KR102866875B1 - Daily behavior detection homecare device and method based on multi-environmental sensors installed in unit space of living environment and operated independently - Google Patents

Abstract

The present invention relates to a home care device that recognizes a user's daily behavior by detecting the user's behavior based on an environmental sensor, and is a daily behavior recognition home care device based on multiple environmental sensors that recognizes the user's daily behavior by detecting the user's behavior based on an environmental sensor, and includes: a sensor unit that detects sensor data that changes according to the user's behavior in a unit space; a segmentation unit that receives a triggering signal that induces segmentation from a device in the vicinity to analyze continuous sensor data acquired through the sensor unit and segments the continuous sensor data into sections; a data level management unit that divides the sensor data into three stages of short-term, middle-term, and long-term and selects a storage location; and a situation recognition unit that recognizes the user's situation based on short-term data, middle-term data, and long-term data. Through this, the user's situation within a space can be accurately analyzed.

Description

Daily behavior detection homecare device and method based on multi-environmental sensors installed in a unit space of living environment and operated independently

The present invention relates to a daily behavior recognition home care device and method based on multiple environmental sensors installed in a unit space of a residential environment and independently operated, and more specifically, to an ADL detector and operating method that can measure ambient environmental data such as temperature, humidity, CO/CO2, TVOC, ammonia, illuminance, indoor sound and noise that change according to the user's behavior using a sensor, analyze the measured sensor data in real time to predict the user's daily behavior, recognize erroneous behavior and provide guidance services, and to a daily behavior recognition home care device and method based on multiple environmental sensors installed in a unit space of a residential environment and independently operated.

In a person's living environment, the state of the surrounding environment changes according to the person's behavior, and the technology that measures these changes with sensors and converts them into data can be used as an important technology to recognize and support the daily behavior of the sick, elderly people living alone, or patients with degenerative brain diseases in real time.

By installing various sensor terminals in a residential environment, the terminals can independently determine and identify various daily activities of residents, such as waking up, washing dishes, urinating and defecating, washing hands, sleeping, and watching TV, without the residents having any special knowledge or awareness of how to use the terminals installed in the residential environment.

However, in various existing similar studies or developments, in order to understand the daily behavior of such residents, various terminals (wearable terminals, fixed terminals, mobile terminals) are installed in the living space, and each terminal communicates with each other to collect the measured sensor signals into a server database, and the data is analyzed to predict and recognize the daily behavior of the residents. Research is being conducted on methods.

However, there are problems that make it difficult to put into practice because installing an excessive number of sensor terminals in a living space requires installation work, causes residents to feel insecure to the point of inconvenience in their lives, requires operating not only multiple terminals but also servers and databases, makes the IT infrastructure very complex and expensive to an extent that individuals cannot afford, and creates an environment that is harmful to the human body due to excessive wired and wireless communication infrastructure in the living environment, such as electromagnetic waves.

Korean Patent Publication No. 10-2062605

The technical problem to be solved by the present invention is to provide an ADL detector and an operating method that can independently detect the user's daily behavior by measuring the surrounding environment data that changes according to the user's behavior using a sensor and analyzing the measured sensor data in real time, and can independently detect the resident's daily behavior by recognizing erroneous behavior and providing a guidance service by attaching the ADL detector to the ceiling or wall of the living environment.

According to one aspect of the present invention, a multi-environment sensor-based daily behavior detection terminal device installed in a unit space of a residential environment and independently operated is a multi-environment sensor-based daily behavior recognition home care device that recognizes the daily behavior of a resident by detecting the user's behavior based on an environmental sensor.

A sensor unit that detects sensor data that changes according to the user's actions in a unit space;

A main computing unit that receives a triggering signal that causes segmentation from a device in the vicinity to analyze continuous sensor data acquired through the above sensor unit, segments the continuous sensor data into sections, analyzes the segmented data, recognizes patterns, and predicts the actual ADL (Activities Of Daily Living) behavior of the resident;

A data storage unit for storing data to analyze the above sensor data and identify resident ADL behavior;

It includes a wired/wireless communication unit that transmits a feedback signal generated by the main computing unit based on the learning results of the resident's ADL behavior as a notification to the user, notifies the resident's guardian, or transmits the signal to a device that operates as an actuator around the resident.

