx2 signal and Rx2 signals from the second wireless signal transceiver 120 together with the Tx1 signal and Rx1 signals from the first wireless signal transceiver 110 .

The signal processing unit 210 amplifies the Tx signals Tx1 and Tx2 and the Rx signals Rx1 and Rx2 and extracts an effective signal from among the amplified signals.

The location information calculating unit 220 receives the Tx signals Tx1 and Tx2 and the Rx signals Rx1 and Rx2 passed through the signal processing unit 210 .

The location information calculator 220 estimates any one of the plurality of Rx1 signals as a reflected wave reflected from the object 10 . The location information calculator 220 estimates the reflected wave from the object 10 based on the amount of change in which the Rx1 signals are delayed. Since the object 10 is a natural person, it continuously moves even a little bit, and the delay degree of the reflected wave from the object 10 is continuously changed. Accordingly, the location information calculating unit 220 estimates that the Rx1 signal with a continuously varying degree of delay is a reflected wave reflected from the object 10 . Hereinafter, in the present specification, the Rx1 signal and the Rx2 signal refer to a reflected wave reflected from the object 10 .

The location information calculator 220 calculates a first separation distance between the first radio signal transceiver 110 and the object 10 based on the degree of delay of the Rx1 signal from the Tx1 signal. As shown in FIG. 5 , the location information calculator 220 may calculate a change in the first separation distance d1 according to time.

In this way, the location information calculator 220 may calculate a change in the second separation distance between the second wireless signal transceiver 120 and the object 10 based on the Tx2 signal and the Rx2 signal.

The location information calculator 220 calculates location information Pxy of the object 10 based on the first and second separation distances. The location information Pxy may correspond to two-dimensional coordinates indicating the location of the object 10 in the monitoring target area.

6 and 7 are diagrams for explaining an embodiment in which the location information calculating unit calculates location information. 6 illustrates a monitoring target area, and FIG. 7 illustrates a transformation of the monitoring target area into two-dimensional coordinates.

6 and 7 , the position of the first radio signal transceiver 110 is indicated by "x1" coordinates on the coordinates, and the position of the second radio signal transceiver 120 is indicated by "x2" coordinates on the coordinates. . The separation distance ds between the x1 coordinates and the x2 coordinates is stored in advance in the location information calculating unit 220 .

The location information calculating unit 220 calculates two-dimensional coordinates corresponding to the location information Pxy of the object 10 based on the first separation distance d1 and the second separation distance d2 at an arbitrary timing. The location information calculator 220 may calculate the location information Pxy of the object 10 at an arbitrary timing, and calculates the location information Pxy of the object 10 that is time-series continuous in a predetermined time unit. .

In the second step (S220), the event determiner 230 monitors the movement of the object 10 based on the change amount of the location information (Pxy).

The event determiner 230 may generate a vector connecting the calculated position information Pxy at two timings, and may determine the size of the vector as a change amount of the position information Pxy. The location information calculator 220 may determine the amount of change of the location information Pxy within 1 millimeter (mm) according to the resolution of analyzing the radio signal. In an embodiment of the present invention, since the event is determined depending on whether the object 10 moves, when the amount of change in the location information Pxy is several centimeters (cm) or less, it can be considered that the object 10 does not move. . The event determiner 230 determines that the object 10 moves when the amount of change in the location information Pxy is greater than or equal to the movement threshold based on the preset movement threshold.

In the third step (S230), the event determination unit 230 monitors whether there is no movement of the object 10 for a critical time.

In the fourth step (S240), the event determination unit 230 generates an event when the state in which the object 10 does not move reaches a threshold time. That is, when the period for which the object 10 stays in a specific place becomes longer than necessary, the event determiner 230 determines an event by determining that there is an abnormality in the body of the object 10 .

The active time of the object 10 is different in the monitoring target area, for example, in the residential space. For example, you can stay for a long time in a room where a bed is placed, and you can stay for a relatively short time in a bathroom or in front of the entrance. Accordingly, the threshold time, which is a criterion for event determination, varies according to the location information Pxy of the object 10 . That is, the event determiner 230 sets the threshold time by varying the location information weight Wp according to the location information Pxy.

