system

Abstract

We provide the system. [Solution] A means of collecting activity information entered by the user, Means for transmitting the activity information to a server, The server has means for receiving the activity information and storing it in a database, The server analyzes stored activity information and has means for detecting singular behavior or anomalies. The server generates an alert based on the detected anomaly and sends it to the client application, A means for notifying the user of alerts received by the terminal, A system that includes this.

Description

Technical Field

[0005] ,

[0001] The technology of the present disclosure relates to a system.

Background Art

[0002] Patent Document 1 discloses a method for controlling a persona chatbot, which is performed by at least one processor, including steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a chatbot character, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance in response to the user utterance.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In modern society, the management of activity information related to childcare and caregiving is very important. However, conventional methods lack means to quickly detect singular behaviors and abnormalities and provide appropriate alerts to users. Also, in caregiving, there is a problem that it is difficult to perform an appropriate evaluation of the health condition and make appropriate proposals for health maintenance in real time. Against this background, there is an increasing need for a system that can detect abnormal behaviors, generate alerts, and make proposals for health maintenance based on activity information in a unified manner.

Means for Solving the Problems

[0005] To solve the above problems, the present invention provides the following means: a system including means for collecting activity information entered by a user, means for transmitting the activity information to a server, means for the server to receive the activity information and store it in a database, means for the server to analyze the stored activity information and detect singular behaviors or anomalies, means for the server to generate an alert based on the detected anomaly and send it to a client application, and means for the terminal to notify the user of the alert received. Furthermore, the server includes means for evaluating the user's health status based on the stored activity information in care mode, generating suggestions for maintaining health, and sending them to the client application. In addition, the server includes means for sending alerts generated based on the detection of anomalies in the stored data to the client application in real time. This enables real-time detection of singular behaviors and anomalies, rapid alert notification, and appropriate health maintenance suggestions.

[0006] "Activity information" refers to specific actions that users perform on a daily basis, and the data related to them. Specifically, this includes data such as childcare information, caregiving activities, health status, travel routes, and travel time.

[0007] "Means of collection" refers to functions and methods for collecting and recording activity information entered by users. These means include sensors, user interfaces, and data input devices.

[0008] A "server" is a central processing unit that receives, stores, and analyzes transmitted activity information. It works in conjunction with a database to manage and analyze data.

[0009] A "database" is an information management system that connects to a server and organizes and stores received activity information.

[0010] "Means of analysis" refer to methods and techniques for identifying singular behaviors and anomalies by performing statistical analysis and pattern recognition based on stored activity information.

[0011] "Singular behavior" refers to actions that clearly deviate from normal behavioral patterns and may indicate an abnormal or emergency situation.

[0012] An "alert" is a warning message used to notify users of detected anomalies or unusual behavior. These alerts are typically expressed through audio, visual displays, or messages.

[0013] A "client application" is software that allows users to input activity information and receive alerts and suggestions from a server. This program runs on the user's device.

[0014] "Care mode" refers to a system operating with settings specifically for caregiving, prioritizing the handling of activity information, particularly data related to health management and caregiving.

[0015] "Health maintenance suggestions" refer to specific action guidelines and advice generated by the server to maintain the health of the user or the person being cared for. Examples include recommendations for exercise and suggestions for improving dietary habits.

[0016] "Real-time" refers to a state where data processing and notifications occur almost instantly, with minimal delay. [Brief explanation of the drawing]

[0017] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] It is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] It is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] It is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] It is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] It shows an emotion map to which multiple emotions are mapped. [Figure 10] It shows an emotion map to which multiple emotions are mapped. [Figure 11] It is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] It is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] It is a sequence diagram showing the processing flow of the data processing system in Example 2 when an emotion engine is combined. [Figure 14] It is a sequence diagram showing the processing flow of the data processing system in Application Example 2 when an emotion engine is combined.

Embodiments for Carrying Out the Invention

[0018] Hereinafter, an example of an embodiment of a system according to the technology of the present disclosure will be described with reference to the accompanying drawings.

[0019] First, the language used in the following description will be explained.

[0020] In the following embodiments, the signed processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Furthermore, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include CPU (Central Processing Unit), GPU (Graphics Processing Unit), GPGPU (General-Purpose computing on Graphics Processing Units), and APU (Accelerated Processing Unit).

[0021] In the following embodiments, signed RAM (Random Access Memory) is a memory that temporarily stores information and is used as work memory by the processor.

[0022] In the following embodiments, the signed storage is one or more non-volatile storage devices that store various programs and various parameters. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes.

[0023] In the following embodiments, the signed communication interface (I / F) is an interface that includes a communication processor and an antenna, etc. The communication interface manages communication between multiple computers. Examples of communication standards applicable to the communication interface include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0024] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." That is, "A and / or B" means that it may be A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or."

[0025] [First Embodiment]

[0026] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0027] As shown in Figure 1, the data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0028] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0029] The smart device 14 comprises a computer 36, a reception device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The reception device 38, output device 40, and camera 42 are also connected to the bus 52.

[0030] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0031] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form perceptible to the user 20 (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0032] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

[0033] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0034] As shown in Figure 2, in the data processing device 12, a specific processing is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" related to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0035] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0036] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with a specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0037] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0038] This invention relates to a system for managing activity information and providing alert notifications related to childcare and elderly care, and in particular to providing means for detecting unusual behaviors and abnormal health conditions and responding to them quickly.

[0039] This system operates by having users input activity information, which is then collected, stored, and analyzed on a server. A specific implementation of the system is shown below.

[0040] System Configuration

[0041] 1. User terminal

[0042] Data entry interface: An interface for users to input activity information. Examples include smartphone and tablet apps.

[0043] Data transmission module: A module that sends the entered activity information to the server.

[0044] Alert receiving module: A module for receiving alerts from the server.

[0045] Alert notification module: A module that notifies the user of received alerts.

[0046] 2. Server

[0047] Data receiving module: Receives activity information sent from the user's terminal.

[0048] Database: Stores received activity information.

[0049] Analysis Module: Analyzes and detects anomalies and singular behaviors based on stored data.

[0050] Alert generation module: Based on the analysis results, it generates alerts as needed and sends them to the user's terminal.

[0051] Health suggestion module: Generates health maintenance suggestions in care mode.

[0052] Program execution flow

[0053] The system's processing flow is explained in detail below.

[0054] Data collection

[0055] User: Enters activity information through the data input interface on the user's terminal. For example, they might enter the estimated arrival time of a child at school or information about meals and exercise for elderly people.

[0056] Example: The user enters "Child A is scheduled to arrive at school at 8:30."

[0057] Data transmission

[0058] Terminal: Sends the entered activity information to the server via the data transmission module.

[0059] Specific example: The device sends data to the server that says, "Child A's estimated arrival time at school: 8:30 AM."

[0060] Data reception and storage

[0061] Server: The data receiving module receives the transmitted data and saves it to the database.

[0062] Specific example: The server saves the data "Child A's estimated arrival time at school: 8:30 AM" to the database.

[0063] Data Analysis

[0064] Server: Based on the data stored by the analysis module, it performs analysis to detect singular behaviors and anomalies.

[0065] Specific example: The server detects that child A has not arrived at school by 8:45 AM and determines that this is an anomaly.

[0066] Alert generation and sending

[0067] Server: Based on the detected anomaly, the alert generation module generates an alert and sends it to the user's terminal.

[0068] Specific example: The server generates an alert stating "Child A has not arrived at school" and sends it to the terminal.

[0069] Alert notification

[0070] Terminal: The alert receiving module receives alerts from the server, and the alert notification module notifies the user.

[0071] Specific example: The device notifies the user via a pop-up alert stating, "Child A has not arrived at school."

[0072] Health assessment and suggestions for caregiving mode

[0073] Data collection and transmission

[0074] User: Enters activity information and health status of elderly individuals into the client application.

[0075] Terminal: The data transmission module sends this information to the server.

[0076] Specific example: The user inputs information such as "walking distance" and "meal details," and the device sends this information to the server.

[0077] Data reception and storage

[0078] Server: The data receiving module receives this information and stores it in the database.

[0079] Health assessment and recommendations

[0080] Server: Analyzes data stored in the health assessment module and evaluates health status.

[0081] Server: Based on the evaluation results in the health suggestion module, it generates specific suggestions for maintaining health and sends them to the user's terminal.

[0082] Specific example: The server suggests to elderly person B that they "take a 30-minute walk every day," and the terminal notifies the user of this.

[0083] This allows the system to centrally manage important activity information related to childcare and elder care in real time, enabling it to detect unusual behaviors and anomalies and respond quickly. Furthermore, in elder care mode, it can contribute to the user's health management by assessing their health status and suggesting appropriate health maintenance measures.

[0084] The following describes the processing flow.

[0085] Step 1:

[0086] User: Enter activity information using the data entry interface of the client application.

[0087] As a concrete example, the user enters "Child A's expected arrival time at school is 8:30 AM."

[0088] Step 2:

[0089] Terminal: Sends the entered activity information to the server via the data transmission module.

[0090] For example, the device sends data to the server such as "Child A's estimated arrival time at school: 8:30 AM".

[0091] Step 3:

[0092] Server: Receives data sent from the terminal using the data receiving module.

[0093] As a concrete example, the server receives data that says "Child A's estimated arrival time at school: 8:30 AM".

[0094] Step 4:

[0095] Server: Saves received data to the database.

[0096] As a concrete example, the data received by the server is stored in a database.

[0097] Step 5:

[0098] Server: Uses analysis modules to analyze stored data and detect anomalies and outlier behaviors.

[0099] As a concrete example, the server references the school's GPS data and time clock records and detects that child A has not arrived at school by 8:45.

[0100] Step 6:

[0101] Server: When singular behavior or anomalies are detected, the alert generation module generates an alert.

[0102] As a concrete example, the server generates an alert stating, "Child A has not arrived at school."

[0103] Step 7:

[0104] Server: Sends generated alerts to the client application.

[0105] As a concrete example, the server sends an alert to the terminal stating, "Child A has not arrived at school."

[0106] Step 8:

[0107] Terminal: The alert receiving module receives alerts sent from the server.

[0108] As a concrete example, the device receives an alert stating, "Child A has not arrived at school."

[0109] Step 9:

[0110] Terminal: Notifies the user of alerts received by the alert notification module.

[0111] As a concrete example, a pop-up notification appears on the user's smartphone stating, "Child A has not arrived at school."

[0112] Health assessment and suggestions for caregiving mode

[0113] Step 1:

[0114] User: Use the client application to input activity information and health status of elderly individuals.

[0115] As a concrete example, you can input information such as the elderly person's "walking distance" and "dietary content."

[0116] Step 2:

[0117] Terminal: Sends the entered information to the server.

[0118] As a specific example, the terminal sends information such as "elderly person B's walking distance and dietary content" to the server.

[0119] Step 3:

[0120] Server: Receives information sent by the data receiving module and stores it in the database.

[0121] As a concrete example, the server stores information such as "elderly person B's walking distance and diet" in a database.

[0122] Step 4:

[0123] Server: Analyzes data received by the health assessment module and evaluates the health status.

[0124] As a concrete example, the server compares current data with past data and concludes that "elderly person B is not getting enough exercise."

[0125] Step 5:

[0126] Server: The health suggestion module generates health maintenance suggestions based on the evaluation results.

[0127] As a concrete example, the server might generate a suggestion such as "We recommend taking a 30-minute walk every day."

[0128] Step 6:

[0129] Server: Sends the generated proposals to the client application.

[0130] As a concrete example, the server sends a suggestion to the terminal saying, "We recommend taking a 30-minute walk every day."

[0131] Step 7:

[0132] Terminal: Receives proposals and notifies the user.

[0133] For example, a notification such as "We recommend taking a 30-minute walk every day" might appear on the user's smartphone.

[0134] In this way, this system smoothly handles the entire process from user input to data collection, analysis, alert generation, and notification, enabling a rapid response to unusual behaviors and abnormal health conditions in childcare and elder care.

[0135] (Example 1)

[0136] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0137] Managing activity information in childcare and elder care is time-consuming and labor-intensive, and delays in recording information and detecting anomalies are a challenge. In particular, the lack of means to detect unusual behaviors or abnormal health conditions early and respond quickly means that users may not be able to take action promptly, leading to problems becoming more serious. Furthermore, in elder care, there is a need to appropriately assess the health status of the elderly and propose appropriate health maintenance measures, but there is a lack of systems to do so.

[0138] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0139] In this invention, the server includes means for collecting activity information entered by the user, means for transmitting the activity information to the server, means for the server to receive the activity information and store it in a database, means for the server to analyze the stored activity information and detect singular behaviors or anomalies, means for the server to generate alerts based on the detected anomalies and send them to a client application, means for the terminal to notify the user of the received alerts, and means for the server to use a health suggestion module to generate health maintenance suggestions in care mode and send them to a client application. This enables centralized management of childcare and caregiving activity information, rapid detection of singular behaviors or anomalies and generation of alerts, and further enables health assessment of the elderly and appropriate health maintenance suggestions in care mode.

[0140] A "user" is someone who uses the system to input activity information and receive alerts and suggestions.

[0141] "Activity information" refers to data about actions and situations related to childcare and elder care.

[0142] A "server" is a device that receives, stores, and analyzes activity information sent by users, and generates alerts and suggestions.

[0143] A "database" is a storage method used by a server to store activity information it has received.

[0144] An "analysis module" is a software component that analyzes information stored in a database to detect anomalies and unusual behavior.

[0145] An "alert generation module" is a software component that generates alerts based on anomalies detected by the analysis module.

[0146] A "client application" is application software that runs on a user's terminal and is used by the user to input activity information and receive alerts and suggestions from the server.

[0147] A "device" refers to a device used by a user, such as a smartphone or tablet.

[0148] The "Health Suggestion Module" is a software component that, in care mode, performs a health assessment based on saved activity information and generates suggestions for maintaining health.

[0149] This invention relates to a system for managing activity information and providing alert notifications related to childcare and elderly care, and in particular to providing means for detecting unusual behaviors and abnormal health conditions and responding quickly. Specific embodiments of the system are shown below.

[0150] System Configuration

[0151] 1. User terminal

[0152] Data entry interface: This is an interface for users to input activity information. Smartphone apps and tablet apps fall into this category.

[0153] Data transmission module: This module transmits the input activity information to the server.

[0154] Alert receiving module: This module is used to receive alerts from the server.

[0155] Alert notification module: This module notifies the user of received alerts.

[0156] 2. Server

[0157] Data receiving module: This module receives activity information sent from the user's terminal.

[0158] Database: A storage device for saving received activity information.

[0159] Analysis Module: A software component used to detect anomalies and outliers based on stored data.

[0160] Alert generation module: This is a software component that generates alerts as needed based on analysis results and sends them to the user's terminal.

[0161] Health Suggestion Module: This is a software component for generating health maintenance suggestions in caregiving mode.

[0162] Explanation of the program's processing

[0163] Data collection

[0164] User: Manually inputs childcare and eldercare activity information through a smartphone or tablet application. For example, inputting the estimated arrival time of a child at school or information on meals and exercise for the elderly.

[0165] Data transmission

[0166] Terminal: Uses a data transmission module to send the entered activity information to the server using an HTTP request.

[0167] Data reception and storage

[0168] Server: The data receiving module receives the transmitted data and saves it to a database such as MySQL (registered trademark).

[0169] Data Analysis

[0170] Server: The analysis module uses information stored in the database to perform analysis to detect singular behaviors and anomalies. Statistical methods and machine learning models are frequently used in this analysis.

[0171] Alert generation and sending

[0172] Server: Based on the anomaly detected by the alert generation module, an alert is generated and sent to the user terminal via an HTTP POST request.

[0173] Alert notification

[0174] Terminal: The alert receiving module receives alerts sent from the server, and the alert notification module notifies the user of these alerts via pop-up or push notifications.

[0175] Health assessment and suggestions for caregiving mode

[0176] Data collection and transmission

[0177] User: Input activity information and health status of elderly individuals into the client application. For example, input information such as walking distance and dietary details.

[0178] Terminal: Uses a data transmission module to send this information to the server.

[0179] Data reception and storage

[0180] Server: The data receiving module receives this information and stores it in the database.

[0181] Health assessment and recommendations

[0182] Server: The health assessment module analyzes the stored data and evaluates the user's health status. Subsequently, the health suggestion module generates appropriate health maintenance suggestions based on the assessment results and sends them to the user's terminal.

[0183] Specific examples and prompt statements

[0184] Specific example

[0185] A user uses a smartphone app to input "Child A is scheduled to arrive at school at 8:30." This data is sent to a server, and an analysis module detects that Child A has not arrived at school at 8:45, generates an alert stating "Child A has not arrived at school," and sends it to the user's device.

[0186] Example of a prompt

[0187] "I would like an alert to be issued and I to be notified if my child has not arrived at school."

[0188] This allows the system to manage activity information related to childcare and elderly care in real time, quickly detect and notify of abnormalities in health conditions, and also provide concrete suggestions for maintaining the health of the elderly.

[0189] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0190] Step 1: Enter activity information

[0191] User: Enters information about activities related to childcare and elder care. Specifically, the user accesses an application on their smartphone or tablet and manually enters information such as "Child A is scheduled to arrive at school at 8:30" and "Breakfast for the elderly: Salad and fruit."

[0192] Input: Activity information such as "Child A is scheduled to arrive at school at 8:30."

[0193] Output: Activity information entered into the user's terminal.

[0194] Step 2: Submit the input data

[0195] Terminal: Uses a data transmission module to send the entered activity information to the server. Specifically, the terminal generates an HTTP POST request and sends the data to the server.

[0196] Input: Activity information entered into the user's terminal.

[0197] Output: Activity information received by the server.

[0198] Step 3: Data reception and storage

[0199] Server: The data receiving module receives the transmitted data and stores it in the database. Specifically, the server parses the received HTTP POST request and stores the data in the MySQL database.

[0200] Input: Activity information sent from the device.

[0201] Output: Activity information stored in the database.

[0202] Step 4: Data Analysis

[0203] Server: The analysis module detects singular behavior and anomalies based on the stored data. Specifically, the server analyzes the data using statistical methods and machine learning models to detect anomalies.

[0204] Input: Activity information stored in the database.

[0205] Data processing / computation: Analysis using statistical methods and machine learning models.

[0206] Output: Detection results of singular behaviors and anomalies.

[0207] Step 5: Generate and send alerts

[0208] Server: Based on the anomalies detected by the alert generation module, the server generates an alert and sends it to the user terminal. Specifically, the server generates an alert message and sends it to the user terminal again using an HTTP POST request.

[0209] Input: Results of detecting singular behavior or anomalies.

[0210] Output: An alert sent to the user's terminal.

[0211] Step 6: Alert Notification

[0212] Terminal: The alert receiving module receives alerts from the server, and the alert notification module notifies the user. Specifically, the terminal generates pop-up notifications or push notifications to inform the user.

[0213] Input: Alert sent from the server.

[0214] Output: An alert sent to the user.

[0215] Step 7: Health assessment and recommendations for care mode

[0216] Data collection and transmission

[0217] User: Enters activity information and health status of elderly individuals into the client application. For example, "Today's walking distance: 5000 steps," "Breakfast: Salad and fruit," etc.

[0218] Terminal: The data transmission module sends this information to the server. Specifically, the terminal sends the input data to the server using an HTTP POST request.

[0219] Input: Activity information and health status of elderly individuals.

[0220] Output: Health information received by the server.

[0221] Data reception and storage

[0222] Server: The data receiving module receives this information and stores it in the database. Specifically, the server parses the received HTTP POST request and stores the data in the database.

[0223] Input: Health information sent from the device.

[0224] Output: Health information stored in the database.

[0225] Health assessment and recommendations

[0226] Server: The health assessment module analyzes the stored data and evaluates the user's health status. Subsequently, the health suggestion module generates appropriate health maintenance suggestions based on the evaluation results and sends them to the user's terminal. Specifically, the server analyzes the data, makes evaluations such as "total daily walking distance is below the recommended value," generates suggestions such as "30 minutes of walking per day is recommended," and sends them to the user's terminal using an HTTP POST request.

[0227] Input: Health information stored in the database.

[0228] Data processing / calculation: Analysis using health assessment algorithms.

[0229] Output: Health suggestions sent to the user's terminal.

[0230] (Application Example 1)

[0231] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0232] In modern society, there is a need to efficiently manage activity information related to childcare and elder care, and to quickly detect and respond to unusual behaviors and abnormal health conditions. However, conventional systems have difficulty collecting real-time location information and situational data, which can lead to delays in responding to abnormalities. Furthermore, they lack mechanisms to provide users with appropriate recommended actions when abnormalities are detected. Therefore, there is a need for a comprehensive system that enables safe and rapid responses.

[0233] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0234] In this invention, the server includes means for collecting activity information entered by the user, means for transmitting the activity information to the server, means for the server to receive the activity information and store it in a database, means for the server to analyze the stored activity information and detect singular behavior or anomalies, means for the server to generate an alert based on the detected anomaly and send it to the client application, means for the terminal to notify the user of the received alert, means for collecting location information and status data in real time and promptly providing alert notifications when an anomaly is detected, and means for generating recommended actions when an anomaly is detected and proposing them to the user. As a result, the user can monitor the location information and status data of family members and those they care for in real time and respond quickly when an anomaly occurs. In addition, appropriate recommended actions are provided for the detected anomaly, improving safety and health maintenance.

[0235] A "user" is an individual or organization that uses the system to input activity information and receive alerts and recommended actions.

[0236] "Activity information" refers to information such as the subject's location, daily behavior data, and health status.

[0237] A "server" is a central device that receives activity information sent by users, stores it in a database, and analyzes it to detect anomalies and abnormalities.

[0238] A "client application" is software installed on a user's terminal that receives data and alerts from a server and notifies the user of that information.

[0239] A "database" is an information processing system used by a server to store activity information it has received.

[0240] "Singular behavior" refers to abnormal behavior that deviates from normal behavioral patterns, and it is through such behavior that abnormalities are detected.

[0241] An "anomaly" is an event that deviates from the normal behavior or state of a user or subject, and an alert is generated based on the detection of such an anomaly.

[0242] An "alert" is a warning message sent to a user when unusual behavior or anomalies are detected.

[0243] "Recommended actions" are specific suggestions of what the user should do in response to detected anomalies.

[0244] "Location information" refers to data that indicates the current location of a user or subject, and is necessary information for real-time monitoring.

[0245] "Status data" refers to all information that represents the state of a user or subject, including but not limited to location information.

[0246] This "Family Safety Monitoring & Alert System" is a comprehensive system that monitors the location and status data of family members and those receiving care in real time, and enables rapid response when an anomaly is detected. The specific implementation of the system is shown below.

[0247] System Configuration

[0248] 1. User terminal

[0249] Data entry interface: An interface for users to input activity information. Smartphone and tablet apps fall into this category.

[0250] Data transmission module: A module that sends the entered activity information to the server.

[0251] Alert receiving module: A module for receiving alerts from the server.

[0252] Alert notification module: A module that notifies the user of received alerts.

[0253] 2. Server

[0254] Data receiving module: Receives activity information sent from the user's terminal.

[0255] Database: Stores received activity information.

[0256] Analysis Module: Analyzes and detects singular behaviors and anomalies based on stored data. Uses scikit-learn for data analysis.

[0257] Alert generation module: Based on analysis results, it generates alerts as needed and sends them to the user's device. Firebase Cloud Messaging (FCM) is used to send alerts.

[0258] Health suggestion module: Generates recommended actions when an anomaly is detected and suggests them to the user.

[0259] Program Processing Description

[0260] This system uses Python, AWS® Lambda, AWS DynamoDB, Flutter®, scikit-learn, and Firebase Cloud Messaging (FCM) as its main hardware and software components.

[0261] Data collection

[0262] User: Enters activity information through the data input interface on the user's terminal. For example, they might enter the estimated arrival time of a child at school or information about meals and exercise for elderly people.

[0263] Example: The user enters "Child A is scheduled to arrive at school at 8:30."

[0264] Data transmission

[0265] Terminal: Sends the entered activity information to the server via the data transmission module.

[0266] Specific example: The device sends data to the server that says, "Child A's estimated arrival time at school: 8:30 AM."

[0267] Data reception and storage

[0268] Server: The data receiving module receives the transmitted data and stores it in AWS DynamoDB.

