KR20210001869A - Lifelog caring system for a user and a method for contrlling the system - Google Patents

Abstract

The present invention provides a user life state monitoring management device (10) and a control method thereof. The user life state monitoring management device comprises: a monitoring sensor unit (200) including an activity sensor (200-1) which detects at least an activity in a living space of a user; a monitoring terminal unit (100) collecting monitoring data including monitoring life log data detected as the at least activity from the monitoring sensor unit (200); and a monitoring management server (400) checking at least an activity index indicating whether the user is active, a sleeping index indicating sleeping information, and a going out index indicating going out information by receiving the monitoring data of the monitoring terminal unit (100) to check and determine stability of a daily state of the user, and transmitting the stability to at least a guardian terminal unit (500) side.

Description

User living condition monitoring management device and its control method {LIFELOG CARING SYSTEM FOR A USER AND A METHOD FOR CONTRLLING THE SYSTEM}

The present invention relates to a system and a control method for performing safety management by detecting and checking the state of a user, for example, a person to be monitored by a sick person or an elderly person.

With the advancement of medical technology in the modern society, the age of survival continues to increase, leading to a life extension society. However, as a benefit to the contrary, a rapid increase in the population of diseases other than the conventional one, for example, a population of dementia patients or those who require psychological or psychological observation is increasing. For example, there is a rapid increase in the number of infringing patients and an increase in the number of elderly living alone, and the demand for medical and life-related protection or observation is rapidly increasing.

Usually, caregivers are in charge of routine probation for dementia patients or elderly people who need help from others because of their difficulty living alone, but the rate of increase in the influx of possible production personnel is remarkably low compared to the rate of increase in the elderly population. There is a remarkable shortage of professional manpower to manage.

In order to solve these problems, it was necessary to commercialize high-quality care services using ICT, and various technologies were researched and developed accordingly, but the development of technology-based wearable healthcare devices is increasing, but the actual use of the elderly is poor, utilization and maintenance. The management is in a remarkably low state and cannot provide practical assistance. In other words, the complicated usage, frequent charging management, and usage conditions that require constant portability act as a considerable burden or burden for the elderly who have difficulty in moving and living alone, resulting in extremely low practical usability and utility. Became.

Therefore, the need to use a non-contact non-aware sensor as an alternative to the elderly's reluctance to wearables has emerged, and the need for a constant and inexpensive life log sensor and a plan to be applied to the majority of the elderly population has been formed, and this solution It is an object of the present invention.

The present invention collects IoT sensor-based information for long-term and continuous life log collection, detects health abnormalities through life log analysis, and executes safety management, and provides appropriate information to growers about changes in life patterns for the elderly. The purpose of this is to provide a system and a control method for executing a cooperative health recommendation service through feedback from and Caregiver. That is, the present invention aims to develop a technology for detecting health abnormalities of a subject to be detected, such as the elderly, and recommending individual health related services based on 24-hour life log monitoring. That is, for example, through long-term and continuous monitoring of the elderly or those subject to mental and physical detection, the amount of activity of the subject, such as the elderly, and the unique life pattern of each individual are analyzed, and brain health-related condition evaluation and its variation are analyzed to be appropriate. It recommends personalized health services and aims to develop technologies that help the elderly continue their lives with healthy and active people through collaborative feedback.

The present invention is equipped with a contactless sensor and a narrow area activity detection sensor (Narrow Area Active Detector (N-AD)), an IoT sensor-based information collection unit for collecting long-term and continuous lifelogs of motoring subjects, and big data processing 24-hour life log monitoring including a health abnormality detection and safety management unit through life log analysis using detection information through, and a customized/cooperative health management service recommendation unit that performs a recommendation function according to life log and brain health status And an abnormality detection and response system and a control method thereof.

That is, the present invention provides a monitoring sensor unit 200 including an activity sensor 200-1 that detects at least activity in a user's living space, and a monitoring life that is detected as at least activity from the monitoring sensor unit 200. A monitoring terminal unit 100 that collects monitoring data including log data, an activity index indicating at least the user's activity by receiving the monitoring terminal unit 100 and monitoring data, sleep information indicating sleep information, and external activities Provides a user living condition monitoring management apparatus 10 including a monitoring management server 400 that checks the outing index indicating information, determines the stability of the user's daily condition, and transmits it to at least the guardian terminal unit 500 side.

In the user's living condition monitoring management apparatus 10, the activity sensors 200-1 may be disposed in a plurality of areas of the user's living space to detect space occupied by the user by time.

In the user living condition monitoring management device 10, the monitoring sensor unit 200: An environment that detects at least water, gas, and electricity usage and illumination conditions reflecting the daily life condition in the user's living space. It may further include a sensor unit 200-4 and a surveillance sensor unit 200-3 for detecting whether or not to go out from the user's living space.

In the user living condition monitoring management apparatus 10, the monitoring terminal unit 100 includes: a monitoring terminal communication unit 110 receiving the monitoring data from the monitoring sensor unit 200, and the monitoring sensor unit 200 ) A monitoring terminal storage unit 130 for storing the monitoring data received from the monitoring terminal control unit 120 for controlling transmission of the received monitoring data to the monitoring management server 400 to the monitoring management server 40 It may also include.

In the user living condition monitoring management apparatus 10, the monitoring management server 40 includes: a server communication module 4001 for receiving the monitoring data transmitted from the monitoring terminal 100, and the monitoring data A monitoring module 4100 that monitors and determines the stability of the user's daily state by checking the activity index indicating at least the user's activity, sleeping information indicating sleep information, and going out index indicating external activity information. ), and a corresponding module 4200 that transmits at least to the parental terminal unit 500 according to an analysis determination result of the monitoring module 4100.

In the user living condition monitoring management device 10, the monitoring module 4100: A spatial analysis monitoring sub for checking the user's space occupancy status information by time from the monitoring life log data detected as at least activeness among the monitoring data A behavior analysis monitoring submodule 4120 for confirming and analyzing user behavior information by using the user's spatial occupancy status information by time identified from the module 4110 and the spatial analysis monitoring submodule 41110, and the spatial analysis monitoring Includes an abnormality analysis monitoring submodule 4130 that monitors and analyzes the user's abnormal state by using the user's space occupancy status information by time of the submodule 4110 and the user's behavior information of the behavior analysis monitoring submodule 4120 You may.

In the user living condition monitoring management apparatus 10, the corresponding module 4200 comprises: an abnormality determination corresponding submodule 4210 executing a corresponding monitoring mode according to an analysis determination of the monitoring module 4100, and the An alarm execution response submodule 4220 that executes an emergency alarm mode when it is determined as an emergency situation in the analysis determination of the monitoring module 4100, and a report corresponding to the corresponding monitoring mode according to the analysis determination of the monitoring module 4100 It may also include a reporting-response sub-module 4230 that transmits to the parental terminal unit 500 side.

In the user's living condition monitoring management device 10, monitoring data of other users can be input to the monitoring module 4100, and the monitoring data of the user and the monitoring data of other users are used by using the monitoring data of the user and the monitoring data of other users. It may further include an AI learning module 4300 that executes machine learning learning to derive a correlation between a label and a feature in the monitoring data of another user.

In the user's living condition monitoring management device 10, the AI learning module 4300 includes: the user's monitoring data and the other user's monitoring data through machine learning using the user's monitoring data and other user's monitoring data. An AI learning model storage unit 4323 that stores an AI learning model for deriving a correlation between a label and a feature in the monitoring data, and the user's monitoring data and other users' monitoring data derived from the AI learning model storage unit 4423. It may also include an AI learning data storage unit 4321 that stores the correlation between the label and the feature in the monitoring data.

In the user's living condition monitoring management device 10, a core feature including time-based space occupancy status information of the user of the spatial analysis monitoring submodule 4110 and behavior information of the user of the behavior analysis monitoring submodule 4120 A similarity analysis monitoring sub-module that checks the similarity between the user's user core feature data and other user's core feature data, and checks and extracts labeling information for other user core feature data based on the data and other user's core feature data ( 4140) may be further included.

In the user's living condition monitoring management device 10, a label is generated by extracting and labeling data events from among the user's monitoring data and other user's monitoring data using the user's monitoring data and other user's monitoring data. It may further include an auto labeling module 4400.

In the user's living condition monitoring management device 10, the auto-labeling module 4400 includes: a data event among the user's monitoring data and other user's monitoring data by using the user's monitoring data and other user's monitoring data. Labeling verification to verify the consistency of the labeling given from the extracted data event extraction submodule 4410, the labeling submodule 4420 extracting and labeling the data event, and the labeling submodule 4420 It may also include a sub-module 4430.

According to another aspect of the present invention, the present invention provides a monitoring sensor unit 200 including an activity sensor 200-1 for detecting at least activity in a user's living space, and at least activity from the monitoring sensor unit 200. A monitoring terminal unit 100 for collecting monitoring data including monitoring life log data detected as, and an activity index indicating at least the user's activity by receiving monitoring data from the monitoring terminal unit 100, and sleeping information. User living condition monitoring management device 10 including a monitoring management server 400 that checks the going out index indicating sleep information and external activity information, determines the stability of the user's daily condition, and transmits it to at least the guardian terminal unit 500 ) Providing step (S10) of providing, and at least activeness detected from the monitoring sensor unit 200 received from the monitoring terminal unit 100 through the server communication module 4001 of the monitoring management server 400 By using monitoring data including monitoring life log data, the activity index indicating at least the user's activity, sleeping information indicating sleeping information, and going out index indicating external activity information are checked to monitor the stability of the user's daily condition. And a monitoring step (S20) of analyzing and determining the stability state by the monitoring module 4100, and a response mode determination step (S30) of determining a corresponding mode by the corresponding module 4200 according to the analysis determination result of the monitoring module 4100 (S30). And, a corresponding mode execution step (S40) of executing the corresponding mode determined in the corresponding mode determination step (S30).

In the method for controlling the user's living condition monitoring management device, the monitoring step (S20) includes: the monitoring sensor unit received from the monitoring terminal unit 100 through the server communication module 4001 of the monitoring management server 400 A monitoring input step (S21) of receiving and inputting monitoring data including monitoring life log data detected as at least active from 200, and a spatial analysis monitoring submodule from the monitoring life log data detected as at least active among the monitoring data The spatial analysis monitoring step (S23) in which the 4110 checks the user's space occupancy status information by time, and the behavioral analysis monitoring submodule using the user's spatial occupancy status information by time identified from the spatial analysis monitoring submodule 41110 The behavior analysis monitoring step (S25) in which the user's behavior information is checked and analyzed at 4120, the user of the spatial occupancy state information by time of the user of the spatial analysis monitoring submodule 4110 and the user of the behavior analysis monitoring submodule 4120 An abnormality analysis monitoring step (S27) of monitoring and analyzing whether the user is in an abnormal state by using the behavior information of the abnormality analysis monitoring submodule 4130 may be included.

In the method for controlling the user's living condition monitoring management device, the abnormal analysis monitoring step (S27) includes: an activity index indicating at least the user's activity by receiving monitoring data from the monitoring terminal 100, and a sleep indicating sleep information It may include a rule base abnormality analysis monitoring step (S271) of checking and determining the stability of the user's daily state by comparing the outing index indicating information and external activity information with a set reference value.

In the method of controlling the user living condition monitoring management device, the monitoring module 4100 may input monitoring data of another user to the user living condition monitoring management device, and the monitoring data of the user and the monitoring data of other users are used. The AI learning module 4300 further includes an AI learning module 4300 that derives a correlation between the user's monitoring data and the label and feature in the monitoring data of another user, and the user of the spatial analysis monitoring submodule 4110 Based on the user's core feature data and other user's core feature data, and the core feature data including the user's behavior information of the behavior analysis monitoring submodule 4120 and the user's core feature data by time Checking the similarity of data, checking and extracting labeling information for other user core feature data, receiving monitoring data with the monitoring terminal 100, at least an activity index indicating the user's activity, and sleeping information indicating sleeping information And an artificial intelligence abnormality analysis monitoring step (S273) of confirming and determining the stability of the user's daily state with respect to the outing index indicating external activity information.

In the method of controlling the user's living condition monitoring management device, the response mode determination step (S30) comprises: determining a response mode according to the rule base abnormality analysis monitoring confirmation result checked in the rule base abnormality analysis monitoring step (S271). It may also include a rule base correspondence mode determination step (S30-1).

In the method for controlling the user's living condition monitoring management device, the analysis monitoring data input step (S31) in which the rule base abnormality analysis monitoring confirmation result checked in the rule base abnormality analysis monitoring step (S271) is input, and the corresponding module (4200). (S33) of determining whether the rule base abnormality analysis monitoring check result is normal, and whether the response module 4200 is cautioned to determine whether the rule base abnormality analysis monitoring confirmation result needs attention. It may also include a determination step (S35).

In the method of controlling the user's living condition monitoring management device, the response mode determination step (S30) comprises: determining a response mode according to the artificial intelligence abnormality analysis monitoring confirmation result confirmed in the artificial intelligence abnormality analysis monitoring step (S273). It may also include an artificial intelligence response mode determination step (S30-2).

In the method for controlling the user's living condition monitoring management device, the analysis monitoring data input step (S301) in which the artificial intelligence abnormality analysis monitoring confirmation result checked in the artificial intelligence abnormality analysis monitoring step (S273) is input, and the corresponding module (4200). ), determining whether the core feature similarity indicating the core feature similarity is higher than the preset core feature high similarity as a result of the artificial intelligence anomaly analysis monitoring check result (S303), and artificial intelligence in the corresponding module 4200 A core feature similarity medium determination step (S305) of determining whether a core feature similarity indicating a core feature similarity is higher than a preset core feature medium similarity as a result of the intelligence anomaly analysis monitoring check result (S305) may be included.