Meanwhile, the main computing unit includes a broadcasting service processing unit capable of generating a feedback notification to a resident through broadcasting based on the ADL behavior prediction result; and a voice signal transmitting unit for transmitting the feedback notification generated by the broadcasting service processing unit to the user.

In addition, the main computing unit can start storing data in the data storage unit when the sensor unit detects the entry and exit of a resident, and can end the storage when a change in another pattern of movement of the resident is detected or a signal is received from an external device.

Additionally, the main computing unit may include collecting and comparing at least one piece of sensor data to distinguish differences in changes in resident behavior.

Meanwhile, the sensor unit may include a sensor that collects temperature, humidity, CO/CO2, TVOC, ammonia, air pressure, and illuminance data, which are the surrounding environment of the unit space, a sensor that collects noise data generated according to the user's actions in the unit space, and an infrared sensor that detects residents.

Additionally, the main computing unit can predict the behavior of residents by analyzing the location of residents in a unit space and their movement patterns from continuous sensor data.

In addition, the main computing unit may include a function to predict and record location-based precise daily activity history by determining environmental data and indoor noise data that change according to the resident's ADL behavior and by detecting the direction and location of movement of indoor users.

Meanwhile, the wireless communication unit may transmit a signal including information that the resident did not perform the ADL action if the resident does not perform the ADL action.

Additionally, the data storage unit can store daily behavioral records such as the collected resident's motor skills, equipment usage skills, behavioral patterns and consistency, and abnormal behavior.

Additionally, the main computing unit can predict the resident's ADL behavior and other behaviors through management of the resident's daily behavior history and generate corrective notifications to notify the resident and the resident's guardian.

Meanwhile, the wired and wireless communication unit may receive feedback on the consistency and appropriateness of the resident's daily behavior by transmitting the daily behavior history stored in the data storage unit to the resident's guardian at regular intervals, and may receive feedback on judgments that can help in the protection and treatment so that the resident's daily behavior can be maintained.

According to another aspect of the present invention, a multi-environment sensor-based daily activity recognition home care method for recognizing daily activities of a resident by detecting a user's behavior based on an environmental sensor is provided, which comprises a sensor data detection step for detecting sensor data that changes according to the user's behavior in a unit space; a step for segmenting a section of continuous sensor data by receiving a triggering signal that induces segmentation from a device in the vicinity in order to analyze continuous sensor data acquired through the sensor unit; a step for predicting actual ADL (Activities of Daily Living) of a resident by analyzing the segmented data and recognizing a pattern to predict actual ADL of a resident; a step for storing ADL data for storing data for analyzing the sensor data to identify the resident's ADL behavior; and a wired/wireless communication step for transmitting a feedback signal generated by a main computing unit according to a learning result of the resident's ADL behavior as a notification to the user, notifying the resident's guardian, or transmitting the feedback signal to a device that operates as an actuator around the resident.

According to one aspect of the present invention described above, by measuring the state of a certain unit space indoors and collecting it into a database, exchanging data through communication between devices to detect changes in the situation, it is possible to accurately analyze a wider space, compare data between sensors, detect malfunctions, or correct sensor data between each other to increase accuracy. In the present invention, the living space of a resident is divided into unit spaces (bedroom, kitchen, bathroom, living room, etc.) and a ceiling-mounted or wall-mounted ADL detector developed through the present invention is installed in each unit space so that all daily behavior details occurring in the unit space can be independently detected and operated by the terminal installed in the unit space, and since there is no need for a separate central server or central database in the living space, data management is very easy.

In addition, since it detects changes in environmental data and noise generation in a unit space according to the movement of residents within that space and predicts the daily behavior of residents, there is no need for numerous devices or terminals for detecting daily details that existing products require, and since it can be installed and attached similarly to fire detectors installed and operating in existing unit spaces, there is no need for facility construction for ADL service, and residents do not need to be aware of how to use this terminal or be conscious of installing it.