Table 1 below is a table showing an example of location information weights set according to location information.

location information Location information weight (Wp) Room 1 (Bed) 200 room 2 72 living room 36 bathroom 6

The event determiner 230 may set a result of multiplying the reference time T_ref and the location information weight Wp as the threshold time T_th. That is, the result calculated by "T_refХWp" may be set as the threshold time T_th. If the reference time (T_ref) is set to 100 (seconds), the critical time for the coordinates belonging to the toilet corresponds to "600 seconds = 10 minutes". That is, the event determiner 230 generates an event when it is determined that the location information Pxy of the object 10 is in a state of not moving for 10 minutes in a state belonging to the toilet.

Table 1 shows schematic weights for explaining the present invention, and the monitoring target area may be classified into a more subdivided area than shown in Table 1. For example, since the time when using the bathtub and the washbasin may be different for the object 10 even in the bathroom, it is possible to subdivide the area in the bathroom and give weight to the object 10 . Similarly, the weight of "Room 1" in which the bed is placed may have different weights for the area where the bed is located and for areas other than the bed.

The event determiner 230 may consider meta information in the process of calculating the threshold time T_th. The meta information may include month, day, time, weather, temperature, and the like.

The event determiner 230 may assign a meta information weight Wm to each piece of meta information, and calculate a threshold time T_th in which the meta information weight Wm is considered. For example, the event determiner 230 may calculate the threshold time T_th to be proportional to the reference time T_ref, the location information weight Wp, and the meta information weight Wm. That is, the threshold time T_th can be calculated through the operation of "T_refХWpХWm".

The arbitrary meta information weight Wm may be the same for all location information Pxy, or the meta information weight Wm may vary according to each location information Pxy. Alternatively, the meta information weight wm may be considered only for specific location information Pxy. In addition, two or more meta-information may be reflected according to arbitrary location information Pxy.

Table 2 below is a table showing an example of meta information weights with respect to time.

location information
Meta information weight (Wm) 08:00~22:00 08:00~09:00 Room 1 (Bed) 0.1 ... room 2 ... ... living room ... ... bathroom ... 1.5

Referring to Table 2, when the location information belongs to the "bed" area, the meta information weight Wm has a size of "0.1" from 08:00 to 22:00. This is to reduce the critical time (T_th) by 10% in the corresponding time range considering that the object 10 does not stay in the bed area for a long time other than the bedtime.

When the location information belongs to the "bathroom" area, the meta information weight Wm has a size of "1.5" from 08:00 to 09:00. This is to increase the threshold time T_th in the corresponding time range in consideration of the time the object 10 uses the bathroom during the morning time.

As such, the meta information weight Wm may be set to adjust the threshold time T_th in consideration of the time the object 10 stays in a specific place at a specific time.

Similarly, the meta-information weight Wm may be set in consideration of a change in the length of time the object 10 stays in a specific place according to meta-information.

As described above, the event determination unit 230 calculates a threshold time (T_th), which is a criterion for generating an event, by using the location information weight (Wp) and the meta information weight (Wm). In particular, the event determiner 230 may learn the location information (Pxy) and meta information based on artificial intelligence, and correct the location information weight (Wp) and the meta information weight (Wm) in real time based on this.

The living pattern of the object 10 may change from time to time, and the structure of the space to be monitored may also vary. Therefore, even if the location information weight (Wp) and the meta information weight (Wm) are set in consideration of the living pattern of the object 10 and the space of the monitoring target, the accuracy of determining the occurrence of an event over time may decrease. .

The event determiner 230 may analyze the movement pattern of the object 10 by accumulating the location information Pxy that changes in time series and learning it. The event determiner 230 may modify the location information weight Wp in consideration of the movement pattern of the object 10 learned based on artificial intelligence as described above.

In addition, the event determiner 230 learns the movement pattern of the object 10 and at the same time learns the change of meta information. In addition, the event determiner 230 may analyze the involvement of meta information in the movement pattern of the object 10 and correct the meta information weight Wm based on this.

