system

Abstract

We provide the system. [Solution] A means of acquiring data on a subject using various sensors, A means for executing an algorithm that analyzes the acquired data and detects anomalies, A means for generating and sending a notification based on the detected anomaly, 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 and includes steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a chatbot character, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance as a response to the user utterance.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In modern society, in order to ensure the safety of children and the elderly, a more rapid and accurate monitoring system is required. However, existing safety systems lack accuracy in detecting abnormalities and accuracy of position information, and necessary information may not be provided in a timely manner. As a result, prompt responses may be delayed or unnecessary false alarms may occur frequently. It is an object of this invention to solve these problems and achieve comprehensive security enhancement across the region.

Means for Solving the Problems

[0005] This invention aims to improve accuracy by incorporating data acquisition means using various sensors and employing a generative model that analyzes the collected data to detect anomalies. Furthermore, it provides means for generating notifications, including detailed information about the situation and recommended countermeasures, based on anomaly detection, by applying natural language processing technology. In this way, it becomes possible to quickly and effectively communicate useful information to users in a timely manner, supporting rapid response on-site. The entire system functions as a highly accurate and efficient monitoring network, thereby improving security.

[0006] "Various sensors" are measuring devices used to acquire a variety of information, such as location information, acceleration, temperature, humidity, sound, and video.

[0007] "Means of acquiring data" refers to a system that collects information about the subject's state and environment through various sensors and wearable devices.

[0008] A "generative model" is an algorithm that uses machine learning to learn patterns from data and then makes predictions and analyses for new situations.

[0009] "Anomaly detection" is the process of identifying deviations from normal behavioral patterns or environmental conditions and determining that a particular event is an anomaly.

[0010] "Natural language processing technology" refers to the technology that enables computers to understand, interpret, and generate human language.

[0011] "Means for generating and sending notifications" refers to a system that creates and sends messages to relevant parties informing them of the situation and countermeasures based on detected anomalies. [Brief explanation of the drawing]

[0012] [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] It is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] It is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] It is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] It is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] It is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] It is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] It shows an emotion map to which a plurality of emotions are mapped. [Figure 10] It shows an emotion map to which a plurality of emotions are mapped. [Figure 11] It is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] It is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] It is a sequence diagram showing the processing flow of the data processing system in Example 2 when an emotion engine is combined. [Figure 14] It is a sequence diagram showing the processing flow of the data processing system in Application Example 2 when an emotion engine is combined.

Embodiments for Carrying Out the Invention

[0013] Hereinafter, an example of an embodiment of a system according to the technology of the present disclosure will be described with reference to the accompanying drawings.

[0014] First, the language used in the following description will be explained.

[0015] In the following embodiments, the labeled 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.

[0016] In the following embodiments, the labeled RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0017] In the following embodiments, the labeled 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, and the like.

[0018] In the following embodiments, the labeled communication I / F (Interface) is an interface including a communication processor and an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark), and the like.

[0019] 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."

[0020] [First Embodiment]

[0021] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0022] 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.

[0023] 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).

[0024] 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.

[0025] 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.

[0026] 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.

[0027] 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.

[0028] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0029] 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.

[0030] 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.

[0031] 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.

[0032] 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".

[0033] This invention is an advanced monitoring system that automatically performs data collection using various sensors, anomaly detection, and notification. This system mainly consists of a data collection module, a data processing module, and a notification management module, and each module works in coordination with the others.

[0034] Program Implementation

[0035] Data Acquisition Module

[0036] The device periodically acquires GPS location information, acceleration data, environmental audio, and video via wearable devices and environmental sensors.

[0037] The collected data is transmitted to the server using wireless communication technology.

[0038] Data Processing Module

[0039] The server first preprocesses the received data, removing outliers and correcting the data.

[0040] Next, a generative model is used to analyze the data and identify differences from normal behavioral patterns to detect anomalies.

[0041] The anomaly detection algorithm incorporates machine learning techniques, continuously learning from past data to improve detection accuracy.

[0042] Notification management module

[0043] The server immediately generates a notification to relevant parties if an anomaly is detected.

[0044] This notification uses natural language processing technology to provide users with a detailed description of the situation and recommended countermeasures.

[0045] Users receive notifications, check the specific situation through the application, and take prompt action as needed.

[0046] Specific example

[0047] For example, suppose a device acquires data from an elderly person's accelerometer indicating a sudden movement, i.e., a fall. The server analyzes this data and detects an anomaly as a deviation from the normal range of movement. It then generates a notification containing details of the anomaly and necessary countermeasures (e.g., "An elderly person may have fallen. Please check the scene."). The user receives this notification and takes action, such as going to the scene or checking remotely.

[0048] Thus, the present invention is a system that efficiently ensures the safety of an entire region by utilizing various sensor data to immediately detect abnormal conditions. For users, it enhances their sense of security in daily life by enabling quick and appropriate responses to the situation.

[0049] The following describes the processing flow.

[0050] Step 1:

[0051] The device periodically acquires data such as GPS location information, acceleration, ambient sound, and video through wearable devices and fixed sensors. This prepares the system for real-time monitoring of the subject's movements and environmental changes.

[0052] Step 2:

[0053] The terminal collects data and transmits it to the server using wireless communication technology. The data is transmitted in a structured format and is immediately ready for analysis.

[0054] Step 3:

[0055] The server stores the received data in data storage and performs preprocessing. This involves removing outliers and imputing missing data to build a reliable dataset.

[0056] Step 4:

[0057] The server applies an anomaly detection algorithm using a generative model to the pre-processed data. The model learns from past data and determines whether the current data deviates from normal behavioral patterns.

[0058] Step 5:

[0059] The server immediately generates an alert if an anomaly is detected. This alert includes a specific description of the anomaly, generated using natural language processing technology, and recommended countermeasures.

[0060] Step 6:

[0061] The server generates alerts and notifies parents and local community watch representatives. Notifications are sent using methods such as push notifications, email, and SMS.

[0062] Step 7:

[0063] Users receive notifications and can use their smartphones or computers to view detailed information. These notifications include instructions for situations requiring immediate action, supporting quick decision-making.

[0064] Step 8:

[0065] The user takes appropriate action based on the notification. For example, they may go to the site, remotely check the situation, or contact emergency services if necessary.

[0066] (Example 1)

[0067] 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."

[0068] In modern society, with the increasing diversity of living environments, there is a growing need for monitoring systems that can quickly and accurately detect anomalies and prompt appropriate responses. Conventional systems have struggled to improve the accuracy of anomaly detection and to provide timely, situation-appropriate countermeasures. Therefore, the challenge to be addressed is to provide a monitoring system that combines efficient and reliable anomaly detection and notification functions.

[0069] 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.

[0070] In this invention, the server includes means for acquiring information using various detection devices, means for transmitting the acquired information using wireless communication technology, and means for analyzing the information using a generative model and detecting anomalies. This enables efficient information collection and rapid response to anomalies based on the results of the analysis.

[0071] A "detection device" is a general term for equipment or devices that can acquire information from an object, and these are used in a variety of environments.

[0072] "Information" refers to a collection of data acquired by a detection device, including location information, operational data, and environmental conditions.

[0073] "Wireless communication technology" refers to all technologies used to transmit and receive information by means other than wired connections.

[0074] A "generative model" is a computational model used to analyze and predict new data by learning from past data.

[0075] An "anomaly" refers to data or situations that deviate from normal operation or state, and is detected based on specific criteria.

[0076] A "notification" is a message generated when the system detects an anomaly, providing warnings or information to the user.

[0077] "Natural language processing technology" refers to the technology that enables computers to understand, generate, and process human natural language.

[0078] A "countermeasure" is a guideline that outlines the specific actions and procedures that users should take in response to detected anomalies.

[0079] Embodiments of this invention include the following specific configurations and operations.

[0080] This system provides advanced monitoring capabilities by acquiring data in real time using various detection devices, detecting anomalies based on that data, and generating notifications. The terminal periodically acquires various information such as heart rate, acceleration data, location information, ambient sounds, temperature, and humidity using wearable devices and environmental sensors. This process often utilizes common wearable devices and IoT sensors.

[0081] The data collected by the terminal is transmitted to the server via wireless communication technologies such as Wi-Fi or Bluetooth. The server preprocesses the received data using Python libraries (e.g., numpy and pandas) to correct for outliers and missing values. Subsequently, a generative model is used for data analysis. This generative model can utilize TENSORFLOW® or PyTorch.

[0082] The server performs data analysis using generative models, identifies differences from normal behavior patterns using machine learning techniques, and detects anomalies. If an anomaly is detected, it uses natural language processing techniques (e.g., OpenAI's GPT model) to generate a notification that includes a detailed description of the situation and recommended countermeasures. This notification is immediately sent to the user's smartphone or tablet via the app.

[0083] Users are expected to take the most appropriate action quickly based on the notifications they receive. This system is particularly useful in situations such as monitoring the health of the elderly and automated safety management. For example, if a terminal acquires data indicating a possible fall by an elderly person, the server will recognize this as an anomaly and generate a notification such as, "An elderly person may have fallen. Please check the site," and send it to the user.

[0084] By utilizing a generative AI model, the system can automatically generate detailed explanations and instructions based on prompts. An example of a prompt might be, "Generate a notification message to prevent falls in the home."

[0085] This configuration enhances the safety of the community and improves people's sense of security in their daily lives.

[0086] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0087] Step 1:

[0088] The device acquires data. Specifically, the device collects heart rate, acceleration data, location information, etc., using wearable devices and environmental sensors. This information is obtained by analyzing signals from the sensors. Environmental sound, temperature, and humidity data are also collected in parallel. The input is raw data from the sensors, and the output is a rationally organized dataset.

[0089] Step 2:

[0090] The device sends data to the server. The device sends the collected data to the server using wireless communication technologies such as Wi-Fi or Bluetooth. The data sent includes all collected sensor information. The input is the dataset stored on the device, and the output is the data transferred to the server.

[0091] Step 3:

[0092] The server preprocesses the data. The server preprocesses the received data using NumPy or pandas, removing outliers and imputing missing values. Specific operations include data cleaning and standardization. The input is unprocessed raw data, and the output is a clean dataset.

[0093] Step 4:

[0094] The server analyzes the data using a generative AI model. The server inputs preprocessed data into the generative AI model and detects anomalies by determining differences from normal behavior patterns. This process uses machine learning frameworks such as TensorFlow and PyTorch. The input is a preprocessed dataset, and the output is the anomaly detection result.

[0095] Step 5:

[0096] The server generates notifications. When an anomaly is detected, the server uses natural language processing techniques to generate a notification that includes a detailed description of the situation and recommended countermeasures. Specifically, it uses models such as the GPT to generate the text. The input is the anomaly detection result, and the output is the generated notification message.

[0097] Step 6:

[0098] The server sends a notification to the user. The notification generated by the server is immediately sent to the user's smartphone or tablet via the app. The input is the generated notification message, and the output is the actual notification sent to the user's device.

[0099] Step 7:

[0100] The user checks the notification and takes appropriate action. Based on the received notification, the user will either check the site in the case of a fall or monitor the situation remotely. The input is the notification message sent from the server, and the output is the user's specific action.

[0101] (Application Example 1)

[0102] 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."

[0103] There is a need to efficiently monitor the safety of elderly people in their living environments and enable rapid response in the event of an anomaly. In particular, it is crucial to monitor the movements and physiological state of elderly people in real time, immediately notify relevant parties when an anomaly is detected, and provide specific countermeasures. However, conventional monitoring systems have issues with detection accuracy and real-time capabilities, making them insufficient for ensuring the safety of the elderly. Therefore, there is a need for monitoring systems that are more accurate and capable of immediate response.

[0104] 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.

[0105] In this invention, the server includes means for acquiring data on the subject's movements and physiological state using various sensors, means for executing an algorithm to analyze the acquired data and detect anomalies, and means for providing details of the anomaly and recommended countermeasures to the relevant parties in real time via a mobile device. This enhances the safety and security of the elderly and enables a rapid response to the situation.

[0106] "Diverse sensors" refers to a set of multiple types of sensors used to comprehensively acquire data on movement and physiological states.

[0107] "Movement and physiological state data" refers to measurement results related to the subject's movement and physical function, and mainly includes information such as acceleration, heart rate, and body temperature.

[0108] An "algorithm for detecting anomalies" is a computational method used to identify situations that deviate from normal behavioral patterns with high accuracy.

[0109] "Providing information via mobile devices" means transmitting and providing information to recipients through portable information terminals such as smartphones and tablets.

[0110] "Providing information to relevant parties in real time" means immediately notifying them the moment an anomaly is detected and quickly disseminating the information to the relevant people.

[0111] This invention is a monitoring system that uses various sensors to ensure the safety of the elderly. The following hardware and software are used to implement the invention.

[0112] The server includes a data acquisition module, a data processing module, and a notification management module. The data acquisition module monitors the movements and physiological state of elderly individuals in real time through various sensors, specifically wearable devices and environmental sensors, acquiring data such as GPS location, acceleration, heart rate, and body temperature. The acquired data is transferred to a mobile device using Bluetooth technology for further processing.

[0113] The data processing module analyzes incoming data from mobile devices and performs anomaly removal and filtering. This involves executing anomaly detection algorithms using data analysis tools such as Python's NumPy and Pandas, as well as machine learning libraries like TensorFlow and Scikit-learn. This allows for the identification of anomalies by comparing them to normal behavioral patterns.

