System

Abstract

A system is provided.SOLUTION: The system includes a means for collecting data in real time by measuring the amount of water used by a sensor, a means for detecting an abnormal use pattern on the basis of the collected data, a means for transmitting a notification to a set emergency contact destination when the abnormal use pattern is detected, and a means for promoting support activities in cooperation with a regional support organization.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

[0002] Patent document 1 discloses a persona chatbot control method performed by at least one processor, the method including the steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to a description of the chatbot character, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance in response to the user utterance. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Japanese Patent Publication No. 2022-180282 Summary of the Invention [Problem to be solved by the invention]

[0004] In today's society, where the number of elderly people and single people is increasing, lonely deaths have become a serious social problem. Late detection of the death can cause significant economic losses and mental stress. In rental housing, lonely deaths often become a major problem for landlords and management companies. This invention aims to detect lonely deaths early and minimize the damage that accompanies them. [Means for solving the problem]

[0005] This invention is a system that includes the following means: a means for measuring water usage with a sensor and collecting data in real time; a means for detecting abnormal usage patterns based on the collected data; a means for sending a notification to a set emergency contact when an abnormal usage pattern is detected; and a means for promoting support activities in collaboration with local support organizations. The system also includes a means for modeling normal usage patterns by referencing data from the previous year and data from similar households, and for simultaneously sending notifications to multiple contacts when an abnormal usage pattern exceeds a threshold. This enables early detection and rapid response, contributing to the prevention of lonely deaths.

[0006] "Water usage" refers to the amount of water consumed by each household or facility during a specific period.

[0007] A "sensor" refers to a device that measures a physical environmental condition (in this case, water flow rate) and outputs it as digital data or an analog signal.

[0008] "Means of collecting data" refers to the mechanism for receiving data sent from sensors and storing it in a database or storage.

[0009] An "abnormal usage pattern" refers to an amount of water usage that is abnormally low or high compared to a normal usage pattern, and in this invention refers to an abnormality that may indicate a solitary death or the like.

[0010] "Means of detection" refers to the algorithms and software used to analyze collected data and identify anomalies.

[0011] "Emergency Contact" refers to the person to whom a notification is sent if an abnormality is detected (for example, the user, family, friends, landlord, or management company).

[0012] "Means for sending notifications" refers to the mechanism for sending notifications to emergency contacts in various ways, such as SMS, email, or push notification, when an abnormality is detected.

[0013] "Community support organizations" refer to local volunteer groups and welfare services that are responsible for watching over and supporting the elderly and single people.

[0014] "Means to promote support activities" refers to a system for working with local support organizations to quickly provide the necessary support.

[0015] "Prior year data" refers to records of water usage from the past year, which are used to model normal usage patterns.

[0016] "Similar household data" refers to records of water usage from other households with similar living arrangements and environmental conditions, and is used to model typical usage patterns.

[0017] "Modeling methods" refers to a system that uses statistical or machine learning techniques to calculate typical usage patterns based on data from the previous year or similar households.

[0018] "Multiple contacts" refers to multiple people or organizations (e.g., family, friends, landlord, management company) to whom notifications are sent when an anomaly is detected. [Brief explanation of the drawings]

[0019] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6]FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 11] FIG. 3 is a sequence diagram showing a processing flow of the data processing system according to the first embodiment. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0020] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

[0021] First, the terms used in the following description will be explained.

[0022] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), and an APU (Accelerated Processing Unit).

[0023] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

[0024] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0025] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, 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), Bluetooth (registered trademark), etc.

[0026] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0027] [First embodiment]

[0028] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0029] 1, a 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.

[0030] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0031] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0032] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the 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.

[0033] 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 of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0034] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

[0035] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0036] 2, in the data processing device 12, a specific process 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" according to the technology of the present 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 process 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.

[0037] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0038] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with the 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 process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0039] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0040] This invention is a system that monitors water usage and detects abnormal patterns. The system collects data in real time and notifies emergency contacts if an abnormality is detected. It also includes a mechanism to promote relief activities by linking with local support networks.

[0041] System configuration

[0042] The system mainly consists of the following components:

[0043] 1. Sensor

[0044] It is attached to the water meter of each home or facility to measure water usage.

[0045] 2. Server

[0046] It collects, stores, and analyzes data sent from sensors in real time.

[0047] Model normal usage patterns and detect anomalies.

[0048] 3. Terminal

[0049] Provides an interface for users to check water usage data and anomaly detection status.

[0050] 4. Emergency Notification System

[0051] If an abnormality is detected, a notification is sent to a pre-registered emergency contact.

[0052] 5. Regional Support Collaboration System

[0053] Work with local support organizations and request their cooperation when necessary.

[0054] Program processing

[0055] Data collection

[0056] The server receives real-time water usage data sent from the sensors and stores it in a database, including timestamps and usage amounts.

[0057] Anomaly detection

[0058] The server uses the collected data to model normal usage patterns, comparing it with data from the previous year and similar households, and uses machine learning algorithms to establish a baseline and determine whether current usage significantly deviates from this baseline.

[0059] notification

[0060] If an anomaly is detected, the server will send a notification to emergency contacts. The notification will include a description of the anomaly, the date and time it was detected, and a recommended action to take. Notifications can be sent via SMS, email, or push notification.

[0061] Specific examples

[0062] Example 1: Elderly people living alone

[0063] The server collects water usage data for Mr. A's home. Normally, Mr. A uses 40 liters of water per day, but for the past three days, it has been less than 5 liters per day. This is deemed abnormal, and the server sends a notification to Mr. A's daughter and the management company. Upon receiving the notification, the daughter tries to contact Mr. A, but receives no response, so she visits him in person. Meanwhile, the management company also dispatches staff to check the situation.

[0064] Example 2: Worker living away from home

[0065] The server collects water usage data from Mr. B's residence. Mr. B usually uses 60 liters of water on weekends, but this weekend he used less than 10 liters, which is considered abnormal. The server sends a notification to his registered friends and his company's management department. The friend receives the notification and contacts Mr. B. Since there is no response, the friend visits Mr. B's residence, and at the same time, the company's management department also begins to take action.

[0066] Local Support Network

[0067] When an abnormality is detected, the server also sends a notification to local support organizations to promptly respond. Support organizations will then carry out support activities such as visiting or making phone calls depending on the situation. Users can also request support via their devices.

