system

Abstract

We provide the system. [Solution] Measurement means for continuously collecting environmental data, An identification means for analyzing data obtained from the measurement means and detecting anomalies, A notification means that issues an alarm based on an abnormality detected by the identification means, A notification means that provides information to a user who has received an alarm from the aforementioned notification means, A learning method that uses collected data to learn and improve the accuracy of the identification method, A system that includes this.

Description

Technical Field

[0004] , ,

[0005] , ,

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] With the increase in the number of elderly people living alone, concerns about safety are spreading. In particular, since it is difficult for the elderly to deal with suspicious persons, effective and prompt support is necessary. In conventional security systems, real-time detection of the intrusion or abnormal behavior of suspicious persons may not be sufficient, resulting in misunderstandings due to false alarms and delays in response. In addition, an effective learning mechanism for improving detection accuracy is lacking, and improvement measures are required.

Means for Solving the Problems

[0005] To solve the above problems, the present invention provides a measurement means for continuously collecting environmental data. Based on the data obtained from this measurement means, an identification means for detecting anomalies is utilized, and a notification means for issuing a rapid alarm is provided, enabling immediate response to detected anomalies. Furthermore, by utilizing the obtained data, a learning means is used to improve the accuracy of the identification means, thereby reducing false alarms. The aim is to provide a sense of security to the elderly and their families and to enhance security.

[0006] A "measuring device" is a device equipped with the function of continuously collecting data such as environmental movement, sound, temperature, and humidity.

[0007] "Identification means" refers to a device or software that uses collected data to perform analysis in order to detect abnormal behavior or the intrusion of suspicious individuals.

[0008] "Notification means" refers to a device or system that has the function of issuing an alarm or sending information to a user based on an anomaly detected by an identification means.

[0009] "Notification means" refers to a device or means for providing users with alarm information issued by a notification means, and includes various forms such as voice, email, and app notifications.

[0010] A "learning tool" is a system or algorithm that performs machine learning to improve the accuracy of an identification tool based on collected data and user feedback.

[0011] A "notification method" refers to a system or protocol for promptly notifying security agencies or relevant third parties based on the results of an anomaly detection. [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] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Figure 11] This is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] This is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] This is a sequence diagram showing the processing flow of the data processing system in Example 2, which incorporates an emotion engine. [Figure 14] This is a sequence diagram showing the processing flow of the data processing system in Application Example 2, which combines an emotion engine. [Modes for carrying out the invention]

[0013] Hereinafter, an example of an embodiment of the system relating to the technology of this disclosure will be described with reference to the attached drawings.

[0014] First, the terms 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] The system according to the present invention is an AI-equipped sensor system for ensuring the safety of the elderly. This system collects various data from the environment, detects anomalies based on that data, and notifies necessary alarms. Furthermore, it is possible to improve detection accuracy by accumulating data using machine learning technology.

[0034] First, sensors placed in and around the living space continuously acquire environmental data such as motion, sound, temperature, and humidity. The data collected by the sensors is sent to a server, which then analyzes the data.

[0035] The server uses an AI model to analyze the acquired data in real time and identify abnormal behavior and patterns. For example, if irregular movements or differences from normal activity are detected during a specific time period, it is immediately judged as abnormal.

[0036] When an anomaly is detected, the server uses notification methods to send an alert to pre-configured family members or security companies. Specifically, users are notified via voice alarms, email notifications, or push notifications through a dedicated app via their devices. Upon receiving the alert, users can take prompt action to ensure the safety of the elderly person.

[0037] Furthermore, the server retrains its AI model based on collected data and user feedback to improve the accuracy of its identification methods. This process reduces false alarms and enables more accurate anomaly detection.

[0038] For example, if an intruder attempts to enter a property at night by opening a window, the sensor will detect the movement and sound, and the server will immediately identify it as abnormal activity. An automatic alarm notification will then be sent to family members or designated security agencies, enabling prompt action.

[0039] Ultimately, this system provides safety and peace of mind to the elderly and their families by monitoring their living environment and immediately notifying them of any abnormal situations.

[0040] The following describes the processing flow.

[0041] Step 1:

[0042] The server receives environmental data collected by the sensors. This data includes information such as movement, sound, temperature, and humidity over time. The server temporarily stores the received data and prepares it for preprocessing.

[0043] Step 2:

[0044] The server performs preprocessing on the received data, such as noise reduction and filtering. This process removes unnecessary data and improves the accuracy of the information needed for analysis.

[0045] Step 3:

[0046] The server inputs pre-processed data into an AI model and performs real-time analysis. The AI ​​model is trained on historical data and has the ability to identify patterns of suspicious intrusion and abnormal behavior.

[0047] Step 4:

[0048] If the AI ​​model detects an anomaly, the server immediately activates notification mechanisms and issues an alarm. The alarm is sent to registered devices as an email or app notification.

[0049] Step 5:

[0050] The terminal displays a notification to the user when it receives an alarm from the server. The user checks the notification and considers taking immediate action. If necessary, they can contact the elderly person directly or notify the security company.

[0051] Step 6:

[0052] The server uses the data collected after notification, along with user feedback, to analyze and retrain the AI ​​model for improved accuracy. This will improve the accuracy of anomaly detection in subsequent instances.

[0053] (Example 1)

[0054] 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."

[0055] The present invention relates to a system for ensuring the safety of the elderly, and more particularly aims to provide a highly accurate system that can collect environmental information in real time, immediately detect anomalies, and issue alarms. More specifically, the objective is to improve the accuracy of anomaly detection, reduce false alarms, and enable rapid notification to users and security agencies.

[0056] 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.

[0057] In this invention, the server includes sensing means for continuously collecting environmental information, detection means for analyzing the information obtained from the sensing means to detect anomalies, and notification means for issuing an alarm based on the anomalies detected by the detection means. This makes it possible to monitor the living environment of elderly people and enable a rapid response in the event of an anomaly.

[0058] "Environmental information" is a general term for data that indicates surrounding elements such as temperature, humidity, sound, and movement, acquired within a specific area.

[0059] "Sensing means" refers to devices and sensors for continuously acquiring environmental information, which allows for real-time data collection.

[0060] "Analysis" is the act or process of processing collected data based on certain criteria to identify anomalies or patterns.

[0061] "Detection means" refers to techniques or methods for detecting anomalies from analyzed data.

[0062] "Abnormal" refers to behavior or a state that deviates from normal patterns or standards, indicating a situation that requires attention.

[0063] "Notification means" refers to a function or device that issues alarms or notifications based on detected abnormal information.

[0064] "Notification means" refers to the means or methods used to inform users of information transmitted by notification means.

[0065] "Analysis improvement means" refers to techniques or methods for improving the accuracy of detection means using collected information and feedback.

[0066] "Notification means" refers to a function that immediately transmits information to security agencies or designated personnel when an anomaly is detected.

[0067] The system according to the present invention is an AI-equipped sensor system designed to ensure the safety of the elderly. It mainly comprises the following elements:

[0068] The device includes multiple sensors installed in the living space. These sensors include motion sensors, sound sensors, and temperature / humidity sensors, and this hardware is used to continuously acquire environmental information. Motion sensors detect human movement, sound sensors capture changes in ambient sound, and temperature / humidity sensors monitor the temperature and humidity of the environment.

[0069] The server receives environmental information transmitted from terminals in real time and uses a generative AI model to analyze the data. This AI model is a powerful tool for learning normal behavior patterns and detecting abnormal patterns. In particular, it utilizes deep learning technology to perform highly accurate anomaly detection based on the obtained data.

[0070] The server also has a function to alert users using notification methods when it detects an anomaly. These notification methods include using the terminal's speaker as an audio alarm or sending notifications to the user's smart device. This allows users to immediately understand the location and time of the anomaly and take appropriate action.

[0071] Furthermore, the server continuously learns from the collected information through analysis and improvement mechanisms, thereby improving the accuracy of the detection mechanisms. User feedback is crucial data for the system to reduce false alarms and perform more precise anomaly detection.

[0072] For example, if a sensor detects a suspicious sound in the middle of the night, the server analyzes this data as an anomaly and immediately sends a push notification to the user's smartphone. At this time, the user can check the status of the room via the app.

[0073] An example of a prompt message could be, "Please explain what kind of data processing is necessary to detect abnormalities in the living environment of elderly people and provide real-time notifications." By inputting such prompt messages into the AI ​​generation model, guidelines can be obtained to ensure that the above-mentioned system is operated safely.

[0074] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0075] Step 1:

[0076] The device collects environmental information using various sensors installed in the living space. Specifically, a motion sensor detects human movement and records that movement information. A sound sensor captures changes in ambient sound, and a temperature and humidity sensor obtains current temperature and humidity data. The input is raw data obtained from each sensor, and the output is formatted environmental data sent to the server.

[0077] Step 2:

[0078] The server receives environmental data transmitted from terminals in real time. The input is environmental data from the terminals, and the output is pre-processed data for anomaly detection. Upon receiving the data, the server classifies each data type and formats it into a format suitable for analysis. This process enables efficient data analysis.

[0079] Step 3:

[0080] The server uses a generative AI model to analyze preprocessed data and detect anomalies. The input is preprocessed data, and the output is the analysis result indicating the presence or absence of anomalies. Specifically, the AI ​​model compares current data with past data to find deviations from normal patterns. The generative AI model uses deep learning techniques and performs complex mathematical calculations to improve the accuracy of anomaly detection.

[0081] Step 4:

[0082] If the server detects an anomaly, it will use a notification system to alert the user. The input is the analysis result of the anomaly detection, and the output is the information sent to the user's device as an alarm notification. Specifically, the server instructs the terminal to emit an audio alarm and also sends a push notification to the user's smartphone.

[0083] Step 5:

[0084] The user takes appropriate action in response to the received alarm. The input is the alarm notification, and the output is the action the user should take. The user launches a dedicated app and checks real-time video and detailed information to determine the appropriate course of action. Specifically, the user checks camera footage through the app and, if necessary, rushes to the scene or contacts relevant parties.

[0085] Step 6:

[0086] The server learns from collected data and user feedback through analytical methods to improve the generated AI model, thereby enhancing the system's accuracy. The input is accumulated data and feedback information, and the output is the updated AI model. Specifically, the server analyzes data that resulted in false alarms, readjusts the model, and improves the success rate of anomaly detection in subsequent instances.

[0087] (Application Example 1)

[0088] 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."

[0089] In elderly households, it is crucial to quickly detect abnormal situations in daily life and ensure safety. However, conventional systems struggle to provide security information to recipients in real time and prompt immediate action, thus creating a need for a more flexible and responsive monitoring system.

[0090] 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.

[0091] In this invention, the server includes measuring means for continuously collecting environmental information, detection means for analyzing the information obtained from the measuring means and identifying anomalies, a notification mechanism for issuing alarms based on the anomalies identified by the detection means, communication means for providing an application for installation on smart devices, and cooperation means for analyzing anomalies in real time and sending notifications to smart devices corresponding to the anomalies. This makes it possible to immediately detect anomalies in the living environment of elderly people and to quickly and accurately notify recipients.

[0092] "Environmental information" refers to various data related to the surrounding conditions, such as temperature, humidity, movement, and sound.

[0093] "Measuring means" refers to devices and methods for continuously acquiring environmental information.

[0094] "Analysis" refers to the process of thoroughly analyzing acquired information and performing necessary steps to identify anomalies.

[0095] "Identification means" refers to methods or models for detecting anomalies from analyzed information.

[0096] An "alarm" refers to a visual, auditory, or digital notification method used to alert someone when an anomaly is detected.

[0097] A "notification mechanism" refers to a system or device for issuing an alarm.

[0098] A "receiver" refers to a person who receives an alert from a notification system and uses the information.

[0099] A "notification mechanism" refers to a system or method for providing data to recipients.

[0100] A "learning mechanism" refers to a learning method or series of processes used to improve a system's performance and identification accuracy based on collected information.

[0101] A "smart device" refers to an electronic device that has information processing capabilities and can connect to a network.

[0102] "Communication methods" refer to methods and protocols for transmitting information to other devices or systems.

[0103] "Coordination means" refers to a method of coordinating between systems to transmit abnormalities to smart devices in a borderless manner and to prompt appropriate responses.

[0104] As a system to realize this application example, the server runs a program that continuously collects environmental information from various sensors installed in the home. The acquired environmental information is temporarily stored in a database and then appropriately analyzed. In the analysis step, the server uses machine learning algorithms to implement identification means for identifying anomalies. This is achieved by using machine learning libraries such as TENSORFLOW® to extract features from the collected data and build an anomaly detection model. Furthermore, when the server detects an anomaly in real time, it sends an alert notification to the user's smart devices using communication methods such as AWS® SNS.

[0105] Upon receiving a notification, users can check the situation and take necessary actions through a dedicated app on their smartphone or tablet. This application visually displays information about anomaly detection, supporting users in responding quickly and accurately. User feedback is automatically sent to the server and used to improve the anomaly detection algorithm. In this way, the system's accuracy continuously improves through learning.

[0106] As a concrete example, if suspicious activity is detected in an elderly person's home at night, the server analyzes the sensor information and immediately recognizes it as an anomaly. This triggers a notification to the user's smartphone, allowing them to quickly understand the situation and take action. An example of a prompt message to ensure the safety of the elderly in this way is as follows: "If suspicious noises are detected in an elderly person's home late at night, please tell me how to notify them and how to support a quick response."

[0107] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0108] Step 1:

[0109] Sensors continuously collect environmental information. The sensors acquire data on ambient temperature, humidity, sound, and motion, and transmit this data to a server. The input is environmental state data, and the output is raw data sent to the server. In this process, physical data is captured by the sensors and transmitted to the server via the network.