[0114] The notification management module immediately generates notifications for family members and caregivers when an anomaly is detected. It uses Firebase Cloud Messaging (FCM) to send push notifications to smartphones, providing details of the anomaly and recommended actions through natural language processing.

[0115] As a concrete example of this system, if an elderly person makes unusual movements late at night, the system will detect these movements as abnormal and send a notification to their smartphone saying, "Your location has changed late at night. Please check if necessary," prompting prompt action to verify their location.

[0116] An example of a prompt message is: "A 70-year-old elderly person is wearing a wearable device. Develop an application that sends a notification when they move to an unusual location at night. Please suggest a suitable anomaly detection algorithm."

[0117] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0118] Step 1:

[0119] The device acquires data on the elderly person's movement and physiological state via wearable devices and environmental sensors. Specifically, it periodically measures heart rate, body temperature, acceleration, and GPS location information, and transmits this data to the mobile device using Bluetooth communication. The input is sensor data, and the output is a Bluetooth message.

[0120] Step 2:

[0121] The mobile device collects the received sensor data and sends it to the server. The server acquires this data and first performs data preprocessing. It cleans the data, such as removing noise and correcting missing values, to generate data that can be analyzed. The input here is sensor data from Bluetooth messages, and the output is clean data for analysis.

[0122] Step 3:

[0123] The server applies machine learning algorithms to preprocessed data to detect anomalies. Specifically, it runs an anomaly detection model using TensorFlow or Scikit-learn to identify deviations from normal behavior. This process continuously trains the model using historical data to improve detection accuracy. The input is the data for analysis, and the output is the result of anomaly detection.

[0124] Step 4:

[0125] When an anomaly is detected, the server uses natural language processing to generate a notification containing details of the anomaly and recommended actions. Firebase Cloud Messaging (FCM) is used to send a push notification to the mobile devices of family members or caregivers. This notification includes a specific alert message tailored to the anomaly. The input here is the anomaly detection result, and the output is the alert message sent to the user.

[0126] Step 5:

[0127] The user receives a notification on their mobile device and checks the alert content. Based on the displayed information, they decide whether to remotely check on the elderly person's situation or go to the site to take action if necessary. The input is the push notification, and the output is the user's action.

[0128] 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.

[0129] This invention combines a system that analyzes data acquired using various sensors to detect anomalies with an emotion engine that recognizes user emotions. This system consists of a data acquisition module, a data processing module, an emotion engine, and a notification management module, and each module works in cooperation with the others.

[0130] Program Implementation

[0131] Data Acquisition Module

[0132] The device acquires GPS location information, acceleration, audio, video, and emotional data derived from the user's facial expressions and voice via wearable devices and environmental sensors. The device then monitors this data in real time.

[0133] Data Processing Module

[0134] The server stores various data sent from the terminals in data storage and performs preprocessing. Here, abnormal data is sorted and prepared for analysis.

[0135] An anomaly detection algorithm is applied to the pre-processed data using a generative model to detect deviations from normal behavioral patterns.

[0136] Emotional Engine

[0137] The server analyzes the user's emotional data to recognize their current emotional state. This emotional information is used to customize anomaly detection algorithms and notification content.

[0138] Notification management module

[0139] Based on the anomalies detected by the server, natural language processing techniques are used to generate notifications that reflect emotional information. The notifications include a detailed description of the situation and corresponding recommended actions.

[0140] Users receive this notification, check the specific situation, and take prompt action based on easily understandable information that aligns with their emotional state.

[0141] Specific example

[0142] For example, suppose a device detects signs of a fall based on acceleration from an elderly person's wearable device, and at the same time collects emotional data from the user's voice indicating a lack of composure. The server analyzes this data and detects an anomaly, indicating a fall, and the emotion engine recognizes emotions such as anxiety and impatience. The server then generates a notification saying, "A fall has been detected. Please check on the person as soon as possible if you are nearby. The user may be experiencing significant anxiety, so please try to speak to them calmly," and sends it to the user.

[0143] Thus, by using an emotion engine, the present invention provides notifications that are more considerate of the user's feelings and promotes a quick and appropriate response. For the user, this system simultaneously provides a sense of being watched over and a sense of security, contributing to an improvement in their quality of life.

[0144] The following describes the processing flow.

[0145] Step 1:

[0146] The device uses wearable devices and surrounding sensors to acquire GPS location information, accelerometer data, voice, video, and emotional data such as facial expressions in real time. The acquired data is immediately prepared to be sent to a server.

[0147] Step 2:

[0148] The device transmits acquired data to the server using wireless communication technology. The data is sent in various formats, including location information, behavioral data, and sentiment data.

[0149] Step 3:

[0150] The server saves the received data to data storage and performs preprocessing such as correcting missing values ​​and removing outliers. This makes the data ready for analysis.

[0151] Step 4:

[0152] The server uses a generative model to analyze the pre-processed dataset and detect anomalies that exhibit behavioral patterns different from the norm. The generative model is learned from historical data, enabling highly accurate anomaly detection.

[0153] Step 5:

[0154] The server runs an emotion engine to analyze the user's emotional data and recognize their current emotional state. The recognition results are used to determine abnormal situations and customize notification content.

[0155] Step 6:

[0156] Based on the anomaly detected by the server and the user's emotional state, natural language processing technology is used to generate customized notifications. These notifications include details of the anomaly, a situational description tailored to the user's emotional state, and recommended actions.

[0157] Step 7:

[0158] The server generates customized notifications and sends them to users via methods such as push notifications, email, and SMS. These notifications are sent immediately to prompt user action.

[0159] Step 8:

[0160] The user receives a notification and reviews the details of the situation. They are supported in responding calmly to the situation based on emotionally sensitive content. The user then takes specific actions, such as going to the site, taking remote control, or making emergency contact as needed.

[0161] (Example 2)

[0162] 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".

[0163] Conventional anomaly detection systems have the drawback of failing to provide users with sufficient peace of mind because they do not take into account the emotional state of individuals and issue uniform notifications of anomalies. Furthermore, their anomaly detection accuracy is limited, leading to problems such as false positives and missed detections.

[0164] 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.

[0165] In this invention, the server includes means for acquiring individual information using various detection devices, means for executing a calculation method for organizing the acquired information and detecting anomalies, and means for determining the emotional state of the individual using emotion analysis means. This enables information processing that combines anomaly detection with emotional information, and allows for the generation of flexible notifications tailored to the user.

[0166] "Detection device" refers to various sensors and devices used to acquire information about a target, and this includes wearable devices and environmental sensors.

[0167] "Information" refers to data related to an individual, including GPS location information, body movements, audio, video, and emotional data.

[0168] "Calculation method" refers to algorithms and analytical techniques used to analyze acquired information and identify anomalies.

[0169] "Emotional analysis methods" refer to technologies that recognize emotions using data such as facial expressions and voice in order to determine an individual's emotional state.

[0170] "Notification" refers to a message or alert that is generated based on detected anomalies and emotional states and sent to an individual or relevant party.

[0171] This invention is a system that enables more personalized responses by detecting anomalies in various situations and generating notifications based on the user's emotional state. The system collects information using detection devices and performs information analysis and notification generation, primarily through a server.

[0172] Data collection and analysis

[0173] The device acquires individual information through wearable devices and environmental sensors. This information includes GPS location data, acceleration, voice, and video. Furthermore, it collects emotional data from the user's facial expressions and voice for emotion analysis.

[0174] The server stores the acquired information in data storage and uses calculation methods to detect anomalies. In this process, it utilizes a generative AI model to identify deviations from normal behavioral patterns, thereby achieving highly accurate anomaly detection.

[0175] Sentiment analysis and notification generation

[0176] The server uses emotion analysis tools to analyze the collected emotional data. This allows it to determine the user's current emotional state and incorporate that information into the anomaly detection algorithm.

[0177] Based on the emotional information associated with the anomaly, the server uses natural language processing techniques to generate personalized notifications. These notifications include details of the detected anomaly and recommended actions.

[0178] Specific example

[0179] For example, the device can monitor the movements of an elderly person and detect signs of a fall, while simultaneously detecting signs of anxiety in the user's voice. Based on this information, the server sends a specific notification to the user, such as, "A fall has been detected. Please check on the person as soon as possible if you are nearby. The user may be experiencing significant anxiety, so please speak to them calmly."

[0180] Example of a prompt

[0181] "Please generate a prompt that triggers an emotional analysis of anxiety-related behavior when a wearable device for the elderly detects a fall."

[0182] In this way, the invention incorporates emotional information to provide information that is adaptable to the individual.

[0183] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0184] Step 1:

[0185] The device uses wearable devices and environmental sensors to collect GPS location information, acceleration data, audio, and video. This data is acquired in real time and sent to the server as a data stream. The input data is raw sensor data, and the output is a data stream to the server. Specifically, the device receives signals from sensors, converts them into a specific format, and transmits them.

[0186] Step 2:

[0187] The server receives the collected data and stores it in data storage. Here, the data integrity is checked to ensure there is no invalid or missing data. The input is the raw data stream sent from the sensor, and a consistent dataset is ensured as the output. The operation includes checking the order of data packets and requesting retransmission of missing data.

[0188] Step 3:

[0189] The server preprocesses the stored data. It applies a denoising filter to remove unwanted information from acceleration and audio data. This process yields analysis-ready data as output from raw data as input. Specifically, the server uses the Fast Fourier Transform to remove noise components.

[0190] Step 4:

[0191] The server analyzes pre-processed data using a generation AI model and executes an anomaly detection algorithm. A machine learning model is used to detect deviations from normal behavioral patterns. The input is pre-processed data, and the output is the detection result of anomaly events. This step includes calculating an anomaly score and comparing it to a threshold.

[0192] Step 5:

[0193] The server uses emotion analysis tools to analyze the user's emotional data and determine their current emotional state. It receives emotion-related data as input and generates an emotional state label as output. Specifically, the server executes an algorithm that identifies the emotional state from voice intonation and facial expression analysis.

[0194] Step 6:

[0195] The server generates a notification using natural language processing technology based on the detected anomaly and the user's emotional state. This notification includes a description of the anomaly and recommended countermeasures. The input is anomaly and emotional data, and the output is a specific notification message. The generated notification is sent to the user in real time. Specifically, the system uses a text generation model to create a recommendation message and sends it to the user's device.

[0196] (Application Example 2)

[0197] 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".

[0198] Rapidly detecting accidents and health problems among the elderly and those receiving care, and prompting appropriate responses, is a crucial challenge in caregiving settings. Furthermore, beyond mere anomaly detection, there is a need for more accurate and reassuring responses that also consider the emotional state of the individual. However, conventional systems struggle to provide notifications that take emotional states into account, often resulting in purely mechanical responses. Therefore, there is a need for a system that incorporates emotional information to achieve rapid and appropriate anomaly responses.

[0199] 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.

[0200] In this invention, the server includes means for acquiring status information of a subject using various devices, means for analyzing the acquired status information to detect anomalies, means for analyzing the subject's emotions from the status information, and means for generating and transmitting notifications based on the anomaly and emotion information. This enables rapid and accurate response to anomalies that takes emotions into consideration.

[0201] A "device" is a piece of hardware or software designed to perform a specific function.

[0202] "Status information" refers to data that shows the physical and physiological changes and characteristics of the subject.

[0203] "Analysis" is the process of meticulously analyzing acquired data to identify anomalies and patterns.

[0204] An "anomaly" is a state or event that deviates from the normal pattern or exhibits different behavior.

[0205] "Emotions" refer to the internal psychological state of a person and are information obtained from their voice and facial expressions.

[0206] A "notification" is a message or alert generated to convey specific information or instructions.

[0207] The system implementing this invention mainly consists of a server, a terminal, and a user. The server receives data from terminals that collect various state information from wearable devices and fixed sensors. The terminals acquire physical state information and emotional data using accelerometers and voice input devices. This collected data is transmitted to the server in real time. The server operates on a cloud infrastructure such as Amazon Web Services and performs data analysis within the server.

[0208] The server first preprocesses the data using AWS Lambda. This preprocessing includes noise reduction and filtering of outliers. Then, a generative model built using AWS SageMaker is applied, where an anomaly detection algorithm is executed. If an anomaly is detected, sentiment data is also considered to identify the situation in more detail. Natural language processing tools such as Amazon Comprehend are used for sentiment analysis.

[0209] Based on the information obtained regarding abnormalities and emotions, the server sends notifications to devices via the Twilio API. For example, if an elderly person is identified as being at risk of falling, a detailed, emotion-sensitive instruction such as "Caution: Signs of a fall have been detected. Please speak to them calmly" is immediately sent to nearby care staff.

[0210] As a specific example, imagine an elderly person living in a nursing home who is going about their daily life without any problems. A wearable device detects a sudden increase in heart rate and movements that suggest they may fall. The server immediately analyzes this and, recognizing anxiety in the person's voice, generates a notification that includes "calm and reassuring words" to encourage the appropriate response.

[0211] Examples of prompts for the generative AI model include: "User sentiment analysis: Analyze the user's current emotions from the voice data," and "Anomaly event detection: Evaluate the likelihood of a fall from the acceleration data and identify behavior that differs from normal activity." This enables highly accurate decision-making based on emotions.

[0212] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0213] Step 1:

[0214] The terminal uses wearable devices and fixed environmental sensors to acquire acceleration data, voice data, and location information of the subject. The input is raw data from the sensors, and the output is data ready to be transmitted to the server in real time. This process involves the collection and format conversion of sensor data.