The event determiner 230 may consider the location information weight Wp and the meta information weight Wm of other objects in the process of correcting the location information weight Wp and the meta information weight Wm. The event determiner 230 may learn location information weights Wp and meta information weights Wm between objects in consideration of the age, gender, and life patterns of other objects, and may reflect them.

In particular, the event determination unit 230 additionally learns when an event occurs and the result of analyzing the biometric information of the object 10 according to the occurrence of the event to obtain a location information weight (Wp) and a meta information weight (Wm) Can be modified.

In order to perform the AI processing as described above, the event determiner 230 of the present invention may include an AI device.

The AI device 20 according to an embodiment of the present invention may include an electronic device including an AI module capable of performing AI processing, or a server including an AI module. In addition, the AI device 20 may be included as a component of at least a part of the event determiner 230 to perform at least a part of AI processing together.

AI processing may include all operations related to the control of the event determiner 230 . For example, the event determiner 230 may process/determine the location information weight (Wp) and the meta information weight (Wm) by AI-processing and determine the event.

The AI apparatus 20 may be a client device that directly uses the AI processing result or a device in a cloud environment that provides the AI processing result to other devices.

Referring to FIG. 8 , the AI device 20 according to the present invention may include an AI processor 21 , a memory 25 and/or a communication unit 27 .

The AI device 20 is a computing device capable of learning a neural network, and may be implemented in various electronic devices such as a server, a desktop PC, a notebook PC, and a tablet PC.

The AI processor 21 may learn the neural network using a program stored in the memory 25 . In particular, the AI processor 21 may learn a neural network for recognizing the location information weight (Wp) and the meta information weight (Wm). Here, the neural network for recognizing the location information weight (Wp) and the meta information weight (Wm) may be designed to simulate the human brain structure on a computer, and a plurality of network nodes that simulate the neurons of the human neural network may include The plurality of network modes may transmit and receive data according to a connection relationship, respectively, so as to simulate a synaptic activity of a neuron in which a neuron sends and receives a signal through a synapse. Here, the neural network may include a deep learning model developed from a neural network model. In a deep learning model, a plurality of network nodes may exchange data according to a convolutional connection relationship while being located in different layers. Examples of neural network models include deep neural networks (DNN), convolutional deep neural networks (CNN), Recurrent Boltzmann Machine (RNN), Restricted Boltzmann Machine (RBM), deep trust It includes various deep learning techniques such as neural networks (DBN, deep belief networks) and deep Q-networks, and can be applied to fields such as computer vision, speech recognition, natural language processing, and voice/signal processing.

Meanwhile, the processor performing the above-described function may be a general-purpose processor (eg, CPU), but may be an AI-only processor (eg, GPU) for artificial intelligence learning.

The memory 25 may store various programs and data necessary for the operation of the AI device 20 . The memory 25 may be implemented as a non-volatile memory, a volatile memory, a flash-memory, a hard disk drive (HDD), or a solid state drive (SDD). The memory 25 is accessed by the AI processor 21 , and reading/writing/modification/deletion/update of data by the AI processor 21 may be performed. Also, the memory 25 may store a neural network model (eg, the deep learning model 26 ) generated through a learning algorithm for data classification/recognition according to an embodiment of the present invention.

Meanwhile, the AI processor 21 may include a data learning unit 22 that learns a neural network for data classification/recognition. The data learning unit 22 may learn a criterion regarding which training data to use to determine data classification/recognition and how to classify and recognize data using the training data. The data learning unit 22 may learn the deep learning model by acquiring learning data to be used for learning and applying the acquired learning data to the deep learning model.

The data learning unit 22 may be manufactured in the form of at least one hardware chip and mounted on the AI device 20 . For example, the data learning unit 22 may be manufactured in the form of a dedicated hardware chip for artificial intelligence (AI), or may be manufactured as a part of a general-purpose processor (CPU) or a graphics-only processor (GPU) to the AI device 20 . may be mounted. Also, the data learning unit 22 may be implemented as a software module. When implemented as a software module (or a program module including instructions), the software module may be stored in a computer-readable non-transitory computer readable medium. In this case, the at least one software module may be provided by an operating system (OS) or may be provided by an application.