[0068] This allows the system to detect abnormalities in real time and provide the ability to prompt a quick response, contributing to the prevention of lonely deaths.

[0069] The processing flow will be explained below.

[0070] Step 1: Data collection

[0071] The server receives real-time water usage data from sensors. In this system, sensors are attached to water meters in each home and transmit the measured data at regular intervals (e.g., every minute) to the server. The server stores the received data in a database and assigns a timestamp to each data point.

[0072] Step 2: Data analysis

[0073] The server models normal usage patterns based on the collected data, references data from previous years and similar households, and uses machine learning algorithms to establish a baseline. It then compares current data against the modeled normal patterns to detect abnormal usage patterns.

[0074] Step 3: Anomaly detection

[0075] The server uses statistical analysis techniques to determine whether current usage data deviates from a set baseline. For example, sustained low usage or sudden fluctuations are detected as an anomaly. If an anomaly is found, the event is recorded in an anomaly event log.

[0076] Step 4: Generate notifications

[0077] When an anomaly is detected, the server consults the configured emergency contact information, which can include the user, family, friends, landlord, management company, etc. The server generates a notification message containing the anomaly, the date and time it was detected, and a recommended action to take.

[0078] Step 5: Sending notifications

[0079] The server then sends the generated notification message to each contact via SMS, email, push notification, etc. For example, email is sent using the SMTP protocol.

[0080] Step 6: User confirmation and response

[0081] The user receives a notification and can check the water usage data and details of any abnormalities through their device. If the user is a family member, they can contact them directly or visit them. Landlords and management companies can also check the situation and visit the site if necessary.

[0082] Step 7: Coordinating local support networks

[0083] If an abnormality is detected, the server also sends a notification to local support organizations, who then promptly consider how to respond and provide the necessary assistance, such as making regular visits or calling to check on the safety of the affected individuals.

[0084] Step 8: Follow up

[0085] After an abnormality is notified, the server tracks the response status and notifies again if necessary. For example, if the abnormality continues or no response is taken, it is possible to send another alert. The user can check the support status through their device and request any additional support needed.

[0086] This allows the system to detect abnormalities in water usage early and prompt a quick response, preventing lonely deaths and other emergencies.

[0087] Example 1

[0088] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0089] In modern society, there are increasing cases of elderly people living alone or people working away from home being unable to respond quickly to abnormal situations, putting their lives at risk. To address these situations, a system is needed that can detect abnormalities in water usage, which is a part of daily life, in real time and quickly notify appropriate contacts and support organizations. Existing systems have issues that are not fully addressed in terms of the accuracy of abnormality detection, the speed of notification, and the coordination of responses.

[0090] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0091] In this invention, the server includes means for receiving data in real time from sensors that measure water usage, means for storing the received data in a database, means for modeling normal usage patterns using a machine learning algorithm based on the stored data and detecting abnormal usage patterns, means for sending a notification to a set emergency contact when an abnormal usage pattern is detected, and means for coordinating with local support organizations to promote support activities. This makes it possible to quickly and accurately detect abnormalities in water usage and immediately notify necessary support.

[0092] A "sensor" is a device that measures water usage and transmits the data in real time.

[0093] A "database" is a system for storing and managing collected data.

[0094] A "machine learning algorithm" is a set of mathematical techniques that use historical data to model normal usage patterns and detect anomalous patterns.

[0095] An "abnormal usage pattern" refers to fluctuations in water usage that deviate significantly from normal usage patterns.

[0096] "Emergency contacts" are pre-defined contacts to whom notifications are sent when an abnormality is detected, and include family members, friends, and administrators.

[0097] A "community support organization" is an organization made up of local groups and institutions that provide support activities in emergencies.

[0098] "Real time" means processing an event at the exact moment it occurs.

[0099] MODE FOR CARRYING OUT THE INVENTION

[0100] This invention is a system that monitors water usage and detects abnormal patterns. The system collects data in real time and notifies emergency contacts if an abnormality is detected. It also includes a mechanism to link with local support networks to facilitate relief efforts.

[0101] System configuration

[0102] The system mainly consists of the following components:

[0103] 1. Sensor

[0104] It is attached to the water meter of each home or facility to measure water usage.

[0105] 2. Server

[0106] It collects, stores, and analyzes data sent from sensors in real time.

[0107] Model normal usage patterns and detect anomalies.

[0108] 3. Terminal

[0109] Provides an interface for users to check water usage data and anomaly detection status.

[0110] 4. Emergency Notification System

[0111] If an abnormality is detected, a notification is sent to a pre-registered emergency contact.

[0112] 5. Regional Support Collaboration System

[0113] Work with local support organizations and request their cooperation when necessary.

[0114] Data collection and storage

[0115] The server receives real-time water usage data sent from the sensors. Specifically, sensors installed in each home and facility measure usage data every minute and send it wirelessly to the server. For example, if the sensor in home A sends data such as "3 liters used at 2023-10-01 08:00:00," the server receives this data. The server receives the data and stores it in a database. The stored data includes a timestamp, usage amount, sensor ID, etc., and is saved in a format such as "3 liters used by sensor ID: A123 at 2023-10-01 08:00:00."

[0116] Anomaly detection

[0117] The server analyzes past usage data stored in a database and models normal usage patterns using a machine learning algorithm (e.g., using TensorFlow). Specifically, it uses data from the past year to set a baseline for normal usage. If the current data deviates significantly from this baseline, it is determined to be abnormal. For example, if person A's normal daily usage is 40 liters, but has been less than 5 liters for the past three days, it is determined to be abnormal.

[0118] emergency notification

[0119] If an abnormality is detected, the server automatically sends a notification to emergency contacts. The notification can be sent in the form of SMS, email, or push notification. For example, an SMS message saying "Mom's water usage is abnormally low. Please check it" is sent to Mr. A's daughter. Specifically, the message is sent to registered contacts using the Twilio API.

[0120] Support and collaboration

[0121] Based on the information about the detected abnormality, the server also sends a notification to local support organizations. For example, an email may be sent to the local welfare service saying, "Water usage at Mr. A's house on xxxx-chome has dropped abnormally. Urgent action is required." Users can also request support using their devices (smartphones or PCs). When a user opens a dedicated app and presses the "Request Support" button, a notification is automatically sent to the local support organization.