[0215] Step 2:

[0216] The server preprocesses the data sent from the terminal on AWS Lambda. The input is the raw data sent from the terminal, and the output is the denoised and outlier-filtered data. This process includes missing value imputation, data normalization, and removal of abnormal spikes.

[0217] Step 3:

[0218] The server applies a generative AI model to pre-processed data using AWS SageMaker. The input is filtered data, and the output is the result of anomaly detection. This process automatically identifies deviations from normal behavior and performs highly accurate anomaly detection.

[0219] Step 4:

[0220] The server uses AWS sentiment analysis services to analyze emotions from voice data. The input is the voice data from the previous step, and the output is a label of the detected emotional state. This enables detailed emotion recognition based on the subject's psychological state.

[0221] Step 5:

[0222] The server uses the Twilio API to generate and send notifications to the device based on the results of anomaly detection and sentiment analysis. The input is the anomaly detection results and sentiment recognition data, and the output is a customized notification message. This notification includes specific actions based on a prompt, specifically safety instructions for the individual and emotionally sensitive messages.

[0223] 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.

[0224] 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.

[0225] 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.

[0226] [Second Embodiment]

[0227] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0228] 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.

[0229] 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).

[0230] 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.

[0231] 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.

[0232] 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).

[0233] 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.

[0234] 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.

[0235] 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.

[0236] 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.

[0237] 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.

[0238] 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".

[0239] This invention is an advanced monitoring system that automatically performs data collection using various sensors, anomaly detection, and notification. This system mainly consists of a data collection module, a data processing module, and a notification management module, and each module works in coordination with the others.

[0240] Program Implementation

[0241] Data Acquisition Module

[0242] The device periodically acquires GPS location information, acceleration data, environmental audio, and video via wearable devices and environmental sensors.

[0243] The collected data is transmitted to the server using wireless communication technology.

[0244] Data Processing Module

[0245] The server first preprocesses the received data, removing outliers and correcting the data.

[0246] Next, a generative model is used to analyze the data and identify differences from normal behavioral patterns to detect anomalies.

[0247] The anomaly detection algorithm incorporates machine learning techniques, continuously learning from past data to improve detection accuracy.

[0248] Notification management module

[0249] The server immediately generates a notification to relevant parties if an anomaly is detected.

[0250] This notification uses natural language processing technology to provide users with a detailed description of the situation and recommended countermeasures.

[0251] Users receive notifications, check the specific situation through the application, and take prompt action as needed.

[0252] Specific example

[0253] For example, suppose a device acquires data from an elderly person's accelerometer indicating a sudden movement, i.e., a fall. The server analyzes this data and detects an anomaly as a deviation from the normal range of movement. It then generates a notification containing details of the anomaly and necessary countermeasures (e.g., "An elderly person may have fallen. Please check the scene."). The user receives this notification and takes action, such as going to the scene or checking remotely.

[0254] Thus, the present invention is a system that efficiently ensures the safety of an entire region by utilizing various sensor data to immediately detect abnormal conditions. For users, it enhances their sense of security in daily life by enabling quick and appropriate responses to the situation.

[0255] The following describes the processing flow.

[0256] Step 1:

[0257] The device periodically acquires data such as GPS location information, acceleration, ambient sound, and video through wearable devices and fixed sensors. This prepares the system for real-time monitoring of the subject's movements and environmental changes.

[0258] Step 2:

[0259] The terminal collects data and transmits it to the server using wireless communication technology. The data is transmitted in a structured format and is immediately ready for analysis.

[0260] Step 3:

[0261] The server stores the received data in data storage and performs preprocessing. This involves removing outliers and imputing missing data to build a reliable dataset.

[0262] Step 4:

[0263] The server applies an anomaly detection algorithm using a generative model to the pre-processed data. The model learns from past data and determines whether the current data deviates from normal behavioral patterns.

[0264] Step 5:

[0265] The server immediately generates an alert if an anomaly is detected. This alert includes a specific description of the anomaly, generated using natural language processing technology, and recommended countermeasures.

[0266] Step 6:

[0267] The server generates alerts and notifies parents and local community watch representatives. Notifications are sent using methods such as push notifications, email, and SMS.

[0268] Step 7:

[0269] Users receive notifications and can use their smartphones or computers to view detailed information. These notifications include instructions for situations requiring immediate action, supporting quick decision-making.

[0270] Step 8:

[0271] The user takes appropriate action based on the notification. For example, they may go to the site, remotely check the situation, or contact emergency services if necessary.

[0272] (Example 1)

[0273] 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."

[0274] In modern society, with the increasing diversity of living environments, there is a growing need for monitoring systems that can quickly and accurately detect anomalies and prompt appropriate responses. Conventional systems have struggled to improve the accuracy of anomaly detection and to provide timely, situation-appropriate countermeasures. Therefore, the challenge to be addressed is to provide a monitoring system that combines efficient and reliable anomaly detection and notification functions.

[0275] 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.

[0276] In this invention, the server includes means for acquiring information using various detection devices, means for transmitting the acquired information by wireless communication technology, and means for analyzing the information using a generation model to detect anomalies. As a result, information can be efficiently collected, and prompt responses can be made in case of anomalies based on the analysis results.

[0277] The "detection device" is a general term for devices and apparatuses that can acquire information from a target, and it is used in various environments.

[0278] "Information" is a set of data acquired by a detection device and includes location information, operation data, environmental conditions, etc.

[0279] "Wireless communication technology" refers to all technologies used to transmit and receive information by means other than wired methods.

[0280] The "generation model" is a computational model used to learn past data and analyze and predict new data.

[0281] "Anomaly" refers to data or situations that deviate from normal operations or states and are detected based on specific criteria.

[0282] "Notification" is a message generated when the system detects an anomaly and provides warnings or information to the user.

[0283] "Natural language processing technology" is a technology for a computer to understand, generate, and process human natural language.

[0284] "Countermeasures" are guidelines indicating specific actions or procedures that a user should take for detected anomalies.

[0285] The embodiments for implementing this invention include the following specific configurations and operations.

[0286] This system provides an advanced monitoring function that acquires data in real time using various detection devices, detects anomalies based on the data, and generates notifications. The terminal uses wearable devices and environmental sensors to regularly acquire various information such as heart rate, acceleration data, location information, environmental sounds, temperature, and humidity. In this process, general wearable devices and IoT sensors are often utilized.

[0287] The data collected by the terminal is transmitted to the server via wireless communication technologies such as Wi-Fi and Bluetooth. The server preprocesses the received data using Python libraries (e.g., numpy and pandas) and performs corrections for outliers and missing values. Then, a generation model is used for data analysis. TensorFlow or PyTorch can be utilized for this generation model.

[0288] The server performs data analysis using the generation model, identifies differences from normal behavior patterns through machine learning techniques, and detects anomalies. When an anomaly is detected, natural language processing techniques (e.g., OpenAI's GPT model) are utilized to generate a notification that includes a specific situation description and recommended countermeasures. This notification is immediately sent to the user's smartphone or tablet via an app.

[0289] The user is required to quickly take appropriate actions according to the situation based on the received notification. This system is particularly useful in scenarios such as health monitoring of the elderly and automated safety management. For example, when the terminal acquires data indicating the possibility of an elderly person falling, the server determines it as an anomaly and generates a notification such as "There is a possibility that the elderly person has fallen. Please check the scene." and sends it to the user.

[0290] By leveraging the generative AI model, the system can automatically generate detailed explanations and instructions based on the prompt text. Examples of prompt texts can include "Please generate a notification message to prevent falling accidents within the home."

[0291] This configuration enhances the safety of the community and improves people's sense of security in their daily lives.

[0292] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0293] Step 1:

[0294] The device acquires data. Specifically, the device collects heart rate, acceleration data, location information, etc., using wearable devices and environmental sensors. This information is obtained by analyzing signals from the sensors. Environmental sound, temperature, and humidity data are also collected in parallel. The input is raw data from the sensors, and the output is a rationally organized dataset.

[0295] Step 2:

[0296] The device sends data to the server. The device sends the collected data to the server using wireless communication technologies such as Wi-Fi or Bluetooth. The data sent includes all collected sensor information. The input is the dataset stored on the device, and the output is the data transferred to the server.

[0297] Step 3:

[0298] The server preprocesses the data. The server preprocesses the received data using NumPy or pandas, removing outliers and imputing missing values. Specific operations include data cleaning and standardization. The input is unprocessed raw data, and the output is a clean dataset.

[0299] Step 4:

[0300] The server analyzes data using a generative AI model. The server inputs the preprocessed data into the generative AI model, determines the differences from normal behavior patterns, and detects anomalies. In this process, machine learning frameworks such as TensorFlow and PyTorch are used. The input is the preprocessed dataset, and the output is the anomaly detection result.

[0301] Step 5:

[0302] The server generates a notification. When an anomaly is detected, the server uses natural language processing technology to generate a notification that includes a specific situation description and recommended countermeasures. Specifically, a model such as GPT is used to generate the text. The input is the anomaly detection result, and the output is the generated notification message.

[0303] Step 6:

[0304] The server sends the notification to the user. The notification generated by the server is immediately sent to the user's smartphone or tablet via an app. The input is the generated notification message, and the output is the actual notification sent to the user device.

[0305] Step 7:

[0306] The user checks the notification and implements countermeasures. Based on the received notification, if it is a case of falling, the user takes actions such as checking the scene or monitoring the situation remotely. The input is the notification message sent from the server, and the output is the user's specific response actions.

[0307] (Application Example 1)

[0308] 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".

[0309] There is a need to efficiently monitor the safety of elderly people in their living environments and enable rapid response in the event of an anomaly. In particular, it is crucial to monitor the movements and physiological state of elderly people in real time, immediately notify relevant parties when an anomaly is detected, and provide specific countermeasures. However, conventional monitoring systems have issues with detection accuracy and real-time capabilities, making them insufficient for ensuring the safety of the elderly. Therefore, there is a need for monitoring systems that are more accurate and capable of immediate response.

[0310] 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.

[0311] In this invention, the server includes means for acquiring data on the subject's movements and physiological state using various sensors, means for executing an algorithm to analyze the acquired data and detect anomalies, and means for providing details of the anomaly and recommended countermeasures to the relevant parties in real time via a mobile device. This enhances the safety and security of the elderly and enables a rapid response to the situation.

[0312] "Diverse sensors" refers to a set of multiple types of sensors used to comprehensively acquire data on movement and physiological states.

[0313] "Movement and physiological state data" refers to measurement results related to the subject's movement and physical function, and mainly includes information such as acceleration, heart rate, and body temperature.

[0314] An "algorithm for detecting anomalies" is a computational method used to identify situations that deviate from normal behavioral patterns with high accuracy.

[0315] "Providing information via mobile devices" means transmitting and providing information to recipients through portable information terminals such as smartphones and tablets.

[0316] "Providing information to relevant parties in real time" means immediately notifying them the moment an anomaly is detected and quickly disseminating the information to the relevant people.

[0317] This invention is a monitoring system that uses various sensors to ensure the safety of the elderly. The following hardware and software are used to implement the invention.

[0318] The server includes a data acquisition module, a data processing module, and a notification management module. The data acquisition module monitors the movements and physiological state of elderly individuals in real time through various sensors, specifically wearable devices and environmental sensors, acquiring data such as GPS location, acceleration, heart rate, and body temperature. The acquired data is transferred to a mobile device using Bluetooth technology for further processing.

[0319] The data processing module analyzes incoming data from mobile devices and performs anomaly removal and filtering. This involves executing anomaly detection algorithms using data analysis tools such as Python's NumPy and Pandas, as well as machine learning libraries like TensorFlow and Scikit-learn. This allows for the identification of anomalies by comparing them to normal behavioral patterns.

[0320] The notification management module immediately generates notifications for family members and caregivers when an anomaly is detected. It uses Firebase Cloud Messaging (FCM) to send push notifications to smartphones, providing details of the anomaly and recommended actions through natural language processing.

[0321] As a concrete example of this system, if an elderly person makes unusual movements late at night, the system will detect these movements as abnormal and send a notification to their smartphone saying, "Your location has changed late at night. Please check if necessary," prompting prompt action to verify their location.

[0322] An example of a prompt message is: "A 70-year-old elderly person is wearing a wearable device. Develop an application that sends a notification when they move to an unusual location at night. Please suggest a suitable anomaly detection algorithm."

[0323] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0324] Step 1:

[0325] The device acquires data on the elderly person's movement and physiological state via wearable devices and environmental sensors. Specifically, it periodically measures heart rate, body temperature, acceleration, and GPS location information, and transmits this data to the mobile device using Bluetooth communication. The input is sensor data, and the output is a Bluetooth message.

[0326] Step 2:

[0327] The mobile device collects the received sensor data and sends it to the server. The server acquires this data and first performs data preprocessing. It cleans the data, such as removing noise and correcting missing values, to generate data that can be analyzed. The input here is sensor data from Bluetooth messages, and the output is clean data for analysis.

[0328] Step 3:

[0329] The server applies machine learning algorithms to preprocessed data to detect anomalies. Specifically, it runs an anomaly detection model using TensorFlow or Scikit-learn to identify deviations from normal behavior. This process continuously trains the model using historical data to improve detection accuracy. The input is the data for analysis, and the output is the result of anomaly detection.

[0330] Step 4:

[0331] When an anomaly is detected, the server uses natural language processing to generate a notification containing details of the anomaly and recommended actions. Firebase Cloud Messaging (FCM) is used to send a push notification to the mobile devices of family members or caregivers. This notification includes a specific alert message tailored to the anomaly. The input here is the anomaly detection result, and the output is the alert message sent to the user.