In the method of controlling the user's living condition monitoring management device, the monitoring management server 400 further includes an auto labeling module 4400, which is executed at least after the providing step (S10), and An auto labeling step (S50) in which a label is generated by extracting and labeling a data event from among the user's monitoring data and other user's monitoring data may be further provided using the user's monitoring data.

In the method of controlling the user living condition monitoring management device, the auto labeling step (S50) includes: an auto labeling monitoring input step (S51) in which the monitoring data is received and input to the auto label module 4400, and monitoring data of the user. And a data event extraction step (S53) in which a data event is extracted from the data event extraction submodule 4410 from the user's monitoring data and other user's monitoring data using the monitoring data of another user, and a labeling submodule 4420. In the preliminary labeling step (S55) in which a label is assigned to the data event extracted in the data event extraction step (S53), and the labeling grant submodule 4420 in the preliminary labeling step (S55) The labeling verification step (S57) of verifying the integrity of the labeling given through the labeling verification submodule 4430 and the labeling that is given in the preliminary labeling step (S55) according to the verification result of the labeling verification step (S59) It may also include a labeling determination step (S59) of determining.

On the other hand, according to another aspect of the present invention, the present invention provides a monitoring sensor unit 200 including an activity sensor 200-1 for detecting at least activity in a user's living space, and the monitoring sensor unit 200. ), a monitoring terminal unit 100 for collecting monitoring data including monitoring life log data detected as at least active activity, and an activity index indicating at least user activity by receiving monitoring data from the monitoring terminal unit 100, Including a monitoring management server 400 that checks the sleep information indicating sleep information and an outing index indicating external activity information, determines the stability of the user's daily state, and transmits it to at least the guardian terminal unit 500, and the monitoring management In the server 400, monitoring data of other users can be input, and the correlation between labels and features in the monitoring data of the user and monitoring data of other users is derived using the monitoring data of the user and the monitoring data of other users. It further includes an AI learning module 4300 for executing machine learning learning, and the monitoring management server 400 de-identifies the monitoring data of the other user according to the minimum setting for de-identification of the monitoring data of the other user. A user life condition monitoring management apparatus comprising a DID module 4600 that performs identification and re-identifies the de-identified monitoring data of the other user to check whether the other user can be identified. Provides (10).

In the user living condition monitoring management apparatus, the monitoring management server 400 includes: a server communication module 4001 for receiving the monitoring data transmitted from the monitoring terminal unit 100, and the monitoring data A monitoring module 4100 that monitors and determines the stability of a user's daily state by checking at least an activity index indicating whether the user is active, sleeping information indicating sleep information, and an outing index indicating external activity information; and It may include a corresponding module 4200 that transmits at least to the parental terminal unit 500 according to the analysis determination result of the monitoring module 4100.

In the user's living condition monitoring management device, monitoring data of other users can be input to the monitoring module 4100, and the AI learning module 4300: Using the monitoring data of the user and the monitoring data of other users An AI learning model storage unit 4323 for storing an AI learning model for deriving a correlation between the user's monitoring data and the label and feature in the monitoring data of other users through machine learning learning, and the AI learning model storage unit ( It may also include an AI learning data storage unit 4321 for storing the correlation between the user's monitoring data derived from 4423 and the label and feature in the other user's monitoring data.

In the user living condition monitoring management apparatus, the DID module 4600: De-identification to de-identify the monitoring data of the other user according to the minimum setting of de-identification of the monitoring data of the other user. An identification submodule 4610, a re-ID confirmation module 4620 for re-identifying the de-identified monitoring data of another user, and a DID similarity confirmation module 4630 for checking whether the other user can be identified. It may also include.

In the user's living condition monitoring management apparatus, the identification sub-module 4610: a di-identification sub-minimum recitation for confirming a minimum requirement required to make re-identification of the monitoring data of the other user impossible. A non-displayed individual whose personal information-related data feature of the monitoring data of the other user is not displayed based on the minimum requirements confirmed by the verification unit 4611 and the di-identification sub-minimum recitation verification unit 4611 The identification sub-feature check unit 4713 for checking an information-related data feature, and the identification sub-feature check unit 4713 for checking the non-display target personal information-related encrypted data feature invisible. It may also include a location subscription (4617).

In the user's living condition monitoring management device, the identification sub-module 4610 is associated with personal information to be non-displayed among the personal information-related data features checked by the identification sub-feature check unit 4713 The identification sub-crypto unit 4615 for encrypting the data feature may be further included.

In the user living condition monitoring management apparatus, the DID module 4600 may further include: a minimum setting storage module 4640 for updating a minimum setting by de-identifying monitoring data of the other user.

In the apparatus for monitoring and managing the user's living condition, the activity sensor 200-1 may be disposed in a plurality of areas of the user's living space to detect space occupied by the user by time.

In the user's living condition monitoring management device, the monitoring sensor unit 200 includes: an environment sensor unit that detects at least water, gas, and electricity consumption and illumination conditions reflecting the daily life condition in the user's living space ( 200-4) and a surveillance sensor unit 200-3 that detects whether or not the user goes out from the living space.

In the user's living condition monitoring management apparatus, the monitoring terminal unit 100 includes: a monitoring terminal communication unit 110 receiving the monitoring data from the monitoring sensor unit 200, and receiving from the monitoring sensor unit 200 And a monitoring terminal storage unit 130 for storing the obtained monitoring data, and a monitoring terminal control unit 120 for controlling transmission of the received monitoring data to the monitoring management server 400 to the monitoring management server 40. May be.

In the user's living condition monitoring management device, the monitoring management server 400 extracts a data event from among the user's monitoring data and other user's monitoring data using the user's monitoring data and other user's monitoring data, It may further include an auto labeling module 4400 for generating a label by performing labeling.

In the user's living condition monitoring management device, the auto-labeling module 4400 includes: data for extracting a data event from among the user's monitoring data and other user's monitoring data using the user's monitoring data and other user's monitoring data An event extraction sub-module 4410, a labeling sub-module 4420 that extracts the data event and assigns a label, and a labeling verification sub-module that verifies the consistency of the labeling given by the labeling sub-module 4420 ( 4430) may also be included.

In the user living condition monitoring management apparatus, the monitoring module 4100 comprises: a space analysis monitoring sub-module 4110 for checking the user's space occupancy status information by time from the monitoring life log data detected as at least activeness among the monitoring data. ), a behavioral analysis monitoring submodule 4120 for confirming and analyzing user's behavior information using the user's time-based space occupancy state information checked from the spatial analysis monitoring submodule 41110, and the spatial analysis monitoring submodule ( It may also include an abnormality analysis monitoring submodule 4130 that monitors and analyzes whether or not a user is in an abnormal state by using the user's space occupancy status information by time of 4110 and the user's behavior information of the behavior analysis monitoring submodule 4120. .

In the user's living condition monitoring management device, core feature data including time-based space occupancy status information of the user of the spatial analysis monitoring submodule 4110 and behavioral information of the user of the behavior analysis monitoring submodule 4120, and others Based on the user's core feature data, a similarity analysis monitoring sub-module 4140 that checks the similarity between the user's user core feature data and other user core feature data, and checks and extracts labeling information for other user core feature data. It may include more.

In the user living condition monitoring management apparatus, the corresponding module 4200 comprises: an abnormality determination corresponding submodule 4210 executing a corresponding monitoring mode according to an analysis determination of the monitoring module 4100, and the monitoring module ( In the analysis determination of 4100), when it is determined that it is an emergency, an alarm execution response submodule 4220 that executes an emergency alarm mode and a report corresponding to the corresponding monitoring mode according to the analysis determination of the monitoring module 4100 are transmitted to the guardian terminal. It may also include a reporting-response sub-module 4230 that is transmitted to the sub-500 side.

According to another aspect of the present invention, the present invention provides a monitoring sensor unit 200 including an activity sensor 200-1 for sensing at least activity in a user's living space, and at least from the monitoring sensor unit 200. A monitoring terminal unit 100 that collects monitoring data including monitoring life log data detected as activity, and an activity index indicating at least the user's activity by receiving monitoring data from the monitoring terminal unit 100, and sleeping information Including a monitoring management server 400 that checks the indicating sleep information and the outing index indicating the external activity information, determines the stability of the user's daily state, and transmits it to at least the guardian terminal unit 500, and the monitoring management server 400 ), monitoring data of other users can be input, and machine learning learning to derive the correlation between labels and features in the monitoring data of the user and monitoring data of other users using the monitoring data of the user and the monitoring data of other users It further includes an AI learning module 4300 to execute, and the monitoring management server 400 de-identifies the monitoring data of the other user according to the minimum setting for de-identification of the monitoring data of the other user. User living condition monitoring management device (10), characterized in that it comprises a DID module (4600) that executes and re-identifies the de-identified monitoring data of the other user to check whether the other user can be identified. A providing step (S10) of providing and monitoring detected as at least activeness from the monitoring sensor unit 200 received from the monitoring terminal unit 100 through the server communication module 4001 of the monitoring management server 400 By using monitoring data including life log data, the activity index indicating at least the user's activity, sleeping information indicating sleeping information, and outing index indicating external activity information are checked. A monitoring step (S20) of monitoring and confirming the stability of the user's daily state and analyzing and determining the stability state in the monitoring module 4100, and a response mode in the response module 4200 according to the analysis determination result of the monitoring module 4100. A method for controlling a user's living condition monitoring management device comprising: determining a corresponding mode determining step (S30) and executing a corresponding mode determined in the corresponding mode determining step (S30) (S40). to provide.

In the method for controlling the user's living condition monitoring management device, the monitoring step (S20) includes: the monitoring sensor unit received from the monitoring terminal unit 100 through the server communication module 4001 of the monitoring management server 400 A monitoring input step (S21) of receiving and inputting monitoring data including monitoring life log data detected as at least active from 200, and a spatial analysis monitoring submodule from the monitoring life log data detected as at least active among the monitoring data The spatial analysis monitoring step (S23) in which the 4110 checks the user's space occupancy status information by time, and the behavioral analysis monitoring submodule using the user's spatial occupancy status information by time identified from the spatial analysis monitoring submodule 41110 The behavior analysis monitoring step (S25) in which the user's behavior information is checked and analyzed at 4120, the user of the spatial occupancy state information by time of the user of the spatial analysis monitoring submodule 4110 and the user of the behavior analysis monitoring submodule 4120 An abnormality analysis monitoring step (S27) of monitoring and analyzing whether the user is in an abnormal state by using the behavior information of the abnormality analysis monitoring submodule 4130 may be included.

In the method for controlling the user's living condition monitoring management device, the abnormal analysis monitoring step (S27) includes: an activity index indicating at least the user's activity by receiving monitoring data from the monitoring terminal 100, and a sleep indicating sleep information It may include a rule base abnormality analysis monitoring step (S271) of checking and determining the stability of the user's daily state by comparing the outing index indicating information and external activity information with a set reference value.

In the method of controlling the user living condition monitoring management device, the monitoring module 4100 may input monitoring data of another user to the user living condition monitoring management device, and the monitoring data of the user and the monitoring data of other users are used. The AI learning module 4300 further includes an AI learning module 4300 that derives a correlation between the user's monitoring data and the label and feature in the monitoring data of another user, and the user of the spatial analysis monitoring submodule 4110 Based on the user's core feature data and other user's core feature data, and the core feature data including the user's behavior information of the behavior analysis monitoring submodule 4120 and the user's core feature data by time Checking the similarity of data, checking and extracting labeling information for other user core feature data, receiving monitoring data with the monitoring terminal 100, at least an activity index indicating the user's activity, and sleeping information indicating sleeping information And an artificial intelligence abnormality analysis monitoring step (S273) of confirming and determining the stability of the user's daily state with respect to the outing index indicating external activity information.

In the method of controlling the user's living condition monitoring management device, the response mode determination step (S30) comprises: determining a response mode according to the rule base abnormality analysis monitoring confirmation result checked in the rule base abnormality analysis monitoring step (S271). It may also include a rule base correspondence mode determination step (S30-1).

In the method for controlling the user's living condition monitoring management device, the analysis monitoring data input step (S31) in which the rule base abnormality analysis monitoring confirmation result checked in the rule base abnormality analysis monitoring step (S271) is input, and the corresponding module (4200). (S33) of determining whether the rule base abnormality analysis monitoring check result is normal, and whether the response module 4200 is cautioned to determine whether the rule base abnormality analysis monitoring confirmation result needs attention. It may also include a determination step (S35).

In the method of controlling the user's living condition monitoring management device, the response mode determination step (S30) comprises: determining a response mode according to the artificial intelligence abnormality analysis monitoring confirmation result confirmed in the artificial intelligence abnormality analysis monitoring step (S273). It may also include an artificial intelligence response mode determination step (S30-2).

In the method for controlling the user's living condition monitoring management device, the analysis monitoring data input step (S301) in which the artificial intelligence abnormality analysis monitoring confirmation result checked in the artificial intelligence abnormality analysis monitoring step (S273) is input, and the corresponding module (4200). ), determining whether the core feature similarity indicating the core feature similarity is higher than the preset core feature high similarity as a result of the artificial intelligence anomaly analysis monitoring check result (S303), and artificial intelligence in the corresponding module 4200 A core feature similarity medium determination step (S305) of determining whether a core feature similarity indicating a core feature similarity is higher than a preset core feature medium similarity as a result of the intelligence anomaly analysis monitoring check result (S305) may be included.