[0122] Hardware and software used

[0123] Hardware: sensors, servers, user devices (smartphones, PCs)

[0124] Software: Database systems (e.g., MySQL, PostgreSQL), machine learning models (e.g., TensorFlow, Scikit-learn), notification systems (e.g., Twilio for SMS, SendGrid for Email)

[0125] Specific examples

[0126] Example 1: Elderly people living alone

[0127] The server collects water usage data from Mr. A's home. Normally, Mr. A uses 40 liters of water per day, but for the past three days, it has been less than 5 liters per day. This is deemed abnormal, and the server sends a notification to Mr. A's daughter and the management agency. Upon receiving the notification, Mr. A's daughter tries to contact Mr. A, but receives no response, so she visits him in person. Meanwhile, the management agency also dispatches staff to check the situation.

[0128] Example 2: Worker living away from home

[0129] The server collects water usage data from Mr. B's residence. Mr. B usually uses 60 liters of water on weekends, but this weekend he used less than 10 liters, which is considered abnormal. The server sends a notification to his registered friends and the management agency. The friend receives the notification and contacts Mr. B. Since there is no response, the friend visits Mr. B's residence, and the management agency also begins to take action.

[0130] Prompt Sentence Examples

[0131] "Mr. A, an elderly person living alone, has noticed that his water usage has dropped from the usual 40 liters to less than 5 liters. Please write code that will treat this as an abnormality and send a notification to an emergency contact."

[0132] Example of prompt input:

[0133] "Please explain in detail the processing steps of a program in which a server detects anomalies in water usage data collected from sensors and sends a notification to emergency contacts if an abnormality is detected. Also, please recall the case of an elderly person living alone as a concrete example."

[0134] This system ensures the safety and security of users by sending data collected by sensors to a server in real time and quickly sending emergency notifications if an abnormality is detected.

[0135] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0136] Program processing

[0137] Step 1: Data collection

[0138] The server receives real-time data sent from the sensors. The input is water usage data measured by sensors attached to water meters in each home or facility. The data includes a timestamp, the amount used, and the sensor ID. The output is raw data transferred to the server in real time. Specifically, the sensor sends data to the server such as "3 liters used with sensor ID: A123 on 2023-10-01 08:00:00."

[0139] Step 2: Save data

[0140] The server stores the received data in a database. The input is the real-time data received in step 1. When stored in the database, the data is structured in the format of a timestamp, amount used, and sensor ID. As an output, the stored data is accumulated in the database. Specifically, the data "3 liters used with sensor ID: A123 on 2023-10-01 08:00:00" is registered in the database.

[0141] Step 3: Data analysis

[0142] The server analyzes past water usage data stored in a database. The inputs are past usage data and current real-time data. A machine learning algorithm is used to model normal usage patterns and perform analysis to detect anomalies. The output is the baseline usage pattern and an anomaly determination result when current usage deviates from the baseline. Specifically, the server sets a baseline based on data from the past year, such as "Person A's normal usage is 40 liters per day," and compares this with current usage to detect anomalies.

[0143] Step 4: Anomaly detection

[0144] The server detects anomalies based on the results of the data analysis in step 3. The inputs are the analyzed usage pattern and the current usage amount. A certain threshold is set, and if the current usage amount exceeds that threshold, it is determined to be an anomaly. The output is a flag indicating whether an anomaly has been detected. Specifically, it determines that an anomaly has occurred if "usage amount for the past three days has been less than 5 liters per day."

[0145] Step 5: Emergency Notification

[0146] If an anomaly is detected, the server sends a notification to the emergency contact. The inputs are the anomaly detection result and the pre-defined emergency contact information. The notification is sent in the form of SMS, email, push notification, etc. The output is the notification message that was sent. Specifically, the Twilio API is used to send a message to Mr. A's daughter saying, "Mom's water usage is abnormally low. Please check."

[0147] Step 6: Support collaboration

[0148] Based on the detected anomaly, the server also sends a notification to local support organizations. The inputs are the anomaly detection results and the support organization's contact information. The notification is sent via email or other communication method. The output is the notification sent to the support organization. Specifically, SendGrid is used to send an email to welfare services stating, "Water usage at Mr. A's residence on xxxx-chome has dropped abnormally. Urgent action is required."

[0149] In this way, a series of processes is carried out, from monitoring water usage to detecting abnormalities, sending emergency notifications, and coordinating support, through each step.

[0150] (Application example 1)

[0151] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0152] For elderly people living alone or those working away from home, it is important to detect abnormalities in water usage early and take appropriate action. However, conventional systems often lack the ability to detect abnormalities in real time or provide prompt notification. Furthermore, there was insufficient collaboration with local support organizations, which sometimes led to delayed early response. Furthermore, there was a lack of a way for users to easily understand their own water usage using smart devices. To solve these problems, a more efficient and reliable water usage monitoring system is needed.

[0153] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0154] In this invention, the server includes means for measuring water usage with a sensor and collecting data in real time, means for detecting abnormal usage patterns based on the collected data, means for sending a notification to a set emergency contact when an abnormal usage pattern is detected, means for promoting support activities in cooperation with local support organizations, as well as means for displaying water usage in real time on a smart device, means for detecting abnormalities using a machine learning algorithm, and means for providing a user interface through the smart device. This enables real-time monitoring of water usage, highly accurate detection of abnormalities using machine learning, and rapid notification and support collaboration.

[0155] "Water usage" is data measuring the amount of water used in homes and facilities.

[0156] A "sensor" is a device that is attached to a water meter and measures water usage in real time.

[0157] "Means for collecting data in real time" refers to the function of instantly receiving and storing water usage data sent from sensors.

[0158] An "abnormal usage pattern" is a unique data pattern that indicates usage that significantly deviates from normal water usage.

[0159] "Means for sending notifications to emergency contacts" is a function that immediately notifies the set contacts via email, SMS, etc. when an abnormality is detected.

[0160] "Means to promote support activities in cooperation with local support organizations" refers to a system that cooperates with local support groups and collaborators to ensure that necessary support can be provided quickly.

