KR20230127512A - Method and system for detecting die alone based on life pattern data - Google Patents

Abstract

Disclosed are a system and a method for checking dying alone based on various pieces of data capable of recognizing a life pattern of a user and outputting an alarm. According to one aspect of the present invention, the method comprises the steps of: obtaining, by a computing system, learning life pattern data measured for a predetermined measurement period by a predetermined data sensing device installed at a residence of a user; learning, by the computing system, an artificial neural network for analyzing a life pattern of the user on the basis of the obtained learning life pattern data; obtaining, by the computing system, dying-alone detecting life pattern data measured by the data sensing device after learning the artificial neural network; inputting, by the computing system, the dying-alone detecting life pattern data to the artificial neural network, and determining a dying-alone risk level of the user on the basis of a result value output by the artificial neural network; and outputting, by the computing system, warning information on the basis of the dying-alone risk level.

Description

Method and system for automatically detecting lonely death based on life pattern data {Method and system for detecting die alone based on life pattern data}

The present invention relates to a method and system for automatically detecting a lonely death based on life pattern data. More specifically, the present invention relates to a system and method capable of confirming the existence of a lonely death and outputting an alarm based on various data capable of grasping a user's life pattern.

Korea is experiencing the fastest aging in the world due to the declining birth rate, and the number of elderly people living alone is also rapidly increasing due to the increase in single-person and unmarried households. As the number of elderly people living alone increases, various social problems related to elderly people living alone are also increasing. In particular, what is pointed out as the biggest problem in relation to the elderly living alone is the issue of death by loneliness, in which the elderly living alone die lonely while being disconnected from the people around them. In the case of a lonely death, it is not easy to detect due to the absence of a cohabitant, and it may take several days to dozens of days to be discovered.

In addition, the age group of lonely deaths is also decreasing from the elderly to the middle-aged or young people, so the problem of lonely death is not limited to the elderly living alone, but is a problem that our society needs to solve as a whole. To this end, the central and local governments are establishing and implementing measures to prevent and support lonely deaths for each life cycle such as young, middle-aged, and elderly through the Act on the Prevention and Management of Lonely Deaths, and establishing basic and implementation plans for preventing lonely deaths every five years. Welfare policies such as making it mandatory are in place, but we are unable to provide effective welfare services due to insufficient manpower and budget.

Republic of Korea Patent No. 10-1836428

A technical problem to be achieved by the present invention is to provide a system and method capable of confirming and warning whether a person is dying alone based on various data that can grasp a user's life pattern.

According to one aspect of the present invention, a computing system, obtaining life pattern data for learning measured during a predetermined measurement period by a predetermined data sensing device installed in the user's residence; learning, by the computing system, an artificial neural network for analyzing a life pattern of the user based on the acquired life pattern data for learning; obtaining, by the computing system, life pattern data for detecting lonely death measured by the data sensing device after the artificial neural network is learned; determining, by the computing system, a risk level of lonely death of the user based on a result value output by inputting the life pattern data for detecting lonely death to the artificial neural network; and outputting, by the computing system, warning information based on the risk level of lonely death.

In one embodiment, the life pattern data may include power consumption data and illuminance data.

In one embodiment, the data sensing device may be a smart plug coupled to an outlet installed in the user's residence.

In one embodiment, the data sensing device includes first to Nth sensors (where N is an integer of 3 or greater), and each of the first to Nth sensors includes a current sensor, a voltage sensor, and an illuminance. , a temperature, humidity, motion detection sensor, a heat detection sensor, a radar sensor, an infrared sensor, and a CO ₂ detection sensor.

In an embodiment, the life pattern data for learning includes first sensing data to Nth sensing data sensed by each of the first sensor to the Nth sensor, and the learning of the artificial neural network includes the first sensing data and the Nth sensing data. The method may include learning the artificial neural network by inputting learning data obtained by merging sensing data to Nth sensing data into the artificial neural network.

In an embodiment, the life pattern data for learning is data measured in a normal state without abnormality of the user, and the artificial neural network may be a neural network for unsupervised learning for anomaly detection.

In an embodiment, the outputting of the warning information may include outputting warning information to the terminal of the user when the risk level of lonely death is a warning level; and outputting warning information to a terminal of a pre-designated person in charge when the risk of dying alone is at or above the level.