[0332] Step 5:

[0333] The user receives a notification on their mobile device and checks the alert content. Based on the displayed information, they decide whether to remotely check on the elderly person's situation or go to the site to take action if necessary. The input is the push notification, and the output is the user's action.

[0334] 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.

[0335] This invention combines a system that analyzes data acquired using various sensors to detect anomalies with an emotion engine that recognizes user emotions. This system consists of a data acquisition module, a data processing module, an emotion engine, and a notification management module, and each module works in cooperation with the others.

[0336] Program Implementation

[0337] Data Acquisition Module

[0338] The device acquires GPS location information, acceleration, audio, video, and emotional data derived from the user's facial expressions and voice via wearable devices and environmental sensors. The device then monitors this data in real time.

[0339] Data Processing Module

[0340] The server stores various data sent from the terminals in data storage and performs preprocessing. Here, abnormal data is sorted and prepared for analysis.

[0341] An anomaly detection algorithm is applied to the pre-processed data using a generative model to detect deviations from normal behavioral patterns.

[0342] Emotional Engine

[0343] The server analyzes the user's emotional data to recognize their current emotional state. This emotional information is used to customize anomaly detection algorithms and notification content.

[0344] Notification management module

[0345] Based on the anomalies detected by the server, natural language processing techniques are used to generate notifications that reflect emotional information. The notifications include a detailed description of the situation and corresponding recommended actions.

[0346] Users receive this notification, check the specific situation, and take prompt action based on easily understandable information that aligns with their emotional state.

[0347] Specific example

[0348] For example, suppose a device detects signs of a fall based on acceleration from an elderly person's wearable device, and at the same time collects emotional data from the user's voice indicating a lack of composure. The server analyzes this data and detects an anomaly, indicating a fall, and the emotion engine recognizes emotions such as anxiety and impatience. The server then generates a notification saying, "A fall has been detected. Please check on the person as soon as possible if you are nearby. The user may be experiencing significant anxiety, so please try to speak to them calmly," and sends it to the user.

[0349] Thus, by using an emotion engine, the present invention provides notifications that are more considerate of the user's feelings and promotes a quick and appropriate response. For the user, this system simultaneously provides a sense of being watched over and a sense of security, contributing to an improvement in their quality of life.

[0350] The following describes the processing flow.

[0351] Step 1:

[0352] The device uses wearable devices and surrounding sensors to acquire GPS location information, accelerometer data, voice, video, and emotional data such as facial expressions in real time. The acquired data is immediately prepared to be sent to a server.

[0353] Step 2:

[0354] The device transmits acquired data to the server using wireless communication technology. The data is sent in various formats, including location information, behavioral data, and sentiment data.

[0355] Step 3:

[0356] The server saves the received data to data storage and performs preprocessing such as correcting missing values ​​and removing outliers. This makes the data ready for analysis.

[0357] Step 4:

[0358] The server uses a generative model to analyze the pre-processed dataset and detect anomalies that exhibit behavioral patterns different from the norm. The generative model is learned from historical data, enabling highly accurate anomaly detection.

[0359] Step 5:

[0360] The server runs an emotion engine to analyze the user's emotional data and recognize their current emotional state. The recognition results are used to determine abnormal situations and customize notification content.

[0361] Step 6:

[0362] Based on the anomaly detected by the server and the user's emotional state, natural language processing technology is used to generate customized notifications. These notifications include details of the anomaly, a situational description tailored to the user's emotional state, and recommended actions.

[0363] Step 7:

[0364] The server generates customized notifications and sends them to users via methods such as push notifications, email, and SMS. These notifications are sent immediately to prompt user action.

[0365] Step 8:

[0366] The user receives a notification and reviews the details of the situation. They are supported in responding calmly to the situation based on emotionally sensitive content. The user then takes specific actions, such as going to the site, taking remote control, or making emergency contact as needed.

[0367] (Example 2)

[0368] 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".

[0369] Conventional anomaly detection systems have the drawback of failing to provide users with sufficient peace of mind because they do not take into account the emotional state of individuals and issue uniform notifications of anomalies. Furthermore, their anomaly detection accuracy is limited, leading to problems such as false positives and missed detections.

[0370] 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.

[0371] In this invention, the server includes means for acquiring individual information using various detection devices, means for executing a calculation method for organizing the acquired information and detecting anomalies, and means for determining the emotional state of the individual using emotion analysis means. This enables information processing that combines anomaly detection with emotional information, and allows for the generation of flexible notifications tailored to the user.

[0372] "Detection device" refers to various sensors and devices used to acquire information about a target, and this includes wearable devices and environmental sensors.

[0373] "Information" refers to data related to an individual, including GPS location information, body movements, audio, video, and emotional data.

[0374] "Calculation method" refers to algorithms and analytical techniques used to analyze acquired information and identify anomalies.

[0375] "Emotional analysis methods" refer to technologies that recognize emotions using data such as facial expressions and voice in order to determine an individual's emotional state.

[0376] "Notification" refers to a message or alert that is generated based on detected anomalies and emotional states and sent to an individual or relevant party.

[0377] This invention is a system that enables more personalized responses by detecting anomalies in various situations and generating notifications based on the user's emotional state. The system collects information using detection devices and performs information analysis and notification generation, primarily through a server.

[0378] Data collection and analysis

[0379] The device acquires individual information through wearable devices and environmental sensors. This information includes GPS location data, acceleration, voice, and video. Furthermore, it collects emotional data from the user's facial expressions and voice for emotion analysis.

[0380] The server stores the acquired information in data storage and uses calculation methods to detect anomalies. In this process, it utilizes a generative AI model to identify deviations from normal behavioral patterns, thereby achieving highly accurate anomaly detection.

[0381] Sentiment analysis and notification generation

[0382] The server uses emotion analysis tools to analyze the collected emotional data. This allows it to determine the user's current emotional state and incorporate that information into the anomaly detection algorithm.

[0383] Based on the emotional information associated with the anomaly, the server uses natural language processing techniques to generate personalized notifications. These notifications include details of the detected anomaly and recommended actions.

[0384] Specific example

[0385] For example, the device can monitor the movements of an elderly person and detect signs of a fall, while simultaneously detecting signs of anxiety in the user's voice. Based on this information, the server sends a specific notification to the user, such as, "A fall has been detected. Please check on the person as soon as possible if you are nearby. The user may be experiencing significant anxiety, so please speak to them calmly."

[0386] Example of a prompt

[0387] "Please generate a prompt that triggers an emotional analysis of anxiety-related behavior when a wearable device for the elderly detects a fall."

[0388] In this way, the invention incorporates emotional information to provide information that is adaptable to the individual.

[0389] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0390] Step 1:

[0391] The device uses wearable devices and environmental sensors to collect GPS location information, acceleration data, audio, and video. This data is acquired in real time and sent to the server as a data stream. The input data is raw sensor data, and the output is a data stream to the server. Specifically, the device receives signals from sensors, converts them into a specific format, and transmits them.

[0392] Step 2:

[0393] The server receives the collected data and stores it in data storage. Here, the data integrity is checked to ensure there is no invalid or missing data. The input is the raw data stream sent from the sensor, and a consistent dataset is ensured as the output. The operation includes checking the order of data packets and requesting retransmission of missing data.

[0394] Step 3:

[0395] The server preprocesses the stored data. It applies a denoising filter to remove unwanted information from acceleration and audio data. This process yields analysis-ready data as output from raw data as input. Specifically, the server uses the Fast Fourier Transform to remove noise components.

[0396] Step 4:

[0397] The server analyzes pre-processed data using a generation AI model and executes an anomaly detection algorithm. A machine learning model is used to detect deviations from normal behavioral patterns. The input is pre-processed data, and the output is the detection result of anomaly events. This step includes calculating an anomaly score and comparing it to a threshold.

[0398] Step 5:

[0399] The server uses emotion analysis tools to analyze the user's emotional data and determine their current emotional state. It receives emotion-related data as input and generates an emotional state label as output. Specifically, the server executes an algorithm that identifies the emotional state from voice intonation and facial expression analysis.

[0400] Step 6:

[0401] The server generates a notification using natural language processing technology based on the detected anomaly and the user's emotional state. This notification includes a description of the anomaly and recommended countermeasures. The input is anomaly and emotional data, and the output is a specific notification message. The generated notification is sent to the user in real time. Specifically, the system uses a text generation model to create a recommendation message and sends it to the user's device.

[0402] (Application Example 2)

[0403] 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."

[0404] Rapidly detecting accidents and health problems among the elderly and those receiving care, and prompting appropriate responses, is a crucial challenge in caregiving settings. Furthermore, beyond mere anomaly detection, there is a need for more accurate and reassuring responses that also consider the emotional state of the individual. However, conventional systems struggle to provide notifications that take emotional states into account, often resulting in purely mechanical responses. Therefore, there is a need for a system that incorporates emotional information to achieve rapid and appropriate anomaly responses.

[0405] 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.

[0406] In this invention, the server includes means for acquiring status information of a subject using various devices, means for analyzing the acquired status information to detect anomalies, means for analyzing the subject's emotions from the status information, and means for generating and transmitting notifications based on the anomaly and emotion information. This enables rapid and accurate response to anomalies that takes emotions into consideration.

[0407] A "device" is a piece of hardware or software designed to perform a specific function.

[0408] "Status information" refers to data that shows the physical and physiological changes and characteristics of the subject.

[0409] "Analysis" is the process of meticulously analyzing acquired data to identify anomalies and patterns.

[0410] An "anomaly" is a state or event that deviates from the normal pattern or exhibits different behavior.

[0411] "Emotions" refer to the internal psychological state of a person and are information obtained from their voice and facial expressions.

[0412] A "notification" is a message or alert generated to convey specific information or instructions.

[0413] The system implementing this invention mainly consists of a server, a terminal, and a user. The server receives data from terminals that collect various state information from wearable devices and fixed sensors. The terminals acquire physical state information and emotional data using accelerometers and voice input devices. This collected data is transmitted to the server in real time. The server operates on a cloud infrastructure such as Amazon Web Services and performs data analysis within the server.

[0414] The server first preprocesses the data using AWS Lambda. This preprocessing includes noise reduction and filtering of outliers. Then, a generative model built using AWS SageMaker is applied, and an anomaly detection algorithm is executed. If an anomaly is detected, sentiment data is also considered to identify the situation in more detail. Natural language processing tools such as Amazon Comprehend are used for sentiment analysis.

[0415] Based on the information obtained regarding abnormalities and emotions, the server sends notifications to devices via the Twilio API. For example, if an elderly person is identified as being at risk of falling, a detailed, emotion-sensitive instruction such as "Caution: Signs of a fall have been detected. Please speak to them calmly" is immediately sent to nearby care staff.

[0416] As a specific example, imagine an elderly person living in a nursing home who is going about their daily life without any problems. A wearable device detects a sudden increase in heart rate and movements that suggest they may fall. The server immediately analyzes this and, recognizing anxiety in the person's voice, generates a notification that includes "calm and reassuring words" to encourage the appropriate response.

[0417] Examples of prompts for the generative AI model include: "User sentiment analysis: Analyze the user's current emotions from the voice data," and "Anomaly event detection: Evaluate the likelihood of a fall from the acceleration data and identify behavior that differs from normal activity." This enables highly accurate decision-making based on emotions.

[0418] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0419] Step 1:

[0420] The terminal uses wearable devices and fixed environmental sensors to acquire acceleration data, voice data, and location information of the subject. The input is raw data from the sensors, and the output is data ready to be transmitted to the server in real time. This process involves the collection and format conversion of sensor data.

[0421] Step 2:

[0422] The server preprocesses the data sent from the terminal on AWS Lambda. The input is the raw data sent from the terminal, and the output is the denoised and outlier-filtered data. This process includes missing value imputation, data normalization, and removal of abnormal spikes.

[0423] Step 3:

[0424] The server applies a generative AI model to pre-processed data using AWS SageMaker. The input is filtered data, and the output is the result of anomaly detection. This process automatically identifies deviations from normal behavior and performs highly accurate anomaly detection.

[0425] Step 4:

[0426] The server uses AWS sentiment analysis services to analyze emotions from voice data. The input is the voice data from the previous step, and the output is a label of the detected emotional state. This enables detailed emotion recognition based on the subject's psychological state.

[0427] Step 5:

[0428] The server uses the Twilio API to generate and send notifications to the device based on the results of anomaly detection and sentiment analysis. The input is the anomaly detection results and sentiment recognition data, and the output is a customized notification message. This notification includes specific actions based on a prompt, specifically safety instructions for the individual and emotionally sensitive messages.

[0429] 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.

[0430] 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.

[0431] 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.

[0432] [Third Embodiment]

[0433] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0434] 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.

[0435] 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).

[0436] 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.

[0437] 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.

[0438] 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).

[0439] 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.

[0440] 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.

[0441] 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.

[0442] 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.

[0443] 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.

[0444] 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".

[0445] This invention is an advanced monitoring system that automatically performs data collection using various sensors, anomaly detection, and notification. This system mainly consists of a data collection module, a data processing module, and a notification management module, and each module works in coordination with the others.

[0446] Program Implementation

[0447] Data Acquisition Module

[0448] The device periodically acquires GPS location information, acceleration data, environmental audio, and video via wearable devices and environmental sensors.

[0449] The collected data is transmitted to the server using wireless communication technology.

