system

Abstract

We provide the system. [Solution] Information gathering methods for learning about the lifestyles of the elderly, A data analysis method that analyzes collected information to identify behavioral characteristics, A timetable generation means that generates an optimal notification timetable based on behavioral characteristics, Information transmission means for notifying users based on the generated timetable, An anomaly detection means that detects abnormal behavioral characteristics and notifies an external organization, Information sharing means to facilitate a rapid response in emergencies, A system that includes this.

Description

Technical Field

[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 the chatbot's character, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance that responds 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] With the increase in the elderly population, especially for the elderly living alone to live safely, means are needed to prevent forgetting important schedules and taking medications due to memory decline. However, existing reminder systems are based on general schedules and are not optimized according to the individual living patterns of the elderly, and notifications may not be made at appropriate times. Therefore, a personalized notification system that is useful for the elderly is required.

Means for Solving the Problems

[0005] This invention utilizes a data collection method that learns the lifestyles of elderly individuals to realize personalized notifications based on their individual daily rhythms. The collected data is stored in a cloud database and analyzed using machine learning algorithms. This generates an optimal notification schedule and provides customized notifications according to the user's preferences. Furthermore, it has a function to automatically notify external organizations if abnormal behavioral patterns are detected. This provides a system that improves the quality of life for elderly individuals and supports a safe and secure life.

[0006] "Data collection methods" refer to functions that collect information about the behavior and lifestyle patterns of elderly people from sensors and devices.

[0007] "Data analysis methods" refer to the methods and processes used to process collected data and identify user behavior patterns.

[0008] "Schedule generation means" refers to a function that determines the optimal time and method of notification to the user based on identified behavioral patterns.

[0009] "Notification sending method" refers to a function that sends reminders and alerts to users based on a pre-set schedule.

[0010] An "anomaly detection method" refers to a function that recognizes unusual behavior or changes in habits and sends notifications to external parties as needed.

[0011] A "cloud database" refers to a database on a remote server that allows data to be stored, managed, and accessed via the internet.

[0012] A "machine learning algorithm" refers to a computational method that automatically finds patterns and rules from data and uses that information to make predictions and decisions.

[0013] "Customization" refers to adjusting and configuring functions and services according to the individual preferences and needs of the user.

[0014] "Personalized notifications" refer to reminders and alerts that are tailored to the user's individual lifestyle and preferences. [Brief explanation of the drawing]

[0015] [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] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This 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] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This 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] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Figure 11] This is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] This 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 Embodiment 2 when the 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 the emotion engine is combined.

Mode for Carrying Out the Invention

[0016] Hereinafter, an example of an embodiment of the system according to the technology of the present disclosure will be described with reference to the accompanying drawings.

[0017] First, the terms used in the following description will be explained.

[0018] In the following embodiments, a tagged processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Also, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), and the like.

[0019] In the following embodiments, a tagged RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0020] In the following embodiments, a tagged storage is one or more non-volatile storage devices that store various programs and various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes, etc.

[0021] 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).

[0022] 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."

[0023] [First Embodiment]

[0024] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0025] 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.

[0026] 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).

[0027] 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.

[0028] 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.

[0029] 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.

[0030] 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.

[0031] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0032] 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.

[0033] 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.

[0034] 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.

[0035] 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".

[0036] This invention is a personalized notification system for supporting the elderly, improving the safety and comfort of the user's daily life. The embodiments for carrying out the invention and the processing of its program are described below.

[0037] The device collects data on the behavior and lifestyle patterns of elderly individuals from sensor devices. For example, it uses smartphones and smartwatches to record location information, steps taken, and heart rate, and to understand their daily routines. This information is collected automatically without requiring user awareness, thus reducing the burden on elderly individuals.

[0038] The server transmits the collected data to a cloud environment for secure storage. The data is organized for each individual user and stored in a dedicated database. Machine learning algorithms are used to analyze this data and identify each user's unique behavioral patterns and lifestyle rhythms.

[0039] Based on the analysis results, the server generates a notification schedule best suited to each user. For example, reminders can be set based on behavioral patterns to manage daily medication times or important appointments. This schedule is customized according to each user's preferences and is delivered in the most optimal format, such as voice notifications, vibrations, or screen displays.

[0040] The device sends reminders to the user according to the generated schedule. When the time comes, a notification such as "It's time to take your medicine" appears on the smartphone. Data about the completed actions is also sent back to the server and used for future analysis and schedule generation.

[0041] Furthermore, the server has a mechanism to respond quickly using anomaly detection means if any unusual behavior is detected. In this case, notifications can be automatically sent to family members or medical institutions, ensuring the safety of the elderly.

[0042] As an example of this system, suppose user C needs to take their blood pressure medication at 7:00 AM every morning. Based on the user's daily routine data, the server schedules a notification to be sent to the device at 6:45 AM every day, and the device smoothly delivers the notification to the user. If the user fails to respond to the notification for three consecutive days, the system sends a notification to a family member to ensure that necessary support is provided.

[0043] This invention reduces anxiety caused by forgetfulness in the elderly, making it possible to manage daily life more safely and efficiently.

[0044] The following describes the processing flow.

[0045] Step 1:

[0046] The device collects data about the lifestyle of elderly individuals. This is done via smartphones or smartwatches and includes location information, step count, heart rate, and schedule information. This data is temporarily stored within the device.

[0047] Step 2:

[0048] The device sends the collected data to the server at regular intervals. The transmitted data is encrypted to protect privacy. After transmission, the data on the device is periodically updated.

[0049] Step 3:

[0050] The server stores received data in a cloud database. This data is organized by user and immediately available for analysis. The system ensures data integrity while always reflecting the latest information.

[0051] Step 4:

[0052] The server uses machine learning algorithms to analyze user behavior patterns based on accumulated data. This reveals the user's typical daily schedule and activity patterns.

[0053] Step 5:

[0054] The server automatically generates individual notification schedules based on the analyzed data. The schedules reflect the user's behavior patterns and set reminders at optimal times.

[0055] Step 6:

[0056] The server sends the generated schedule to the device, which then prepares to notify the user. The schedule is designed to notify the user in the most suitable way (e.g., voice notification, screen display, vibration).

[0057] Step 7:

[0058] The device sends a notification to the user at a set time. For example, when it's time to take medication, a notification saying "It's time to take your medication" will appear on the screen. Once the user acknowledges the notification, a record of that is sent to the server.

[0059] Step 8:

[0060] The server collects user response data and uses it for future analysis and scheduling improvements. This improves the accuracy of reminders and user convenience.

[0061] Step 9:

[0062] The server continuously monitors user behavior for any abnormalities. If an abnormality is detected, for example, if there is no response to multiple notifications, notifications are automatically sent to family members or healthcare providers to ensure appropriate support is provided.

[0063] (Example 1)

[0064] 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."

[0065] In daily life, older adults may face difficulties in efficiently and safely managing their health and performing important daily tasks. In particular, failure to properly take regular medications or manage important appointments increases health risks. Furthermore, a lack of prompt response when older adults exhibit abnormal behavior can lead to further danger. Therefore, personalized support based on the individual behavioral characteristics of older adults is needed to improve safety and comfort.

[0066] 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.

[0067] In this invention, the server includes information acquisition means for acquiring biometric data and learning the user's behavioral patterns, analysis means for analyzing the acquired information and identifying behavioral characteristics, and schedule creation means for creating optimized notification schedules based on behavioral characteristics. This makes it possible to contribute to the health and safety of the elderly.

[0068] "Biometric data" refers to information such as location data, step count, and heart rate acquired to indicate the activity level and health status of elderly individuals.

[0069] "Information acquisition means" refers to a system for collecting biometric data from sensor devices and learning the user's behavioral patterns.

[0070] "Analysis means" refers to techniques used to analyze acquired information and identify user behavioral characteristics.

[0071] A "schedule creation method" is a method for generating an optimal notification schedule for a user based on analyzed behavioral characteristics.

[0072] An "information transmission method" is a system that appropriately transmits necessary information to users according to a created schedule.

[0073] An "anomaly detection method" is a technology that detects behavioral characteristics that are different from the norm and transmits information to an external mechanism as needed.

[0074] This invention is a system designed to support the elderly, learning each user's individual lifestyle and enabling safe and efficient daily management. Specifically, it uses smartphones and smartwatches as sensor devices to automatically collect biometric data. These devices acquire data such as the user's location, steps taken, and heart rate, providing various biometric information.

[0075] The device sends this data to the cloud, where necessary information is accumulated through collaboration with the server. The server utilizes cloud-based storage media and employs machine learning algorithms. This allows for precise analysis of the collected information and identification of user behavioral characteristics.

[0076] Next, the server generates a notification schedule optimized for the user's behavior based on the analysis results. The generated schedule is customized in various forms, such as voice, vibration, and screen display, and adjusted according to the user's preferences. For example, if a user needs to take medication at 7:00 AM every morning, the server will set up a notification to be sent to the device at 6:45 AM.

[0077] Based on this generated schedule, the device sends notifications to the user at the specified times. This allows the user to avoid forgetting important appointments and tasks and to respond in a timely manner. Data on whether the user responded to the notification is also sent from the device to the server, which is used to improve future notification schedules.

[0078] If the server detects any unusual behavioral patterns, it will use anomaly detection measures to respond quickly. If necessary, it will send alerts to family members or medical institutions to ensure user safety.

[0079] As a concrete example, the following prompt is given: "Please explain, with specific examples, how to generate a personalized notification schedule based on the lifestyle pattern data of elderly individuals."

[0080] This system allows users to live their lives with peace of mind, and also provides families with a means to remotely monitor the condition of elderly individuals.

[0081] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0082] Step 1:

[0083] The device uses sensor devices (smartphones and smartwatches) to collect biometric data (location information, steps, heart rate, etc.). This data is used to understand the user's daily behavior and health status. It receives biometric data from sensors as input and converts it into a format for transmission to the cloud as output. Specifically, each device periodically collects data and standardizes the data format as needed.

[0084] Step 2:

[0085] The device sends the collected data to the cloud environment. The cloud receives the data while protecting privacy by using data encryption technology. It takes standardized data sent from the device as input and securely stores it on a storage medium in the cloud as output. Specifically, this involves transferring data in real time via a data transmission protocol and storing it in a cloud database.

[0086] Step 3:

[0087] The server analyzes data stored in the cloud. Using machine learning algorithms, it analyzes user behavioral characteristics and identifies patterns. It uses a large amount of biometric data acquired from the cloud as input and extracts behavioral patterns based on user characteristics as output. Specifically, it performs data cleansing, then applies algorithms to generate various statistical information.

[0088] Step 4:

[0089] The server generates an optimal notification schedule for the user based on the analysis results. It uses behavioral patterns extracted by the server as input and creates a notification schedule optimized for the user's daily routine as output. Specific actions include setting notification timings that take into account the user's specific needs (e.g., medication timing).

[0090] Step 5:

[0091] The device receives notification schedules generated by the server and sends notifications to the user. It receives schedule information provided by the server as input and notifies the user in the form of audio notifications, vibrations, screen displays, etc. The specific operation includes a process where the device triggers a notification at a specified time and provides an alert to the user.

[0092] Step 6:

[0093] The server collects user responses to notifications as data again to use for subsequent analysis. It receives user response data sent from the terminal as input and generates data to improve scheduling through continuous pattern analysis as output. Specifically, it checks whether the user followed the notification and whether there were any anomalies, and updates the dataset to reflect the results.

[0094] Step 7:

[0095] The server utilizes a function to send notifications to external organizations when it detects abnormal behavior. It extracts patterns that deviate from normal behavior as input, and sends alerts to family members or medical institutions as needed as output. The specific operation involves data analysis using an anomaly detection algorithm and automatic message sending to configured contacts.

[0096] (Application Example 1)

[0097] 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."

[0098] In the lives of the elderly, daily health management and schedule management are often not properly carried out, and they frequently forget to take medication or exercise, which can lead to a deterioration of their health and safety. Furthermore, when abnormal behavior occurs, prompt action may not be taken, and the safety of the elderly is not adequately ensured. To improve this situation, an efficient and personalized notification system is needed.

[0099] 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.

[0100] In this invention, the server includes information gathering means, data analysis means, timetable generation means, information transmission means, anomaly detection means, and information linking means. This enables continuous management of the daily lives of elderly people and provides optimal notifications based on individual behavioral patterns. Furthermore, because it can quickly cooperate with external organizations to respond when abnormal behavior is detected, it becomes possible to provide a safer and more comfortable living environment.

[0101] "Information gathering means" refers to a system that automatically collects data on the lifestyles of elderly people, and the information obtained through smart devices, etc.

[0102] "Data analysis means" refers to a processing method for analyzing collected data and identifying the behavioral characteristics of elderly people, and may utilize machine learning algorithms.

[0103] The "timetable generation means" is a device that has the function of creating individually optimized notification schedules based on analyzed behavioral characteristics.

[0104] An "information transmission means" is a system for providing users with information such as reminders based on a generated notification schedule.

[0105] An "anomaly detection mechanism" is a system for detecting behavioral characteristics that are different from the norm and responding quickly, and includes a function to send notifications to external parties as needed.

[0106] "Information sharing means" refers to communication methods used to share detected anomaly information and important notifications with external organizations to facilitate a rapid response.

[0107] To implement this invention, a smart device is first used as a means of information gathering. Specifically, sensors in a smartphone or smartwatch are used to continuously collect data such as the elderly person's location, steps taken, and heart rate. This data is acquired automatically, without the user's awareness, and the information is transmitted to a cloud server.

[0108] The server stores this collected data in a centralized database and analyzes it using machine learning algorithms, specifically TENSORFLOW®. The data analysis identifies each user's behavioral characteristics and generates individually optimized notification schedules based on these characteristics. This schedule generation method can, for example, estimate the timing of a user's medication intake or exercise.