[0161] "Smart devices" refers to information devices that can connect to the Internet, such as smartphones, tablets, and smartwatches.

[0162] A "machine learning algorithm" is a computational method that learns patterns based on large amounts of data and makes automatic decisions.

[0163] A "user interface" is the screen or means by which a user operates an application and inputs and obtains information.

[0164] "Historical Data" refers to historical water usage data previously collected.

[0165] "Current data" refers to the latest ongoing water usage data.

[0166] "Multiple contacts" refers to multiple contact information (family, friends, administrator, etc.) registered in advance for sending notifications in the event of an abnormality.

[0167] A "local support network" is a network of support formed by collaborators and organizations within the local area.

[0168] MODE FOR CARRYING OUT THE INVENTION

[0169] The configuration and operation of a specific system for realizing this invention will be described. This system includes smart water meters installed in homes and facilities, as well as a server, cloud storage, a notification system, and smart devices.

[0170] Hardware and software used

[0171] Hardware

[0172] Smart water meter: A device that uses sensors to measure water usage in homes and facilities.

[0173] Server: Installed in the cloud, it collects data, analyzes it, and sends notifications. It uses Amazon EC2 instances.

[0174] Smart Device: The device used by the user, such as a smartphone or tablet.

[0175] software

[0176] Database: Data is stored using Amazon RDS and PostgreSQL.

[0177] AI algorithms: Anomaly detection models are built using TensorFlow and Scikit-learn.

[0178] Smartphone app: Develop cross-platform applications using Flutter.

[0179] Notification system: Uses Amazon SNS to send notifications.

[0180] Data collection

[0181] The sensor measures water usage in real time and sends the data to AWS IoT Core via MQTT protocol. The received data is stored in Amazon RDS via AWS Lambda. This data includes a timestamp and usage amount.

[0182] Anomaly detection

[0183] The server analyzes the collected data in real time and compares it with historical data to model normal usage patterns. Machine learning algorithms (such as Scikit-learn's Isolation Forest) are used to detect anomalies. If an anomaly is detected, the server sends a notification to emergency contacts and local assistance networks.

[0184] notification

[0185] If an anomaly is detected, AWS IoT Core will trigger a notification using Amazon SNS, which can be delivered via push notification, SMS, or email.

[0186] User Interface

[0187] Users can use the smartphone app to view past water usage, anomaly detection history, and real-time usage. The application was developed using Flutter and is compatible with both iOS and Android.

[0188] Specific examples

[0189] Cases of elderly people living alone

[0190] The server regularly monitors the water usage at Mr. A's home. Normally, Mr. A uses 40 liters of water per day, but for the past three days, it has been less than 5 liters per day. Detecting this abnormality, the server sends a notification to Mr. A's family, who are his emergency contacts, and to the management company. Upon receiving the notification, the family attempts to contact Mr. A, but receives no response, so they visit him in person. The management company also dispatches staff to check on the situation.

[0191] Prompt Sentence Examples

[0192] User registration prompt:

[0193] Welcome to Safe Water Check! This app monitors your water usage in real time and automatically notifies you if there are any irregularities. To use it, please enter the following information:

[0194] Emergency contact information (email address or phone number)

[0195] Local support network preference (e.g., local government or neighbors)

[0196] Pairing information for your home's water meter and smartphone

[0197] If you have any questions regarding usage, please feel free to let us know.

[0198] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0199] Program processing flow

[0200] Step 1: Collect water usage data

[0201] Sensors measure water usage in each home or facility in real time. The measured data is sent to AWS IoT Core via the MQTT protocol. The input is the measurement data (timestamp and usage amount), and the output is data passed to AWS Lambda.

[0202] Input: Timestamp and usage data measured by sensors

[0203] Data processing: Send data to AWS IoT Core via MQTT protocol

[0204] Output: Measurement data sent to AWS IoT Core

[0205] Step 2: Save your data

[0206] AWS Lambda receives the received data in real time and stores it in Amazon RDS (e.g., PostgreSQL). The input is the data sent from AWS IoT Core, and the output is a message that the data was successfully stored in the database.

[0207] Input: Timestamp and usage data sent from AWS IoT Core

[0208] Data processing: AWS Lambda receives the data, formats it, and stores it in Amazon RDS

[0209] Output: Message that saving to database was successful

[0210] Step 3: Analyze the data

[0211] The server analyzes the collected data in real time, comparing historical data with current data and using machine learning algorithms (e.g., Scikit-learn's Isolation Forest) to model normal usage patterns. The input is the stored data, and the output is the anomaly detection results.

[0212] Input: Historical and Current Data

[0213] Data processing: Anomaly detection using Scikit-learn's Isolation Forest

[0214] Output: Anomaly detection results (presence or absence of anomaly, type of anomaly)

[0215] Step 4: Anomaly detection

[0216] If the server detects an anomaly based on the analysis results, it summarizes the details of the anomaly. If the anomaly threshold is exceeded, it proceeds to the next step. The input is the anomaly detection result, and the output is notification information.

[0217] Input: Anomaly detection result

[0218] Data processing: Summarizing details of anomalies

[0219] Output: Notification information (details of the abnormality, detection date and time, recommended action)

[0220] Step 5: Sending notifications

[0221] The server uses Amazon SNS to send notifications to emergency contacts and local support networks when an anomaly is detected. The input is the notification information, and the output is a message that the notification has been sent.

[0222] Input: Notification information (details of the abnormality, detection date and time, recommended action)

[0223] Data processing: Format the notification content and send it via Amazon SNS

[0224] Output: Notification sent message

[0225] Step 6: Update the User Interface

[0226] The terminal (smart device) receives notifications from the server and updates the application interface. The user can check abnormality notifications and past data history through the app. The input is notification information and past data, and the output is an updated user interface.

[0227] Input: Notification information, past data

[0228] Data processing: updating and displaying the user interface

[0229] Output: Updated user interface

[0230] Step 7: Request assistance

[0231] The user can request additional assistance through the application. When assistance is requested, the information is sent to the server, which notifies the local assistance network. The input is the user's request for assistance, and the output is a notification to the local assistance network.