In the method for controlling the user's living condition monitoring management device, executed at least after the providing step (S10), and the minimum setting of de-identification of the monitoring data of the other user in the DID module 4600 of the monitoring management server 400 According to the Diadi step of performing de-identification of de-identifying the monitoring data of the other user and re-identifying the de-identified monitoring data of the other user to confirm whether the other user can be identified (S60) ) May be further included.

In the method for controlling the user's living condition monitoring management device, the DID step (S60) includes: a DID monitoring input step (S61) in which the monitoring data is received and input to the DID module 4600, and monitoring data of the other user. The de-identification step (S63) in which the de-identification of de-identifying the monitoring data of the other user is executed in the de-identification submodule 4610 according to the minimum setting of de-identification, and the de-identification The minimum setting requirement verification step (S65) in which the monitoring data of other users is re-identified and compared with the minimum setting requirement to confirm whether re-identification is possible, and the requirement verification result in the minimum setting requirement verification step (S65) It may also include a verification response step (S67) of executing the verification response set according to.

In the method for controlling the user's living condition monitoring management device, the de-identification step (S63) is: In the de-identification sub-minimum recitation confirmation unit 4611 of the di-identification sub-module 4610, the The identification sub-minimum recitation confirmation step (S631) of confirming the minimum requirements required to prevent re-identification of the monitoring data of other users, and the identification sub of the identification sub-module 4610 Non-displayed personal information in which personal information related data features of other users' monitoring data are hidden based on the minimum requirements confirmed by the de-identification sub-minimum reclamation confirmation unit 4611 in the feature check unit 4713 The identification sub-feature check step (S633) of checking the associated data feature, and the identification sub-feature check unit in the identification sub-screening unit 4616 of the identification sub-module 4610 It may include a de-identification subscription step (S635) of non-displaying the personal information-related data feature to be undisplayed among the personal information-related data features identified in (4613).

In the method for controlling the user's living condition monitoring management device, the de-identification step (S63) includes: the de-identification sub-crypto unit 4615 of the de-identification sub-module 4610 A de-identification sub-crypto step (S367) of encrypting a non-display target personal information-related data feature among the personal information-related data features identified by the sub-feature check unit 4713 may be further included.

In the method for controlling the user's living condition monitoring management device, the step of verifying the minimum setting requirement (S65) includes: the non-identified other user in the re-ID confirmation module 4620 of the di-identification sub-module 4610. The re-ID confirmation step (S651) of re-identifying the monitoring data, and the DID similarity calculated by the DID similarity checking module 4630, indicating whether the re-identified monitoring data of the other user can be identified by another user. A confirmation step (S653) and a DID completion confirmation step (S655) of determining whether the minimum setting requirement of the D-Identification is satisfied by whether the DID similarity calculated in the DID similarity checking step (S653) is less than a preset similarity It may include more.

According to the present invention, according to the need to develop IoT sensor-based information collection technology for long-term, continuous life log collection in consideration of the elderly, based on information extracted by sustainable sensing using an activity detector with a contactless sensor By using the data acquired along with the provision of an activity level detector that makes the study of the amount of activity and life pattern through combination with other sensors, secure big data on the life pattern of the elderly in a non-contact state, and the activity amount and life pattern over a long period of time It is possible to secure clinical information on the correlation between the change in the user's health status, for example, the brain health status.

According to the present invention, by securing an inexpensive monitoring means that will cover the majority of the elderly, health abnormality detection and safety management system development through life log analysis are performed, medical information and constant monitoring life log through the identification of super ager's lifestyle. Based on the information of and, it is possible to provide customized health programs for the elderly. In other words, a model that predicts the health abnormalities of the general elderly is needed, which marks changes in the patterns of life, etc. of Parkinson patients including dementia including dementia and chronic diseases in relation to brain cognition as an analysis reference and applies them to the general elderly. Analyze the correlation between data (life patterns) and brain health status through clinical trials, and apply it to the elderly, so it is possible to run a model for predicting the health status of the general population, and the cost burden of use through minimal optimization of installation and operation costs It may be possible to provide sufficient monitoring and management services to more elderly users by minimizing and expanding user coverage.

In addition, it is possible to increase the importance of continuous health management even in places other than medical institutions in need of rapid accident response and prevention through detection of emergency situations through life pattern analysis. Data acquisition/analysis using mobile devices capable of continuous monitoring and interaction is necessary, and it is necessary to provide customized healthcare services suitable for individual health status, emotional status, and preferences, and reduction of activity volume over a period of 24 hours and a long period of time, and life patterns It is necessary to measure the amount of change in (activity, sleep, going out, toilet use, etc.), and through this, it can provide a sense of psychological and emotional stability that the elderly can receive help in emergency situations in their home life.

The present invention has accumulated many years of care experience for silver care, and developed a telecare communication infrastructure and equipment using a wireless network for the first time through the technology of safety service for the elderly through the self-owned capabilities of equipment, protocols and telecare platforms. The ability to provide lifestyle habits and health services tailored to the elderly.

The present invention, through the implementation of the rule base-based monitoring function and simultaneously or selectively through the implementation of the artificial intelligence monitoring function, by comparing the preset reference value and the user's own monitor data through monitoring data including the user's own monitoring lifelog data. Rule base-based monitoring and response process may be performed, and risk or attention by monitoring the current state of life of the current user by using a priori events of other users through machine learning for monitoring data of other users other than the user's own monitoring data. It may be possible to provide advance notification of the situation or to implement preventive measures.

In addition, in the present invention, when using the monitoring data of the present user and/or the monitoring data of other users, labeling the monitoring data to maintain the amount of data processing and to increase the accuracy of data analysis, but automatic labeling By enabling the operation, it is possible to more accurately monitor and manage life information of the user through rapid update with a meaningful label of the monitoring data.

In addition, the present invention is to perform machine learning using the monitoring data of other users in addition to the monitoring data of the present user, when using the monitoring data of other users, including computational obligatory records, de-identification for personal information protection measures. Respond by reviewing the necessity of additional de-identification measures by checking whether re-identification is possible and responding to the minimum de-identification measures in accordance with regulations through the components and methods that perform functions. By doing so, while optimizing the amount of computation, it is possible to minimize the risk of personal information leakage.

1 is a schematic configuration diagram of a user living condition monitoring management apparatus according to an embodiment of the present invention.
2 and 3 are schematic and detailed configuration diagrams of a monitoring sensor unit and a monitoring terminal unit of an apparatus for monitoring a user's living condition according to an embodiment of the present invention.
4 is a schematic block diagram of a monitoring management server of a user living condition monitoring management apparatus according to an embodiment of the present invention.
5 to 8 are schematic block diagrams of a detailed configuration of a monitoring management server of a user living condition monitoring management apparatus according to an embodiment of the present invention.
9 is a schematic flowchart of a control method of an apparatus for monitoring and managing a user's living condition according to an embodiment of the present invention.
10 to 17 are schematic flowcharts and detailed flowcharts of a control method of an apparatus for monitoring and managing a user's living condition according to one or more exemplary embodiments of the present invention.
18 is a detailed block diagram of an apparatus for monitoring and managing a user's living condition according to a variation of an embodiment of the present invention.
19 is a flowchart of a method for controlling a user living condition monitoring management apparatus according to a variation of an embodiment of the present invention.

Hereinafter, preferred embodiments of the present invention will be described in detail with reference to the accompanying drawings. First of all, in adding reference numerals to elements of each drawing, it should be noted that the same elements have the same numerals as possible even if they are indicated on different drawings. In addition, in describing the present invention, if it is determined that a detailed description of a related known configuration or function may obscure the subject matter of the present invention, a detailed description thereof will be omitted.

The user's living condition monitoring management device 10 of the present invention includes a monitoring sensor unit 200, a monitoring terminal unit 100, and a monitoring management server 400, and the monitoring management server 400 is a user preset It communicates with the guardian terminal unit 300 on the guardian side.

The monitoring sensor unit 200 of the present invention is disposed in a user's living space, as shown in FIGS. 1 and 2. The monitoring sensor unit 200 is a user who needs management or protection, that is, a person with mild cognitive impairment, a person with musculoskeletal disease, a person with respiratory disease such as chronic obstructive pulmonary disease (COPD), a person with a mental illness such as crying disorder, etc. Acquires information from users' living spaces, such as. That is, the monitoring sensor unit 200 is disposed in the living space of the sick or the elderly to acquire the user's life activity information, so-called life log data, and the monitoring sensor unit 200 of the present invention is a non-possible contactless sensing structure To achieve. In the case of the sick or the elderly, the hassle that occurs when a separate sensor device is provided to detect and grasp the life log as a life pattern, the detection accuracy decreases due to frequent non-possibility, and the hassle for charging the battery or undetected due to battery discharge. In order to solve problems such as formation of a state, the monitoring sensor unit 200 of the present invention takes a structure that the user does not possess and is directly mounted in the user's living space.

That is, it includes an activity sensor 200-1 that detects at least activity in the user's living space. The activity sensor 200-1 is disposed in the user's living space, and its placement position may be adjusted according to the sensing environment. The activity sensor 200-1 may be configured as an infrared sensor within a range that detects the user's activity, and various selections are possible. In the present embodiment, the activity sensor 200-1 is shown to be disposed one by one in each space, but in some cases, a narrow area activity sensor and a wide area activity sensor of a wide detection area are respectively provided to detect detailed motion by narrowing the detection area. It is possible to implement a variety of implementations according to design specifications, such as being able to take a configuration in which a plurality of are arranged.

Meanwhile, the activity sensor 200-1 may include an activity sensor detector 201, an activity sensor control unit 203, and an activity sensor communication unit 205. Other sensors of the monitoring sensor unit 200 described below may also take a configuration including a detector, a control unit, and a communication unit. Here, the communication unit may take various types of communication structures such as ZigBee and 5G, and enables data transmission and reception by establishing a communication method for implementing the function of IOT.

The monitoring module 4100 of the monitoring management server 400 of the present invention utilizes the detection signal of the activity sensor 200-1, according to changes in the space occupied by the user, the occupied time in the occupied space, and the occupied space. It enables the acquisition of secondary information such as mobility. In this way, based on the information extracted through sustainable sensing through the activity sensor 200-1 of the non-carrying contactless sensor of the present invention, a study of the amount of activity and life pattern through a combination with other sensors is conducted. By using the data acquired along with the provision of the activity level detector to be achieved, it is possible to secure big data on the life pattern of the elderly in a non-awareness and non-contact state, and by securing clinical information that correlates with the change of activity and life pattern over a long period of time and brain health. , By securing inexpensive monitoring means to cover the majority of the elderly, it is possible to detect health abnormalities through life log analysis and implement a safety management system, and extract meaningful information or events through tracking lifestyles of the sick or the elderly. It is possible to provide a health program tailored to the elderly based on the information with the constant monitoring life log.

That is, the present invention collects the lifelog data related to the user's daily life and compares it with a preset reference value to monitor the current state of the user, or compares it with the lifelog data of the user's own previous monitoring data, and/or It provides a structure to monitor the user's current state by comparing it with other's monitoring data. The user checks the previous life pattern, that is, a similar or different pattern different from the life log pattern through his or her own time series of monitoring data points, and compares it with the reference set value to determine whether there is an abnormality. Can make the countermeasures in action feasible.

In addition, in some cases, users can judge whether they are similar or abnormal through comparison with other people's monitoring data in addition to their own time series of monitoring data points, and warn them to take action. You may. In other words, it is possible to perform countermeasures by judging whether or not similarity or abnormality is detected by comparing monitoring data of the same age group or other person with the same disease based on the current time or with time-series time series monitoring data.

Through this configuration, through the user's own monitoring data or the monitoring data of another person, for example, the monitoring information of the other person, the pattern of daily information related to the life of the diseased person such as mild cognitive impairment or Parkinson patients and chronic diseases. It is also possible to mark the change as an analysis reference and compare it with the monitoring data of the general user to monitor the possibility of preliminary disease caused by the change in the daily life pattern of the general user.

For example, by comparing and applying information on the elderly or others to predict the health abnormality of the general elderly, or, conversely, by comparing the daily information of the general elderly and information on the diseased person to monitor the predicted disease probability, or Patients with diseases through clinical trials and life log data (life patterns) of others of the user, such as enabling preliminary warnings or precautionary measures to be taken about possible or anticipated situations by comparing the information about the patient with the information of other diseases. Analyzing the correlation between the health status of and applying it to the elderly, it is also possible to execute the operation of the health status prediction model of the general public. In particular, in consideration of the high possibility that the users of the present invention are elderly people, a non-possessed contactless sensing structure using an IoT sensor-based information collection technology for long-term and continuous life log collection is implemented.

The activity sensor 200-1 may be configured to detect both a narrow area or a wide area by mounting and mounting both a narrow area activity sensor and a wide area activity sensor as described above in a user space. -1) A plurality of user's living spaces may be arranged. In other words, the activity sensor 200-1 may be disposed in a plurality of areas of the user's living space to minimize blind areas, thereby enabling accurate collection of life log data and monitoring data regarding the user's activity. Detects space occupied by time.