[0110] Step 2:

[0111] The server stores the received data in the database. The input is the raw data sent in step 1, and the output is the data stored in the database. The server uses a database management system for efficient data storage and access.

[0112] Step 3:

[0113] The server analyzes stored data and identifies anomalies. Specifically, it uses a generative AI model to analyze data patterns and detect unusual movements or sounds. The input is environmental data obtained from a database, and the output is the result of anomaly detection. The server executes machine learning algorithms to perform pattern recognition and anomaly detection.

[0114] Step 4:

[0115] When the server detects an anomaly, it sends a notification to the terminal using communication methods such as AWS SNS. The input is the result of the anomaly detection, and the output is the alarm notification sent to the terminal. The server analyzes the anomaly data in real time and immediately sends an alarm to the configured contacts when suspicious activity is detected.

[0116] Step 5:

[0117] The terminal provides the user with received notifications. Input is an alarm notification from the server, and output is an alarm message displayed on the terminal screen. The user can review the notification content and take prompt action based on that information. The terminal presents notifications clearly through its user interface.

[0118] Step 6:

[0119] The system sends user feedback to the server to retrain the AI ​​model. The input is the user's responses and feedback data, and the output is the updated AI model. The server takes in the received feedback and performs additional training to improve the performance of the generated AI model.

[0120] 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.

[0121] This invention combines an AI-powered sensor system for ensuring the safety of the elderly with a function to recognize the user's emotions. In addition to the conventional anomaly detection function based on environmental data, this system can analyze the user's emotional state using an emotion engine and optimize the method and content of alarms.

[0122] First, the sensors collect environmental data from the elderly person's room and surrounding area. This data is sent to a server, where an AI model is used to detect abnormal behavior. The server immediately processes the collected data and analyzes it to determine whether there has been an intruder or abnormal behavior.

[0123] Next, the emotion engine evaluates the user's emotional state based on past interaction data and real-time voice analysis. Based on this evaluation, the server considers the user's stress level and emotional state and notifies them of an alert in an appropriate manner. For example, if the user is in a high-stress state, it will prioritize notifications such as calm voice messages or connections to emergency support.

[0124] In addition, based on unusual circumstances and the user's emotions, the device can provide more personalized support information. Users can not only receive notifications of suspicious activity, but also get suggestions for stress management and relaxation in their daily lives.

[0125] For example, if a sensor detects an intruder attempting to enter through a window at night, the server identifies the anomaly, and the emotion engine selects a calm notification sound based on the user's emotional data. The device then receives this information, notifies the user, and prompts them to take the necessary action. This allows the user to process the information calmly and respond quickly.

[0126] This system aims not only to improve the safety of the living environment for the elderly, but also to contribute to the mental health care of users, providing more comprehensive protection.

[0127] The following describes the processing flow.

[0128] Step 1:

[0129] The server receives environmental data from the room and its surroundings collected by sensors. This data includes information such as movement, sound, temperature, and humidity, and is first pre-processed to verify its validity.

[0130] Step 2:

[0131] The server supplies pre-processed data to the AI ​​model, which detects abnormal patterns in real time. At this stage, it analyzes whether there are any anomalies indicating intruder activity or changes in the elderly person's physical condition.

[0132] Step 3:

[0133] If an anomaly is detected, the server uses an emotion engine to evaluate the user's emotional state. Through voice analysis and past behavioral patterns, it infers the user's current emotional state.

[0134] Step 4:

[0135] The server determines the content and method of the alarm notification based on the results of the anomaly detection and the user's emotional state. For example, if it is determined that the user is feeling stressed, it will select a calm notification sound or a voice message in a calm tone.

[0136] Step 5:

[0137] The terminal receives an alarm from the server based on the determined content and notifies the user. This notification includes detailed information, prompting the user to understand the situation and take appropriate action. For example, there is an option to notify a security company or emergency contacts.

[0138] Step 6:

[0139] The system responds based on the information provided by the user. Users not only identify anomalies and take necessary actions, but they also receive emotionally reassuring support information, which can give them a greater sense of security.

[0140] Step 7:

[0141] After all processing is complete, the server uses the acquired data and user feedback to retrain the AI ​​model and emotion engine, improving the overall accuracy of the system. This makes anomaly detection and notification more effective in the future.

[0142] (Example 2)

[0143] 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".

[0144] Ensuring the safety of the elderly in modern society is a crucial issue. However, simply collecting environmental data and detecting anomalies makes it difficult to provide appropriate responses that take into account the user's psychological state. When users are under high stress, this can lead to poor judgment and unnecessary anxiety. Therefore, more personalized alerts and information provision based on the user's emotional state are needed.

[0145] 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.

[0146] In this invention, the server includes a collection means for continuously collecting environmental information, an analysis means for analyzing the information obtained from the collection means to detect anomalies, and an emotion analysis means for analyzing past interaction information and real-time voice information to evaluate the user's emotional state. This enables the detection of abnormal behavior, as well as the provision of flexible and appropriate warnings and information according to the user's emotional state.

[0147] "Environmental information" refers to data about the surrounding physical and natural conditions, including room temperature, humidity, sound, and motion detection information.

[0148] "Collection means" refers to a mechanism or device that continuously acquires environmental information and transmits it to a server.

[0149] "Analysis means" refers to the function of executing processes and algorithms to identify anomalies based on collected environmental information.

[0150] An "anomaly" refers to a phenomenon or event that deviates from the expected normal state or pattern.

[0151] "Emotion analysis means" refers to a process or function that analyzes a user's past interaction information and real-time voice information to evaluate their emotional state.

[0152] "Alarming mechanisms" refer to systems that transmit appropriate warnings and notifications to the system based on abnormalities or the user's emotional state.

[0153] "Notification means" refers to a display, speaker, or other interface used to convey information to the user.

[0154] "Learning methods" refer to the process of improving the algorithms of analytical methods by utilizing collected information, thereby enhancing their accuracy and efficiency.

[0155] "Response" refers to the actions or feedback a user gives in response to a system notification or alert.

[0156] This invention is an AI-powered sensor system aimed at ensuring the safety and mental support of the elderly. The server acquires information such as temperature, humidity, sound, and motion detection data through multiple sensors that collect various environmental information both inside and outside the living space. This information is transmitted to the server via a network.

[0157] The server uses generative AI models (such as machine learning frameworks like TensorFlow or PyTorch) to analyze environmental information and identify abnormal behavior or intruders. This model is trained on a large amount of historical data and continuously learns to improve the accuracy of anomaly detection.

[0158] Furthermore, the server analyzes the user's voice and past interaction information using sentiment analysis tools to evaluate their emotional state. Specifically, a sentiment analysis engine based on speech recognition technology (e.g., a general-purpose sentiment analysis API) may be used.

[0159] Based on these analysis results, the server has a function to optimize alarms according to the user's stress level and emotional state. When an anomaly is detected, the alarm system provides the user with calm notifications or information prompting emergency action through voice messages and visual displays via the terminal.

[0160] The device receives optimized notification instructions and delivers information to the user in the most appropriate way. In addition, users can receive suggestions for stress management and relaxation that are useful in their daily lives through the device.

[0161] For example, if an anomaly is detected, such as a suspicious person approaching at night, the server quickly identifies the anomaly and selects a calm voice message to notify the user, preventing them from panicking. The terminal then delivers this information to the user, prompting them to take the necessary action.

[0162] An example of a prompt message would be, "Please describe in detail how the emotion recognition AI system for ensuring the safety of the elderly works." This system supports the safe and secure lives of the elderly and provides appropriate mental health care.

[0163] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0164] Step 1:

[0165] The server collects environmental information from inside and outside the elderly person's living space via sensors. Inputs include temperature, humidity, sound, and motion data. The data is transmitted to the server in real time via the network, where it is received and stored in storage. Specific operations include acquiring sensor data and transferring that data to the server.

[0166] Step 2:

[0167] The server analyzes the collected environmental information using a generative AI model. The input is the data collected in step 1. The server inputs each dataset into the AI ​​model and determines whether or not anomalies are present. The generative AI model is trained on historical data and analyzes data patterns to detect abnormal behavior. The output is an anomaly status result. The specific operation of this step involves computational processing by the AI ​​model.

[0168] Step 3:

[0169] The server evaluates the user's emotional state using emotion analysis tools. Past interaction data and real-time voice data are used as input. Voice recognition technology is used to convert the voice data into text, and the emotion analysis engine evaluates the emotional state. The output is a numerical result of the user's emotional state. Specific operations include voice data analysis and emotion scoring.

[0170] Step 4:

[0171] The server integrates the anomaly detection results and the emotional state evaluation results to generate the optimal alarm. The input is the output of steps 2 and 3. Based on the two results, the server controls the alarm system and sends an appropriate alarm instruction to the terminal. The output is the alarm instruction information. The specific operation includes data integration and alarm selection by a decision-making algorithm.

[0172] Step 5:

[0173] The terminal receives alarm instructions from the server and notifies the user. The input is the alarm instructions provided by the server. The terminal displays a message on its screen and provides audio notification through its speaker. The output is the transmission of information to the user. Specific actions include generating and displaying notification content and playing audio.

[0174] Step 6:

[0175] The user acts based on information received through the device. Input is notification information from the device. The user understands the information and, as needed, follows suggestions for stress management and relaxation. Output is the user's appropriate response. Specific actions include confirming the information and performing the suggested actions.

[0176] (Application Example 2)

[0177] 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 device 14 will be referred to as the "terminal."

[0178] In the living environments of the elderly, a challenge is to issue appropriate alarms that consider the user's emotional state while ensuring safety. Conventional systems simply detect anomalies and issue alarms, but lack consideration for the user's stress levels and emotions. Furthermore, there is a need for improved detection accuracy and the provision of personalized support information to users.

[0179] 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.

[0180] In this invention, the server includes a measurement means for continuously collecting environmental data, an analysis means for analyzing the data obtained from the measurement means and detecting anomalies, and an emotion analysis means for analyzing voice data and identifying the emotional state. This makes it possible to issue appropriate and personalized alarms and provide support information based on the user's emotional state.

[0181] "Environmental data" is a general term for various types of information acquired by sensors that record the physical conditions of the user and their surroundings.

[0182] "Measuring means" refers to a device or function for continuously acquiring and recording environmental data.

[0183] "Analysis means" refers to an algorithm or processor used to analyze data acquired by measurement means and detect deviations from a normal state.

[0184] "Transmission means" refers to a device or function that notifies users or related organizations of warnings or information based on anomalies detected by the analysis means.

[0185] "Display means" refers to a device or function for providing information to a user visually or audibly.

[0186] "Audio data" refers to acoustic information that records the user's speech and surrounding sounds.

[0187] "Emotion analysis means" refers to an algorithm or processor that uses voice data to identify the user's emotional state.

[0188] "Adjustment means" refers to a device or process for changing the output content of a transmission means based on the emotional state obtained by an emotion analysis means.

[0189] "Learning means" refers to an algorithm or process that uses collected data to improve the accuracy of analysis means and other related functions.

[0190] A "protective organization" refers to an institution or group that can take response measures in the event of an abnormal situation.

[0191] The system that realizes this invention primarily involves a server, terminal, and user, and performs anomaly detection and emotion analysis using environmental data and voice data.

[0192] The server is equipped with a measurement and analysis system that acquires data via multiple sensors that continuously collect environmental data and performs analysis on that data. Preprocessing includes data filtering and noise reduction. The analysis implements an anomaly detection algorithm using AI models, and libraries such as TensorFlow and PyTorch can be used.

[0193] The server also collects the user's voice data and converts it to text using the Google® Cloud Speech-to-Text API. Based on this text data, sentiment analysis is performed using the Google Cloud Natural Language API to identify the user's emotional state. As a result, the alarm content is adjusted based on the identified emotional state.

[0194] The terminal receives information transmitted from the server and displays warnings and information to the user. The terminal is equipped with a display and speaker, enabling the provision of both visual and audible information.

[0195] As a specific example, in a residence where elderly people stay overnight, if a window opening / closing sensor detects an unknown movement, the server immediately identifies the anomaly and simultaneously analyzes the user's voice to provide a notification that takes their emotional state into account. If the emotional state indicates anxiety, a message in a calmer tone is sent to encourage a quick and appropriate response.

[0196] Example prompts for generative AI models:

[0197] "Please tell me how to properly understand user emotions, detect security anomalies in real time, and propose the optimal response."

[0198] In this way, this system can improve the safety of the living environment for the elderly while also providing mental health care support to users.

[0199] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0200] Step 1:

[0201] The server collects environmental data by acquiring signals from various sensors within the residence (e.g., temperature, humidity, window open / closed). These acquired signals are used as input. The server records this data in a database and processes it into meaningful data through noise filtering.

[0202] Step 2:

[0203] The server analyzes the environmental data processed in Step 1 in real time. This analysis uses an AI model to detect anomalies. The input is filtered environmental data, and the output is information about the presence and type of anomalies. A machine learning model using TensorFlow is employed for this analysis.

[0204] Step 3:

[0205] The server receives the user's voice data from the device. The voice data is converted to text using the Google Cloud Speech-to-Text API. In this conversion process, the voice input is output as text data.

[0206] Step 4:

[0207] The server uses the text data obtained in step 3 as input and performs sentiment analysis using the Google Cloud Natural Language API. This identifies the user's emotional state. The output is information about the emotional state.

[0208] Step 5:

[0209] The terminal receives anomaly detection information and emotional state information from the server. Based on this information, the terminal generates alarms and messages and notifies the user through the display and speaker. The input is the output information from steps 2 and 4, and the output is the displayed alarms and audio messages.