[0269] Specific example: The server saves the data "Child A's estimated arrival time at school: 8:30 AM" to the database.

[0270] Data Analysis

[0271] Server: Uses scikit-learn to perform analysis on stored data to detect singular behaviors and anomalies.

[0272] Specific example: The server detects that child A has not arrived at school by 8:45 AM and determines that this is an anomaly.

[0273] Alert generation and sending

[0274] Server: Based on the detected anomaly, the alert generation module uses FCM to generate an alert and sends it to the user terminal.

[0275] Specific example: The server generates an alert stating "Child A has not arrived at school" and sends it to the terminal.

[0276] Alert notification

[0277] Terminal: The alert receiving module receives alerts from the server, and the alert notification module notifies the user.

[0278] Specific example: The device notifies the user via a pop-up alert stating, "Child A has not arrived at school."

[0279] Recommended Actions

[0280] Server: Generates specific recommended actions to address detected anomalies and sends them to the user's terminal.

[0281] Specific example: The server generates a recommended action, "Child A is late arriving at school. Please contact the school immediately," and sends it to the device.

[0282] Example of a prompt

[0283] text

[0284] User ID: 12345, Activity Information: 'The child is scheduled to arrive at the park at 17:00', Current Time: '17:30'

[0285] With this system, users can efficiently and quickly monitor the safety and health status of their families and can take appropriate actions immediately when an abnormality occurs.

[0286] The flow of the specific process in Application Example 1 will be described using FIG. 12.

[0287] Step 1:

[0288] Data Collection

[0289] The user inputs activity information through the data input interface of the smartphone or tablet app. The data to be input includes location information, scheduled time, action content, etc. For example, the user inputs "Child A is scheduled to arrive at school at 8:30". This information is input into the terminal and processed by the data transmission module.

[0290] Input: User's activity information (location information, scheduled time, action content)

[0291] Output: Information input into the data transmission module in the terminal

[0292] Step 2:

[0293] Data Transmission

[0294] The terminal uses the data transmission module to send the input activity information to the server via the Internet. For example, the terminal sends data such as "Scheduled arrival time of Child A at school: 8:30" to the server. By this operation, the activity information is passed to the server side.

[0295] Input: Information input into the data transmission module in the terminal

[0296] Output: Information sent to the server's data reception module

[0297] Step 3:

[0298] Data reception and storage

[0299] The server uses the data reception module to receive the activity information sent from the user terminal and stores it in the database. As a specific example, the server stores the data "Scheduled arrival time of child A: 8:30" in the database.

[0300] Input: Information sent to the server's data reception module

[0301] Output: Activity information stored in the database

[0302] Step 4:

[0303] Data analysis

[0304] The server uses scikit-learn to perform analysis for detecting singular behaviors and anomalies based on the stored data. For example, the server detects that child A has not arrived at school even at 8:45 and determines this as an anomaly. Machine learning algorithms are used for anomaly detection, and patterns are analyzed based on past data.

[0305] Input: Activity information stored in the database

[0306] Output: Anomaly detection results (singular behaviors, anomalies)

[0307] Step 5:

[0308] Alert generation and transmission

[0309] The server generates an alert using an alert generation module based on the detected anomaly and sends it to the user's device using Firebase Cloud Messaging (FCM). Specifically, the server generates an alert stating "Child A has not arrived at school" and sends it to the device.

[0310] Input: Anomaly detection result

[0311] Output: Alert message

[0312] Step 6:

[0313] Alert notification

[0314] The user's device receives alerts from the server using an alert receiving module, and then notifies the user via a pop-up display or audio notification using an alert notification module. Specifically, the device notifies the user of an alert stating that "Child A has not arrived at school."

[0315] Input: Alert message sent from FCM

[0316] Output: Alert notification (pop-up display, audio notification)

[0317] Step 7:

[0318] Recommended Actions

[0319] The server generates specific recommended actions to address the detected anomaly and sends them to the user's terminal. For example, the server might generate and send the recommended action, "Child A is late arriving at school. Please contact the school immediately."

[0320] Input: Anomaly detection result (singular behavior, anomaly)

[0321] Output: Recommended action message

[0322] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0323] This invention relates to a childcare and elderly care support system that combines an emotion engine that recognizes user emotions, and provides a means for rapidly detecting singular behaviors and abnormal health conditions and providing appropriate alerts to the user.

[0324] In addition to collecting and managing activity information entered by users, this system uses an emotion engine to recognize the user's emotional state, enabling more accurate analysis and alert generation.

[0325] System Configuration

[0326] 1. User terminal

[0327] Data entry interface: An interface for users to input activity information. Examples include smartphone and tablet apps.

[0328] Data transmission module: A module that sends the entered activity information to the server.

[0329] Alert receiving module: A module for receiving alerts from the server.

[0330] Alert notification module: A module that notifies the user of received alerts.

[0331] Emotion Recognition Module: A module that uses an emotion engine to analyze the user's emotions in real time as they input data.

[0332] 2. Server

[0333] Data receiving module: Receives activity information sent from the user's terminal.

[0334] Database: Stores received activity and sentiment information.

[0335] Analysis Module: Analyzes and detects anomalies and singular behaviors based on stored data.

[0336] Alert generation module: Based on the analysis results, it generates alerts as needed and sends them to the user's terminal.

[0337] Health suggestion module: Generates health maintenance suggestions in care mode.

[0338] Emotion Analysis Module: Uses an emotion engine to perform data analysis based on the results of user emotion analysis.

[0339] Program execution flow

[0340] The system's processing flow is explained in detail below.

[0341] Data collection

[0342] User: Activity information is entered through the client application's data entry interface. Additionally, an emotion recognition module analyzes the user's emotions in real time during the input process.

[0343] Specific example: A user enters "Child A's expected arrival time at school is 8:30 AM," and the user's emotions (e.g., anxiety, impatience) are analyzed at that time.

[0344] Data transmission

[0345] Terminal: Sends input activity and emotion information to the server via a data transmission module.

[0346] Specific example: The device sends data to the server: "Child A's estimated arrival time at school: 8:30 AM" and "User's emotional state: Anxious."

[0347] Data reception and storage

[0348] Server: The data receiving module receives data sent from the terminal and stores it in the database.

[0349] Specific example: The server saves the following data to the database: "Child A's estimated arrival time at school: 8:30 AM" and "User's emotional state: Anxious."

[0350] Data Analysis

[0351] Server: Uses the analysis module to perform analysis based on stored activity information and sentiment analysis results to detect singular behaviors and anomalies.

[0352] Specific example: The server references the school's GPS data and time clock information, detects that child A has not arrived at school by 8:45 AM, and that the user's emotional state is "anxious," and determines that this is an anomaly.

[0353] Alert generation and sending

[0354] Server: When singular behavior or anomalies are detected, the alert generation module generates an alert. The alert content is also adjusted based on the sentiment analysis results.

[0355] Specific example: The server generates an alert stating "Child A has not arrived at school," and considering the user's emotional state of anxiety, the alert is modified to encourage a more prompt response.

[0356] Alert notification

[0357] Terminal: The alert receiving module receives alerts from the server, and the alert notification module notifies the user.

[0358] Specific example: The device notifies the user via a pop-up alert stating, "Child A has not arrived at school."

[0359] Health assessment and suggestions for caregiving mode

[0360] Data collection and transmission

[0361] User: Uses a client application to input activity information and health status of elderly individuals. During input, an emotion recognition module analyzes the user's emotions in real time.

[0362] Specific example: Users input information such as "walking distance" and "meal content," and their emotional state (e.g., feeling safe, satisfied) is analyzed at that time.

[0363] Data reception and storage

[0364] Server: Receives activity and emotion information sent by the data receiving module and stores it in the database.

[0365] Specific example: The server stores information such as "elderly person B's walking distance and diet" and "user's emotional state: feeling safe" in a database.

[0366] Health assessment and recommendations

[0367] Server: Analyzes data stored in the health assessment module to evaluate health status. It also adjusts suggestions based on the emotion analysis results.

[0368] Specific example: The server compares past data and assesses that "elderly person B is not getting enough exercise," and since their emotional state is "reassured," it generates more proactive exercise suggestions.

[0369] Proposal submission and notification

[0370] Server: The health suggestion module generates health maintenance suggestions based on the evaluation results and sends them to the user's terminal.

[0371] Terminal: Receives proposals and notifies the user.

[0372] Specific example: The server generates a suggestion such as "We recommend taking a 30-minute walk every day," and the device notifies the user of this.

[0373] In this way, by combining this system with an emotion engine, it becomes possible to provide more accurate alert notifications and suggestions that take into account the user's emotional state, enabling the management of important activity information in childcare and elder care and prompt responses.

[0374] The following describes the processing flow.

[0375] Step 1:

[0376] User: Enters activity information using the client application's data entry interface. Simultaneously, the emotion recognition module analyzes the user's emotions in real time as they are being entered.

[0377] For example, a user might enter "Child A's expected arrival time at school is 8:30 AM," and the user's emotional state (e.g., anxiety, impatience) is then analyzed.

[0378] Step 2:

[0379] Terminal: Sends input activity and emotion information to the server via a data transmission module.

[0380] As a specific example, the device sends data to the server such as "Child A's estimated arrival time at school is 8:30" and "User's emotional state: Anxious."

[0381] Step 3:

[0382] Server: Receives data sent from the terminal using the data receiving module.

[0383] As a specific example, the server receives data indicating "Child A's estimated arrival time at school is 8:30 AM" and "User's emotional state: Anxious."

[0384] Step 4:

[0385] Server: Saves received data to the database.

[0386] As a concrete example, the server stores the data it receives, "Child A's estimated arrival time at school: 8:30 AM" and "User's emotional state: Anxious," into a database.

[0387] Step 5:

[0388] Server: Uses the analysis module to perform analysis based on stored activity information and sentiment analysis results to detect singular behaviors and anomalies.

[0389] As a specific example, the server refers to the school's GPS data and time clock information, detects that child A has not arrived at school by 8:45 AM, and that the user's emotional state is "anxious," and determines that this is an anomaly.

[0390] Step 6:

[0391] Server: When singular behavior or anomalies are detected, the alert generation module generates an alert. The alert content is also adjusted based on the sentiment analysis results.

[0392] As a concrete example, the server generates an alert stating "Child A has not arrived at school," and considering the user's emotional state of anxiety, the alert is designed to prompt a more rapid response.

[0393] Step 7:

[0394] Server: Sends generated alerts to the client application.

[0395] As a concrete example, the server sends an alert to the terminal stating, "Child A has not arrived at school."

[0396] Step 8:

[0397] Terminal: The alert receiving module receives alerts from the server.

[0398] As a concrete example, the device receives an alert stating, "Child A has not arrived at school."

[0399] Step 9:

[0400] Terminal: Notifies the user of alerts received by the alert notification module.

[0401] As a concrete example, a pop-up notification appears on the user's smartphone stating, "Child A has not arrived at school."

[0402] Health assessment and suggestions for caregiving mode

[0403] Step 1:

[0404] User: Uses a client application to input activity information and health status of elderly individuals. Simultaneously, an emotion recognition module analyzes the user's emotions in real time as they input data.

[0405] As a concrete example, users input information such as "walking distance" and "meal content," and their emotional state (e.g., feeling safe, satisfied) is analyzed at that time.

[0406] Step 2:

[0407] Terminal: Sends the entered information to the server.

[0408] As a specific example, the device sends information such as "elderly person B's walking distance and diet" and "user's emotional state: feeling safe" to the server.

[0409] Step 3:

[0410] Server: Receives information sent by the data receiving module and stores it in the database.

[0411] As a specific example, the server stores information such as "elderly person B's walking distance and diet" and "user's emotional state: feeling secure" in a database.

[0412] Step 4:

[0413] Server: Analyzes data stored in the health assessment module to evaluate health status. It also adjusts suggestions based on the emotion analysis results.

[0414] As a concrete example, the server compares past data and evaluates that "elderly person B is not getting enough exercise," and since their emotional state is "reassured," it generates more proactive exercise suggestions.

[0415] Step 5:

[0416] Server: The health suggestion module generates health maintenance suggestions based on the evaluation results and sends them to the user's terminal.

[0417] As a concrete example, the server generates a suggestion such as "We recommend taking a 30-minute walk every day" and sends it to the terminal.

[0418] Step 6:

[0419] Terminal: Receives proposals and notifies the user.

[0420] For example, a notification such as "We recommend taking a 30-minute walk every day" might appear on the user's smartphone.

[0421] In this way, by combining this system with an emotion engine, it becomes possible to provide more accurate alert notifications and suggestions that take into account the user's emotional state, enabling the management of important activity information in childcare and elder care and prompt responses.

[0422] (Example 2)

[0423] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0424] Conventional childcare and eldercare support systems collect and analyze activity information without considering the user's emotional state, resulting in low accuracy in detecting anomalies and abnormalities, and a failure to provide appropriate alerts and suggestions. In addition, because emotional information is not utilized, responses to users are uniform, making it difficult to provide appropriate responses tailored to individual situations.

[0425] The identification processing by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for collecting activity information and emotion information input by the user; means for transmitting the activity information and emotion information to the server; means for the server to receive the activity information and emotion information and store it in a database; means for the server to analyze the stored activity information and emotion information and detect singular behavior or anomalies; means for the server to generate an alert based on the detected anomalies and emotion analysis results and send it to the client application; and means for the terminal to notify the user of the alert received. This enables highly accurate alert notifications and suggestions that take into account the user's emotional state.

[0426] A "user" refers to an individual who inputs activity and emotional information into the system.

[0427] "Activity information" refers to information about daily activities and events that users input into the system.

[0428] "Emotional information" refers to data that analyzes a user's emotional state in real time.

[0429] A "server" refers to the core of a system that receives, stores, and analyzes activity and sentiment information, generates alerts and suggestions, and sends them to client applications.

[0430] A "database" refers to a storage device used to store received activity and emotional information.

[0431] An "analysis module" refers to software used to detect anomalies or anomalies based on stored data.

[0432] An "alert generation module" refers to software that has the function of generating alerts based on the detection of anomalies and the results of sentiment analysis.

[0433] A "client application" refers to an application on a device that a user uses to input activity and sentiment information and to receive alerts and suggestions.

[0434] "Care mode" refers to the operating mode of a system that evaluates the activity information and health status of elderly people and makes suggestions for maintaining their health.

[0435] A "health assessment module" refers to software that evaluates health status based on stored activity and emotional information and generates recommendations.

[0436] This invention is a system intended to support childcare and elder care, and incorporates an emotion engine that recognizes the user's emotions. This system can quickly detect unusual behaviors and abnormal health conditions, and provide the user with appropriate alerts and suggestions.

[0437] System Configuration

[0438] 1. User terminal

[0439] Data entry interface: An interface for users to input activity information. Examples include smartphone and tablet apps.

[0440] Data transmission module: A module that transmits input activity and emotion information to the server.

[0441] Alert receiving module: A module for receiving alerts from the server.

[0442] Alert notification module: A module that notifies the user of received alerts.

[0443] Emotion Recognition Module: A module that uses an emotion engine to analyze the user's emotions in real time as they input data.

[0444] 2. Server

[0445] Data receiving module: Receives activity and emotion information sent from the user's terminal.

[0446] Database: Stores received activity and sentiment information.

[0447] Analysis Module: Analyzes and detects anomalies and singular behaviors based on stored data.

[0448] Alert generation module: Based on the analysis results, it generates alerts as needed and sends them to the user's terminal.

[0449] Health suggestion module: Generates health maintenance suggestions in care mode.

[0450] Emotion Analysis Module: Uses an emotion engine to perform data analysis based on the results of user emotion analysis.

[0451] Specific examples of program processing

[0452] User: Enters activity information through the client application's data entry interface. During input, the emotion recognition module analyzes the user's emotions in real time.

[0453] Specific example: A user enters "Child A's expected arrival time at school is 8:30 AM." At this time, the user's emotions (e.g., anxiety or impatience) are analyzed.

[0454] Terminal: Sends activity and emotion information entered via the data transmission module to the server.

[0455] Specific example: The device sends data to the server: "Child A's estimated arrival time at school: 8:30 AM" and "User's emotional state: Anxious."

[0456] Server: The data receiving module receives data sent from the terminal and stores it in the database.

[0457] Specific example: The server saves the following data to the database: "Child A's estimated arrival time at school: 8:30 AM" and "User's emotional state: Anxious."

[0458] Server: Uses an analysis module to detect singular behaviors and anomalies based on stored activity information and sentiment analysis results.

[0459] Specific example: The server checks the school's GPS data and time clock information, detects that child A has not arrived at school by 8:45 AM, and also detects that the user's emotional state is "anxious," and determines that this is an anomaly.

[0460] Server: When singular behavior or anomalies are detected, the alert generation module generates an alert and adjusts the content of the alert considering the sentiment analysis results.

[0461] Specific example: The server generates an alert stating "Child A has not arrived at school," and considering the user's emotional state of anxiety, the alert is modified to encourage a more prompt response.

[0462] Terminal: The alert receiving module receives alerts from the server, and the alert notification module notifies the user.

[0463] Specific example: The device notifies the user via a pop-up alert stating, "Child A has not arrived at school."

[0464] Specific examples of health assessment and recommendations for caregiving.

[0465] User: Uses a client application to input activity information and health status of elderly individuals. During input, an emotion recognition module analyzes emotions in real time.

[0466] Specific example: When a user enters information such as "walking distance" or "meal content," their emotions (e.g., feeling safe or satisfied) are analyzed.

[0467] Server: Receives activity and emotion information sent by the data receiving module and stores it in the database.

[0468] Specific example: The server stores information such as "elderly person B's walking distance and diet" and "user's emotional state: feeling safe" in a database.

[0469] Server: Analyzes data stored in the health assessment module and evaluates health status. Adjusts suggestions based on the emotion analysis results.

[0470] Specific example: The server compares data with past data and assesses that "elderly person B is not getting enough exercise," and based on their emotional state being "reassured," it generates more proactive exercise suggestions.

[0471] Server: The health suggestion module generates health maintenance suggestions based on the evaluation results and sends them to the user's terminal.

[0472] Terminal: Receives proposals and notifies the user.

[0473] Specific example: The server generates a suggestion such as "We recommend taking a 30-minute walk every day," and the device notifies the user of this.

[0474] Example prompts for a generative AI model

[0475] Example prompt: "Describe a system that takes input information about daily activities related to childcare or elder care (e.g., a child's arrival time at school or the elderly person's meals), performs real-time sentiment recognition, and generates appropriate alerts or suggestions if anomalies are detected."

[0476] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0477] Step 1:

[0478] Users input activity and emotion information through the data entry interface of the client application. This allows for real-time recording of the user's activity and emotion data.

[0479] Specific operation: The user opens a smartphone app and enters "Child A's estimated arrival time at school: 8:30." Simultaneously, the emotion recognition module analyzes the user's facial expressions and tone of voice to recognize emotions such as anxiety or impatience.

[0480] Input: Text information entered by the user and real-time sentiment data (facial expressions and voice).

[0481] Output: Activity information and analyzed sentiment information.

[0482] Step 2:

[0483] The terminal's data transmission module sends the input activity information and emotion information to the server.

[0484] Specific action: The device encrypts and sends the following data to the server via the network: "Child A's estimated arrival time at school: 8:30 AM" and "User's emotional state: Anxious."

[0485] Input: Activity information and sentiment information.

[0486] Output: Activity and sentiment information sent to the server.

[0487] Step 3:

[0488] The server's data receiving module receives data sent from the terminal and saves it to the database.

[0489] Specific operation: The server analyzes the received data and writes "Child A's estimated arrival time at school: 8:30 AM" and "User's emotional state: Anxious" to the database.

[0490] Input: Received activity and sentiment information.

[0491] Output: Activity and sentiment information stored in the database.

[0492] Step 4:

[0493] The server's analysis module analyzes stored activity and emotion information to detect singular behaviors and anomalies.

[0494] Specific operation: The server executes a script that cross-checks activity information and sentiment data in the database. For example, it might refer to the school's GPS data and detect that child A has not arrived at school by 8:45 AM, and that the user's sentiment state is anxious.

[0495] Input: Activity and sentiment information from the database.

[0496] Output: Detected singular behaviors or anomalies.

[0497] Step 5:

[0498] The server's alert generation module generates alerts based on anomaly and sentiment analysis results and sends them to the client application.

[0499] Specific operation: When the server detects an anomaly, the alert generation module generates a message stating, "Child A has not arrived at school." Furthermore, considering the user's emotional state of anxiety, the alert content is adjusted to encourage a quicker response.

[0500] Input: Detected anomalies and sentiment analysis results.

[0501] Output: Alert message.

[0502] Step 6:

[0503] The terminal's alert receiving module receives alerts from the server, and the alert notification module notifies the user.

[0504] Specific action: The device uses push notifications to display a pop-up alert to the user stating, "Child A has not arrived at school." The user can view detailed information when they open the app.

[0505] Input: Alert message sent from the server.

[0506] Output: Alert notification to the user.

[0507] Step 7:

[0508] Users input activity information and health status of elderly individuals using a client application. During input, an emotion recognition module analyzes the user's emotions in real time.

[0509] Specific operation: When the user inputs "walking distance" or "meal contents," the emotion recognition module analyzes their facial expressions and tone of voice to determine, for example, an emotional state such as "feeling at ease."

[0510] Input: Activity and emotional information of elderly individuals.

[0511] Output: Activity information including sentiment analysis results.

[0512] Step 8:

[0513] The server's data receiving module receives activity and emotion information sent from the terminal and stores it in the database.

[0514] Specific operation: The server saves information such as "elderly person B's walking distance and diet" and "user's emotional state: feeling safe" to the database.

[0515] Input: Activity and emotional information of elderly individuals transmitted from their devices.

[0516] Output: Activity and sentiment information stored in the database.

[0517] Step 9:

[0518] The server's health assessment module analyzes stored data to evaluate its health status. It also adjusts the suggested solutions based on the sentiment analysis results.

[0519] Specific operation: The server compares the current data with past data, assesses that "elderly person B is not getting enough exercise," and generates health maintenance suggestions that provide reassurance, such as "a 30-minute walk per day is recommended."

[0520] Input: Activity information and sentiment analysis results from the database.

[0521] Output: Health assessment results and recommendations.

[0522] Step 10:

[0523] The server's health suggestion module generates health maintenance suggestions based on the evaluation results and sends them to the user's terminal.

[0524] Specific operation: The server generates specific suggestions, such as "We recommend taking a 30-minute walk every day," and sends them to the terminal via the network.

[0525] Input: Evaluation results and proposed content.

[0526] Output: Health maintenance suggestions sent to the terminal.

[0527] Step 11:

[0528] The device receives the suggestion and notifies the user.

[0529] Specific action: The device will use a notification sound and vibration to display a pop-up message to the user recommending a 30-minute walk each day, and will provide a link to more information.

[0530] Input: Health maintenance suggestions sent from the server.

[0531] Output: Suggestion notification to the user.

[0532] (Application Example 2)

[0533] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as a "server" and the smart device 14 as a "terminal".

[0534] Conventional emotion recognition systems often had low accuracy and were unable to provide appropriate alerts or suggestions because they analyzed activity information without considering the user's emotional state, thus failing to detect anomalies or abnormalities. Furthermore, in areas such as worker safety management and improving work efficiency in factories, they were unable to provide appropriate measures quickly by considering emotional states.

[0535] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0536] In this invention, the server includes means for analyzing the user's emotional state in real time using an emotion recognition algorithm, means for adjusting the analysis results and alert content based on the emotional state, and means for adjusting the suggested content based on the emotional state. This enables highly accurate anomaly detection, appropriate alert notifications, and suggestions for improving work efficiency, all while taking the user's emotional state into consideration.

[0537] A "user" is defined as the entity that uses this system, inputs activity information, and receives real-time sentiment analysis based on that information.

[0538] "Activity information" refers to data about the user's daily actions and tasks, which is received and analyzed by the server.

[0539] A "server" is a central system that receives activity information and emotional state data, stores and analyzes it in a database, and performs anomaly detection and suggestion generation.

[0540] A "database" is a storage device that stores activity information and emotion information received within a server.

[0541] "Singular behavior" refers to behavior that deviates from normal activity patterns and is a sign of abnormality or a problem.

[0542] An "anomaly" is a state in which singular behavior or risks are detected, and it is a situation that requires users to be alerted or take action.