The data learning unit 22 may include a training data acquiring unit 23 and a model learning unit 24 .

The training data acquisition unit 23 may acquire training data required for a neural network model for classifying and recognizing data. For example, the training data acquisition unit 23 may acquire, as training data, a position information weight Wp and a meta information weight Wm to be input to the neural network model.

The model learning unit 24 may use the acquired training data to learn so that the neural network model has a criterion for determining how to classify predetermined data. In this case, the model learning unit 24 may train the neural network model through supervised learning using at least a portion of the training data as a criterion for determination. Alternatively, the model learning unit 24 may learn the neural network model through unsupervised learning for discovering a judgment criterion by self-learning using learning data without guidance. Also, the model learning unit 24 may train the neural network model through reinforcement learning using feedback on whether the result of the situation determination according to the learning is correct. Also, the model learning unit 24 may train the neural network model by using a learning algorithm including an error back-propagation method or a gradient decent method.

When the neural network model is trained, the model learning unit 24 may store the learned neural network model in a memory. The model learning unit 24 may store the learned neural network model in the memory of the server connected to the AI device 20 through a wired or wireless network.

The data learning unit 22 further includes a training data preprocessing unit (not shown) and a training data selection unit (not shown) to improve the analysis result of the recognition model or to save resources or time required for generating the recognition model You may.

The learning data preprocessor may preprocess the acquired data so that the acquired data can be used for learning for situation determination. For example, the training data preprocessor may process the acquired data into a preset format so that the model learning unit 24 may use the acquired training data for image recognition learning.

In addition, the learning data selection unit may select data required for learning from among the learning data acquired by the learning data acquiring unit 23 or the training data preprocessed by the preprocessing unit. The selected training data may be provided to the model learning unit 24 . For example, the training data selection unit may select the training data centering on a specific area from the location information obtained by the location information calculating unit 220 .

In addition, the data learning unit 22 may further include a model evaluation unit (not shown) in order to improve the analysis result of the neural network model.

The model evaluator may input evaluation data to the neural network model and, when an analysis result output from the evaluation data does not satisfy a predetermined criterion, may cause the model learning unit 22 to learn again. In this case, the evaluation data may be predefined data for evaluating the recognition model. As an example, the model evaluator may evaluate as not satisfying a predetermined criterion when, among the analysis results of the learned recognition model for the evaluation data, the number or ratio of evaluation data for which the analysis result is not accurate exceeds a preset threshold. have.

The communication unit 27 may receive meta information from the outside and also transmit the AI processing result to the outside. For example, the communication unit 27 may receive meta information such as weather through a weather observation server. In addition, according to the result of the biometric information analysis unit 240 , a relief action may be transmitted to a relief organization through the communication unit 27 .

On the other hand, the AI device 20 shown in FIG. 8 has been described as functionally divided into the AI processor 21, the memory 25, the communication unit 27, and the like, but the above-described components are integrated into one module and the AI module may be called as In addition, the AI device 20 shown in FIG. 8 corresponds to one embodiment, and an additional configuration may be added for AI processing, or an arbitrary configuration may be omitted.

In the fifth step (S250), the biometric information analysis unit 240 interprets the biometric information of the object 10 when an event occurs.

How to interpret biometric information

9 is a diagram illustrating an embodiment in which the biometric information analysis unit 240 analyzes biometric information.

Referring to FIG. 9 , the biometric information analysis unit 240 analyzes the biometric information based on the reflected wave. For example, the Rx1 signal may include a main frequency fm and a peripheral frequency fs. The main frequency fm is used to detect the motion of the object 10 described above. In addition to the movement of the object 10 , the Rx1 signal is mixed with a fine peripheral frequency fs according to the heart rate or respiration of the object 10 . The peripheral frequency fs is considered noise in the process of calculating the location information Pxy of the object 10, but the biometric information analysis unit 240 detects a specific frequency component of the peripheral frequency fs, Based on this, biometric information such as a heart rate of the object 10 may be acquired.

When the amount of change in the biometric information changes greatly instantaneously, the biometric information analysis unit 240 determines that a health abnormality of the object 10 has arrived and generates an alarm.