[0210] Step 6:

[0211] Users receive notifications and provide feedback via their devices as needed. This feedback is collected by the server for the learning process. The server receives this feedback as training data and performs data processing and calculations to improve the accuracy of the AI ​​model.

[0212] 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.

[0213] 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.

[0214] 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.

[0215] [Second Embodiment]

[0216] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0217] 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.

[0218] 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).

[0219] 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.

[0220] 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.

[0221] 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).

[0222] 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.

[0223] 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.

[0224] 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.

[0225] 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.

[0226] 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.

[0227] 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".

[0228] The system according to the present invention is an AI-equipped sensor system for ensuring the safety of the elderly. This system collects various data from the environment, detects anomalies based on that data, and notifies necessary alarms. Furthermore, it is possible to improve detection accuracy by accumulating data using machine learning technology.

[0229] First, sensors placed in and around the living space continuously acquire environmental data such as motion, sound, temperature, and humidity. The data collected by the sensors is sent to a server, which then analyzes the data.

[0230] The server uses an AI model to analyze the acquired data in real time and identify abnormal behavior and patterns. For example, if irregular movements or differences from normal activity are detected during a specific time period, it is immediately judged as abnormal.

[0231] When an anomaly is detected, the server uses notification methods to send an alert to pre-configured family members or security companies. Specifically, users are notified via voice alarms, email notifications, or push notifications through a dedicated app via their devices. Upon receiving the alert, users can take prompt action to ensure the safety of the elderly person.

[0232] Furthermore, the server retrains its AI model based on collected data and user feedback to improve the accuracy of its identification methods. This process reduces false alarms and enables more accurate anomaly detection.

[0233] For example, if an intruder attempts to enter a property at night by opening a window, the sensor will detect the movement and sound, and the server will immediately identify it as abnormal activity. An automatic alarm notification will then be sent to family members or designated security agencies, enabling prompt action.

[0234] Ultimately, this system provides safety and peace of mind to the elderly and their families by monitoring their living environment and immediately notifying them of any abnormal situations.

[0235] The following describes the processing flow.

[0236] Step 1:

[0237] The server receives environmental data collected by the sensors. This data includes information such as movement, sound, temperature, and humidity over time. The server temporarily stores the received data and prepares it for preprocessing.

[0238] Step 2:

[0239] The server performs preprocessing on the received data, such as noise reduction and filtering. This process removes unnecessary data and improves the accuracy of the information needed for analysis.

[0240] Step 3:

[0241] The server inputs pre-processed data into an AI model and performs real-time analysis. The AI ​​model is trained on historical data and has the ability to identify patterns of suspicious intrusion and abnormal behavior.

[0242] Step 4:

[0243] If the AI ​​model detects an anomaly, the server immediately activates notification mechanisms and issues an alarm. The alarm is sent to registered devices as an email or app notification.

[0244] Step 5:

[0245] The terminal displays a notification to the user when it receives an alarm from the server. The user checks the notification and considers taking immediate action. If necessary, they can contact the elderly person directly or notify the security company.

[0246] Step 6:

[0247] The server uses the data collected after notification, along with user feedback, to analyze and retrain the AI ​​model for improved accuracy. This will improve the accuracy of anomaly detection in subsequent instances.

[0248] (Example 1)

[0249] 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."

[0250] The present invention relates to a system for ensuring the safety of the elderly, and more particularly aims to provide a highly accurate system that can collect environmental information in real time, immediately detect anomalies, and issue alarms. More specifically, the objective is to improve the accuracy of anomaly detection, reduce false alarms, and enable rapid notification to users and security agencies.

[0251] 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.

[0252] In this invention, the server includes sensing means for continuously collecting environmental information, detection means for analyzing the information obtained from the sensing means to detect anomalies, and notification means for issuing an alarm based on the anomalies detected by the detection means. This makes it possible to monitor the living environment of elderly people and enable a rapid response in the event of an anomaly.

[0253] "Environmental information" is a general term for data that indicates surrounding elements such as temperature, humidity, sound, and movement, acquired within a specific area.

[0254] "Sensing means" refers to devices and sensors for continuously acquiring environmental information, which allows for real-time data collection.

[0255] "Analysis" is the act or process of processing collected data based on certain criteria to identify anomalies or patterns.

[0256] "Detection means" refers to techniques or methods for detecting anomalies from analyzed data.

[0257] "Abnormal" refers to behavior or a state that deviates from normal patterns or standards, indicating a situation that requires attention.

[0258] "Notification means" refers to a function or device that issues alarms or notifications based on detected abnormal information.

[0259] "Notification means" refers to the means or methods used to inform users of information transmitted by notification means.

[0260] "Analysis improvement means" refers to techniques or methods for improving the accuracy of detection means using collected information and feedback.

[0261] "Notification means" refers to a function that immediately transmits information to security agencies or designated personnel when an anomaly is detected.

[0262] The system according to the present invention is an AI-equipped sensor system designed to ensure the safety of the elderly. It mainly comprises the following elements:

[0263] The device includes multiple sensors installed in the living space. These sensors include motion sensors, sound sensors, and temperature / humidity sensors, and this hardware is used to continuously acquire environmental information. Motion sensors detect human movement, sound sensors capture changes in ambient sound, and temperature / humidity sensors monitor the temperature and humidity of the environment.

[0264] The server receives environmental information transmitted from terminals in real time and uses a generative AI model to analyze the data. This AI model is a powerful tool for learning normal behavior patterns and detecting abnormal patterns. In particular, it utilizes deep learning technology to perform highly accurate anomaly detection based on the obtained data.

[0265] The server also has a function to alert users using notification methods when it detects an anomaly. These notification methods include using the terminal's speaker as an audio alarm or sending notifications to the user's smart device. This allows users to immediately understand the location and time of the anomaly and take appropriate action.

[0266] Furthermore, the server continuously learns from the collected information through analysis and improvement mechanisms, thereby improving the accuracy of the detection mechanisms. User feedback is crucial data for the system to reduce false alarms and perform more precise anomaly detection.

[0267] For example, if a sensor detects a suspicious sound in the middle of the night, the server analyzes this data as an anomaly and immediately sends a push notification to the user's smartphone. At this time, the user can check the status of the room via the app.

[0268] An example of a prompt message could be, "Please explain what kind of data processing is necessary to detect abnormalities in the living environment of elderly people and provide real-time notifications." By inputting such prompt messages into the AI ​​generation model, guidelines can be obtained to ensure that the above-mentioned system is operated safely.

[0269] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0270] Step 1:

[0271] The device collects environmental information using various sensors installed in the living space. Specifically, a motion sensor detects human movement and records that movement information. A sound sensor captures changes in ambient sound, and a temperature and humidity sensor obtains current temperature and humidity data. The input is raw data obtained from each sensor, and the output is formatted environmental data sent to the server.

[0272] Step 2:

[0273] The server receives environmental data transmitted from terminals in real time. The input is environmental data from the terminals, and the output is pre-processed data for anomaly detection. Upon receiving the data, the server classifies each data type and formats it into a format suitable for analysis. This process enables efficient data analysis.

[0274] Step 3:

[0275] The server uses a generative AI model to analyze preprocessed data and detect anomalies. The input is preprocessed data, and the output is the analysis result indicating the presence or absence of anomalies. Specifically, the AI ​​model compares current data with past data to find deviations from normal patterns. The generative AI model uses deep learning techniques and performs complex mathematical calculations to improve the accuracy of anomaly detection.

[0276] Step 4:

[0277] If the server detects an anomaly, it will use a notification system to alert the user. The input is the analysis result of the anomaly detection, and the output is the information sent to the user's device as an alarm notification. Specifically, the server instructs the terminal to emit an audio alarm and also sends a push notification to the user's smartphone.

[0278] Step 5:

[0279] The user takes appropriate action in response to the received alarm. The input is the alarm notification, and the output is the action the user should take. The user launches a dedicated app and checks real-time video and detailed information to determine the appropriate course of action. Specifically, the user checks camera footage through the app and, if necessary, rushes to the scene or contacts relevant parties.

[0280] Step 6:

[0281] The server learns from collected data and user feedback through analytical methods to improve the generated AI model, thereby enhancing the system's accuracy. The input is accumulated data and feedback information, and the output is the updated AI model. Specifically, the server analyzes data that resulted in false alarms, readjusts the model, and improves the success rate of anomaly detection in subsequent instances.

[0282] (Application Example 1)

[0283] Next, Application Example 1 will be described. In the following description, the data processing device 12 is referred to as a "server", and the smart glasses 214 are referred to as a "terminal".

[0284] In the homes of the elderly, it is important to quickly detect abnormal situations in daily life and ensure safety. However, in conventional systems, it is difficult to provide security information to the recipient in real time and prompt immediate response, so a more flexible and highly immediate monitoring system is needed.

[0285] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0286] In this invention, the server includes a measurement means for continuously collecting environmental information, a detection means for analyzing the information obtained from the measurement means and identifying abnormalities, a notification mechanism for issuing an alarm based on the abnormalities identified by the detection means, a communication means for providing an application for installation on a smart device, and a cooperation means for analyzing abnormalities in real time and transmitting a notification according to the abnormalities to the smart device. Thereby, it becomes possible to immediately detect abnormalities in the living environment of the elderly and quickly and accurately notify the recipient.

[0287] "Environmental information" refers to various data such as temperature, humidity, movement, and sound related to the surrounding situation.

[0288] "Measurement means" refers to a device or method for continuously acquiring environmental information.

[0289] "Analysis" refers to performing the processing necessary to analyze the acquired information in detail and identify abnormalities.

[0290] "Identification means" refers to a technique or model for detecting abnormalities from the analyzed information.

[0291] An "alarm" refers to a visual, auditory, or digital notification method used to alert someone when an anomaly is detected.

[0292] A "notification mechanism" refers to a system or device for issuing an alarm.

[0293] A "receiver" refers to a person who receives an alert from a notification system and uses the information.

[0294] A "notification mechanism" refers to a system or method for providing data to recipients.

[0295] A "learning mechanism" refers to a learning method or series of processes used to improve a system's performance and identification accuracy based on collected information.

[0296] A "smart device" refers to an electronic device that has information processing capabilities and can connect to a network.

[0297] "Communication methods" refer to methods and protocols for transmitting information to other devices or systems.

[0298] "Coordination means" refers to a method of coordinating between systems to transmit abnormalities to smart devices in a borderless manner and to prompt appropriate responses.

[0299] In this application, the system involves a server running a program that continuously collects environmental information from various sensors installed in the home. The acquired environmental information is temporarily stored in a database for appropriate analysis. In the analysis step, the server implements an identification method to identify anomalies using machine learning algorithms. This is achieved by using machine learning libraries such as TensorFlow to extract features from the collected data and build an anomaly detection model. Furthermore, when the server detects an anomaly in real time, it sends an alert notification to the user's smart devices using communication methods such as AWS SNS.

[0300] Upon receiving a notification, users can check the situation and take necessary actions through a dedicated app on their smartphone or tablet. This application visually displays information about anomaly detection, supporting users in responding quickly and accurately. User feedback is automatically sent to the server and used to improve the anomaly detection algorithm. In this way, the system's accuracy continuously improves through learning.

[0301] As a concrete example, if suspicious activity is detected in an elderly person's home at night, the server analyzes the sensor information and immediately recognizes it as an anomaly. This triggers a notification to the user's smartphone, allowing them to quickly understand the situation and take action. An example of a prompt message to ensure the safety of the elderly in this way is as follows: "If suspicious noises are detected in an elderly person's home late at night, please tell me how to notify them and how to support a quick response."

[0302] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0303] Step 1:

[0304] Sensors continuously collect environmental information. The sensors acquire data on ambient temperature, humidity, sound, and motion, and transmit this data to a server. The input is environmental state data, and the output is raw data sent to the server. In this process, physical data is captured by the sensors and transmitted to the server via the network.

[0305] Step 2:

[0306] The server stores the received data in the database. The input is the raw data sent in step 1, and the output is the data stored in the database. The server uses a database management system for efficient data storage and access.

[0307] Step 3:

[0308] The server analyzes the stored data and identifies anomalies. Specifically, it uses a generative AI model to analyze data patterns and detect movements and sounds that are different from normal. The input is environmental data obtained from the database, and the output is the result of anomaly detection. The server executes a machine learning algorithm to perform pattern recognition and anomaly judgment.

[0309] Step 4:

[0310] When the server detects an anomaly, it sends a notification to the terminal using a communication means such as AWS SNS. The input is the result of anomaly detection, and the output is an alarm notification to the terminal. The server analyzes the anomaly data in real time and immediately issues an alarm to the designated contacts when suspicious activities are detected.

[0311] Step 5:

[0312] The terminal provides the received notification to the user. The input is the alarm notification from the server, and the output is an alarm message on the terminal screen. The user can check the notified content and make a prompt response based on that information. The terminal presents the notification clearly through the user interface.

[0313] Step 6:

[0314] Send the feedback from the user to the server to perform re-learning of the AI model. The input is the user's response or feedback data, and the output is the updated AI model. The server incorporates the received feedback and performs additional learning to improve the performance of the generative AI model.

[0315] Furthermore, an emotion engine for estimating the user's emotion may be combined. That is, the specific processing unit 290 may estimate the user's emotion using the emotion recognition model 59 and perform specific processing using the user's emotion.

[0316] This invention combines an AI-powered sensor system for ensuring the safety of the elderly with a function to recognize the user's emotions. In addition to the conventional anomaly detection function based on environmental data, this system can analyze the user's emotional state using an emotion engine and optimize the method and content of alarms.