Additionally, since there is no need for a central server or database, resident ADL data can be prevented from being leaked externally.

Figure 1 is a block diagram of a daily behavior detection terminal device based on a multi-environment sensor that is installed in a unit space of a residential environment and operates independently according to one embodiment of the present invention.
Figure 2 is a block diagram of the sensor unit of a daily behavior detection terminal device based on a multi-environment sensor that is installed in a unit space of the residential environment illustrated in Figure 1 and operates independently.
Figure 3 is a diagram illustrating an example of the main computing unit illustrated in Figure 1 processing a broadcast service and transmitting it as a voice signal.
Figure 4 is a configuration diagram of a daily behavior detection terminal device based on multiple environmental sensors that is installed in a unit space of a residential environment and operates independently.
Figure 5 is an example of an installation of a daily behavior detection terminal device based on a multi-environment sensor that is installed in a unit space of a residential environment and operates independently according to another embodiment.
FIG. 6 is a flowchart illustrating a method for detecting daily behaviors based on a multi-environment sensor that is installed in a unit space of a residential environment and operated independently according to another embodiment of the present invention.

The following detailed description of the present invention refers to the accompanying drawings, which illustrate specific embodiments in which the present invention may be practiced. These embodiments are described in sufficient detail to enable those skilled in the art to practice the present invention. It should be understood that the various embodiments of the present invention, while different from each other, are not necessarily mutually exclusive. For example, specific shapes, structures, and characteristics described herein may be implemented in other embodiments without departing from the spirit and scope of the present invention. Furthermore, it should be understood that the positions or arrangements of individual components within each disclosed embodiment may be modified without departing from the spirit and scope of the present invention. Accordingly, the following detailed description is not intended to be limiting, and the scope of the present invention is defined only by the appended claims, along with the full scope of equivalents to which such claims are entitled, if properly described. Like reference numerals in the drawings designate the same or similar functionality throughout the several aspects.

Conventional daily action recognition devices have the problem that it is difficult to predict what is happening in a unit space with just a single environmental sensor because it is not enough to predict what is happening in a unit space with just a single environmental sensor, and each sensor can show different measurement patterns for a single state.

Therefore, the daily activity recognition terminal (hereinafter referred to as the "device") based on multiple environmental sensors according to the present embodiment can recognize the user's daily activity by detecting the user's activity based on sensor data. In particular, according to the present embodiment, a device within a unit space can manage sensors through collaboration between other devices within a different unit space, thereby detecting malfunctions or correcting sensor data between each other to increase data accuracy.

Such a home care device (100) can be implemented as an edge computing device such as a portable terminal or computer.

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

FIG. 1 is a block diagram of a daily behavior detection terminal device based on multiple environmental sensors that is installed in a unit space of a residential environment and operates independently according to one embodiment of the present invention.

Referring to FIG. 1, a home care device (100) according to the present embodiment is a multi-environment sensor-based daily behavior recognition home care device (100) that recognizes the daily behavior of a resident by detecting the user's behavior based on an environmental sensor, and includes a sensor unit (110), a wired/wireless communication unit (120), a main computing unit (130), and a data storage unit (140).

This home care device (100) can be implemented as an edge computing device such as a portable terminal or a computer. Here, the portable terminal is a wireless communication device that guarantees portability and mobility, and may include all types of handheld-based wireless communication devices such as a PCS (Personal Communication System), GSM (Global System for Mobile communication), PDC (Personal Digital Cellular), PHS (Personal Handyphone System), PDA (Personal Digital Assistant), IMT (International Mobile Telecommunication)-2000, CDMA (Code Division Multiple Access)-2000, w-CDMA (w-Code Division Multiple Access), Wibro (Wireless Broadband Internet) terminal, and the computer may include a desktop, notebook, laptop, etc. equipped with a web browser. In addition, the home care device (100) may be various smart devices such as a smartphone, a smart note, a tablet PC, a smart camera, a smart TV, a smart watch, a wearable computer, etc. However, the home care device (100) is not limited to the form of the terminal listed above.

The home care device (100) according to this embodiment detects sensor data that changes according to the user's actions in a unit space through a sensor unit (110).