[0232] Input: User's request for assistance

[0233] Data processing: Send support request information to the server

[0234] Output: Notification to local support network

[0235] Furthermore, an emotion engine that estimates the user's emotion may be combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0236] This invention is a system that not only monitors water usage and detects abnormal patterns, but also utilizes user emotional data to improve the accuracy of anomaly detection and emergency response. The system collects data in real time and has the ability to notify emergency contacts if an abnormality is detected. It also includes a mechanism to promote relief activities by linking with local support networks.

[0237] System configuration

[0238] The system mainly consists of the following components:

[0239] 1. Sensor

[0240] It is attached to the water meter of each home or facility to measure water usage.

[0241] 2. Emotion Engine

[0242] Emotions are assessed by analyzing the user's voice, facial expressions, and behavioral data.

[0243] 3. Server

[0244] Water usage data sent from sensors is collected, stored, and analyzed in real time.

[0245] The emotional data sent from the emotion engine is also analyzed.

[0246] Model normal usage patterns and detect anomalies.

[0247] 4. Terminal

[0248] It provides an interface for users to check water usage data, emotion data, and anomaly detection status.

[0249] 5. Emergency Notification System

[0250] If an abnormality is detected, a notification is sent to a pre-registered emergency contact.

[0251] 6. Regional Support Collaboration System

[0252] Work with local support organizations and request their cooperation when necessary.

[0253] Program processing

[0254] Data collection

[0255] The server receives water usage data sent from the sensors in real time and stores it in a database. Each data is time-stamped, and emotion data from the emotion engine is also collected at the same time.

[0256] Anomaly detection

[0257] The server uses the water usage data and emotion data to model typical usage and emotion patterns, comparing them with data from previous years and similar households, and uses machine learning algorithms to establish a baseline and determine whether the current data significantly deviates from this baseline.

[0258] notification

[0259] If an anomaly is detected, the server evaluates the urgency based on the emotion data and sends a notification to the configured emergency contacts. The notification includes the details of the anomaly, the emotion rating, the date and time of detection, and a recommended response. Notifications are sent via SMS, email, or push notification.

[0260] Specific examples

[0261] Example 1: Elderly people living alone

[0262] The server collects water usage data from Mr. A's home. Normally, Mr. A uses 40 liters of water per day, but for the past three days, he has used less than 5 liters per day. Furthermore, the emotion engine detects increased anxiety and stress from Mr. A's voice and behavior. This is deemed an abnormality, and the server sends a notification to Mr. A's daughter and the management company. Upon receiving the notification, the daughter attempts to contact Mr. A, but receives no response, so she visits him in person. Meanwhile, the management company also dispatches staff to check on the situation.

[0263] Example 2: Worker living away from home

[0264] The server collects water usage data from Mr. B's residence. Mr. B normally uses 60 liters of water on weekends, but this weekend it was less than 10 liters, which is determined to be abnormal. The emotion engine also detects that Mr. B looks tired from his facial expression. The server then sends a notification to his registered friends and his company's management department. The friend receives the notification and contacts Mr. B, but receives no response, so he visits his residence, and at the same time, the company's management department also begins to take action.

[0265] Local Support Network

[0266] When an abnormality is detected, the server combines the information with emotion data and sends a notification to local support organizations to prompt a prompt response. Support organizations will then carry out support activities such as visiting or making phone calls depending on the situation. Users can also request support via their devices.

[0267] This allows the system to detect anomalies by combining water usage data and user emotional data, and by prompting a quick response, it can prevent lonely deaths and other emergencies.

[0268] The processing flow will be explained below.

[0269] Step 1: Data collection

[0270] The server receives real-time water usage data sent from sensors. The sensors are attached to the water meters in each home and send the measurement data to the server at regular intervals (e.g., every minute). The received data is stored in a database, and each data is given a timestamp.

[0271] Step 2: Collecting Emotional Data

[0272] The emotion engine receives the user's voice, facial expression, and behavioral data from sensors and devices, and evaluates their emotions. The evaluated emotion data is sent to the server and also stored in a database.

[0273] Step 3: Modeling normal patterns

[0274] The server uses collected water usage and sentiment data to model typical usage and sentiment patterns using data from the previous year and similar households, and uses machine learning algorithms to establish a baseline.

[0275] Step 4: Anomaly detection

[0276] The server compares current usage and emotion data with baselines and uses statistical analysis to detect anomalies. For example, a persistently low water usage combined with stress or anxiety detected by the emotion engine is considered an anomaly. When an anomaly is detected, the event is recorded in an anomaly event log.

[0277] Step 5: Assess the severity

[0278] When an abnormality is detected, the server evaluates the urgency based on the emotional data. For example, if the intensity of anxiety or stress level is high, the urgency is judged to be high.

[0279] Step 6: Generate notifications

[0280] The server generates a notification message based on the severity rating, which includes the anomaly description, sentiment rating, detection date and time, and recommended action.

[0281] Step 7: Sending notifications

[0282] The server then sends the generated notification message to multiple emergency contacts, including the user, family, friends, landlords, management companies, etc. Notifications can be sent via SMS, email, or push notification.

[0283] Step 8: User confirmation and response

[0284] The user receives a notification and can check the water usage data, emotional data, and details of any abnormalities through their device. If the user is a family member, they can contact or visit the person directly. The landlord or management company can also respond in the same way.

[0285] Step 9: Linking local support networks

[0286] If an abnormality is detected, the server also sends a notification to local support organizations, who then promptly consider how to respond and provide the necessary assistance, such as by making regular visits or phone calls to check on the safety of the affected individuals.

[0287] Step 10: Follow up

[0288] After notification, the server continuously monitors the response status and notifies again as necessary. If the abnormality persists or no response is taken, it is possible to send another alert. The user can check the progress of support through their device and request any additional support that is required.

[0289] This allows the system to detect anomalies by combining water usage data with user emotional data, and by prompting a quick response, it can prevent lonely deaths and other emergencies.

[0290] Example 2

[0291] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0292] In modern society, the number of individuals whose health and safety are a concern is increasing, such as elderly people living alone and people working away from home. Under these circumstances, monitoring their lifestyle habits, detecting abnormalities early, and taking appropriate action is a major challenge. In particular, it is becoming increasingly important to detect emergencies from abnormalities in water usage, but existing systems still have issues with the accuracy of anomaly detection and the speed of response. In addition, there is a need for more accurate anomaly detection and emergency response by combining not only water usage data but also user emotional data.