[0317] First, the sensors collect environmental data from the elderly person's room and surrounding area. This data is sent to a server, where an AI model is used to detect abnormal behavior. The server immediately processes the collected data and analyzes it to determine whether there has been an intruder or abnormal behavior.

[0318] Next, the emotion engine evaluates the user's emotional state based on past interaction data and real-time voice analysis. Based on this evaluation, the server considers the user's stress level and emotional state and notifies them of an alert in an appropriate manner. For example, if the user is in a high-stress state, it will prioritize notifications such as calm voice messages or connections to emergency support.

[0319] In addition, based on unusual circumstances and the user's emotions, the device can provide more personalized support information. Users can not only receive notifications of suspicious activity, but also get suggestions for stress management and relaxation in their daily lives.

[0320] For example, if a sensor detects an intruder attempting to enter through a window at night, the server identifies the anomaly, and the emotion engine selects a calm notification sound based on the user's emotional data. The device then receives this information, notifies the user, and prompts them to take the necessary action. This allows the user to process the information calmly and respond quickly.

[0321] This system aims not only to improve the safety of the living environment for the elderly, but also to contribute to the mental health care of users, providing more comprehensive protection.

[0322] The following describes the processing flow.

[0323] Step 1:

[0324] The server receives environmental data from the room and its surroundings collected by sensors. This data includes information such as movement, sound, temperature, and humidity, and is first pre-processed to verify its validity.

[0325] Step 2:

[0326] The server supplies pre-processed data to the AI ​​model, which detects abnormal patterns in real time. At this stage, it analyzes whether there are any anomalies indicating intruder activity or changes in the elderly person's physical condition.

[0327] Step 3:

[0328] If an anomaly is detected, the server uses an emotion engine to evaluate the user's emotional state. Through voice analysis and past behavioral patterns, it infers the user's current emotional state.

[0329] Step 4:

[0330] The server determines the content and method of the alarm notification based on the results of the anomaly detection and the user's emotional state. For example, if it is determined that the user is feeling stressed, it will select a calm notification sound or a voice message in a calm tone.

[0331] Step 5:

[0332] The terminal receives an alarm from the server based on the determined content and notifies the user. This notification includes detailed information, prompting the user to understand the situation and take appropriate action. For example, there is an option to notify a security company or emergency contacts.

[0333] Step 6:

[0334] The system responds based on the information provided by the user. Users not only identify anomalies and take necessary actions, but they also receive emotionally reassuring support information, which can give them a greater sense of security.

[0335] Step 7:

[0336] After all processing is complete, the server uses the acquired data and user feedback to retrain the AI ​​model and emotion engine, improving the overall accuracy of the system. This makes anomaly detection and notification more effective in the future.

[0337] (Example 2)

[0338] 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".

[0339] Ensuring the safety of the elderly in modern society is a crucial issue. However, simply collecting environmental data and detecting anomalies makes it difficult to provide appropriate responses that take into account the user's psychological state. When users are under high stress, this can lead to poor judgment and unnecessary anxiety. Therefore, more personalized alerts and information provision based on the user's emotional state are needed.

[0340] 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.

[0341] In this invention, the server includes a collection means for continuously collecting environmental information, an analysis means for analyzing the information obtained from the collection means to detect anomalies, and an emotion analysis means for analyzing past interaction information and real-time voice information to evaluate the user's emotional state. This enables the detection of abnormal behavior, as well as the provision of flexible and appropriate warnings and information according to the user's emotional state.

[0342] "Environmental information" refers to data about the surrounding physical and natural conditions, including room temperature, humidity, sound, and motion detection information.

[0343] "Collection means" refers to a mechanism or device that continuously acquires environmental information and transmits it to a server.

[0344] "Analysis means" refers to the function of executing processes and algorithms to identify anomalies based on collected environmental information.

[0345] An "anomaly" refers to a phenomenon or event that deviates from the expected normal state or pattern.

[0346] "Emotion analysis means" refers to a process or function that analyzes a user's past interaction information and real-time voice information to evaluate their emotional state.

[0347] "Alarming mechanisms" refer to systems that transmit appropriate warnings and notifications to the system based on abnormalities or the user's emotional state.

[0348] "Notification means" refers to a display, speaker, or other interface used to convey information to the user.

[0349] "Learning methods" refer to the process of improving the algorithms of analytical methods by utilizing collected information, thereby enhancing their accuracy and efficiency.

[0350] "Response" refers to the actions or feedback a user gives in response to a system notification or alert.

[0351] This invention is an AI-powered sensor system aimed at ensuring the safety and mental support of the elderly. The server acquires information such as temperature, humidity, sound, and motion detection data through multiple sensors that collect various environmental information both inside and outside the living space. This information is transmitted to the server via a network.

[0352] The server uses generative AI models (such as machine learning frameworks like TensorFlow or PyTorch) to analyze environmental information and identify abnormal behavior or intruders. This model is trained on a large amount of historical data and continuously learns to improve the accuracy of anomaly detection.

[0353] Furthermore, the server analyzes the user's voice and past interaction information using sentiment analysis tools to evaluate their emotional state. Specifically, a sentiment analysis engine based on speech recognition technology (e.g., a general-purpose sentiment analysis API) may be used.

[0354] Based on these analysis results, the server has a function to optimize alarms according to the user's stress level and emotional state. When an anomaly is detected, the alarm system provides the user with calm notifications or information prompting emergency action through voice messages and visual displays via the terminal.

[0355] The device receives optimized notification instructions and delivers information to the user in the most appropriate way. In addition, users can receive suggestions for stress management and relaxation that are useful in their daily lives through the device.

[0356] For example, if an anomaly is detected, such as a suspicious person approaching at night, the server quickly identifies the anomaly and selects a calm voice message to notify the user, preventing them from panicking. The terminal then delivers this information to the user, prompting them to take the necessary action.

[0357] An example of a prompt message would be, "Please describe in detail how the emotion recognition AI system for ensuring the safety of the elderly works." This system supports the safe and secure lives of the elderly and provides appropriate mental health care.

[0358] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0359] Step 1:

[0360] The server collects environmental information from inside and outside the elderly person's living space via sensors. Inputs include temperature, humidity, sound, and motion data. The data is transmitted to the server in real time via the network, where it is received and stored in storage. Specific operations include acquiring sensor data and transferring that data to the server.

[0361] Step 2:

[0362] The server analyzes the collected environmental information using a generative AI model. The input is the data collected in step 1. The server inputs each dataset into the AI ​​model and determines whether or not anomalies are present. The generative AI model is trained on historical data and analyzes data patterns to detect abnormal behavior. The output is an anomaly status result. The specific operation of this step involves computational processing by the AI ​​model.

[0363] Step 3:

[0364] The server evaluates the user's emotional state using emotion analysis tools. Past interaction data and real-time voice data are used as input. Voice recognition technology is used to convert the voice data into text, and the emotion analysis engine evaluates the emotional state. The output is a numerical result of the user's emotional state. Specific operations include voice data analysis and emotion scoring.

[0365] Step 4:

[0366] The server integrates the anomaly detection results and the emotional state evaluation results to generate the optimal alarm. The input is the output of steps 2 and 3. Based on the two results, the server controls the alarm system and sends an appropriate alarm instruction to the terminal. The output is the alarm instruction information. The specific operation includes data integration and alarm selection by a decision-making algorithm.

[0367] Step 5:

[0368] The terminal receives alarm instructions from the server and notifies the user. The input is the alarm instructions provided by the server. The terminal displays a message on its screen and provides audio notification through its speaker. The output is the transmission of information to the user. Specific actions include generating and displaying notification content and playing audio.

[0369] Step 6:

[0370] The user acts based on information received through the device. Input is notification information from the device. The user understands the information and, as needed, follows suggestions for stress management and relaxation. Output is the user's appropriate response. Specific actions include confirming the information and performing the suggested actions.

[0371] (Application Example 2)

[0372] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0373] In the living environments of the elderly, a challenge is to issue appropriate alarms that consider the user's emotional state while ensuring safety. Conventional systems simply detect anomalies and issue alarms, but lack consideration for the user's stress levels and emotions. Furthermore, there is a need for improved detection accuracy and the provision of personalized support information to users.

[0374] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0375] In this invention, the server includes a measurement means for continuously collecting environmental data, an analysis means for analyzing the data obtained from the measurement means and detecting anomalies, and an emotion analysis means for analyzing voice data and identifying the emotional state. This makes it possible to issue appropriate and personalized alarms and provide support information based on the user's emotional state.

[0376] "Environmental data" is a general term for various types of information acquired by sensors that record the physical conditions of the user and their surroundings.

[0377] "Measuring means" refers to a device or function for continuously acquiring and recording environmental data.

[0378] "Analysis means" refers to an algorithm or processor used to analyze data acquired by measurement means and detect deviations from a normal state.

[0379] "Transmission means" refers to a device or function that notifies users or related organizations of warnings or information based on anomalies detected by the analysis means.

[0380] "Display means" refers to a device or function for providing information to a user visually or audibly.

[0381] "Audio data" refers to acoustic information that records the user's speech and surrounding sounds.

[0382] "Emotion analysis means" refers to an algorithm or processor that uses voice data to identify the user's emotional state.

[0383] "Adjustment means" refers to a device or process for changing the output content of a transmission means based on the emotional state obtained by an emotion analysis means.

[0384] "Learning means" refers to an algorithm or process that uses collected data to improve the accuracy of analysis means and other related functions.

[0385] A "protective organization" refers to an institution or group that can take response measures in the event of an abnormal situation.

[0386] The system that realizes this invention primarily involves a server, terminal, and user, and performs anomaly detection and emotion analysis using environmental data and voice data.

[0387] The server is equipped with a measurement and analysis system that acquires data via multiple sensors that continuously collect environmental data and performs analysis on that data. Preprocessing includes data filtering and noise reduction. The analysis implements an anomaly detection algorithm using AI models, and libraries such as TensorFlow and PyTorch can be used.

[0388] The server also collects the user's voice data and converts it to text using the Google Cloud Speech-to-Text API. Based on this text data, sentiment analysis is performed using the Google Cloud Natural Language API to identify the user's emotional state. As a result, the alarm content is adjusted based on the identified emotional state.

[0389] The terminal receives information transmitted from the server and displays warnings and information to the user. The terminal is equipped with a display and speaker, enabling the provision of both visual and audible information.

[0390] As a specific example, in a residence where elderly people stay overnight, if a window opening / closing sensor detects an unknown movement, the server immediately identifies the anomaly and simultaneously analyzes the user's voice to provide a notification that takes their emotional state into account. If the emotional state indicates anxiety, a message in a calmer tone is sent to encourage a quick and appropriate response.

[0391] Example prompts for generative AI models:

[0392] "Please tell me how to properly understand user emotions, detect security anomalies in real time, and propose the optimal response."

[0393] In this way, this system can improve the safety of the living environment for the elderly while also providing mental health care support to users.

[0394] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0395] Step 1:

[0396] The server collects environmental data by acquiring signals from various sensors within the residence (e.g., temperature, humidity, window open / closed). These acquired signals are used as input. The server records this data in a database and processes it into meaningful data through noise filtering.

[0397] Step 2:

[0398] The server analyzes the environmental data processed in Step 1 in real time. This analysis uses an AI model to detect anomalies. The input is filtered environmental data, and the output is information about the presence and type of anomalies. A machine learning model using TensorFlow is employed for this analysis.

[0399] Step 3:

[0400] The server receives the user's voice data from the device. The voice data is converted to text using the Google Cloud Speech-to-Text API. In this conversion process, the voice input is output as text data.

[0401] Step 4:

[0402] The server uses the text data obtained in step 3 as input and performs sentiment analysis using the Google Cloud Natural Language API. This identifies the user's emotional state. The output is information about the emotional state.

[0403] Step 5:

[0404] The terminal receives anomaly detection information and emotional state information from the server. Based on this information, the terminal generates alarms and messages and notifies the user through the display and speaker. The input is the output information from steps 2 and 4, and the output is the displayed alarms and audio messages.

[0405] Step 6:

[0406] Users receive notifications and provide feedback via their devices as needed. This feedback is collected by the server for the learning process. The server receives this feedback as training data and performs data processing and calculations to improve the accuracy of the AI ​​model.

[0407] 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.

[0408] 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.

[0409] 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.

[0410] [Third Embodiment]

[0411] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0412] 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.

[0413] 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).

[0414] 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.

[0415] 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.

[0416] 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).

[0417] 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.

[0418] 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.

[0419] 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.

[0420] 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.

[0421] 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.

[0422] 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".

[0423] The system according to the present invention is an AI-equipped sensor system for ensuring the safety of the elderly. This system collects various data from the environment, detects anomalies based on that data, and notifies necessary alarms. Furthermore, it is possible to improve detection accuracy by accumulating data using machine learning technology.

[0424] First, sensors placed in and around the living space continuously acquire environmental data such as motion, sound, temperature, and humidity. The data collected by the sensors is sent to a server, which then analyzes the data.

[0425] The server uses an AI model to analyze the acquired data in real time and identify abnormal behavior and patterns. For example, if irregular movements or differences from normal activity are detected during a specific time period, it is immediately judged as abnormal.

[0426] When an anomaly is detected, the server uses notification methods to send an alert to pre-configured family members or security companies. Specifically, users are notified via voice alarms, email notifications, or push notifications through a dedicated app via their devices. Upon receiving the alert, users can take prompt action to ensure the safety of the elderly person.

[0427] Furthermore, the server retrains its AI model based on collected data and user feedback to improve the accuracy of its identification methods. This process reduces false alarms and enables more accurate anomaly detection.