Even if a single sensor has high sensitivity, it cannot accurately determine the situation when detecting the change in state that the sensor is trying to measure.

For example, it's very difficult to distinguish, using single sensor data, whether a change in humidity occurring over the same period of time is due to the inflow of moist air from the outdoors or the presence of an artificial humidity-increasing device, such as a humidifier, indoors. However, if temperature sensor data measured at the same location over the same period of time is available, analyzing the temperature change value and rate of change can make this distinction easier.

Accordingly, the sensor unit (110) according to the present embodiment can be implemented in the form of 'Sensor Fusion' in which a number of environmental sensors are combined, thereby making it possible to determine high-dimensional situations that cannot be confirmed with single sensor data.

Figure 2 is a block diagram of the sensor unit (110) in the home care device (100) illustrated in Figure 1.

Figure 4 is a configuration diagram of a home care device (100).

Referring to FIGS. 2 and 4, the sensor unit (110) includes a multi-environment data measurement sensor (111), a noise sensor (112), an illuminance sensor (113), and a movement detection sensor (114).

The sensor unit (110) may include a sensor that collects temperature, humidity, CO/CO2, TVOC, ammonia, air pressure, and illuminance data, which are the surrounding environment of the unit space, a sensor that collects noise data generated according to the user's actions in the unit space, and an infrared sensor that detects residents.

Meanwhile, the data collected by the sensor unit (110) shows various sensitivity to changes depending on the value measured by the sensor.

More specifically, temperature and humidity sensors exhibit response times on the order of milliseconds, while air quality and IR sensors require measurement times ranging from hundreds of milliseconds to several seconds, depending on the sensing cycle. Therefore, sensor data with short and long cycles must be stored hierarchically, depending on the measurement cycle.

Additionally, human behavior patterns cannot be accurately determined through sensor data detected at a specific point in time, and can only be determined after sensor data is collected over a certain period of time.

For example, actions such as cooking or showering cannot be confirmed through sensor data at a specific point in time, such as "the temperature and humidity are high," but can be confirmed through sensor data over a specific period of time, such as "the humidity rose and fell over a specific period of time."

Additionally, the sensor unit (110) can detect sensor data that changes according to actions in a unit space.

The wired/wireless communication unit (120) can transmit data to the outside or receive data from the outside via a communication network. At this time, the communication network means a connection structure that enables information exchange between each node, such as terminals and servers, and such communication networks include, but are not limited to, the Internet, Wireless LAN (Wireless Local Area Network), WAN (Wide Area Network), PAN (Personal Area Network), 3G, LTE (Long Term Evolution), WiFi (Wireless Fidelity), WiMAX (World Interoperability for Microwave Access), WiGig (Wireless gigabit), etc.

In particular, the wired/wireless communication unit (120) according to the present embodiment can receive a triggering signal that causes segmentation of sensor data from peripheral devices or other devices.

The wired/wireless communication unit (120) can transmit a feedback signal generated by the main computing unit (130) as a notification to the user based on the learning results of the resident's ADL behavior, and can notify the resident's guardian or transmit the signal to a device that operates as an actuator around the resident.

In addition, the wired/wireless communication unit (120) may transmit the daily behavior history stored in the data storage unit to the guardian of the resident at regular intervals, thereby receiving feedback on the consistency and appropriateness of the resident's daily behavior and receiving feedback on a judgment that is helpful for protection and treatment so that the resident's daily behavior can be maintained.

Additionally, the wired/wireless communication unit (120) may transmit a signal including information that the resident did not perform the ADL behavior when the resident does not perform the ADL behavior.

Meanwhile, the wired/wireless communication unit (120) may transmit the daily behavior history stored in the data storage unit to the guardian of the resident at regular intervals, thereby receiving feedback on the consistency and appropriateness of the resident's daily behavior and receiving feedback on a judgment that is helpful for protection and treatment so that the resident's daily behavior can be maintained.

The main computing unit (130) can analyze the environmental data collected from the sensor unit (110) to predict what actions the user actually performed.