According to another aspect of the present invention, a computer program installed in a data processing device and recorded on a medium for performing the above method is provided.

According to another aspect of the present invention, a computer readable recording medium on which a computer program for performing the above method is recorded is provided.

According to another aspect of the present invention, a computing system comprising: a processor; and a memory storing a computer program, wherein the computer program, when executed by the processor, causes the computing system to perform the above-described method.

According to another aspect of the present invention, a first acquisition module for acquiring life pattern data for learning measured during a predetermined measurement period by a predetermined data sensing device installed in a user's residence; a learning module for learning an artificial neural network for analyzing the life pattern of the user based on the acquired life pattern data for learning; a second acquisition module for acquiring life pattern data for detecting lonely death measured by the data sensing device after the artificial neural network is learned; a judgment module for inputting the life pattern data for detecting lonely death to the artificial neural network and determining a risk level of the user dying from loneliness based on a result value output from the artificial neural network; and a warning module outputting warning information based on the risk level of lonely death.

In one embodiment, the data sensing device includes a first sensor to an Nth sensor (where N is an integer of 3 or more), and each of the first sensor to the Nth sensor is a current sensor, a voltage sensor, and an illuminance sensor. , It may be any one of temperature, humidity, motion sensor, heat sensor, radar sensor, infrared sensor, and CO ₂ sensor, and the life pattern data for learning is detected by each of the first sensor to the Nth sensor. It includes first sensing data to Nth sensing data, and the learning module may learn the artificial neural network by inputting learning data obtained by merging the first sensing data to Nth sensing data to the artificial neural network.

In one embodiment, the warning module outputs warning information to the terminal of the user when the risk level of lonely death is a warning level, and sends warning information to a terminal of a predetermined person in charge when the risk level of lonely death is an abnormal level. can be printed out.

According to the technical idea of the present invention, it is possible to provide a system and method capable of confirming whether a person died alone and giving a warning based on various data that can grasp a user's life pattern. That is, it is possible to provide a method and system for detecting a lonely death that can predict the possibility of a lonely death of a user who is likely to suffer a lonely death and detect the actual occurrence of a lonely death.

In order to more fully understand the drawings cited in the detailed description of the present invention, a brief description of each drawing is provided.
1 is a diagram schematically illustrating an environment in which a method for automatically detecting lonely death based on life pattern data according to the technical concept of the present invention is performed.
2 is a diagram showing a schematic configuration of a data sensing device according to an embodiment of the present invention.
3 is a flowchart illustrating a method for detecting a lonely death according to an embodiment of the present invention.
4 is a diagram schematically illustrating an example of a physical configuration of a lonely death detection system according to an embodiment of the present invention.
5 is a diagram schematically illustrating an example of a logical configuration of a lonely death detection system according to an embodiment of the present invention.

Since the present invention can apply various transformations and have various embodiments, specific embodiments will be illustrated in the drawings and described in detail in the detailed description. However, it should be understood that this is not intended to limit the present invention to specific embodiments, and includes all transformations, equivalents, and substitutes included in the spirit and scope of the present invention. In describing the present invention, if it is determined that a detailed description of related known technologies may obscure the gist of the present invention, the detailed description will be omitted.

Terms such as first and second may be used to describe various components, but the components should not be limited by the terms. Terms such as first and second do not indicate a particular order, and are used only for the purpose of distinguishing one element from another.

Terms used in this application are only used to describe specific embodiments, and are not intended to limit the present invention. Singular expressions include plural expressions unless the context clearly dictates otherwise.

In this specification, terms such as "include" or "have" are intended to designate that there is a feature, number, step, operation, component, part, or combination thereof described in the specification, but one or more other It should be understood that the presence or addition of features, numbers, steps, operations, components, parts, or combinations thereof is not precluded.

In addition, in the present specification, when one component 'transmits' data to another component, the component may directly transmit the data to the other component, or through at least one other component. It means that the data can be transmitted to the other component. Conversely, when one component 'directly transmits' data to another component, it means that the data is transmitted from the component to the other component without going through the other component.

Hereinafter, the present invention will be described in detail with reference to the accompanying drawings, focusing on embodiments of the present invention. Like reference numerals in each figure indicate like members.