[0428] For example, if an intruder attempts to enter by opening a window at night, the sensor will detect the movement and sound, and the server will immediately identify it as abnormal activity. An automatic alarm notification will then be sent to family members or designated security agencies, allowing for prompt action.

[0429] Ultimately, this system provides safety and peace of mind to the elderly and their families by monitoring their living environment and immediately notifying them of any abnormal situations.

[0430] The following describes the processing flow.

[0431] Step 1:

[0432] The server receives environmental data collected by the sensors. This data includes information such as movement, sound, temperature, and humidity over time. The server temporarily stores the received data and prepares it for preprocessing.

[0433] Step 2:

[0434] The server performs preprocessing on the received data, such as noise reduction and filtering. This process removes unnecessary data and improves the accuracy of the information needed for analysis.

[0435] Step 3:

[0436] The server inputs pre-processed data into an AI model and performs real-time analysis. The AI ​​model is trained on historical data and has the ability to identify patterns of suspicious intrusion and abnormal behavior.

[0437] Step 4:

[0438] If the AI ​​model detects an anomaly, the server immediately activates notification mechanisms and issues an alarm. The alarm is sent to registered devices as an email or app notification.

[0439] Step 5:

[0440] The terminal displays a notification to the user when it receives an alarm from the server. The user checks the notification and considers taking immediate action. If necessary, they can contact the elderly person directly or notify the security company.

[0441] Step 6:

[0442] The server uses the data collected after notification, along with user feedback, to analyze and retrain the AI ​​model for improved accuracy. This will improve the accuracy of anomaly detection in subsequent instances.

[0443] (Example 1)

[0444] 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."

[0445] The present invention relates to a system for ensuring the safety of the elderly, and more particularly aims to provide a highly accurate system that can collect environmental information in real time, immediately detect anomalies, and issue alarms. More specifically, the objective is to improve the accuracy of anomaly detection, reduce false alarms, and enable rapid notification to users and security agencies.

[0446] 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.

[0447] In this invention, the server includes sensing means for continuously collecting environmental information, detection means for analyzing the information obtained from the sensing means to detect anomalies, and notification means for issuing an alarm based on the anomalies detected by the detection means. This makes it possible to monitor the living environment of elderly people and enable a rapid response in the event of an anomaly.

[0448] "Environmental information" is a general term for data that indicates surrounding elements such as temperature, humidity, sound, and movement, acquired within a specific area.

[0449] "Sensing means" refers to devices and sensors for continuously acquiring environmental information, which allows for real-time data collection.

[0450] "Analysis" is the act or process of processing collected data based on certain criteria to identify anomalies or patterns.

[0451] "Detection means" refers to techniques or methods for detecting anomalies from analyzed data.

[0452] "Abnormal" refers to behavior or a state that deviates from normal patterns or standards, indicating a situation that requires attention.

[0453] "Notification means" refers to a function or device that issues alarms or notifications based on detected abnormal information.

[0454] "Notification means" refers to the means or methods used to inform users of information transmitted by notification means.

[0455] "Analysis improvement means" refers to techniques or methods for improving the accuracy of detection means using collected information and feedback.

[0456] "Notification means" refers to a function that immediately transmits information to security agencies or designated personnel when an anomaly is detected.

[0457] The system according to the present invention is an AI-equipped sensor system designed to ensure the safety of the elderly. It mainly comprises the following elements:

[0458] The device includes multiple sensors installed in the living space. These sensors include motion sensors, sound sensors, and temperature / humidity sensors, and this hardware is used to continuously acquire environmental information. Motion sensors detect human movement, sound sensors capture changes in ambient sound, and temperature / humidity sensors monitor the temperature and humidity of the environment.

[0459] The server receives environmental information transmitted from terminals in real time and uses a generative AI model to analyze the data. This AI model is a powerful tool for learning normal behavior patterns and detecting abnormal patterns. In particular, it utilizes deep learning technology to perform highly accurate anomaly detection based on the obtained data.

[0460] The server also has a function to alert users using notification methods when it detects an anomaly. These notification methods include using the terminal's speaker as an audio alarm or sending notifications to the user's smart device. This allows users to immediately understand the location and time of the anomaly and take appropriate action.

[0461] Furthermore, the server continuously learns from the collected information through analysis and improvement mechanisms, thereby improving the accuracy of the detection mechanisms. User feedback is crucial data for the system to reduce false alarms and perform more precise anomaly detection.

[0462] For example, if a sensor detects a suspicious sound in the middle of the night, the server analyzes this data as an anomaly and immediately sends a push notification to the user's smartphone. At this time, the user can check the status of the room via the app.

[0463] An example of a prompt message could be, "Please explain what kind of data processing is necessary to detect abnormalities in the living environment of elderly people and provide real-time notifications." By inputting such prompt messages into the AI ​​generation model, guidelines can be obtained to ensure that the above-mentioned system is operated safely.

[0464] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0465] Step 1:

[0466] The device collects environmental information using various sensors installed in the living space. Specifically, a motion sensor detects human movement and records that movement information. A sound sensor captures changes in ambient sound, and a temperature and humidity sensor obtains current temperature and humidity data. The input is raw data obtained from each sensor, and the output is formatted environmental data sent to the server.

[0467] Step 2:

[0468] The server receives environmental data transmitted from terminals in real time. The input is environmental data from the terminals, and the output is pre-processed data for anomaly detection. Upon receiving the data, the server classifies each data type and formats it into a format suitable for analysis. This process enables efficient data analysis.

[0469] Step 3:

[0470] The server uses a generative AI model to analyze preprocessed data and detect anomalies. The input is preprocessed data, and the output is the analysis result indicating the presence or absence of anomalies. Specifically, the AI ​​model compares current data with past data to find deviations from normal patterns. The generative AI model uses deep learning techniques and performs complex mathematical calculations to improve the accuracy of anomaly detection.

[0471] Step 4:

[0472] If the server detects an anomaly, it will use a notification system to alert the user. The input is the analysis result of the anomaly detection, and the output is the information sent to the user's device as an alarm notification. Specifically, the server instructs the terminal to emit an audio alarm and also sends a push notification to the user's smartphone.

[0473] Step 5:

[0474] The user takes appropriate action in response to the received alarm. The input is the alarm notification, and the output is the action the user should take. The user launches a dedicated app and checks real-time video and detailed information to determine the appropriate course of action. Specifically, the user checks camera footage through the app and, if necessary, rushes to the scene or contacts relevant parties.

[0475] Step 6:

[0476] The server learns from collected data and user feedback through analytical methods to improve the generated AI model, thereby enhancing the system's accuracy. The input is accumulated data and feedback information, and the output is the updated AI model. Specifically, the server analyzes data that resulted in false alarms, readjusts the model, and improves the success rate of anomaly detection in subsequent instances.

[0477] (Application Example 1)

[0478] 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."

[0479] In elderly households, it is crucial to quickly detect abnormal situations in daily life and ensure safety. However, conventional systems struggle to provide security information to recipients in real time and prompt immediate action, thus creating a need for a more flexible and responsive monitoring system.

[0480] 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.

[0481] In this invention, the server includes measuring means for continuously collecting environmental information, detection means for analyzing the information obtained from the measuring means and identifying anomalies, a notification mechanism for issuing alarms based on the anomalies identified by the detection means, communication means for providing an application for installation on smart devices, and cooperation means for analyzing anomalies in real time and sending notifications to smart devices corresponding to the anomalies. This makes it possible to immediately detect anomalies in the living environment of elderly people and to quickly and accurately notify recipients.

[0482] "Environmental information" refers to various data related to the surrounding conditions, such as temperature, humidity, movement, and sound.

[0483] "Measuring means" refers to devices and methods for continuously acquiring environmental information.

[0484] "Analysis" refers to the process of thoroughly analyzing acquired information and performing necessary steps to identify anomalies.

[0485] "Identification means" refers to methods or models for detecting anomalies from analyzed information.

[0486] An "alarm" refers to a visual, auditory, or digital notification method used to alert someone when an anomaly is detected.

[0487] A "notification mechanism" refers to a system or device for issuing an alarm.

[0488] A "receiver" refers to a person who receives an alert from a notification system and uses the information.

[0489] A "notification mechanism" refers to a system or method for providing data to recipients.

[0490] A "learning mechanism" refers to a learning method or series of processes used to improve a system's performance and identification accuracy based on collected information.

[0491] A "smart device" refers to an electronic device that has information processing capabilities and can connect to a network.

[0492] "Communication methods" refer to methods and protocols for transmitting information to other devices or systems.

[0493] "Coordination means" refers to a method of coordinating between systems to transmit abnormalities to smart devices in a borderless manner and to prompt appropriate responses.

[0494] In this application, the system involves a server running a program that continuously collects environmental information from various sensors installed in the home. The acquired environmental information is temporarily stored in a database for appropriate analysis. In the analysis step, the server implements an identification method to identify anomalies using machine learning algorithms. This is achieved by using machine learning libraries such as TensorFlow to extract features from the collected data and build an anomaly detection model. Furthermore, when the server detects an anomaly in real time, it sends an alert notification to the user's smart devices using communication methods such as AWS SNS.

[0495] Upon receiving a notification, users can check the situation and take necessary actions through a dedicated app on their smartphone or tablet. This application visually displays information about anomaly detection, supporting users in responding quickly and accurately. User feedback is automatically sent to the server and used to improve the anomaly detection algorithm. In this way, the system's accuracy continuously improves through learning.

[0496] As a concrete example, if suspicious activity is detected in an elderly person's home at night, the server analyzes the sensor information and immediately recognizes it as an anomaly. This triggers a notification to the user's smartphone, allowing them to quickly understand the situation and take action. An example of a prompt message to ensure the safety of the elderly in this way is as follows: "If suspicious noises are detected in an elderly person's home late at night, please tell me how to notify them and how to support a quick response."

[0497] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0498] Step 1:

[0499] Sensors continuously collect environmental information. The sensors acquire data on ambient temperature, humidity, sound, and motion, and transmit this data to a server. The input is environmental state data, and the output is raw data sent to the server. In this process, physical data is captured by the sensors and transmitted to the server via the network.

[0500] Step 2:

[0501] The server stores the received data in the database. The input is the raw data sent in step 1, and the output is the data stored in the database. The server uses a database management system for efficient data storage and access.

[0502] Step 3:

[0503] The server analyzes stored data and identifies anomalies. Specifically, it uses a generative AI model to analyze data patterns and detect unusual movements or sounds. The input is environmental data obtained from a database, and the output is the result of anomaly detection. The server executes machine learning algorithms to perform pattern recognition and anomaly detection.

[0504] Step 4:

[0505] When the server detects an anomaly, it sends a notification to the terminal using communication methods such as AWS SNS. The input is the result of the anomaly detection, and the output is the alarm notification sent to the terminal. The server analyzes the anomaly data in real time and immediately sends an alarm to the configured contacts when suspicious activity is detected.

[0506] Step 5:

[0507] The terminal provides the user with received notifications. Input is an alarm notification from the server, and output is an alarm message displayed on the terminal screen. The user can review the notification content and take prompt action based on that information. The terminal presents notifications clearly through its user interface.

[0508] Step 6:

[0509] The system sends user feedback to the server to retrain the AI ​​model. The input is the user's responses and feedback data, and the output is the updated AI model. The server takes in the received feedback and performs additional training to improve the performance of the generated AI model.

[0510] 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.

[0511] This invention combines an AI-powered sensor system for ensuring the safety of the elderly with a function to recognize the user's emotions. In addition to the conventional anomaly detection function based on environmental data, this system can analyze the user's emotional state using an emotion engine and optimize the method and content of alarms.

[0512] First, the sensors collect environmental data from the elderly person's room and surrounding area. This data is sent to a server, where an AI model is used to detect abnormal behavior. The server immediately processes the collected data and analyzes it to determine whether there has been an intruder or abnormal behavior.

[0513] Next, the emotion engine evaluates the user's emotional state based on past interaction data and real-time voice analysis. Based on this evaluation, the server considers the user's stress level and emotional state and notifies them of an alert in an appropriate manner. For example, if the user is in a high-stress state, it will prioritize notifications such as calm voice messages or connections to emergency support.

[0514] In addition, based on unusual circumstances and the user's emotions, the device can provide more personalized support information. Users can not only receive notifications of suspicious activity, but also get suggestions for stress management and relaxation in their daily lives.

[0515] For example, if a sensor detects an intruder attempting to enter through a window at night, the server identifies the anomaly, and the emotion engine selects a calm notification sound based on the user's emotional data. The device then receives this information, notifies the user, and prompts them to take the necessary action. This allows the user to process the information calmly and respond quickly.

[0516] This system aims not only to improve the safety of the living environment for the elderly, but also to contribute to the mental health care of users, providing more comprehensive protection.

[0517] The following describes the processing flow.

[0518] Step 1:

[0519] The server receives environmental data from the room and its surroundings collected by sensors. This data includes information such as movement, sound, temperature, and humidity, and is first pre-processed to verify its validity.

[0520] Step 2:

[0521] The server supplies pre-processed data to the AI ​​model, which detects abnormal patterns in real time. At this stage, it analyzes whether there are any anomalies indicating intruder activity or changes in the elderly person's physical condition.

[0522] Step 3:

[0523] If an anomaly is detected, the server uses an emotion engine to evaluate the user's emotional state. Through voice analysis and past behavioral patterns, it infers the user's current emotional state.

[0524] Step 4:

[0525] The server determines the content and method of the alarm notification based on the results of the anomaly detection and the user's emotional state. For example, if it is determined that the user is feeling stressed, it will select a calm notification sound or a voice message in a calm tone.