[0109] The user's device sends appropriate reminders via the information transmission means, according to the schedule created by the timetable generation means. Reminders may be provided as voice notifications or text messages. The anomaly detection means identifies unusual behavioral characteristics and uses the information sharing means to quickly notify external organizations and family members based on the results.

[0110] For example, if an elderly person needs to take their blood pressure medication at 8:00 AM every morning, the system is designed to send a reminder to their smartphone at 7:50 AM based on data analysis. If the user fails to heed this notification, and this continues for three consecutive days, the system will automatically contact their family through an information sharing mechanism.

[0111] An example of a prompt message might be, "Write a scenario for a care support app that analyzes the behavioral patterns of elderly people and sends reminders at specific times." Such a system would make life safer and more comfortable for the elderly.

[0112] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0113] Step 1:

[0114] The device automatically collects data such as the elderly person's location, steps taken, and heart rate using the smart device's sensors. This collected data is then sent directly to a cloud server as input. This process involves utilizing the device's sensor data, continuously acquiring data in the background, and uploading the data to the server via the network.

[0115] Step 2:

[0116] The server stores the data sent to the cloud in a centralized database. On the server, this data is formatted into a pre-configured format and then organized and saved in the storage space allocated to each user. This is the server's input, and the organized information in the database is the output.

[0117] Step 3:

[0118] The server begins analyzing the accumulated data using machine learning algorithms. Specifically, TensorFlow is used to model and analyze the behavioral characteristics of each user. This process identifies each user's behavioral pattern, and the results are stored as output. The data before analysis is the input, and the behavioral patterns resulting from the analysis are the output.

[0119] Step 4:

[0120] The server uses a timetable generation mechanism based on behavioral patterns to create an optimized notification schedule. In this step, based on the analysis results, the server calculates the notification timing according to the user's daily routine and determines the specific reminder content. The resulting timetable is then output.

[0121] Step 5:

[0122] The device retrieves the notification schedule sent from the server and notifies the user at the appropriate time. This notification is presented to the user as an audio alarm or a push notification on the screen. In this step, the output is the notification content to be provided to the user.

[0123] Step 6:

[0124] The server uses anomaly detection means to detect behavior that differs from the received behavior pattern. If an anomaly exceeding a set threshold is detected, it notifies external organizations and family members through information sharing means. The detection of abnormal behavior becomes the input, and a warning notification is generated as the output.

[0125] 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.

[0126] This invention provides advanced support that takes into account the user's emotional state by combining a personalized notification system for assisting the elderly with an emotion engine. An embodiment of this system will be described in detail.

[0127] The device collects basic data about the elderly person's activity and lifestyle patterns through sensor devices. This data includes location information, steps taken, heart rate, and schedule lists. The device also uses its built-in camera and microphone to activate an emotion engine that recognizes the user's emotions. It can evaluate the user's emotions in real time by utilizing facial expression analysis, voice tone analysis, and even linguistic analysis in text.

[0128] The server simultaneously transmits both collected behavioral and emotional data to a cloud database for secure storage. The data is precisely analyzed to identify not only typical user behavioral patterns but also emotional patterns. Machine learning algorithms are used in this analysis, combining historical and new data to provide responses tailored to user needs.

[0129] The emotion data recognized by the emotion engine is used to generate customized notifications tailored to the user's emotional state. For example, if the user is stressed, the content of the notification can be changed to softer language or words of encouragement. Furthermore, the emotion data is evaluated in correlation with behavioral data, and the notification schedule is adjusted to match the user's optimal mental state.

[0130] The device sends notifications to the user based on the generated schedule. These notifications are delivered at the appropriate time and in the appropriate manner, taking into account the user's emotional state. For example, if the user is feeling tired when it's time to take medication, the voice tone can be changed to a calmer one, and the notification can say something like, "Take your medication after you've had a short rest."

[0131] The presence of an emotion engine allows the system to respond quickly to changes in the user's emotions and provide emotional support in daily life. Furthermore, by combining it with conventional anomaly detection functions, it can notify family members and medical institutions if abnormalities occur not only in the user's behavior but also in their emotions.

[0132] Thus, the present invention incorporates cutting-edge technology to improve the quality of life for the elderly and provide a safe and emotionally comfortable living environment.

[0133] The following describes the processing flow.

[0134] Step 1:

[0135] The device collects data related to the activities and lifestyle patterns of elderly individuals using sensor devices. Specifically, this includes biometric information such as location, steps taken, and heart rate. This information is stored within the device as basic data for understanding daily lifestyle habits.

[0136] Step 2:

[0137] The device utilizes its built-in camera and microphone to recognize the user's emotional state in real time. This process analyzes the user's facial expressions and voice tone to determine their current emotional state. As a result, emotional data is recorded within the device.

[0138] Step 3:

[0139] The device periodically sends collected behavioral and emotional data to a server. The transmitted data is encrypted, and secure data storage in the cloud is guaranteed.

[0140] Step 4:

[0141] The server analyzes data stored in the cloud database using machine learning algorithms. It simultaneously analyzes behavioral and emotional patterns to form an intelligent understanding based on the individual needs and requirements of the user.

[0142] Step 5:

[0143] The server dynamically generates notification content and timing based on the user's emotional state. For example, it might generate calming notifications for users experiencing stress and adjust the notification schedule accordingly.

[0144] Step 6:

[0145] The server sends the generated notifications and schedules to the device. This prepares the notifications and enables user-optimized reminders.

[0146] Step 7:

[0147] The device will send notifications to the user based on a schedule. These notifications will be delivered in a way and with content that takes into account the user's emotional state. For example, a message such as "Take your medication after you have relaxed" may be presented in a calm voice or on-screen display.

[0148] Step 8:

[0149] The server collects user responses as data after a notification is sent and uses this data to optimize the next notification schedule.

[0150] Step 9:

[0151] The server monitors the user's behavior and emotional state for any abnormalities. If an emotional abnormality is detected, it automatically notifies family members and medical institutions so that necessary support can be provided.

[0152] (Example 2)

[0153] 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".

[0154] Supporting the elderly requires not only understanding their behavioral patterns but also providing flexible responses tailored to their individual emotional states. However, conventional systems have struggled to quickly detect emotional changes and respond appropriately. Furthermore, they lacked mechanisms to provide timely notifications when abnormal emotional states occurred. This resulted in a problem where the quality of life for the elderly could not be adequately improved.

[0155] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0156] In this invention, the server includes information gathering means for learning the lifestyle and emotional state of elderly people, information analysis means for analyzing the collected information to identify behavioral and emotional patterns, and plan generation means for generating an optimal notification schedule based on the behavioral and emotional patterns. This enables notification delivery tailored to the individual emotional state of elderly people, thereby improving their quality of life and providing a safe environment.

[0157] "Information gathering means" refers to devices or software used to acquire data on the lifestyle and emotional state of elderly people.

[0158] "Information analysis methods" refer to technologies that use collected data to identify patterns in the behavior and emotions of elderly individuals.

[0159] The "plan generation method" is a function that creates an optimal notification schedule for elderly people based on the analysis results.

[0160] "Notification delivery means" refers to a device or method that provides users with emotionally relevant information according to a generated schedule.

[0161] An "anomaly detection system" is a mechanism that quickly identifies changes in emotions and behavior and issues warnings to external organizations as needed.

[0162] A "remote data recording device" is a cloud or server environment for securely storing collected information.

[0163] "Data analysis technology" refers to analytical methods used to evaluate collected information and gain useful insights.

[0164] This invention is a personalized notification system for supporting the elderly, providing notifications that take into account the user's lifestyle and emotional state. This system is composed of a combination of information gathering means, information analysis means, and plan generation means.

[0165] The device functions as a means of information gathering, acquiring data on the daily activities and emotional state of elderly individuals. This includes sensor devices for acquiring location information, step count, and heart rate, as well as cameras and microphones for analyzing the user's facial expressions and voice. This makes it possible to assess the user's emotions in real time.

[0166] The server functions as an information analysis tool, storing data collected from terminals in a remote data recording device. Furthermore, it analyzes the data using machine learning algorithms to identify specific behavioral and emotional patterns. Based on these analysis results, the plan generation tool creates an optimal notification schedule.

[0167] Based on this schedule, the device acts as a notification delivery mechanism, providing users with appropriate and customized notifications. The content of the notifications changes according to the user's emotional state, allowing for flexible responses. For example, if the user is feeling stressed, the device can use a calmer voice tone and notify them with a message like, "Take a short break and then take your medicine."

[0168] As a concrete example, the following is an example of a prompt statement to be input to a generative AI model.

[0169] Prompt example: "A 70-year-old female user appears more tired than usual during her recent walks. Use the emotion engine to create an encouraging message for the user based on this information."

[0170] This system allows elderly people to live their daily lives with peace of mind, improving both their quality of life and safety at the same time.

[0171] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0172] Step 1:

[0173] The device uses sensor devices to collect data about the daily lives of elderly individuals. This data includes location information, step count, and heart rate. Using this physiological data as input, the device uses its built-in camera and microphone to analyze the user's facial expressions and voice in real time using an emotion engine. The output is data indicating the user's emotional state.

[0174] Step 2:

[0175] The server receives and stores behavioral and emotional data transmitted from terminals in a remote data recording device. Inputs include data from terminals, which the server stores in a secure cloud environment. Outputs are datasets prepared for analysis. Based on this dataset, the server uses machine learning algorithms to identify behavioral and emotional patterns.

[0176] Step 3:

[0177] The server analyzes identified behavioral and emotional patterns and generates an optimized notification schedule based on the user's state. The input is the dataset obtained in step 2, and the output is a personalized notification schedule for the user. In this step, a generative AI model is used to generate prompts that adjust the notification content. For example, the prompt might say, "The user is tired, please create a message to help them relax."

[0178] Step 4:

[0179] The device delivers notifications to the user at the appropriate time according to a notification schedule sent from the server. The input is the generated notification schedule, and the output is the customized notification provided to the user. Notifications are delivered via voice assistant or screen display and respond flexibly to the user's emotional state. For example, it can support the user in acting at their own pace by delivering a voice message such as, "Take your medicine after a short break."

[0180] (Application Example 2)

[0181] 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".

[0182] While elderly individuals require support in daily activities and health management, notification systems that merely inform them of the timing of such events have the problem of failing to provide appropriate support tailored to their emotional state. Furthermore, notification systems that do not consider emotional support may cause stress to the elderly. In addition, conventional systems have difficulty comprehensively capturing abnormal behavior or emotional states, making it difficult to respond in a timely manner.

[0183] 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.

[0184] In this invention, the server includes data collection means, data analysis means, schedule generation means, sentiment analysis means, and notification customization means. This enables a comprehensive evaluation of the user's behavior patterns and emotional state, and personalized notifications tailored to each individual's emotional state.

[0185] A "data collection device" is a device that uses sensors to acquire information about the daily activities and health status of elderly people.

[0186] A "data analysis tool" is a processing system used to identify patterns of behavior and emotion based on collected information.

[0187] A "schedule generation device" is a device that plans to send notifications at appropriate times according to the user's behavior patterns.

[0188] A "notification transmission means" is a device used to convey information to users based on a predetermined schedule.

[0189] An "anomaly detection device" is a device that detects unusual behavior or emotional changes and, if necessary, notifies external parties such as family members or medical institutions.

[0190] "Emotional analysis methods" refer to the process of analyzing a user's facial expressions and voice to identify their emotional state at that time.

[0191] A "notification customization method" is a processing system that adjusts notification content to convey information in an appropriate manner, taking into account the user's emotional state.

[0192] The system implementing this invention is designed as a personalized notification platform to assist the elderly. This system consists of a terminal, a server, a cloud database, and an emotion recognition engine.

[0193] The device functions as a data collection tool to acquire activity and health data from elderly individuals. This data includes location information, step count, heart rate, and schedule lists. It also features an emotion analysis system that uses a built-in camera and microphone to analyze the user's facial expressions and voice, recognizing their emotional state in real time. This allows the user to receive notifications tailored to their current mental state.

[0194] The server securely transmits and stores collected data in a cloud database as a data analysis tool. The data in the cloud is analyzed using machine learning algorithms to identify user behavior and emotional patterns. Based on these analysis results, a schedule generation tool creates an optimal notification schedule.

[0195] The notification customization feature adjusts notification content according to the user's emotional state. For example, if emotion analysis indicates that the user is stressed, the notification will use calm language and encouraging words.

[0196] For example, if the system determines that a user is feeling tired during a walk, the notification will be sent in a gentle tone, such as, "Slow down and take a break." Another example of a prompt used in the "Generative AI Model" is, "Use the following user behavior and emotion data to generate a notification for stress reduction for the elderly: increased heart rate, tired appearance, planned walk, and words of encouragement are needed."

[0197] In this way, it becomes possible to provide more personalized support while aiming to improve the quality of life for the elderly throughout the entire system.

[0198] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0199] Step 1:

[0200] The device collects location information, steps taken, heart rate, and schedule lists of elderly individuals through sensors. This data serves as foundational data for monitoring the user's daily activities and health status. Input is raw data from sensors, and output is activity information in an organized data format.

[0201] Step 2:

[0202] The device's built-in camera and microphone analyze the user's facial expressions and voice in real time. This identifies the emotions the user is feeling. The input is video and audio data, and the output is emotion labels such as joy, sadness, and stress. This process collects emotion-based data.

[0203] Step 3:

[0204] The device sends collected behavioral and emotional data to a server. This data is stored in a cloud database and analyzed by machine learning algorithms. The input is all the data sent from the device, and the output is the analysis results of behavioral and emotional patterns.