FIG. 1 is a diagram schematically illustrating an environment in which a method for automatically detecting a lonely death based on life pattern data (hereinafter, referred to as a “method for detecting a lonely death”) according to a technical concept of the present invention is performed.

Referring to FIG. 1 , it may be performed by an automatic lonely death detection system (100; hereinafter referred to as 'a lonely death detection system') based on life pattern data according to an embodiment of the present invention. The lonely death detection system 100 learns an artificial neural network for analyzing the user's life pattern based on life pattern data for learning measured by a predetermined data sensing device 20 installed in the user's residence 1. It is possible to determine the risk level of lonely death of the user based on the learned artificial neural network, and output warning information when it is determined that there is a risk of dying alone.

The lonely death detection system 100 may be a computing system that is a data processing device having an arithmetic capability for implementing the technical idea of the present invention, and generally a server or server device that is a data processing device accessible by a client through a network, and It may be in the form of a combination of software installed in the server device. The server device may be implemented as a single device or a device group consisting of a plurality of devices connected through a predetermined communication interface. For example, the lonely death detection system 100 may be a cloud server.

The lonely death detection system 100 may be implemented with any one physical device, but if necessary, a plurality of physical devices may be organically combined to implement the lonely death detection system 100 according to the technical spirit of the present invention. An average expert in the art of the present invention will be able to easily infer that there is.

The data sensing device 20 may be installed in the user's residence 1 and may acquire life pattern information of the user.

In particular, in one embodiment, the data sensing device 20 may be a smart plug coupled to an outlet installed in the user's residence. In this case, since the smart plug is directly installed in the outlet, power can be supplied and operated without charging.

In one embodiment, the life pattern information acquired by the data sensing device 20 may include power consumption data and illuminance data. The power consumption data is data on power consumed by various electrical/electronic devices 10 (eg, lights, TVs, washing machines, dryers, etc.) installed in the residence 1 and connected to the data sensing device 20. can Illuminance data may be data representing the intensity of light installed in the residence 1 .

Depending on the embodiment, the data sensing device 20 may sense various data other than power data and illuminance data. 2 is a diagram showing a schematic configuration of a data sensing device 20 according to an embodiment of the present invention.

As shown in FIG. 2 , the data sensing device may include a first sensor 21-1 to an Nth sensor 20-N (N is an integer of 3 or greater). Each of the first sensor 21-1 to the N-th sensor 21-N includes a current sensor, a voltage sensor, an illuminance sensor, a temperature sensor, a humidity sensor, a motion sensor, a thermal sensor, a radar sensor, an infrared sensor, and a CO ₂ sensor. It may be any one of the detection sensors.

The data sensing device 20 may include a communication module 22 through which wired or wireless communication may be performed with the lonely death detection system 100 . The communication module is, for example, a wireless communication method such as WLAN (Wireless LAN), Wi-Fi, Wibro, Wimax, HSDPA (High Speed Downlink Packet Access) or Ethernet , xDSL (ADSL, VDSL), HFC (Hybrid Fiber Coax), FTTC (Fiber to The Curb), FTTH (Fiber To The Home), and the like can be used. Preferably, the communication module 22 may transmit sensed information to the lonely death detection system 100 without configuring a separate communication network using the NarrowBand-Internet of Things.

Alternatively, the data sensing device 20 performs wireless communication with the data sensing device 20, and the lonely death detection system through a wireless relay device (not shown) performing wired communication with the lonely death detection system 100. Communication with (100) may also be performed.

The data sensing device 20 may include a control module 23 . The control module 23 can control the overall operation of the data sensing device 20, and detects lonely death by processing signals, data, information, etc. input or output through the components described above or by driving an application program. Appropriate information or functions may be provided or processed to system 100 .

Although FIG. 1 shows only one electrical/electronic device 10 and one data sensing device 20 for convenience, the lonely death detection system 100 receives data from a plurality of data sensing devices connected to the electrical/electronic device. It can be collected and used for learning artificial neural networks.

In the present specification, an artificial neural network is a neural network artificially constructed based on the operating principles of human neurons, and includes a multilayer perceptron model, and refers to a set of information expressing a series of design matters defining an artificial neural network. can The artificial neural network may be an artificial neural network composed of several hidden layers between an input layer and an output layer.