The biometric information analysis unit 240 may learn biometric information based on artificial intelligence and generate an alarm based on this. In addition, in the process of learning the biometric information, the biometric information analysis unit 240 may consider the biometric information learning results of other objects.

In the sixth step (S260), when an alarm about the health abnormality of the object 10 is generated from the biometric information analysis unit 240, the signal analysis unit 200 takes relief measures such as calling in the relief period do.

As described above, the present invention can monitor the health state of the object 10 by a radar method.

Since the present invention does not monitor the object 10 based on image capture or an audio signal, the invasion of privacy of the object 10 can be minimized.

In addition, since the present invention does not use image capturing, it is possible to solve the problem that it is difficult to monitor the state of the object 10 due to the ambient illuminance and light reflection of the monitoring target. Since the present invention does not use a voice signal, it is possible to solve the problem that it is difficult to monitor the state of the object 10 due to the surrounding noise. In addition, a radio signal such as a chirped radar may monitor the object 10 without being affected by an obstacle between the first and second radio signal transceivers 110 and 120 and the object 10 . As such, according to the present invention, the object 10 can be monitored without being affected by an obstructive element and without a shadow area.

In addition, since the object 10 does not need to attach or hold an additional device to the body in order to practice the present invention, the object 10 may not feel discomfort.

Embodiments of the present invention and the drawings attached to this specification merely clearly show some of the technical ideas included in the above-described technology, and those skilled in the art can Modifications and specific embodiments that can be easily inferred will be apparent to be included in the scope of the above-described technology.

10: object 110, 120: radio signal transceiver
200: signal analysis unit 210: signal processing unit
220: location information calculation unit 230: event determination unit
240: biometric information analysis unit

Claims (6)

In a monitoring method for care for the elderly in a monitoring system for health care,
Amplifying the transmission/reception signals transmitted/received between the first wireless signal transceiver and the object through a low noise amplifier, and extracting an effective signal from the amplified transmission/reception signals;
determining any one received signal as a first reflected wave reflected from the object based on a delayed change amount of the received signals in the extracted valid signal;
amplifying the transmission/reception signals transmitted/received between the second wireless signal transceiver and the object through a low noise amplifier, and extracting an effective signal from the amplified transmission/reception signals;
determining any one received signal as a second reflected wave reflected from the object based on a delayed change amount of the received signals in the extracted valid signal;
calculating a first separation distance between the first radio signal transceiver and the object based on the delay degree of the first reflected wave;
calculating a second separation distance between the second wireless signal transceiver and the object based on the delay degree of the second reflected wave;
obtaining location information of the object calculated as two-dimensional coordinates based on the first separation distance and the second separation distance;
determining whether to move the object by comparing the change amount of the location information with a preset movement threshold; and
Including generating an event when the object does not move for a threshold time,
The threshold time is set based on the product of the reference time, the location information weight, and the meta information weight,
The location information weight is set differently according to the location information,
Further comprising the step of analyzing the biometric information of the object based on the first reflected wave and the second reflected wave,
The first reflected wave and the second reflected wave each include a main frequency and a peripheral frequency,
Interpreting the biometric information comprises:
Detecting an ambient frequency from each of the first reflected wave and the second reflected wave, and interpreting the heart rate of the object based on a specific frequency component of the detected ambient frequency,
The obtained location information of the object calculates the location information of the object continuously in time series in a predetermined time unit,
The change amount of the location information is determined by the size of a vector connecting the location information calculated at two timings,
The meta information weight is set based on the time the object stays in a specific place according to the meta information,
The meta information includes at least one of month, day, time, weather, and temperature,
The location information weight is modified based on the movement pattern of the object analyzed through learning of the obtained location information,
The meta information weight is modified based on the analysis result through learning about the movement pattern of the object and the change of the meta information,
The location information weight and the meta information weight is a monitoring method for care for the elderly, characterized in that it is modified based on a result of learning about the biometric information of the object according to the generated event. delete delete The method of claim 1,
The location information weight and the meta information weight are modified by additionally considering the location information weight and the meta information weight of another object. delete delete

Images