[0450] Data Processing Module

[0451] The server first preprocesses the received data, removing outliers and correcting the data.

[0452] Next, a generative model is used to analyze the data and identify differences from normal behavioral patterns to detect anomalies.

[0453] The anomaly detection algorithm incorporates machine learning techniques, continuously learning from past data to improve detection accuracy.

[0454] Notification management module

[0455] The server immediately generates a notification to relevant parties if an anomaly is detected.

[0456] This notification uses natural language processing technology to provide users with a detailed description of the situation and recommended countermeasures.

[0457] Users receive notifications, check the specific situation through the application, and take prompt action as needed.

[0458] Specific example

[0459] For example, suppose a device acquires data from an elderly person's accelerometer indicating a sudden movement, i.e., a fall. The server analyzes this data and detects an anomaly as a deviation from the normal range of movement. It then generates a notification containing details of the anomaly and necessary countermeasures (e.g., "An elderly person may have fallen. Please check the scene."). The user receives this notification and takes action, such as going to the scene or checking remotely.

[0460] Thus, the present invention is a system that efficiently ensures the safety of an entire region by utilizing various sensor data to immediately detect abnormal conditions. For users, it enhances their sense of security in daily life by enabling quick and appropriate responses to the situation.

[0461] The following describes the processing flow.

[0462] Step 1:

[0463] The device periodically acquires data such as GPS location information, acceleration, ambient sound, and video through wearable devices and fixed sensors. This prepares the system for real-time monitoring of the subject's movements and environmental changes.

[0464] Step 2:

[0465] The terminal collects data and transmits it to the server using wireless communication technology. The data is transmitted in a structured format and is immediately ready for analysis.

[0466] Step 3:

[0467] The server stores the received data in data storage and performs preprocessing. This involves removing outliers and imputing missing data to build a reliable dataset.

[0468] Step 4:

[0469] The server applies an anomaly detection algorithm using a generative model to the pre-processed data. The model learns from past data and determines whether the current data deviates from normal behavioral patterns.

[0470] Step 5:

[0471] The server immediately generates an alert if an anomaly is detected. This alert includes a specific description of the anomaly, generated using natural language processing technology, and recommended countermeasures.

[0472] Step 6:

[0473] The server generates alerts and notifies parents and local community watch representatives. Notifications are sent using methods such as push notifications, email, and SMS.

[0474] Step 7:

[0475] Users receive notifications and can use their smartphones or computers to view detailed information. These notifications include instructions for situations requiring immediate action, supporting quick decision-making.

[0476] Step 8:

[0477] The user takes appropriate action based on the notification. For example, they may go to the site, remotely check the situation, or contact emergency services if necessary.

[0478] (Example 1)

[0479] 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."

[0480] In modern society, with the increasing diversity of living environments, there is a growing need for monitoring systems that can quickly and accurately detect anomalies and prompt appropriate responses. Conventional systems have struggled to improve the accuracy of anomaly detection and to provide timely, situation-appropriate countermeasures. Therefore, the challenge to be addressed is to provide a monitoring system that combines efficient and reliable anomaly detection and notification functions.

[0481] 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.

[0482] In this invention, the server includes means for acquiring information using various detection devices, means for transmitting the acquired information using wireless communication technology, and means for analyzing the information using a generative model and detecting anomalies. This enables efficient information collection and rapid response to anomalies based on the results of the analysis.

[0483] A "detection device" is a general term for equipment or devices that can acquire information from an object, and these are used in a variety of environments.

[0484] "Information" refers to a collection of data acquired by a detection device, including location information, operational data, and environmental conditions.

[0485] "Wireless communication technology" refers to all technologies used to transmit and receive information by means other than wired connections.

[0486] A "generative model" is a computational model used to analyze and predict new data by learning from past data.

[0487] An "anomaly" refers to data or situations that deviate from normal operation or state, and is detected based on specific criteria.

[0488] A "notification" is a message generated when the system detects an anomaly, providing warnings or information to the user.

[0489] "Natural language processing technology" refers to the technology that enables computers to understand, generate, and process human natural language.

[0490] A "countermeasure" is a guideline that outlines the specific actions and procedures that users should take in response to detected anomalies.

[0491] Embodiments of this invention include the following specific configurations and operations.

[0492] This system provides advanced monitoring capabilities by acquiring data in real time using various detection devices, detecting anomalies based on that data, and generating notifications. The terminal periodically acquires various information such as heart rate, acceleration data, location information, ambient sounds, temperature, and humidity using wearable devices and environmental sensors. This process often utilizes common wearable devices and IoT sensors.

[0493] The data collected by the device is transmitted to the server via wireless communication technologies such as Wi-Fi or Bluetooth. The server preprocesses the received data using Python libraries (e.g., numpy and pandas) to correct for outliers and missing values. Then, a generative model is used for data analysis. TensorFlow or PyTorch can be used for this generative model.

[0494] The server performs data analysis using generative models, identifies differences from normal behavior patterns using machine learning techniques, and detects anomalies. If an anomaly is detected, it uses natural language processing techniques (e.g., OpenAI's GPT model) to generate a notification that includes a detailed description of the situation and recommended countermeasures. This notification is immediately sent to the user's smartphone or tablet via the app.

[0495] Users are expected to take the most appropriate action quickly based on the notifications they receive. This system is particularly useful in situations such as monitoring the health of the elderly and automated safety management. For example, if a terminal acquires data indicating a possible fall by an elderly person, the server will recognize this as an anomaly and generate a notification such as, "An elderly person may have fallen. Please check the site," and send it to the user.

[0496] By utilizing a generative AI model, the system can automatically generate detailed explanations and instructions based on prompts. An example of a prompt might be, "Generate a notification message to prevent falls in the home."

[0497] This configuration enhances the safety of the community and improves people's sense of security in their daily lives.

[0498] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0499] Step 1:

[0500] The device acquires data. Specifically, the device collects heart rate, acceleration data, location information, etc., using wearable devices and environmental sensors. This information is obtained by analyzing signals from the sensors. Environmental sound, temperature, and humidity data are also collected in parallel. The input is raw data from the sensors, and the output is a rationally organized dataset.

[0501] Step 2:

[0502] The device sends data to the server. The device sends the collected data to the server using wireless communication technologies such as Wi-Fi or Bluetooth. The data sent includes all collected sensor information. The input is the dataset stored on the device, and the output is the data transferred to the server.

[0503] Step 3:

[0504] The server preprocesses the data. The server preprocesses the received data using NumPy or pandas, removing outliers and imputing missing values. Specific operations include data cleaning and standardization. The input is unprocessed raw data, and the output is a clean dataset.

[0505] Step 4:

[0506] The server analyzes the data using a generative AI model. The server inputs preprocessed data into the generative AI model and detects anomalies by determining differences from normal behavior patterns. This process uses machine learning frameworks such as TensorFlow and PyTorch. The input is a preprocessed dataset, and the output is the anomaly detection result.

[0507] Step 5:

[0508] The server generates notifications. When an anomaly is detected, the server uses natural language processing techniques to generate a notification that includes a detailed description of the situation and recommended countermeasures. Specifically, it uses models such as the GPT to generate the text. The input is the anomaly detection result, and the output is the generated notification message.

[0509] Step 6:

[0510] The server sends a notification to the user. The notification generated by the server is immediately sent to the user's smartphone or tablet via the app. The input is the generated notification message, and the output is the actual notification sent to the user's device.

[0511] Step 7:

[0512] The user checks the notification and takes appropriate action. Based on the received notification, the user will either check the site in the case of a fall or monitor the situation remotely. The input is the notification message sent from the server, and the output is the user's specific action.

[0513] (Application Example 1)

[0514] 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."

[0515] There is a need to efficiently monitor the safety of elderly people in their living environments and enable rapid response in the event of an anomaly. In particular, it is crucial to monitor the movements and physiological state of elderly people in real time, immediately notify relevant parties when an anomaly is detected, and provide specific countermeasures. However, conventional monitoring systems have issues with detection accuracy and real-time capabilities, making them insufficient for ensuring the safety of the elderly. Therefore, there is a need for monitoring systems that are more accurate and capable of immediate response.

[0516] 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.

[0517] In this invention, the server includes means for acquiring data on the subject's movements and physiological state using various sensors, means for executing an algorithm to analyze the acquired data and detect anomalies, and means for providing details of the anomaly and recommended countermeasures to the relevant parties in real time via a mobile device. This enhances the safety and security of the elderly and enables a rapid response to the situation.

[0518] "Diverse sensors" refers to a set of multiple types of sensors used to comprehensively acquire data on movement and physiological states.

[0519] "Movement and physiological state data" refers to measurement results related to the subject's movement and physical function, and mainly includes information such as acceleration, heart rate, and body temperature.

[0520] An "algorithm for detecting anomalies" is a computational method used to identify situations that deviate from normal behavioral patterns with high accuracy.

[0521] "Providing information via mobile devices" means transmitting and providing information to recipients through portable information terminals such as smartphones and tablets.

[0522] "Providing information to relevant parties in real time" means immediately notifying them the moment an anomaly is detected and quickly disseminating the information to the relevant people.

[0523] This invention is a monitoring system that uses various sensors to ensure the safety of the elderly. The following hardware and software are used to implement the invention.

[0524] The server includes a data acquisition module, a data processing module, and a notification management module. The data acquisition module monitors the movements and physiological state of elderly individuals in real time through various sensors, specifically wearable devices and environmental sensors, acquiring data such as GPS location, acceleration, heart rate, and body temperature. The acquired data is transferred to a mobile device using Bluetooth technology for further processing.

[0525] The data processing module analyzes incoming data from mobile devices and performs anomaly removal and filtering. This involves executing anomaly detection algorithms using data analysis tools such as Python's NumPy and Pandas, as well as machine learning libraries like TensorFlow and Scikit-learn. This allows for the identification of anomalies by comparing them to normal behavioral patterns.

[0526] The notification management module immediately generates notifications for family members and caregivers when an anomaly is detected. It uses Firebase Cloud Messaging (FCM) to send push notifications to smartphones, providing details of the anomaly and recommended actions through natural language processing.

[0527] As a concrete example of this system, if an elderly person makes unusual movements late at night, the system will detect these movements as abnormal and send a notification to their smartphone saying, "Your location has changed late at night. Please check if necessary," prompting prompt action to verify their location.

[0528] An example of a prompt message is: "A 70-year-old elderly person is wearing a wearable device. Develop an application that sends a notification when they move to an unusual location at night. Please suggest a suitable anomaly detection algorithm."

[0529] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0530] Step 1:

[0531] The device acquires data on the elderly person's movement and physiological state via wearable devices and environmental sensors. Specifically, it periodically measures heart rate, body temperature, acceleration, and GPS location information, and transmits this data to the mobile device using Bluetooth communication. The input is sensor data, and the output is a Bluetooth message.

[0532] Step 2:

[0533] The mobile device collects the received sensor data and sends it to the server. The server acquires this data and first performs data preprocessing. It cleans the data, such as removing noise and correcting missing values, to generate data that can be analyzed. The input here is sensor data from Bluetooth messages, and the output is clean data for analysis.

[0534] Step 3:

[0535] The server applies machine learning algorithms to preprocessed data to detect anomalies. Specifically, it runs an anomaly detection model using TensorFlow or Scikit-learn to identify deviations from normal behavior. This process continuously trains the model using historical data to improve detection accuracy. The input is the data for analysis, and the output is the result of anomaly detection.

[0536] Step 4:

[0537] When an anomaly is detected, the server uses natural language processing to generate a notification containing details of the anomaly and recommended actions. Firebase Cloud Messaging (FCM) is used to send a push notification to the mobile devices of family members or caregivers. This notification includes a specific alert message tailored to the anomaly. The input here is the anomaly detection result, and the output is the alert message sent to the user.

[0538] Step 5:

[0539] The user receives a notification on their mobile device and checks the alert content. Based on the displayed information, they decide whether to remotely check on the elderly person's situation or go to the site to take action if necessary. The input is the push notification, and the output is the user's action.

[0540] 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.

[0541] This invention combines a system that analyzes data acquired using various sensors to detect anomalies with an emotion engine that recognizes user emotions. This system consists of a data acquisition module, a data processing module, an emotion engine, and a notification management module, and each module works in cooperation with the others.

[0542] Program Implementation

[0543] Data Acquisition Module

[0544] The device acquires GPS location information, acceleration, audio, video, and emotional data derived from the user's facial expressions and voice via wearable devices and environmental sensors. The device then monitors this data in real time.

[0545] Data Processing Module

[0546] The server stores various data sent from the terminals in data storage and performs preprocessing. Here, abnormal data is sorted and prepared for analysis.

[0547] An anomaly detection algorithm is applied to the pre-processed data using a generative model to detect deviations from normal behavioral patterns.

[0548] Emotional Engine

[0549] The server analyzes the user's emotional data to recognize their current emotional state. This emotional information is used to customize anomaly detection algorithms and notification content.

[0550] Notification management module

[0551] Based on the anomalies detected by the server, natural language processing techniques are used to generate notifications that reflect emotional information. The notifications include a detailed description of the situation and corresponding recommended actions.

[0552] Users receive this notification, check the specific situation, and take prompt action based on easily understandable information that aligns with their emotional state.