In addition, the main computing unit (130) receives a triggering signal that causes segmentation from a device in the vicinity to analyze continuous sensor data acquired through the sensor unit (110), segments the continuous sensor data into sections, analyzes the segmented data, recognizes patterns, and can predict the actual ADL (Activities of Daily Living) behavior of the resident.

In addition, the main computing unit (130) may include a broadcasting service processing unit (131) capable of generating feedback notifications to residents through broadcasting based on the ADL behavior prediction results, and a voice signal transmitting unit (132) for transmitting the feedback notifications generated by the broadcasting service processing unit (131) to users.

The voice signal transmission unit (132) may include a speaker for transmitting a feedback signal to the user according to the user's ADL behavior predicted by the main computing unit (130).

Meanwhile, the main computing unit (130) can act independently to request data from the sensor unit (110) or store data in the data storage unit (140), and can receive data from the outside or transmit data through the wired/wireless communication unit (120).

In addition, the main computing unit (130) can start storing data in the data storage unit (140) when the sensor unit (110) detects the entry and exit of a resident, and can end the storage when a change in the resident's movement pattern is detected or a signal is received from an external device.

Additionally, the main computing unit (130) may include collecting and comparing at least one sensor data to distinguish differences in changes in resident behavior.

Meanwhile, the main computing unit (130) may predict the behavior of residents by analyzing the location of residents in a unit space and the movement pattern of residents from continuous sensor data.

In addition, the main computing unit (130) may include a function to predict and record, by determining, location-based precise daily behavior history through environmental data and indoor noise data that change according to the ADL behavior of the resident and the movement direction and location detection function of the indoor user, and to predict the behavior of the resident by analyzing the location of the resident in a unit space and the movement pattern of the resident from continuous sensor data.

In addition, the main computing unit (130) includes a function to predict and record location-based precise daily behavior history through environmental data and indoor noise data that change according to the resident's ADL behavior and the indoor user's movement direction and location detection function.

In addition, the main computing unit (130) can predict the resident's ADL behavior and other behaviors through management of the resident's daily behavior history and generate a corrective notification to notify the resident and the resident's guardian.

In addition, data collected and analyzed from the main computing unit (130) is transmitted and stored in the form of a database, and the stored data can be used in the ADL learning engine of the main computing unit (130) or transmitted to an external database via a wired or wireless communication unit (120) as needed.

In addition, the main computing unit (130) is connected to the data storage unit (140) and can store data collected over a certain period of time in the data storage unit (140).

In addition, the main computing unit (130) creates a data management queue in the data storage unit (140) to continuously store environmental data and sound data received from the sensor unit (110), and the data can be updated in real time to update the ADL learning engine.

The main computing unit (130) selects and analyzes data stored in a database to process a large amount of data on an edge device with relatively insufficient storage capacity.

To this end, the main computing unit (130) utilizes segmentation signals received via the wired/wireless communication unit (120). These segmentation signals are data received from other peripherals or devices. Rather than analyzing all data stored in the database, only data from the time a segmentation signal is received until the next segmentation signal is received is analyzed.

At this time, data segmentation is performed by the environmental data and sound data of the main computing unit (130), and the segmented data is learned and analyzed through the ADL learning engine and can be used to predict the user's ADL.

The data storage unit (140) can store data for analyzing sensor data to identify resident ADL behavior.

In addition, the data storage unit (140) may be a storage unit that stores data required by the main computing unit (130) and stores data collected by the sensor unit (110) in the form of RAW data or stores the results of calculations and analysis performed by the main computing unit (130).

Additionally, the data storage unit (140) may store daily behavioral records such as the collected resident's motor skills, equipment usage skills, behavioral patterns and consistency, and abnormal behavior.

Fig. 5 is an installation example of a home care device (100) according to another embodiment.

The home care device (110) can use a battery as the main power source, so it is not suitable for using speakers with high power consumption, but the wall-mounted home care device (100) can be used by directly attaching it to a power outlet on the wall, so it can be freer from the problem of power consumption.