[0205] Step 4:

[0206] The server uses a schedule generation mechanism to create an optimal notification schedule based on the user's behavioral and emotional patterns. The input is the result of data analysis, and the output is a notification schedule tailored to a specific timing.

[0207] Step 5:

[0208] The server adjusts notification content using notification customization means according to the emotional state obtained by the emotion analysis means. The input is an emotional state label, and the output is a personalized notification message. For example, if a stressful state is detected, the notification content is changed to a calm and gentle one.

[0209] Step 6:

[0210] The device sends notifications to the user based on a generated schedule and customized content. The input is the customized notification content and schedule sent from the server, and the output is a timely and appropriate notification message to the user. This allows the user to receive emotionally tailored advice and reminders.

[0211] 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.

[0212] 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.

[0213] 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.

[0214] [Second Embodiment]

[0215] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0216] 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.

[0217] 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).

[0218] 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.

[0219] 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.

[0220] 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).

[0221] 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.

[0222] 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.

[0223] 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.

[0224] 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.

[0225] 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.

[0226] 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".

[0227] This invention is a personalized notification system for supporting the elderly, improving the safety and comfort of the user's daily life. The embodiments for carrying out the invention and the processing of its program are described below.

[0228] The device collects data on the behavior and lifestyle patterns of elderly individuals from sensor devices. For example, it uses smartphones and smartwatches to record location information, steps taken, and heart rate, and to understand their daily routines. This information is collected automatically without requiring user awareness, thus reducing the burden on elderly individuals.

[0229] The server transmits the collected data to a cloud environment for secure storage. The data is organized for each individual user and stored in a dedicated database. Machine learning algorithms are used to analyze this data and identify each user's unique behavioral patterns and lifestyle rhythms.

[0230] Based on the analysis results, the server generates a notification schedule best suited to each user. For example, reminders can be set based on behavioral patterns to manage daily medication times or important appointments. This schedule is customized according to each user's preferences and is delivered in the most optimal format, such as voice notifications, vibrations, or screen displays.

[0231] The device sends reminders to the user according to the generated schedule. When the time comes, a notification such as "It's time to take your medicine" appears on the smartphone. Data about the completed actions is also sent back to the server and used for future analysis and schedule generation.

[0232] Furthermore, the server has a mechanism to respond quickly using anomaly detection means if any unusual behavior is detected. In this case, notifications can be automatically sent to family members or medical institutions, ensuring the safety of the elderly.

[0233] As an example of this system, suppose user C needs to take their blood pressure medication at 7:00 AM every morning. Based on the user's daily routine data, the server schedules a notification to be sent to the device at 6:45 AM every day, and the device smoothly delivers the notification to the user. If the user fails to respond to the notification for three consecutive days, the system sends a notification to a family member to ensure that necessary support is provided.

[0234] This invention reduces anxiety caused by forgetfulness in the elderly, making it possible to manage daily life more safely and efficiently.

[0235] The following describes the processing flow.

[0236] Step 1:

[0237] The device collects data about the lifestyle of elderly individuals. This is done via smartphones or smartwatches and includes location information, step count, heart rate, and schedule information. This data is temporarily stored within the device.

[0238] Step 2:

[0239] The device sends the collected data to the server at regular intervals. The transmitted data is encrypted to protect privacy. After transmission, the data on the device is periodically updated.

[0240] Step 3:

[0241] The server stores received data in a cloud database. This data is organized by user and immediately available for analysis. The system ensures data integrity while always reflecting the latest information.

[0242] Step 4:

[0243] The server uses machine learning algorithms to analyze user behavior patterns based on accumulated data. This reveals the user's typical daily schedule and activity patterns.

[0244] Step 5:

[0245] The server automatically generates individual notification schedules based on the analyzed data. The schedules reflect the user's behavior patterns and set reminders at optimal times.

[0246] Step 6:

[0247] The server sends the generated schedule to the device, which then prepares to notify the user. The schedule is designed to notify the user in the most suitable way (e.g., voice notification, screen display, vibration).

[0248] Step 7:

[0249] The device sends a notification to the user at a set time. For example, when it's time to take medication, a notification saying "It's time to take your medication" will appear on the screen. Once the user acknowledges the notification, a record of that is sent to the server.

[0250] Step 8:

[0251] The server collects user response data and uses it for future analysis and scheduling improvements. This improves the accuracy of reminders and user convenience.

[0252] Step 9:

[0253] The server continuously monitors user behavior for any abnormalities. If an abnormality is detected, for example, if there is no response to multiple notifications, notifications are automatically sent to family members or healthcare providers to ensure appropriate support is provided.

[0254] (Example 1)

[0255] 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."

[0256] In daily life, older adults may face difficulties in efficiently and safely managing their health and performing important daily tasks. In particular, failure to properly take regular medications or manage important appointments increases health risks. Furthermore, a lack of prompt response when older adults exhibit abnormal behavior can lead to further danger. Therefore, personalized support based on the individual behavioral characteristics of older adults is needed to improve safety and comfort.

[0257] 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.

[0258] In this invention, the server includes information acquisition means for acquiring biometric data and learning the user's behavioral patterns, analysis means for analyzing the acquired information and identifying behavioral characteristics, and schedule creation means for creating optimized notification schedules based on behavioral characteristics. This makes it possible to contribute to the health and safety of the elderly.

[0259] "Biometric data" refers to information such as location data, step count, and heart rate acquired to indicate the activity level and health status of elderly individuals.

[0260] "Information acquisition means" refers to a system for collecting biometric data from sensor devices and learning the user's behavioral patterns.

[0261] "Analysis means" refers to techniques used to analyze acquired information and identify user behavioral characteristics.

[0262] A "schedule creation method" is a method for generating an optimal notification schedule for a user based on analyzed behavioral characteristics.

[0263] An "information transmission method" is a system that appropriately transmits necessary information to users according to a created schedule.

[0264] An "anomaly detection method" is a technology that detects behavioral characteristics that are different from the norm and transmits information to an external mechanism as needed.

[0265] This invention is a system designed to support the elderly, learning each user's individual lifestyle and enabling safe and efficient daily management. Specifically, it uses smartphones and smartwatches as sensor devices to automatically collect biometric data. These devices acquire data such as the user's location, steps taken, and heart rate, providing various biometric information.

[0266] The device sends this data to the cloud, where necessary information is accumulated through collaboration with the server. The server utilizes cloud-based storage media and employs machine learning algorithms. This allows for precise analysis of the collected information and identification of user behavioral characteristics.

[0267] Next, the server generates a notification schedule optimized for the user's behavior based on the analysis results. The generated schedule is customized in various forms, such as voice, vibration, and screen display, and adjusted according to the user's preferences. For example, if a user needs to take medication at 7:00 AM every morning, the server will set up a notification to be sent to the device at 6:45 AM.

[0268] Based on this generated schedule, the device sends notifications to the user at the specified times. This allows the user to avoid forgetting important appointments and tasks and to respond in a timely manner. Data on whether the user responded to the notification is also sent from the device to the server, which is used to improve future notification schedules.

[0269] If the server detects any unusual behavioral patterns, it will use anomaly detection measures to respond quickly. If necessary, it will send alerts to family members or medical institutions to ensure user safety.

[0270] As a concrete example, the following prompt is given: "Please explain, with specific examples, how to generate a personalized notification schedule based on the lifestyle pattern data of elderly individuals."

[0271] This system allows users to live their lives with peace of mind, and also provides families with a means to remotely monitor the condition of elderly individuals.

[0272] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0273] Step 1:

[0274] The device uses sensor devices (smartphones and smartwatches) to collect biometric data (location information, steps, heart rate, etc.). This data is used to understand the user's daily behavior and health status. It receives biometric data from sensors as input and converts it into a format for transmission to the cloud as output. Specifically, each device periodically collects data and standardizes the data format as needed.

[0275] Step 2:

[0276] The device sends the collected data to the cloud environment. The cloud receives the data while protecting privacy by using data encryption technology. It takes standardized data sent from the device as input and securely stores it on a storage medium in the cloud as output. Specifically, this involves transferring data in real time via a data transmission protocol and storing it in a cloud database.

[0277] Step 3:

[0278] The server analyzes the data stored in the cloud. Using machine learning algorithms, it analyzes the user's behavior characteristics and identifies patterns. Taking a large amount of biological data obtained from the cloud as input and extracting behavior patterns based on the user's characteristics as output. The specific operation is to perform data cleansing and then apply algorithms to generate various statistical information.

[0279] Step 4:

[0280] Based on the analysis results, the server generates an optimal notification schedule for the user. Using the behavior patterns extracted by the server as input and creating a notification schedule optimized for the user's life rhythm as output. The specific operation includes setting the notification timing considering the user's specific needs (e.g., the time to take medicine).

[0281] Step 5:

[0282] The terminal receives the notification schedule generated by the server and sends notifications to the user. Receiving the schedule information provided by the server as input and notifying the user in the form of voice notifications, vibrations, screen displays, etc. as output. The specific operation includes the process of the terminal activating the notification at the specified time and providing an alert to the user.

[0283] Step 6:

[0284] The server collects the user's responses to the notifications as data again and uses them for the next analysis. Receiving the user's response data sent from the terminal as input and generating data for improving the schedule through continuous pattern analysis as output. Specifically, it checks whether the user follows the notifications and whether there are any abnormalities, and updates the dataset reflecting the results.

[0285] Step 7:

[0286] When the server detects abnormal behavior, it utilizes the function of sending notifications to external organizations. As input, it extracts patterns deviating from normal behavior, and as output, it sends alerts to family members and medical institutions as needed. The specific operations are data analysis by an anomaly detection algorithm and automatic message sending to the set contacts.

[0287] (Application Example 1)

[0288] Next, Application Example 1 will be described. In the following description, the data processing device 12 is referred to as the "server", and the smart glasses 214 are referred to as the "terminal".

[0289] In the life of the elderly, daily health management and schedule management are not properly carried out, and they often forget to take medicine, exercise, etc. This may cause deterioration of health status and safety. Also, when abnormal behavior occurs, prompt response may not be taken, and the safety of the elderly is not sufficiently ensured. To improve such a situation, an efficient and personalized notification system is necessary.

[0290] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0291] In this invention, the server includes an information collection means, a data analysis means, a schedule generation means, an information transmission means, an anomaly detection means, and an information cooperation means. Thereby, the daily life of the elderly can be continuously managed, and optimal notifications based on individual behavior patterns can be made. Furthermore, when abnormal behavior is detected, it can quickly cooperate with external organizations to respond, so it is possible to provide a safer and more comfortable living environment.

[0292] The "information collection means" is a mechanism for automatically collecting data on the lifestyle of the elderly, and refers to information obtained through smart devices, etc.

[0293] "Data analysis means" refers to a processing method for analyzing collected data and identifying the behavioral characteristics of elderly people, and may utilize machine learning algorithms.

[0294] The "timetable generation means" is a device that has the function of creating individually optimized notification schedules based on analyzed behavioral characteristics.

[0295] An "information transmission means" is a system for providing users with information such as reminders based on a generated notification schedule.

[0296] An "anomaly detection mechanism" is a system for detecting behavioral characteristics that are different from the norm and responding quickly, and includes a function to send notifications to external parties as needed.

[0297] "Information sharing means" refers to communication methods used to share detected anomaly information and important notifications with external organizations to facilitate a rapid response.

[0298] To implement this invention, a smart device is first used as a means of information gathering. Specifically, sensors in a smartphone or smartwatch are used to continuously collect data such as the elderly person's location, steps taken, and heart rate. This data is acquired automatically, without the user's awareness, and the information is transmitted to a cloud server.

[0299] The server stores this collected data in a centralized database and analyzes it using machine learning algorithms, specifically TensorFlow. This data analysis identifies each user's behavioral characteristics and generates individually optimized notification schedules based on those characteristics. This schedule generation method can, for example, estimate the timing of a user's medication intake or exercise.

[0300] The user's device sends appropriate reminders via the information transmission means, according to the schedule created by the timetable generation means. Reminders may be provided as voice notifications or text messages. The anomaly detection means identifies unusual behavioral characteristics and uses the information sharing means to quickly notify external organizations and family members based on the results.

[0301] For example, if an elderly person needs to take their blood pressure medication at 8:00 AM every morning, the system is designed to send a reminder to their smartphone at 7:50 AM based on data analysis. If the user fails to heed this notification, and this continues for three consecutive days, the system will automatically contact their family through an information sharing mechanism.

[0302] An example of a prompt message might be, "Write a scenario for a care support app that analyzes the behavioral patterns of elderly people and sends reminders at specific times." Such a system would make life safer and more comfortable for the elderly.

[0303] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0304] Step 1:

[0305] The device automatically collects data such as the elderly person's location, steps taken, and heart rate using the smart device's sensors. This collected data is then sent directly to a cloud server as input. This process involves utilizing the device's sensor data, continuously acquiring data in the background, and uploading the data to the server via the network.

[0306] Step 2:

[0307] The server accumulates the data sent to the cloud in a centralized database. On the server, this data is formatted into a pre-set format and processed to be sorted and stored in the storage space allocated to each user. This is the input of the server, and the information sorted in the database is the output.

[0308] Step 3:

[0309] The server starts analyzing the accumulated data using a machine learning algorithm. Specifically, here TensorFlow is utilized to model and analyze the behavior characteristics of each user. Through this process, the behavior pattern of each user is identified, and the result is retained as the output. The data before analysis is the input, and the behavior pattern of the analysis result is the output.

[0310] Step 4:

[0311] The server utilizes a scheduling generation means based on the behavior pattern to create an optimized notification schedule. In this step, based on the analysis result, the notification timing according to the user's daily routine is calculated, and the specific reminder content is determined. The calculated schedule becomes the output.