In one embodiment, the artificial neural network may be a convolutional neural network (CNN) or may include a convolutional neural network. As is well known, a convolutional neural network may include an input layer, a plurality of hidden layers, and an output layer. Each of the plurality of hidden layers may include a convolution layer and a pooling layer (or subsampling layer). A convolutional neural network may be defined by a function, filter, stride, weight factor, etc. for defining each of these layers. Also, the output layer may be defined as a fully connected FeedForward layer. Design matters for each layer constituting a convolutional neural network are widely known. For example, known functions may be used for each of the number of layers to be included in a plurality of layers, a convolution function, a pooling function, and an activation function for defining the plurality of layers, and to implement the technical idea of the present invention. Separately defined functions may also be used.

However, the artificial neural network is not necessarily a convolutional neural network, and according to an embodiment, the artificial neural network is a Recurrent Neural Network (RNN), a Long Short-Term Memory (LSTM) model, or an encoder/decoder model. It could be.

In one embodiment, the artificial neural network may be a neural network for anomaly detection or may be a neural network for unsupervised learning that can be learned with unlabeled data. When the artificial neural network is configured as a neural network for unsupervised learning, there is an advantage in that the neural network can be learned without labeling learning data, which requires much effort and resources.

For example, the artificial neural network may be a model based on a generative adversarial network (GAN), but the technical concept of the present invention is not limited thereto.

Meanwhile, the learned neural network may be stored in the lonely death detection system 100, and the lonely death detection system 100 may use the learned artificial neural network to determine whether the user is abnormal or the risk level of lonely death. can

Meanwhile, the lonely death detection system 100 may transmit warning information to the terminal 30 of a shopping mall user and/or the terminal 40 of a manager designated in advance when a lonely death is detected or a risk level of lonely death is high.

The user terminal 30 and the manager terminal 40 may be information processing systems that perform electronic information processing. The user terminal 30 and the manager terminal 40 may include a handheld device such as a mobile phone, a satellite phone, a wireless phone, a smart phone, a tablet PC, a PDA (Personal Digital Assistant), or a laptop or desktop. It is not limited to this.

3 is a flowchart illustrating a method for detecting a lonely death according to an embodiment of the present invention.

Referring to FIG. 3 , the lonely death detection system 100 may acquire life pattern data for learning measured during a predetermined measurement period by a predetermined data sensing device 20 installed in the user's residence 1 ( S100). For example, the lonely death detection system 100 may acquire life pattern data for learning including power consumption data and illuminance data from the data sensing device 20 .

Alternatively, the data sensing device 20 includes first to Nth sensors (where N is an integer of 3 or greater), and each of the first to Nth sensors includes a current sensor, a voltage sensor, illumination, and temperature. , humidity, motion detection sensor, heat detection sensor, radar sensor, infrared sensor, CO ₂ detection sensor. It may include first sensing data to Nth sensing data.

With the acquired life pattern data for learning, the lonely death detection system 100 may generate learning data to learn the artificial neural network (S200).

Preferably or representatively, the lonely death detection system 100 generates learning data by merging the first sensing data to the Nth sensing data, inputs the generated learning data to an input layer of the artificial neural network, and Artificial neural networks can be trained.

In one embodiment, the lonely death detection system 100 generates learning data by converting (enlarging or reducing) all of the first sensing data to the Nth sensing data to the same size and then stacking the converted data. can do. More specifically, the lonely death detection system 100 may generate learning data by configuring data obtained by converting the first sensing data to the Nth sensing data to the same size into different channels.

Meanwhile, the lonely death detection system 100 may repeat steps S110 and S120 a plurality of times until a predetermined learning completion condition is satisfied in order to learn the artificial neural network (see S120). Alternatively, the lonely death detection system 100 may divide measurement data measured for a long period of time or obtain measurement data at regular intervals to repeat steps S110 and S120 a plurality of times.

Meanwhile, the life pattern data for learning may be data measured in a normal state in which the user has no abnormality. In this case, the artificial neural network may be a neural network for unsupervised learning for anomaly detection. Therefore, in this embodiment, it is possible to determine whether the user is abnormal even if the user does not learn from data when the user is in an abnormal (abnormal) situation, but only learns from data collected during a normal life.