[0293] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0294] In this invention, the server includes means for measuring water usage with a sensor and collecting data in real time, means for detecting abnormal usage patterns based on the collected data, means for sending a notification to a set emergency contact when an abnormal usage pattern is detected, means for analyzing the user's voice, facial expression, and behavior data to evaluate their emotions, means for improving the accuracy of anomaly detection and emergency response based on the emotion data, and means for collaborating with local support organizations to promote support activities. This not only improves the accuracy of anomaly detection, but also enables quick and appropriate responses.

[0295] "Water usage data" is information that indicates the amount of water consumed by each household or facility, and is measured in real time using sensors.

[0296] A "sensor" is a device that is attached to a water meter, measures water usage, and sends the data to a server.

[0297] The "server" is a computer system that receives water usage data and emotion data sent from the sensor, analyzes them, and detects abnormalities.

[0298] "Emotion data" is information that evaluates a user's emotions by analyzing their voice, facial expressions, and behavior, and is used to improve the accuracy of anomaly detection.

[0299] An "abnormal usage pattern" refers to fluctuations in water usage that deviate significantly from normal usage patterns, and refers to usage patterns that deviate from a baseline modeled based on data from the previous year or similar households.

[0300] "Emergency Contacts" are pre-configured contacts to send notifications when an abnormality is detected based on water usage data or emotion data.

[0301] "Local support organizations" are local groups and institutions that receive notifications when abnormalities are detected and work together to provide rapid response and support activities.

[0302] "Notifications" are messages that send warnings or information to emergency contacts or local support organizations when an anomaly is detected.

[0303] "Modeling" is the process of statistically representing normal usage patterns based on data from the previous year and similar households, and setting criteria for anomaly detection.

[0304] "Abnormality detection accuracy" refers to the ability to accurately detect abnormalities by combining water usage data and emotion data.

[0305] This invention is a system that not only monitors water usage and detects abnormal patterns, but also utilizes user emotional data to improve the accuracy of anomaly detection and emergency response. The system collects data in real time and has the ability to notify emergency contacts if an abnormality is detected. It also includes a mechanism to promote relief activities in collaboration with local relief organizations.

[0306] System configuration

[0307] The system mainly consists of the following components:

[0308] 1. Sensor

[0309] It is installed in the water meter of each home or facility to measure water usage, and transmits data using, for example, a LoRa module or Wi-Fi module.

[0310] 2. Emotion Engine

[0311] Emotions are assessed by analyzing the user's voice, facial expressions, and behavioral data. Specifically, emotion analysis is performed using the Emotion SDK.

[0312] 3. Server

[0313] Water usage data sent from sensors is collected, stored, and analyzed in real time.

[0314] The emotion data sent from the emotion engine is also analyzed, using machine learning algorithms such as TensorFlow and PyTorch.

[0315] Model normal usage patterns and detect anomalies.

[0316] 4. Terminal

[0317] It provides an interface for users to check water usage data, emotion data, and anomaly detection status using a smartphone app or web interface.

[0318] 5. Emergency Notification System

[0319] If an abnormality is detected, a notification will be sent to pre-registered emergency contacts using services such as Amazon SNS (Simple Notification Service).

[0320] 6. Regional Support Collaboration System

[0321] Work with local support organizations and request their cooperation when necessary.

[0322] Specific examples

[0323] Example 1: Elderly people living alone

[0324] The server collects water usage data from Mr. A's home. Normally, Mr. A uses 40 liters of water per day, but for the past three days, he has used less than 5 liters per day. Furthermore, the emotion engine detects increased anxiety and stress from Mr. A's voice and behavior. This is deemed an abnormality, and the server sends a notification to Mr. A's daughter and the management company. Upon receiving the notification, the daughter attempts to contact Mr. A, but receives no response, so she visits him in person. Meanwhile, the management company also dispatches staff to check on the situation.

[0325] Example 2: Worker living away from home

[0326] The server collects water usage data from Mr. B's residence. Mr. B normally uses 60 liters of water on weekends, but this weekend it was less than 10 liters, which is determined to be abnormal. The emotion engine also detects that Mr. B looks tired from his facial expression. The server then sends a notification to his registered friends and his company's management department. The friend receives the notification and contacts Mr. B, but receives no response, so he visits his residence, and at the same time, the company's management department also begins to take action.

[0327] Example prompts for generative AI models

[0328] Prompt statement example 1:

[0329] "Mr. A, an elderly person living alone, has been using significantly less water than usual for the past three days, and the emotion engine has detected increased anxiety and stress. What is the appropriate response for Mr. A in this situation?"

[0330] Prompt statement example 2:

[0331] "Mr. B, who is working away from home, used significantly less water than usual over the weekend, and the emotion engine detected his fatigue. Please advise whether an emergency response is required and what action would you recommend?"

[0332] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0333] Step 1: Data collection

[0334] The server receives water usage data sent from sensors in real time. The input is water usage data from sensors installed in each home or facility. Specifically, the sensors measure water usage every minute or every hour and send the data to the server via a LoRa module or Wi-Fi module. The server receives this data and assigns a timestamp to each data point. This allows the water usage data to be organized chronologically.

[0335] Step 2: Data storage and organization

[0336] The server stores the received data in a database. The input is water usage data with a timestamp. Specifically, the server uses a database (e.g., PostgreSQL) to store the data and organizes it based on the timestamp. The emotion data is also stored in the database. This allows for quick data access and analysis in subsequent analysis steps.

[0337] Step 3: Data analysis and anomaly detection

[0338] The server performs anomaly detection based on the stored data. The inputs are time-stamped water usage data and emotion data. Specifically, the server uses a machine learning algorithm (e.g., TensorFlow or PyTorch) to model normal usage patterns based on data from the previous year and data from similar households. It then analyzes whether the current water usage data significantly deviates from this baseline and detects anomalies. The output is the anomaly detection result (normal or abnormal).

[0339] Step 4: Evaluate the emotional data

[0340] The server improves the accuracy of anomaly detection based on emotion data. The input is emotion data obtained from the emotion engine. Specifically, it uses the emotion engine (e.g., Emotion SDK) to analyze the user's voice, facial expression, and behavioral data to evaluate their emotions. As a result, it outputs the user's stress level and anxiety as a numerical value. This allows the server to combine abnormalities in water usage with emotion data to evaluate the overall urgency.