[0312] Step 5:

[0313] The terminal acquires the notification schedule sent from the server and notifies the user in accordance with the time. This notification is presented to the user as an audio alarm or a push notification on the screen. In this step, the notification content provided to the user becomes the output.

[0314] Step 6:

[0315] The server uses an anomaly detection means to detect behaviors different from the received behavior pattern. At this time, if an anomaly exceeding the set threshold is detected, a notification is sent to an external organization or family through an information cooperation means. The detection of abnormal behavior is the input, and a warning notification is generated as the output.

[0316] 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.

[0317] This invention provides advanced support that takes into account the user's emotional state by combining a personalized notification system for assisting the elderly with an emotion engine. An embodiment of this system will be described in detail.

[0318] The device collects basic data about the elderly person's activity and lifestyle patterns through sensor devices. This data includes location information, steps taken, heart rate, and schedule lists. The device also uses its built-in camera and microphone to activate an emotion engine that recognizes the user's emotions. It can evaluate the user's emotions in real time by utilizing facial expression analysis, voice tone analysis, and even linguistic analysis in text.

[0319] The server simultaneously transmits both collected behavioral and emotional data to a cloud database for secure storage. The data is precisely analyzed to identify not only typical user behavioral patterns but also emotional patterns. Machine learning algorithms are used in this analysis, combining historical and new data to provide responses tailored to user needs.

[0320] The emotion data recognized by the emotion engine is used to generate customized notifications tailored to the user's emotional state. For example, if the user is stressed, the content of the notification can be changed to softer language or words of encouragement. Furthermore, the emotion data is evaluated in correlation with behavioral data, and the notification schedule is adjusted to match the user's optimal mental state.

[0321] The device sends notifications to the user based on the generated schedule. These notifications are delivered at the appropriate time and in the appropriate manner, taking into account the user's emotional state. For example, if the user is feeling tired when it's time to take medication, the voice tone can be changed to a calmer one, and the notification can say something like, "Take your medication after you've had a short rest."

[0322] The presence of an emotion engine allows the system to respond quickly to changes in the user's emotions and provide emotional support in daily life. Furthermore, by combining it with conventional anomaly detection functions, it can notify family members and medical institutions if abnormalities occur not only in the user's behavior but also in their emotions.

[0323] Thus, the present invention incorporates cutting-edge technology to improve the quality of life for the elderly and provide a safe and emotionally comfortable living environment.

[0324] The following describes the processing flow.

[0325] Step 1:

[0326] The device collects data related to the activities and lifestyle patterns of elderly individuals using sensor devices. Specifically, this includes biometric information such as location, steps taken, and heart rate. This information is stored within the device as basic data for understanding daily lifestyle habits.

[0327] Step 2:

[0328] The device utilizes its built-in camera and microphone to recognize the user's emotional state in real time. This process analyzes the user's facial expressions and voice tone to determine their current emotional state. As a result, emotional data is recorded within the device.

[0329] Step 3:

[0330] The device periodically sends collected behavioral and emotional data to a server. The transmitted data is encrypted, and secure storage in the cloud is guaranteed.

[0331] Step 4:

[0332] The server analyzes data stored in the cloud database using machine learning algorithms. It simultaneously analyzes behavioral and emotional patterns to form an intelligent understanding based on the individual needs and requirements of the user.

[0333] Step 5:

[0334] The server dynamically generates notification content and timing based on the user's emotional state. For example, it might generate calming notifications for users experiencing stress and adjust the notification schedule accordingly.

[0335] Step 6:

[0336] The server sends the generated notifications and schedules to the device. This prepares the notifications and enables user-optimized reminders.

[0337] Step 7:

[0338] The device will send notifications to the user based on a schedule. These notifications will be delivered in a way and with content that takes into account the user's emotional state. For example, a message such as "Take your medication after you have relaxed" might be displayed in a calm voice or on screen.

[0339] Step 8:

[0340] The server collects user responses as data after a notification is sent and uses this data to optimize the next notification schedule.

[0341] Step 9:

[0342] The server monitors the user's behavior and emotional state for any abnormalities. If an emotional abnormality is detected, it automatically notifies family members and medical institutions so that necessary support can be provided.

[0343] (Example 2)

[0344] 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".

[0345] Supporting the elderly requires not only understanding their behavioral patterns but also providing flexible responses tailored to their individual emotional states. However, conventional systems have struggled to quickly detect emotional changes and respond appropriately. Furthermore, they lacked mechanisms to provide timely notifications when abnormal emotional states occurred. This resulted in a problem where the quality of life for the elderly could not be adequately improved.

[0346] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0347] In this invention, the server includes information gathering means for learning the lifestyle and emotional state of elderly people, information analysis means for analyzing the collected information to identify behavioral and emotional patterns, and plan generation means for generating an optimal notification schedule based on the behavioral and emotional patterns. This enables notification delivery tailored to the individual emotional state of elderly people, thereby improving their quality of life and providing a safe environment.

[0348] "Information gathering means" refers to devices or software used to acquire data on the lifestyle and emotional state of elderly people.

[0349] "Information analysis methods" refer to technologies that use collected data to identify patterns in the behavior and emotions of elderly individuals.

[0350] The "plan generation method" is a function that creates an optimal notification schedule for elderly people based on the analysis results.

[0351] "Notification delivery means" refers to a device or method that provides users with emotionally relevant information according to a generated schedule.

[0352] An "anomaly detection system" is a mechanism that quickly identifies changes in emotions and behavior and issues warnings to external organizations as needed.

[0353] A "remote data recording device" is a cloud or server environment for securely storing collected information.

[0354] "Data analysis technology" refers to analytical methods used to evaluate collected information and gain useful insights.

[0355] This invention is a personalized notification system for supporting the elderly, providing notifications that take into account the user's lifestyle and emotional state. This system is composed of a combination of information gathering means, information analysis means, and plan generation means.

[0356] The device functions as a means of information gathering, acquiring data on the daily activities and emotional state of elderly individuals. This includes sensor devices for acquiring location information, step count, and heart rate, as well as cameras and microphones for analyzing the user's facial expressions and voice. This makes it possible to assess the user's emotions in real time.

[0357] The server functions as an information analysis tool, storing data collected from terminals in a remote data recording device. Furthermore, it analyzes the data using machine learning algorithms to identify specific behavioral and emotional patterns. Based on these analysis results, the plan generation tool creates an optimal notification schedule.

[0358] Based on this schedule, the device acts as a notification delivery mechanism, providing users with appropriate and customized notifications. The content of the notifications changes according to the user's emotional state, allowing for flexible responses. For example, if the user is feeling stressed, the device can use a calmer voice tone and notify them with a message like, "Take a short break and then take your medicine."

[0359] As a concrete example, the following is an example of a prompt statement to be input to a generative AI model.

[0360] Prompt example: "A 70-year-old female user appears more tired than usual during her recent walks. Use the emotion engine to create an encouraging message for the user based on this information."

[0361] This system allows elderly people to live their daily lives with peace of mind, improving both their quality of life and safety at the same time.

[0362] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0363] Step 1:

[0364] The device uses sensor devices to collect data about the daily lives of elderly individuals. This data includes location information, step count, and heart rate. Using this physiological data as input, the device uses its built-in camera and microphone to analyze the user's facial expressions and voice in real time using an emotion engine. The output is data indicating the user's emotional state.

[0365] Step 2:

[0366] The server receives and stores behavioral and emotional data transmitted from terminals in a remote data recording device. Inputs include data from terminals, which the server stores in a secure cloud environment. Outputs are datasets prepared for analysis. Based on this dataset, the server uses machine learning algorithms to identify behavioral and emotional patterns.

[0367] Step 3:

[0368] The server analyzes identified behavioral and emotional patterns and generates an optimized notification schedule based on the user's state. The input is the dataset obtained in step 2, and the output is a personalized notification schedule for the user. In this step, a generative AI model is used to generate prompts that adjust the notification content. For example, the prompt might say, "The user is tired, please create a message to help them relax."

[0369] Step 4:

[0370] The device delivers notifications to the user at the appropriate time according to a notification schedule sent from the server. The input is the generated notification schedule, and the output is the customized notification provided to the user. Notifications are delivered via voice assistant or screen display and respond flexibly to the user's emotional state. For example, it can support the user in acting at their own pace by delivering a voice message such as, "Take your medicine after a short break."

[0371] (Application Example 2)

[0372] 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."

[0373] While elderly individuals require support in daily activities and health management, notification systems that merely inform them of the timing of such events have the problem of failing to provide appropriate support tailored to their emotional state. Furthermore, notification systems that do not consider emotional support may cause stress to the elderly. In addition, conventional systems have difficulty comprehensively capturing abnormal behavior or emotional states, making it difficult to respond in a timely manner.

[0374] 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.

[0375] In this invention, the server includes data collection means, data analysis means, schedule generation means, sentiment analysis means, and notification customization means. This enables a comprehensive evaluation of the user's behavior patterns and emotional state, and personalized notifications tailored to each individual's emotional state.

[0376] A "data collection device" is a device that uses sensors to acquire information about the daily activities and health status of elderly people.

[0377] A "data analysis tool" is a processing system used to identify patterns of behavior and emotion based on collected information.

[0378] A "schedule generation device" is a device that plans to send notifications at appropriate times according to the user's behavior patterns.

[0379] A "notification transmission means" is a device used to convey information to users based on a predetermined schedule.

[0380] An "anomaly detection device" is a device that detects unusual behavior or emotional changes and, if necessary, notifies external parties such as family members or medical institutions.

[0381] "Emotional analysis methods" refer to the process of analyzing a user's facial expressions and voice to identify their emotional state at that time.

[0382] A "notification customization method" is a processing system that adjusts notification content to convey information in an appropriate manner, taking into account the user's emotional state.

[0383] The system implementing this invention is designed as a personalized notification platform to assist the elderly. This system consists of a terminal, a server, a cloud database, and an emotion recognition engine.

[0384] The device functions as a data collection tool to acquire activity and health data from elderly individuals. This data includes location information, step count, heart rate, and schedule lists. It also features an emotion analysis system that uses a built-in camera and microphone to analyze the user's facial expressions and voice, recognizing their emotional state in real time. This allows the user to receive notifications tailored to their current mental state.

[0385] The server securely transmits and stores collected data in a cloud database as a data analysis tool. The data in the cloud is analyzed using machine learning algorithms to identify user behavior and emotional patterns. Based on these analysis results, a schedule generation tool creates an optimal notification schedule.

[0386] The notification customization feature adjusts notification content according to the user's emotional state. For example, if emotion analysis indicates that the user is stressed, the notification will use calm language and encouraging words.

[0387] For example, if the system determines that a user is feeling tired during a walk, the notification will be sent in a gentle tone, such as, "Slow down and take a break." Another example of a prompt used in the "Generative AI Model" is, "Use the following user behavior and emotion data to generate a notification for stress reduction for the elderly: increased heart rate, tired appearance, planned walk, and words of encouragement are needed."

[0388] In this way, it becomes possible to provide more personalized support while aiming to improve the quality of life for the elderly throughout the entire system.

[0389] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0390] Step 1:

[0391] The device collects location information, steps taken, heart rate, and schedule lists of elderly individuals through sensors. This data serves as foundational data for monitoring the user's daily activities and health status. Input is raw data from sensors, and output is activity information in an organized data format.

[0392] Step 2:

[0393] The device's built-in camera and microphone analyze the user's facial expressions and voice in real time. This identifies the emotions the user is feeling. The input is video and audio data, and the output is emotion labels such as joy, sadness, and stress. This process collects emotion-based data.

[0394] Step 3:

[0395] The device sends collected behavioral and emotional data to a server. This data is stored in a cloud database and analyzed by machine learning algorithms. The input is all the data sent from the device, and the output is the analysis results of behavioral and emotional patterns.

[0396] Step 4:

[0397] The server uses a schedule generation mechanism to create an optimal notification schedule based on the user's behavioral and emotional patterns. The input is the result of data analysis, and the output is a notification schedule tailored to a specific timing.

[0398] Step 5:

[0399] The server adjusts notification content using notification customization means according to the emotional state obtained by the emotion analysis means. The input is an emotional state label, and the output is a personalized notification message. For example, if a stressful state is detected, the notification content is changed to a calm and gentle one.

[0400] Step 6:

[0401] The device sends notifications to the user based on a generated schedule and customized content. The input is the customized notification content and schedule sent from the server, and the output is a timely and appropriate notification message to the user. This allows the user to receive emotionally tailored advice and reminders.

[0402] 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.

[0403] 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.

[0404] 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.

[0405] [Third Embodiment]

[0406] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0407] 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.

[0408] 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).

[0409] 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.

[0410] 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.

[0411] 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).

[0412] 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.

[0413] 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.

[0414] 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.

[0415] 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.

[0416] 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.

[0417] 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".

[0418] This invention is a personalized notification system for supporting the elderly, improving the safety and comfort of the user's daily life. The embodiments for carrying out the invention and the processing of its program are described below.

[0419] The device collects data on the behavior and lifestyle patterns of elderly individuals from sensor devices. For example, it uses smartphones and smartwatches to record location information, steps taken, and heart rate, and to understand their daily routines. This information is collected automatically without requiring user awareness, thus reducing the burden on elderly individuals.

[0420] The server transmits the collected data to a cloud environment for secure storage. The data is organized for each individual user and stored in a dedicated database. Machine learning algorithms are used to analyze this data and identify each user's unique behavioral patterns and lifestyle rhythms.

[0421] Based on the analysis results, the server generates a notification schedule best suited to each user. For example, reminders can be set based on behavioral patterns to manage daily medication times or important appointments. This schedule is customized according to each user's preferences and is delivered in the most optimal format, such as voice notifications, vibrations, or screen displays.