[0553] Specific example

[0554] For example, suppose a device detects signs of a fall based on acceleration from an elderly person's wearable device, and at the same time collects emotional data from the user's voice indicating a lack of composure. The server analyzes this data and detects an anomaly, indicating a fall, and the emotion engine recognizes emotions such as anxiety and impatience. The server then generates a notification saying, "A fall has been detected. Please check on the person as soon as possible if you are nearby. The user may be experiencing significant anxiety, so please try to speak to them calmly," and sends it to the user.

[0555] Thus, by using an emotion engine, the present invention provides notifications that are more considerate of the user's feelings and promotes a quick and appropriate response. For the user, this system simultaneously provides a sense of being watched over and a sense of security, contributing to an improvement in their quality of life.

[0556] The following describes the processing flow.

[0557] Step 1:

[0558] The device uses wearable devices and surrounding sensors to acquire GPS location information, accelerometer data, voice, video, and emotional data such as facial expressions in real time. The acquired data is immediately prepared to be sent to a server.

[0559] Step 2:

[0560] The device transmits acquired data to the server using wireless communication technology. The data is sent in various formats, including location information, behavioral data, and sentiment data.

[0561] Step 3:

[0562] The server saves the received data to data storage and performs preprocessing such as correcting missing values ​​and removing outliers. This makes the data ready for analysis.

[0563] Step 4:

[0564] The server uses a generative model to analyze the pre-processed dataset and detect anomalies that exhibit behavioral patterns different from the norm. The generative model is learned from historical data, enabling highly accurate anomaly detection.

[0565] Step 5:

[0566] The server runs an emotion engine to analyze the user's emotional data and recognize their current emotional state. The recognition results are used to determine abnormal situations and customize notification content.

[0567] Step 6:

[0568] Based on the anomaly detected by the server and the user's emotional state, natural language processing technology is used to generate customized notifications. These notifications include details of the anomaly, a situational description tailored to the user's emotional state, and recommended actions.

[0569] Step 7:

[0570] The server generates customized notifications and sends them to users via methods such as push notifications, email, and SMS. These notifications are sent immediately to prompt user action.

[0571] Step 8:

[0572] The user receives a notification and reviews the details of the situation. They are supported in responding calmly to the situation based on emotionally sensitive content. The user then takes specific actions, such as going to the site, taking remote control, or making emergency contact as needed.

[0573] (Example 2)

[0574] 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."

[0575] Conventional anomaly detection systems have the drawback of failing to provide users with sufficient peace of mind because they do not take into account the emotional state of individuals and issue uniform notifications of anomalies. Furthermore, their anomaly detection accuracy is limited, leading to problems such as false positives and missed detections.

[0576] 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.

[0577] In this invention, the server includes means for acquiring individual information using various detection devices, means for executing a calculation method for organizing the acquired information and detecting anomalies, and means for determining the emotional state of the individual using emotion analysis means. This enables information processing that combines anomaly detection with emotional information, and allows for the generation of flexible notifications tailored to the user.

[0578] "Detection device" refers to various sensors and devices used to acquire information about a target, and this includes wearable devices and environmental sensors.

[0579] "Information" refers to data related to an individual, including GPS location information, body movements, audio, video, and emotional data.

[0580] "Calculation method" refers to algorithms and analytical techniques used to analyze acquired information and identify anomalies.

[0581] "Emotional analysis methods" refer to technologies that recognize emotions using data such as facial expressions and voice in order to determine an individual's emotional state.

[0582] "Notification" refers to a message or alert that is generated based on detected anomalies and emotional states and sent to an individual or relevant party.

[0583] This invention is a system that enables more personalized responses by detecting anomalies in various situations and generating notifications based on the user's emotional state. The system collects information using detection devices and performs information analysis and notification generation, primarily through a server.

[0584] Data collection and analysis

[0585] The device acquires individual information through wearable devices and environmental sensors. This information includes GPS location data, acceleration, voice, and video. Furthermore, it collects emotional data from the user's facial expressions and voice for emotion analysis.

[0586] The server stores the acquired information in data storage and uses calculation methods to detect anomalies. In this process, it utilizes a generative AI model to identify deviations from normal behavioral patterns, thereby achieving highly accurate anomaly detection.

[0587] Sentiment analysis and notification generation

[0588] The server uses emotion analysis tools to analyze the collected emotional data. This allows it to determine the user's current emotional state and incorporate that information into the anomaly detection algorithm.

[0589] Based on the emotional information associated with the anomaly, the server uses natural language processing techniques to generate personalized notifications. These notifications include details of the detected anomaly and recommended actions.

[0590] Specific example

[0591] For example, the device can monitor the movements of an elderly person and detect signs of a fall, while simultaneously detecting signs of anxiety in the user's voice. Based on this information, the server sends a specific notification to the user, such as, "A fall has been detected. Please check on the person as soon as possible if you are nearby. The user may be experiencing significant anxiety, so please speak to them calmly."

[0592] Example of a prompt

[0593] "Please generate a prompt that triggers an emotional analysis of anxiety-related behavior when a wearable device for the elderly detects a fall."

[0594] In this way, the invention incorporates emotional information to provide information that is adaptable to the individual.

[0595] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0596] Step 1:

[0597] The device uses wearable devices and environmental sensors to collect GPS location information, acceleration data, audio, and video. This data is acquired in real time and sent to the server as a data stream. The input data is raw sensor data, and the output is a data stream to the server. Specifically, the device receives signals from sensors, converts them into a specific format, and transmits them.

[0598] Step 2:

[0599] The server receives the collected data and stores it in data storage. Here, the data integrity is checked to ensure there is no invalid or missing data. The input is the raw data stream sent from the sensor, and a consistent dataset is ensured as the output. The operation includes checking the order of data packets and requesting retransmission of missing data.

[0600] Step 3:

[0601] The server preprocesses the stored data. It applies a denoising filter to remove unwanted information from acceleration and audio data. This process yields analysis-ready data as output from raw data as input. Specifically, the server uses the Fast Fourier Transform to remove noise components.

[0602] Step 4:

[0603] The server analyzes pre-processed data using a generation AI model and executes an anomaly detection algorithm. A machine learning model is used to detect deviations from normal behavioral patterns. The input is pre-processed data, and the output is the detection result of anomaly events. This step includes calculating an anomaly score and comparing it to a threshold.

[0604] Step 5:

[0605] The server uses emotion analysis tools to analyze the user's emotional data and determine their current emotional state. It receives emotion-related data as input and generates an emotional state label as output. Specifically, the server executes an algorithm that identifies the emotional state from voice intonation and facial expression analysis.

[0606] Step 6:

[0607] The server generates a notification using natural language processing technology based on the detected anomaly and the user's emotional state. This notification includes a description of the anomaly and recommended countermeasures. The input is anomaly and emotional data, and the output is a specific notification message. The generated notification is sent to the user in real time. Specifically, the system uses a text generation model to create a recommendation message and sends it to the user's device.

[0608] (Application Example 2)

[0609] 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."

[0610] Rapidly detecting accidents and health problems among the elderly and those receiving care, and prompting appropriate responses, is a crucial challenge in caregiving settings. Furthermore, beyond mere anomaly detection, there is a need for more accurate and reassuring responses that also consider the emotional state of the individual. However, conventional systems struggle to provide notifications that take emotional states into account, often resulting in purely mechanical responses. Therefore, there is a need for a system that incorporates emotional information to achieve rapid and appropriate anomaly responses.

[0611] 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.

[0612] In this invention, the server includes means for acquiring status information of a subject using various devices, means for analyzing the acquired status information to detect anomalies, means for analyzing the subject's emotions from the status information, and means for generating and transmitting notifications based on the anomaly and emotion information. This enables rapid and accurate response to anomalies that takes emotions into consideration.

[0613] A "device" is a piece of hardware or software designed to perform a specific function.

[0614] "Status information" refers to data that shows the physical and physiological changes and characteristics of the subject.

[0615] "Analysis" is the process of meticulously analyzing acquired data to identify anomalies and patterns.

[0616] An "anomaly" is a state or event that deviates from the normal pattern or exhibits different behavior.

[0617] "Emotions" refer to the internal psychological state of a person and are information obtained from their voice and facial expressions.

[0618] A "notification" is a message or alert generated to convey specific information or instructions.

[0619] The system implementing this invention mainly consists of a server, a terminal, and a user. The server receives data from terminals that collect various state information from wearable devices and fixed sensors. The terminals acquire physical state information and emotional data using accelerometers and voice input devices. This collected data is transmitted to the server in real time. The server operates on a cloud infrastructure such as Amazon Web Services and performs data analysis within the server.

[0620] The server first preprocesses the data using AWS Lambda. This preprocessing includes noise reduction and filtering of outliers. Then, a generative model built using AWS SageMaker is applied, and an anomaly detection algorithm is executed. If an anomaly is detected, sentiment data is also considered to identify the situation in more detail. Natural language processing tools such as Amazon Comprehend are used for sentiment analysis.

[0621] Based on the information obtained regarding abnormalities and emotions, the server sends notifications to devices via the Twilio API. For example, if an elderly person is identified as being at risk of falling, a detailed, emotion-sensitive instruction such as "Caution: Signs of a fall have been detected. Please speak to them calmly" is immediately sent to nearby care staff.

[0622] As a specific example, imagine an elderly person living in a nursing home who is going about their daily life without any problems. A wearable device detects a sudden increase in heart rate and movements that suggest they may fall. The server immediately analyzes this and, recognizing anxiety in the person's voice, generates a notification that includes "calm and reassuring words" to encourage the appropriate response.

[0623] Examples of prompts for the generative AI model include: "User sentiment analysis: Analyze the user's current emotions from the voice data," and "Anomaly event detection: Evaluate the likelihood of a fall from the acceleration data and identify behavior that differs from normal activity." This enables highly accurate decision-making based on emotions.

[0624] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0625] Step 1:

[0626] The terminal uses wearable devices and fixed environmental sensors to acquire acceleration data, voice data, and location information of the subject. The input is raw data from the sensors, and the output is data ready to be transmitted to the server in real time. This process involves the collection and format conversion of sensor data.

[0627] Step 2:

[0628] The server preprocesses the data sent from the terminal on AWS Lambda. The input is the raw data sent from the terminal, and the output is the denoised and outlier-filtered data. This process includes missing value imputation, data normalization, and removal of abnormal spikes.

[0629] Step 3:

[0630] The server applies a generative AI model to pre-processed data using AWS SageMaker. The input is filtered data, and the output is the result of anomaly detection. This process automatically identifies deviations from normal behavior and performs highly accurate anomaly detection.

[0631] Step 4:

[0632] The server uses AWS sentiment analysis services to analyze emotions from voice data. The input is the voice data from the previous step, and the output is a label of the detected emotional state. This enables detailed emotion recognition based on the subject's psychological state.

[0633] Step 5:

[0634] The server uses the Twilio API to generate and send notifications to the device based on the results of anomaly detection and sentiment analysis. The input is the anomaly detection results and sentiment recognition data, and the output is a customized notification message. This notification includes specific actions based on a prompt, specifically safety instructions for the individual and emotionally sensitive messages.

[0635] 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.

[0636] 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.

[0637] 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.

[0638] [Fourth Embodiment]

[0639] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0640] 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.

[0641] 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).

[0642] 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.

[0643] 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.

[0644] 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).

[0645] 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.

[0646] 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.

[0647] 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.

[0648] 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.

[0649] 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.

[0650] 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.

[0651] 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".

[0652] This invention is an advanced monitoring system that automatically performs data collection using various sensors, anomaly detection, and notification. This system mainly consists of a data collection module, a data processing module, and a notification management module, and each module works in coordination with the others.

[0653] Program Implementation

[0654] Data Acquisition Module

[0655] The device periodically acquires GPS location information, acceleration data, environmental audio, and video via wearable devices and environmental sensors.

[0656] The collected data is transmitted to the server using wireless communication technology.

[0657] Data Processing Module

[0658] The server first preprocesses the received data, removing outliers and correcting the data.

[0659] Next, a generative model is used to analyze the data and identify differences from normal behavioral patterns to detect anomalies.

[0660] The anomaly detection algorithm incorporates machine learning techniques, continuously learning from past data to improve detection accuracy.

[0661] Notification management module

[0662] The server immediately generates a notification to relevant parties if an anomaly is detected.

[0663] This notification uses natural language processing technology to provide users with a detailed description of the situation and recommended countermeasures.

[0664] Users receive notifications, check the specific situation through the application, and take prompt action as needed.

[0665] Specific example

[0666] For example, suppose a device acquires data from an elderly person's accelerometer indicating a sudden movement, i.e., a fall. The server analyzes this data and detects an anomaly as a deviation from the normal range of movement. It then generates a notification containing details of the anomaly and necessary countermeasures (e.g., "An elderly person may have fallen. Please check the scene."). The user receives this notification and takes action, such as going to the scene or checking remotely.

[0667] Thus, the present invention is a system that efficiently ensures the safety of an entire region by utilizing various sensor data to immediately detect abnormal conditions. For users, it enhances their sense of security in daily life by enabling quick and appropriate responses to the situation.

[0668] The following describes the processing flow.

[0669] Step 1:

[0670] The device periodically acquires data such as GPS location information, acceleration, ambient sound, and video through wearable devices and fixed sensors. This prepares the system for real-time monitoring of the subject's movements and environmental changes.

[0671] Step 2:

[0672] The terminal collects data and transmits it to the server using wireless communication technology. The data is transmitted in a structured format and is immediately ready for analysis.

[0673] Step 3:

[0674] The server stores the received data in data storage and performs preprocessing. This involves removing outliers and imputing missing data to build a reliable dataset.