After learning of the artificial neural network is completed, the system 100 for detecting lonely death may acquire life pattern data for detecting lonely death measured by the data sensing device (S200). In addition, the lonely death detection system 100 may generate data for judgment corresponding to the life pattern data for detecting lonely death, and input the data for judgment corresponding to the diagnosis data to the learned artificial neural network, The risk level of the user dying alone may be determined based on the output value output from the artificial neural network (S210). Since the process of generating decision data from life pattern data for detecting lonely death is very similar to the process of generating learning data, a separate description thereof will be omitted.

In one embodiment, the lonely death detection system 100 may determine whether or not the user is in a normal state based on an output value output from the artificial neural network, and the non-normal state may be longer than a predetermined reference time. If it is prolonged, it can be determined that it is an abnormal state.

In one embodiment, the risk level of lonely death may be any one of normal (low risk), warning (medium risk), and abnormal (high risk), and the lonely death detection system 100 outputs an output from the artificial neural network. Based on the value, it is determined whether the user is in a normal state (a state similar to a normal life pattern) or not, and if the non-normal state is longer than a predetermined first reference time, it may be determined that it is a warning level, and it is a warning level. If the non-normal state in the determined state is longer than the predetermined second reference time, it may be determined that the abnormal level is reached.

The lonely death detection system 100 outputs warning information to the terminal 30 of the user when the risk level of lonely death is a warning level, and when the risk level of lonely death is an abnormal level, the terminal 40 of a designated person in charge ) to output warning information. The lonely death detection system 100 may output warning information through means such as a device alarm, an application alarm, a phone call, or a text message.

4 is a diagram schematically illustrating an example of a physical configuration of the lonely death detection system 100 according to an embodiment of the present invention. The lonely death detection system 100 may physically have a configuration as shown in FIG. 3 . The lonely death detection system 100 includes a memory 170 storing a program 171 and an artificial neural network 172 for implementing the technical idea of the present invention, and a program for executing the program stored in the memory 170. A processor 160 may be provided.

An average expert in the technical field of the present invention can easily infer that the processor 160 can be named by various names such as CPU, APU, microprocessor, ASIC, etc. according to the implementation example of the computing system 100. will be. In addition, as described above, the computing system 100 may be implemented by organically combining a plurality of physical devices. In this case, at least one processor 160 is provided for each physical device, and the computing system 100 of the present invention ) can be implemented, the average expert in the art of the present invention will be able to easily infer. The processor 160 may include a GPU used to train the deep learning model 30 .

The memory 170 stores the program, and may be implemented as any type of storage device accessible by the processor to drive the program. Also, according to a hardware implementation example, the memory 170 may be implemented as a plurality of storage devices instead of a single storage device. In addition, the memory 170 may include a temporary storage device as well as a main memory device. It may also be implemented as volatile memory or non-volatile memory. The memory 170 may include, for example, flash memory, ROM, RAM, EEROM, EPROM, EEPROM, hard disk, and registers. Alternatively, the memory 170 may be defined as including all types of information storage means implemented so that the program can be stored and driven by the processor.

The lonely death detection system 100 may perform the lonely death detection method according to the technical concept of the present invention according to an embodiment. In addition, according to the embodiment of the lonely death detection system 100, various peripheral devices (peripheral device 1 to peripheral device K, 180) may be further provided. For example, an average expert in the technical field of the present invention can easily infer that a keyboard, a display device, a graphic card, a networking device, a storage device, and the like may be further included in the lonely death detection system 100 as peripheral devices. There will be.

Hereinafter, when a predetermined module performs a certain function in this specification, it means that the processor 160 executes the function by driving a program included in the memory 170. An expert will be able to infer easily.

5 is a diagram schematically illustrating an example of a logical configuration of the lonely death detection system 100 according to an embodiment of the present invention.