[0422] The device sends reminders to the user according to the generated schedule. When the time comes, a notification such as "It's time to take your medicine" appears on the smartphone. Data about the completed actions is also sent back to the server and used for future analysis and schedule generation.

[0423] Furthermore, the server has a mechanism to respond quickly using anomaly detection means if any unusual behavior is detected. In this case, notifications can be automatically sent to family members or medical institutions, ensuring the safety of the elderly.

[0424] As an example of this system, suppose user C needs to take their blood pressure medication at 7:00 AM every morning. Based on the user's daily routine data, the server schedules a notification to be sent to the device at 6:45 AM every day, and the device smoothly delivers the notification to the user. If the user fails to respond to the notification for three consecutive days, the system sends a notification to a family member to ensure that necessary support is provided.

[0425] This invention reduces anxiety caused by forgetfulness in the elderly, making it possible to manage daily life more safely and efficiently.

[0426] The following describes the processing flow.

[0427] Step 1:

[0428] The device collects data about the lifestyle of elderly individuals. This is done via smartphones or smartwatches and includes location information, step count, heart rate, and schedule information. This data is temporarily stored within the device.

[0429] Step 2:

[0430] The device sends the collected data to the server at regular intervals. The transmitted data is encrypted to protect privacy. After transmission, the data on the device is periodically updated.

[0431] Step 3:

[0432] The server stores received data in a cloud database. This data is organized by user and immediately available for analysis. The system ensures data integrity while always reflecting the latest information.

[0433] Step 4:

[0434] The server uses machine learning algorithms to analyze user behavior patterns based on accumulated data. This reveals the user's typical daily schedule and activity patterns.

[0435] Step 5:

[0436] The server automatically generates individual notification schedules based on the analyzed data. The schedules reflect the user's behavior patterns and set reminders at optimal times.

[0437] Step 6:

[0438] The server sends the generated schedule to the device, which then prepares to notify the user. The schedule is designed to notify the user in the most suitable way (e.g., voice notification, screen display, vibration).

[0439] Step 7:

[0440] The device sends a notification to the user at a set time. For example, when it's time to take medication, a notification saying "It's time to take your medication" will appear on the screen. Once the user acknowledges the notification, a record of that is sent to the server.

[0441] Step 8:

[0442] The server collects user response data and uses it for future analysis and scheduling improvements. This improves the accuracy of reminders and user convenience.

[0443] Step 9:

[0444] The server continuously monitors user behavior for any abnormalities. If an abnormality is detected, for example, if there is no response to multiple notifications, notifications are automatically sent to family members or healthcare providers to ensure appropriate support is provided.

[0445] (Example 1)

[0446] 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."

[0447] In daily life, older adults may face difficulties in efficiently and safely managing their health and performing important daily tasks. In particular, failure to properly take regular medications or manage important appointments increases health risks. Furthermore, a lack of prompt response when older adults exhibit abnormal behavior can lead to further danger. Therefore, personalized support based on the individual behavioral characteristics of older adults is needed to improve safety and comfort.

[0448] 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.

[0449] In this invention, the server includes information acquisition means for acquiring biometric data and learning the user's behavioral patterns, analysis means for analyzing the acquired information and identifying behavioral characteristics, and schedule creation means for creating optimized notification schedules based on behavioral characteristics. This makes it possible to contribute to the health and safety of the elderly.

[0450] "Biometric data" refers to information such as location data, step count, and heart rate acquired to indicate the activity level and health status of elderly individuals.

[0451] "Information acquisition means" refers to a system for collecting biometric data from sensor devices and learning the user's behavioral patterns.

[0452] "Analysis means" refers to techniques used to analyze acquired information and identify user behavioral characteristics.

[0453] A "schedule creation method" is a method for generating an optimal notification schedule for a user based on analyzed behavioral characteristics.

[0454] An "information transmission method" is a system that appropriately transmits necessary information to users according to a created schedule.

[0455] An "anomaly detection method" is a technology that detects behavioral characteristics that are different from the norm and transmits information to an external mechanism as needed.

[0456] This invention is a system designed to support the elderly, learning each user's individual lifestyle and enabling safe and efficient daily management. Specifically, it uses smartphones and smartwatches as sensor devices to automatically collect biometric data. These devices acquire data such as the user's location, steps taken, and heart rate, providing various biometric information.

[0457] The device sends this data to the cloud, where necessary information is accumulated through collaboration with the server. The server utilizes cloud-based storage media and employs machine learning algorithms. This allows for precise analysis of the collected information and identification of user behavioral characteristics.

[0458] Next, the server generates a notification schedule optimized for the user's behavior based on the analysis results. The generated schedule is customized in various forms, such as voice, vibration, and screen display, and adjusted according to the user's preferences. For example, if a user needs to take medication at 7:00 AM every morning, the server will set up a notification to be sent to the device at 6:45 AM.

[0459] Based on this generated schedule, the device sends notifications to the user at the specified times. This allows the user to avoid forgetting important appointments and tasks and to respond in a timely manner. Data on whether the user responded to the notification is also sent from the device to the server, which is used to improve future notification schedules.

[0460] If the server detects any unusual behavioral patterns, it will use anomaly detection measures to respond quickly. If necessary, it will send alerts to family members or medical institutions to ensure user safety.

[0461] As a concrete example, the following prompt is given: "Please explain, with specific examples, how to generate a personalized notification schedule based on the lifestyle pattern data of elderly individuals."

[0462] This system allows users to live their lives with peace of mind, and also provides families with a means to remotely monitor the condition of elderly individuals.

[0463] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0464] Step 1:

[0465] The device uses sensor devices (smartphones and smartwatches) to collect biometric data (location information, steps, heart rate, etc.). This data is used to understand the user's daily behavior and health status. It receives biometric data from sensors as input and converts it into a format for transmission to the cloud as output. Specifically, each device periodically collects data and standardizes the data format as needed.

[0466] Step 2:

[0467] The device sends the collected data to the cloud environment. The cloud receives the data while protecting privacy by using data encryption technology. It takes standardized data sent from the device as input and securely stores it on a storage medium in the cloud as output. Specifically, this involves transferring data in real time via a data transmission protocol and storing it in a cloud database.

[0468] Step 3:

[0469] The server analyzes data stored in the cloud. Using machine learning algorithms, it analyzes user behavioral characteristics and identifies patterns. It uses a large amount of biometric data acquired from the cloud as input and extracts behavioral patterns based on user characteristics as output. Specifically, it performs data cleansing, then applies algorithms to generate various statistical information.

[0470] Step 4:

[0471] The server generates an optimal notification schedule for the user based on the analysis results. It uses behavioral patterns extracted by the server as input and creates a notification schedule optimized for the user's daily routine as output. Specific actions include setting notification timings that take into account the user's specific needs (e.g., medication timing).

[0472] Step 5:

[0473] The device receives notification schedules generated by the server and sends notifications to the user. It receives schedule information provided by the server as input and notifies the user in the form of audio notifications, vibrations, screen displays, etc. The specific operation includes a process where the device triggers a notification at a specified time and provides an alert to the user.

[0474] Step 6:

[0475] The server collects user responses to notifications as data again to use for subsequent analysis. It receives user response data sent from the terminal as input and generates data to improve scheduling through continuous pattern analysis as output. Specifically, it checks whether the user followed the notification and whether there were any anomalies, and updates the dataset to reflect the results.

[0476] Step 7:

[0477] The server utilizes a function to send notifications to external organizations when it detects abnormal behavior. It extracts patterns that deviate from normal behavior as input, and sends alerts to family members or medical institutions as needed as output. The specific operation involves data analysis using an anomaly detection algorithm and automatic message sending to configured contacts.

[0478] (Application Example 1)

[0479] 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."

[0480] In the lives of the elderly, daily health management and schedule management are often not properly carried out, and they frequently forget to take medication or exercise, which can lead to a deterioration of their health and safety. Furthermore, when abnormal behavior occurs, prompt action may not be taken, and the safety of the elderly is not adequately ensured. To improve this situation, an efficient and personalized notification system is needed.

[0481] 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.

[0482] In this invention, the server includes information gathering means, data analysis means, timetable generation means, information transmission means, anomaly detection means, and information linking means. This enables continuous management of the daily lives of elderly people and provides optimal notifications based on individual behavioral patterns. Furthermore, because it can quickly cooperate with external organizations to respond when abnormal behavior is detected, it becomes possible to provide a safer and more comfortable living environment.

[0483] "Information gathering means" refers to a system that automatically collects data on the lifestyles of elderly people, and the information obtained through smart devices, etc.

[0484] "Data analysis means" refers to a processing method for analyzing collected data and identifying the behavioral characteristics of elderly people, and may utilize machine learning algorithms.

[0485] The "timetable generation means" is a device that has the function of creating individually optimized notification schedules based on analyzed behavioral characteristics.

[0486] An "information transmission means" is a system for providing users with information such as reminders based on a generated notification schedule.

[0487] An "anomaly detection mechanism" is a system for detecting behavioral characteristics that are different from the norm and responding quickly, and includes a function to send notifications to external parties as needed.

[0488] "Information sharing means" refers to communication methods used to share detected anomaly information and important notifications with external organizations to facilitate a rapid response.

[0489] To implement this invention, a smart device is first used as a means of information gathering. Specifically, sensors in a smartphone or smartwatch are used to continuously collect data such as the elderly person's location, steps taken, and heart rate. This data is acquired automatically, without the user's awareness, and the information is transmitted to a cloud server.

[0490] The server stores this collected data in a centralized database and analyzes it using machine learning algorithms, specifically TensorFlow. This data analysis identifies each user's behavioral characteristics and generates individually optimized notification schedules based on those characteristics. This schedule generation method can, for example, estimate the timing of a user's medication intake or exercise.

[0491] The user's device sends appropriate reminders via the information transmission means, according to the schedule created by the timetable generation means. Reminders may be provided as voice notifications or text messages. The anomaly detection means identifies unusual behavioral characteristics and uses the information sharing means to quickly notify external organizations and family members based on the results.

[0492] For example, if an elderly person needs to take their blood pressure medication at 8:00 AM every morning, the system is designed to send a reminder to their smartphone at 7:50 AM based on data analysis. If the user fails to heed this notification, and this continues for three consecutive days, the system will automatically contact their family through an information sharing mechanism.

[0493] An example of a prompt message might be, "Write a scenario for a care support app that analyzes the behavioral patterns of elderly people and sends reminders at specific times." Such a system would make life safer and more comfortable for the elderly.

[0494] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0495] Step 1:

[0496] The device automatically collects data such as the elderly person's location, steps taken, and heart rate using the smart device's sensors. This collected data is then sent directly to a cloud server as input. This process involves utilizing the device's sensor data, continuously acquiring data in the background, and uploading the data to the server via the network.

[0497] Step 2:

[0498] The server stores the data sent to the cloud in a centralized database. On the server, this data is formatted into a pre-configured format and then organized and saved in the storage space allocated to each user. This is the server's input, and the organized information in the database is the output.

[0499] Step 3:

[0500] The server begins analyzing the accumulated data using machine learning algorithms. Specifically, TensorFlow is used to model and analyze the behavioral characteristics of each user. This process identifies each user's behavioral pattern, and the results are stored as output. The data before analysis is the input, and the behavioral patterns resulting from the analysis are the output.

[0501] Step 4:

[0502] The server uses a timetable generation mechanism based on behavioral patterns to create an optimized notification schedule. In this step, based on the analysis results, the server calculates the notification timing according to the user's daily routine and determines the specific reminder content. The resulting timetable is then output.

[0503] Step 5:

[0504] The device retrieves the notification schedule sent from the server and notifies the user at the appropriate time. This notification is presented to the user as an audio alarm or a push notification on the screen. In this step, the output is the notification content to be provided to the user.

[0505] Step 6:

[0506] The server uses anomaly detection means to detect behavior that differs from the received behavior pattern. If an anomaly exceeding a set threshold is detected, it notifies external organizations and family members through information sharing means. The detection of abnormal behavior becomes the input, and a warning notification is generated as the output.

[0507] 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.

[0508] This invention provides advanced support that takes into account the user's emotional state by combining a personalized notification system for assisting the elderly with an emotion engine. An embodiment of this system will be described in detail.

[0509] The device collects basic data about the elderly person's activity and lifestyle patterns through sensor devices. This data includes location information, steps taken, heart rate, and schedule lists. The device also uses its built-in camera and microphone to activate an emotion engine that recognizes the user's emotions. It can evaluate the user's emotions in real time by utilizing facial expression analysis, voice tone analysis, and even linguistic analysis in text.

[0510] The server simultaneously transmits both collected behavioral and emotional data to a cloud database for secure storage. The data is precisely analyzed to identify not only typical user behavioral patterns but also emotional patterns. Machine learning algorithms are used in this analysis, combining historical and new data to provide responses tailored to user needs.

[0511] The emotion data recognized by the emotion engine is used to generate customized notifications tailored to the user's emotional state. For example, if the user is stressed, the content of the notification can be changed to softer language or words of encouragement. Furthermore, the emotion data is evaluated in correlation with behavioral data, and the notification schedule is adjusted to match the user's optimal mental state.

[0512] The device sends notifications to the user based on the generated schedule. These notifications are delivered at the appropriate time and in the appropriate manner, taking into account the user's emotional state. For example, if the user is feeling tired when it's time to take medication, the voice tone can be changed to a calmer one, and the notification can say something like, "Take your medication after you've had a short rest."

[0513] The presence of an emotion engine allows the system to respond quickly to changes in the user's emotions and provide emotional support in daily life. Furthermore, by combining it with conventional anomaly detection functions, it can notify family members and medical institutions if abnormalities occur not only in the user's behavior but also in their emotions.

[0514] Thus, the present invention incorporates cutting-edge technology to improve the quality of life for the elderly and provide a safe and emotionally comfortable living environment.