[0543] An "alert" is a warning notification generated based on detected anomalies, prompting users to take safety measures and responses.

[0544] A "client application" is application software installed on a user's terminal that allows for the input of activity information, the reception of alerts, and the display of sentiment analysis results.

[0545] An "emotion recognition algorithm" is an algorithm that analyzes a user's facial expressions and voice data to determine their emotional state in real time.

[0546] "Emotional state" refers to the user's psychological state as analyzed by an emotion recognition algorithm, and is used to adjust content and generate suggestions.

[0547] A "suggestion" is a recommended action or advice generated by the server and notified to the user for purposes such as maintaining health or improving work efficiency.

[0548] "Real-time" refers to a state where the entire process, from data collection to analysis and notification, is carried out immediately, without any delay.

[0549] This invention is a system aimed at improving worker safety management and work efficiency within a factory, and its specific embodiments are described below. The main hardware and software used, as well as the data processing and calculation methods, will be explained.

[0550] System Configuration

[0551] hardware

[0552] User device: Smart glasses (e.g., Google Glass®)

[0553] Server: A central computer for data processing and storage (e.g., AWS, Google Cloud)

[0554] software

[0555] Emotion Recognition Algorithm: Uses Face API and Emotion SDK to analyze the user's emotional state in real time.

[0556] Data analysis platform: Data analysis and anomaly detection are performed using TENSORFLOW® and Scikit-learn.

[0557] Specific processing flow

[0558] 1. Data Collection

[0559] User terminal: While the worker is wearing the smart glasses, the built-in camera and microphone are used to analyze facial expressions and voice. The collected data is then analyzed in real time by an emotion recognition algorithm to determine the emotional state.

[0560] Specific example: When a worker begins welding, smart glasses recognize their level of fatigue and analyze it as an emotional state of "fatigue."

[0561] 2. Data transmission

[0562] User terminal: Emotional data and work information are sent to the server using the HTTPS protocol.

[0563] Specific example: The worker's emotional state is "fatigued," and this environmental data is sent to the server.

[0564] 3. Data reception and storage

[0565] Server: Receives the transmitted data and saves it to the database.

[0566] Specific example: The server's database stores "worker A's fatigue status" and "environmental data".

[0567] 4. Data Analysis

[0568] Server: Uses analytical platforms such as TensorFlow and Scikit-learn to analyze collected data and detect singular behavior and anomalies.

[0569] Specific example: The server references other sensor data (e.g., temperature sensor data or machine operating status) to detect that a worker is fatigued in a high-temperature environment.

[0570] 5. Generate and send alerts

[0571] Server: Generates alert content based on detected risks and emotional states, and sends it to the user's terminal.

[0572] Specific example: The server generates and sends an alert stating, "You are experiencing fatigue due to the high-temperature environment. Please rest in a safe place."

[0573] 6. Alert notifications

[0574] User terminal: Uses the smart glasses API to notify workers of visual and audible alerts.

[0575] Specific example: A pop-up appears on a worker's smart glasses saying, "You are experiencing fatigue due to the high-temperature environment. Please rest in a safe place."

[0576] Adding specific examples

[0577] Example of a prompt

[0578] Prompt: Based on the following data, assess the fatigue level and generate an appropriate alert:

[0579] Worker A's facial expression data: [Specific values ​​of facial expression data]

[0580] Voice data from worker A: [Specific values ​​of the voice data]

[0581] Environmental data (temperature, humidity, noise level, etc.): [Specific values ​​for environmental data]

[0582] Work details: Welding work

[0583] Specific examples

[0584] Facial expression data for worker A: "Heaviness in the eyes", "Frown lines between the eyebrows"

[0585] Audio data from worker A: "Low voice tone"

[0586] Environmental data (temperature, humidity, noise level, etc.): "Temperature: 35℃, Humidity: 60%, Noise level: 85dB"

[0587] Work details: Welding work

[0588] Example Output

[0589] "Worker A is experiencing fatigue due to the high-temperature environment. Please take a rest."

[0590] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0591] Step 1:

[0592] Data collection

[0593] The user device (smart glasses) uses its built-in camera and microphone to collect facial expressions and voice while the worker is wearing it. This data is analyzed in real time by emotion recognition algorithms (e.g., Face API, Emotion SDK) to determine the worker's emotional state.

[0594] Input: Facial expression data, audio data

[0595] Data processing: An emotion recognition algorithm analyzes the input data and identifies the emotional state.

[0596] Output: Emotional state (e.g., fatigue, anxiety)

[0597] Step 2:

[0598] Data transmission

[0599] The user terminal sends the analyzed emotion data and work information to the server using the HTTPS protocol.

[0600] Input: Emotional state data, work information

[0601] Data processing: Data packaging and encryption

[0602] Output: Transmit data packet

[0603] Specific operation: A transmission module inside the smart glasses sends data to the server.

[0604] Step 3:

[0605] Data reception and storage

[0606] The server receives the transmitted data and stores it in the database. This process includes data verification and format conversion.

[0607] Input: Transmit data packet

[0608] Data processing: Data decoding and format conversion

[0609] Output: Saved emotional state data, work information

[0610] Specific operation: The server's receiving module receives data and stores it in the database.

[0611] Step 4:

[0612] Data Analysis

[0613] The server uses TensorFlow and Scikit-learn to analyze the stored data and detect singular behavior and anomalies.

[0614] Input: Saved emotional state data, work information

[0615] Data processing: Anomaly detection using machine learning models

[0616] Output: Anomaly detection results

[0617] Specific operation: The server's analysis module runs a machine learning model to detect anomalies and other issues.

[0618] Step 5:

[0619] Alert generation and sending

[0620] The server generates an alert based on the detected anomaly and sends the alert content to the user's terminal. It also takes the user's emotional state into consideration when adjusting the alert content.

[0621] Input: Anomaly detection results, emotional state data

[0622] Data processing: Generating alert content and adjusting it based on emotional state.

[0623] Output: Alert notification data

[0624] Specific operation: The server's alert generation module generates an alert, and the transmission module sends it to the user's terminal.

[0625] Step 6:

[0626] Alert notification

[0627] The user terminal notifies the worker of received alerts visually and audibly.

[0628] Input: Alert notification data

[0629] Data processing: Decoding and formatting of alert data.

[0630] Output: Visual and audio notifications

[0631] Specific operation: The smart glasses' notification module displays an alert and also provides audio output.

[0632] The above outlines the specific processing flow of the system that implements the application example. This enables highly accurate anomaly detection and alert notification based on the user's emotional state.

[0633] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0634] Data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0635] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart device 14.

[0636] [Second Embodiment]

[0637] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0638] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0639] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0640] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0641] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0642] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0643] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0644] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0645] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0646] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0647] In the smart glasses 214, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0648] Next, the identification processing performed by the identification processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0649] This invention relates to a system for managing activity information and providing alert notifications related to childcare and elderly care, and in particular to providing means for detecting unusual behaviors and abnormal health conditions and responding to them quickly.

[0650] This system operates by having users input activity information, which is then collected, stored, and analyzed on a server. A specific implementation of the system is shown below.

[0651] System Configuration

[0652] 1. User terminal

[0653] Data entry interface: An interface for users to input activity information. Examples include smartphone and tablet apps.

[0654] Data transmission module: A module that sends the entered activity information to the server.

[0655] Alert receiving module: A module for receiving alerts from the server.

[0656] Alert notification module: A module that notifies the user of received alerts.

[0657] 2. Server

[0658] Data receiving module: Receives activity information sent from the user's terminal.

[0659] Database: Stores received activity information.

[0660] Analysis Module: Analyzes and detects anomalies and singular behaviors based on stored data.

[0661] Alert generation module: Based on the analysis results, it generates alerts as needed and sends them to the user's terminal.

[0662] Health suggestion module: Generates health maintenance suggestions in care mode.

[0663] Program execution flow

[0664] The system's processing flow is explained in detail below.

[0665] Data collection

[0666] User: Enters activity information through the data input interface on the user's terminal. For example, they might enter the estimated arrival time of a child at school or information about meals and exercise for elderly people.

[0667] Example: The user enters "Child A is scheduled to arrive at school at 8:30."

[0668] Data transmission

[0669] Terminal: Sends the entered activity information to the server via the data transmission module.

[0670] Specific example: The device sends data to the server that says, "Child A's estimated arrival time at school: 8:30 AM."

[0671] Data reception and storage

[0672] Server: The data receiving module receives the transmitted data and saves it to the database.

[0673] Specific example: The server saves the data "Child A's estimated arrival time at school: 8:30 AM" to the database.

[0674] Data Analysis

[0675] Server: Based on the data stored by the analysis module, it performs analysis to detect singular behaviors and anomalies.

[0676] Specific example: The server detects that child A has not arrived at school by 8:45 AM and determines that this is an anomaly.

[0677] Alert generation and sending

[0678] Server: Based on the detected anomaly, the alert generation module generates an alert and sends it to the user's terminal.

[0679] Specific example: The server generates an alert stating "Child A has not arrived at school" and sends it to the terminal.

[0680] Alert notification

[0681] Terminal: The alert receiving module receives alerts from the server, and the alert notification module notifies the user.

[0682] Specific example: The device notifies the user via a pop-up alert stating, "Child A has not arrived at school."

[0683] Health assessment and suggestions for caregiving mode

[0684] Data collection and transmission

[0685] User: Enters activity information and health status of elderly individuals into the client application.

[0686] Terminal: The data transmission module sends this information to the server.

[0687] Specific example: The user inputs information such as "walking distance" and "meal details," and the device sends this information to the server.

[0688] Data reception and storage

[0689] Server: The data receiving module receives this information and stores it in the database.

[0690] Health assessment and recommendations

[0691] Server: Analyzes data stored in the health assessment module and evaluates health status.

[0692] Server: Based on the evaluation results in the health suggestion module, it generates specific suggestions for maintaining health and sends them to the user's terminal.

[0693] Specific example: The server suggests to elderly person B that they "take a 30-minute walk every day," and the terminal notifies the user of this.

[0694] This allows the system to centrally manage important activity information related to childcare and elder care in real time, enabling it to detect unusual behaviors and anomalies and respond quickly. Furthermore, in elder care mode, it can contribute to the user's health management by assessing their health status and suggesting appropriate health maintenance measures.

[0695] The following describes the processing flow.

[0696] Step 1:

[0697] User: Enter activity information using the data entry interface of the client application.

[0698] As a concrete example, the user enters "Child A's expected arrival time at school is 8:30 AM."

[0699] Step 2:

[0700] Terminal: Sends the entered activity information to the server via the data transmission module.

[0701] For example, the device sends data to the server such as "Child A's estimated arrival time at school: 8:30 AM".

[0702] Step 3:

[0703] Server: Receives data sent from the terminal using the data receiving module.

[0704] As a concrete example, the server receives data that says "Child A's estimated arrival time at school: 8:30 AM".

[0705] Step 4:

[0706] Server: Saves received data to the database.

[0707] As a concrete example, the data received by the server is stored in a database.

[0708] Step 5:

[0709] Server: Uses analysis modules to analyze stored data and detect anomalies and outlier behaviors.

[0710] As a concrete example, the server references the school's GPS data and time clock records and detects that child A has not arrived at school by 8:45.

[0711] Step 6:

[0712] Server: When singular behavior or anomalies are detected, the alert generation module generates an alert.

[0713] As a concrete example, the server generates an alert stating, "Child A has not arrived at school."

[0714] Step 7:

[0715] Server: Sends generated alerts to the client application.

[0716] As a concrete example, the server sends an alert to the terminal stating, "Child A has not arrived at school."

[0717] Step 8:

[0718] Terminal: The alert receiving module receives alerts sent from the server.

[0719] As a concrete example, the device receives an alert stating, "Child A has not arrived at school."

[0720] Step 9:

[0721] Terminal: Notifies the user of alerts received by the alert notification module.

[0722] As a concrete example, a pop-up notification appears on the user's smartphone stating, "Child A has not arrived at school."

[0723] Health assessment and suggestions for caregiving mode

[0724] Step 1:

[0725] User: Use the client application to input activity information and health status of elderly individuals.

[0726] As a concrete example, you can input information such as the elderly person's "walking distance" and "dietary content."

[0727] Step 2:

[0728] Terminal: Sends the entered information to the server.

[0729] As a specific example, the terminal sends information such as "elderly person B's walking distance and dietary content" to the server.

[0730] Step 3:

[0731] Server: Receives information sent by the data receiving module and stores it in the database.

[0732] As a concrete example, the server stores information such as "elderly person B's walking distance and diet" in a database.

[0733] Step 4:

[0734] Server: Analyzes data received by the health assessment module and evaluates the health status.

[0735] As a concrete example, the server compares current data with past data and concludes that "elderly person B is not getting enough exercise."

[0736] Step 5:

[0737] Server: The health suggestion module generates health maintenance suggestions based on the evaluation results.

[0738] As a concrete example, the server might generate a suggestion such as "We recommend taking a 30-minute walk every day."

[0739] Step 6:

[0740] Server: Sends the generated proposals to the client application.

[0741] As a concrete example, the server sends a suggestion to the terminal saying, "We recommend taking a 30-minute walk every day."

[0742] Step 7:

[0743] Terminal: Receives proposals and notifies the user.

[0744] For example, a notification such as "We recommend taking a 30-minute walk every day" might appear on the user's smartphone.

[0745] In this way, this system smoothly handles the entire process from user input to data collection, analysis, alert generation, and notification, enabling a rapid response to unusual behaviors and abnormal health conditions in childcare and elder care.

[0746] (Example 1)

[0747] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0748] Managing activity information in childcare and elder care is time-consuming and labor-intensive, and delays in recording information and detecting anomalies are a challenge. In particular, the lack of means to detect unusual behaviors or abnormal health conditions early and respond quickly means that users may not be able to take action promptly, leading to problems becoming more serious. Furthermore, in elder care, there is a need to appropriately assess the health status of the elderly and propose appropriate health maintenance measures, but there is a lack of systems to do so.

[0749] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0750] In this invention, the server includes means for collecting activity information entered by the user, means for transmitting the activity information to the server, means for the server to receive the activity information and store it in a database, means for the server to analyze the stored activity information and detect singular behaviors or anomalies, means for the server to generate alerts based on the detected anomalies and send them to a client application, means for the terminal to notify the user of the received alerts, and means for the server to use a health suggestion module to generate health maintenance suggestions in care mode and send them to a client application. This enables centralized management of childcare and caregiving activity information, rapid detection of singular behaviors or anomalies and generation of alerts, and further enables health assessment of the elderly and appropriate health maintenance suggestions in care mode.

[0751] A "user" is someone who uses the system to input activity information and receive alerts and suggestions.

[0752] "Activity information" refers to data about actions and situations related to childcare and elder care.

[0753] A "server" is a device that receives, stores, and analyzes activity information sent by users, and generates alerts and suggestions.

[0754] A "database" is a storage method used by a server to store activity information it has received.

[0755] An "analysis module" is a software component that analyzes information stored in a database to detect anomalies and unusual behavior.

[0756] An "alert generation module" is a software component that generates alerts based on anomalies detected by the analysis module.

[0757] A "client application" is application software that runs on a user's terminal and is used by the user to input activity information and receive alerts and suggestions from the server.

[0758] A "device" refers to a device used by a user, such as a smartphone or tablet.

[0759] The "Health Suggestion Module" is a software component that, in care mode, performs a health assessment based on saved activity information and generates suggestions for maintaining health.

[0760] This invention relates to a system for managing activity information and providing alert notifications related to childcare and elderly care, and in particular to providing means for detecting unusual behaviors and abnormal health conditions and responding quickly. Specific embodiments of the system are shown below.

[0761] System Configuration

[0762] 1. User terminal

[0763] Data entry interface: This is an interface for users to input activity information. Smartphone apps and tablet apps fall into this category.

[0764] Data transmission module: This module transmits the input activity information to the server.

[0765] Alert receiving module: This module is used to receive alerts from the server.

[0766] Alert notification module: This module notifies the user of received alerts.

[0767] 2. Server

[0768] Data receiving module: This module receives activity information sent from the user's terminal.

[0769] Database: A storage device for saving received activity information.

[0770] Analysis Module: A software component used to detect anomalies and outliers based on stored data.

[0771] Alert generation module: This is a software component that generates alerts as needed based on analysis results and sends them to the user's terminal.

[0772] Health Suggestion Module: This is a software component for generating health maintenance suggestions in caregiving mode.

[0773] Explanation of the program's processing

[0774] Data collection

[0775] User: Manually inputs childcare and eldercare activity information through a smartphone or tablet application. For example, inputting the estimated arrival time of a child at school or information on meals and exercise for the elderly.

[0776] Data transmission

[0777] Terminal: Uses a data transmission module to send the entered activity information to the server using an HTTP request.

[0778] Data reception and storage

[0779] Server: The data receiving module receives the transmitted data and saves it to a database such as MySQL.

[0780] Data Analysis

[0781] Server: The analysis module uses information stored in the database to perform analysis to detect singular behaviors and anomalies. Statistical methods and machine learning models are frequently used in this analysis.

[0782] Alert generation and sending

[0783] Server: Based on the anomaly detected by the alert generation module, an alert is generated and sent to the user terminal via an HTTP POST request.

[0784] Alert notification

[0785] Terminal: The alert receiving module receives alerts sent from the server, and the alert notification module notifies the user of these alerts via pop-up or push notifications.

[0786] Health assessment and suggestions for caregiving mode

[0787] Data collection and transmission

[0788] User: Input activity information and health status of elderly individuals into the client application. For example, input information such as walking distance and dietary details.

[0789] Terminal: Uses a data transmission module to send this information to the server.

[0790] Data reception and storage

[0791] Server: The data receiving module receives this information and stores it in the database.

[0792] Health assessment and recommendations

[0793] Server: The health assessment module analyzes the stored data and evaluates the user's health status. Subsequently, the health suggestion module generates appropriate health maintenance suggestions based on the assessment results and sends them to the user's terminal.

[0794] Specific examples and prompt statements

[0795] Specific example

[0796] A user uses a smartphone app to input "Child A is scheduled to arrive at school at 8:30." This data is sent to a server, and an analysis module detects that Child A has not arrived at school at 8:45, generates an alert stating "Child A has not arrived at school," and sends it to the user's device.

[0797] Example of a prompt

[0798] "I would like an alert to be issued and I to be notified if my child has not arrived at school."

[0799] This allows the system to manage activity information related to childcare and elderly care in real time, quickly detect and notify of abnormalities in health conditions, and also provide concrete suggestions for maintaining the health of the elderly.

[0800] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0801] Step 1: Enter activity information

[0802] User: Enters information about activities related to childcare and elder care. Specifically, the user accesses an application on their smartphone or tablet and manually enters information such as "Child A is scheduled to arrive at school at 8:30" and "Breakfast for the elderly: Salad and fruit."

[0803] Input: Activity information such as "Child A is scheduled to arrive at school at 8:30."

[0804] Output: Activity information entered into the user's terminal.

[0805] Step 2: Submit the input data

[0806] Terminal: Uses a data transmission module to send the entered activity information to the server. Specifically, the terminal generates an HTTP POST request and sends the data to the server.

[0807] Input: Activity information entered into the user's terminal.

[0808] Output: Activity information received by the server.

[0809] Step 3: Data reception and storage

[0810] Server: The data receiving module receives the transmitted data and stores it in the database. Specifically, the server parses the received HTTP POST request and stores the data in the MySQL database.

[0811] Input: Activity information sent from the device.

[0812] Output: Activity information stored in the database.

[0813] Step 4: Data Analysis

[0814] Server: The analysis module detects singular behavior and anomalies based on the stored data. Specifically, the server analyzes the data using statistical methods and machine learning models to detect anomalies.

[0815] Input: Activity information stored in the database.

[0816] Data processing / computation: Analysis using statistical methods and machine learning models.

[0817] Output: Detection results of singular behaviors and anomalies.

[0818] Step 5: Generate and send alerts

[0819] Server: Based on the anomalies detected by the alert generation module, the server generates an alert and sends it to the user terminal. Specifically, the server generates an alert message and sends it to the user terminal again using an HTTP POST request.

[0820] Input: Results of detecting singular behavior or anomalies.

[0821] Output: An alert sent to the user's terminal.

[0822] Step 6: Alert Notification

[0823] Terminal: The alert receiving module receives alerts from the server, and the alert notification module notifies the user. Specifically, the terminal generates pop-up notifications or push notifications to inform the user.

[0824] Input: Alert sent from the server.

[0825] Output: An alert sent to the user.

[0826] Step 7: Health assessment and recommendations for care mode

[0827] Data collection and transmission

[0828] User: Enters activity information and health status of elderly individuals into the client application. For example, "Today's walking distance: 5000 steps," "Breakfast: Salad and fruit," etc.

[0829] Terminal: The data transmission module sends this information to the server. Specifically, the terminal sends the input data to the server using an HTTP POST request.

[0830] Input: Activity information and health status of elderly individuals.

[0831] Output: Health information received by the server.

[0832] Data reception and storage

[0833] Server: The data receiving module receives this information and stores it in the database. Specifically, the server parses the received HTTP POST request and stores the data in the database.

[0834] Input: Health information sent from the device.

[0835] Output: Health information stored in the database.

[0836] Health assessment and recommendations

[0837] Server: The health assessment module analyzes the stored data and evaluates the user's health status. Subsequently, the health suggestion module generates appropriate health maintenance suggestions based on the evaluation results and sends them to the user's terminal. Specifically, the server analyzes the data, makes evaluations such as "total daily walking distance is below the recommended value," generates suggestions such as "30 minutes of walking per day is recommended," and sends them to the user's terminal using an HTTP POST request.

[0838] Input: Health information stored in the database.

[0839] Data processing / calculation: Analysis using health assessment algorithms.

[0840] Output: Health suggestions sent to the user's terminal.

[0841] (Application Example 1)

[0842] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0843] In modern society, there is a need to efficiently manage activity information related to childcare and elder care, and to quickly detect and respond to unusual behaviors and abnormal health conditions. However, conventional systems have difficulty collecting real-time location information and situational data, which can lead to delays in responding to abnormalities. Furthermore, they lack mechanisms to provide users with appropriate recommended actions when abnormalities are detected. Therefore, there is a need for a comprehensive system that enables safe and rapid responses.

[0844] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0845] In this invention, the server includes means for collecting activity information entered by the user, means for transmitting the activity information to the server, means for the server to receive the activity information and store it in a database, means for the server to analyze the stored activity information and detect singular behavior or anomalies, means for the server to generate an alert based on the detected anomaly and send it to the client application, means for the terminal to notify the user of the received alert, means for collecting location information and status data in real time and promptly providing alert notifications when an anomaly is detected, and means for generating recommended actions when an anomaly is detected and proposing them to the user. As a result, the user can monitor the location information and status data of family members and those they care for in real time and respond quickly when an anomaly occurs. In addition, appropriate recommended actions are provided for the detected anomaly, improving safety and health maintenance.

[0846] A "user" is an individual or organization that uses the system to input activity information and receive alerts and recommended actions.

[0847] "Activity information" refers to information such as the subject's location, daily behavior data, and health status.

[0848] A "server" is a central device that receives activity information sent by users, stores it in a database, and analyzes it to detect anomalies and abnormalities.

[0849] A "client application" is software installed on a user's terminal that receives data and alerts from a server and notifies the user of that information.

[0850] A "database" is an information processing system used by a server to store activity information it has received.

[0851] "Singular behavior" refers to abnormal behavior that deviates from normal behavioral patterns, and it is through such behavior that abnormalities are detected.

[0852] An "anomaly" is an event that deviates from the normal behavior or state of a user or subject, and an alert is generated based on the detection of such an anomaly.

[0853] An "alert" is a warning message sent to a user when unusual behavior or anomalies are detected.

[0854] "Recommended actions" are specific suggestions of what the user should do in response to detected anomalies.

[0855] "Location information" refers to data that indicates the current location of a user or subject, and is necessary information for real-time monitoring.

[0856] "Status data" refers to all information that represents the state of a user or subject, including but not limited to location information.

[0857] This "Family Safety Monitoring & Alert System" is a comprehensive system that monitors the location and status data of family members and those receiving care in real time, and enables rapid response when an anomaly is detected. The specific implementation of the system is shown below.

[0858] System Configuration

[0859] 1. User terminal

[0860] Data entry interface: An interface for users to input activity information. Smartphone and tablet apps fall into this category.