The present invention may further include various sensors for collecting various lifelog data, that is, monitoring data in addition to detecting the user's activity. That is, the monitoring sensor unit 200 further includes an environment sensor unit 200-4 and a surveillance sensor unit 200-3, wherein the environment sensor unit 200-4 is At least water, gas, and electricity usage and illumination conditions reflecting the daily living conditions in the space are sensed, and the surveillance sensor unit 200-3 detects whether or not the user goes out from the living space.

The environment sensor unit 200-4 and the surveillance sensor unit 200-3, like the activity sensor 200-1, include a sensor detector, a sensor control unit, and a sensor communication unit to perform detected lifelog data. It enables transmission to the monitoring management server 400 side.

The environment sensor unit 200-4 acquires information on the user's daily life environment in the space where the user resides, that is, information on the user's space such as gas, electricity, water, and illuminance and/or temperature and humidity. In this embodiment, the user's living space mainly includes a bedroom space (Abd), a living space (Alv), a bathroom space (Abt), a kitchen space (Akc), and an access space (Adr), which is an example of the present invention. The user's living space is not limited thereto, and various modifications are possible within the range of detecting the user's activity behavior, but in this embodiment, the bedroom space (Abd), the living space (Alv), the bathroom space (Abt), and the kitchen space (Akc) , The access space (Adr) is set as a user activity space or a living space.

That is, the environment sensor unit 200-4 includes an environment illuminance sensor 200-4a, an environment temperature and humidity sensor 200-4c, and an environment metering sensor 200-4b, 200-4d, 200 -4e,200-4f),

The environment illuminance sensor 200-4a detects illuminance in each living space in which the illumination lamp 160 is disposed. In the case of illuminance, in particular, it is one of the important living environment factors affecting the mental state of the sick or elderly users who suffer from mental illness or need attention. For example, in the case of elderly patients with mild cognitive impairment, a sudden change in illuminance may induce physical and mental changes such as sudden seizures in some cases, and consider the user's activity status or direction of activity to prevent sudden changes in illuminance. Accordingly, it is possible to provide an optimized living environment to the user by controlling the operation of the lighting lamp 160.

In addition, the environment temperature and humidity sensor 200-4c detects the temperature and humidity in the active living space of the user. It may be used to derive a correlation affecting each user's activity through comparison of the temperature and humidity data from the environment temperature/humidity sensor 200-4c with the user's activity amount lifelog data.

In addition, the environment metering sensor (200-4b, 200-4d, 200-4e, 200-4f) detects the use of water, gas, and electricity in the living space where the user lives and monitors it to the monitoring management server 40 side. Enables the transfer of data. The environment weighing sensor (200-4b,200-4d,200-4e,200-4f) includes the environment electricity metering sensor (200-4d) and the environment water metering sensor (200-4e) and the environment. A gas metering sensor 200-4f may be included, and in some cases, an environment kitchen activity metering sensor 200-4b may be included.

The environment electricity metering sensor 200-4d detects the amount of electricity used in the user's living space, and the environment water metering sensor 200-4e detects the amount of water used in the user's living space, The environment gas metering sensor 200-4f detects the amount of gas used in the user's living space. In some cases, the use of gas for the heater or the use of the gas range for the kitchen range may be considered, and in the case of district heating or use of an induction range, each situation may be considered and reflected in the life log.

In addition, as the environment kitchen activity metering sensor 200-4b, it detects essential items such as home appliances used in the kitchen, for example, the number of times the door of the appliance door is opened and closed of refrigerated appliances such as refrigerators and kimchi refrigerators. The same environment kitchen activity metering sensor 200-4b may be further provided.

The surveillance sensor unit 200-3 may detect whether or not the user goes out from the living space. That is, the surveillance sensor unit 200-3 includes a surveillance door lock sensor unit 200-3a, a private school surveillance door sensor unit 200-3b, and a surveillance access activity sensor unit 200-3c. Includes.

Surveillance door lock sensor unit (200-3a) is the operation sensor of the door lock of the user's living house, the surveillance door sensor unit (200-3b) is a sensor that checks whether the user's door is opened, the surveillance The access activity sensor unit 200-3c includes a sensor that checks whether the user has entered through the door, and the surveillance sensor unit 200-3 may include a separate sensor for preventing theft function. have.

In addition, the monitoring sensor unit 200 may further include a safety sensor unit 200-2 for life safety in a user's living space. The safety sensor unit 200-2 is implemented as a gas fire-related sensor in this embodiment, and the safety sensor unit 200-2 includes a safety gas blocking sensor unit 200-2a and a safety gas sensor unit 200-2b. , And a safety fire sensor unit (200-2c). The safety gas cut-off sensor unit 200-2a detects whether a switch for gas devices such as a gas range in the user's space is cut off, and the safety gas sensor part 200-2b detects whether gas is leaking, and a safety fire sensor. The unit 200-2c may detect whether a fire has occurred in the user's indoor space and transmit fire-related information to monitor gas leakage and fire-related safety information.

The arrangement and configuration of the monitoring sensor unit 200 is an example, and various modifications are possible within a range of acquiring various information of monitoring data of the user's lifelog data.

Meanwhile, the monitoring terminal unit 100 collects monitoring data including at least monitoring life log data detected as active from the monitoring sensor unit 200 and transmits the collected monitoring data to the monitoring management server 400. The monitoring terminal unit 100 functions as a monitoring management server gateway for the information detected by the monitoring sensor unit 200 for detecting monitoring data, which is lifelog data in the user space where the user lives.

The monitoring terminal unit 100 includes a monitoring terminal communication unit 110, a monitoring terminal storage unit 130, and a monitoring terminal control unit 120.

The monitoring terminal communication unit 110 receives monitoring data from the monitoring sensor unit 200 and transmits the received monitoring data to the monitoring management server 400 according to the transmission control of the monitoring terminal control unit 120 to be described below. The monitoring terminal storage unit 130 stores monitoring data received from the monitoring sensor unit 200, and the monitoring terminal control unit 120 transmits the monitoring data received to the monitoring management server 40 to the monitoring management server 400. Control.

The monitoring management server 400 receives the monitoring terminal unit 100 and monitoring data. The monitoring management server 400 checks the stability of the user's daily state by checking at least an activity index indicating whether the user is active, sleeping information indicating sleeping information, and an outing index indicating external activity information. The monitoring management server 400 transmits or processes the confirmation determination to at least the guardian terminal unit 300 based on the confirmation determination.

The monitoring management server 40 includes a server communication module 4001, a monitoring module 4100, and a corresponding module 4200, each of which has a modular configuration, but in some cases, the overall server control unit of the monitoring management server is used. Various modifications are possible, such as being able to take a configuration in which each module is controlled.

The server communication module 4001 receives monitoring data transmitted from the monitoring terminal unit 100. In some cases, the monitoring management server 40 includes a separate server signal processing module 4003 to process monitoring data received from the monitoring terminal unit 100 to process data to other components of the monitoring management server 40. You can also enable transmission.

The monitoring module 4100 monitors and checks the stability of the user's daily state by checking at least an activity index indicating whether the user is active, sleeping information indicating sleeping information, and an outing index indicating external activity information using monitoring data. Analyze and judge.

In this embodiment, the monitoring module 4100 includes a spatial analysis monitoring sub-module 4110, a behavior analysis monitoring sub-module 4120, and an abnormality analysis monitoring sub-module 4130.

The spatial analysis monitoring sub-module 4110 checks the user's space occupancy status information by time from monitoring life log data detected as at least activity among the monitoring data. That is, the spatial analysis monitoring sub-module 4110 is a monitoring representing the user's activity among user monitoring data received from the sub communication module 4001 of the monitoring management server 40 and signal-processed by the sub signal processing module 4003. By detecting and checking the user's activity by living space from the life log data, the user's activity amount, user's occupancy by space, bedtime information such as sleep time, external information through information on the space currently occupied by the user and changes in occupied space It is possible to form processing data such as access to and emergency matters.

The behavior analysis monitoring submodule 4120 confirms and analyzes the user's behavior information by using the user's spatial occupancy status information by time identified from the spatial analysis monitoring submodule 4110. In other words, the behavior analysis monitoring submodule 4120 uses the user's space occupancy status information by time identified from the spatial analysis monitoring submodule 4110, from which the user's state activity amount, sleep information, activity index for external activities, etc. You can calculate the index and outing index.

The abnormality analysis monitoring submodule 4130 monitors and analyzes the user's abnormal state by using the user's time-specific space occupancy status information of the spatial analysis monitoring submodule 4110 and the user's behavior information of the behavior analysis monitoring submodule 4120. do. That is, the abnormality analysis monitoring submodule 4130 compares the user's behavior information calculated and analyzed by the behavior analysis monitoring submodule 4120, that is, the calculated activity index, sleep index, and going out index with preset values, etc. Abnormal state analysis may be performed.

The corresponding module 4200 transmits at least to the parental terminal unit 300 according to the analysis determination result of the monitoring module 4100. That is, the corresponding module 4200 according to the analysis determination result in the spatial analysis monitoring sub-module 4110, the behavioral analysis monitoring sub-module 4120, and the abnormality analysis monitoring sub-module 4130 of the monitoring module 4100, If the user is in a normal state, monitoring information on the normal state can be reported to at least the guardian terminal of the guardian side, and in case of an abnormal state, a follow-up procedure can be executed to take a preset emergency response measure.

The response module 4200 includes an abnormality determination response submodule 4210, an alarm execution response response submodule 4220, and a reporting response response submodule 4230.

The abnormality determination response submodule 4210 executes a corresponding monitoring mode according to the analysis determination of the monitoring module 4100. The corresponding mode executed in this embodiment includes a rule base response mode according to comparison of preset values, and in some cases, may further include an artificial intelligence response mode when processing including data of other users.

The rule base response mode includes three response modes in the present embodiment, which include a normal response mode, an attention response mode, and an emergency response mode.

In the normal response mode, the user determines that there is no particular abnormal state, and performs a reporting response operation in which information on the user's life log is transmitted to the guardian terminal unit 300 of the guardian side set in advance at a predetermined time point.

In the caution response mode, the user is not in a special abnormal state yet, but it is determined that it is a living state that requires attention unlike usual, and the information on the user's life log is transmitted to the guardian terminal unit 300 of the predetermined guardian side at a predetermined time. , Execute a reporting response action to advise the guardian or user's careful observation.

In the emergency response mode, the user determines that it is an abnormal state that requires a special emergency response, and immediately transmits information on the user's life log indicating a situation that requires an emergency response operation to the guardian terminal unit 300 of the pre-set guardian side. The reporting response operation is executed.

The alert execution response submodule 4220 executes the emergency response mode when it is determined that it is an emergency situation in the analysis determination of the monitoring module 4100. That is, when it is determined that the response mode to be executed is an emergency response mode, the alarm execution response submodule 4220 executes an emergency interrupt rather than a regular monitoring operation, and requests an emergency response operation from the guardian terminal unit 300 of the guardian side. The notification is executed and, in some cases, an emergency contact is made to a preset emergency institution, for example, 119 to the institution server 500 on the hospital side where the usual medical examination has been performed, thereby executing an emergency response follow-up operation.

The reporting response submodule 4230 transmits a report corresponding to the corresponding monitoring mode to the parental terminal unit 300 according to the analysis determination of the monitoring module 4100. In this embodiment, in the case of the normal response mode and the caution response mode, a function of transmitting the user's monitoring lifelog data or processed reporting data to the parental terminal unit 300 is performed. It can be adjusted according to the setting value, and setting through the setting value adjustment of the user or guardian may be possible.

On the other hand, the response mode executed in this embodiment includes a rule base response mode according to comparison of preset values, and in some cases, may further include an artificial intelligence response mode when processing including data of other users. Various modifications are possible, such as a configuration in which only the artificial intelligence response mode can be executed independently, or a configuration in parallel with the rule base response mode can be taken. In the case of further comprising such an artificial intelligence response mode, the monitoring management server 400 of the user living condition monitoring management apparatus 10 of the present invention may further include an AI learning module 4300. The monitoring module 4100 may have a structure in which monitoring data of other users can be input. That is, the monitoring management server 40 of the user living condition monitoring management device 10 of the present invention responds to more stable artificial intelligence so that the amount of data can be increased to execute the artificial intelligence response mode through the AI learning module 4300 The mode can be implemented, but the user's own past monitoring lifelog data is limited in its implementation.Therefore, the monitoring module 4100 of the monitoring management server 40 includes monitoring lifelog data of others through the monitoring module input unit. It takes a structure in which data can be input.

The AI learning module 4300 uses machine-learning or deep-learning learning to derive the correlation between the user's monitoring data and labels and features in the monitoring data of other users, using the user's monitoring data and inputted monitoring data of other users. Run. Here, the user's monitoring data and other user's monitoring data may include an Electronic Medical Record (EMR) in addition to monitoring lifelog data.

In addition, the monitoring data can be modified in various ways, such as being able to form another data feature by additionally receiving climate information about the location area of the living space where the user resides through communication with an external server.

Labels in the user's monitoring data and other user's monitoring data are formed for events included in the user's monitoring data and other user's monitoring data.For example, the user or other user's outpatient or hospitalization records, doctors This is a meaningful categorized event such as diagnosis information of the patient, medication information, call record information of emergency response organizations such as 119, and information about going out during the late night, and is specified through labeling of the user's monitoring data and other user's monitoring data. An event refers to an event, and a feature refers to each feature data of the user's monitoring data and the other user's monitoring data, that is, each feature detected through the monitoring sensor unit 200, and the core feature described later is the user's It refers to a feature having a high correlation calculated through machine learning and/or deep learning between a label and a feature derived through data processing to be described later among various features constituting monitoring data and monitoring data of other users.