[0515] The following describes the processing flow.

[0516] Step 1:

[0517] The device collects data related to the activities and lifestyle patterns of elderly individuals using sensor devices. Specifically, this includes biometric information such as location, steps taken, and heart rate. This information is stored within the device as basic data for understanding daily lifestyle habits.

[0518] Step 2:

[0519] The device utilizes its built-in camera and microphone to recognize the user's emotional state in real time. This process analyzes the user's facial expressions and voice tone to determine their current emotional state. As a result, emotional data is recorded within the device.

[0520] Step 3:

[0521] The device periodically sends collected behavioral and emotional data to a server. The transmitted data is encrypted, and secure data storage in the cloud is guaranteed.

[0522] Step 4:

[0523] The server analyzes data stored in the cloud database using machine learning algorithms. It simultaneously analyzes behavioral and emotional patterns to form an intelligent understanding based on the individual needs and requirements of the user.

[0524] Step 5:

[0525] The server dynamically generates notification content and timing based on the user's emotional state. For example, it might generate calming notifications for users experiencing stress and adjust the notification schedule accordingly.

[0526] Step 6:

[0527] The server sends the generated notifications and schedules to the device. This prepares the notifications and enables user-optimized reminders.

[0528] Step 7:

[0529] The device will send notifications to the user based on a schedule. These notifications will be delivered in a way and with content that takes into account the user's emotional state. For example, a message such as "Take your medication after you have relaxed" may be presented in a calm voice or on-screen display.

[0530] Step 8:

[0531] The server collects user responses as data after a notification is sent and uses this data to optimize the next notification schedule.

[0532] Step 9:

[0533] The server monitors the user's behavior and emotional state for any abnormalities. If an emotional abnormality is detected, it automatically notifies family members and medical institutions so that necessary support can be provided.

[0534] (Example 2)

[0535] 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."

[0536] Supporting the elderly requires not only understanding their behavioral patterns but also providing flexible responses tailored to their individual emotional states. However, conventional systems have struggled to quickly detect emotional changes and respond appropriately. Furthermore, they lacked mechanisms to provide timely notifications when abnormal emotional states occurred. This resulted in a problem where the quality of life for the elderly could not be adequately improved.

[0537] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0538] In this invention, the server includes information gathering means for learning the lifestyle and emotional state of elderly people, information analysis means for analyzing the collected information to identify behavioral and emotional patterns, and plan generation means for generating an optimal notification schedule based on the behavioral and emotional patterns. This enables notification delivery tailored to the individual emotional state of elderly people, thereby improving their quality of life and providing a safe environment.

[0539] "Information gathering means" refers to devices or software used to acquire data on the lifestyle and emotional state of elderly people.

[0540] "Information analysis methods" refer to technologies that use collected data to identify patterns in the behavior and emotions of elderly individuals.

[0541] The "plan generation method" is a function that creates an optimal notification schedule for elderly people based on the analysis results.

[0542] "Notification delivery means" refers to a device or method that provides users with emotionally relevant information according to a generated schedule.

[0543] An "anomaly detection system" is a mechanism that quickly identifies changes in emotions and behavior and issues warnings to external organizations as needed.

[0544] A "remote data recording device" is a cloud or server environment for securely storing collected information.

[0545] "Data analysis technology" refers to analytical methods used to evaluate collected information and gain useful insights.

[0546] This invention is a personalized notification system for supporting the elderly, providing notifications that take into account the user's lifestyle and emotional state. This system is composed of a combination of information gathering means, information analysis means, and plan generation means.

[0547] The device functions as a means of information gathering, acquiring data on the daily activities and emotional state of elderly individuals. This includes sensor devices for acquiring location information, step count, and heart rate, as well as cameras and microphones for analyzing the user's facial expressions and voice. This makes it possible to assess the user's emotions in real time.

[0548] The server functions as an information analysis tool, storing data collected from terminals in a remote data recording device. Furthermore, it analyzes the data using machine learning algorithms to identify specific behavioral and emotional patterns. Based on these analysis results, the plan generation tool creates an optimal notification schedule.

[0549] Based on this schedule, the device acts as a notification delivery mechanism, providing users with appropriate and customized notifications. The content of the notifications changes according to the user's emotional state, allowing for flexible responses. For example, if the user is feeling stressed, the device can use a calmer voice tone and notify them with a message like, "Take a short break and then take your medicine."

[0550] As a concrete example, the following is an example of a prompt statement to be input to a generative AI model.

[0551] Prompt example: "A 70-year-old female user appears more tired than usual during her recent walks. Use the emotion engine to create an encouraging message for the user based on this information."

[0552] This system allows elderly people to live their daily lives with peace of mind, improving both their quality of life and safety at the same time.

[0553] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0554] Step 1:

[0555] The device uses sensor devices to collect data about the daily lives of elderly individuals. This data includes location information, step count, and heart rate. Using this physiological data as input, the device uses its built-in camera and microphone to analyze the user's facial expressions and voice in real time using an emotion engine. The output is data indicating the user's emotional state.

[0556] Step 2:

[0557] The server receives and stores behavioral and emotional data transmitted from terminals in a remote data recording device. Inputs include data from terminals, which the server stores in a secure cloud environment. Outputs are datasets prepared for analysis. Based on this dataset, the server uses machine learning algorithms to identify behavioral and emotional patterns.

[0558] Step 3:

[0559] The server analyzes identified behavioral and emotional patterns and generates an optimized notification schedule based on the user's state. The input is the dataset obtained in step 2, and the output is a personalized notification schedule for the user. In this step, a generative AI model is used to generate prompts that adjust the notification content. For example, the prompt might say, "The user is tired, please create a message to help them relax."

[0560] Step 4:

[0561] The device delivers notifications to the user at the appropriate time according to a notification schedule sent from the server. The input is the generated notification schedule, and the output is the customized notification provided to the user. Notifications are delivered via voice assistant or screen display and respond flexibly to the user's emotional state. For example, it can support the user in acting at their own pace by delivering a voice message such as, "Take your medicine after a short break."

[0562] (Application Example 2)

[0563] 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."

[0564] While elderly individuals require support in daily activities and health management, notification systems that merely inform them of the timing of such events have the problem of failing to provide appropriate support tailored to their emotional state. Furthermore, notification systems that do not consider emotional support may cause stress to the elderly. In addition, conventional systems have difficulty comprehensively capturing abnormal behavior or emotional states, making it difficult to respond in a timely manner.

[0565] 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.

[0566] In this invention, the server includes data collection means, data analysis means, schedule generation means, sentiment analysis means, and notification customization means. This enables a comprehensive evaluation of the user's behavior patterns and emotional state, and personalized notifications tailored to each individual's emotional state.

[0567] A "data collection device" is a device that uses sensors to acquire information about the daily activities and health status of elderly people.

[0568] A "data analysis tool" is a processing system used to identify patterns of behavior and emotion based on collected information.

[0569] A "schedule generation device" is a device that plans to send notifications at appropriate times according to the user's behavior patterns.

[0570] A "notification transmission means" is a device used to convey information to users based on a predetermined schedule.

[0571] An "anomaly detection device" is a device that detects unusual behavior or emotional changes and, if necessary, notifies external parties such as family members or medical institutions.

[0572] "Emotional analysis methods" refer to the process of analyzing a user's facial expressions and voice to identify their emotional state at that time.

[0573] A "notification customization method" is a processing system that adjusts notification content to convey information in an appropriate manner, taking into account the user's emotional state.

[0574] The system implementing this invention is designed as a personalized notification platform to assist the elderly. This system consists of a terminal, a server, a cloud database, and an emotion recognition engine.

[0575] The device functions as a data collection tool to acquire activity and health data from elderly individuals. This data includes location information, step count, heart rate, and schedule lists. It also features an emotion analysis system that uses a built-in camera and microphone to analyze the user's facial expressions and voice, recognizing their emotional state in real time. This allows the user to receive notifications tailored to their current mental state.

[0576] The server securely transmits and stores collected data in a cloud database as a data analysis tool. The data in the cloud is analyzed using machine learning algorithms to identify user behavior and emotional patterns. Based on these analysis results, a schedule generation tool creates an optimal notification schedule.

[0577] The notification customization feature adjusts notification content according to the user's emotional state. For example, if emotion analysis indicates that the user is stressed, the notification will use calm language and encouraging words.

[0578] For example, if the system determines that a user is feeling tired during a walk, the notification will be sent in a gentle tone, such as, "Slow down and take a break." Another example of a prompt used in the "Generative AI Model" is, "Use the following user behavior and emotion data to generate a notification for stress reduction for the elderly: increased heart rate, tired appearance, planned walk, and words of encouragement are needed."

[0579] In this way, it becomes possible to provide more personalized support while aiming to improve the quality of life for the elderly throughout the entire system.

[0580] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0581] Step 1:

[0582] The device collects location information, steps taken, heart rate, and schedule lists of elderly individuals through sensors. This data serves as foundational data for monitoring the user's daily activities and health status. Input is raw data from sensors, and output is activity information in an organized data format.

[0583] Step 2:

[0584] The device's built-in camera and microphone analyze the user's facial expressions and voice in real time. This identifies the emotions the user is feeling. The input is video and audio data, and the output is emotion labels such as joy, sadness, and stress. This process collects emotion-based data.

[0585] Step 3:

[0586] The device sends collected behavioral and emotional data to a server. This data is stored in a cloud database and analyzed by machine learning algorithms. The input is all the data sent from the device, and the output is the analysis results of behavioral and emotional patterns.

[0587] Step 4:

[0588] The server uses a schedule generation mechanism to create an optimal notification schedule based on the user's behavioral and emotional patterns. The input is the result of data analysis, and the output is a notification schedule tailored to a specific timing.

[0589] Step 5:

[0590] The server adjusts notification content using notification customization means according to the emotional state obtained by the emotion analysis means. The input is an emotional state label, and the output is a personalized notification message. For example, if a stressful state is detected, the notification content is changed to a calm and gentle one.

[0591] Step 6:

[0592] The device sends notifications to the user based on a generated schedule and customized content. The input is the customized notification content and schedule sent from the server, and the output is a timely and appropriate notification message to the user. This allows the user to receive emotionally tailored advice and reminders.

[0593] 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.

[0594] 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.

[0595] 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.

[0596] [Fourth Embodiment]

[0597] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0598] 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.

[0599] 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).

[0600] 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.

[0601] 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.

[0602] 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).

[0603] 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.

[0604] 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.

[0605] 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.

[0606] 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.

[0607] 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.

[0608] 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.

[0609] 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".

[0610] This invention is a personalized notification system for supporting the elderly, improving the safety and comfort of the user's daily life. The embodiments for carrying out the invention and the processing of its program are described below.

[0611] The device collects data on the behavior and lifestyle patterns of elderly individuals from sensor devices. For example, it uses smartphones and smartwatches to record location information, steps taken, and heart rate, and to understand their daily routines. This information is collected automatically without requiring user awareness, thus reducing the burden on elderly individuals.

[0612] The server transmits the collected data to a cloud environment for secure storage. The data is organized for each individual user and stored in a dedicated database. Machine learning algorithms are used to analyze this data and identify each user's unique behavioral patterns and lifestyle rhythms.

[0613] Based on the analysis results, the server generates a notification schedule best suited to each user. For example, reminders can be set based on behavioral patterns to manage daily medication times or important appointments. This schedule is customized according to each user's preferences and is delivered in the most optimal format, such as voice notifications, vibrations, or screen displays.

[0614] The device sends reminders to the user according to the generated schedule. When the time comes, a notification such as "It's time to take your medicine" appears on the smartphone. Data about the completed actions is also sent back to the server and used for future analysis and schedule generation.

[0615] Furthermore, the server has a mechanism to respond quickly using anomaly detection means if any unusual behavior is detected. In this case, notifications can be automatically sent to family members or medical institutions, ensuring the safety of the elderly.

[0616] As an example of this system, suppose user C needs to take their blood pressure medication at 7:00 AM every morning. Based on the user's daily routine data, the server schedules a notification to be sent to the device at 6:45 AM every day, and the device smoothly delivers the notification to the user. If the user fails to respond to the notification for three consecutive days, the system sends a notification to a family member to ensure that necessary support is provided.

[0617] This invention reduces anxiety caused by forgetfulness in the elderly, making it possible to manage daily life more safely and efficiently.

[0618] The following describes the processing flow.

[0619] Step 1:

[0620] The device collects data about the lifestyle of elderly individuals. This is done via smartphones or smartwatches and includes location information, step count, heart rate, and schedule information. This data is temporarily stored within the device.

[0621] Step 2:

[0622] The device sends the collected data to the server at regular intervals. The transmitted data is encrypted to protect privacy. After transmission, the data on the device is periodically updated.

[0623] Step 3:

[0624] The server stores received data in a cloud database. This data is organized by user and immediately available for analysis. The system ensures data integrity while always reflecting the latest information.

[0625] Step 4:

[0626] The server uses machine learning algorithms to analyze user behavior patterns based on accumulated data. This reveals the user's typical daily schedule and activity patterns.

[0627] Step 5:

[0628] The server automatically generates individual notification schedules based on the analyzed data. The schedules reflect the user's behavior patterns and set reminders at optimal times.

[0629] Step 6:

[0630] The server sends the generated schedule to the device, which then prepares to notify the user. The schedule is designed to notify the user in the most suitable way (e.g., voice notification, screen display, vibration).

[0631] Step 7:

[0632] The device sends a notification to the user at a set time. For example, when it's time to take medication, a notification saying "It's time to take your medication" will appear on the screen. Once the user acknowledges the notification, a record of that is sent to the server.