[0861] Data transmission module: A module that sends the entered activity information to the server.

[0862] Alert receiving module: A module for receiving alerts from the server.

[0863] Alert notification module: A module that notifies the user of received alerts.

[0864] 2. Server

[0865] Data receiving module: Receives activity information sent from the user's terminal.

[0866] Database: Stores received activity information.

[0867] Analysis Module: Analyzes and detects singular behaviors and anomalies based on stored data. Uses scikit-learn for data analysis.

[0868] Alert generation module: Based on analysis results, it generates alerts as needed and sends them to the user's device. Firebase Cloud Messaging (FCM) is used to send alerts.

[0869] Health suggestion module: Generates recommended actions when an anomaly is detected and suggests them to the user.

[0870] Program Processing Description

[0871] This system uses Python, AWS Lambda, AWS DynamoDB, Flutter, scikit-learn, and Firebase Cloud Messaging (FCM) as its main hardware and software components.

[0872] Data collection

[0873] User: Enters activity information through the data input interface on the user's terminal. For example, they might enter the estimated arrival time of a child at school or information about meals and exercise for elderly people.

[0874] Example: The user enters "Child A is scheduled to arrive at school at 8:30."

[0875] Data transmission

[0876] Terminal: Sends the entered activity information to the server via the data transmission module.

[0877] Specific example: The device sends data to the server that says, "Child A's estimated arrival time at school: 8:30 AM."

[0878] Data reception and storage

[0879] Server: The data receiving module receives the transmitted data and stores it in AWS DynamoDB.

[0880] Specific example: The server saves the data "Child A's estimated arrival time at school: 8:30 AM" to the database.

[0881] Data Analysis

[0882] Server: Uses scikit-learn to perform analysis on stored data to detect singular behaviors and anomalies.

[0883] Specific example: The server detects that child A has not arrived at school by 8:45 AM and determines that this is an anomaly.

[0884] Alert generation and sending

[0885] Server: Based on the detected anomaly, the alert generation module uses FCM to generate an alert and sends it to the user terminal.

[0886] Specific example: The server generates an alert stating "Child A has not arrived at school" and sends it to the terminal.

[0887] Alert notification

[0888] Terminal: The alert receiving module receives alerts from the server, and the alert notification module notifies the user.

[0889] Specific example: The device notifies the user via a pop-up alert stating, "Child A has not arrived at school."

[0890] Recommended Actions

[0891] Server: Generates specific recommended actions to address detected anomalies and sends them to the user's terminal.

[0892] Specific example: The server generates a recommended action, "Child A is late arriving at school. Please contact the school immediately," and sends it to the device.

[0893] Example of a prompt

[0894] text

[0895] User ID: 12345, Activity Information: 'Child is expected to arrive at the park at 5 PM', Current Time: '5:30 PM'

[0896] This system allows users to efficiently and quickly monitor the safety and health of their family members and take immediate, appropriate action when an abnormality occurs.

[0897] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0898] Step 1:

[0899] Data collection

[0900] Users input activity information through a data entry interface on their smartphone or tablet app. The data includes location information, scheduled times, and details of activities. For example, a user might input, "Child A is scheduled to arrive at school at 8:30." This information is entered into the device and processed by a data transmission module.

[0901] Input: User activity information (location, scheduled time, activity details)

[0902] Output: Information input to the data transmission module within the terminal.

[0903] Step 2:

[0904] Data transmission

[0905] The terminal uses a data transmission module to send the entered activity information to the server via the internet. For example, the terminal sends the data "Child A's estimated arrival time at school: 8:30" to the server. This operation transfers the activity information to the server.

[0906] Input: Information entered into the data transmission module within the device.

[0907] Output: Information sent to the server's data receiving module.

[0908] Step 3:

[0909] Data reception and storage

[0910] The server uses a data receiving module to receive activity information sent from the user terminal and stores it in the database. For example, the server stores the data "Child A's estimated arrival time at school: 8:30" in the database.

[0911] Input: Information sent to the server's data receiving module.

[0912] Output: Activity information stored in the database

[0913] Step 4:

[0914] Data Analysis

[0915] The server uses scikit-learn to analyze stored data to detect anomalies and outliers. For example, the server detects that child A has not arrived at school by 8:45 AM and identifies this as an anomaly. Machine learning algorithms are used for anomaly detection, analyzing patterns based on past data.

[0916] Input: Activity information stored in the database

[0917] Output: Anomaly detection results (singular behavior, anomaly)

[0918] Step 5:

[0919] Alert generation and sending

[0920] The server generates an alert using an alert generation module based on the detected anomaly and sends it to the user's device using Firebase Cloud Messaging (FCM). Specifically, the server generates an alert stating "Child A has not arrived at school" and sends it to the device.

[0921] Input: Anomaly detection result

[0922] Output: Alert message

[0923] Step 6:

[0924] Alert notification

[0925] The user's device receives alerts from the server using an alert receiving module, and then notifies the user via a pop-up display or audio notification using an alert notification module. Specifically, the device notifies the user of an alert stating that "Child A has not arrived at school."

[0926] Input: Alert message sent from FCM

[0927] Output: Alert notification (pop-up display, audio notification)

[0928] Step 7:

[0929] Recommended Actions

[0930] The server generates specific recommended actions to address the detected anomaly and sends them to the user's terminal. For example, the server might generate and send the recommended action, "Child A is late arriving at school. Please contact the school immediately."

[0931] Input: Anomaly detection result (singular behavior, anomaly)

[0932] Output: Recommended action message

[0933] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0934] This invention relates to a childcare and elderly care support system that combines an emotion engine that recognizes user emotions, and provides a means for rapidly detecting singular behaviors and abnormal health conditions and providing appropriate alerts to the user.

[0935] In addition to collecting and managing activity information entered by users, this system uses an emotion engine to recognize the user's emotional state, enabling more accurate analysis and alert generation.

[0936] System Configuration

[0937] 1. User terminal

[0938] Data entry interface: An interface for users to input activity information. Examples include smartphone and tablet apps.

[0939] Data transmission module: A module that sends the entered activity information to the server.

[0940] Alert receiving module: A module for receiving alerts from the server.

[0941] Alert notification module: A module that notifies the user of received alerts.

[0942] Emotion Recognition Module: A module that uses an emotion engine to analyze the user's emotions in real time as they input data.

[0943] 2. Server

[0944] Data receiving module: Receives activity information sent from the user's terminal.

[0945] Database: Stores received activity and sentiment information.

[0946] Analysis Module: Analyzes and detects anomalies and singular behaviors based on stored data.

[0947] Alert generation module: Based on the analysis results, it generates alerts as needed and sends them to the user's terminal.

[0948] Health suggestion module: Generates health maintenance suggestions in care mode.

[0949] Emotion Analysis Module: Uses an emotion engine to perform data analysis based on the results of user emotion analysis.

[0950] Program execution flow

[0951] The system's processing flow is explained in detail below.

[0952] Data collection

[0953] User: Activity information is entered through the client application's data entry interface. Additionally, an emotion recognition module analyzes the user's emotions in real time during the input process.

[0954] Specific example: A user enters "Child A's expected arrival time at school is 8:30 AM," and the user's emotions (e.g., anxiety, impatience) are analyzed at that time.

[0955] Data transmission

[0956] Terminal: Sends input activity and emotion information to the server via a data transmission module.

[0957] Specific example: The device sends data to the server: "Child A's estimated arrival time at school: 8:30 AM" and "User's emotional state: Anxious."

[0958] Data reception and storage

[0959] Server: The data receiving module receives data sent from the terminal and stores it in the database.

[0960] Specific example: The server saves the following data to the database: "Child A's estimated arrival time at school: 8:30 AM" and "User's emotional state: Anxious."

[0961] Data Analysis

[0962] Server: Uses the analysis module to perform analysis based on stored activity information and sentiment analysis results to detect singular behaviors and anomalies.

[0963] Specific example: The server references the school's GPS data and time clock information, detects that child A has not arrived at school by 8:45 AM, and that the user's emotional state is "anxious," and determines that this is an anomaly.

[0964] Alert generation and sending

[0965] Server: When singular behavior or anomalies are detected, the alert generation module generates an alert. The alert content is also adjusted based on the sentiment analysis results.

[0966] Specific example: The server generates an alert stating "Child A has not arrived at school," and considering the user's emotional state of anxiety, the alert is modified to encourage a more prompt response.

[0967] Alert notification

[0968] Terminal: The alert receiving module receives alerts from the server, and the alert notification module notifies the user.

[0969] Specific example: The device notifies the user via a pop-up alert stating, "Child A has not arrived at school."

[0970] Health assessment and suggestions for caregiving mode

[0971] Data collection and transmission

[0972] User: Uses a client application to input activity information and health status of elderly individuals. During input, an emotion recognition module analyzes the user's emotions in real time.

[0973] Specific example: Users input information such as "walking distance" and "meal content," and their emotional state (e.g., feeling safe, satisfied) is analyzed at that time.

[0974] Data reception and storage

[0975] Server: Receives activity and emotion information sent by the data receiving module and stores it in the database.

[0976] Specific example: The server stores information such as "elderly person B's walking distance and diet" and "user's emotional state: feeling safe" in a database.

[0977] Health assessment and recommendations

[0978] Server: Analyzes data stored in the health assessment module to evaluate health status. It also adjusts suggestions based on the emotion analysis results.

[0979] Specific example: The server compares past data and assesses that "elderly person B is not getting enough exercise," and since their emotional state is "reassured," it generates more proactive exercise suggestions.

[0980] Proposal submission and notification

[0981] Server: The health suggestion module generates health maintenance suggestions based on the evaluation results and sends them to the user's terminal.

[0982] Terminal: Receives proposals and notifies the user.

[0983] Specific example: The server generates a suggestion such as "We recommend taking a 30-minute walk every day," and the device notifies the user of this.

[0984] In this way, by combining this system with an emotion engine, it becomes possible to provide more accurate alert notifications and suggestions that take into account the user's emotional state, enabling the management of important activity information in childcare and elder care and prompt responses.

[0985] The following describes the processing flow.

[0986] Step 1:

[0987] User: Enters activity information using the client application's data entry interface. Simultaneously, the emotion recognition module analyzes the user's emotions in real time as they are being entered.

[0988] For example, a user might enter "Child A's expected arrival time at school is 8:30 AM," and the user's emotional state (e.g., anxiety, impatience) is then analyzed.

[0989] Step 2:

[0990] Terminal: Sends input activity and emotion information to the server via a data transmission module.

[0991] As a specific example, the device sends data to the server such as "Child A's estimated arrival time at school is 8:30" and "User's emotional state: Anxious."

[0992] Step 3:

[0993] Server: Receives data sent from the terminal using the data receiving module.

[0994] As a specific example, the server receives data indicating "Child A's estimated arrival time at school is 8:30 AM" and "User's emotional state: Anxious."

[0995] Step 4:

[0996] Server: Saves received data to the database.

[0997] As a concrete example, the server stores the data it receives, "Child A's estimated arrival time at school: 8:30 AM" and "User's emotional state: Anxious," into a database.

[0998] Step 5:

[0999] Server: Uses the analysis module to perform analysis based on stored activity information and sentiment analysis results to detect singular behaviors and anomalies.

[1000] As a specific example, the server refers to the school's GPS data and time clock information, detects that child A has not arrived at school by 8:45 AM, and that the user's emotional state is "anxious," and determines that this is an anomaly.

[1001] Step 6:

[1002] Server: When singular behavior or anomalies are detected, the alert generation module generates an alert. The alert content is also adjusted based on the sentiment analysis results.

[1003] As a concrete example, the server generates an alert stating "Child A has not arrived at school," and considering the user's emotional state of anxiety, the alert is designed to prompt a more rapid response.

[1004] Step 7:

[1005] Server: Sends generated alerts to the client application.

[1006] As a concrete example, the server sends an alert to the terminal stating, "Child A has not arrived at school."

[1007] Step 8:

[1008] Terminal: The alert receiving module receives alerts from the server.

[1009] As a concrete example, the device receives an alert stating, "Child A has not arrived at school."

[1010] Step 9:

[1011] Terminal: Notifies the user of alerts received by the alert notification module.

[1012] As a concrete example, a pop-up notification appears on the user's smartphone stating, "Child A has not arrived at school."

[1013] Health assessment and suggestions for caregiving mode

[1014] Step 1:

[1015] User: Uses a client application to input activity information and health status of elderly individuals. Simultaneously, an emotion recognition module analyzes the user's emotions in real time as they input data.

[1016] As a concrete example, users input information such as "walking distance" and "meal content," and their emotional state (e.g., feeling safe, satisfied) is analyzed at that time.

[1017] Step 2:

[1018] Terminal: Sends the entered information to the server.

[1019] As a specific example, the device sends information such as "elderly person B's walking distance and diet" and "user's emotional state: feeling safe" to the server.

[1020] Step 3:

[1021] Server: Receives information sent by the data receiving module and stores it in the database.

[1022] As a specific example, the server stores information such as "elderly person B's walking distance and diet" and "user's emotional state: feeling secure" in a database.

[1023] Step 4:

[1024] Server: Analyzes data stored in the health assessment module to evaluate health status. It also adjusts suggestions based on the emotion analysis results.

[1025] As a concrete example, the server compares past data and evaluates that "elderly person B is not getting enough exercise," and since their emotional state is "reassured," it generates more proactive exercise suggestions.

[1026] Step 5:

[1027] Server: The health suggestion module generates health maintenance suggestions based on the evaluation results and sends them to the user's terminal.

[1028] As a concrete example, the server generates a suggestion such as "We recommend taking a 30-minute walk every day" and sends it to the terminal.

[1029] Step 6:

[1030] Terminal: Receives proposals and notifies the user.

[1031] For example, a notification such as "We recommend taking a 30-minute walk every day" might appear on the user's smartphone.

[1032] In this way, by combining this system with an emotion engine, it becomes possible to provide more accurate alert notifications and suggestions that take into account the user's emotional state, enabling the management of important activity information in childcare and elder care and prompt responses.

[1033] (Example 2)

[1034] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[1035] Conventional childcare and eldercare support systems collect and analyze activity information without considering the user's emotional state, resulting in low accuracy in detecting anomalies and abnormalities, and a failure to provide appropriate alerts and suggestions. In addition, because emotional information is not utilized, responses to users are uniform, making it difficult to provide appropriate responses tailored to individual situations.

[1036] The identification processing by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for collecting activity information and emotion information input by the user; means for transmitting the activity information and emotion information to the server; means for the server to receive the activity information and emotion information and store it in a database; means for the server to analyze the stored activity information and emotion information and detect singular behavior or anomalies; means for the server to generate an alert based on the detected anomalies and emotion analysis results and send it to the client application; and means for the terminal to notify the user of the alert received. This enables highly accurate alert notifications and suggestions that take into account the user's emotional state.

[1037] A "user" refers to an individual who inputs activity and emotional information into the system.

[1038] "Activity information" refers to information about daily activities and events that users input into the system.

[1039] "Emotional information" refers to data that analyzes a user's emotional state in real time.

[1040] A "server" refers to the core of a system that receives, stores, and analyzes activity and sentiment information, generates alerts and suggestions, and sends them to client applications.

[1041] A "database" refers to a storage device used to store received activity and emotional information.

[1042] An "analysis module" refers to software used to detect anomalies or anomalies based on stored data.

[1043] An "alert generation module" refers to software that has the function of generating alerts based on the detection of anomalies and the results of sentiment analysis.

[1044] A "client application" refers to an application on a device that a user uses to input activity and sentiment information and to receive alerts and suggestions.

[1045] "Care mode" refers to the operating mode of a system that evaluates the activity information and health status of elderly people and makes suggestions for maintaining their health.

[1046] A "health assessment module" refers to software that evaluates health status based on stored activity and emotional information and generates recommendations.

[1047] This invention is a system intended to support childcare and elder care, and incorporates an emotion engine that recognizes the user's emotions. This system can quickly detect unusual behaviors and abnormal health conditions, and provide the user with appropriate alerts and suggestions.

[1048] System Configuration

[1049] 1. User terminal

[1050] Data entry interface: An interface for users to input activity information. Examples include smartphone and tablet apps.

[1051] Data transmission module: A module that transmits input activity and emotion information to the server.

[1052] Alert receiving module: A module for receiving alerts from the server.

[1053] Alert notification module: A module that notifies the user of received alerts.

[1054] Emotion Recognition Module: A module that uses an emotion engine to analyze the user's emotions in real time as they input data.

[1055] 2. Server

[1056] Data receiving module: Receives activity and emotion information sent from the user's terminal.

[1057] Database: Stores received activity and sentiment information.

[1058] Analysis Module: Analyzes and detects anomalies and singular behaviors based on stored data.

[1059] Alert generation module: Based on the analysis results, it generates alerts as needed and sends them to the user's terminal.

[1060] Health suggestion module: Generates health maintenance suggestions in care mode.

[1061] Emotion Analysis Module: Uses an emotion engine to perform data analysis based on the results of user emotion analysis.

[1062] Specific examples of program processing

[1063] User: Enters activity information through the client application's data entry interface. During input, the emotion recognition module analyzes the user's emotions in real time.

[1064] Specific example: A user enters "Child A's expected arrival time at school is 8:30 AM." At this time, the user's emotions (e.g., anxiety or impatience) are analyzed.

[1065] Terminal: Sends activity and emotion information entered via the data transmission module to the server.

[1066] Specific example: The device sends data to the server: "Child A's estimated arrival time at school: 8:30 AM" and "User's emotional state: Anxious."

[1067] Server: The data receiving module receives data sent from the terminal and stores it in the database.

[1068] Specific example: The server saves the following data to the database: "Child A's estimated arrival time at school: 8:30 AM" and "User's emotional state: Anxious."

[1069] Server: Uses an analysis module to detect singular behaviors and anomalies based on stored activity information and sentiment analysis results.

[1070] Specific example: The server checks the school's GPS data and time clock information, detects that child A has not arrived at school by 8:45 AM, and also detects that the user's emotional state is "anxious," and determines that this is an anomaly.

[1071] Server: When singular behavior or anomalies are detected, the alert generation module generates an alert and adjusts the content of the alert considering the sentiment analysis results.

[1072] Specific example: The server generates an alert stating "Child A has not arrived at school," and considering the user's emotional state of anxiety, the alert is modified to encourage a more prompt response.

[1073] Terminal: The alert receiving module receives alerts from the server, and the alert notification module notifies the user.

[1074] Specific example: The device notifies the user via a pop-up alert stating, "Child A has not arrived at school."

[1075] Specific examples of health assessment and recommendations for caregiving.

[1076] User: Uses a client application to input activity information and health status of elderly individuals. During input, an emotion recognition module analyzes emotions in real time.

[1077] Specific example: When a user enters information such as "walking distance" or "meal content," their emotions (e.g., feeling safe or satisfied) are analyzed.

[1078] Server: Receives activity and emotion information sent by the data receiving module and stores it in the database.

[1079] Specific example: The server stores information such as "elderly person B's walking distance and diet" and "user's emotional state: feeling safe" in a database.

[1080] Server: Analyzes data stored in the health assessment module and evaluates health status. Adjusts suggestions based on the emotion analysis results.

[1081] Specific example: The server compares data with past data and assesses that "elderly person B is not getting enough exercise," and based on their emotional state being "reassured," it generates more proactive exercise suggestions.

[1082] Server: The health suggestion module generates health maintenance suggestions based on the evaluation results and sends them to the user's terminal.

[1083] Terminal: Receives proposals and notifies the user.

[1084] Specific example: The server generates a suggestion such as "We recommend taking a 30-minute walk every day," and the device notifies the user of this.

[1085] Example prompts for a generative AI model

[1086] Example prompt: "Describe a system that takes input information about daily activities related to childcare or elder care (e.g., a child's arrival time at school or the elderly person's meals), performs real-time sentiment recognition, and generates appropriate alerts or suggestions if anomalies are detected."

[1087] The flow of the specific processing in Example 2 will be explained using Figure 13.

[1088] Step 1:

[1089] Users input activity and emotion information through the data entry interface of the client application. This allows for real-time recording of the user's activity and emotion data.

[1090] Specific operation: The user opens a smartphone app and enters "Child A's estimated arrival time at school: 8:30." Simultaneously, the emotion recognition module analyzes the user's facial expressions and tone of voice to recognize emotions such as anxiety or impatience.

[1091] Input: Text information entered by the user and real-time sentiment data (facial expressions and voice).

[1092] Output: Activity information and analyzed sentiment information.

[1093] Step 2:

[1094] The terminal's data transmission module sends the input activity information and emotion information to the server.

[1095] Specific action: The device encrypts and sends the following data to the server via the network: "Child A's estimated arrival time at school: 8:30 AM" and "User's emotional state: Anxious."

[1096] Input: Activity information and sentiment information.

[1097] Output: Activity and sentiment information sent to the server.

[1098] Step 3:

[1099] The server's data receiving module receives data sent from the terminal and saves it to the database.

[1100] Specific operation: The server analyzes the received data and writes "Child A's estimated arrival time at school: 8:30 AM" and "User's emotional state: Anxious" to the database.

[1101] Input: Received activity and sentiment information.

[1102] Output: Activity and sentiment information stored in the database.

[1103] Step 4:

[1104] The server's analysis module analyzes stored activity and emotion information to detect singular behaviors and anomalies.

[1105] Specific operation: The server executes a script that cross-checks activity information and sentiment data in the database. For example, it might refer to the school's GPS data and detect that child A has not arrived at school by 8:45 AM, and that the user's sentiment state is anxious.

[1106] Input: Activity and sentiment information from the database.

[1107] Output: Detected singular behaviors or anomalies.

[1108] Step 5:

[1109] The server's alert generation module generates alerts based on anomaly and sentiment analysis results and sends them to the client application.

[1110] Specific operation: When the server detects an anomaly, the alert generation module generates a message stating, "Child A has not arrived at school." Furthermore, considering the user's emotional state of anxiety, the alert content is adjusted to encourage a quicker response.

[1111] Input: Detected anomalies and sentiment analysis results.

[1112] Output: Alert message.

[1113] Step 6:

[1114] The terminal's alert receiving module receives alerts from the server, and the alert notification module notifies the user.

[1115] Specific action: The device uses push notifications to display a pop-up alert to the user stating, "Child A has not arrived at school." The user can view detailed information when they open the app.

[1116] Input: Alert message sent from the server.

[1117] Output: Alert notification to the user.

[1118] Step 7:

[1119] Users input activity information and health status of elderly individuals using a client application. During input, an emotion recognition module analyzes the user's emotions in real time.

[1120] Specific operation: When the user inputs "walking distance" or "meal contents," the emotion recognition module analyzes their facial expressions and tone of voice to determine, for example, an emotional state such as "feeling at ease."

[1121] Input: Activity and emotional information of elderly individuals.

[1122] Output: Activity information including sentiment analysis results.

[1123] Step 8:

[1124] The server's data receiving module receives activity and emotion information sent from the terminal and stores it in the database.

[1125] Specific operation: The server saves information such as "elderly person B's walking distance and diet" and "user's emotional state: feeling safe" to the database.

[1126] Input: Activity and emotional information of elderly individuals transmitted from their devices.

[1127] Output: Activity and sentiment information stored in the database.

[1128] Step 9:

[1129] The server's health assessment module analyzes stored data to evaluate its health status. It also adjusts the suggested solutions based on the sentiment analysis results.

[1130] Specific operation: The server compares the current data with past data, assesses that "elderly person B is not getting enough exercise," and generates health maintenance suggestions that provide reassurance, such as "a 30-minute walk per day is recommended."

[1131] Input: Activity information and sentiment analysis results from the database.

[1132] Output: Health assessment results and recommendations.

[1133] Step 10:

[1134] The server's health suggestion module generates health maintenance suggestions based on the evaluation results and sends them to the user's terminal.

[1135] Specific operation: The server generates specific suggestions, such as "We recommend taking a 30-minute walk every day," and sends them to the terminal via the network.

[1136] Input: Evaluation results and proposed content.

[1137] Output: Health maintenance suggestions sent to the terminal.

[1138] Step 11:

[1139] The device receives the suggestion and notifies the user.

[1140] Specific action: The device will use a notification sound and vibration to display a pop-up message to the user recommending a 30-minute walk each day, and will provide a link to more information.