[0675] Step 4:

[0676] The server applies an anomaly detection algorithm using a generative model to the pre-processed data. The model learns from past data and determines whether the current data deviates from normal behavioral patterns.

[0677] Step 5:

[0678] The server immediately generates an alert if an anomaly is detected. This alert includes a specific description of the anomaly, generated using natural language processing technology, and recommended countermeasures.

[0679] Step 6:

[0680] The server generates alerts and notifies parents and local community watch representatives. Notifications are sent using methods such as push notifications, email, and SMS.

[0681] Step 7:

[0682] Users receive notifications and can use their smartphones or computers to view detailed information. These notifications include instructions for situations requiring immediate action, supporting quick decision-making.

[0683] Step 8:

[0684] The user takes appropriate action based on the notification. For example, they may go to the site, remotely check the situation, or contact emergency services if necessary.

[0685] (Example 1)

[0686] 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".

[0687] In modern society, with the increasing diversity of living environments, there is a growing need for monitoring systems that can quickly and accurately detect anomalies and prompt appropriate responses. Conventional systems have struggled to improve the accuracy of anomaly detection and to provide timely, situation-appropriate countermeasures. Therefore, the challenge to be addressed is to provide a monitoring system that combines efficient and reliable anomaly detection and notification functions.

[0688] 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.

[0689] In this invention, the server includes means for acquiring information using various detection devices, means for transmitting the acquired information using wireless communication technology, and means for analyzing the information using a generative model and detecting anomalies. This enables efficient information collection and rapid response to anomalies based on the results of the analysis.

[0690] A "detection device" is a general term for equipment or devices that can acquire information from an object, and these are used in a variety of environments.

[0691] "Information" refers to a collection of data acquired by a detection device, including location information, operational data, and environmental conditions.

[0692] "Wireless communication technology" refers to all technologies used to transmit and receive information by means other than wired connections.

[0693] A "generative model" is a computational model used to analyze and predict new data by learning from past data.

[0694] An "anomaly" refers to data or situations that deviate from normal operation or state, and is detected based on specific criteria.

[0695] A "notification" is a message generated when the system detects an anomaly, providing warnings or information to the user.

[0696] "Natural language processing technology" refers to the technology that enables computers to understand, generate, and process human natural language.

[0697] A "countermeasure" is a guideline that outlines the specific actions and procedures that users should take in response to detected anomalies.

[0698] Embodiments of this invention include the following specific configurations and operations.

[0699] This system provides advanced monitoring capabilities by acquiring data in real time using various detection devices, detecting anomalies based on that data, and generating notifications. The terminal periodically acquires various information such as heart rate, acceleration data, location information, ambient sounds, temperature, and humidity using wearable devices and environmental sensors. This process often utilizes common wearable devices and IoT sensors.

[0700] The data collected by the device is transmitted to the server via wireless communication technologies such as Wi-Fi or Bluetooth. The server preprocesses the received data using Python libraries (e.g., numpy and pandas) to correct for outliers and missing values. Then, a generative model is used for data analysis. TensorFlow or PyTorch can be used for this generative model.

[0701] The server performs data analysis using generative models, identifies differences from normal behavior patterns using machine learning techniques, and detects anomalies. If an anomaly is detected, it uses natural language processing techniques (e.g., OpenAI's GPT model) to generate a notification that includes a detailed description of the situation and recommended countermeasures. This notification is immediately sent to the user's smartphone or tablet via the app.

[0702] Users are expected to take the most appropriate action quickly based on the notifications they receive. This system is particularly useful in situations such as monitoring the health of the elderly and automated safety management. For example, if a terminal acquires data indicating a possible fall by an elderly person, the server will recognize this as an anomaly and generate a notification such as, "An elderly person may have fallen. Please check the site," and send it to the user.

[0703] By utilizing a generative AI model, the system can automatically generate detailed explanations and instructions based on prompts. An example of a prompt might be, "Generate a notification message to prevent falls in the home."

[0704] This configuration enhances the safety of the community and improves people's sense of security in their daily lives.

[0705] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0706] Step 1:

[0707] The device acquires data. Specifically, the device collects heart rate, acceleration data, location information, etc., using wearable devices and environmental sensors. This information is obtained by analyzing signals from the sensors. Environmental sound, temperature, and humidity data are also collected in parallel. The input is raw data from the sensors, and the output is a rationally organized dataset.

[0708] Step 2:

[0709] The device sends data to the server. The device sends the collected data to the server using wireless communication technologies such as Wi-Fi or Bluetooth. The data sent includes all collected sensor information. The input is the dataset stored on the device, and the output is the data transferred to the server.

[0710] Step 3:

[0711] The server preprocesses the data. The server preprocesses the received data using NumPy or pandas, removing outliers and imputing missing values. Specific operations include data cleaning and standardization. The input is unprocessed raw data, and the output is a clean dataset.

[0712] Step 4:

[0713] The server analyzes the data using a generative AI model. The server inputs preprocessed data into the generative AI model and detects anomalies by determining differences from normal behavior patterns. This process uses machine learning frameworks such as TensorFlow and PyTorch. The input is a preprocessed dataset, and the output is the anomaly detection result.

[0714] Step 5:

[0715] The server generates notifications. When an anomaly is detected, the server uses natural language processing techniques to generate a notification that includes a detailed description of the situation and recommended countermeasures. Specifically, it uses models such as the GPT to generate the text. The input is the anomaly detection result, and the output is the generated notification message.

[0716] Step 6:

[0717] The server sends a notification to the user. The notification generated by the server is immediately sent to the user's smartphone or tablet via the app. The input is the generated notification message, and the output is the actual notification sent to the user's device.

[0718] Step 7:

[0719] The user checks the notification and takes appropriate action. Based on the received notification, the user will either check the site in the case of a fall or monitor the situation remotely. The input is the notification message sent from the server, and the output is the user's specific action.

[0720] (Application Example 1)

[0721] 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".

[0722] There is a need to efficiently monitor the safety of elderly people in their living environments and enable rapid response in the event of an anomaly. In particular, it is crucial to monitor the movements and physiological state of elderly people in real time, immediately notify relevant parties when an anomaly is detected, and provide specific countermeasures. However, conventional monitoring systems have issues with detection accuracy and real-time capabilities, making them insufficient for ensuring the safety of the elderly. Therefore, there is a need for monitoring systems that are more accurate and capable of immediate response.

[0723] 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.

[0724] In this invention, the server includes means for acquiring data on the subject's movements and physiological state using various sensors, means for executing an algorithm to analyze the acquired data and detect anomalies, and means for providing details of the anomaly and recommended countermeasures to the relevant parties in real time via a mobile device. This enhances the safety and security of the elderly and enables a rapid response to the situation.

[0725] "Diverse sensors" refers to a set of multiple types of sensors used to comprehensively acquire data on movement and physiological states.

[0726] "Movement and physiological state data" refers to measurement results related to the subject's movement and physical function, and mainly includes information such as acceleration, heart rate, and body temperature.

[0727] An "algorithm for detecting anomalies" is a computational method used to identify situations that deviate from normal behavioral patterns with high accuracy.

[0728] "Providing information via mobile devices" means transmitting and providing information to recipients through portable information terminals such as smartphones and tablets.

[0729] "Providing information to relevant parties in real time" means immediately notifying them the moment an anomaly is detected and quickly disseminating the information to the relevant people.

[0730] This invention is a monitoring system that uses various sensors to ensure the safety of the elderly. The following hardware and software are used to implement the invention.

[0731] The server includes a data acquisition module, a data processing module, and a notification management module. The data acquisition module monitors the movements and physiological state of elderly individuals in real time through various sensors, specifically wearable devices and environmental sensors, acquiring data such as GPS location, acceleration, heart rate, and body temperature. The acquired data is transferred to a mobile device using Bluetooth technology for further processing.

[0732] The data processing module analyzes incoming data from mobile devices and performs anomaly removal and filtering. This involves executing anomaly detection algorithms using data analysis tools such as Python's NumPy and Pandas, as well as machine learning libraries like TensorFlow and Scikit-learn. This allows for the identification of anomalies by comparing them to normal behavioral patterns.

[0733] The notification management module immediately generates notifications for family members and caregivers when an anomaly is detected. It uses Firebase Cloud Messaging (FCM) to send push notifications to smartphones, providing details of the anomaly and recommended actions through natural language processing.

[0734] As a concrete example of this system, if an elderly person makes unusual movements late at night, the system will detect these movements as abnormal and send a notification to their smartphone saying, "Your location has changed late at night. Please check if necessary," prompting prompt action to verify their location.

[0735] An example of a prompt message is: "A 70-year-old elderly person is wearing a wearable device. Develop an application that sends a notification when they move to an unusual location at night. Please suggest a suitable anomaly detection algorithm."

[0736] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0737] Step 1:

[0738] The device acquires data on the elderly person's movement and physiological state via wearable devices and environmental sensors. Specifically, it periodically measures heart rate, body temperature, acceleration, and GPS location information, and transmits this data to the mobile device using Bluetooth communication. The input is sensor data, and the output is a Bluetooth message.

[0739] Step 2:

[0740] The mobile device collects the received sensor data and sends it to the server. The server acquires this data and first performs data preprocessing. It cleans the data, such as removing noise and correcting missing values, to generate data that can be analyzed. The input here is sensor data from Bluetooth messages, and the output is clean data for analysis.

[0741] Step 3:

[0742] The server applies machine learning algorithms to preprocessed data to detect anomalies. Specifically, it runs an anomaly detection model using TensorFlow or Scikit-learn to identify deviations from normal behavior. This process continuously trains the model using historical data to improve detection accuracy. The input is the data for analysis, and the output is the result of anomaly detection.

[0743] Step 4:

[0744] When an anomaly is detected, the server uses natural language processing to generate a notification containing details of the anomaly and recommended actions. Firebase Cloud Messaging (FCM) is used to send a push notification to the mobile devices of family members or caregivers. This notification includes a specific alert message tailored to the anomaly. The input here is the anomaly detection result, and the output is the alert message sent to the user.

[0745] Step 5:

[0746] The user receives a notification on their mobile device and checks the alert content. Based on the displayed information, they decide whether to remotely check on the elderly person's situation or go to the site to take action if necessary. The input is the push notification, and the output is the user's action.

[0747] 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.

[0748] This invention combines a system that analyzes data acquired using various sensors to detect anomalies with an emotion engine that recognizes user emotions. This system consists of a data acquisition module, a data processing module, an emotion engine, and a notification management module, and each module works in cooperation with the others.

[0749] Program Implementation

[0750] Data Acquisition Module

[0751] The device acquires GPS location information, acceleration, audio, video, and emotional data derived from the user's facial expressions and voice via wearable devices and environmental sensors. The device then monitors this data in real time.

[0752] Data Processing Module

[0753] The server stores various data sent from the terminals in data storage and performs preprocessing. Here, abnormal data is sorted and prepared for analysis.

[0754] An anomaly detection algorithm is applied to the pre-processed data using a generative model to detect deviations from normal behavioral patterns.

[0755] Emotional Engine

[0756] The server analyzes the user's emotional data to recognize their current emotional state. This emotional information is used to customize anomaly detection algorithms and notification content.

[0757] Notification management module

[0758] Based on the anomalies detected by the server, natural language processing techniques are used to generate notifications that reflect emotional information. The notifications include a detailed description of the situation and corresponding recommended actions.

[0759] Users receive this notification, check the specific situation, and take prompt action based on easily understandable information that aligns with their emotional state.

[0760] Specific example

[0761] For example, suppose a device detects signs of a fall based on acceleration from an elderly person's wearable device, and at the same time collects emotional data from the user's voice indicating a lack of composure. The server analyzes this data and detects an anomaly, indicating a fall, and the emotion engine recognizes emotions such as anxiety and impatience. The server then generates a notification saying, "A fall has been detected. Please check on the person as soon as possible if you are nearby. The user may be experiencing significant anxiety, so please try to speak to them calmly," and sends it to the user.

[0762] Thus, by using an emotion engine, the present invention provides notifications that are more considerate of the user's feelings and promotes a quick and appropriate response. For the user, this system simultaneously provides a sense of being watched over and a sense of security, contributing to an improvement in their quality of life.

[0763] The following describes the processing flow.

[0764] Step 1:

[0765] The device uses wearable devices and surrounding sensors to acquire GPS location information, accelerometer data, voice, video, and emotional data such as facial expressions in real time. The acquired data is immediately prepared to be sent to a server.

[0766] Step 2:

[0767] The device transmits acquired data to the server using wireless communication technology. The data is sent in various formats, including location information, behavioral data, and sentiment data.

[0768] Step 3:

[0769] The server saves the received data to data storage and performs preprocessing such as correcting missing values ​​and removing outliers. This makes the data ready for analysis.

[0770] Step 4:

[0771] The server uses a generative model to analyze the pre-processed dataset and detect anomalies that exhibit behavioral patterns different from the norm. The generative model is learned from historical data, enabling highly accurate anomaly detection.

[0772] Step 5:

[0773] The server runs an emotion engine to analyze the user's emotional data and recognize their current emotional state. The recognition results are used to determine abnormal situations and customize notification content.

[0774] Step 6:

[0775] Based on the anomaly detected by the server and the user's emotional state, natural language processing technology is used to generate customized notifications. These notifications include details of the anomaly, a situational description tailored to the user's emotional state, and recommended actions.