[0633] Step 8:

[0634] The server collects user response data and uses it for future analysis and scheduling improvements. This improves the accuracy of reminders and user convenience.

[0635] Step 9:

[0636] The server continuously monitors user behavior for any abnormalities. If an abnormality is detected, for example, if there is no response to multiple notifications, notifications are automatically sent to family members or healthcare providers to ensure appropriate support is provided.

[0637] (Example 1)

[0638] 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".

[0639] In daily life, older adults may face difficulties in efficiently and safely managing their health and performing important daily tasks. In particular, failure to properly take regular medications or manage important appointments increases health risks. Furthermore, a lack of prompt response when older adults exhibit abnormal behavior can lead to further danger. Therefore, personalized support based on the individual behavioral characteristics of older adults is needed to improve safety and comfort.

[0640] 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.

[0641] In this invention, the server includes information acquisition means for acquiring biometric data and learning the user's behavioral patterns, analysis means for analyzing the acquired information and identifying behavioral characteristics, and schedule creation means for creating optimized notification schedules based on behavioral characteristics. This makes it possible to contribute to the health and safety of the elderly.

[0642] "Biometric data" refers to information such as location data, step count, and heart rate acquired to indicate the activity level and health status of elderly individuals.

[0643] "Information acquisition means" refers to a system for collecting biometric data from sensor devices and learning the user's behavioral patterns.

[0644] "Analysis means" refers to techniques used to analyze acquired information and identify user behavioral characteristics.

[0645] A "schedule creation method" is a method for generating an optimal notification schedule for a user based on analyzed behavioral characteristics.

[0646] An "information transmission method" is a system that appropriately transmits necessary information to users according to a created schedule.

[0647] An "anomaly detection method" is a technology that detects behavioral characteristics that are different from the norm and transmits information to an external mechanism as needed.

[0648] This invention is a system designed to support the elderly, learning each user's individual lifestyle and enabling safe and efficient daily management. Specifically, it uses smartphones and smartwatches as sensor devices to automatically collect biometric data. These devices acquire data such as the user's location, steps taken, and heart rate, providing various biometric information.

[0649] The device sends this data to the cloud, where necessary information is accumulated through collaboration with the server. The server utilizes cloud-based storage media and employs machine learning algorithms. This allows for precise analysis of the collected information and identification of user behavioral characteristics.

[0650] Next, the server generates a notification schedule optimized for the user's behavior based on the analysis results. The generated schedule is customized in various forms, such as voice, vibration, and screen display, and adjusted according to the user's preferences. For example, if a user needs to take medication at 7:00 AM every morning, the server will set up a notification to be sent to the device at 6:45 AM.

[0651] Based on this generated schedule, the device sends notifications to the user at the specified times. This allows the user to avoid forgetting important appointments and tasks and to respond in a timely manner. Data on whether the user responded to the notification is also sent from the device to the server, which is used to improve future notification schedules.

[0652] If the server detects any unusual behavioral patterns, it will use anomaly detection measures to respond quickly. If necessary, it will send alerts to family members or medical institutions to ensure user safety.

[0653] As a concrete example, the following prompt is given: "Please explain, with specific examples, how to generate a personalized notification schedule based on the lifestyle pattern data of elderly individuals."

[0654] This system allows users to live their lives with peace of mind, and also provides families with a means to remotely monitor the condition of elderly individuals.

[0655] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0656] Step 1:

[0657] The device uses sensor devices (smartphones and smartwatches) to collect biometric data (location information, steps, heart rate, etc.). This data is used to understand the user's daily behavior and health status. It receives biometric data from sensors as input and converts it into a format for transmission to the cloud as output. Specifically, each device periodically collects data and standardizes the data format as needed.

[0658] Step 2:

[0659] The device sends the collected data to the cloud environment. The cloud receives the data while protecting privacy by using data encryption technology. It takes standardized data sent from the device as input and securely stores it on a storage medium in the cloud as output. Specifically, this involves transferring data in real time via a data transmission protocol and storing it in a cloud database.

[0660] Step 3:

[0661] The server analyzes data stored in the cloud. Using machine learning algorithms, it analyzes user behavioral characteristics and identifies patterns. It uses a large amount of biometric data acquired from the cloud as input and extracts behavioral patterns based on user characteristics as output. Specifically, it performs data cleansing, then applies algorithms to generate various statistical information.

[0662] Step 4:

[0663] The server generates an optimal notification schedule for the user based on the analysis results. It uses behavioral patterns extracted by the server as input and creates a notification schedule optimized for the user's daily routine as output. Specific actions include setting notification timings that take into account the user's specific needs (e.g., medication timing).

[0664] Step 5:

[0665] The device receives notification schedules generated by the server and sends notifications to the user. It receives schedule information provided by the server as input and notifies the user in the form of audio notifications, vibrations, screen displays, etc. The specific operation includes a process where the device triggers a notification at a specified time and provides an alert to the user.

[0666] Step 6:

[0667] The server collects user responses to notifications as data again to use for subsequent analysis. It receives user response data sent from the terminal as input and generates data to improve scheduling through continuous pattern analysis as output. Specifically, it checks whether the user followed the notification and whether there were any anomalies, and updates the dataset to reflect the results.

[0668] Step 7:

[0669] The server utilizes a function to send notifications to external organizations when it detects abnormal behavior. It extracts patterns that deviate from normal behavior as input, and sends alerts to family members or medical institutions as needed as output. The specific operation involves data analysis using an anomaly detection algorithm and automatic message sending to configured contacts.

[0670] (Application Example 1)

[0671] 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".

[0672] In the lives of the elderly, daily health management and schedule management are often not properly carried out, and they frequently forget to take medication or exercise, which can lead to a deterioration of their health and safety. Furthermore, when abnormal behavior occurs, prompt action may not be taken, and the safety of the elderly is not adequately ensured. To improve this situation, an efficient and personalized notification system is needed.

[0673] 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.

[0674] In this invention, the server includes information gathering means, data analysis means, timetable generation means, information transmission means, anomaly detection means, and information linking means. This enables continuous management of the daily lives of elderly people and provides optimal notifications based on individual behavioral patterns. Furthermore, because it can quickly cooperate with external organizations to respond when abnormal behavior is detected, it becomes possible to provide a safer and more comfortable living environment.

[0675] "Information gathering means" refers to a system that automatically collects data on the lifestyles of elderly people, and the information obtained through smart devices, etc.

[0676] "Data analysis means" refers to a processing method for analyzing collected data and identifying the behavioral characteristics of elderly people, and may utilize machine learning algorithms.

[0677] The "timetable generation means" is a device that has the function of creating individually optimized notification schedules based on analyzed behavioral characteristics.

[0678] An "information transmission means" is a system for providing users with information such as reminders based on a generated notification schedule.

[0679] An "anomaly detection mechanism" is a system for detecting behavioral characteristics that are different from the norm and responding quickly, and includes a function to send notifications to external parties as needed.

[0680] "Information sharing means" refers to communication methods used to share detected anomaly information and important notifications with external organizations to facilitate a rapid response.

[0681] To implement this invention, a smart device is first used as a means of information gathering. Specifically, sensors in a smartphone or smartwatch are used to continuously collect data such as the elderly person's location, steps taken, and heart rate. This data is acquired automatically, without the user's awareness, and the information is transmitted to a cloud server.

[0682] The server stores this collected data in a centralized database and analyzes it using machine learning algorithms, specifically TensorFlow. This data analysis identifies each user's behavioral characteristics and generates individually optimized notification schedules based on those characteristics. This schedule generation method can, for example, estimate the timing of a user's medication intake or exercise.

[0683] The user's device sends appropriate reminders via the information transmission means, according to the schedule created by the timetable generation means. Reminders may be provided as voice notifications or text messages. The anomaly detection means identifies unusual behavioral characteristics and uses the information sharing means to quickly notify external organizations and family members based on the results.

[0684] For example, if an elderly person needs to take their blood pressure medication at 8:00 AM every morning, the system is designed to send a reminder to their smartphone at 7:50 AM based on data analysis. If the user fails to heed this notification, and this continues for three consecutive days, the system will automatically contact their family through an information sharing mechanism.

[0685] An example of a prompt message might be, "Write a scenario for a care support app that analyzes the behavioral patterns of elderly people and sends reminders at specific times." Such a system would make life safer and more comfortable for the elderly.

[0686] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0687] Step 1:

[0688] The device automatically collects data such as the elderly person's location, steps taken, and heart rate using the smart device's sensors. This collected data is then sent directly to a cloud server as input. This process involves utilizing the device's sensor data, continuously acquiring data in the background, and uploading the data to the server via the network.

[0689] Step 2:

[0690] The server stores the data sent to the cloud in a centralized database. On the server, this data is formatted into a pre-configured format and then organized and saved in the storage space allocated to each user. This is the server's input, and the organized information in the database is the output.

[0691] Step 3:

[0692] The server begins analyzing the accumulated data using machine learning algorithms. Specifically, TensorFlow is used to model and analyze the behavioral characteristics of each user. This process identifies each user's behavioral pattern, and the results are stored as output. The data before analysis is the input, and the behavioral patterns resulting from the analysis are the output.

[0693] Step 4:

[0694] The server uses a timetable generation mechanism based on behavioral patterns to create an optimized notification schedule. In this step, based on the analysis results, the server calculates the notification timing according to the user's daily routine and determines the specific reminder content. The resulting timetable is then output.

[0695] Step 5:

[0696] The device retrieves the notification schedule sent from the server and notifies the user at the appropriate time. This notification is presented to the user as an audio alarm or a push notification on the screen. In this step, the output is the notification content to be provided to the user.

[0697] Step 6:

[0698] The server uses anomaly detection means to detect behavior that differs from the received behavior pattern. If an anomaly exceeding a set threshold is detected, it notifies external organizations and family members through information sharing means. The detection of abnormal behavior becomes the input, and a warning notification is generated as the output.

[0699] 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.

[0700] This invention provides advanced support that takes into account the user's emotional state by combining a personalized notification system for assisting the elderly with an emotion engine. An embodiment of this system will be described in detail.

[0701] The device collects basic data about the elderly person's activity and lifestyle patterns through sensor devices. This data includes location information, steps taken, heart rate, and schedule lists. The device also uses its built-in camera and microphone to activate an emotion engine that recognizes the user's emotions. It can evaluate the user's emotions in real time by utilizing facial expression analysis, voice tone analysis, and even linguistic analysis in text.

[0702] The server simultaneously transmits both collected behavioral and emotional data to a cloud database for secure storage. The data is precisely analyzed to identify not only typical user behavioral patterns but also emotional patterns. Machine learning algorithms are used in this analysis, combining historical and new data to provide responses tailored to user needs.

[0703] The emotion data recognized by the emotion engine is used to generate customized notifications tailored to the user's emotional state. For example, if the user is stressed, the content of the notification can be changed to softer language or words of encouragement. Furthermore, the emotion data is evaluated in correlation with behavioral data, and the notification schedule is adjusted to match the user's optimal mental state.

[0704] The device sends notifications to the user based on the generated schedule. These notifications are delivered at the appropriate time and in the appropriate manner, taking into account the user's emotional state. For example, if the user is feeling tired when it's time to take medication, the voice tone can be changed to a calmer one, and the notification can say something like, "Take your medication after you've had a short rest."

[0705] The presence of an emotion engine allows the system to respond quickly to changes in the user's emotions and provide emotional support in daily life. Furthermore, by combining it with conventional anomaly detection functions, it can notify family members and medical institutions if abnormalities occur not only in the user's behavior but also in their emotions.

[0706] Thus, the present invention incorporates cutting-edge technology to improve the quality of life for the elderly and provide a safe and emotionally comfortable living environment.

[0707] The following describes the processing flow.

[0708] Step 1:

[0709] The device collects data related to the activities and lifestyle patterns of elderly individuals using sensor devices. Specifically, this includes biometric information such as location, steps taken, and heart rate. This information is stored within the device as basic data for understanding daily lifestyle habits.

[0710] Step 2:

[0711] The device utilizes its built-in camera and microphone to recognize the user's emotional state in real time. This process analyzes the user's facial expressions and voice tone to determine their current emotional state. As a result, emotional data is recorded within the device.

[0712] Step 3:

[0713] The device periodically sends collected behavioral and emotional data to a server. The transmitted data is encrypted, and secure data storage in the cloud is guaranteed.

[0714] Step 4:

[0715] The server analyzes data stored in the cloud database using machine learning algorithms. It simultaneously analyzes behavioral and emotional patterns to form an intelligent understanding based on the individual needs and requirements of the user.

[0716] Step 5:

[0717] The server dynamically generates notification content and timing based on the user's emotional state. For example, it might generate calming notifications for users experiencing stress and adjust the notification schedule accordingly.

[0718] Step 6:

[0719] The server sends the generated notifications and schedules to the device. This prepares the notifications and enables user-optimized reminders.

[0720] Step 7:

[0721] The device will send notifications to the user based on a schedule. These notifications will be delivered in a way and with content that takes into account the user's emotional state. For example, a message such as "Take your medication after you have relaxed" may be presented in a calm voice or on-screen display.

[0722] Step 8:

[0723] The server collects user responses as data after a notification is sent and uses this data to optimize the next notification schedule.

[0724] Step 9:

[0725] The server monitors the user's behavior and emotional state for any abnormalities. If an emotional abnormality is detected, it automatically notifies family members and medical institutions so that necessary support can be provided.

[0726] (Example 2)

[0727] 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".

[0728] Supporting the elderly requires not only understanding their behavioral patterns but also providing flexible responses tailored to their individual emotional states. However, conventional systems have struggled to quickly detect emotional changes and respond appropriately. Furthermore, they lacked mechanisms to provide timely notifications when abnormal emotional states occurred. This resulted in a problem where the quality of life for the elderly could not be adequately improved.