[1141] Input: Health maintenance suggestions sent from the server.

[1142] Output: Suggestion notification to the user.

[1143] (Application Example 2)

[1144] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[1145] Conventional emotion recognition systems often had low accuracy and were unable to provide appropriate alerts or suggestions because they analyzed activity information without considering the user's emotional state, thus failing to detect anomalies or abnormalities. Furthermore, in areas such as worker safety management and improving work efficiency in factories, they were unable to provide appropriate measures quickly by considering emotional states.

[1146] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[1147] In this invention, the server includes means for analyzing the user's emotional state in real time using an emotion recognition algorithm, means for adjusting the analysis results and alert content based on the emotional state, and means for adjusting the suggested content based on the emotional state. This enables highly accurate anomaly detection, appropriate alert notifications, and suggestions for improving work efficiency, all while taking the user's emotional state into consideration.

[1148] A "user" is defined as the entity that uses this system, inputs activity information, and receives real-time sentiment analysis based on that information.

[1149] "Activity information" refers to data about the user's daily actions and tasks, which is received and analyzed by the server.

[1150] A "server" is a central system that receives activity information and emotional state data, stores and analyzes it in a database, and performs anomaly detection and suggestion generation.

[1151] A "database" is a storage device that stores activity information and emotion information received within a server.

[1152] "Singular behavior" refers to behavior that deviates from normal activity patterns and is a sign of abnormality or a problem.

[1153] An "anomaly" is a state in which singular behavior or risks are detected, and it is a situation that requires users to be alerted or take action.

[1154] An "alert" is a warning notification generated based on detected anomalies, prompting users to take safety measures and responses.

[1155] A "client application" is application software installed on a user's terminal that allows for the input of activity information, the reception of alerts, and the display of sentiment analysis results.

[1156] An "emotion recognition algorithm" is an algorithm that analyzes a user's facial expressions and voice data to determine their emotional state in real time.

[1157] "Emotional state" refers to the user's psychological state as analyzed by an emotion recognition algorithm, and is used to adjust content and generate suggestions.

[1158] A "suggestion" is a recommended action or advice generated by the server and notified to the user for purposes such as maintaining health or improving work efficiency.

[1159] "Real-time" refers to a state where the entire process, from data collection to analysis and notification, is carried out immediately, without any delay.

[1160] This invention is a system aimed at improving worker safety management and work efficiency within a factory, and its specific embodiments are described below. The main hardware and software used, as well as the data processing and calculation methods, will be explained.

[1161] System Configuration

[1162] hardware

[1163] User device: Smart glasses (e.g., Google Glass)

[1164] Server: A central computer for data processing and storage (e.g., AWS, Google Cloud)

[1165] software

[1166] Emotion Recognition Algorithm: Uses Face API and Emotion SDK to analyze the user's emotional state in real time.

[1167] Data analysis platform: Uses TensorFlow and Scikit-learn to analyze data and detect anomalies.

[1168] Specific processing flow

[1169] 1. Data Collection

[1170] User terminal: While the worker is wearing the smart glasses, the built-in camera and microphone are used to analyze facial expressions and voice. The collected data is then analyzed in real time by an emotion recognition algorithm to determine the emotional state.

[1171] Specific example: When a worker begins welding, smart glasses recognize their level of fatigue and analyze it as an emotional state of "fatigue."

[1172] 2. Data transmission

[1173] User terminal: Emotional data and work information are sent to the server using the HTTPS protocol.

[1174] Specific example: The worker's emotional state is "fatigued," and this environmental data is sent to the server.

[1175] 3. Data reception and storage

[1176] Server: Receives the transmitted data and saves it to the database.

[1177] Specific example: The server's database stores "worker A's fatigue status" and "environmental data".

[1178] 4. Data Analysis

[1179] Server: Uses analytical platforms such as TensorFlow and Scikit-learn to analyze collected data and detect singular behavior and anomalies.

[1180] Specific example: The server references other sensor data (e.g., temperature sensor data or machine operating status) to detect that a worker is fatigued in a high-temperature environment.

[1181] 5. Generate and send alerts

[1182] Server: Generates alert content based on detected risks and emotional states, and sends it to the user's terminal.

[1183] Specific example: The server generates and sends an alert stating, "You are experiencing fatigue due to the high-temperature environment. Please rest in a safe place."

[1184] 6. Alert notifications

[1185] User terminal: Uses the smart glasses API to notify workers of visual and audible alerts.

[1186] Specific example: A pop-up appears on a worker's smart glasses saying, "You are experiencing fatigue due to the high-temperature environment. Please rest in a safe place."

[1187] Adding specific examples

[1188] Example of a prompt

[1189] Prompt: Based on the following data, assess the fatigue level and generate an appropriate alert:

[1190] Worker A's facial expression data: [Specific values ​​of facial expression data]

[1191] Voice data from worker A: [Specific values ​​of the voice data]

[1192] Environmental data (temperature, humidity, noise level, etc.): [Specific values ​​for environmental data]

[1193] Work details: Welding work

[1194] Specific examples

[1195] Facial expression data for worker A: "Heaviness in the eyes", "Frown lines between the eyebrows"

[1196] Audio data from worker A: "Low voice tone"

[1197] Environmental data (temperature, humidity, noise level, etc.): "Temperature: 35℃, Humidity: 60%, Noise level: 85dB"

[1198] Work details: Welding work

[1199] Example Output

[1200] "Worker A is experiencing fatigue due to the high-temperature environment. Please take a rest."

[1201] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[1202] Step 1:

[1203] Data collection

[1204] The user device (smart glasses) uses its built-in camera and microphone to collect facial expressions and voice while the worker is wearing it. This data is analyzed in real time by emotion recognition algorithms (e.g., Face API, Emotion SDK) to determine the worker's emotional state.

[1205] Input: Facial expression data, audio data

[1206] Data processing: An emotion recognition algorithm analyzes the input data and identifies the emotional state.

[1207] Output: Emotional state (e.g., fatigue, anxiety)

[1208] Step 2:

[1209] Data transmission

[1210] The user terminal sends the analyzed emotion data and work information to the server using the HTTPS protocol.

[1211] Input: Emotional state data, work information

[1212] Data processing: Data packaging and encryption

[1213] Output: Transmit data packet

[1214] Specific operation: A transmission module inside the smart glasses sends data to the server.

[1215] Step 3:

[1216] Data reception and storage

[1217] The server receives the transmitted data and stores it in the database. This process includes data verification and format conversion.

[1218] Input: Transmit data packet

[1219] Data processing: Data decoding and format conversion

[1220] Output: Saved emotional state data, work information

[1221] Specific operation: The server's receiving module receives data and stores it in the database.

[1222] Step 4:

[1223] Data Analysis

[1224] The server uses TensorFlow and Scikit-learn to analyze the stored data and detect singular behavior and anomalies.

[1225] Input: Saved emotional state data, work information

[1226] Data processing: Anomaly detection using machine learning models

[1227] Output: Anomaly detection results

[1228] Specific operation: The server's analysis module runs a machine learning model to detect anomalies and other issues.

[1229] Step 5:

[1230] Alert generation and sending

[1231] The server generates an alert based on the detected anomaly and sends the alert content to the user's terminal. It also takes the user's emotional state into consideration when adjusting the alert content.

[1232] Input: Anomaly detection results, emotional state data

[1233] Data processing: Generating alert content and adjusting it based on emotional state.

[1234] Output: Alert notification data

[1235] Specific operation: The server's alert generation module generates an alert, and the transmission module sends it to the user's terminal.

[1236] Step 6:

[1237] Alert notification

[1238] The user terminal notifies the worker of received alerts visually and audibly.

[1239] Input: Alert notification data

[1240] Data processing: Decoding and formatting of alert data.

[1241] Output: Visual and audio notifications

[1242] Specific operation: The smart glasses' notification module displays an alert and also provides audio output.

[1243] The above outlines the specific processing flow of the system that implements the application example. This enables highly accurate anomaly detection and alert notification based on the user's emotional state.

[1244] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[1245] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1246] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart glasses 214.

[1247] [Third Embodiment]

[1248] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[1249] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[1250] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1251] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[1252] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[1253] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[1254] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[1255] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[1256] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[1257] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1258] In the headset terminal 314, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[1259] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the headset terminal 314 will be referred to as the "terminal".

[1260] This invention relates to a system for managing activity information and providing alert notifications related to childcare and elderly care, and in particular to providing means for detecting unusual behaviors and abnormal health conditions and responding to them quickly.

[1261] This system operates by having users input activity information, which is then collected, stored, and analyzed on a server. A specific implementation of the system is shown below.

[1262] System Configuration

[1263] 1. User terminal

[1264] Data entry interface: An interface for users to input activity information. Examples include smartphone and tablet apps.

[1265] Data transmission module: A module that sends the entered activity information to the server.

[1266] Alert receiving module: A module for receiving alerts from the server.

[1267] Alert notification module: A module that notifies the user of received alerts.

[1268] 2. Server

[1269] Data receiving module: Receives activity information sent from the user's terminal.

[1270] Database: Stores received activity information.

[1271] Analysis Module: Analyzes and detects anomalies and singular behaviors based on stored data.

[1272] Alert generation module: Based on the analysis results, it generates alerts as needed and sends them to the user's terminal.

[1273] Health suggestion module: Generates health maintenance suggestions in care mode.

[1274] Program execution flow

[1275] The system's processing flow is explained in detail below.

[1276] Data collection

[1277] User: Enters activity information through the data input interface on the user's terminal. For example, they might enter the estimated arrival time of a child at school or information about meals and exercise for elderly people.

[1278] Example: The user enters "Child A is scheduled to arrive at school at 8:30."

[1279] Data transmission

[1280] Terminal: Sends the entered activity information to the server via the data transmission module.

[1281] Specific example: The device sends data to the server that says, "Child A's estimated arrival time at school: 8:30 AM."

[1282] Data reception and storage

[1283] Server: The data receiving module receives the transmitted data and saves it to the database.

[1284] Specific example: The server saves the data "Child A's estimated arrival time at school: 8:30 AM" to the database.

[1285] Data Analysis

[1286] Server: Based on the data stored by the analysis module, it performs analysis to detect singular behaviors and anomalies.

[1287] Specific example: The server detects that child A has not arrived at school by 8:45 AM and determines that this is an anomaly.

[1288] Alert generation and sending

[1289] Server: Based on the detected anomaly, the alert generation module generates an alert and sends it to the user's terminal.

[1290] Specific example: The server generates an alert stating "Child A has not arrived at school" and sends it to the terminal.

[1291] Alert notification

[1292] Terminal: The alert receiving module receives alerts from the server, and the alert notification module notifies the user.

[1293] Specific example: The device notifies the user via a pop-up alert stating, "Child A has not arrived at school."

[1294] Health assessment and suggestions for caregiving mode

[1295] Data collection and transmission

[1296] User: Enters activity information and health status of elderly individuals into the client application.

[1297] Terminal: The data transmission module sends this information to the server.

[1298] Specific example: The user inputs information such as "walking distance" and "meal details," and the device sends this information to the server.

[1299] Data reception and storage

[1300] Server: The data receiving module receives this information and stores it in the database.

[1301] Health assessment and recommendations

[1302] Server: Analyzes data stored in the health assessment module and evaluates health status.

[1303] Server: Based on the evaluation results in the health suggestion module, it generates specific suggestions for maintaining health and sends them to the user's terminal.

[1304] Specific example: The server suggests to elderly person B that they "take a 30-minute walk every day," and the terminal notifies the user of this.

[1305] This allows the system to centrally manage important activity information related to childcare and elder care in real time, enabling it to detect unusual behaviors and anomalies and respond quickly. Furthermore, in elder care mode, it can contribute to the user's health management by assessing their health status and suggesting appropriate health maintenance measures.

[1306] The following describes the processing flow.

[1307] Step 1:

[1308] User: Enter activity information using the data entry interface of the client application.

[1309] As a concrete example, the user enters "Child A's expected arrival time at school is 8:30 AM."

[1310] Step 2:

[1311] Terminal: Sends the entered activity information to the server via the data transmission module.

[1312] For example, the device sends data to the server such as "Child A's estimated arrival time at school: 8:30 AM".

[1313] Step 3:

[1314] Server: Receives data sent from the terminal using the data receiving module.

[1315] As a concrete example, the server receives data that says "Child A's estimated arrival time at school: 8:30 AM".

[1316] Step 4:

[1317] Server: Saves received data to the database.

[1318] As a concrete example, the data received by the server is stored in a database.

[1319] Step 5:

[1320] Server: Uses analysis modules to analyze stored data and detect anomalies and outlier behaviors.

[1321] As a concrete example, the server references the school's GPS data and time clock records and detects that child A has not arrived at school by 8:45.

[1322] Step 6:

[1323] Server: When singular behavior or anomalies are detected, the alert generation module generates an alert.

[1324] As a concrete example, the server generates an alert stating, "Child A has not arrived at school."

[1325] Step 7:

[1326] Server: Sends generated alerts to the client application.

[1327] As a concrete example, the server sends an alert to the terminal stating, "Child A has not arrived at school."

[1328] Step 8:

[1329] Terminal: The alert receiving module receives alerts sent from the server.

[1330] As a concrete example, the device receives an alert stating, "Child A has not arrived at school."

[1331] Step 9:

[1332] Terminal: Notifies the user of alerts received by the alert notification module.

[1333] As a concrete example, a pop-up notification appears on the user's smartphone stating, "Child A has not arrived at school."

[1334] Health assessment and suggestions for caregiving mode

[1335] Step 1:

[1336] User: Use the client application to input activity information and health status of elderly individuals.

[1337] As a concrete example, you can input information such as the elderly person's "walking distance" and "dietary content."

[1338] Step 2:

[1339] Terminal: Sends the entered information to the server.

[1340] As a specific example, the terminal sends information such as "elderly person B's walking distance and dietary content" to the server.

[1341] Step 3:

[1342] Server: Receives information sent by the data receiving module and stores it in the database.

[1343] As a concrete example, the server stores information such as "elderly person B's walking distance and diet" in a database.

[1344] Step 4:

[1345] Server: Analyzes data received by the health assessment module and evaluates the health status.

[1346] As a concrete example, the server compares current data with past data and concludes that "elderly person B is not getting enough exercise."

[1347] Step 5:

[1348] Server: The health suggestion module generates health maintenance suggestions based on the evaluation results.

[1349] As a concrete example, the server might generate a suggestion such as "We recommend taking a 30-minute walk every day."

[1350] Step 6:

[1351] Server: Sends the generated proposals to the client application.

[1352] As a concrete example, the server sends a suggestion to the terminal saying, "We recommend taking a 30-minute walk every day."

[1353] Step 7:

[1354] Terminal: Receives proposals and notifies the user.

[1355] For example, a notification such as "We recommend taking a 30-minute walk every day" might appear on the user's smartphone.

[1356] In this way, this system smoothly handles the entire process from user input to data collection, analysis, alert generation, and notification, enabling a rapid response to unusual behaviors and abnormal health conditions in childcare and elder care.

[1357] (Example 1)

[1358] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[1359] Managing activity information in childcare and elder care is time-consuming and labor-intensive, and delays in recording information and detecting anomalies are a challenge. In particular, the lack of means to detect unusual behaviors or abnormal health conditions early and respond quickly means that users may not be able to take action promptly, leading to problems becoming more serious. Furthermore, in elder care, there is a need to appropriately assess the health status of the elderly and propose appropriate health maintenance measures, but there is a lack of systems to do so.

[1360] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[1361] In this invention, the server includes means for collecting activity information entered by the user, means for transmitting the activity information to the server, means for the server to receive the activity information and store it in a database, means for the server to analyze the stored activity information and detect singular behaviors or anomalies, means for the server to generate alerts based on the detected anomalies and send them to a client application, means for the terminal to notify the user of the received alerts, and means for the server to use a health suggestion module to generate health maintenance suggestions in care mode and send them to a client application. This enables centralized management of childcare and caregiving activity information, rapid detection of singular behaviors or anomalies and generation of alerts, and further enables health assessment of the elderly and appropriate health maintenance suggestions in care mode.

[1362] A "user" is someone who uses the system to input activity information and receive alerts and suggestions.

[1363] "Activity information" refers to data about actions and situations related to childcare and elder care.

[1364] A "server" is a device that receives, stores, and analyzes activity information sent by users, and generates alerts and suggestions.

[1365] A "database" is a storage method used by a server to store activity information it has received.

[1366] An "analysis module" is a software component that analyzes information stored in a database to detect anomalies and unusual behavior.

[1367] An "alert generation module" is a software component that generates alerts based on anomalies detected by the analysis module.

[1368] A "client application" is application software that runs on a user's terminal and is used by the user to input activity information and receive alerts and suggestions from the server.

[1369] A "device" refers to a device used by a user, such as a smartphone or tablet.

[1370] The "Health Suggestion Module" is a software component that, in care mode, performs a health assessment based on saved activity information and generates suggestions for maintaining health.

[1371] This invention relates to a system for managing activity information and providing alert notifications related to childcare and elderly care, and in particular to providing means for detecting unusual behaviors and abnormal health conditions and responding quickly. Specific embodiments of the system are shown below.

[1372] System Configuration

[1373] 1. User terminal

[1374] Data entry interface: This is an interface for users to input activity information. Smartphone apps and tablet apps fall into this category.

[1375] Data transmission module: This module transmits the input activity information to the server.

[1376] Alert receiving module: This module is used to receive alerts from the server.

[1377] Alert notification module: This module notifies the user of received alerts.

[1378] 2. Server

[1379] Data receiving module: This module receives activity information sent from the user's terminal.

[1380] Database: A storage device for saving received activity information.

[1381] Analysis Module: A software component used to detect anomalies and outliers based on stored data.

[1382] Alert generation module: This is a software component that generates alerts as needed based on analysis results and sends them to the user's terminal.

[1383] Health Suggestion Module: This is a software component for generating health maintenance suggestions in caregiving mode.

[1384] Explanation of the program's processing

[1385] Data collection

[1386] User: Manually inputs childcare and eldercare activity information through a smartphone or tablet application. For example, inputting the estimated arrival time of a child at school or information on meals and exercise for the elderly.

[1387] Data transmission

[1388] Terminal: Uses a data transmission module to send the entered activity information to the server using an HTTP request.

[1389] Data reception and storage

[1390] Server: The data receiving module receives the transmitted data and saves it to a database such as MySQL.

[1391] Data Analysis

[1392] Server: The analysis module uses information stored in the database to perform analysis to detect singular behaviors and anomalies. Statistical methods and machine learning models are frequently used in this analysis.

[1393] Alert generation and sending

[1394] Server: Based on the anomaly detected by the alert generation module, an alert is generated and sent to the user terminal via an HTTP POST request.

[1395] Alert notification

[1396] Terminal: The alert receiving module receives alerts sent from the server, and the alert notification module notifies the user of these alerts via pop-up or push notifications.

[1397] Health assessment and suggestions for caregiving mode

[1398] Data collection and transmission

[1399] User: Input activity information and health status of elderly individuals into the client application. For example, input information such as walking distance and dietary details.

[1400] Terminal: Uses a data transmission module to send this information to the server.

[1401] Data reception and storage

[1402] Server: The data receiving module receives this information and stores it in the database.

[1403] Health assessment and recommendations

[1404] Server: The health assessment module analyzes the stored data and evaluates the user's health status. Subsequently, the health suggestion module generates appropriate health maintenance suggestions based on the assessment results and sends them to the user's terminal.

[1405] Specific examples and prompt statements

[1406] Specific example

[1407] A user uses a smartphone app to input "Child A is scheduled to arrive at school at 8:30." This data is sent to a server, and an analysis module detects that Child A has not arrived at school at 8:45, generates an alert stating "Child A has not arrived at school," and sends it to the user's device.

[1408] Example of a prompt

[1409] "I would like an alert to be issued and I to be notified if my child has not arrived at school."

[1410] This allows the system to manage activity information related to childcare and elderly care in real time, quickly detect and notify of abnormalities in health conditions, and also provide concrete suggestions for maintaining the health of the elderly.

[1411] The flow of the specific processing in Example 1 will be explained using Figure 11.

[1412] Step 1: Enter activity information

[1413] User: Enters information about activities related to childcare and elder care. Specifically, the user accesses an application on their smartphone or tablet and manually enters information such as "Child A is scheduled to arrive at school at 8:30" and "Breakfast for the elderly: Salad and fruit."

[1414] Input: Activity information such as "Child A is scheduled to arrive at school at 8:30."

[1415] Output: Activity information entered into the user's terminal.

[1416] Step 2: Submit the input data

[1417] Terminal: Uses a data transmission module to send the entered activity information to the server. Specifically, the terminal generates an HTTP POST request and sends the data to the server.

[1418] Input: Activity information entered into the user's terminal.

[1419] Output: Activity information received by the server.

[1420] Step 3: Data reception and storage

[1421] Server: The data receiving module receives the transmitted data and stores it in the database. Specifically, the server parses the received HTTP POST request and stores the data in the MySQL database.

[1422] Input: Activity information sent from the device.

[1423] Output: Activity information stored in the database.

[1424] Step 4: Data Analysis

[1425] Server: The analysis module detects singular behavior and anomalies based on the stored data. Specifically, the server analyzes the data using statistical methods and machine learning models to detect anomalies.

[1426] Input: Activity information stored in the database.

[1427] Data processing / computation: Analysis using statistical methods and machine learning models.

[1428] Output: Detection results of singular behaviors and anomalies.

[1429] Step 5: Generate and send alerts

[1430] Server: Based on the anomalies detected by the alert generation module, the server generates an alert and sends it to the user terminal. Specifically, the server generates an alert message and sends it to the user terminal again using an HTTP POST request.

[1431] Input: Results of detecting singular behavior or anomalies.

[1432] Output: An alert sent to the user's terminal.

[1433] Step 6: Alert Notification

[1434] Terminal: The alert receiving module receives alerts from the server, and the alert notification module notifies the user. Specifically, the terminal generates pop-up notifications or push notifications to inform the user.

[1435] Input: Alert sent from the server.

[1436] Output: An alert sent to the user.

[1437] Step 7: Health assessment and recommendations for care mode

[1438] Data collection and transmission

[1439] User: Enters activity information and health status of elderly individuals into the client application. For example, "Today's walking distance: 5000 steps," "Breakfast: Salad and fruit," etc.

[1440] Terminal: The data transmission module sends this information to the server. Specifically, the terminal sends the input data to the server using an HTTP POST request.

[1441] Input: Activity information and health status of elderly individuals.

[1442] Output: Health information received by the server.

[1443] Data reception and storage

[1444] Server: The data receiving module receives this information and stores it in the database. Specifically, the server parses the received HTTP POST request and stores the data in the database.

[1445] Input: Health information sent from the device.

[1446] Output: Health information stored in the database.

[1447] Health assessment and recommendations

[1448] Server: The health assessment module analyzes the stored data and evaluates the user's health status. Subsequently, the health suggestion module generates appropriate health maintenance suggestions based on the evaluation results and sends them to the user's terminal. Specifically, the server analyzes the data, makes evaluations such as "total daily walking distance is below the recommended value," generates suggestions such as "30 minutes of walking per day is recommended," and sends them to the user's terminal using an HTTP POST request.

[1449] Input: Health information stored in the database.

[1450] Data processing / calculation: Analysis using health assessment algorithms.

[1451] Output: Health suggestions sent to the user's terminal.

[1452] (Application Example 1)

[1453] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[1454] In modern society, there is a need to efficiently manage activity information related to childcare and elder care, and to quickly detect and respond to unusual behaviors and abnormal health conditions. However, conventional systems have difficulty collecting real-time location information and situational data, which can lead to delays in responding to abnormalities. Furthermore, they lack mechanisms to provide users with appropriate recommended actions when abnormalities are detected. Therefore, there is a need for a comprehensive system that enables safe and rapid responses.

[1455] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[1456] In this invention, the server includes means for collecting activity information entered by the user, means for transmitting the activity information to the server, means for the server to receive the activity information and store it in a database, means for the server to analyze the stored activity information and detect singular behavior or anomalies, means for the server to generate an alert based on the detected anomaly and send it to the client application, means for the terminal to notify the user of the received alert, means for collecting location information and status data in real time and promptly providing alert notifications when an anomaly is detected, and means for generating recommended actions when an anomaly is detected and proposing them to the user. As a result, the user can monitor the location information and status data of family members and those they care for in real time and respond quickly when an anomaly occurs. In addition, appropriate recommended actions are provided for the detected anomaly, improving safety and health maintenance.