The AI learning module 4300 includes an AI learning model storage unit 4323 and an AI learning data storage unit 4321. The AI learning model storage unit 4323 stores an AI learning model, where machine learning learning is performed using the user's monitoring data and other user's monitoring data by the AI learning model, and the user's monitoring data and other user's monitoring data. Correlation between labels and features in the data is derived.

The AI learning model stored in the AI learning model storage unit 4323 can use machine learning or deep learning algorithm models such as Regression, Logistic Regression, Auto Encoder, CNN (Convvolutional Neural Network), and RNN (Reccurrent Neural Network). It is not limited to a specific model, and various modifications are possible within the range of improving the efficiency of learning using each data or deriving correlations.

The AI learning data storage unit 4321 stores the user's monitoring data derived from the AI learning model storage unit 4423 and the correlation between labels and features in the monitoring data of other users. That is, by executing machine learning through the AI learning module 4300, a correlation between a label and a feature is derived.

When the AI learning module 4300 includes the AI learning model storage unit 4323 and the AI learning data storage unit 4321, the monitoring module 4100 may further include a similarity analysis monitoring submodule 4140. have.

In the similarity analysis monitoring submodule 4140, core feature data including user's spatial occupancy status information by time of the spatial analysis monitoring submodule 4110 and user behavior information of the behavior analysis monitoring submodule 4120, and the core of other users Based on the feature data, similarity between the user's user core feature data and other user core feature data is checked. The similarity analysis monitoring submodule 4140 may check and extract labeling information for other user core feature data having a high similarity between the user's user core feature data and the other user core feature data. That is, through machine learning of the AI learning module 4300, the user's core feature is compared among the user's monitoring data and the core features of other users are compared to extract high-correlated labeling information, and whether there is an event that the current user should pay attention to. By analyzing and judging whether or not, the process of avoiding dangerous situations through precautionary or precautionary processes is provided in advance by providing in advance which events are likely to occur not only from the current user's past history, but also from the monitoring data of other users in different spaces. It can also be achieved.

On the other hand, the user life condition monitoring management device 10 of the present invention extracts core features through machine learning and correlation analysis through the AI learning module 4300 and the similarity analysis monitoring submodule 4130, and the current user In executing the process of evading the current user's risk situation by extracting similar labeling information through similarity analysis of core features of other users, it is possible to require labels of monitoring data of users and monitoring data of other users. In some cases, the AI learning model as an AI engine stored in the AI learning model storage unit 4323 of the AI learning module 4300 for machine learning may include a model for processing structured data, In some cases, a model for processing unstructured data may be included, but in the present embodiment, a model for processing semi-structured data when structured data and unstructured data are mixed It is organized around In other words, the monitoring data of the current user's past history is appropriately classified and it is easy to take a labeled structured data structure, but there is a high possibility of unlabeled unstructured data for monitoring data or EMR data of other users. In order to improve the reliability of correlation analysis between features and labels of each monitoring data in a mixed state of standardized data and unstructured data, the AI learning module 4300 of the present invention is used for processing semi-standardized data. It is implemented by including the model.

In this case, the monitoring management server 400 of the present invention may further include an auto labeling module 4400, and the auto labeling module 4400 automatically executes labeling of monitoring data of a user and/or another user. That is, the auto labeling module 4400 extracts and labels data events from the user's monitoring data and other user's monitoring data by using the user's monitoring data and other user's monitoring data. Labels are created and assigned to monitoring data.

More specifically, the auto labeling module 4400 includes a data event extraction submodule 4410, a labeling assignment submodule 4420, and a labeling verification submodule 4430. The data event extraction submodule 4410 extracts a data event from the user's monitoring data and other user's monitoring data by using the user's monitoring data and the other user's monitoring data. That is, the data event extraction submodule 4410 is a meaningful label among the user's monitoring data and other user's monitoring data, for example, the user or other user's outpatient or hospitalization records, doctor's diagnosis information, medication information, 119 Information such as call record information of emergency response organizations such as, etc., information about going out in late-night time, and counseling record of a worker are extracted.

In addition, the labeling submodule 4420 of the auto labeling module 4400 assigns a label to the data event. That is, the labeling assignment submodule 4420 of the auto labeling module 4400 classifies or re-extracts aesthetically significant data events among the data events extracted by the data event extraction submodule 4410 and assigns a label thereto.

In this case, the monitoring management server 400 may further include a semantic module 4500 equipped with a semantic engine, and the semantic module 4500 may be used in a data event extraction process and/or a labeling process. That is, the process of extracting information such as records of outpatient or admission records of users or other users, diagnosis information of doctors, medication information, call record information of emergency response organizations such as 119, outing information at night time, and counseling records of a worker. Data mining is performed such as semantic text extraction and classification from monitoring data through a semantic module 4500 equipped with a semantic engine, extracting data events, and labeling meaningful data events among the extracted data events. It could be.

When the labeling process is performed in the labeling submodule 4420, the labeling verification submodule 4430 verifies whether a meaningful labeling process has been performed. That is, the labeling verification submodule 4430 can verify the consistency of the labeling given by the labeling granting submodule 4420, which compares with the previously stored label stored in the monitoring management server 400 and monitors the new label as a whole. Considering the frequency of the corresponding label in the data, it is possible to take a configuration in which whether or not a new label is assigned is judged and verified by comparing with a preset frequency that can be determined to have a significant frequency.

Through this machine learning process, for example, a core feature that has a correlation to an event called'fall' that occurred to another user is extracted, and if the user forms a life pattern similar to that of the corresponding core feature, an event called'fall' It detects the possibility of occurrence and executes alerts such as warnings or warnings to the terminal of the user or guardian, and takes preliminary countermeasures for matters that are highly likely to occur due to the judgment made in the correlation extracted through big data processing. You can also try to prevent it from occurring.

Hereinafter, a method of controlling a user living condition monitoring management apparatus according to the present invention will be described with reference to the drawings.

The method of controlling a user's living condition monitoring management apparatus according to the present invention includes a providing step (S10), a monitoring step (S20), a response mode determination step (S30), and a response mode execution step (S40).

In the providing step (S10), a monitoring sensor unit 200 including an activity sensor 200-1 that detects at least activity in the user's living space, and a monitoring life log detected as at least activity from the monitoring sensor unit 200 A monitoring terminal unit 100 that collects monitoring data including data, an activity index indicating at least the user's activity by receiving monitoring data from the monitoring terminal unit 100, sleep information indicating sleep information, and external activity information. There is provided a user living condition monitoring management apparatus 10 including a monitoring management server 400 that checks the indicated outing index, determines the stability of the user's daily condition, and transmits it to at least the guardian terminal unit 300. The user's living condition monitoring management device 10 includes a monitoring sensor unit 200, a monitoring terminal unit 100, and a monitoring management server 400, and a detailed description thereof is replaced with the preceding description, and a duplicate description is Omit it.

Then, the monitoring step (S20) is executed. In the monitoring step (S20), the stability of the user's daily state is monitored and checked, and the stability state is analyzed and determined. In other words,

The monitoring sensor unit 200 detects monitoring data including at least monitoring life log data detected as active and transmits it to the monitoring management server 400. The monitoring management server 400 of the monitoring module 4100 communicates with the server. Through the module 4001, monitoring data including at least monitoring life log data detected as active is received from the monitoring terminal unit 100. Using the received monitoring data, the monitoring module 4100 monitors the stability of the daily state and analyzes whether or not the stability is determined. That is, the monitoring module 4100 monitors the stability of the user's daily state by checking at least an activity index indicating the user's activity, a sleeping information indicating sleep information, and an outing index indicating external activity information, and monitoring the stability state. Analyze judgment at (4100).

More specifically, the monitoring step (S20), the monitoring step (S20) is a monitoring input step (S21), a spatial analysis monitoring step (S23), a behavior analysis monitoring step (S25), and an abnormal analysis monitoring step (S27). Includes.

First, in the monitoring input step (S21), monitoring data is received and input from the monitoring terminal unit 100 through the server communication module 4001 of the monitoring management server 400. Here, the monitoring data includes monitoring life log data, and the monitoring life log data indicates at least activity and is sensed by the monitoring sensor unit 200. That is, the monitoring data includes monitoring life log data, and in some cases, in addition to the directly detected data, the monitoring data may include the previously described Electronic Medical Record (EMR).

In the spatial analysis monitoring step (S23), spatial information on the space occupied by the user is calculated from the user's monitoring data, that is, monitoring life log data. That is, the spatial analysis monitoring sub-module 4110 is the spatial analysis monitoring sub-module 4110 from the monitoring life log data detected as activity at least among the monitoring data received and input in the spatial analysis monitoring step (S23). Check the information. In other words, by using data that detects the user's hourly location, the user occupies which space at what time period, for example, whether it is mainly located in the living room, kitchen, or bedroom space in the afternoon. It is possible to grasp the space occupancy level of the user for 24 hours or the space occupancy rate by time slot, that is, the spatial information including the space occupancy status information by time, from the location information for each time period, such as how the occupancy time or frequency of.

Then, the behavior analysis monitoring step (S25) is executed. In the behavior analysis monitoring step (S25), the behavior analysis monitoring submodule 4120 extracts and analyzes the user's behavior information from the spatial information acquired in step S23. That is, in the behavior analysis monitoring step (S25), the behavior analysis monitoring submodule 4120 uses spatial information including the user's spatial occupancy status information by time identified from the spatial analysis monitoring submodule 41110 to store user behavior information. Check and analyze. Since the movement of the user has no choice but to take a continuous motion structure, it is possible to extract the user's behavior information from the spatial information sensed for each time period through information on the moving direction of the user and the user space located. For example, when the occupied space of the user moves to the kitchen space through the bedroom space, the living room space, and stays in the kitchen space for a predetermined time, the user extracts behavior information, such as determining that the user will perform cooking actions such as eating or cooking. This is possible.

After the behavior analysis monitoring step (S25) is executed, the abnormal analysis monitoring step (S27) is executed. In the abnormality analysis monitoring step (S27), the abnormality analysis monitoring submodule 4130 uses spatial information, in particular, space occupied state information and behavior information by time, and performs monitoring and analysis to determine the user's normal state, attention state, or abnormal state. do. At this time, by using activity information, sleeping information, going out information, and toilet information when analyzing behavior information, it is determined whether the current user's state is a normal response mode, which is a normal state, an attention response mode, which is an attention state, or an emergency response mode that is an emergency state. In determining, a process of determining the current state of the current user may be executed through comparison with a preset reference value.

The abnormality analysis monitoring step (S27) may include a rule base abnormality analysis monitoring step (S271), as described above. In the rule base abnormality analysis monitoring step (S271), the abnormality analysis monitoring submodule 4130 receives monitoring data from the monitoring terminal unit 100 to provide at least an activity index indicating the user's activity, sleep information indicating sleep information, and external The safety of the user's daily state is checked and determined by comparing the outing index indicating activity information with a set reference value.

For example, if the occupancy of space in the living room of the user drops sharply, the occupancy of the space in the sleeping space increases, and the activity drops sharply, the sleep index increases, the activity index decreases, and the frequency of going out decreases. This will form a decline in the outing index. Here, such an index is calculated by the behavior analysis monitoring submodule 4120, and the abnormality analysis monitoring submodule 4130 determines whether there is an abnormality according to the rule base criteria in the rulebase abnormality analysis monitoring step (S271). Compared with a reference value such as the user's reference value, the cumulative average value for a certain period, such as the cumulative average value for 10 years, or the cumulative average value for the same quarter of the previous year of the user, or the cumulative average value for a certain period of the same age group or people with the same disease. The comparative analysis step is executed in a rule base method to analyze whether the current user is in an abnormal state.

Then, the response mode determination step (S30) is executed. In the response mode determination step (S30), the response mode is set according to the determination result of the analysis of the monitoring module 4100, that is, which step is determined in step S20. ), it is determined whether the user's current corresponding execution response mode is a normal response mode, an attention response mode, or an emergency response mode.

In more detail, the response mode determination step (S30) includes a rule base response mode determination step (S30-1). In the rule base response mode determination step (S30-1), the response module 4200 monitors rule base abnormality analysis According to the rule base abnormality analysis monitoring confirmation result checked in step S271, a response mode is determined.

The rule base correspondence mode determination step (S30-1) includes an analysis monitoring data input step (S31), a confirmation result determination step (S33), and a caution determination step (S35). In the analysis monitoring data input step (S31), the rule base abnormality analysis monitoring confirmation result checked in the rule base abnormality analysis monitoring step (S271) is input, and the rule base abnormality in the abnormality determination response submodule 4210 of the response module 4200. The analysis monitoring confirmation result is entered.

Thereafter, the check result determination step (S33) is executed in the abnormality determination response submodule 4210, and the rule base abnormality analysis monitoring check result in the abnormality determination response submodule 4210 of the response module 4200 is normal. Is judged. If the abnormality determination response submodule 4210 determines that the rule base abnormality analysis monitoring confirmation result is not normal, the abnormality response submodule 4210 sets the rule base mode to be executed as an emergency response mode (step S37). . On the other hand, in step S33, if the abnormality determination response submodule 4210 determines that the rule base abnormality analysis monitoring confirmation result is normal, the control flow is switched to step S35, and a caution determination step (S35) is executed.