[0526] Step 5:

[0527] The terminal receives an alarm from the server based on the determined content and notifies the user. This notification includes detailed information, prompting the user to understand the situation and take appropriate action. For example, there is an option to notify a security company or emergency contacts.

[0528] Step 6:

[0529] The system responds based on the information provided by the user. Users not only identify anomalies and take necessary actions, but they also receive emotionally reassuring support information, which can give them a greater sense of security.

[0530] Step 7:

[0531] After all processing is complete, the server uses the acquired data and user feedback to retrain the AI ​​model and emotion engine, improving the overall accuracy of the system. This makes anomaly detection and notification more effective in the future.

[0532] (Example 2)

[0533] 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."

[0534] Ensuring the safety of the elderly in modern society is a crucial issue. However, simply collecting environmental data and detecting anomalies makes it difficult to provide appropriate responses that take into account the user's psychological state. When users are under high stress, this can lead to poor judgment and unnecessary anxiety. Therefore, more personalized alerts and information provision based on the user's emotional state are needed.

[0535] 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.

[0536] In this invention, the server includes a collection means for continuously collecting environmental information, an analysis means for analyzing the information obtained from the collection means to detect anomalies, and an emotion analysis means for analyzing past interaction information and real-time voice information to evaluate the user's emotional state. This enables the detection of abnormal behavior, as well as the provision of flexible and appropriate warnings and information according to the user's emotional state.

[0537] "Environmental information" refers to data about the surrounding physical and natural conditions, including room temperature, humidity, sound, and motion detection information.

[0538] "Collection means" refers to a mechanism or device that continuously acquires environmental information and transmits it to a server.

[0539] "Analysis means" refers to the function of executing processes and algorithms to identify anomalies based on collected environmental information.

[0540] An "anomaly" refers to a phenomenon or event that deviates from the expected normal state or pattern.

[0541] "Emotion analysis means" refers to a process or function that analyzes a user's past interaction information and real-time voice information to evaluate their emotional state.

[0542] "Alarming mechanisms" refer to systems that transmit appropriate warnings and notifications to the system based on abnormalities or the user's emotional state.

[0543] "Notification means" refers to a display, speaker, or other interface used to convey information to the user.

[0544] "Learning methods" refer to the process of improving the algorithms of analytical methods by utilizing collected information, thereby enhancing their accuracy and efficiency.

[0545] "Response" refers to the actions or feedback a user gives in response to a system notification or alert.

[0546] This invention is an AI-powered sensor system aimed at ensuring the safety and mental support of the elderly. The server acquires information such as temperature, humidity, sound, and motion detection data through multiple sensors that collect various environmental information both inside and outside the living space. This information is transmitted to the server via a network.

[0547] The server uses generative AI models (such as machine learning frameworks like TensorFlow or PyTorch) to analyze environmental information and identify abnormal behavior or intruders. This model is trained on a large amount of historical data and continuously learns to improve the accuracy of anomaly detection.

[0548] Furthermore, the server analyzes the user's voice and past interaction information using sentiment analysis tools to evaluate their emotional state. Specifically, a sentiment analysis engine based on speech recognition technology (e.g., a general-purpose sentiment analysis API) may be used.

[0549] Based on these analysis results, the server has a function to optimize alarms according to the user's stress level and emotional state. When an anomaly is detected, the alarm system provides the user with calm notifications or information prompting emergency action through voice messages and visual displays via the terminal.

[0550] The device receives optimized notification instructions and delivers information to the user in the most appropriate way. In addition, users can receive suggestions for stress management and relaxation that are useful in their daily lives through the device.

[0551] For example, if an anomaly is detected, such as a suspicious person approaching at night, the server quickly identifies the anomaly and selects a calm voice message to notify the user, preventing them from panicking. The terminal then delivers this information to the user, prompting them to take the necessary action.

[0552] An example of a prompt message would be, "Please describe in detail how the emotion recognition AI system for ensuring the safety of the elderly works." This system supports the safe and secure lives of the elderly and provides appropriate mental health care.

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

[0554] Step 1:

[0555] The server collects environmental information from inside and outside the elderly person's living space via sensors. Inputs include temperature, humidity, sound, and motion data. The data is transmitted to the server in real time via the network, where it is received and stored in storage. Specific operations include acquiring sensor data and transferring that data to the server.

[0556] Step 2:

[0557] The server analyzes the collected environmental information using a generative AI model. The input is the data collected in step 1. The server inputs each dataset into the AI ​​model and determines whether or not anomalies are present. The generative AI model is trained on historical data and analyzes data patterns to detect abnormal behavior. The output is an anomaly status result. The specific operation of this step involves computational processing by the AI ​​model.

[0558] Step 3:

[0559] The server evaluates the user's emotional state using emotion analysis tools. Past interaction data and real-time voice data are used as input. Voice recognition technology is used to convert the voice data into text, and the emotion analysis engine evaluates the emotional state. The output is a numerical result of the user's emotional state. Specific operations include voice data analysis and emotion scoring.

[0560] Step 4:

[0561] The server integrates the anomaly detection results and the emotional state evaluation results to generate the optimal alarm. The input is the output of steps 2 and 3. Based on the two results, the server controls the alarm system and sends an appropriate alarm instruction to the terminal. The output is the alarm instruction information. The specific operation includes data integration and alarm selection by a decision-making algorithm.

[0562] Step 5:

[0563] The terminal receives alarm instructions from the server and notifies the user. The input is the alarm instructions provided by the server. The terminal displays a message on its screen and provides audio notification through its speaker. The output is the transmission of information to the user. Specific actions include generating and displaying notification content and playing audio.

[0564] Step 6:

[0565] The user acts based on information received through the device. Input is notification information from the device. The user understands the information and, as needed, follows suggestions for stress management and relaxation. Output is the user's appropriate response. Specific actions include confirming the information and performing the suggested actions.

[0566] (Application Example 2)

[0567] 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."

[0568] In the living environments of the elderly, a challenge is to issue appropriate alarms that consider the user's emotional state while ensuring safety. Conventional systems simply detect anomalies and issue alarms, but lack consideration for the user's stress levels and emotions. Furthermore, there is a need for improved detection accuracy and the provision of personalized support information to users.

[0569] 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.

[0570] In this invention, the server includes a measurement means for continuously collecting environmental data, an analysis means for analyzing the data obtained from the measurement means and detecting anomalies, and an emotion analysis means for analyzing voice data and identifying the emotional state. This makes it possible to issue appropriate and personalized alarms and provide support information based on the user's emotional state.

[0571] "Environmental data" is a general term for various types of information acquired by sensors that record the physical conditions of the user and their surroundings.

[0572] "Measuring means" refers to a device or function for continuously acquiring and recording environmental data.

[0573] "Analysis means" refers to an algorithm or processor used to analyze data acquired by measurement means and detect deviations from a normal state.

[0574] "Transmission means" refers to a device or function that notifies users or related organizations of warnings or information based on anomalies detected by the analysis means.

[0575] "Display means" refers to a device or function for providing information to a user visually or audibly.

[0576] "Audio data" refers to acoustic information that records the user's speech and surrounding sounds.

[0577] "Emotion analysis means" refers to an algorithm or processor that uses voice data to identify the user's emotional state.

[0578] "Adjustment means" refers to a device or process for changing the output content of a transmission means based on the emotional state obtained by an emotion analysis means.

[0579] "Learning means" refers to an algorithm or process that uses collected data to improve the accuracy of analysis means and other related functions.

[0580] A "protective organization" refers to an institution or group that can take response measures in the event of an abnormal situation.

[0581] The system that realizes this invention primarily involves a server, terminal, and user, and performs anomaly detection and emotion analysis using environmental data and voice data.

[0582] The server is equipped with a measurement and analysis system that acquires data via multiple sensors that continuously collect environmental data and performs analysis on that data. Preprocessing includes data filtering and noise reduction. The analysis implements an anomaly detection algorithm using AI models, and libraries such as TensorFlow and PyTorch can be used.

[0583] The server also collects the user's voice data and converts it to text using the Google Cloud Speech-to-Text API. Based on this text data, sentiment analysis is performed using the Google Cloud Natural Language API to identify the user's emotional state. As a result, the alarm content is adjusted based on the identified emotional state.

[0584] The terminal receives information transmitted from the server and displays warnings and information to the user. The terminal is equipped with a display and speaker, enabling the provision of both visual and audible information.

[0585] As a specific example, in a residence where elderly people stay overnight, if a window opening / closing sensor detects an unknown movement, the server immediately identifies the anomaly and simultaneously analyzes the user's voice to provide a notification that takes their emotional state into account. If the emotional state indicates anxiety, a message in a calmer tone is sent to encourage a quick and appropriate response.

[0586] Example prompts for generative AI models:

[0587] "Please tell me how to properly understand user emotions, detect security anomalies in real time, and propose the optimal response."

[0588] In this way, this system can improve the safety of the living environment for the elderly while also providing mental health care support to users.

[0589] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0590] Step 1:

[0591] The server collects environmental data by acquiring signals from various sensors within the residence (e.g., temperature, humidity, window open / closed). These acquired signals are used as input. The server records this data in a database and processes it into meaningful data through noise filtering.

[0592] Step 2:

[0593] The server analyzes the environmental data processed in Step 1 in real time. This analysis uses an AI model to detect anomalies. The input is filtered environmental data, and the output is information about the presence and type of anomalies. A machine learning model using TensorFlow is employed for this analysis.

[0594] Step 3:

[0595] The server receives the user's voice data from the device. The voice data is converted to text using the Google Cloud Speech-to-Text API. In this conversion process, the voice input is output as text data.

[0596] Step 4:

[0597] The server uses the text data obtained in step 3 as input and performs sentiment analysis using the Google Cloud Natural Language API. This identifies the user's emotional state. The output is information about the emotional state.

[0598] Step 5:

[0599] The terminal receives anomaly detection information and emotional state information from the server. Based on this information, the terminal generates alarms and messages and notifies the user through the display and speaker. The input is the output information from steps 2 and 4, and the output is the displayed alarms and audio messages.

[0600] Step 6:

[0601] Users receive notifications and provide feedback via their devices as needed. This feedback is collected by the server for the learning process. The server receives this feedback as training data and performs data processing and calculations to improve the accuracy of the AI ​​model.

[0602] 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.

[0603] 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.

[0604] 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.

[0605] [Fourth Embodiment]

[0606] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0607] 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.

[0608] 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).

[0609] 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.

[0610] 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.

[0611] 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).

[0612] 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.

[0613] 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.

[0614] 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.

[0615] 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.

[0616] 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.

[0617] 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.

[0618] 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".

[0619] The system according to the present invention is an AI-equipped sensor system for ensuring the safety of the elderly. This system collects various data from the environment, detects anomalies based on that data, and notifies necessary alarms. Furthermore, it is possible to improve detection accuracy by accumulating data using machine learning technology.

[0620] First, sensors placed in and around the living space continuously acquire environmental data such as motion, sound, temperature, and humidity. The data collected by the sensors is sent to a server, which then analyzes the data.

[0621] The server uses an AI model to analyze the acquired data in real time and identify abnormal behavior and patterns. For example, if irregular movements or differences from normal activity are detected during a specific time period, it is immediately judged as abnormal.

[0622] When an anomaly is detected, the server uses notification methods to send an alert to pre-configured family members or security companies. Specifically, users are notified via voice alarms, email notifications, or push notifications through a dedicated app via their devices. Upon receiving the alert, users can take prompt action to ensure the safety of the elderly person.

[0623] Furthermore, the server retrains its AI model based on collected data and user feedback to improve the accuracy of its identification methods. This process reduces false alarms and enables more accurate anomaly detection.

[0624] For example, if an intruder attempts to enter a property at night by opening a window, the sensor will detect the movement and sound, and the server will immediately identify it as abnormal activity. An automatic alarm notification will then be sent to family members or designated security agencies, enabling prompt action.

[0625] Ultimately, this system provides safety and peace of mind to the elderly and their families by monitoring their living environment and immediately notifying them of any abnormal situations.

[0626] The following describes the processing flow.

[0627] Step 1:

[0628] The server receives environmental data collected by the sensors. This data includes information such as movement, sound, temperature, and humidity over time. The server temporarily stores the received data and prepares it for preprocessing.

[0629] Step 2:

[0630] The server performs preprocessing on the received data, such as noise reduction and filtering. This process removes unnecessary data and improves the accuracy of the information needed for analysis.

[0631] Step 3:

[0632] The server inputs pre-processed data into an AI model and performs real-time analysis. The AI ​​model is trained on historical data and has the ability to identify patterns of suspicious intrusion and abnormal behavior.

[0633] Step 4:

[0634] If the AI ​​model detects an anomaly, the server immediately activates notification mechanisms and issues an alarm. The alarm is sent to registered devices as an email or app notification.

[0635] Step 5:

[0636] The terminal displays a notification to the user when it receives an alarm from the server. The user checks the notification and considers taking immediate action. If necessary, they can contact the elderly person directly or notify the security company.

[0637] Step 6:

[0638] The server uses the data collected after notification, along with user feedback, to analyze and retrain the AI ​​model for improved accuracy. This will improve the accuracy of anomaly detection in subsequent instances.

[0639] (Example 1)

[0640] 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".

[0641] The present invention relates to a system for ensuring the safety of the elderly, and more particularly aims to provide a highly accurate system that can collect environmental information in real time, immediately detect anomalies, and issue alarms. More specifically, the objective is to improve the accuracy of anomaly detection, reduce false alarms, and enable rapid notification to users and security agencies.

[0642] 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.