[1457] A "user" is an individual or organization that uses the system to input activity information and receive alerts and recommended actions.

[1458] "Activity information" refers to information such as the subject's location, daily behavior data, and health status.

[1459] A "server" is a central device that receives activity information sent by users, stores it in a database, and analyzes it to detect anomalies and abnormalities.

[1460] A "client application" is software installed on a user's terminal that receives data and alerts from a server and notifies the user of that information.

[1461] A "database" is an information processing system used by a server to store activity information it has received.

[1462] "Singular behavior" refers to abnormal behavior that deviates from normal behavioral patterns, and it is through such behavior that abnormalities are detected.

[1463] An "anomaly" is an event that deviates from the normal behavior or state of a user or subject, and an alert is generated based on the detection of such an anomaly.

[1464] An "alert" is a warning message sent to a user when unusual behavior or anomalies are detected.

[1465] "Recommended actions" are specific suggestions of what the user should do in response to detected anomalies.

[1466] "Location information" refers to data that indicates the current location of a user or subject, and is necessary information for real-time monitoring.

[1467] "Status data" refers to all information that represents the state of a user or subject, including but not limited to location information.

[1468] This "Family Safety Monitoring & Alert System" is a comprehensive system that monitors the location and status data of family members and those receiving care in real time, and enables rapid response when an anomaly is detected. The specific implementation of the system is shown below.

[1469] System Configuration

[1470] 1. User terminal

[1471] Data entry interface: An interface for users to input activity information. Smartphone and tablet apps fall into this category.

[1472] Data transmission module: A module that sends the entered activity information to the server.

[1473] Alert receiving module: A module for receiving alerts from the server.

[1474] Alert notification module: A module that notifies the user of received alerts.

[1475] 2. Server

[1476] Data receiving module: Receives activity information sent from the user's terminal.

[1477] Database: Stores received activity information.

[1478] Analysis Module: Analyzes and detects singular behaviors and anomalies based on stored data. Uses scikit-learn for data analysis.

[1479] Alert generation module: Based on analysis results, it generates alerts as needed and sends them to the user's device. Firebase Cloud Messaging (FCM) is used to send alerts.

[1480] Health suggestion module: Generates recommended actions when an anomaly is detected and suggests them to the user.

[1481] Program Processing Description

[1482] This system uses Python, AWS Lambda, AWS DynamoDB, Flutter, scikit-learn, and Firebase Cloud Messaging (FCM) as its main hardware and software components.

[1483] Data collection

[1484] User: Enters activity information through the data input interface on the user's terminal. For example, they might enter the estimated arrival time of a child at school or information about meals and exercise for elderly people.

[1485] Example: The user enters "Child A is scheduled to arrive at school at 8:30."

[1486] Data transmission

[1487] Terminal: Sends the entered activity information to the server via the data transmission module.

[1488] Specific example: The device sends data to the server that says, "Child A's estimated arrival time at school: 8:30 AM."

[1489] Data reception and storage

[1490] Server: The data receiving module receives the transmitted data and stores it in AWS DynamoDB.

[1491] Specific example: The server saves the data "Child A's estimated arrival time at school: 8:30 AM" to the database.

[1492] Data Analysis

[1493] Server: Uses scikit-learn to perform analysis on stored data to detect singular behaviors and anomalies.

[1494] Specific example: The server detects that child A has not arrived at school by 8:45 AM and determines that this is an anomaly.

[1495] Alert generation and sending

[1496] Server: Based on the detected anomaly, the alert generation module uses FCM to generate an alert and sends it to the user terminal.

[1497] Specific example: The server generates an alert stating "Child A has not arrived at school" and sends it to the terminal.

[1498] Alert notification

[1499] Terminal: The alert receiving module receives alerts from the server, and the alert notification module notifies the user.

[1500] Specific example: The device notifies the user via a pop-up alert stating, "Child A has not arrived at school."

[1501] Recommended Actions

[1502] Server: Generates specific recommended actions to address detected anomalies and sends them to the user's terminal.

[1503] Specific example: The server generates a recommended action, "Child A is late arriving at school. Please contact the school immediately," and sends it to the device.

[1504] Example of a prompt

[1505] text

[1506] User ID: 12345, Activity Information: 'Child is expected to arrive at the park at 5 PM', Current Time: '5:30 PM'

[1507] This system allows users to efficiently and quickly monitor the safety and health of their family members and take immediate, appropriate action when an abnormality occurs.

[1508] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[1509] Step 1:

[1510] Data collection

[1511] Users input activity information through a data entry interface on their smartphone or tablet app. The data includes location information, scheduled times, and details of activities. For example, a user might input, "Child A is scheduled to arrive at school at 8:30." This information is entered into the device and processed by a data transmission module.

[1512] Input: User activity information (location, scheduled time, activity details)

[1513] Output: Information input to the data transmission module within the terminal.

[1514] Step 2:

[1515] Data transmission

[1516] The terminal uses a data transmission module to send the entered activity information to the server via the internet. For example, the terminal sends the data "Child A's estimated arrival time at school: 8:30" to the server. This operation transfers the activity information to the server.

[1517] Input: Information entered into the data transmission module within the device.

[1518] Output: Information sent to the server's data receiving module.

[1519] Step 3:

[1520] Data reception and storage

[1521] The server uses a data receiving module to receive activity information sent from the user terminal and stores it in the database. For example, the server stores the data "Child A's estimated arrival time at school: 8:30" in the database.

[1522] Input: Information sent to the server's data receiving module.

[1523] Output: Activity information stored in the database

[1524] Step 4:

[1525] Data Analysis

[1526] The server uses scikit-learn to analyze stored data to detect anomalies and outliers. For example, the server detects that child A has not arrived at school by 8:45 AM and identifies this as an anomaly. Machine learning algorithms are used for anomaly detection, analyzing patterns based on past data.

[1527] Input: Activity information stored in the database

[1528] Output: Anomaly detection results (singular behavior, anomaly)

[1529] Step 5:

[1530] Alert generation and sending

[1531] The server generates an alert using an alert generation module based on the detected anomaly and sends it to the user's device using Firebase Cloud Messaging (FCM). Specifically, the server generates an alert stating "Child A has not arrived at school" and sends it to the device.

[1532] Input: Anomaly detection result

[1533] Output: Alert message

[1534] Step 6:

[1535] Alert notification

[1536] The user's device receives alerts from the server using an alert receiving module, and then notifies the user via a pop-up display or audio notification using an alert notification module. Specifically, the device notifies the user of an alert stating that "Child A has not arrived at school."

[1537] Input: Alert message sent from FCM

[1538] Output: Alert notification (pop-up display, audio notification)

[1539] Step 7:

[1540] Recommended Actions

[1541] The server generates specific recommended actions to address the detected anomaly and sends them to the user's terminal. For example, the server might generate and send the recommended action, "Child A is late arriving at school. Please contact the school immediately."

[1542] Input: Anomaly detection result (singular behavior, anomaly)

[1543] Output: Recommended action message

[1544] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[1545] This invention relates to a childcare and elderly care support system that combines an emotion engine that recognizes user emotions, and provides a means for rapidly detecting singular behaviors and abnormal health conditions and providing appropriate alerts to the user.

[1546] In addition to collecting and managing activity information entered by users, this system uses an emotion engine to recognize the user's emotional state, enabling more accurate analysis and alert generation.

[1547] System Configuration

[1548] 1. User terminal

[1549] Data entry interface: An interface for users to input activity information. Examples include smartphone and tablet apps.

[1550] Data transmission module: A module that sends the entered activity information to the server.

[1551] Alert receiving module: A module for receiving alerts from the server.

[1552] Alert notification module: A module that notifies the user of received alerts.

[1553] Emotion Recognition Module: A module that uses an emotion engine to analyze the user's emotions in real time as they input data.

[1554] 2. Server

[1555] Data receiving module: Receives activity information sent from the user's terminal.

[1556] Database: Stores received activity and sentiment information.

[1557] Analysis Module: Analyzes and detects anomalies and singular behaviors based on stored data.

[1558] Alert generation module: Based on the analysis results, it generates alerts as needed and sends them to the user's terminal.

[1559] Health suggestion module: Generates health maintenance suggestions in care mode.

[1560] Emotion Analysis Module: Uses an emotion engine to perform data analysis based on the results of user emotion analysis.

[1561] Program execution flow

[1562] The system's processing flow is explained in detail below.

[1563] Data collection

[1564] User: Activity information is entered through the client application's data entry interface. Additionally, an emotion recognition module analyzes the user's emotions in real time during the input process.

[1565] Specific example: A user enters "Child A's expected arrival time at school is 8:30 AM," and the user's emotions (e.g., anxiety, impatience) are analyzed at that time.

[1566] Data transmission

[1567] Terminal: Sends input activity and emotion information to the server via a data transmission module.

[1568] Specific example: The device sends data to the server: "Child A's estimated arrival time at school: 8:30 AM" and "User's emotional state: Anxious."

[1569] Data reception and storage

[1570] Server: The data receiving module receives data sent from the terminal and stores it in the database.

[1571] Specific example: The server saves the following data to the database: "Child A's estimated arrival time at school: 8:30 AM" and "User's emotional state: Anxious."

[1572] Data Analysis

[1573] Server: Uses the analysis module to perform analysis based on stored activity information and sentiment analysis results to detect singular behaviors and anomalies.

[1574] Specific example: The server references the school's GPS data and time clock information, detects that child A has not arrived at school by 8:45 AM, and that the user's emotional state is "anxious," and determines that this is an anomaly.

[1575] Alert generation and sending

[1576] Server: When singular behavior or anomalies are detected, the alert generation module generates an alert. The alert content is also adjusted based on the sentiment analysis results.

[1577] Specific example: The server generates an alert stating "Child A has not arrived at school," and considering the user's emotional state of anxiety, the alert is modified to encourage a more prompt response.

[1578] Alert notification

[1579] Terminal: The alert receiving module receives alerts from the server, and the alert notification module notifies the user.

[1580] Specific example: The device notifies the user via a pop-up alert stating, "Child A has not arrived at school."

[1581] Health assessment and suggestions for caregiving mode

[1582] Data collection and transmission

[1583] User: Uses a client application to input activity information and health status of elderly individuals. During input, an emotion recognition module analyzes the user's emotions in real time.

[1584] Specific example: Users input information such as "walking distance" and "meal content," and their emotional state (e.g., feeling safe, satisfied) is analyzed at that time.

[1585] Data reception and storage

[1586] Server: Receives activity and emotion information sent by the data receiving module and stores it in the database.

[1587] Specific example: The server stores information such as "elderly person B's walking distance and diet" and "user's emotional state: feeling safe" in a database.

[1588] Health assessment and recommendations

[1589] Server: Analyzes data stored in the health assessment module to evaluate health status. It also adjusts suggestions based on the emotion analysis results.

[1590] Specific example: The server compares past data and assesses that "elderly person B is not getting enough exercise," and since their emotional state is "reassured," it generates more proactive exercise suggestions.

[1591] Proposal submission and notification

[1592] Server: The health suggestion module generates health maintenance suggestions based on the evaluation results and sends them to the user's terminal.

[1593] Terminal: Receives proposals and notifies the user.

[1594] Specific example: The server generates a suggestion such as "We recommend taking a 30-minute walk every day," and the device notifies the user of this.

[1595] In this way, by combining this system with an emotion engine, it becomes possible to provide more accurate alert notifications and suggestions that take into account the user's emotional state, enabling the management of important activity information in childcare and elder care and prompt responses.

[1596] The following describes the processing flow.

[1597] Step 1:

[1598] User: Enters activity information using the client application's data entry interface. Simultaneously, the emotion recognition module analyzes the user's emotions in real time as they are being entered.

[1599] For example, a user might enter "Child A's expected arrival time at school is 8:30 AM," and the user's emotional state (e.g., anxiety, impatience) is then analyzed.

[1600] Step 2:

[1601] Terminal: Sends input activity and emotion information to the server via a data transmission module.

[1602] As a specific example, the device sends data to the server such as "Child A's estimated arrival time at school is 8:30" and "User's emotional state: Anxious."

[1603] Step 3:

[1604] Server: Receives data sent from the terminal using the data receiving module.

[1605] As a specific example, the server receives data indicating "Child A's estimated arrival time at school is 8:30 AM" and "User's emotional state: Anxious."

[1606] Step 4:

[1607] Server: Saves received data to the database.

[1608] As a concrete example, the server stores the data it receives, "Child A's estimated arrival time at school: 8:30 AM" and "User's emotional state: Anxious," into a database.

[1609] Step 5:

[1610] Server: Uses the analysis module to perform analysis based on stored activity information and sentiment analysis results to detect singular behaviors and anomalies.

[1611] As a specific example, the server refers to the school's GPS data and time clock information, detects that child A has not arrived at school by 8:45 AM, and that the user's emotional state is "anxious," and determines that this is an anomaly.

[1612] Step 6:

[1613] Server: When singular behavior or anomalies are detected, the alert generation module generates an alert. The alert content is also adjusted based on the sentiment analysis results.

[1614] As a concrete example, the server generates an alert stating "Child A has not arrived at school," and considering the user's emotional state of anxiety, the alert is designed to prompt a more rapid response.

[1615] Step 7:

[1616] Server: Sends generated alerts to the client application.

[1617] As a concrete example, the server sends an alert to the terminal stating, "Child A has not arrived at school."

[1618] Step 8:

[1619] Terminal: The alert receiving module receives alerts from the server.

[1620] As a concrete example, the device receives an alert stating, "Child A has not arrived at school."

[1621] Step 9:

[1622] Terminal: Notifies the user of alerts received by the alert notification module.

[1623] As a concrete example, a pop-up notification appears on the user's smartphone stating, "Child A has not arrived at school."

[1624] Health assessment and suggestions for caregiving mode

[1625] Step 1:

[1626] User: Uses a client application to input activity information and health status of elderly individuals. Simultaneously, an emotion recognition module analyzes the user's emotions in real time as they input data.

[1627] As a concrete example, users input information such as "walking distance" and "meal content," and their emotional state (e.g., feeling safe, satisfied) is analyzed at that time.

[1628] Step 2:

[1629] Terminal: Sends the entered information to the server.

[1630] As a specific example, the device sends information such as "elderly person B's walking distance and diet" and "user's emotional state: feeling safe" to the server.

[1631] Step 3:

[1632] Server: Receives information sent by the data receiving module and stores it in the database.

[1633] As a specific example, the server stores information such as "elderly person B's walking distance and diet" and "user's emotional state: feeling secure" in a database.

[1634] Step 4:

[1635] Server: Analyzes data stored in the health assessment module to evaluate health status. It also adjusts suggestions based on the emotion analysis results.

[1636] As a concrete example, the server compares past data and evaluates that "elderly person B is not getting enough exercise," and since their emotional state is "reassured," it generates more proactive exercise suggestions.

[1637] Step 5:

[1638] Server: The health suggestion module generates health maintenance suggestions based on the evaluation results and sends them to the user's terminal.

[1639] As a concrete example, the server generates a suggestion such as "We recommend taking a 30-minute walk every day" and sends it to the terminal.

[1640] Step 6:

[1641] Terminal: Receives proposals and notifies the user.

[1642] For example, a notification such as "We recommend taking a 30-minute walk every day" might appear on the user's smartphone.

[1643] In this way, by combining this system with an emotion engine, it becomes possible to provide more accurate alert notifications and suggestions that take into account the user's emotional state, enabling the management of important activity information in childcare and elder care and prompt responses.

[1644] (Example 2)

[1645] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[1646] Conventional childcare and eldercare support systems collect and analyze activity information without considering the user's emotional state, resulting in low accuracy in detecting anomalies and abnormalities, and a failure to provide appropriate alerts and suggestions. In addition, because emotional information is not utilized, responses to users are uniform, making it difficult to provide appropriate responses tailored to individual situations.

[1647] The identification processing by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for collecting activity information and emotion information input by the user; means for transmitting the activity information and emotion information to the server; means for the server to receive the activity information and emotion information and store it in a database; means for the server to analyze the stored activity information and emotion information and detect singular behavior or anomalies; means for the server to generate an alert based on the detected anomalies and emotion analysis results and send it to the client application; and means for the terminal to notify the user of the alert received. This enables highly accurate alert notifications and suggestions that take into account the user's emotional state.

[1648] A "user" refers to an individual who inputs activity and emotional information into the system.

[1649] "Activity information" refers to information about daily activities and events that users input into the system.

[1650] "Emotional information" refers to data that analyzes a user's emotional state in real time.

[1651] A "server" refers to the core of a system that receives, stores, and analyzes activity and sentiment information, generates alerts and suggestions, and sends them to client applications.

[1652] A "database" refers to a storage device used to store received activity and emotional information.

[1653] An "analysis module" refers to software used to detect anomalies or anomalies based on stored data.

[1654] An "alert generation module" refers to software that has the function of generating alerts based on the detection of anomalies and the results of sentiment analysis.

[1655] A "client application" refers to an application on a device that a user uses to input activity and sentiment information and to receive alerts and suggestions.

[1656] "Care mode" refers to the operating mode of a system that evaluates the activity information and health status of elderly people and makes suggestions for maintaining their health.

[1657] A "health assessment module" refers to software that evaluates health status based on stored activity and emotional information and generates recommendations.

[1658] This invention is a system intended to support childcare and elder care, and incorporates an emotion engine that recognizes the user's emotions. This system can quickly detect unusual behaviors and abnormal health conditions, and provide the user with appropriate alerts and suggestions.

[1659] System Configuration

[1660] 1. User terminal

[1661] Data entry interface: An interface for users to input activity information. Examples include smartphone and tablet apps.

[1662] Data transmission module: A module that transmits input activity and emotion information to the server.

[1663] Alert receiving module: A module for receiving alerts from the server.

[1664] Alert notification module: A module that notifies the user of received alerts.

[1665] Emotion Recognition Module: A module that uses an emotion engine to analyze the user's emotions in real time as they input data.

[1666] 2. Server

[1667] Data receiving module: Receives activity and emotion information sent from the user's terminal.

[1668] Database: Stores received activity and sentiment information.

[1669] Analysis Module: Analyzes and detects anomalies and singular behaviors based on stored data.

[1670] Alert generation module: Based on the analysis results, it generates alerts as needed and sends them to the user's terminal.

[1671] Health suggestion module: Generates health maintenance suggestions in care mode.

[1672] Emotion Analysis Module: Uses an emotion engine to perform data analysis based on the results of user emotion analysis.

[1673] Specific examples of program processing

[1674] User: Enters activity information through the client application's data entry interface. During input, the emotion recognition module analyzes the user's emotions in real time.

[1675] Specific example: A user enters "Child A's expected arrival time at school is 8:30 AM." At this time, the user's emotions (e.g., anxiety or impatience) are analyzed.

[1676] Terminal: Sends activity and emotion information entered via the data transmission module to the server.

[1677] Specific example: The device sends data to the server: "Child A's estimated arrival time at school: 8:30 AM" and "User's emotional state: Anxious."

[1678] Server: The data receiving module receives data sent from the terminal and stores it in the database.

[1679] Specific example: The server saves the following data to the database: "Child A's estimated arrival time at school: 8:30 AM" and "User's emotional state: Anxious."

[1680] Server: Uses an analysis module to detect singular behaviors and anomalies based on stored activity information and sentiment analysis results.

[1681] Specific example: The server checks the school's GPS data and time clock information, detects that child A has not arrived at school by 8:45 AM, and also detects that the user's emotional state is "anxious," and determines that this is an anomaly.

[1682] Server: When singular behavior or anomalies are detected, the alert generation module generates an alert and adjusts the content of the alert considering the sentiment analysis results.

[1683] Specific example: The server generates an alert stating "Child A has not arrived at school," and considering the user's emotional state of anxiety, the alert is modified to encourage a more prompt response.

[1684] Terminal: The alert receiving module receives alerts from the server, and the alert notification module notifies the user.

[1685] Specific example: The device notifies the user via a pop-up alert stating, "Child A has not arrived at school."

[1686] Specific examples of health assessment and recommendations for caregiving.

[1687] User: Uses a client application to input activity information and health status of elderly individuals. During input, an emotion recognition module analyzes emotions in real time.

[1688] Specific example: When a user enters information such as "walking distance" or "meal content," their emotions (e.g., feeling safe or satisfied) are analyzed.

[1689] Server: Receives activity and emotion information sent by the data receiving module and stores it in the database.

[1690] Specific example: The server stores information such as "elderly person B's walking distance and diet" and "user's emotional state: feeling safe" in a database.

[1691] Server: Analyzes data stored in the health assessment module and evaluates health status. Adjusts suggestions based on the emotion analysis results.

[1692] Specific example: The server compares data with past data and assesses that "elderly person B is not getting enough exercise," and based on their emotional state being "reassured," it generates more proactive exercise suggestions.

[1693] Server: The health suggestion module generates health maintenance suggestions based on the evaluation results and sends them to the user's terminal.

[1694] Terminal: Receives proposals and notifies the user.

[1695] Specific example: The server generates a suggestion such as "We recommend taking a 30-minute walk every day," and the device notifies the user of this.

[1696] Example prompts for a generative AI model

[1697] Example prompt: "Describe a system that takes input information about daily activities related to childcare or elder care (e.g., a child's arrival time at school or the elderly person's meals), performs real-time sentiment recognition, and generates appropriate alerts or suggestions if anomalies are detected."

[1698] The flow of the specific processing in Example 2 will be explained using Figure 13.

[1699] Step 1:

[1700] Users input activity and emotion information through the data entry interface of the client application. This allows for real-time recording of the user's activity and emotion data.

[1701] Specific operation: The user opens a smartphone app and enters "Child A's estimated arrival time at school: 8:30." Simultaneously, the emotion recognition module analyzes the user's facial expressions and tone of voice to recognize emotions such as anxiety or impatience.

[1702] Input: Text information entered by the user and real-time sentiment data (facial expressions and voice).

[1703] Output: Activity information and analyzed sentiment information.

[1704] Step 2:

[1705] The terminal's data transmission module sends the input activity information and emotion information to the server.

[1706] Specific action: The device encrypts and sends the following data to the server via the network: "Child A's estimated arrival time at school: 8:30 AM" and "User's emotional state: Anxious."

[1707] Input: Activity information and sentiment information.

[1708] Output: Activity and sentiment information sent to the server.

[1709] Step 3:

[1710] The server's data receiving module receives data sent from the terminal and saves it to the database.

[1711] Specific operation: The server analyzes the received data and writes "Child A's estimated arrival time at school: 8:30 AM" and "User's emotional state: Anxious" to the database.

[1712] Input: Received activity and sentiment information.

[1713] Output: Activity and sentiment information stored in the database.

[1714] Step 4:

[1715] The server's analysis module analyzes stored activity and emotion information to detect singular behaviors and anomalies.

[1716] Specific operation: The server executes a script that cross-checks activity information and sentiment data in the database. For example, it might refer to the school's GPS data and detect that child A has not arrived at school by 8:45 AM, and that the user's sentiment state is anxious.

[1717] Input: Activity and sentiment information from the database.

[1718] Output: Detected singular behaviors or anomalies.

[1719] Step 5:

[1720] The server's alert generation module generates alerts based on anomaly and sentiment analysis results and sends them to the client application.

[1721] Specific operation: When the server detects an anomaly, the alert generation module generates a message stating, "Child A has not arrived at school." Furthermore, considering the user's emotional state of anxiety, the alert content is adjusted to encourage a quicker response.

[1722] Input: Detected anomalies and sentiment analysis results.

[1723] Output: Alert message.

[1724] Step 6:

[1725] The terminal's alert receiving module receives alerts from the server, and the alert notification module notifies the user.

[1726] Specific action: The device uses push notifications to display a pop-up alert to the user stating, "Child A has not arrived at school." The user can view detailed information when they open the app.

[1727] Input: Alert message sent from the server.

[1728] Output: Alert notification to the user.

[1729] Step 7:

[1730] Users input activity information and health status of elderly individuals using a client application. During input, an emotion recognition module analyzes the user's emotions in real time.

[1731] Specific operation: When the user inputs "walking distance" or "meal contents," the emotion recognition module analyzes their facial expressions and tone of voice to determine, for example, an emotional state such as "feeling at ease."