The method for recognizing daily activities based on multiple environmental sensors according to the present embodiment is a method for recognizing daily activities based on multiple environmental sensors that detects the user's behavior based on environmental sensors and recognizes the user's daily activities, and includes a sensor data detection step (S10) for detecting sensor data that changes according to the user's behavior in a unit space, a step (S20) for predicting the resident's actual ADL (Activities of Daily Living) by receiving a triggering signal that causes segmentation from a device in the vicinity to analyze continuous sensor data acquired through a sensor unit, segmenting a section of continuous sensor data, analyzing the segmented data and recognizing a pattern to predict the resident's actual ADL, a step (S30) for storing ADL data for storing data for analyzing the sensor data to understand the resident's ADL behavior, and a wired/wireless communication step (S40) for transmitting a feedback signal generated by a main computing unit according to the learning result of the resident's ADL behavior as a notification to the user, notifying the resident's guardian, or transmitting the feedback signal to a device that operates as an actuator around the resident.

In addition, it includes a step (T10) of collecting and recording unit ADL behavior data to generate learning results (algorithms) to be used for ADL behavior inference, a step (T20) of learning ADL data based on the data, and a step (T30) of storing the learning results in an internal storage device and recording them to be used for ADL behavior inference.

The method for detecting a user's behavior and recognizing the user's daily behavior based on the environmental sensor of the present invention may be implemented in the form of program commands that can be executed by various computer components and recorded on a computer-readable recording medium. The computer-readable recording medium may include program commands, data files, data structures, etc., either singly or in combination.

The program commands recorded on the above computer-readable recording medium may be specially designed and configured for the present invention or may be known and available to those skilled in the art of computer software.

Examples of computer-readable recording media include magnetic media such as hard disks, floppy disks, and magnetic tapes, optical recording media such as CD-ROMs and DVDs, magneto-optical media such as floptical disks, and hardware devices specifically configured to store and execute program instructions such as ROM, RAM, and flash memory.

Examples of program instructions include not only machine language codes, such as those generated by a compiler, but also high-level language codes that can be executed by a computer using an interpreter or the like. The hardware device may be configured to operate as one or more software modules to perform processing according to the present invention, and vice versa.

Although various embodiments of the present invention have been illustrated and described above, the present invention is not limited to the specific embodiments described above, and various modifications can be made by a person having ordinary skill in the art to which the present invention pertains without departing from the gist of the present invention as claimed in the claims, and such modifications should not be understood individually from the technical idea or prospect of the present invention.

110: Sensor section
111: Multi-environment data measurement sensor
112: Noise sensor
113: Light sensor
114: Movement detection sensor
120: Wireless Communication Department
130: Main Computing Department
131: Broadcast Service Processing Department
132: Voice signal transmission unit
140: Data storage

Claims (13)