[0643] In this invention, the server includes sensing means for continuously collecting environmental information, detection means for analyzing the information obtained from the sensing means to detect anomalies, and notification means for issuing an alarm based on the anomalies detected by the detection means. This makes it possible to monitor the living environment of elderly people and enable a rapid response in the event of an anomaly.

[0644] "Environmental information" is a general term for data that indicates surrounding elements such as temperature, humidity, sound, and movement, acquired within a specific area.

[0645] "Sensing means" refers to devices and sensors for continuously acquiring environmental information, which allows for real-time data collection.

[0646] "Analysis" is the act or process of processing collected data based on certain criteria to identify anomalies or patterns.

[0647] "Detection means" refers to techniques or methods for detecting anomalies from analyzed data.

[0648] "Abnormal" refers to behavior or a state that deviates from normal patterns or standards, indicating a situation that requires attention.

[0649] "Notification means" refers to a function or device that issues alarms or notifications based on detected abnormal information.

[0650] "Notification means" refers to the means or methods used to inform users of information transmitted by notification means.

[0651] "Analysis improvement means" refers to techniques or methods for improving the accuracy of detection means using collected information and feedback.

[0652] "Notification means" refers to a function that immediately transmits information to security agencies or designated personnel when an anomaly is detected.

[0653] The system according to the present invention is an AI-equipped sensor system designed to ensure the safety of the elderly. It mainly comprises the following elements:

[0654] The device includes multiple sensors installed in the living space. These sensors include motion sensors, sound sensors, and temperature / humidity sensors, and this hardware is used to continuously acquire environmental information. Motion sensors detect human movement, sound sensors capture changes in ambient sound, and temperature / humidity sensors monitor the temperature and humidity of the environment.

[0655] The server receives environmental information transmitted from terminals in real time and uses a generative AI model to analyze the data. This AI model is a powerful tool for learning normal behavior patterns and detecting abnormal patterns. In particular, it utilizes deep learning technology to perform highly accurate anomaly detection based on the obtained data.

[0656] The server also has a function to alert users using notification methods when it detects an anomaly. These notification methods include using the terminal's speaker as an audio alarm or sending notifications to the user's smart device. This allows users to immediately understand the location and time of the anomaly and take appropriate action.

[0657] Furthermore, the server continuously learns from the collected information through analysis and improvement mechanisms, thereby improving the accuracy of the detection mechanisms. User feedback is crucial data for the system to reduce false alarms and perform more precise anomaly detection.

[0658] For example, if a sensor detects a suspicious sound in the middle of the night, the server analyzes this data as an anomaly and immediately sends a push notification to the user's smartphone. At this time, the user can check the status of the room via the app.

[0659] An example of a prompt message could be, "Please explain what kind of data processing is necessary to detect abnormalities in the living environment of elderly people and provide real-time notifications." By inputting such prompt messages into the AI ​​generation model, guidelines can be obtained to ensure that the above-mentioned system is operated safely.

[0660] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0661] Step 1:

[0662] The device collects environmental information using various sensors installed in the living space. Specifically, a motion sensor detects human movement and records that movement information. A sound sensor captures changes in ambient sound, and a temperature and humidity sensor obtains current temperature and humidity data. The input is raw data obtained from each sensor, and the output is formatted environmental data sent to the server.

[0663] Step 2:

[0664] The server receives environmental data transmitted from terminals in real time. The input is environmental data from the terminals, and the output is pre-processed data for anomaly detection. Upon receiving the data, the server classifies each data type and formats it into a format suitable for analysis. This process enables efficient data analysis.

[0665] Step 3:

[0666] The server uses a generative AI model to analyze preprocessed data and detect anomalies. The input is preprocessed data, and the output is the analysis result indicating the presence or absence of anomalies. Specifically, the AI ​​model compares current data with past data to find deviations from normal patterns. The generative AI model uses deep learning techniques and performs complex mathematical calculations to improve the accuracy of anomaly detection.

[0667] Step 4:

[0668] If the server detects an anomaly, it will use a notification system to alert the user. The input is the analysis result of the anomaly detection, and the output is the information sent to the user's device as an alarm notification. Specifically, the server instructs the terminal to emit an audio alarm and also sends a push notification to the user's smartphone.

[0669] Step 5:

[0670] The user takes appropriate action in response to the received alarm. The input is the alarm notification, and the output is the action the user should take. The user launches a dedicated app and checks real-time video and detailed information to determine the appropriate course of action. Specifically, the user checks camera footage through the app and, if necessary, rushes to the scene or contacts relevant parties.

[0671] Step 6:

[0672] The server learns from collected data and user feedback through analytical methods to improve the generated AI model, thereby enhancing the system's accuracy. The input is accumulated data and feedback information, and the output is the updated AI model. Specifically, the server analyzes data that resulted in false alarms, readjusts the model, and improves the success rate of anomaly detection in subsequent instances.

[0673] (Application Example 1)

[0674] 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".

[0675] In elderly households, it is crucial to quickly detect abnormal situations in daily life and ensure safety. However, conventional systems struggle to provide security information to recipients in real time and prompt immediate action, thus creating a need for a more flexible and responsive monitoring system.

[0676] 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.

[0677] In this invention, the server includes measuring means for continuously collecting environmental information, detection means for analyzing the information obtained from the measuring means and identifying anomalies, a notification mechanism for issuing alarms based on the anomalies identified by the detection means, communication means for providing an application for installation on smart devices, and cooperation means for analyzing anomalies in real time and sending notifications to smart devices corresponding to the anomalies. This makes it possible to immediately detect anomalies in the living environment of elderly people and to quickly and accurately notify recipients.

[0678] "Environmental information" refers to various data related to the surrounding conditions, such as temperature, humidity, movement, and sound.

[0679] "Measuring means" refers to devices and methods for continuously acquiring environmental information.

[0680] "Analysis" refers to the process of thoroughly analyzing acquired information and performing necessary steps to identify anomalies.

[0681] "Identification means" refers to methods or models for detecting anomalies from analyzed information.

[0682] An "alarm" refers to a visual, auditory, or digital notification method used to alert someone when an anomaly is detected.

[0683] A "notification mechanism" refers to a system or device for issuing an alarm.

[0684] A "receiver" refers to a person who receives an alert from a notification system and uses the information.

[0685] A "notification mechanism" refers to a system or method for providing data to recipients.

[0686] A "learning mechanism" refers to a learning method or series of processes used to improve a system's performance and identification accuracy based on collected information.

[0687] A "smart device" refers to an electronic device that has information processing capabilities and can connect to a network.

[0688] "Communication methods" refer to methods and protocols for transmitting information to other devices or systems.

[0689] "Coordination means" refers to a method of coordinating between systems to transmit abnormalities to smart devices in a borderless manner and to prompt appropriate responses.

[0690] In this application, the system involves a server running a program that continuously collects environmental information from various sensors installed in the home. The acquired environmental information is temporarily stored in a database for appropriate analysis. In the analysis step, the server implements an identification method to identify anomalies using machine learning algorithms. This is achieved by using machine learning libraries such as TensorFlow to extract features from the collected data and build an anomaly detection model. Furthermore, when the server detects an anomaly in real time, it sends an alert notification to the user's smart devices using communication methods such as AWS SNS.

[0691] Upon receiving a notification, users can check the situation and take necessary actions through a dedicated app on their smartphone or tablet. This application visually displays information about anomaly detection, supporting users in responding quickly and accurately. User feedback is automatically sent to the server and used to improve the anomaly detection algorithm. In this way, the system's accuracy continuously improves through learning.

[0692] As a concrete example, if suspicious activity is detected in an elderly person's home at night, the server analyzes the sensor information and immediately recognizes it as an anomaly. This triggers a notification to the user's smartphone, allowing them to quickly understand the situation and take action. An example of a prompt message to ensure the safety of the elderly in this way is as follows: "If suspicious noises are detected in an elderly person's home late at night, please tell me how to notify them and how to support a quick response."

[0693] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0694] Step 1:

[0695] Sensors continuously collect environmental information. The sensors acquire data on ambient temperature, humidity, sound, and motion, and transmit this data to a server. The input is environmental state data, and the output is raw data sent to the server. In this process, physical data is captured by the sensors and transmitted to the server via the network.

[0696] Step 2:

[0697] The server stores the received data in the database. The input is the raw data sent in step 1, and the output is the data stored in the database. The server uses a database management system for efficient data storage and access.

[0698] Step 3:

[0699] The server analyzes stored data and identifies anomalies. Specifically, it uses a generative AI model to analyze data patterns and detect unusual movements or sounds. The input is environmental data obtained from a database, and the output is the result of anomaly detection. The server executes machine learning algorithms to perform pattern recognition and anomaly detection.

[0700] Step 4:

[0701] When the server detects an anomaly, it sends a notification to the terminal using communication methods such as AWS SNS. The input is the result of the anomaly detection, and the output is the alarm notification sent to the terminal. The server analyzes the anomaly data in real time and immediately sends an alarm to the configured contacts when suspicious activity is detected.

[0702] Step 5:

[0703] The terminal provides the user with received notifications. Input is an alarm notification from the server, and output is an alarm message displayed on the terminal screen. The user can review the notification content and take prompt action based on that information. The terminal presents notifications clearly through its user interface.

[0704] Step 6:

[0705] The system sends user feedback to the server to retrain the AI ​​model. The input is the user's responses and feedback data, and the output is the updated AI model. The server takes in the received feedback and performs additional training to improve the performance of the generated AI model.

[0706] 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.

[0707] This invention combines an AI-powered sensor system for ensuring the safety of the elderly with a function to recognize the user's emotions. In addition to the conventional anomaly detection function based on environmental data, this system can analyze the user's emotional state using an emotion engine and optimize the method and content of alarms.

[0708] First, the sensors collect environmental data from the elderly person's room and surrounding area. This data is sent to a server, where an AI model is used to detect abnormal behavior. The server immediately processes the collected data and analyzes it to determine whether there has been an intruder or abnormal behavior.

[0709] Next, the emotion engine evaluates the user's emotional state based on past interaction data and real-time voice analysis. Based on this evaluation, the server considers the user's stress level and emotional state and notifies them of an alert in an appropriate manner. For example, if the user is in a high-stress state, it will prioritize notifications such as calm voice messages or connections to emergency support.

[0710] In addition, based on unusual circumstances and the user's emotions, the device can provide more personalized support information. Users can not only receive notifications of suspicious activity, but also get suggestions for stress management and relaxation in their daily lives.

[0711] For example, if a sensor detects an intruder attempting to enter through a window at night, the server identifies the anomaly, and the emotion engine selects a calm notification sound based on the user's emotional data. The device then receives this information, notifies the user, and prompts them to take the necessary action. This allows the user to process the information calmly and respond quickly.

[0712] This system aims not only to improve the safety of the living environment for the elderly, but also to contribute to the mental health care of users, providing more comprehensive protection.

[0713] The following describes the processing flow.

[0714] Step 1:

[0715] The server receives environmental data from the room and its surroundings collected by sensors. This data includes information such as movement, sound, temperature, and humidity, and is first pre-processed to verify its validity.

[0716] Step 2:

[0717] The server supplies pre-processed data to the AI ​​model, which detects abnormal patterns in real time. At this stage, it analyzes whether there are any anomalies indicating intruder activity or changes in the elderly person's physical condition.

[0718] Step 3:

[0719] If an anomaly is detected, the server uses an emotion engine to evaluate the user's emotional state. Through voice analysis and past behavioral patterns, it infers the user's current emotional state.

[0720] Step 4:

[0721] The server determines the content and method of the alarm notification based on the results of the anomaly detection and the user's emotional state. For example, if it is determined that the user is feeling stressed, it will select a calm notification sound or a voice message in a calm tone.

[0722] Step 5:

[0723] The terminal receives an alarm from the server based on the determined content and notifies the user. This notification includes detailed information, prompting the user to understand the situation and take appropriate action. For example, there is an option to notify a security company or emergency contacts.

[0724] Step 6:

[0725] The system responds based on the information provided by the user. Users not only identify anomalies and take necessary actions, but they also receive emotionally reassuring support information, which can give them a greater sense of security.

[0726] Step 7:

[0727] After all processing is complete, the server uses the acquired data and user feedback to retrain the AI ​​model and emotion engine, improving the overall accuracy of the system. This makes anomaly detection and notification more effective in the future.

[0728] (Example 2)

[0729] 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".

[0730] Ensuring the safety of the elderly in modern society is a crucial issue. However, simply collecting environmental data and detecting anomalies makes it difficult to provide appropriate responses that take into account the user's psychological state. When users are under high stress, this can lead to poor judgment and unnecessary anxiety. Therefore, more personalized alerts and information provision based on the user's emotional state are needed.

[0731] 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.

[0732] In this invention, the server includes a collection means for continuously collecting environmental information, an analysis means for analyzing the information obtained from the collection means to detect anomalies, and an emotion analysis means for analyzing past interaction information and real-time voice information to evaluate the user's emotional state. This enables the detection of abnormal behavior, as well as the provision of flexible and appropriate warnings and information according to the user's emotional state.

[0733] "Environmental information" refers to data about the surrounding physical and natural conditions, including room temperature, humidity, sound, and motion detection information.

[0734] "Collection means" refers to a mechanism or device that continuously acquires environmental information and transmits it to a server.

[0735] "Analysis means" refers to the function of executing processes and algorithms to identify anomalies based on collected environmental information.

[0736] An "anomaly" refers to a phenomenon or event that deviates from the expected normal state or pattern.

[0737] "Emotion analysis means" refers to a process or function that analyzes a user's past interaction information and real-time voice information to evaluate their emotional state.

[0738] "Alarming mechanisms" refer to systems that transmit appropriate warnings and notifications to the system based on abnormalities or the user's emotional state.