[1732] Input: Activity and emotional information of elderly individuals.

[1733] Output: Activity information including sentiment analysis results.

[1734] Step 8:

[1735] The server's data receiving module receives activity and emotion information sent from the terminal and stores it in the database.

[1736] Specific operation: The server saves information such as "elderly person B's walking distance and diet" and "user's emotional state: feeling safe" to the database.

[1737] Input: Activity and emotional information of elderly individuals transmitted from their devices.

[1738] Output: Activity and sentiment information stored in the database.

[1739] Step 9:

[1740] The server's health assessment module analyzes stored data to evaluate its health status. It also adjusts the suggested solutions based on the sentiment analysis results.

[1741] Specific operation: The server compares the current data with past data, assesses that "elderly person B is not getting enough exercise," and generates health maintenance suggestions that provide reassurance, such as "a 30-minute walk per day is recommended."

[1742] Input: Activity information and sentiment analysis results from the database.

[1743] Output: Health assessment results and recommendations.

[1744] Step 10:

[1745] The server's health suggestion module generates health maintenance suggestions based on the evaluation results and sends them to the user's terminal.

[1746] Specific operation: The server generates specific suggestions, such as "We recommend taking a 30-minute walk every day," and sends them to the terminal via the network.

[1747] Input: Evaluation results and proposed content.

[1748] Output: Health maintenance suggestions sent to the terminal.

[1749] Step 11:

[1750] The device receives the suggestion and notifies the user.

[1751] Specific action: The device will use a notification sound and vibration to display a pop-up message to the user recommending a 30-minute walk each day, and will provide a link to more information.

[1752] Input: Health maintenance suggestions sent from the server.

[1753] Output: Suggestion notification to the user.

[1754] (Application Example 2)

[1755] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[1756] Conventional emotion recognition systems often had low accuracy and were unable to provide appropriate alerts or suggestions because they analyzed activity information without considering the user's emotional state, thus failing to detect anomalies or abnormalities. Furthermore, in areas such as worker safety management and improving work efficiency in factories, they were unable to provide appropriate measures quickly by considering emotional states.

[1757] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[1758] In this invention, the server includes means for analyzing the user's emotional state in real time using an emotion recognition algorithm, means for adjusting the analysis results and alert content based on the emotional state, and means for adjusting the suggested content based on the emotional state. This enables highly accurate anomaly detection, appropriate alert notifications, and suggestions for improving work efficiency, all while taking the user's emotional state into consideration.

[1759] A "user" is defined as the entity that uses this system, inputs activity information, and receives real-time sentiment analysis based on that information.

[1760] "Activity information" refers to data about the user's daily actions and tasks, which is received and analyzed by the server.

[1761] A "server" is a central system that receives activity information and emotional state data, stores and analyzes it in a database, and performs anomaly detection and suggestion generation.

[1762] A "database" is a storage device that stores activity information and emotion information received within a server.

[1763] "Singular behavior" refers to behavior that deviates from normal activity patterns and is a sign of abnormality or a problem.

[1764] An "anomaly" is a state in which singular behavior or risks are detected, and it is a situation that requires users to be alerted or take action.

[1765] An "alert" is a warning notification generated based on detected anomalies, prompting users to take safety measures and responses.

[1766] A "client application" is application software installed on a user's terminal that allows for the input of activity information, the reception of alerts, and the display of sentiment analysis results.

[1767] An "emotion recognition algorithm" is an algorithm that analyzes a user's facial expressions and voice data to determine their emotional state in real time.

[1768] "Emotional state" refers to the user's psychological state as analyzed by an emotion recognition algorithm, and is used to adjust content and generate suggestions.

[1769] A "suggestion" is a recommended action or advice generated by the server and notified to the user for purposes such as maintaining health or improving work efficiency.

[1770] "Real-time" refers to a state where the entire process, from data collection to analysis and notification, is carried out immediately, without any delay.

[1771] This invention is a system aimed at improving worker safety management and work efficiency within a factory, and its specific embodiments are described below. The main hardware and software used, as well as the data processing and calculation methods, will be explained.

[1772] System Configuration

[1773] hardware

[1774] User device: Smart glasses (e.g., Google Glass)

[1775] Server: A central computer for data processing and storage (e.g., AWS, Google Cloud)

[1776] software

[1777] Emotion Recognition Algorithm: Uses Face API and Emotion SDK to analyze the user's emotional state in real time.

[1778] Data analysis platform: Uses TensorFlow and Scikit-learn to analyze data and detect anomalies.

[1779] Specific processing flow

[1780] 1. Data Collection

[1781] User terminal: While the worker is wearing the smart glasses, the built-in camera and microphone are used to analyze facial expressions and voice. The collected data is then analyzed in real time by an emotion recognition algorithm to determine the emotional state.

[1782] Specific example: When a worker begins welding, smart glasses recognize their level of fatigue and analyze it as an emotional state of "fatigue."

[1783] 2. Data transmission

[1784] User terminal: Emotional data and work information are sent to the server using the HTTPS protocol.

[1785] Specific example: The worker's emotional state is "fatigued," and this environmental data is sent to the server.

[1786] 3. Data reception and storage

[1787] Server: Receives the transmitted data and saves it to the database.

[1788] Specific example: The server's database stores "worker A's fatigue status" and "environmental data".

[1789] 4. Data Analysis

[1790] Server: Uses analytical platforms such as TensorFlow and Scikit-learn to analyze collected data and detect singular behavior and anomalies.

[1791] Specific example: The server references other sensor data (e.g., temperature sensor data or machine operating status) to detect that a worker is fatigued in a high-temperature environment.

[1792] 5. Generate and send alerts

[1793] Server: Generates alert content based on detected risks and emotional states, and sends it to the user's terminal.

[1794] Specific example: The server generates and sends an alert stating, "You are experiencing fatigue due to the high-temperature environment. Please rest in a safe place."

[1795] 6. Alert notifications

[1796] User terminal: Uses the smart glasses API to notify workers of visual and audible alerts.

[1797] Specific example: A pop-up appears on a worker's smart glasses saying, "You are experiencing fatigue due to the high-temperature environment. Please rest in a safe place."

[1798] Adding specific examples

[1799] Example of a prompt

[1800] Prompt: Based on the following data, assess the fatigue level and generate an appropriate alert:

[1801] Worker A's facial expression data: [Specific values ​​of facial expression data]

[1802] Voice data from worker A: [Specific values ​​of the voice data]

[1803] Environmental data (temperature, humidity, noise level, etc.): [Specific values ​​for environmental data]

[1804] Work details: Welding work

[1805] Specific examples

[1806] Facial expression data for worker A: "Heaviness in the eyes", "Frown lines between the eyebrows"

[1807] Audio data from worker A: "Low voice tone"

[1808] Environmental data (temperature, humidity, noise level, etc.): "Temperature: 35℃, Humidity: 60%, Noise level: 85dB"

[1809] Work details: Welding work

[1810] Example Output

[1811] "Worker A is experiencing fatigue due to the high-temperature environment. Please take a rest."

[1812] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[1813] Step 1:

[1814] Data collection

[1815] The user device (smart glasses) uses its built-in camera and microphone to collect facial expressions and voice while the worker is wearing it. This data is analyzed in real time by emotion recognition algorithms (e.g., Face API, Emotion SDK) to determine the worker's emotional state.

[1816] Input: Facial expression data, audio data

[1817] Data processing: An emotion recognition algorithm analyzes the input data and identifies the emotional state.

[1818] Output: Emotional state (e.g., fatigue, anxiety)

[1819] Step 2:

[1820] Data transmission

[1821] The user terminal sends the analyzed emotion data and work information to the server using the HTTPS protocol.

[1822] Input: Emotional state data, work information

[1823] Data processing: Data packaging and encryption

[1824] Output: Transmit data packet

[1825] Specific operation: A transmission module inside the smart glasses sends data to the server.

[1826] Step 3:

[1827] Data reception and storage

[1828] The server receives the transmitted data and stores it in the database. This process includes data verification and format conversion.

[1829] Input: Transmit data packet

[1830] Data processing: Data decoding and format conversion

[1831] Output: Saved emotional state data, work information

[1832] Specific operation: The server's receiving module receives data and stores it in the database.

[1833] Step 4:

[1834] Data Analysis

[1835] The server uses TensorFlow and Scikit-learn to analyze the stored data and detect singular behavior and anomalies.

[1836] Input: Saved emotional state data, work information

[1837] Data processing: Anomaly detection using machine learning models

[1838] Output: Anomaly detection results

[1839] Specific operation: The server's analysis module runs a machine learning model to detect anomalies and other issues.

[1840] Step 5:

[1841] Alert generation and sending

[1842] The server generates an alert based on the detected anomaly and sends the alert content to the user's terminal. It also takes the user's emotional state into consideration when adjusting the alert content.

[1843] Input: Anomaly detection results, emotional state data

[1844] Data processing: Generating alert content and adjusting it based on emotional state.

[1845] Output: Alert notification data

[1846] Specific operation: The server's alert generation module generates an alert, and the transmission module sends it to the user's terminal.

[1847] Step 6:

[1848] Alert notification

[1849] The user terminal notifies the worker of received alerts visually and audibly.

[1850] Input: Alert notification data

[1851] Data processing: Decoding and formatting of alert data.

[1852] Output: Visual and audio notifications

[1853] Specific operation: The smart glasses' notification module displays an alert and also provides audio output.

[1854] The above outlines the specific processing flow of the system that implements the application example. This enables highly accurate anomaly detection and alert notification based on the user's emotional state.

[1855] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[1856] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1857] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and specific processing may also be performed by the headset terminal 314.

[1858] [Fourth Embodiment]

[1859] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[1860] As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[1861] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1862] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[1863] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[1864] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[1865] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[1866] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. Furthermore, the robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[1867] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[1868] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[1869] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1870] In robot 414, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[1871] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1872] This invention relates to a system for managing activity information and providing alert notifications related to childcare and elderly care, and in particular to providing means for detecting unusual behaviors and abnormal health conditions and responding to them quickly.

[1873] This system operates by having users input activity information, which is then collected, stored, and analyzed on a server. A specific implementation of the system is shown below.

[1874] System Configuration

[1875] 1. User terminal

[1876] Data entry interface: An interface for users to input activity information. Examples include smartphone and tablet apps.

[1877] Data transmission module: A module that sends the entered activity information to the server.

[1878] Alert receiving module: A module for receiving alerts from the server.

[1879] Alert notification module: A module that notifies the user of received alerts.

[1880] 2. Server

[1881] Data receiving module: Receives activity information sent from the user's terminal.

[1882] Database: Stores received activity information.

[1883] Analysis Module: Analyzes and detects anomalies and singular behaviors based on stored data.

[1884] Alert generation module: Based on the analysis results, it generates alerts as needed and sends them to the user's terminal.

[1885] Health suggestion module: Generates health maintenance suggestions in care mode.

[1886] Program execution flow

[1887] The system's processing flow is explained in detail below.

[1888] Data collection

[1889] User: Enters activity information through the data input interface on the user's terminal. For example, they might enter the estimated arrival time of a child at school or information about meals and exercise for elderly people.

[1890] Example: The user enters "Child A is scheduled to arrive at school at 8:30."

[1891] Data transmission

[1892] Terminal: Sends the entered activity information to the server via the data transmission module.

[1893] Specific example: The device sends data to the server that says, "Child A's estimated arrival time at school: 8:30 AM."

[1894] Data reception and storage

[1895] Server: The data receiving module receives the transmitted data and saves it to the database.

[1896] Specific example: The server saves the data "Child A's estimated arrival time at school: 8:30 AM" to the database.

[1897] Data Analysis

[1898] Server: Based on the data stored by the analysis module, it performs analysis to detect singular behaviors and anomalies.

[1899] Specific example: The server detects that child A has not arrived at school by 8:45 AM and determines that this is an anomaly.

[1900] Alert generation and sending

[1901] Server: Based on the detected anomaly, the alert generation module generates an alert and sends it to the user's terminal.

[1902] Specific example: The server generates an alert stating "Child A has not arrived at school" and sends it to the terminal.

[1903] Alert notification

[1904] Terminal: The alert receiving module receives alerts from the server, and the alert notification module notifies the user.

[1905] Specific example: The device notifies the user via a pop-up alert stating, "Child A has not arrived at school."

[1906] Health assessment and suggestions for caregiving mode

[1907] Data collection and transmission

[1908] User: Enters activity information and health status of elderly individuals into the client application.

[1909] Terminal: The data transmission module sends this information to the server.

[1910] Specific example: The user inputs information such as "walking distance" and "meal details," and the device sends this information to the server.

[1911] Data reception and storage

[1912] Server: The data receiving module receives this information and stores it in the database.

[1913] Health assessment and recommendations

[1914] Server: Analyzes data stored in the health assessment module and evaluates health status.

[1915] Server: Based on the evaluation results in the health suggestion module, it generates specific suggestions for maintaining health and sends them to the user's terminal.

[1916] Specific example: The server suggests to elderly person B that they "take a 30-minute walk every day," and the terminal notifies the user of this.

[1917] This allows the system to centrally manage important activity information related to childcare and elder care in real time, enabling it to detect unusual behaviors and anomalies and respond quickly. Furthermore, in elder care mode, it can contribute to the user's health management by assessing their health status and suggesting appropriate health maintenance measures.

[1918] The following describes the processing flow.

[1919] Step 1:

[1920] User: Enter activity information using the data entry interface of the client application.

[1921] As a concrete example, the user enters "Child A's expected arrival time at school is 8:30 AM."

[1922] Step 2:

[1923] Terminal: Sends the entered activity information to the server via the data transmission module.

[1924] For example, the device sends data to the server such as "Child A's estimated arrival time at school: 8:30 AM".

[1925] Step 3:

[1926] Server: Receives data sent from the terminal using the data receiving module.

[1927] As a concrete example, the server receives data that says "Child A's estimated arrival time at school: 8:30 AM".

[1928] Step 4:

[1929] Server: Saves received data to the database.

[1930] As a concrete example, the data received by the server is stored in a database.

[1931] Step 5:

[1932] Server: Uses analysis modules to analyze stored data and detect anomalies and outlier behaviors.

[1933] As a concrete example, the server references the school's GPS data and time clock records and detects that child A has not arrived at school by 8:45.

[1934] Step 6:

[1935] Server: When singular behavior or anomalies are detected, the alert generation module generates an alert.

[1936] As a concrete example, the server generates an alert stating, "Child A has not arrived at school."

[1937] Step 7:

[1938] Server: Sends generated alerts to the client application.

[1939] As a concrete example, the server sends an alert to the terminal stating, "Child A has not arrived at school."

[1940] Step 8:

[1941] Terminal: The alert receiving module receives alerts sent from the server.

[1942] As a concrete example, the device receives an alert stating, "Child A has not arrived at school."

[1943] Step 9:

[1944] Terminal: Notifies the user of alerts received by the alert notification module.

[1945] As a concrete example, a pop-up notification appears on the user's smartphone stating, "Child A has not arrived at school."

[1946] Health assessment and suggestions for caregiving mode

[1947] Step 1:

[1948] User: Use the client application to input activity information and health status of elderly individuals.

[1949] As a concrete example, you can input information such as the elderly person's "walking distance" and "dietary content."

[1950] Step 2:

[1951] Terminal: Sends the entered information to the server.

[1952] As a specific example, the terminal sends information such as "elderly person B's walking distance and dietary content" to the server.

[1953] Step 3:

[1954] Server: Receives information sent by the data receiving module and stores it in the database.

[1955] As a concrete example, the server stores information such as "elderly person B's walking distance and diet" in a database.

[1956] Step 4:

[1957] Server: Analyzes data received by the health assessment module and evaluates the health status.

[1958] As a concrete example, the server compares current data with past data and concludes that "elderly person B is not getting enough exercise."

[1959] Step 5:

[1960] Server: The health suggestion module generates health maintenance suggestions based on the evaluation results.

[1961] As a concrete example, the server might generate a suggestion such as "We recommend taking a 30-minute walk every day."

[1962] Step 6:

[1963] Server: Sends the generated proposals to the client application.

[1964] As a concrete example, the server sends a suggestion to the terminal saying, "We recommend taking a 30-minute walk every day."

[1965] Step 7:

[1966] Terminal: Receives proposals and notifies the user.

[1967] For example, a notification such as "We recommend taking a 30-minute walk every day" might appear on the user's smartphone.

[1968] In this way, this system smoothly handles the entire process from user input to data collection, analysis, alert generation, and notification, enabling a rapid response to unusual behaviors and abnormal health conditions in childcare and elder care.

[1969] (Example 1)

[1970] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1971] Managing activity information in childcare and elder care is time-consuming and labor-intensive, and delays in recording information and detecting anomalies are a challenge. In particular, the lack of means to detect unusual behaviors or abnormal health conditions early and respond quickly means that users may not be able to take action promptly, leading to problems becoming more serious. Furthermore, in elder care, there is a need to appropriately assess the health status of the elderly and propose appropriate health maintenance measures, but there is a lack of systems to do so.

[1972] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[1973] In this invention, the server includes means for collecting activity information entered by the user, means for transmitting the activity information to the server, means for the server to receive the activity information and store it in a database, means for the server to analyze the stored activity information and detect singular behaviors or anomalies, means for the server to generate alerts based on the detected anomalies and send them to a client application, means for the terminal to notify the user of the received alerts, and means for the server to use a health suggestion module to generate health maintenance suggestions in care mode and send them to a client application. This enables centralized management of childcare and caregiving activity information, rapid detection of singular behaviors or anomalies and generation of alerts, and further enables health assessment of the elderly and appropriate health maintenance suggestions in care mode.

[1974] A "user" is someone who uses the system to input activity information and receive alerts and suggestions.

[1975] "Activity information" refers to data about actions and situations related to childcare and elder care.

[1976] A "server" is a device that receives, stores, and analyzes activity information sent by users, and generates alerts and suggestions.

[1977] A "database" is a storage method used by a server to store activity information it has received.

[1978] An "analysis module" is a software component that analyzes information stored in a database to detect anomalies and unusual behavior.

[1979] An "alert generation module" is a software component that generates alerts based on anomalies detected by the analysis module.

[1980] A "client application" is application software that runs on a user's terminal and is used by the user to input activity information and receive alerts and suggestions from the server.

[1981] A "device" refers to a device used by a user, such as a smartphone or tablet.

[1982] The "Health Suggestion Module" is a software component that, in care mode, performs a health assessment based on saved activity information and generates suggestions for maintaining health.

[1983] This invention relates to a system for managing activity information and providing alert notifications related to childcare and elderly care, and in particular to providing means for detecting unusual behaviors and abnormal health conditions and responding quickly. Specific embodiments of the system are shown below.

[1984] System Configuration

[1985] 1. User terminal

[1986] Data entry interface: This is an interface for users to input activity information. Smartphone apps and tablet apps fall into this category.

[1987] Data transmission module: This module transmits the input activity information to the server.

[1988] Alert receiving module: This module is used to receive alerts from the server.

[1989] Alert notification module: This module notifies the user of received alerts.

[1990] 2. Server

[1991] Data receiving module: This module receives activity information sent from the user's terminal.

[1992] Database: A storage device for saving received activity information.

[1993] Analysis Module: A software component used to detect anomalies and outliers based on stored data.

[1994] Alert generation module: This is a software component that generates alerts as needed based on analysis results and sends them to the user's terminal.

[1995] Health Suggestion Module: This is a software component for generating health maintenance suggestions in caregiving mode.

[1996] Explanation of the program's processing

[1997] Data collection

[1998] User: Manually inputs childcare and eldercare activity information through a smartphone or tablet application. For example, inputting the estimated arrival time of a child at school or information on meals and exercise for the elderly.

[1999] Data transmission

[2000] Terminal: Uses a data transmission module to send the entered activity information to the server using an HTTP request.

[2001] Data reception and storage

[2002] Server: The data receiving module receives the transmitted data and saves it to a database such as MySQL.

[2003] Data Analysis

[2004] Server: The analysis module uses information stored in the database to perform analysis to detect singular behaviors and anomalies. Statistical methods and machine learning models are frequently used in this analysis.

[2005] Alert generation and sending

[2006] Server: Based on the anomaly detected by the alert generation module, an alert is generated and sent to the user terminal via an HTTP POST request.

[2007] Alert notification

[2008] Terminal: The alert receiving module receives alerts sent from the server, and the alert notification module notifies the user of these alerts via pop-up or push notifications.

[2009] Health assessment and suggestions for caregiving mode

[2010] Data collection and transmission

[2011] User: Input activity information and health status of elderly individuals into the client application. For example, input information such as walking distance and dietary details.

[2012] Terminal: Uses a data transmission module to send this information to the server.

[2013] Data reception and storage

[2014] Server: The data receiving module receives this information and stores it in the database.

[2015] Health assessment and recommendations

[2016] Server: The health assessment module analyzes the stored data and evaluates the user's health status. Subsequently, the health suggestion module generates appropriate health maintenance suggestions based on the assessment results and sends them to the user's terminal.

[2017] Specific examples and prompt statements

[2018] Specific example

[2019] A user uses a smartphone app to input "Child A is scheduled to arrive at school at 8:30." This data is sent to a server, and an analysis module detects that Child A has not arrived at school at 8:45, generates an alert stating "Child A has not arrived at school," and sends it to the user's device.

[2020] Example of a prompt

[2021] "I would like an alert to be issued and I to be notified if my child has not arrived at school."

[2022] This allows the system to manage activity information related to childcare and elderly care in real time, quickly detect and notify of abnormalities in health conditions, and also provide concrete suggestions for maintaining the health of the elderly.

[2023] The flow of the specific processing in Example 1 will be explained using Figure 11.

[2024] Step 1: Enter activity information

[2025] User: Enters information about activities related to childcare and elder care. Specifically, the user accesses an application on their smartphone or tablet and manually enters information such as "Child A is scheduled to arrive at school at 8:30" and "Breakfast for the elderly: Salad and fruit."

[2026] Input: Activity information such as "Child A is scheduled to arrive at school at 8:30."

[2027] Output: Activity information entered into the user's terminal.

[2028] Step 2: Submit the input data

[2029] Terminal: Uses a data transmission module to send the entered activity information to the server. Specifically, the terminal generates an HTTP POST request and sends the data to the server.

[2030] Input: Activity information entered into the user's terminal.

[2031] Output: Activity information received by the server.

[2032] Step 3: Data reception and storage

[2033] Server: The data receiving module receives the transmitted data and stores it in the database. Specifically, the server parses the received HTTP POST request and stores the data in the MySQL database.

[2034] Input: Activity information sent from the device.

[2035] Output: Activity information stored in the database.

[2036] Step 4: Data Analysis

[2037] Server: The analysis module detects singular behavior and anomalies based on the stored data. Specifically, the server analyzes the data using statistical methods and machine learning models to detect anomalies.

[2038] Input: Activity information stored in the database.

[2039] Data processing / computation: Analysis using statistical methods and machine learning models.

[2040] Output: Detection results of singular behaviors and anomalies.

[2041] Step 5: Generate and send alerts

[2042] Server: Based on the anomalies detected by the alert generation module, the server generates an alert and sends it to the user terminal. Specifically, the server generates an alert message and sends it to the user terminal again using an HTTP POST request.

[2043] Input: Results of detecting singular behavior or anomalies.

[2044] Output: An alert sent to the user's terminal.

[2045] Step 6: Alert Notification

[2046] Terminal: The alert receiving module receives alerts from the server, and the alert notification module notifies the user. Specifically, the terminal generates pop-up notifications or push notifications to inform the user.

[2047] Input: Alert sent from the server.

[2048] Output: An alert sent to the user.

[2049] Step 7: Health assessment and recommendations for care mode

[2050] Data collection and transmission

[2051] User: Enters activity information and health status of elderly individuals into the client application. For example, "Today's walking distance: 5000 steps," "Breakfast: Salad and fruit," etc.

[2052] Terminal: The data transmission module sends this information to the server. Specifically, the terminal sends the input data to the server using an HTTP POST request.

[2053] Input: Activity information and health status of elderly individuals.

[2054] Output: Health information received by the server.

[2055] Data reception and storage

[2056] Server: The data receiving module receives this information and stores it in the database. Specifically, the server parses the received HTTP POST request and stores the data in the database.

[2057] Input: Health information sent from the device.

[2058] Output: Health information stored in the database.