[0341] Step 5: Notification Processing

[0342] If an anomaly is detected, the server sends a notification to the configured emergency contacts. The input is the anomaly detection result and emotion data. Specific behavior is to use an emergency notification system (e.g., Amazon SNS) to send a notification that includes the anomaly description, emotion rating, detection date and time, and recommended action. The output is a communication sent via SMS, email, or push notification.

[0343] Step 6: User Interface

[0344] Users can check water usage data and emotion data through a terminal. The input is the water usage data and emotion data stored in a database. Specifically, this data is displayed visually using a smartphone app or web interface. The output is a data display in a format that is easy for users to view. This allows users to easily check the anomaly detection status and past history data.

[0345] Step 7: Regional support collaboration

[0346] When an anomaly is detected, the server also sends a notification to the local support organization. The input is the anomaly detection result and emotion data. Specifically, the notification system is used to send information including the nature of the anomaly and its urgency to the local support organization. The output is a notification to the local support organization. This encourages a rapid response and ensures effective support activities.

[0347] (Application example 2)

[0348] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0349] To strengthen monitoring of elderly people and those living alone, it is necessary to not only monitor water usage but also to consider the user's emotional state. Current systems only detect abnormalities in water usage and require emergency responses based on changes in usage patterns, but this alone does not fully grasp the user's psychological and physical state. This also poses the risk of delaying emergency responses. To solve this problem, it is necessary to achieve more accurate monitoring and faster support.

[0350] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting and analyzing emotion data and water usage data, means for detecting abnormal usage patterns and combining them with the emotion data to determine the abnormality, means for assessing the urgency and sending a notification when an abnormality is detected, and means for promoting support activities in cooperation with local support organizations. This makes it possible to more accurately grasp the user's physical and psychological condition and to respond appropriately and quickly in an emergency.

[0351] "Water usage" means the amount of water consumed in a household or facility.

[0352] "Sensor" refers to a device used to measure water usage.

[0353] "Real-time" refers to the instantaneous collection and analysis of data.

[0354] "Data collection means" refers to the technological means for collecting water usage data through sensors.

[0355] "Abnormal usage pattern" means usage that significantly deviates from normal water usage.

[0356] "Anomaly detection measures" refers to technical measures that analyze collected data and detect abnormal usage patterns.

[0357] "Emergency Contact" means a contact configured to receive notification if an Anomaly is detected.

[0358] "Notification means" refers to the technical means for sending a notification to an emergency contact when an abnormality is detected.

[0359] "Community support organization" means an organization established to provide support in the local community.

[0360] "Support promotion measures" refer to technical measures for coordinating with local support organizations and implementing rapid support activities.

[0361] "User" means any individual or entity that uses the System.

[0362] "Emotion data" refers to the emotional state of the user as assessed from their voice, facial expression, and behavior.

[0363] "Evaluation means" refers to a technical means for analyzing emotion data and evaluating the user's emotional state.

[0364] "Emotion analysis" refers to the process of assessing a user's state of mind based on their emotional data.

[0365] "Urgency assessment means" refers to a technical means for assessing the urgency based on emotional data when an abnormality is detected.

[0366] "Registered Contacts" means contacts that are pre-configured within the System to receive notifications.

[0367] This invention is a system that monitors water usage and user emotion data, detects abnormalities, and promotes emergency response. The system is composed of the following main components and processing means.

[0368] System configuration

[0369] 1. Sensor

[0370] This is a sensor that is attached to the water meter of each home or facility to measure water usage.

[0371] 2. Emotion Engine

[0372] This software collects the user's voice, facial expression, and behavioral data, and analyzes and evaluates their emotions.

[0373] 3. Server

[0374] The system receives, stores, and analyzes water usage data and emotion data in real time. It detects abnormal usage patterns and sends notifications to emergency contacts if an abnormality is detected. It also assesses the level of urgency based on emotion data and connects with local support organizations.

[0375] 4. Terminal

[0376] It provides an interface for users to check water usage data, emotion data, and anomaly detection status. The terminal is a smartphone application through which users can check and set data.

[0377] Data collection

[0378] The server collects water usage data in real time from sensors installed in each home and facility. In parallel with this, the emotion engine collects the user's voice, facial expressions, and behavioral data to generate data that evaluates their emotions. The collected data is time-stamped and stored in the server's database.

[0379] Anomaly detection

[0380] The server analyzes water usage data and sentiment data to model normal usage patterns, comparing them with data from previous years and similar households, and uses machine learning algorithms to establish a baseline and determine whether the current data significantly deviates from this baseline.

[0381] Notification and Emergency Response

[0382] If an anomaly is detected, the server evaluates the urgency level based on the emotion data and sends a notification to the configured emergency contacts. The notification includes the nature of the anomaly, the emotion rating, the date and time of detection, and a recommended response. The notification is sent via SMS, email, or push notification. In addition, the server sends similar information to local support organizations to encourage a prompt response.

[0383] Specific examples

[0384] Example 1: Elderly people living alone

[0385] The server collects water usage data for User A's home. User A normally uses 40 liters of water per day, but for the past three days, it has been less than 5 liters per day. Furthermore, the emotion engine detects increased anxiety and stress from User A's voice and behavior. This is deemed an abnormality, and the server sends a notification to User A's family and the administrator. The family members who receive the notification try to contact User A, but receive no response, so they visit in person. Meanwhile, the administrator also dispatches staff to check on the situation.

[0386] Example 2: Worker living away from home

[0387] The server collects water usage data from User B's home. User B normally uses 60 liters of water on weekends, but this weekend it was less than 10 liters, which is determined to be abnormal. The emotion engine also detects that User B looks tired from his facial expression. The server sends a notification to registered friends and the management department. The friend receives the notification and contacts User B, but receives no response, so the server visits User B's home, and the management department also begins to respond.

[0388] Generative AI model prompt example

[0389] Please provide your current and past water usage data. Also provide your emotional data. We will notify you if an abnormality is detected or if your emotional state indicates 'sadness' or 'stress'.