[0776] Step 7:

[0777] The server generates customized notifications and sends them to users via methods such as push notifications, email, and SMS. These notifications are sent immediately to prompt user action.

[0778] Step 8:

[0779] The user receives a notification and reviews the details of the situation. They are supported in responding calmly to the situation based on emotionally sensitive content. The user then takes specific actions, such as going to the site, taking remote control, or making emergency contact as needed.

[0780] (Example 2)

[0781] 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".

[0782] Conventional anomaly detection systems have the drawback of failing to provide users with sufficient peace of mind because they do not take into account the emotional state of individuals and issue uniform notifications of anomalies. Furthermore, their anomaly detection accuracy is limited, leading to problems such as false positives and missed detections.

[0783] 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.

[0784] In this invention, the server includes means for acquiring individual information using various detection devices, means for executing a calculation method for organizing the acquired information and detecting anomalies, and means for determining the emotional state of the individual using emotion analysis means. This enables information processing that combines anomaly detection with emotional information, and allows for the generation of flexible notifications tailored to the user.

[0785] "Detection device" refers to various sensors and devices used to acquire information about a target, and this includes wearable devices and environmental sensors.

[0786] "Information" refers to data related to an individual, including GPS location information, body movements, audio, video, and emotional data.

[0787] "Calculation method" refers to algorithms and analytical techniques used to analyze acquired information and identify anomalies.

[0788] "Emotional analysis methods" refer to technologies that recognize emotions using data such as facial expressions and voice in order to determine an individual's emotional state.

[0789] "Notification" refers to a message or alert that is generated based on detected anomalies and emotional states and sent to an individual or relevant party.

[0790] This invention is a system that enables more personalized responses by detecting anomalies in various situations and generating notifications based on the user's emotional state. The system collects information using detection devices and performs information analysis and notification generation, primarily through a server.

[0791] Data collection and analysis

[0792] The device acquires individual information through wearable devices and environmental sensors. This information includes GPS location data, acceleration, voice, and video. Furthermore, it collects emotional data from the user's facial expressions and voice for emotion analysis.

[0793] The server stores the acquired information in data storage and uses calculation methods to detect anomalies. In this process, it utilizes a generative AI model to identify deviations from normal behavioral patterns, thereby achieving highly accurate anomaly detection.

[0794] Sentiment analysis and notification generation

[0795] The server uses emotion analysis tools to analyze the collected emotional data. This allows it to determine the user's current emotional state and incorporate that information into the anomaly detection algorithm.

[0796] Based on the emotional information associated with the anomaly, the server uses natural language processing techniques to generate personalized notifications. These notifications include details of the detected anomaly and recommended actions.

[0797] Specific example

[0798] For example, the device can monitor the movements of an elderly person and detect signs of a fall, while simultaneously detecting signs of anxiety in the user's voice. Based on this information, the server sends a specific notification to the user, such as, "A fall has been detected. Please check on the person as soon as possible if you are nearby. The user may be experiencing significant anxiety, so please speak to them calmly."

[0799] Example of a prompt

[0800] "Please generate a prompt that triggers an emotional analysis of anxiety-related behavior when a wearable device for the elderly detects a fall."

[0801] In this way, the invention incorporates emotional information to provide information that is adaptable to the individual.

[0802] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0803] Step 1:

[0804] The device uses wearable devices and environmental sensors to collect GPS location information, acceleration data, audio, and video. This data is acquired in real time and sent to the server as a data stream. The input data is raw sensor data, and the output is a data stream to the server. Specifically, the device receives signals from sensors, converts them into a specific format, and transmits them.

[0805] Step 2:

[0806] The server receives the collected data and stores it in data storage. Here, the data integrity is checked to ensure there is no invalid or missing data. The input is the raw data stream sent from the sensor, and a consistent dataset is ensured as the output. The operation includes checking the order of data packets and requesting retransmission of missing data.

[0807] Step 3:

[0808] The server preprocesses the stored data. It applies a denoising filter to remove unwanted information from acceleration and audio data. This process yields analysis-ready data as output from raw data as input. Specifically, the server uses the Fast Fourier Transform to remove noise components.

[0809] Step 4:

[0810] The server analyzes pre-processed data using a generation AI model and executes an anomaly detection algorithm. A machine learning model is used to detect deviations from normal behavioral patterns. The input is pre-processed data, and the output is the detection result of anomaly events. This step includes calculating an anomaly score and comparing it to a threshold.

[0811] Step 5:

[0812] The server uses emotion analysis tools to analyze the user's emotional data and determine their current emotional state. It receives emotion-related data as input and generates an emotional state label as output. Specifically, the server executes an algorithm that identifies the emotional state from voice intonation and facial expression analysis.

[0813] Step 6:

[0814] The server generates a notification using natural language processing technology based on the detected anomaly and the user's emotional state. This notification includes a description of the anomaly and recommended countermeasures. The input is anomaly and emotional data, and the output is a specific notification message. The generated notification is sent to the user in real time. Specifically, the system uses a text generation model to create a recommendation message and sends it to the user's device.

[0815] (Application Example 2)

[0816] 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".

[0817] Rapidly detecting accidents and health problems among the elderly and those receiving care, and prompting appropriate responses, is a crucial challenge in caregiving settings. Furthermore, beyond mere anomaly detection, there is a need for more accurate and reassuring responses that also consider the emotional state of the individual. However, conventional systems struggle to provide notifications that take emotional states into account, often resulting in purely mechanical responses. Therefore, there is a need for a system that incorporates emotional information to achieve rapid and appropriate anomaly responses.

[0818] 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.

[0819] In this invention, the server includes means for acquiring status information of a subject using various devices, means for analyzing the acquired status information to detect anomalies, means for analyzing the subject's emotions from the status information, and means for generating and transmitting notifications based on the anomaly and emotion information. This enables rapid and accurate response to anomalies that takes emotions into consideration.

[0820] A "device" is a piece of hardware or software designed to perform a specific function.

[0821] "Status information" refers to data that shows the physical and physiological changes and characteristics of the subject.

[0822] "Analysis" is the process of meticulously analyzing acquired data to identify anomalies and patterns.

[0823] An "anomaly" is a state or event that deviates from the normal pattern or exhibits different behavior.

[0824] "Emotions" refer to the internal psychological state of a person and are information obtained from their voice and facial expressions.

[0825] A "notification" is a message or alert generated to convey specific information or instructions.

[0826] The system implementing this invention mainly consists of a server, a terminal, and a user. The server receives data from terminals that collect various state information from wearable devices and fixed sensors. The terminals acquire physical state information and emotional data using accelerometers and voice input devices. This collected data is transmitted to the server in real time. The server operates on a cloud infrastructure such as Amazon Web Services and performs data analysis within the server.

[0827] The server first preprocesses the data using AWS Lambda. This preprocessing includes noise reduction and filtering of outliers. Then, a generative model built using AWS SageMaker is applied, and an anomaly detection algorithm is executed. If an anomaly is detected, sentiment data is also considered to identify the situation in more detail. Natural language processing tools such as Amazon Comprehend are used for sentiment analysis.

[0828] Based on the information obtained regarding abnormalities and emotions, the server sends notifications to devices via the Twilio API. For example, if an elderly person is identified as being at risk of falling, a detailed, emotion-sensitive instruction such as "Caution: Signs of a fall have been detected. Please speak to them calmly" is immediately sent to nearby care staff.

[0829] As a specific example, imagine an elderly person living in a nursing home who is going about their daily life without any problems. A wearable device detects a sudden increase in heart rate and movements that suggest they may fall. The server immediately analyzes this and, recognizing anxiety in the person's voice, generates a notification that includes "calm and reassuring words" to encourage the appropriate response.

[0830] Examples of prompts for the generative AI model include: "User sentiment analysis: Analyze the user's current emotions from the voice data," and "Anomaly event detection: Evaluate the likelihood of a fall from the acceleration data and identify behavior that differs from normal activity." This enables highly accurate decision-making based on emotions.

[0831] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0832] Step 1:

[0833] The terminal uses wearable devices and fixed environmental sensors to acquire acceleration data, voice data, and location information of the subject. The input is raw data from the sensors, and the output is data ready to be transmitted to the server in real time. This process involves the collection and format conversion of sensor data.

[0834] Step 2:

[0835] The server preprocesses the data sent from the terminal on AWS Lambda. The input is the raw data sent from the terminal, and the output is the denoised and outlier-filtered data. This process includes missing value imputation, data normalization, and removal of abnormal spikes.

[0836] Step 3:

[0837] The server applies a generative AI model to pre-processed data using AWS SageMaker. The input is filtered data, and the output is the result of anomaly detection. This process automatically identifies deviations from normal behavior and performs highly accurate anomaly detection.

[0838] Step 4:

[0839] The server uses AWS sentiment analysis services to analyze emotions from voice data. The input is the voice data from the previous step, and the output is a label of the detected emotional state. This enables detailed emotion recognition based on the subject's psychological state.

[0840] Step 5:

[0841] The server uses the Twilio API to generate and send notifications to the device based on the results of anomaly detection and sentiment analysis. The input is the anomaly detection results and sentiment recognition data, and the output is a customized notification message. This notification includes specific actions based on a prompt, specifically safety instructions for the individual and emotionally sensitive messages.

[0842] 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.

[0843] 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.

[0844] 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.

[0845] 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.

[0846] 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.

[0847] 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.

[0848] 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.

[0849] 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.

[0850] 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."

[0851] 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.

[0852] 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.

[0853] 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.

[0854] 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.

[0855] 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.

[0856] 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.

[0857] 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.

[0858] 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.

[0859] 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.

[0860] 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.

[0861] 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.

[0862] 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.

[0863] The following is further disclosed regarding the embodiments described above.

[0864] (Claim 1)

[0865] A means of acquiring data on a subject using various sensors,

[0866] A means for executing an algorithm that analyzes the acquired data and detects anomalies,

[0867] A means for generating and sending a notification based on the detected anomaly,

[0868] A system that includes this.

[0869] (Claim 2)

[0870] The system according to claim 1, which uses a generative model to learn in data analysis and improves the accuracy of anomaly detection.

[0871] (Claim 3)

[0872] The system according to claim 1, which uses natural language processing techniques to include details of the situation and recommended actions in the notification.

[0873] "Example 1"

[0874] (Claim 1)

[0875] A means of acquiring information about the target using various detection devices,

[0876] Means for transmitting the acquired information using wireless communication technology,

[0877] Means for preprocessing the transmitted information to remove abnormal values,

[0878] A means for analyzing the information using a generative model, identifying differences from normal operating patterns, and detecting anomalies,

[0879] A means for generating and transmitting a notification that includes a description of the situation and recommended countermeasures based on the detected anomaly,

[0880] A system that includes this.

[0881] (Claim 2)

[0882] The system according to claim 1, which improves the accuracy of anomaly detection by performing data analysis using a generative model and learning from it.

[0883] (Claim 3)

[0884] The system according to claim 1, which uses natural language processing technology to include a description of the situation and recommended actions in a notification.

[0885] "Application Example 1"

[0886] (Claim 1)

[0887] A means of acquiring data on the subject's movements and physiological state using various sensors,

[0888] A means for executing an algorithm that analyzes the acquired data and detects anomalies,

[0889] A means for generating and sending a notification based on the detected anomaly,

[0890] A means of providing stakeholders with details of anomalies and recommended countermeasures in real time via mobile devices,

[0891] A system that includes this.

[0892] (Claim 2)

[0893] The system according to claim 1, which continuously learns from data using machine learning methods in data analysis to improve the accuracy of anomaly detection.

[0894] (Claim 3)

[0895] The system according to claim 1, which uses natural language processing technology to include in notifications a specific description of the abnormal situation and recommended actions.

[0896] "Example 2 of combining an emotion engine"

[0897] (Claim 1)

[0898] A means of acquiring information about an individual using various detection devices,

[0899] Means for organizing the acquired information and executing a calculation method for detecting anomalies,

[0900] A means of determining an individual's emotional state using emotion analysis methods,

[0901] A means for generating and transmitting a notification based on the detected abnormality and emotional state,

[0902] A system that includes this.

[0903] (Claim 2)

[0904] The system according to claim 1, which learns using a generative calculation method in information analysis and improves the accuracy of anomaly detection.

[0905] (Claim 3)

[0906] The system according to claim 1, which uses natural language processing techniques to include detailed information and recommended actions in a notification.

[0907] "Application example 2 when combining with an emotional engine"

[0908] (Claim 1)

[0909] Means for acquiring subject status information using various devices,

[0910] A means for analyzing the acquired state information to detect anomalies,

[0911] A means for analyzing the subject's emotions from the aforementioned state information,

[0912] A means of generating and sending notifications based on abnormal and emotional information,

[0913] A detection device that includes [this].

[0914] (Claim 2)

[0915] The detection device according to claim 1, which learns using a generative algorithm in data analysis to improve the accuracy of anomaly detection and emotion recognition.

[0916] (Claim 3)

[0917] The detection device according to claim 1, which uses natural language processing technology to provide notifications that include details of the situation and recommended countermeasures, and that take into account the emotional state of the recipient. [Explanation of symbols]

[0918] 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. A means of acquiring data on a subject using various sensors, A means for executing an algorithm that analyzes the acquired data and detects anomalies, A means for generating and sending a notification based on the detected anomaly, A system that includes this.

2. The system according to claim 1, which uses a generative model to learn in data analysis and improves the accuracy of anomaly detection.

3. The system according to claim 1, which uses natural language processing technology to include details of the situation and recommended actions in the notification.

Images