The lonely death detection system 100 may refer to a logical configuration having hardware resources and/or software required to implement the technical concept of the present invention, and necessarily refers to one physical component or It does not mean a single device. That is, the lonely death detection system 100 may mean a logical combination of hardware and/or software provided to implement the technical idea of the present invention, and if necessary, installed in devices spaced apart from each other to perform respective functions. It may be implemented as a set of logical configurations for implementing the technical idea of the present invention by performing. In addition, the lonely death detection system 100 and the data sensing device 20 may refer to a set of components implemented separately for each function or role to implement the technical idea of the present invention. Each component of the lonely death detection system 100 and the rotating machine diagnosis system 200 may be located in different physical devices or may be located in the same physical device. In addition, depending on the embodiment, the combination of software and / or hardware constituting each of the components of the lonely death detection system 100 and the rotating machine diagnosis system 200 is also located in different physical devices, and is located in different physical devices. The located components may be organically combined with each other to implement each of the modules.

Also, in this specification, a module may mean a functional and structural combination of hardware for implementing the technical concept of the present invention and software for driving the hardware. For example, the module may mean a logical unit of a predetermined code and a hardware resource for executing the predetermined code, and does not necessarily mean a physically connected code or one type of hardware. can be easily deduced to an average expert in the art of the present invention.

Referring to FIG. 4 , the lonely death detection system 100 includes a storage module 110, a first acquisition module 120, a learning module 130, a second acquisition module 125, a determination module 140, and a warning. module 140. Depending on the embodiment of the present invention, some of the above-described components may not necessarily correspond to components essential to the implementation of the present invention, and also according to the embodiment, the lonely death detection system 100 Of course, may include more components than this. For example, the lonely death detection system 100 further includes a communication module (not shown) for communicating with an external device and a control module (not shown) for controlling components and resources of the lonely death detection system 100. can include

The storage module 110 may store an artificial neural network.

The acquisition module 120 may acquire life pattern data for learning measured during a predetermined measurement period by a data sensing device.

The learning module 130 may learn the artificial neural network for analyzing the user's life pattern based on the acquired life pattern data for learning.

The second acquisition module 125 may acquire life pattern data for detecting lonely death measured by the data sensing device 20 after the artificial neural network is learned, and the determination module 140 may Life pattern data for detecting lonely death may be input to the artificial neural network, and the risk level of the user may be determined based on a result value output from the artificial neural network.

Meanwhile, the warning module 150 may output warning information based on the risk level of lonely death. More specifically, the warning module 150 may output the user's terminal when the risk level of lonely death is a warning level. Warning information is transmitted to (30), and when the risk level of lonely death is greater than or equal to, the warning information can be transmitted to the terminal 40 of a pre-designated person in charge.

On the other hand, the method according to the embodiment of the present invention may be implemented in the form of computer-readable program instructions and stored in a computer-readable recording medium, and the control program and target program according to the embodiment of the present invention are also computer-readable. It can be stored on a readable recording medium. The computer-readable recording medium includes all types of recording devices in which data that can be read by a computer system is stored.

Program commands recorded on the recording medium may be specially designed and configured for the present invention, or may be known and usable to those skilled in the software field.

Examples of computer-readable recording media include magnetic media such as hard disks, floppy disks and magnetic tapes, optical media such as CD-ROMs and DVDs, floptical disks and hardware devices specially configured to store and execute program instructions, such as magneto-optical media and ROM, RAM, flash memory, and the like. In addition, the computer-readable recording medium is distributed in computer systems connected through a network, so that computer-readable codes can be stored and executed in a distributed manner.

Examples of program instructions include high-level language codes that can be executed by a device that electronically processes information using an interpreter, for example, a computer, as well as machine language codes generated by a compiler.

The hardware device described above may be configured to operate as one or more software modules to perform the operations of the present invention, and vice versa.

The above description of the present invention is for illustrative purposes, and those skilled in the art can understand that it can be easily modified into other specific forms without changing the technical spirit or essential features of the present invention. will be. Therefore, the embodiments described above should be understood as illustrative in all respects and not limiting. For example, each component described as a single type may be implemented in a distributed manner, and similarly, components described as distributed may be implemented in a combined form.

The scope of the present invention is indicated by the following claims rather than the detailed description above, and all changes or modifications derived from the meaning and scope of the claims and equivalent concepts thereof should be construed as being included in the scope of the present invention. .