In other words, in the caution determination step (S35), the response module 4200 determines whether the rule base abnormality analysis monitoring check result needs attention, and the rule base abnormality analysis monitoring confirmation result is noted in the caution determination step (S35). When it is determined that there is a need, the abnormal response submodule 4210 sets the rule base mode to be executed as a caution response mode (step S36), and the rule base abnormal analysis monitoring check result needs attention in the caution determination step (S35). When it is determined that there is no abnormality response submodule 4210, the rule base mode to be executed is set as a normal response mode (step S38).

After the corresponding mode determination step S30, the corresponding mode execution step S40 is executed, and the corresponding mode determined in the corresponding mode determination step S30 is executed. That is, the corresponding response mode determined according to the determination result of whether the user's current corresponding execution response mode is a normal response mode, an attention response mode, or an emergency response mode is executed.

For example, when it is determined that the response mode to be executed is a normal response mode, monitoring data including monitoring lifelog data of the user is continuously detected and acquired through the monitoring sensor unit 200 without a separate interrupt, and monitored. The terminal unit 100 transmits to the monitoring management server 400 side, and executes the user's day or preset periodic reporting to at least the guardian terminal unit 300 of the guardian side at a predetermined time point. That is, the parental terminal unit 300 provides the user's previous day's activity in the form of a text or a push-up message, space occupancy by living space, sleep index, outing index, activity index, toilet index, etc. It is also possible to improve the ease of awareness of the guardian about the user status through simultaneous provision.

In addition, if the execution response mode to be executed is the caution response mode, the routine of the previous normal response mode is processed, but at least the day of the user or a preset periodic reporting to the guardian terminal unit 300 of the guardian side at a predetermined time. In addition, the step of sending an additional warning message is executed. That is, the parental terminal unit 300 provides the user's previous day's activity in the form of a text or a push-up message, space occupancy by living space, sleep index, outing index, activity index, toilet index, etc. In addition to the simultaneous provision, it is also possible to increase the need for caregivers to pay attention to conditions that require user attention by sending out a notification function for the user's insufficient instruction. For example, when a user's outing index decreases rapidly due to a decrease in the number of outings, the user's outing frequency decreases by notifying the user's own outing status change and providing comparison information with the frequency compared to the same age group or the same period. A, information may be provided so that it is possible to reasonably judge whether it is caused by a physical change of the user himself or a climatic requirement due to a sudden drop in winter weather. On the other hand, in some cases, in the case of the caution response mode, various modifications are possible, such as being able to transmit a caution response message through an interrupt to the guardian terminal unit 300 of the guardian side, out of the routine of the normal response mode.

In addition, when the execution response mode to be executed is the emergency response mode, it is switched to the emergency mode through an interrupt outside the routine of the previous normal response mode, and transmits an emergency response notification message to the guardian terminal unit 300 of the guardian side. , It is possible to transmit an emergency response request notification message to the institutional server 500 of an institution such as a regular outpatient hospital or 119.

On the other hand, in the previous embodiment, the user living condition monitoring management device includes a rule base-based response mode determination and response mode execution step (S340, S40) having a structure including the monitoring module 4100 and the response module 4200 in a rule base method. Although the configuration to be implemented is taken, the present invention is not limited thereto and various modifications are possible.

As an example, as described above, the step of determining the response mode and executing the response mode performed in the present embodiment includes a rule base response mode according to comparison of preset values, and is processed including data of other users in some cases. In this case, an artificial intelligence response mode may be further included. Various modifications are possible, such as a configuration in which only the artificial intelligence response mode is independently executed, or a configuration in parallel with the rule base response mode may be taken.

First, if the artificial intelligence response mode step is further provided, the monitoring management server 400 of the user living condition monitoring management device 10 provided in the providing step (S10) of the user living condition monitoring management device control method of the present invention. ) May further include an AI learning module 4300, and the monitoring module 4100 may take a structure in which monitoring data of other users can be input. The monitoring management server 40 of the user living condition monitoring management device 10 of the present invention implements a more stable artificial intelligence response mode so that the amount of data can be increased to execute the artificial intelligence response mode through the AI learning module 4300 This is possible, but since the implementation of the user's own past monitoring lifelog data is limited, the monitoring module 4100 of the monitoring management server 40 provides monitoring data including the monitoring lifelog data of others through the monitoring module input unit. The fact that it takes a structure that can be input is the same as described exemplarily.

As a prerequisite for the execution of the artificial intelligence response mode, the monitoring step S20 may include an artificial intelligence anomaly analysis monitoring step S273. In this embodiment, after the rule base abnormality monitoring step (S271) is executed or at the same time, the artificial intelligence abnormality analysis monitoring step (S273) may be executed.In the artificial intelligence abnormality analysis monitoring step (S273), the user core feature data The similarity of the user core feature data can be checked, and labeling information for other user core feature data can be checked and extracted. Here, this step is based on the core feature data including the user's temporal space occupancy status information of the spatial analysis monitoring submodule 4110 and the user's behavior information of the behavior analysis monitoring submodule 4120 and the core feature data of other users. do. That is, the feature data is detected by each data information of the monitoring data, for example, the activity sensor unit 200-1, the environment sensor unit 200-4, etc., and transmitted to the monitoring terminal unit 100. The sensor value data refers to daily features, and the core feature data is the key feature selected as the correlation between the event and feature data, which will be described later, is determined to be high. Refers to data.

Based on the core feature data including the user's time-specific space occupancy status information of the user of the spatial analysis monitoring submodule 4110 and the user's behavior information of the behavior analysis monitoring submodule 4120 and the core feature data of other users, the monitoring module ( The similarity analysis monitoring submodule 4140 of 4100) checks the similarity between the user's user core feature data and other user's core feature data in the artificial intelligence anomaly analysis monitoring step (S273), Labeling information can be checked and extracted, and the monitoring terminal 100 and monitoring data are received using the labeling information having a high correlation, and at least an activity index indicating whether or not the user is active, sleeping information indicating sleeping information, and external activities The stability of the user's daily state with respect to the outing index indicating information may be determined. In other words, in the artificial intelligence anomaly analysis monitoring step (S273), by comparing the core feature data of the current user and other users and checking similarity, it is checked whether or not there is labeling information with high relevance, and responds to the extracted labeling information. By comparing the core feature data of other users and the current user monitoring data, it is monitored to see if other user labels with high relevance can occur to the current user.

In this case, in addition to the monitoring step, a specific configuration change is also accompanied in the response mode determination and response mode execution steps S30 and S40. That is, the step of determining the correspondence mode (S30) may include a step of determining the AI correspondence mode (S30-2) other than the step of determining the rule base correspondence mode described above. In the artificial intelligence response mode determination step (S30-2), the response mode is determined according to the artificial intelligence anomaly analysis monitoring confirmation result confirmed in the artificial intelligence anomaly analysis monitoring step (S273).

More specifically, the AI response mode determination step (S30-2) may include an analysis monitoring data input step (S301), a core feature similarity high determination step (S303), and a core feature similarity medium determination step (S305). have. In this case, in the analysis monitoring data input step (S301), the artificial intelligence abnormality analysis monitoring confirmation result confirmed in the artificial intelligence abnormality analysis monitoring step (S273) is input.

Then, the core feature similarity high determination step (S303) is executed.In the core feature similarity high determination step (S303), the artificial intelligence of the monitoring module 4100 analyzes the similarity of the monitoring module 4100 in the corresponding module 4200. As a result of the analysis monitoring check, it is determined whether the core feature similarity indicating the core feature similarity is higher than the preset core feature high similarity. That is, when the corresponding module 4200 determines that the core feature similarity is higher than the preset core feature high similarity, the control flow is switched to step S308 and the artificial intelligence mode (AI mode) to be executed is set as the high similarity pattern mode ( S308).

On the other hand, if the corresponding module 4200 determines that the core feature similarity is not higher than the preset core feature high similarity, the control flow is switched to step S305. In the core feature similarity medium determination step (S305), the corresponding module 4200 determines whether the core feature similarity indicating the core feature similarity is higher than the preset core feature medium similarity as a result of the artificial intelligence anomaly analysis monitoring check result, and the corresponding module When it is determined in 4200 that the core feature similarity is not higher than the preset core feature medium similarity, the control flow is switched to step S310 and the artificial intelligence mode (AI mode) to be executed is set to a row similarity pattern mode (S310).

On the other hand, in the core feature similarity medium determination step (S305), when the corresponding module 4200 determines that the core feature similarity indicating the core feature similarity is higher than the preset core feature medium similarity as a result of the artificial intelligence anomaly analysis monitoring check result, the control flow is The artificial intelligence mode (AI mode) to be switched to step S309 and executed is set to a medium similarity pattern mode (S309).

Depending on the confirmed and determined response mode, the response mode selected in step S40 is executed. As in the previous response determination step, the response mode execution step also executes each mode, that is, the rule base response mode execution step and the artificial intelligence response mode. Each step may be executed, or in some cases, a simultaneous notification operation may be executed as an integrated execution step, and an operation mode selection function is given to the user by giving the user a choice for each execution type. In other words, various modifications are possible according to design specifications, such as being able to selectively execute one of the rule base-based rule base response execution mode or artificial intelligence-based artificial intelligence response execution mode.

On the other hand, in the case of the execution type of the artificial intelligence response mode of the present invention described above, it may be executed in the direction of utilizing a large amount of big data of other users in order to solve the constraints accompanying only the application of the user's data. As described, whether it is the user's monitoring data or other user's monitoring data, each monitoring data is meaningful in order to enable a more rapid response by reducing the computational load of each data and to improve the reliability according to the classification of the data. A label for feature data is formed. In another embodiment of the present invention, a component for automating the labeling operation forming such a label may be further provided.

That is, an auto labeling module 4400 may be further included in the monitoring management server 400 provided in the providing step of the present invention, and the auto labeling step S50 may be executed in the auto labeling module 4400. In the auto-labeling step (S50), it is executed at least after the provision step (S10), and data events are extracted and labeled from the user's monitoring data and other user's monitoring data using the user's monitoring data and other user's monitoring data. The label is created. That is, the auto labeling step (S50) of the present embodiment may be executed at any step after the providing step (S10), preferably, the monitoring data input after the monitoring input step (S21) is executed in the monitoring step (S20) exists. In case it is desirable to run in parallel.

More specifically, the auto labeling step (S50) includes an auto labeling monitoring input step (S51), a data event extraction step (S53), a preliminary labeling step (S55), a labeling verification step (S57), and labeling confirmation. It includes step S59.

In the auto labeling monitoring input step (S51), monitoring data is received and input to the auto label module 4400, and such input monitoring data may be performed in the monitoring step (S20) as described above, or directly through a separate input unit. Various modifications are possible, such as being able to take a configuration input to the monitoring management server 400 side. The input monitoring data, as described above, may be the past and present monitoring lifelog data of the user, monitoring lifelog data of other users, and electronic obligations of the user and/or other users. Various data may be selected that provide meaningful information about a user's daily life, such as a record (EMR).

After the monitoring data is input in the auto labeling monitoring input step S51, the data event extraction step S53 is executed. In the data event extraction step (S53), the data event extraction submodule 4410 uses the monitoring data input in the auto labeling monitoring input step (S51), that is, the user's monitoring data and other user's monitoring data, Extracts data events from monitoring data of other users. As described above, in the data event extraction step (S53), the data event extraction submodule 4410 is a meaningful label among the user's monitoring data and other user's monitoring data, for example, a user or another user's outpatient hospital Significant information or information events such as hospitalization records, doctor's diagnosis information, medication information, call record information of emergency response organizations such as 119, outing information during late-night time, and counseling records of a worker are extracted. These are users or other users. It is classified and extracted as a meaningful event as information or information event that affects or reflects the daily life of the person, so that the correlation between the event and the feature data can be learned and reviewed in the AI learning module.

In the preliminary labeling step (S55), the labeling submodule 4420 assigns a label to the data event extracted in the data event extraction step (S53). In this case, in some cases, the monitoring management server 400 may further include a semantic module 4500 equipped with a semantic engine, and the semantic module 4500 may be used in a data event extraction process and/or a labeling process. , In the process of extracting information such as user or other user's outpatient or hospitalization records, doctor's diagnosis information, medication information, call record information of emergency response organizations such as 119, outing information at night time, and counseling records of a worker. , Data mining is performed such as semantic text extraction and classification from monitoring data through the semantic module 4500 having a semantic engine to extract data events, and labeling of significant data events among the extracted data events is executed. May be.

After the preliminary labeling step (S55) is executed, the labeling verification step (S57) is executed. In the preliminary labeling step (S55), the labeling verification sub is used to verify the consistency of the labeling assigned through the labeling submodule 4420. Module 4430 verifies.

The method of executing the labeling verification step (S57) can be variously selected according to the design specification.In the labeling verification step (S57) in the present embodiment, the labeling verification submodule 4430 performs verification based on the name of the label. Take For example, in the present embodiment, in the labeling verification step (S57), the labeling verification submodule 4430 compares the previously stored label stored in the monitoring management server 400 in verifying whether a meaningful labeling process has been executed. Method. That is, the previously stored label name is used first, and if the name of the preliminarily assigned label does not exist among the names of the previously stored label, a new label name is assigned, and for the new label name, a label name is newly established to accumulate the frequency. Is done. The frequency of the label in the overall monitoring data is checked, and the frequency of the label with a new name is compared with the preset frequency, and the preset frequency is determined that the label corresponding to the label name has a significant frequency. Possible reference values and can be adjusted according to the design method. In this way, data events are extracted and a label is temporarily assigned, and whether the label is a label name existing in the existing data or a label to which a new name is assigned, and if it is determined as a label with a significant frequency, the newly named name is newly assigned. It is also possible to take a configuration that is judged and verified by giving it as a label. In some cases, a preliminary label that has not reached the frequency can be modified in various ways, such as a step of providing a separate check label so that an administrator can subsequently check it.