A home care device based on multiple environmental sensors that collects environmental change data occurring at the location linked to the indoor movement and location detection of the resident, detects the user's behavior based on environmental sensors in the space without external data, and recognizes the resident's daily behavior.
A sensor unit that detects sensor data that changes according to the user's actions in a unit space;
A main computing unit that receives a triggering signal that causes segmentation from a device in the vicinity to analyze continuous sensor data acquired through the above sensor unit, segments the continuous sensor data into sections, analyzes the segmented data, recognizes patterns, and predicts the actual ADL (Activities Of Daily Living) behavior of the resident;
A data storage unit for storing data to analyze the above sensor data and identify resident ADL behavior;
A wired/wireless communication unit that transmits a feedback signal generated by the main computing unit based on the learning results of the resident's ADL behavior as a notification to the user, notifies the resident's guardian, or transmits the signal to a device that operates as an actuator around the resident;
Includes,
The above main computing unit,
When the above sensor unit detects the entry and exit of a resident, data is stored in the data storage unit, and at least one sensor data is collected and compared to distinguish differences in resident behavior changes.
The above main computing unit,
From continuous sensor data, the location of the resident in a unit space and the resident's movement pattern are analyzed, and the environmental data and indoor noise data that change according to the resident's ADL behavior, and the indoor user's movement direction and location detection function are used to determine the location-based precise daily behavior history, thereby predicting and recording the resident's behavior.
The above main computing unit,
By managing the resident's daily behavior history, we predict the resident's ADL behavior and other behaviors and generate corrective alerts to notify the resident and the resident's caregiver.
The above wireless communication department,
A home care device for recognizing daily behavior based on multiple environmental sensors, which transmits the daily behavior history stored in the above data storage unit to the guardian of the resident at regular intervals, thereby receiving feedback on the consistency and appropriateness of the resident's daily behavior, and receiving feedback on judgments that are helpful for protection and treatment so that the resident's daily behavior can be maintained.
In the first paragraph,
The above main computing unit,
Includes a broadcast service processing unit that can generate feedback notifications to residents through broadcasting based on the above ADL behavior prediction results,
The above multi-environment sensor-based daily behavior recognition home care device is,
A home care device for recognizing daily behavior based on multiple environmental sensors, further comprising a voice signal transmission unit for transmitting feedback notifications generated by the above broadcast service processing unit to a user. delete delete In paragraph 1,
The above sensor part,
A daily behavior recognition home care device based on multiple environmental sensors, including a sensor that collects temperature, humidity, CO/CO2, TVOC, ammonia, air pressure, and illuminance data, which are the surrounding environment data of a unit space, a sensor that collects noise data generated according to the user's behavior in the unit space, and an infrared sensor that detects residents.
delete delete In paragraph 1,
The above wireless communication department,
A home care device based on multiple environmental sensors for recognizing daily activities, which transmits a signal including information that the resident has not performed an ADL activity when the resident does not perform the ADL activity.
In paragraph 1,
The above data storage unit,
A home care device that recognizes daily behaviors based on multiple environmental sensors, storing daily behavioral records such as the resident's motor skills, equipment usage skills, behavioral patterns and consistency, and abnormal behaviors.
delete delete In paragraph 1,
The Ministry of Wired and Wireless Communications,
A home care device based on multiple environmental sensors for recognizing daily activities, which includes a device that operates as an actuator around the resident through remote operation by the resident's caregiver, or a device that receives a remote equipment operation signal and converts it into a device operation signal that operates as an actuator around the resident, thereby controlling the peripheral device, when the resident does not perform ADL activities.
A home care method for recognizing daily behavior of residents based on multiple environmental sensors that detects user behavior based on environmental sensors.
A sensor data detection step that detects sensor data that changes according to the user's actions in a unit space;
A step of predicting the resident's actual ADL (Activities Of Daily Living) behavior by receiving a triggering signal that causes segmentation from a device in the vicinity to analyze continuous sensor data acquired through a sensor unit, segmenting the continuous sensor data into sections, analyzing the segmented data, recognizing patterns, and predicting the resident's actual ADL;
A step of storing ADL data for storing data for identifying resident ADL behavior by analyzing the sensor data through a data storage unit;
A wired/wireless communication step for transmitting a feedback signal generated by the main computing unit based on the learning results of the resident's ADL behavior as a notification to the user, notifying the resident's guardian, or transmitting the signal to a device that operates as an actuator around the resident;
The above main computing unit,
When the above sensor unit detects the entry and exit of a resident, data is stored in the data storage unit, and at least one sensor data is collected and compared to distinguish differences in resident behavior changes.
The above main computing unit,
From continuous sensor data, the location of the resident in a unit space and the resident's movement pattern are analyzed, and the environmental data and indoor noise data that change according to the resident's ADL behavior, and the indoor user's movement direction and location detection function are used to determine the location-based precise daily behavior history, thereby predicting and recording the resident's behavior.
The above main computing unit,
By managing the resident's daily behavior history, we predict the resident's ADL behavior and other behaviors and generate corrective alerts to notify the resident and the resident's caregiver.
The above wired and wireless communication steps are:
A home care method for recognizing daily behavior based on multiple environmental sensors, in which the daily behavior history saved in the step of storing the above data is transmitted to the guardian of the resident at regular intervals, thereby receiving feedback on the judgment regarding the consistency and appropriateness of the resident's daily behavior, and receiving feedback on judgment that is helpful for protection and treatment so that the resident's daily behavior can be maintained.