Claims (15)

obtaining, by a computing system, life pattern data for learning measured during a predetermined measurement period by a predetermined data sensing device installed in a user's residence;
learning, by the computing system, an artificial neural network for analyzing a life pattern of the user based on the acquired life pattern data for learning;
obtaining, by the computing system, life pattern data for detecting lonely death measured by the data sensing device after the artificial neural network is learned;
determining, by the computing system, a risk level of lonely death of the user based on a result value output by inputting the life pattern data for detecting lonely death to the learned artificial neural network; and
and outputting, by the computing system, warning information based on the risk level of lonely death.
According to claim 1,
The method of automatically detecting lonely death based on life pattern data, wherein the life pattern data includes power consumption data and illuminance data.
According to claim 1,
The method of automatically detecting lonely death based on life pattern data, characterized in that the data sensing device is a smart plug-in coupled to an outlet installed in the user's residence.
According to claim 1,
The data sensing device,
Including a first sensor to an Nth sensor (where N is an integer of 3 or more),
Each of the first sensor to the Nth sensor,
A method for automatically detecting lonely deaths based on life pattern data, characterized in that any one of a current sensor, a voltage sensor, an illuminance, temperature, humidity, motion sensor, a heat sensor, a radar sensor, an infrared sensor, and a CO ₂ sensor.
According to claim 4,
The life pattern data for learning,
It includes first sensing data to Nth sensing data sensed by each of the first sensor to the Nth sensor,
The step of learning the artificial neural network,
A method for automatically detecting lonely death based on life pattern data, comprising the step of learning the artificial neural network by inputting learning data obtained by merging first sensing data to Nth sensing data into the artificial neural network.
According to claim 1,
The life pattern data for learning is data measured in a normal state where the user has no abnormalities,
The artificial neural network is a neural network for unsupervised learning for anomaly detection.
According to claim 1,
The step of outputting the warning information,
outputting warning information to the terminal of the user when the risk level of dying alone is a warning level; and
A method for automatically detecting lonely death based on life pattern data comprising the step of outputting warning information to a terminal of a pre-designated person in charge when the risk level of lonely death is an abnormal level.
A computer readable recording medium on which a computer program for performing the method according to any one of claims 1 to 7 is recorded.
a first acquisition module for acquiring life pattern data for learning measured during a predetermined measurement period by a predetermined data sensing device installed in the user's residence;
a learning module for learning an artificial neural network for analyzing the life pattern of the user based on the acquired life pattern data for learning;
a second acquisition module for acquiring life pattern data for detecting lonely death measured by the data sensing device after the artificial neural network is learned;
a judgment module for inputting the life pattern data for detecting lonely death to the artificial neural network and determining a risk level of the user dying from loneliness based on a result value output from the artificial neural network; and
A system for automatically detecting lonely death based on life pattern data including a warning module outputting warning information based on the risk level of lonely death.
According to claim 9,
The life pattern data includes life pattern data including power consumption data and illuminance data.
According to claim 9,
The automatic detection system for lonely death based on life pattern data, characterized in that the data sensing device is a smart plug-in coupled to an outlet installed in the user's residence.
According to claim 9,
The data sensing device,
Including a first sensor to an Nth sensor (where N is an integer of 3 or more),
Each of the first sensor to the Nth sensor,
A lonely death automatic detection system based on life pattern data, characterized in that it is any one of a current sensor, voltage sensor, illumination, temperature, humidity, motion detection sensor, heat detection sensor, radar sensor, infrared sensor, and CO ₂ detection sensor.
According to claim 12,
The life pattern data for learning,
It includes first sensing data to Nth sensing data sensed by each of the first sensor to the Nth sensor,
The learning module,
A system for automatically detecting lonely death based on life pattern data for learning the artificial neural network by inputting learning data obtained by merging the first sensing data to the Nth sensing data into the artificial neural network.
According to claim 9,
The life pattern data for learning is data measured in a normal state where the user has no abnormalities,
The artificial neural network is a neural network for unsupervised learning for anomaly detection. According to claim 9,
The warning module,
When the risk level of lonely death is a warning level, warning information is output to the user's terminal;
A system for automatically detecting lonely death based on life pattern data that outputs warning information to a terminal of a pre-designated person in charge when the risk level of lonely death is at an abnormal level.