[0739] "Notification means" refers to a display, speaker, or other interface used to convey information to the user.

[0740] "Learning methods" refer to the process of improving the algorithms of analytical methods by utilizing collected information, thereby enhancing their accuracy and efficiency.

[0741] "Response" refers to the actions or feedback a user gives in response to a system notification or alert.

[0742] This invention is an AI-powered sensor system aimed at ensuring the safety and mental support of the elderly. The server acquires information such as temperature, humidity, sound, and motion detection data through multiple sensors that collect various environmental information both inside and outside the living space. This information is transmitted to the server via a network.

[0743] The server uses generative AI models (such as machine learning frameworks like TensorFlow or PyTorch) to analyze environmental information and identify abnormal behavior or intruders. This model is trained on a large amount of historical data and continuously learns to improve the accuracy of anomaly detection.

[0744] Furthermore, the server analyzes the user's voice and past interaction information using sentiment analysis tools to evaluate their emotional state. Specifically, a sentiment analysis engine based on speech recognition technology (e.g., a general-purpose sentiment analysis API) may be used.

[0745] Based on these analysis results, the server has a function to optimize alarms according to the user's stress level and emotional state. When an anomaly is detected, the alarm system provides the user with calm notifications or information prompting emergency action through voice messages and visual displays via the terminal.

[0746] The device receives optimized notification instructions and delivers information to the user in the most appropriate way. In addition, users can receive suggestions for stress management and relaxation that are useful in their daily lives through the device.

[0747] For example, if an anomaly is detected, such as a suspicious person approaching at night, the server quickly identifies the anomaly and selects a calm voice message to notify the user, preventing them from panicking. The terminal then delivers this information to the user, prompting them to take the necessary action.

[0748] An example of a prompt message would be, "Please describe in detail how the emotion recognition AI system for ensuring the safety of the elderly works." This system supports the safe and secure lives of the elderly and provides appropriate mental health care.

[0749] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0750] Step 1:

[0751] The server collects environmental information from inside and outside the elderly person's living space via sensors. Inputs include temperature, humidity, sound, and motion data. The data is transmitted to the server in real time via the network, where it is received and stored in storage. Specific operations include acquiring sensor data and transferring that data to the server.

[0752] Step 2:

[0753] The server analyzes the collected environmental information using a generative AI model. The input is the data collected in step 1. The server inputs each dataset into the AI ​​model and determines whether or not anomalies are present. The generative AI model is trained on historical data and analyzes data patterns to detect abnormal behavior. The output is an anomaly status result. The specific operation of this step involves computational processing by the AI ​​model.

[0754] Step 3:

[0755] The server evaluates the user's emotional state using emotion analysis tools. Past interaction data and real-time voice data are used as input. Voice recognition technology is used to convert the voice data into text, and the emotion analysis engine evaluates the emotional state. The output is a numerical result of the user's emotional state. Specific operations include voice data analysis and emotion scoring.

[0756] Step 4:

[0757] The server integrates the anomaly detection results and the emotional state evaluation results to generate the optimal alarm. The input is the output of steps 2 and 3. Based on the two results, the server controls the alarm system and sends an appropriate alarm instruction to the terminal. The output is the alarm instruction information. The specific operation includes data integration and alarm selection by a decision-making algorithm.

[0758] Step 5:

[0759] The terminal receives alarm instructions from the server and notifies the user. The input is the alarm instructions provided by the server. The terminal displays a message on its screen and provides audio notification through its speaker. The output is the transmission of information to the user. Specific actions include generating and displaying notification content and playing audio.

[0760] Step 6:

[0761] The user acts based on information received through the device. Input is notification information from the device. The user understands the information and, as needed, follows suggestions for stress management and relaxation. Output is the user's appropriate response. Specific actions include confirming the information and performing the suggested actions.

[0762] (Application Example 2)

[0763] 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".

[0764] In the living environments of the elderly, a challenge is to issue appropriate alarms that consider the user's emotional state while ensuring safety. Conventional systems simply detect anomalies and issue alarms, but lack consideration for the user's stress levels and emotions. Furthermore, there is a need for improved detection accuracy and the provision of personalized support information to users.

[0765] 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.

[0766] In this invention, the server includes a measurement means for continuously collecting environmental data, an analysis means for analyzing the data obtained from the measurement means and detecting anomalies, and an emotion analysis means for analyzing voice data and identifying the emotional state. This makes it possible to issue appropriate and personalized alarms and provide support information based on the user's emotional state.

[0767] "Environmental data" is a general term for various types of information acquired by sensors that record the physical conditions of the user and their surroundings.

[0768] "Measuring means" refers to a device or function for continuously acquiring and recording environmental data.

[0769] "Analysis means" refers to an algorithm or processor used to analyze data acquired by measurement means and detect deviations from a normal state.

[0770] "Transmission means" refers to a device or function that notifies users or related organizations of warnings or information based on anomalies detected by the analysis means.

[0771] "Display means" refers to a device or function for providing information to a user visually or audibly.

[0772] "Audio data" refers to acoustic information that records the user's speech and surrounding sounds.

[0773] "Emotion analysis means" refers to an algorithm or processor that uses voice data to identify the user's emotional state.

[0774] "Adjustment means" refers to a device or process for changing the output content of a transmission means based on the emotional state obtained by an emotion analysis means.

[0775] "Learning means" refers to an algorithm or process that uses collected data to improve the accuracy of analysis means and other related functions.

[0776] A "protective organization" refers to an institution or group that can take response measures in the event of an abnormal situation.

[0777] The system that realizes this invention primarily involves a server, terminal, and user, and performs anomaly detection and emotion analysis using environmental data and voice data.

[0778] The server is equipped with a measurement and analysis system that acquires data via multiple sensors that continuously collect environmental data and performs analysis on that data. Preprocessing includes data filtering and noise reduction. The analysis implements an anomaly detection algorithm using AI models, and libraries such as TensorFlow and PyTorch can be used.

[0779] The server also collects the user's voice data and converts it to text using the Google Cloud Speech-to-Text API. Based on this text data, sentiment analysis is performed using the Google Cloud Natural Language API to identify the user's emotional state. As a result, the alarm content is adjusted based on the identified emotional state.

[0780] The terminal receives information transmitted from the server and displays warnings and information to the user. The terminal is equipped with a display and speaker, enabling the provision of both visual and audible information.

[0781] As a specific example, in a residence where elderly people stay overnight, if a window opening / closing sensor detects an unknown movement, the server immediately identifies the anomaly and simultaneously analyzes the user's voice to provide a notification that takes their emotional state into account. If the emotional state indicates anxiety, a message in a calmer tone is sent to encourage a quick and appropriate response.

[0782] Example prompts for generative AI models:

[0783] "Please tell me how to properly understand user emotions, detect security anomalies in real time, and propose the optimal response."

[0784] In this way, this system can improve the safety of the living environment for the elderly while also providing mental health care support to users.

[0785] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0786] Step 1:

[0787] The server collects environmental data by acquiring signals from various sensors within the residence (e.g., temperature, humidity, window open / closed). These acquired signals are used as input. The server records this data in a database and processes it into meaningful data through noise filtering.

[0788] Step 2:

[0789] The server analyzes the environmental data processed in Step 1 in real time. This analysis uses an AI model to detect anomalies. The input is filtered environmental data, and the output is information about the presence and type of anomalies. A machine learning model using TensorFlow is employed for this analysis.

[0790] Step 3:

[0791] The server receives the user's voice data from the device. The voice data is converted to text using the Google Cloud Speech-to-Text API. In this conversion process, the voice input is output as text data.

[0792] Step 4:

[0793] The server uses the text data obtained in step 3 as input and performs sentiment analysis using the Google Cloud Natural Language API. This identifies the user's emotional state. The output is information about the emotional state.

[0794] Step 5:

[0795] The terminal receives anomaly detection information and emotional state information from the server. Based on this information, the terminal generates alarms and messages and notifies the user through the display and speaker. The input is the output information from steps 2 and 4, and the output is the displayed alarms and audio messages.

[0796] Step 6:

[0797] Users receive notifications and provide feedback via their devices as needed. This feedback is collected by the server for the learning process. The server receives this feedback as training data and performs data processing and calculations to improve the accuracy of the AI ​​model.

[0798] 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.

[0799] 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.

[0800] 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.

[0801] 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.

[0802] 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.

[0803] 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.

[0804] 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.

[0805] 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.

[0806] 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."

[0807] 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.

[0808] 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.

[0809] 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.

[0810] 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.

[0811] 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.

[0812] 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.

[0813] 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.

[0814] 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.

[0815] 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.

[0816] 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.

[0817] 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.

[0818] 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 as being incorporated by reference.

[0819] The following is further disclosed regarding the embodiments described above.

[0820] (Claim 1)

[0821] Measurement means for continuously collecting environmental data,

[0822] An identification means for analyzing data obtained from the measurement means and detecting anomalies,

[0823] A notification means that issues an alarm based on an abnormality detected by the identification means,

[0824] A notification means that provides information to a user who has received an alarm from the aforementioned notification means,

[0825] A learning method that uses collected data to learn and improve the accuracy of the identification method,

[0826] A system that includes this.

[0827] (Claim 2)

[0828] The system according to claim 1, further comprising a means for notifying a security agency in real time based on the results of an anomaly detection.

[0829] (Claim 3)

[0830] The system according to claim 1, characterized in that the learning means updates the algorithm of the identification means using user feedback.

[0831] "Example 1"

[0832] (Claim 1)

[0833] A sensing means for continuously collecting environmental information,

[0834] A detection means that analyzes the information obtained from the sensing means to detect an anomaly,

[0835] A notification means that issues an alarm based on an abnormality detected by the aforementioned detection means,

[0836] A notification means that provides information to a user who has received an alarm from the aforementioned notification means,

[0837] An analysis improvement means that uses the collected information to learn and improve the accuracy of the detection means,

[0838] A system that includes this.

[0839] (Claim 2)

[0840] The system according to claim 1, further comprising a means for notifying a security agency in real time based on the results of an anomaly detection.

[0841] (Claim 3)

[0842] The system according to claim 1, characterized in that the analysis improvement means updates the algorithm of the detection means using feedback from users.

[0843] "Application Example 1"

[0844] (Claim 1)

[0845] Measurement means for continuously collecting environmental information,

[0846] A detection means that analyzes the information obtained from the measurement means and identifies an anomaly,

[0847] A notification mechanism that issues an alarm based on an abnormality identified by the detection means,

[0848] A notification mechanism that provides data to a recipient who has received an alarm from the aforementioned notification mechanism,

[0849] A learning mechanism that uses collected information to learn and improve the accuracy of the detection means,

[0850] A means of communication that provides an application for installation on smart devices,

[0851] A means of collaboration that analyzes anomalies in real time and sends notifications to smart devices in response to those anomalies,

[0852] A system that includes this.

[0853] (Claim 2)

[0854] The system according to claim 1, further comprising a notification mechanism that notifies security authorities in real time based on the results of anomaly detection.

[0855] (Claim 3)

[0856] The system according to claim 1, characterized in that the learning mechanism updates the algorithm of the detection means using feedback from the receiver.

[0857] "Example 2 of combining an emotion engine"

[0858] (Claim 1)

[0859] A means of continuously collecting environmental information,

[0860] An analysis means for analyzing information obtained from the aforementioned collection means and detecting anomalies,

[0861] An emotion analysis means that analyzes past interaction information and real-time voice information to evaluate the user's emotional state,

[0862] An alarm means that issues an alarm based on the abnormality detected by the analysis means and the evaluation obtained by the emotion analysis means,

[0863] A notification means that provides information to a user who has received an alarm from the aforementioned alarm means,

[0864] A learning method that uses collected information to learn and improve the accuracy of the analysis method,

[0865] A system that includes this.

[0866] (Claim 2)

[0867] The system according to claim 1, further comprising a notification means for notifying a protection agency in real time based on the results of anomaly detection and sentiment analysis.

[0868] (Claim 3)

[0869] The system according to claim 1, characterized in that the learning means updates the algorithm of the analysis means using user feedback.

[0870] "Application example 2 when combining with an emotional engine"

[0871] (Claim 1)

[0872] Measurement means for continuously collecting environmental data,

[0873] An analysis means for analyzing data obtained from the measurement means and detecting anomalies,

[0874] A transmitting means that issues an alarm based on the abnormality detected by the analysis means,

[0875] A display means that provides information to a user who has received an alarm from the aforementioned transmitting means,

[0876] An emotion analysis method that analyzes audio data to identify emotional states,

[0877] An adjustment means that adjusts the content of the alarm of the transmission means based on the emotional state obtained by the emotion analysis means,

[0878] A learning method that uses collected data to learn and improve the accuracy of the analysis method,

[0879] A system that includes this.

[0880] (Claim 2)

[0881] The system according to claim 1, further comprising a notification means for notifying a protective organization in real time based on the results of anomaly detection and the output of the emotion analysis means.

[0882] (Claim 3)

[0883] The system according to claim 1, characterized in that the learning means updates the algorithm of the analysis means using evaluations from users. [Explanation of symbols]

[0884] 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. Measurement means for continuously collecting environmental data, An identification means for analyzing data obtained from the measurement means and detecting anomalies, A notification means that issues an alarm based on an abnormality detected by the identification means, A notification means that provides information to a user who has received an alarm from the aforementioned notification means, A learning method that uses collected data to learn and improve the accuracy of the identification method, A system that includes this.

2. The system according to claim 1, further comprising a notification means for notifying a security agency in real time based on the results of an anomaly detection.

3. The system according to claim 1, characterized in that the learning means updates the algorithm of the identification means using feedback from the user.

Images