Thereafter, a labeling determination step (S59) of determining the labeling assigned in the preliminary labeling step (S55) is performed according to the verification result of the labeling verification step (S59).

In the present embodiment, the verification was performed based on the name of the label, but this is an example, and various selections are possible within a range in which data events are more accurately extracted and labeled.

On the other hand, in the above embodiment, a configuration using monitoring data of other users other than the user's monitoring data has been described. However, the apparatus for monitoring and managing the user's living condition and the control method thereof according to the present invention are used to protect personal information such as the Personal Information Protection Act It may further include a component for the de-identification function for. Descriptions overlapped with the above-described contents are replaced with the previous technology, and hereinafter, a description will be made focusing on a configuration that performs a de-identification function.

That is, the user life condition monitoring management apparatus 10 of the present invention having a de-identification function includes a monitoring sensor unit 200, a monitoring terminal unit 100, and a monitoring management server 400, and monitors are managed. The server 400 includes an AI learning module 4300 and further includes a DID module 4600.

The monitoring sensor unit 200, the monitoring terminal unit 100, and the monitoring management server 400 are the same as those described above. The AI learning module 4300 is a component that is further provided in the monitoring management server 400, and it is possible to input monitoring data of other users, and use the monitoring data of the user and the monitoring data of other users. It is possible to execute machine learning learning to derive a correlation between a label and a feature in the user's monitoring data, and its concrete implementation is as described above.

At this time, the monitoring management server 400 of the present invention further includes a DID module 4600, which de-identifies the monitoring data of other users according to the minimum setting for de-identifying monitoring data of other users. Execute de-identification and re-identify the de-identified monitoring data of other users to check whether other users can be identified.

More specifically, the DI module 4600 includes a DI identification sub-module 4610, a re-ID checking module 4620, and a DI-ID similarity checking module 4630.

The identification sub-module 4610 receives and inputs other user monitoring data of another user. The de-identification submodule 4610 performs de-identification to de-identify the monitoring data of the other user according to the minimum setting for de-identification of the monitoring data of other users. Here, the identification is based on personal information that can identify other users among the monitoring data of other users, for example, personal information such as name, address, social security number, vehicle number, phone number, and mobile phone number. It refers to performing a screening operation in an encrypted form or removing the corresponding personal information to prevent the execution of a process that enables specific, estimation or identification.This de-identification is an important process to prevent leakage of personal information. to be.

The identification sub-module 4610 according to an embodiment of the present invention includes the identification sub-minimum reclamation confirmation unit 4611, the identification sub-feature check unit 4713, and the identification It includes an application sub-crypto unit 4615 and a de-identification subscription unit 4616.

The identification sub-minimum reclamation confirmation unit 4611 of the identification sub-module 4610 confirms the minimum requirements required to prevent re-identification of monitoring data of other users. Here, the minimum requirements refer to essential items that must be technically or legally removed for personal information protection, and the minimum requirements use data stored in the minimum setting storage module 4640 provided in the DID module 4600. In some cases, the minimum setting storage module 4640 updates the minimum requirement change according to the change in laws, and immediately when the minimum conditions change occurs, the identification sub-minimum reclamation confirmation unit of the identification submodule 4610 ( 4611) checks this and updates the de-identification function of the identification submodule 4610 to enable the application of the latest regulations.

The identification sub-feature check unit 4713 hides the personal information-related data features of the monitoring data of other users based on the minimum requirements confirmed by the identification sub-minimum reclamation check unit 4611. Confirm the data features associated with the non-displayed personal information. In other words, among the monitoring data of other users, personal information that can identify other users, for example, name, address, social security number, vehicle number, phone number, mobile phone number, etc. Among the data features related to personal information such as name, address, social security number, phone number, mobile phone number, vehicle number, skin color, race, age, disease item, name, address, social security number, and phone number Check the data features related to non-displayed personal information, items that are de-identified according to minimum requirements such as mobile phone number, vehicle number, etc.

The identification subscription screening unit 4517 hides the personal information-related data feature to be undisplayed among the personal information-related data features identified by the identification sub-feature check unit 4713. In this case, the non-display process may be performed on the entire data feature related to personal information to be non-displayed, or may be performed on only some information. That is, the entire resident registration number may be encrypted, or in some cases, only a specific part such as the last digit of the resident registration number or the first second digit of the resident registration number may be screened.

Meanwhile, in some cases, a component that executes an encryption process for the non-displayed portion may be further provided in the identification submodule 4610. That is, the identification sub-screening unit 4517 hides the personal information-related data feature to be displayed among the personal information-related data features identified in the identification sub-feature check unit 4713, but the portion that is not displayed. A de-identification sub-crypto unit 4615 that encrypts the data may be further provided.

That is, the identification sub-crypto unit 4615 encrypts the personal information-related data feature to be undisplayed among the personal information-related data features identified by the identification sub-feature check unit 4713. In this case, as in the case of the previously screened part, the encryption process may be performed on the entire data feature related to personal information to be undisplayed, or may be performed on only some information. That is, the entire resident registration number may be encrypted, and in some cases, various modifications are possible, such as that only a specific part such as the last digit of the resident registration number or the first second digit of the resident registration number may be executed.

The re-ID confirmation module 4620 re-identifies the monitoring data of other de-identified users and determines whether the user can be re-identified from the monitoring data. In the process of re-identification determination of the re-ID confirmation module 4620 The ID similarity checking module 4630 is required. That is, the DID similarity checking module 4630 is used to determine the non-identified data features other than the non-identified data features of the de-identified other user's monitoring data, and more specifically, the de-identified monitoring data of other users. In the process of checking the possibility of extraction of other users before being identified, the probability of matching other users before being de-identified is calculated from the de-identified other user monitoring data, and the re-ID confirmation module 4620 is a preset reference value It is determined whether re-identification is possible by comparing (SIDS) and the probability of matching other users (SID) before being de-identified from the de-identified other user monitoring data.

In other words. Among the data features related to personal information such as name, address, social security number, phone number, mobile phone number, vehicle number, skin color, race, age, disease item, etc. for the monitoring data of other users for a total of 20,000 people including A, name, Only the address, social security number, phone number, mobile phone number, and vehicle number meet the minimum requirements, and after screening and encryption for de-identification are performed, trace back from the data and the data features of the remaining unidentified monitoring data. It is performed by calculating the perceptible probability for A and comparing whether its probability value is less than a preset reference value. For example, the number of other users with the same disease and age is calculated through screening and encryption through data features for disease and age among de-identified data features, and the reciprocal of these numbers is calculated as identification probability, and this If it is lower than the set reference value, for example, 5%, the probability that A is identified from the unidentified data feature is determined to be extremely small, and thus an additional identification step for an additional data feature is not provided.

On the other hand, in the above example, if it is determined that the identification probability that A can be identified is greater than or equal to the preset value, it is determined that the identification probability of A is high and the additional de-identification process is repeated for other data features according to the preset order. do.

This de-identification process may be performed for all users or may be applied to local users. However, since there is a difference in the number of users when it is executed for all users and when it is executed for local users, the preset value compared with the identification probability value may vary depending on the type.

That is, the identification probability value of the DID similarity confirmation module 4630 is transmitted to the REID confirmation module 4620 to determine whether re-identification is possible or impossible by comparing the identification probability for the currently de-identified item with a predetermined preset value. According to the determination and the determination result, the re-ID verification module 4620 maintains the current screening encryption state without the need for additional personal information related data features screening or encryption or additional measures.

Hereinafter, a diadentification process will be described with reference to the drawings. The details of the apparatus for monitoring and managing the user's living condition according to the present invention are replaced with the above, and a duplicate description will be omitted.

First, a Diady step (S60) performed at least after the providing step (S10) of the present invention may be further included. In the DID step (S60), the DID module 4600 of the monitoring management server 400 executes the DIDENTIFICATION which de-identifies the monitoring data of other users according to the minimum setting of de-identification of the other users. In addition, by re-identifying the de-identified monitoring data of other users, it is checked whether other users can be identified.

More specifically, the DI step (S60) includes a DI monitoring input step (S61), a die identification step (S63), a minimum setting requirement verification step (S65), and a verification response step (S67).

In the DID monitoring input step (S61), monitoring data is received and input to the DID module 4600, and in the Didentification step (S63), the monitoring data of other users is de-identified according to the minimum setting, In (4610), de-identification is performed to de-identify the monitoring data of other users. Thereafter, the minimum setting requirement verification step (S65) is executed, and the monitoring data of other users de-identified in the minimum setting requirement verification step (S65) is re-identified and compared with the minimum setting requirement to determine whether or not re-identification is possible. It is verified and verified, and the verification correspondence set according to the result of the requirement verification in the minimum setting requirement verification step S65 in the verification response step S67 is executed.

More specifically, the identification step (S63) includes the identification sub-minimum recitation confirmation step (S631), the identification sub-feature check step (S633), and the identification sub-screening step ( S635).

In the identification sub-minimum recitation confirmation step (S631), the identification sub-minimum recitation confirmation unit 4611 of the identification sub-module 4610 re-identifies the monitoring data of the other user. The minimum requirements that are required to be non-commutable are identified

Thereafter, the identification sub-feature check step (S633) is executed, and the identification sub-feature check unit 4713 of the identification sub-module 4610 checks the identification sub-minimum recitation. Based on the minimum requirements identified in the part 4611, a non-displayed personal information-related data feature that has been hidden from the personal information-related data feature of the monitoring data of another user is checked.

Then, the identification subscription step (S635) is executed. In the identification subscription step (S635), the identification subscription unit 4517 of the identification submodule 4610 is performed. Among the personal information-related data features identified by the identification sub-feature check unit 4713, the personal information-related data feature to be undisplayed is not displayed.

Meanwhile, in the de-identification step S63, in addition to screening, an encryption process may be additionally performed to prevent leakage of personal information due to data leakage from the monitoring management server. That is, the de-identification step (S63) may further include a de-identification sub-crypto step (S367), and the de-identification sub-crypto step (S367) is a de-identification sub-crypto step (S367). The identification sub-crypto unit 4615 encrypts a non-display target personal information-related data feature among the personal information-related data features identified by the de-identification sub-feature check unit 4713.

The minimum setting requirement verification step (S65) includes a re-ID verification step (S651), a DID similarity verification step (S653), and a DID completion verification step (S655). In some cases, a minimum setting requirement update step (S650) for checking and updating the latest minimum setting requirements may be further included before the re-ID confirmation step (S651). Data stored in the setting storage module 4610 can be used.

The re-ID confirmation step (S651) may be executed in the re-ID confirmation module 4620. In the re-ID confirmation module 4620, the data features of a specific age and disease are randomly selected from among the data features of disease and age. Re-identification is executed by specifying other users. For example, for monitoring data of other users other than target user A, for example, a total of 20,000 people, name, address, social security number, phone number, mobile phone number, vehicle number, skin color, race, age, disease, etc. Among the data features related to personal information, only the name, address, social security number, phone number, mobile phone number, and vehicle number are set to meet the minimum setting requirements, and after screening and encryption for de-identification are performed, the remaining ratio As a data feature of unidentified monitoring data, age and disease are random or the same value as the age range or disease that has a certain fluctuation value before and after the age applied to the target user A to be compared. Re-identification is performed to check other users. That is, after screening and encryption through data features for disease and age among the de-identified data features, a predetermined number of other users having the same disease and age are specified and re-identification is performed. That is, in the re-ID confirmation step (S651), as described above for the re-identification process, the monitoring data of other users through the data feature that is not de-identified in the re-ID confirmation module 4620 of the DI module 4600 is The re-identification process is carried out.

Then, from the monitoring data of other users re-identified in the DID similarity checking step (S653), a DID similarity (SID) indicating whether the other user is identifiable or not is calculated, and the DID similarity checking module 4630 Is calculated from That is, in the DID similarity checking step (S653), the DID similarity (SID) is calculated.For example, the DID similarity (SID) is the identification probability of the number of other users specified compared to the total number of users in the reID verification step (S651). It can also be calculated. For example, the number of other users with the same disease and age is calculated through screening and encryption through data features for disease and age among unidentified data features, and the reciprocal of these numbers is identified as DID similarity (SID). It is calculated by probability.

Then, the DID completion confirmation step (S655) is executed in the reID confirmation module 4620, and in some cases, it may be performed in another lower module of the DID module.

The DID completion confirmation step (S655) includes a DID similarity comparison determination step (S6551) and a DID completion confirmation step (S6553).

First, in the DID similarity comparison determination step (S6551), the REID verification module 4620 compares the calculated DID similarity (SID) with a preset reference DID similarity (SIDS). According to the comparison result of the DID similarity (SID) and the preset standard DID similarity (SIDS) in step S6551, the control flow is transferred to the DID completion check step (S6553) to check whether the DID identification process is complete. The step of checking whether the ID (S6553) includes a step of confirming the completion of the ID (S65531) and the step of confirming the completion of the ID (S65533).If the comparison result, the similarity of the ID (SID) is less than the similarity of the preset reference, the control flow is The conversion to the DID completion confirmation step (S65531) determines that the DID identification process is properly performed and no further de-identification measures are necessary.For example, the DID similarity as an identification probability is the preset standard DID similarity (SIDS). If it is lower than the exemplary value of 5%, the probability of identifying A from the unidentified data feature is extremely insignificant, and the DID completion confirmation step (S65531) is set to not have an additional identification step for an additional data feature (S65531 ) Is confirmed.