[2059] Health assessment and recommendations

[2060] Server: The health assessment module analyzes the stored data and evaluates the user's health status. Subsequently, the health suggestion module generates appropriate health maintenance suggestions based on the evaluation results and sends them to the user's terminal. Specifically, the server analyzes the data, makes evaluations such as "total daily walking distance is below the recommended value," generates suggestions such as "30 minutes of walking per day is recommended," and sends them to the user's terminal using an HTTP POST request.

[2061] Input: Health information stored in the database.

[2062] Data processing / calculation: Analysis using health assessment algorithms.

[2063] Output: Health suggestions sent to the user's terminal.

[2064] (Application Example 1)

[2065] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[2066] In modern society, there is a need to efficiently manage activity information related to childcare and elder care, and to quickly detect and respond to unusual behaviors and abnormal health conditions. However, conventional systems have difficulty collecting real-time location information and situational data, which can lead to delays in responding to abnormalities. Furthermore, they lack mechanisms to provide users with appropriate recommended actions when abnormalities are detected. Therefore, there is a need for a comprehensive system that enables safe and rapid responses.

[2067] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[2068] In this invention, the server includes means for collecting activity information entered by the user, means for transmitting the activity information to the server, means for the server to receive the activity information and store it in a database, means for the server to analyze the stored activity information and detect singular behavior or anomalies, means for the server to generate an alert based on the detected anomaly and send it to the client application, means for the terminal to notify the user of the received alert, means for collecting location information and status data in real time and promptly providing alert notifications when an anomaly is detected, and means for generating recommended actions when an anomaly is detected and proposing them to the user. As a result, the user can monitor the location information and status data of family members and those they care for in real time and respond quickly when an anomaly occurs. In addition, appropriate recommended actions are provided for the detected anomaly, improving safety and health maintenance.

[2069] A "user" is an individual or organization that uses the system to input activity information and receive alerts and recommended actions.

[2070] "Activity information" refers to information such as the subject's location, daily behavior data, and health status.

[2071] A "server" is a central device that receives activity information sent by users, stores it in a database, and analyzes it to detect anomalies and abnormalities.

[2072] A "client application" is software installed on a user's terminal that receives data and alerts from a server and notifies the user of that information.

[2073] A "database" is an information processing system used by a server to store activity information it has received.

[2074] "Singular behavior" refers to abnormal behavior that deviates from normal behavioral patterns, and it is through such behavior that abnormalities are detected.

[2075] An "anomaly" is an event that deviates from the normal behavior or state of a user or subject, and an alert is generated based on the detection of such an anomaly.

[2076] An "alert" is a warning message sent to a user when unusual behavior or anomalies are detected.

[2077] "Recommended actions" are specific suggestions of what the user should do in response to detected anomalies.

[2078] "Location information" refers to data that indicates the current location of a user or subject, and is necessary information for real-time monitoring.

[2079] "Status data" refers to all information that represents the state of a user or subject, including but not limited to location information.

[2080] This "Family Safety Monitoring & Alert System" is a comprehensive system that monitors the location and status data of family members and those receiving care in real time, and enables rapid response when an anomaly is detected. The specific implementation of the system is shown below.

[2081] System Configuration

[2082] 1. User terminal

[2083] Data entry interface: An interface for users to input activity information. Smartphone and tablet apps fall into this category.

[2084] Data transmission module: A module that sends the entered activity information to the server.

[2085] Alert receiving module: A module for receiving alerts from the server.

[2086] Alert notification module: A module that notifies the user of received alerts.

[2087] 2. Server

[2088] Data receiving module: Receives activity information sent from the user's terminal.

[2089] Database: Stores received activity information.

[2090] Analysis Module: Analyzes and detects singular behaviors and anomalies based on stored data. Uses scikit-learn for data analysis.

[2091] Alert generation module: Based on analysis results, it generates alerts as needed and sends them to the user's device. Firebase Cloud Messaging (FCM) is used to send alerts.

[2092] Health suggestion module: Generates recommended actions when an anomaly is detected and suggests them to the user.

[2093] Program Processing Description

[2094] This system uses Python, AWS Lambda, AWS DynamoDB, Flutter, scikit-learn, and Firebase Cloud Messaging (FCM) as its main hardware and software components.

[2095] Data collection

[2096] User: Enters activity information through the data input interface on the user's terminal. For example, they might enter the estimated arrival time of a child at school or information about meals and exercise for elderly people.

[2097] Example: The user enters "Child A is scheduled to arrive at school at 8:30."

[2098] Data transmission

[2099] Terminal: Sends the entered activity information to the server via the data transmission module.

[2100] Specific example: The device sends data to the server that says, "Child A's estimated arrival time at school: 8:30 AM."

[2101] Data reception and storage

[2102] Server: The data receiving module receives the transmitted data and stores it in AWS DynamoDB.

[2103] Specific example: The server saves the data "Child A's estimated arrival time at school: 8:30 AM" to the database.

[2104] Data Analysis

[2105] Server: Uses scikit-learn to perform analysis on stored data to detect singular behaviors and anomalies.

[2106] Specific example: The server detects that child A has not arrived at school by 8:45 AM and determines that this is an anomaly.

[2107] Alert generation and sending

[2108] Server: Based on the detected anomaly, the alert generation module uses FCM to generate an alert and sends it to the user terminal.

[2109] Specific example: The server generates an alert stating "Child A has not arrived at school" and sends it to the terminal.

[2110] Alert notification

[2111] Terminal: The alert receiving module receives alerts from the server, and the alert notification module notifies the user.

[2112] Specific example: The device notifies the user via a pop-up alert stating, "Child A has not arrived at school."

[2113] Recommended Actions

[2114] Server: Generates specific recommended actions to address detected anomalies and sends them to the user's terminal.

[2115] Specific example: The server generates a recommended action, "Child A is late arriving at school. Please contact the school immediately," and sends it to the device.

[2116] Example of a prompt

[2117] text

[2118] User ID: 12345, Activity Information: 'Child is expected to arrive at the park at 5 PM', Current Time: '5:30 PM'

[2119] This system allows users to efficiently and quickly monitor the safety and health of their family members and take immediate, appropriate action when an abnormality occurs.

[2120] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[2121] Step 1:

[2122] Data collection

[2123] Users input activity information through a data entry interface on their smartphone or tablet app. The data includes location information, scheduled times, and details of activities. For example, a user might input, "Child A is scheduled to arrive at school at 8:30." This information is entered into the device and processed by a data transmission module.

[2124] Input: User activity information (location, scheduled time, activity details)

[2125] Output: Information input to the data transmission module within the terminal.

[2126] Step 2:

[2127] Data transmission

[2128] The terminal uses a data transmission module to send the entered activity information to the server via the internet. For example, the terminal sends the data "Child A's estimated arrival time at school: 8:30" to the server. This operation transfers the activity information to the server.

[2129] Input: Information entered into the data transmission module within the device.

[2130] Output: Information sent to the server's data receiving module.

[2131] Step 3:

[2132] Data reception and storage

[2133] The server uses a data receiving module to receive activity information sent from the user terminal and stores it in the database. For example, the server stores the data "Child A's estimated arrival time at school: 8:30" in the database.

[2134] Input: Information sent to the server's data receiving module.

[2135] Output: Activity information stored in the database

[2136] Step 4:

[2137] Data Analysis

[2138] The server uses scikit-learn to analyze stored data to detect anomalies and outliers. For example, the server detects that child A has not arrived at school by 8:45 AM and identifies this as an anomaly. Machine learning algorithms are used for anomaly detection, analyzing patterns based on past data.

[2139] Input: Activity information stored in the database

[2140] Output: Anomaly detection results (singular behavior, anomaly)

[2141] Step 5:

[2142] Alert generation and sending

[2143] The server generates an alert using an alert generation module based on the detected anomaly and sends it to the user's device using Firebase Cloud Messaging (FCM). Specifically, the server generates an alert stating "Child A has not arrived at school" and sends it to the device.

[2144] Input: Anomaly detection result

[2145] Output: Alert message

[2146] Step 6:

[2147] Alert notification

[2148] The user's device receives alerts from the server using an alert receiving module, and then notifies the user via a pop-up display or audio notification using an alert notification module. Specifically, the device notifies the user of an alert stating that "Child A has not arrived at school."

[2149] Input: Alert message sent from FCM

[2150] Output: Alert notification (pop-up display, audio notification)

[2151] Step 7:

[2152] Recommended Actions

[2153] The server generates specific recommended actions to address the detected anomaly and sends them to the user's terminal. For example, the server might generate and send the recommended action, "Child A is late arriving at school. Please contact the school immediately."

[2154] Input: Anomaly detection result (singular behavior, anomaly)

[2155] Output: Recommended action message

[2156] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[2157] This invention relates to a childcare and elderly care support system that combines an emotion engine that recognizes user emotions, and provides a means for rapidly detecting singular behaviors and abnormal health conditions and providing appropriate alerts to the user.

[2158] In addition to collecting and managing activity information entered by users, this system uses an emotion engine to recognize the user's emotional state, enabling more accurate analysis and alert generation.

[2159] System Configuration

[2160] 1. User terminal

[2161] Data entry interface: An interface for users to input activity information. Examples include smartphone and tablet apps.

[2162] Data transmission module: A module that sends the entered activity information to the server.

[2163] Alert receiving module: A module for receiving alerts from the server.

[2164] Alert notification module: A module that notifies the user of received alerts.

[2165] Emotion Recognition Module: A module that uses an emotion engine to analyze the user's emotions in real time as they input data.

[2166] 2. Server

[2167] Data receiving module: Receives activity information sent from the user's terminal.

[2168] Database: Stores received activity and sentiment information.

[2169] Analysis Module: Analyzes and detects anomalies and singular behaviors based on stored data.

[2170] Alert generation module: Based on the analysis results, it generates alerts as needed and sends them to the user's terminal.

[2171] Health suggestion module: Generates health maintenance suggestions in care mode.

[2172] Emotion Analysis Module: Uses an emotion engine to perform data analysis based on the results of user emotion analysis.

[2173] Program execution flow

[2174] The system's processing flow is explained in detail below.

[2175] Data collection

[2176] User: Activity information is entered through the client application's data entry interface. Additionally, an emotion recognition module analyzes the user's emotions in real time during the input process.

[2177] Specific example: A user enters "Child A's expected arrival time at school is 8:30 AM," and the user's emotions (e.g., anxiety, impatience) are analyzed at that time.

[2178] Data transmission

[2179] Terminal: Sends input activity and emotion information to the server via a data transmission module.

[2180] Specific example: The device sends data to the server: "Child A's estimated arrival time at school: 8:30 AM" and "User's emotional state: Anxious."

[2181] Data reception and storage

[2182] Server: The data receiving module receives data sent from the terminal and stores it in the database.

[2183] Specific example: The server saves the following data to the database: "Child A's estimated arrival time at school: 8:30 AM" and "User's emotional state: Anxious."

[2184] Data Analysis

[2185] Server: Uses the analysis module to perform analysis based on stored activity information and sentiment analysis results to detect singular behaviors and anomalies.

[2186] Specific example: The server references the school's GPS data and time clock information, detects that child A has not arrived at school by 8:45 AM, and that the user's emotional state is "anxious," and determines that this is an anomaly.

[2187] Alert generation and sending

[2188] Server: When singular behavior or anomalies are detected, the alert generation module generates an alert. The alert content is also adjusted based on the sentiment analysis results.

[2189] Specific example: The server generates an alert stating "Child A has not arrived at school," and considering the user's emotional state of anxiety, the alert is modified to encourage a more prompt response.

[2190] Alert notification

[2191] Terminal: The alert receiving module receives alerts from the server, and the alert notification module notifies the user.

[2192] Specific example: The device notifies the user via a pop-up alert stating, "Child A has not arrived at school."

[2193] Health assessment and suggestions for caregiving mode

[2194] Data collection and transmission

[2195] User: Uses a client application to input activity information and health status of elderly individuals. During input, an emotion recognition module analyzes the user's emotions in real time.

[2196] Specific example: Users input information such as "walking distance" and "meal content," and their emotional state (e.g., feeling safe, satisfied) is analyzed at that time.

[2197] Data reception and storage

[2198] Server: Receives activity and emotion information sent by the data receiving module and stores it in the database.

[2199] Specific example: The server stores information such as "elderly person B's walking distance and diet" and "user's emotional state: feeling safe" in a database.

[2200] Health assessment and recommendations

[2201] Server: Analyzes data stored in the health assessment module to evaluate health status. It also adjusts suggestions based on the emotion analysis results.

[2202] Specific example: The server compares past data and assesses that "elderly person B is not getting enough exercise," and since their emotional state is "reassured," it generates more proactive exercise suggestions.

[2203] Proposal submission and notification

[2204] Server: The health suggestion module generates health maintenance suggestions based on the evaluation results and sends them to the user's terminal.

[2205] Terminal: Receives proposals and notifies the user.

[2206] Specific example: The server generates a suggestion such as "We recommend taking a 30-minute walk every day," and the device notifies the user of this.

[2207] In this way, by combining this system with an emotion engine, it becomes possible to provide more accurate alert notifications and suggestions that take into account the user's emotional state, enabling the management of important activity information in childcare and elder care and prompt responses.

[2208] The following describes the processing flow.

[2209] Step 1:

[2210] User: Enters activity information using the client application's data entry interface. Simultaneously, the emotion recognition module analyzes the user's emotions in real time as they are being entered.

[2211] For example, a user might enter "Child A's expected arrival time at school is 8:30 AM," and the user's emotional state (e.g., anxiety, impatience) is then analyzed.

[2212] Step 2:

[2213] Terminal: Sends input activity and emotion information to the server via a data transmission module.

[2214] As a specific example, the device sends data to the server such as "Child A's estimated arrival time at school is 8:30" and "User's emotional state: Anxious."

[2215] Step 3:

[2216] Server: Receives data sent from the terminal using the data receiving module.

[2217] As a specific example, the server receives data indicating "Child A's estimated arrival time at school is 8:30 AM" and "User's emotional state: Anxious."

[2218] Step 4:

[2219] Server: Saves received data to the database.

[2220] As a concrete example, the server stores the data it receives, "Child A's estimated arrival time at school: 8:30 AM" and "User's emotional state: Anxious," into a database.

[2221] Step 5:

[2222] Server: Uses the analysis module to perform analysis based on stored activity information and sentiment analysis results to detect singular behaviors and anomalies.

[2223] As a specific example, the server refers to the school's GPS data and time clock information, detects that child A has not arrived at school by 8:45 AM, and that the user's emotional state is "anxious," and determines that this is an anomaly.

[2224] Step 6:

[2225] Server: When singular behavior or anomalies are detected, the alert generation module generates an alert. The alert content is also adjusted based on the sentiment analysis results.

[2226] As a concrete example, the server generates an alert stating "Child A has not arrived at school," and considering the user's emotional state of anxiety, the alert is designed to prompt a more rapid response.

[2227] Step 7:

[2228] Server: Sends generated alerts to the client application.

[2229] As a concrete example, the server sends an alert to the terminal stating, "Child A has not arrived at school."

[2230] Step 8:

[2231] Terminal: The alert receiving module receives alerts from the server.

[2232] As a concrete example, the device receives an alert stating, "Child A has not arrived at school."

[2233] Step 9:

[2234] Terminal: Notifies the user of alerts received by the alert notification module.

[2235] As a concrete example, a pop-up notification appears on the user's smartphone stating, "Child A has not arrived at school."

[2236] Health assessment and suggestions for caregiving mode

[2237] Step 1:

[2238] User: Uses a client application to input activity information and health status of elderly individuals. Simultaneously, an emotion recognition module analyzes the user's emotions in real time as they input data.

[2239] As a concrete example, users input information such as "walking distance" and "meal content," and their emotional state (e.g., feeling safe, satisfied) is analyzed at that time.

[2240] Step 2:

[2241] Terminal: Sends the entered information to the server.

[2242] As a specific example, the device sends information such as "elderly person B's walking distance and diet" and "user's emotional state: feeling safe" to the server.

[2243] Step 3:

[2244] Server: Receives information sent by the data receiving module and stores it in the database.

[2245] As a specific example, the server stores information such as "elderly person B's walking distance and diet" and "user's emotional state: feeling secure" in a database.

[2246] Step 4:

[2247] Server: Analyzes data stored in the health assessment module to evaluate health status. It also adjusts suggestions based on the emotion analysis results.

[2248] As a concrete example, the server compares past data and evaluates that "elderly person B is not getting enough exercise," and since their emotional state is "reassured," it generates more proactive exercise suggestions.

[2249] Step 5:

[2250] Server: The health suggestion module generates health maintenance suggestions based on the evaluation results and sends them to the user's terminal.

[2251] As a concrete example, the server generates a suggestion such as "We recommend taking a 30-minute walk every day" and sends it to the terminal.

[2252] Step 6:

[2253] Terminal: Receives proposals and notifies the user.

[2254] For example, a notification such as "We recommend taking a 30-minute walk every day" might appear on the user's smartphone.

[2255] In this way, by combining this system with an emotion engine, it becomes possible to provide more accurate alert notifications and suggestions that take into account the user's emotional state, enabling the management of important activity information in childcare and elder care and prompt responses.

[2256] (Example 2)

[2257] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[2258] Conventional childcare and eldercare support systems collect and analyze activity information without considering the user's emotional state, resulting in low accuracy in detecting anomalies and abnormalities, and a failure to provide appropriate alerts and suggestions. In addition, because emotional information is not utilized, responses to users are uniform, making it difficult to provide appropriate responses tailored to individual situations.

[2259] The identification processing by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for collecting activity information and emotion information input by the user; means for transmitting the activity information and emotion information to the server; means for the server to receive the activity information and emotion information and store it in a database; means for the server to analyze the stored activity information and emotion information and detect singular behavior or anomalies; means for the server to generate an alert based on the detected anomalies and emotion analysis results and send it to the client application; and means for the terminal to notify the user of the alert received. This enables highly accurate alert notifications and suggestions that take into account the user's emotional state.

[2260] A "user" refers to an individual who inputs activity and emotional information into the system.

[2261] "Activity information" refers to information about daily activities and events that users input into the system.

[2262] "Emotional information" refers to data that analyzes a user's emotional state in real time.

[2263] A "server" refers to the core of a system that receives, stores, and analyzes activity and sentiment information, generates alerts and suggestions, and sends them to client applications.

[2264] A "database" refers to a storage device used to store received activity and emotional information.

[2265] An "analysis module" refers to software used to detect anomalies or anomalies based on stored data.

[2266] An "alert generation module" refers to software that has the function of generating alerts based on the detection of anomalies and the results of sentiment analysis.

[2267] A "client application" refers to an application on a device that a user uses to input activity and sentiment information and to receive alerts and suggestions.

[2268] "Care mode" refers to the operating mode of a system that evaluates the activity information and health status of elderly people and makes suggestions for maintaining their health.

[2269] A "health assessment module" refers to software that evaluates health status based on stored activity and emotional information and generates recommendations.

[2270] This invention is a system intended to support childcare and elder care, and incorporates an emotion engine that recognizes the user's emotions. This system can quickly detect unusual behaviors and abnormal health conditions, and provide the user with appropriate alerts and suggestions.

[2271] System Configuration

[2272] 1. User terminal

[2273] Data entry interface: An interface for users to input activity information. Examples include smartphone and tablet apps.

[2274] Data transmission module: A module that transmits input activity and emotion information to the server.

[2275] Alert receiving module: A module for receiving alerts from the server.

[2276] Alert notification module: A module that notifies the user of received alerts.

[2277] Emotion Recognition Module: A module that uses an emotion engine to analyze the user's emotions in real time as they input data.

[2278] 2. Server

[2279] Data receiving module: Receives activity and emotion information sent from the user's terminal.

[2280] Database: Stores received activity and sentiment information.

[2281] Analysis Module: Analyzes and detects anomalies and singular behaviors based on stored data.

[2282] Alert generation module: Based on the analysis results, it generates alerts as needed and sends them to the user's terminal.

[2283] Health suggestion module: Generates health maintenance suggestions in care mode.

[2284] Emotion Analysis Module: Uses an emotion engine to perform data analysis based on the results of user emotion analysis.

[2285] Specific examples of program processing

[2286] User: Enters activity information through the client application's data entry interface. During input, the emotion recognition module analyzes the user's emotions in real time.

[2287] Specific example: A user enters "Child A's expected arrival time at school is 8:30 AM." At this time, the user's emotions (e.g., anxiety or impatience) are analyzed.

[2288] Terminal: Sends activity and emotion information entered via the data transmission module to the server.

[2289] Specific example: The device sends data to the server: "Child A's estimated arrival time at school: 8:30 AM" and "User's emotional state: Anxious."

[2290] Server: The data receiving module receives data sent from the terminal and stores it in the database.

[2291] Specific example: The server saves the following data to the database: "Child A's estimated arrival time at school: 8:30 AM" and "User's emotional state: Anxious."

[2292] Server: Uses an analysis module to detect singular behaviors and anomalies based on stored activity information and sentiment analysis results.

[2293] Specific example: The server checks the school's GPS data and time clock information, detects that child A has not arrived at school by 8:45 AM, and also detects that the user's emotional state is "anxious," and determines that this is an anomaly.

[2294] Server: When singular behavior or anomalies are detected, the alert generation module generates an alert and adjusts the content of the alert considering the sentiment analysis results.

[2295] Specific example: The server generates an alert stating "Child A has not arrived at school," and considering the user's emotional state of anxiety, the alert is modified to encourage a more prompt response.

[2296] Terminal: The alert receiving module receives alerts from the server, and the alert notification module notifies the user.

[2297] Specific example: The device notifies the user via a pop-up alert stating, "Child A has not arrived at school."

[2298] Specific examples of health assessment and recommendations for caregiving.

[2299] User: Uses a client application to input activity information and health status of elderly individuals. During input, an emotion recognition module analyzes emotions in real time.

[2300] Specific example: When a user enters information such as "walking distance" or "meal content," their emotions (e.g., feeling safe or satisfied) are analyzed.

[2301] Server: Receives activity and emotion information sent by the data receiving module and stores it in the database.

[2302] Specific example: The server stores information such as "elderly person B's walking distance and diet" and "user's emotional state: feeling safe" in a database.

[2303] Server: Analyzes data stored in the health assessment module and evaluates health status. Adjusts suggestions based on the emotion analysis results.

[2304] Specific example: The server compares data with past data and assesses that "elderly person B is not getting enough exercise," and based on their emotional state being "reassured," it generates more proactive exercise suggestions.

[2305] Server: The health suggestion module generates health maintenance suggestions based on the evaluation results and sends them to the user's terminal.

[2306] Terminal: Receives proposals and notifies the user.

[2307] Specific example: The server generates a suggestion such as "We recommend taking a 30-minute walk every day," and the device notifies the user of this.

[2308] Example prompts for a generative AI model

[2309] Example prompt: "Describe a system that takes input information about daily activities related to childcare or elder care (e.g., a child's arrival time at school or the elderly person's meals), performs real-time sentiment recognition, and generates appropriate alerts or suggestions if anomalies are detected."

[2310] The flow of the specific processing in Example 2 will be explained using Figure 13.

[2311] Step 1:

[2312] Users input activity and emotion information through the data entry interface of the client application. This allows for real-time recording of the user's activity and emotion data.

[2313] Specific operation: The user opens a smartphone app and enters "Child A's estimated arrival time at school: 8:30." Simultaneously, the emotion recognition module analyzes the user's facial expressions and tone of voice to recognize emotions such as anxiety or impatience.

[2314] Input: Text information entered by the user and real-time sentiment data (facial expressions and voice).

[2315] Output: Activity information and analyzed sentiment information.

[2316] Step 2:

[2317] The terminal's data transmission module sends the input activity ...

Claims

1. A means of collecting activity information entered by the user, Means for transmitting the activity information to a server, The server has means for receiving the activity information and storing it in a database, The server analyzes stored activity information and has means for detecting singular behavior or anomalies. The server generates an alert based on the detected anomaly and sends it to the client application, A means for notifying the user of alerts received by the terminal, A system that includes this.

2. The system according to claim 1, wherein the server includes means for evaluating the health status based on activity information stored in care mode, generating suggestions for maintaining health, and transmitting them to a client application.

3. The system according to claim 1, wherein the server includes means for sending alerts generated based on the detection of anomalies in stored data to a client application in real time.

Images