[0729] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0730] In this invention, the server includes information gathering means for learning the lifestyle and emotional state of elderly people, information analysis means for analyzing the collected information to identify behavioral and emotional patterns, and plan generation means for generating an optimal notification schedule based on the behavioral and emotional patterns. This enables notification delivery tailored to the individual emotional state of elderly people, thereby improving their quality of life and providing a safe environment.

[0731] "Information gathering means" refers to devices or software used to acquire data on the lifestyle and emotional state of elderly people.

[0732] "Information analysis methods" refer to technologies that use collected data to identify patterns in the behavior and emotions of elderly individuals.

[0733] The "plan generation method" is a function that creates an optimal notification schedule for elderly people based on the analysis results.

[0734] "Notification delivery means" refers to a device or method that provides users with emotionally relevant information according to a generated schedule.

[0735] An "anomaly detection system" is a mechanism that quickly identifies changes in emotions and behavior and issues warnings to external organizations as needed.

[0736] A "remote data recording device" is a cloud or server environment for securely storing collected information.

[0737] "Data analysis technology" refers to analytical methods used to evaluate collected information and gain useful insights.

[0738] This invention is a personalized notification system for supporting the elderly, providing notifications that take into account the user's lifestyle and emotional state. This system is composed of a combination of information gathering means, information analysis means, and plan generation means.

[0739] The device functions as a means of information gathering, acquiring data on the daily activities and emotional state of elderly individuals. This includes sensor devices for acquiring location information, step count, and heart rate, as well as cameras and microphones for analyzing the user's facial expressions and voice. This makes it possible to assess the user's emotions in real time.

[0740] The server functions as an information analysis tool, storing data collected from terminals in a remote data recording device. Furthermore, it analyzes the data using machine learning algorithms to identify specific behavioral and emotional patterns. Based on these analysis results, the plan generation tool creates an optimal notification schedule.

[0741] Based on this schedule, the device acts as a notification delivery mechanism, providing users with appropriate and customized notifications. The content of the notifications changes according to the user's emotional state, allowing for flexible responses. For example, if the user is feeling stressed, the device can use a calmer voice tone and notify them with a message like, "Take a short break and then take your medicine."

[0742] As a concrete example, the following is an example of a prompt statement to be input to a generative AI model.

[0743] Prompt example: "A 70-year-old female user appears more tired than usual during her recent walks. Use the emotion engine to create an encouraging message for the user based on this information."

[0744] This system allows elderly people to live their daily lives with peace of mind, improving both their quality of life and safety at the same time.

[0745] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0746] Step 1:

[0747] The device uses sensor devices to collect data about the daily lives of elderly individuals. This data includes location information, step count, and heart rate. Using this physiological data as input, the device uses its built-in camera and microphone to analyze the user's facial expressions and voice in real time using an emotion engine. The output is data indicating the user's emotional state.

[0748] Step 2:

[0749] The server receives and stores behavioral and emotional data transmitted from terminals in a remote data recording device. Inputs include data from terminals, which the server stores in a secure cloud environment. Outputs are datasets prepared for analysis. Based on this dataset, the server uses machine learning algorithms to identify behavioral and emotional patterns.

[0750] Step 3:

[0751] The server analyzes identified behavioral and emotional patterns and generates an optimized notification schedule based on the user's state. The input is the dataset obtained in step 2, and the output is a personalized notification schedule for the user. In this step, a generative AI model is used to generate prompts that adjust the notification content. For example, the prompt might say, "The user is tired, please create a message to help them relax."

[0752] Step 4:

[0753] The device delivers notifications to the user at the appropriate time according to a notification schedule sent from the server. The input is the generated notification schedule, and the output is the customized notification provided to the user. Notifications are delivered via voice assistant or screen display and respond flexibly to the user's emotional state. For example, it can support the user in acting at their own pace by delivering a voice message such as, "Take your medicine after a short break."

[0754] (Application Example 2)

[0755] 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 robot 414 as the "terminal".

[0756] While elderly individuals require support in daily activities and health management, notification systems that merely inform them of the timing of such events have the problem of failing to provide appropriate support tailored to their emotional state. Furthermore, notification systems that do not consider emotional support may cause stress to the elderly. In addition, conventional systems have difficulty comprehensively capturing abnormal behavior or emotional states, making it difficult to respond in a timely manner.

[0757] 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.

[0758] In this invention, the server includes data collection means, data analysis means, schedule generation means, sentiment analysis means, and notification customization means. This enables a comprehensive evaluation of the user's behavior patterns and emotional state, and personalized notifications tailored to each individual's emotional state.

[0759] A "data collection device" is a device that uses sensors to acquire information about the daily activities and health status of elderly people.

[0760] A "data analysis tool" is a processing system used to identify patterns of behavior and emotion based on collected information.

[0761] A "schedule generation device" is a device that plans to send notifications at appropriate times according to the user's behavior patterns.

[0762] A "notification transmission means" is a device used to convey information to users based on a predetermined schedule.

[0763] An "anomaly detection device" is a device that detects unusual behavior or emotional changes and, if necessary, notifies external parties such as family members or medical institutions.

[0764] "Emotional analysis methods" refer to the process of analyzing a user's facial expressions and voice to identify their emotional state at that time.

[0765] A "notification customization method" is a processing system that adjusts notification content to convey information in an appropriate manner, taking into account the user's emotional state.

[0766] The system implementing this invention is designed as a personalized notification platform to assist the elderly. This system consists of a terminal, a server, a cloud database, and an emotion recognition engine.

[0767] The device functions as a data collection tool to acquire activity and health data from elderly individuals. This data includes location information, step count, heart rate, and schedule lists. It also features an emotion analysis system that uses a built-in camera and microphone to analyze the user's facial expressions and voice, recognizing their emotional state in real time. This allows the user to receive notifications tailored to their current mental state.

[0768] The server securely transmits and stores collected data in a cloud database as a data analysis tool. The data in the cloud is analyzed using machine learning algorithms to identify user behavior and emotional patterns. Based on these analysis results, a schedule generation tool creates an optimal notification schedule.

[0769] The notification customization feature adjusts notification content according to the user's emotional state. For example, if emotion analysis indicates that the user is stressed, the notification will use calm language and encouraging words.

[0770] For example, if the system determines that a user is feeling tired during a walk, the notification will be sent in a gentle tone, such as, "Slow down and take a break." Another example of a prompt used in the "Generative AI Model" is, "Use the following user behavior and emotion data to generate a notification for stress reduction for the elderly: increased heart rate, tired appearance, planned walk, and words of encouragement are needed."

[0771] In this way, it becomes possible to provide more personalized support while aiming to improve the quality of life for the elderly throughout the entire system.

[0772] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0773] Step 1:

[0774] The device collects location information, steps taken, heart rate, and schedule lists of elderly individuals through sensors. This data serves as foundational data for monitoring the user's daily activities and health status. Input is raw data from sensors, and output is activity information in an organized data format.

[0775] Step 2:

[0776] The device's built-in camera and microphone analyze the user's facial expressions and voice in real time. This identifies the emotions the user is feeling. The input is video and audio data, and the output is emotion labels such as joy, sadness, and stress. This process collects emotion-based data.

[0777] Step 3:

[0778] The device sends collected behavioral and emotional data to a server. This data is stored in a cloud database and analyzed by machine learning algorithms. The input is all the data sent from the device, and the output is the analysis results of behavioral and emotional patterns.

[0779] Step 4:

[0780] The server uses a schedule generation mechanism to create an optimal notification schedule based on the user's behavioral and emotional patterns. The input is the result of data analysis, and the output is a notification schedule tailored to a specific timing.

[0781] Step 5:

[0782] The server adjusts notification content using notification customization means according to the emotional state obtained by the emotion analysis means. The input is an emotional state label, and the output is a personalized notification message. For example, if a stressful state is detected, the notification content is changed to a calm and gentle one.

[0783] Step 6:

[0784] The device sends notifications to the user based on a generated schedule and customized content. The input is the customized notification content and schedule sent from the server, and the output is a timely and appropriate notification message to the user. This allows the user to receive emotionally tailored advice and reminders.

[0785] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the controlled object 443 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.

[0786] 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.

[0787] In the above embodiment, an example was given in which the 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 robot 414.

[0788] Furthermore, the emotion identification model 59, acting as an emotion engine, may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0789] Figure 9 shows an emotion map 400 in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0790] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0791] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0792] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, motorcycles, etc., emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0793] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0794] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0795] The above description primarily focuses on the functions of the data processing device 12 in relation to this disclosure. However, the system related to this disclosure is not necessarily implemented on a server. The system related to this disclosure may be implemented as a general information processing system. This disclosure may be implemented, for example, as a software program that runs on a personal computer or as an application that runs on a smartphone. The method related to this disclosure may be provided to users in SaaS (Software as a Service) format.

[0796] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing of the specific process may be performed by multiple computers, including computer 22. For example, a data generation model 58 may be provided in an external device of the data processing device 12, and the external device may generate data according to the input data.

[0797] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0798] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[0799] Furthermore, it is not necessary to store the entirety of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0800] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0801] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0802] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0803] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0804] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and the like that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0805] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0806] The following is further disclosed regarding the embodiments described above.

[0807] (Claim 1)

[0808] A data collection method for learning about the lifestyles of the elderly,

[0809] A data analysis method that analyzes collected data to identify behavioral patterns,

[0810] A schedule generation means that generates an optimal notification schedule based on behavioral patterns,

[0811] A notification sending means that notifies the user based on the generated schedule,

[0812] An anomaly detection means that detects abnormal behavioral patterns and notifies an external organization,

[0813] A system that includes this.

[0814] (Claim 2)

[0815] The system according to claim 1, wherein collected data is stored in a cloud database and analyzed using a machine learning algorithm.

[0816] (Claim 3)

[0817] The system according to claim 1, wherein the generated notifications are customized according to the user's preferences.

[0818] "Example 1"

[0819] (Claim 1)

[0820] A means of acquiring information that obtains biometric data and learns the user's behavioral patterns,

[0821] An analytical means for analyzing acquired information and identifying behavioral characteristics,

[0822] A scheduling method for creating notification schedules optimized based on behavioral characteristics,

[0823] A means of information transmission that conveys information to users according to the created schedule,

[0824] An anomaly detection means that detects abnormal behavioral characteristics and transmits information to an external mechanism,

[0825] A system that includes this.

[0826] (Claim 2)

[0827] The system according to claim 1, wherein acquired information is stored on a cloud-based recording medium and analyzed using machine learning techniques.

[0828] (Claim 3)

[0829] The system according to claim 1, wherein the generated notifications are adjusted according to the user's preferences.

[0830] "Application Example 1"

[0831] (Claim 1)

[0832] Information gathering methods for learning about the lifestyles of the elderly,

[0833] A data analysis method that analyzes collected information to identify behavioral characteristics,

[0834] A timetable generation means that generates an optimal notification timetable based on behavioral characteristics,

[0835] Information transmission means for notifying users based on the generated timetable,

[0836] An anomaly detection means that detects abnormal behavioral characteristics and notifies an external organization,

[0837] Information sharing means to facilitate a rapid response in emergencies,

[0838] A system that includes this.

[0839] (Claim 2)

[0840] The system according to claim 1, wherein collected information is stored in a centralized database and analyzed using a machine learning algorithm.

[0841] (Claim 3)

[0842] The system according to claim 1, wherein the generated notifications are adapted according to the user's preferences.

[0843] "Example 2 of combining an emotion engine"

[0844] (Claim 1)

[0845] Information gathering methods for learning about the lifestyles and emotional states of the elderly,

[0846] Information analysis means for analyzing collected information to identify behavioral and emotional patterns,

[0847] A plan generation means for generating an optimal notification schedule based on behavioral and emotional patterns,

[0848] A notification delivery method that provides emotion-responsive notifications to users based on a generated schedule,

[0849] An anomaly detection method that quickly detects changes in emotions and notifies an external organization,

[0850] A system that includes this.

[0851] (Claim 2)

[0852] The system according to claim 1, wherein collected information is stored in a remote data recording device and analyzed using data analysis technology.

[0853] (Claim 3)

[0854] The system according to claim 1, wherein the generated notification is adjusted according to the user's emotions.

[0855] "Application example 2 when combining with an emotional engine"

[0856] (Claim 1)

[0857] A data collection method for learning about the lifestyles of the elderly,

[0858] A data analysis method that analyzes collected data to identify behavioral patterns,

[0859] A schedule generation means that generates an optimal notification schedule based on behavioral patterns,

[0860] A notification sending means that notifies the user based on the generated schedule,

[0861] An anomaly detection means that detects abnormal behavioral patterns and notifies an external organization,

[0862] An emotion analysis means that analyzes the user's facial expressions and voice to identify emotions,

[0863] A notification customization method that adjusts notification content according to emotional state,

[0864] A system that includes this.

[0865] (Claim 2)

[0866] The system according to claim 1, wherein collected data is stored in a cloud database and analyzed using a machine learning algorithm.

[0867] (Claim 3)

[0868] The system according to claim 1, wherein the generated notifications are customized according to the user's preferences and emotional state. [Explanation of Symbols]

[0869] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. Information gathering methods for learning about the lifestyles of the elderly, A data analysis method that analyzes collected information to identify behavioral characteristics, A timetable generation means that generates an optimal notification timetable based on behavioral characteristics, Information transmission means for notifying users based on the generated timetable, An anomaly detection means that detects abnormal behavioral characteristics and notifies an external organization, Information sharing means to facilitate a rapid response in emergencies, A system that includes this.

2. The system according to claim 1, wherein collected information is stored in a centralized database and analyzed using a machine learning algorithm.

3. The system according to claim 1, wherein the generated notifications are adapted according to the user's preferences.

Images