On the other hand, as a result of comparing the DID similarity (SID) and the preset reference DID similarity (SIDS) in step S6551, if the DID similarity (SID) is not less than the preset reference DID similarity (SIDS), that is, if the value is greater, the control flow is The transition to the non-complete confirmation step (S65533) determines that an additional de-identification process should be performed and no additional de-identification action is necessary.

Thereafter, the control flow is switched to step S67, and the corresponding execution is performed according to the confirmation result selected among the DID completion confirmation step (S65531) and the DID non-complete confirmation step (S65533) of the DID completion confirmation step (S6553). If the step (S65531) is checked and selected, the control flow to terminate the de-identification process is performed, and if the ID non-complete confirmation step (S65533) is checked and selected, the control flow is step S63 or preset to further execute the de-identification process. In a manner or in a manner that lowers the similarity of the DID, non-core features may be sequentially excluded.

The above-described contents are examples for explaining the present invention, and the present invention is not limited thereto. For example, in the process of executing machine learning using the monitoring data of oneself and/or other users, the correlation between the data core feature and the label may be formed in the form of a function, or the numerical value of the data core feature An example of taking a method of warning of the possibility of occurrence of a specific label by inputting is described, but the present invention is not limited thereto, and the occupancy level in a living space occupied by a user or another user is visually graphed, and the visual graph image thereof is By forming machine learning again, it is possible to learn or take cautionary warnings in a way that extracts changes in items for a specific event, a core feature that affects when an event named by a label, if extracted, occurs. Transformation is possible.

That is, the above description is merely illustrative of the technical idea of the present invention, and those of ordinary skill in the technical field to which the present invention pertains will be able to make various modifications and variations without departing from the essential characteristics of the present invention. . Accordingly, the embodiments disclosed in the present invention are not intended to limit the technical idea of the present invention, but to explain the technical idea, and the scope of the technical idea of the present invention is not limited by these embodiments. The scope of protection of the present invention should be interpreted by the following claims, and all technical ideas within the scope equivalent thereto should be interpreted as being included in the scope of the present invention.

Claims (22)

A monitoring sensor unit 200 including an activity sensor 200-1 for detecting at least activity in the user's living space,
A monitoring terminal unit 100 that collects monitoring data including monitoring life log data detected as at least active from the monitoring sensor unit 200,
By receiving the monitoring data from the monitoring terminal unit 100, at least an activity index indicating whether or not the user is active, sleeping information indicating sleeping information, and an outing index indicating external activity information are checked to determine the stability of the user's daily state. A user living condition monitoring management device 10 including a monitoring management server 400 that transmits at least to the guardian terminal unit 300 side.
The method of claim 1,
The activity sensor (200-1) is a user living condition monitoring management device (10), characterized in that each disposed in a plurality of areas of the user's living space to detect the user's space occupied by time.
The method of claim 2,
The monitoring sensor unit 200 is:
An environment sensor unit 200-4 that detects at least water, gas, and electricity usage and illumination conditions reflecting the daily life conditions in the user's living space,
User living condition monitoring management apparatus 10, characterized in that it further comprises a surveillance sensor unit (200-3) for detecting whether or not to go out from the user's living space.
The method of claim 1,
The monitoring terminal unit 100 is:
A monitoring terminal communication unit 110 for receiving the monitoring data from the monitoring sensor unit 200,
A monitoring terminal storage unit 130 for storing monitoring data received from the monitoring sensor unit 200,
And a monitoring terminal control unit (120) for controlling transmission of the received monitoring data to the monitoring management server (400) to the monitoring management server (40).
The method of claim 1,
The monitoring management server 40 is:
A server communication module 4001 for receiving the monitoring data transmitted from the monitoring terminal 100,
Using the monitoring data, the activity index indicating at least the user's activity, sleeping information indicating sleeping information, and going out index indicating external activity information are checked to monitor the stability of the user's daily state and analyze and determine the stability state. A monitoring module 4100,
A user living condition monitoring management device (10), characterized in that it comprises a corresponding module (4200) that transmits at least to the parental terminal unit (300) according to the analysis determination result of the monitoring module (4100).
The method of claim 5,
The monitoring module 4100 is:
A space analysis monitoring sub-module 4110 for checking information on a user's space occupancy status by time from the monitoring life log data detected as at least activeness among the monitoring data;
A behavior analysis monitoring sub-module 4120 for confirming and analyzing user behavior information using the user's time-based space occupancy state information checked from the spatial analysis monitoring sub-module 41110;
An anomaly analysis monitoring submodule ( User living condition monitoring management device 10, characterized in that it comprises a 4130).
The method of claim 6,
The corresponding module 4200 is:
An abnormality determination response submodule 4210 that executes a corresponding monitoring mode according to the analysis determination of the monitoring module 4100,
An alarm execution response submodule 4220 that executes an emergency response mode when it is determined that it is an emergency situation in the analysis determination of the monitoring module 4100;
And a reporting-response sub-module 4230 that transmits a report corresponding to a corresponding monitoring mode to the parental terminal unit 300 according to the analysis determination of the monitoring module 4100. 10).
The method of claim 6,
In the monitoring module 4100, monitoring data of other users can be input,
Further comprising an AI learning module 4300 for executing machine learning learning to derive a correlation between the user's monitoring data and other user's monitoring data labels and features using the user's monitoring data and other user's monitoring data. User living condition monitoring management device 10, characterized in that.
The method of claim 8,
The AI learning module 4300 is:
An AI learning model that stores an AI learning model for deriving the correlation between the user's monitoring data and the labels and features in the monitoring data of other users through machine learning learning using the user's monitoring data and other user's monitoring data. A storage unit 4323,
User life, characterized in that it comprises an AI learning data storage unit (4321) for storing the correlation between the user's monitoring data derived from the AI learning model storage unit (4423) and the label and feature in the monitoring data of other users Condition monitoring management device 10.
The method of claim 9,
Based on the user's spatial occupation state information of the spatial analysis monitoring submodule 4110 by time and the core feature data including the user's behavior information of the behavior analysis monitoring submodule 4120 and core feature data of other users, the User life state, characterized in that it further comprises a similarity analysis monitoring submodule 4140 that checks the similarity between the user's user core feature data and other user core feature data, and checks and extracts labeling information for other user core feature data. Monitoring management device 10.
The method of claim 8,
Further comprising an auto labeling module 4400 for generating a label by extracting and labeling a data event from the user's monitoring data and other user's monitoring data using the user's monitoring data and other user's monitoring data. User living condition monitoring management device (10).
The method of claim 11,
The auto labeling module 4400 is:
A data event extraction submodule 4410 for extracting a data event from among the user's monitoring data and other user's monitoring data using the user's monitoring data and other user's monitoring data,
A labeling submodule 4420 extracting the data event and assigning a label,
And a labeling verification sub-module (4430) for verifying the integrity of the labeling assigned by the labeling sub-module (4420).
Monitoring including a monitoring sensor unit 200 including an activity sensor 200-1 that detects at least activity in the user's living space, and monitoring life log data detected as at least activity from the monitoring sensor unit 200 A monitoring terminal unit 100 for collecting data, an activity index indicating at least the user's activity by receiving the monitoring data from the monitoring terminal unit 100, sleeping information indicating sleeping information, and an outing index indicating external activity information. A providing step (S10) of providing a user living condition monitoring management apparatus 10 including a monitoring management server 400 that checks and determines the stability of the user's daily condition and transmits at least to the guardian terminal unit 300,
Using monitoring data including at least monitoring life log data detected as active from the monitoring sensor unit 200 received from the monitoring terminal unit 100 through the server communication module 4001 of the monitoring management server 400 Thus, by checking the activity index indicating at least the user's activity, sleeping information indicating sleeping information, and going out index indicating external activity information, monitoring the stability of the user's daily condition and analyzing the stability state in the monitoring module 4100 The monitoring step (S20) to determine and,
A response mode determination step (S30) of determining a response mode in the response module 4200 according to the analysis determination result of the monitoring module 4100;
And a corresponding mode execution step (S40) of executing the corresponding mode determined in the corresponding mode determination step (S30).
The method of claim 13,
The monitoring step (S20) is:
Monitoring data including at least monitoring life log data detected as activity is received from the monitoring sensor unit 200 received from the monitoring terminal unit 100 through the server communication module 4001 of the monitoring management server 400 The input monitoring input step (S21) and,
A spatial analysis monitoring step (S23) in which the spatial analysis monitoring submodule 4110 checks the user's space occupancy status information by time from the monitoring life log data detected as at least activeness among the monitoring data;
A behavior analysis monitoring step (S25) of confirming and analyzing the user's behavior information in the behavior analysis monitoring sub-module 4120 using the user's spatial occupancy status information by time checked from the spatial analysis monitoring sub-module 41110, and
The abnormality analysis monitoring submodule 4130 determines whether the user is in an abnormal state by using the user's time-specific space occupancy status information of the spatial analysis monitoring submodule 4110 and the user's behavior information of the behavior analysis monitoring submodule 4120. An abnormality analysis monitoring step (S27) of monitoring and analyzing a user living condition monitoring management device control method comprising a.
The method of claim 14,
The abnormal analysis monitoring step (S27) is:
The stability of the daily state of the user by comparing the monitoring terminal 100 and the monitoring data with an activity index indicating at least the user's activity, sleeping information indicating sleeping information, and going out index indicating external activity information and a set reference value A method for controlling a user living condition monitoring management apparatus comprising a rule base abnormality analysis monitoring step (S271) of confirming and determining.
The method of claim 15,
In the user's living condition monitoring management device, monitoring data of other users can be input to the monitoring module 4100, and monitoring data of the user and monitoring data of other users are used using the monitoring data of the user and the monitoring data of other users. An AI learning module 4300 that executes machine learning learning to derive a correlation between my label and feature is further included,
Based on the user's spatial occupation state information of the spatial analysis monitoring submodule 4110 by time and the core feature data including the user's behavior information of the behavior analysis monitoring submodule 4120 and core feature data of other users, the Check the similarity between the user's user core feature data and other user's core feature data, check and extract labeling information about the other user's core feature data, and receive the monitoring data with the monitoring terminal 100 to at least whether the user is active User life, characterized in that it further comprises an artificial intelligence abnormality analysis monitoring step (S273) of confirming and determining the stability of the user's daily state for the activity index indicating the activity index, the sleeping information indicating the sleeping information, and the going out index indicating the external activity information Health monitoring management device control method.
The method of claim 16,
The corresponding mode determination step (S30) is:
And a rule base response mode determination step (S30-1) of determining a response mode according to the rule base abnormality analysis monitoring confirmation result checked in the rule base abnormality analysis monitoring step (S271). Management device control method.
The method of claim 17,
An analysis monitoring data input step (S31) in which the rule base abnormality analysis monitoring confirmation result checked in the rule base abnormality analysis monitoring step (S271) is input,
A confirmation result determination step (S33) of determining whether a rule base abnormality analysis monitoring confirmation result is normal in the corresponding module 4200;
And a caution determination step (S35) of determining whether a rule base abnormality analysis monitoring check result in the response module 4200 requires attention (S35).
The method of claim 18,
The corresponding mode determination step (S30) is:
And an artificial intelligence response mode determination step (S30-2) of determining a response mode according to a result of the artificial intelligence anomaly analysis monitoring confirmation checked in the artificial intelligence abnormality analysis monitoring step (S273). Management device control method.
The method of claim 19,
An analysis monitoring data input step (S301) in which the artificial intelligence abnormality analysis monitoring confirmation result checked in the artificial intelligence abnormality analysis monitoring step (S273) is input,
A core feature similarity high determination step (S303) of determining whether a core feature similarity indicating a core feature similarity is higher than a preset core feature high similarity as a result of the artificial intelligence anomaly analysis monitoring check result in the corresponding module 4200;
And a core feature similarity medium determination step (S305) of determining whether a core feature similarity indicating a core feature similarity is higher than a preset core feature medium similarity as a result of the artificial intelligence anomaly analysis monitoring check result in the corresponding module 4200. User living condition monitoring management device control method.
The method of claim 16,
The monitoring management server 400 further includes an auto labeling module 4400,
It is executed at least after the providing step (S10), and a label is generated by extracting and labeling a data event from among the user's monitoring data and other user's monitoring data using the user's monitoring data and other user's monitoring data. Auto labeling step (S50), characterized in that the user living condition monitoring management device measuring method is further provided.
The method of claim 21,
The auto labeling step (S50) is:
An auto labeling monitoring input step (S51) in which the monitoring data is received and input to the auto label module 4400,
A data event extraction step (S53) in which a data event from among the user's monitoring data and other user's monitoring data is extracted from the data event extraction submodule 4410 using the user's monitoring data and other user's monitoring data;
A preliminary labeling step (S55) in which the labeling submodule 4420 assigns a label to the data event extracted in the data event extraction step (S53),
A labeling verification step (S57) of verifying, in the labeling verification submodule 4430, the consistency of the labeling given through the labeling granting submodule 4420 in the preliminary labeling step (S55),
And a labeling determination step (S59) of determining the labeling given in the preliminary labeling step (S55) according to the verification result of the labeling verification step (S59).

Images