[0390] In this way, to implement the invention, it is necessary to build a system that properly links sensors, emotion engines, servers, and terminals to detect abnormalities and quickly respond to emergencies. This system comprehensively monitors the user's psychological and physical state, thereby enhancing safety.

[0391] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0392] Step 1:

[0393] Sensors are attached to water meters in homes and facilities and measure water usage in real time. The sensors collect measurement data at regular intervals and send it to a server. The input is water usage data, and the output is the measurement data sent to the server.

[0394] Step 2:

[0395] The emotion engine collects the user's voice, facial expression, and behavioral data, and analyzes and evaluates their emotions. The emotion engine acquires user data using devices such as cameras and microphones, and evaluates the user's emotions using an emotion analysis algorithm. The input is the user's voice, facial expression, and behavioral data, and the output is emotion evaluation data.

[0396] Step 3:

[0397] The server receives and stores water usage data sent from the sensor and emotion data sent from the emotion engine in real time. These data are recorded in a database with a timestamp. The input is water usage data and emotion data, and the output is the data stored in the database.

[0398] Step 4:

[0399] The server models normal usage patterns based on the collected data, references historical data and data from similar households, and uses machine learning algorithms to set a baseline. The input is historical and current data, and the output is the set baseline.

[0400] Step 5:

[0401] The server determines whether the current data significantly deviates from the baseline and detects anomalous usage patterns. The inputs are current water usage data and emotion data, and the output is the anomaly detection results.

[0402] Step 6:

[0403] When an anomaly is detected, the server evaluates the urgency level based on the emotion data. If the urgency level is high, a notification is sent to the configured emergency contacts. The notification includes the details of the anomaly, the emotion rating, the date and time of detection, and a recommended response. The input is the anomaly detection result and the emotion rating data, and the output is an emergency notification.

[0404] Step 7:

[0405] The server also connects with local support organizations and promotes support activities as needed. Support organizations are sent information on the nature of the abnormality along with an assessment of the level of urgency, and are required to respond quickly. The input is emergency notification information, and the output is information to connect to support organizations.

[0406] Step 8:

[0407] Users can use the terminal to check water usage data, emotion data, and anomaly detection status. An interface is provided on the terminal, allowing users to check their own data in real time and configure the system. The input is data sent from the server, and the output is information displayed on the user's terminal.

[0408] For specific actions, the following prompt sentence example is used:

[0409] Please provide your current and past water usage data. Also provide your emotional data. We will notify you if an abnormality is detected or if your emotional state indicates 'sadness' or 'stress'.

[0410] 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 a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the 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.

[0411] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0412] In the above embodiment, an example in which the specific process is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0413] [Second embodiment]

[0414] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0415] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0416] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0417] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0418] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0419] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0420] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0421] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0422] The specific processing program 56 is an example of a "program" according to the technology of the present 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.

[0423] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0424] In the smart glasses 214, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. 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 process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0425] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. 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."

[0426] This invention is a system that monitors water usage and detects abnormal patterns. The system collects data in real time and notifies emergency contacts if an abnormality is detected. It also includes a mechanism to promote relief activities by linking with local support networks.

[0427] System configuration

[0428] The system mainly consists of the following components:

[0429] 1. Sensor

[0430] It is attached to the water meter of each home or facility to measure water usage.

[0431] 2. Server

[0432] It collects, stores, and analyzes data sent from sensors in real time.

[0433] Model normal usage patterns and detect anomalies.

[0434] 3. Terminal

[0435] Provides an interface for users to check water usage data and anomaly detection status.

[0436] 4. Emergency Notification System

[0437] If an abnormality is detected, a notification is sent to a pre-registered emergency contact.

[0438] 5. Regional Support Collaboration System

[0439] Work with local support organizations and request their cooperation when necessary.

[0440] Program processing

[0441] Data collection

[0442] The server receives real-time water usage data sent from the sensors and stores it in a database, including timestamps and usage amounts.

[0443] Anomaly detection

[0444] The server uses the collected data to model normal usage patterns, comparing it with data from the previous year and similar households, and uses machine learning algorithms to establish a baseline and determine whether current usage significantly deviates from this baseline.

[0445] notification

[0446] If an anomaly is detected, the server will send a notification to emergency contacts. The notification will include a description of the anomaly, the date and time it was detected, and a recommended action to take. Notifications can be sent via SMS, email, or push notification.

[0447] Specific examples

[0448] Example 1: Elderly people living alone

[0449] The server collects water usage data for Mr. A's home. Normally, Mr. A uses 40 liters of water per day, but for the past three days, it has been less than 5 liters per day. This is deemed abnormal, and the server sends a notification to Mr. A's daughter and the management company. Upon receiving the notification, the daughter tries to contact Mr. A, but receives no response, so she visits him in person. Meanwhile, the management company also dispatches staff to check the situation.

[0450] Example 2: Worker living away from home

[0451] The server collects water usage data from Mr. B's residence. Mr. B usually uses 60 liters of water on weekends, but this weekend he used less than 10 liters, which is considered abnormal. The server sends a notification to his registered friends and his company's management department. The friend receives the notification and contacts Mr. B. Since there is no response, the friend visits Mr. B's residence, and at the same time, the company's management department also begins to take action.

[0452] Local Support Network

[0453] When an abnormality is detected, the server also sends a notification to local support organizations to promptly respond. Support organizations will then carry out support activities such as visiting or making phone calls depending on the situation. Users can also request support via their devices.

[0454] This allows the system to detect abnormalities in real time and provide the ability to prompt a quick response, contributing to the prevention of lonely deaths.

[0455] The processing flow will be explained below.

[0456] Step 1: Data collection

[0457] The server receives real-time water usage data from sensors. In this system, sensors are attached to water meters in each home and transmit the measured data at regular intervals (e.g., every minute) to the server. The server stores the received data in a database and assigns a timestamp to each data point.

[0458] Step 2: Data analysis

[0459] The server models normal usage patterns based on the collected data, references data from previous years and similar households, and uses machine learning algorithms to establish a baseline. It then compares current data against the modeled normal patterns to detect abnormal usage patterns.

[0460] Step 3: Anomaly detection

[0461] The server uses statistical analysis techniques to determine whether current usage data deviates from a set baseline. For example, sustained low usage or sudden fluctuations are detected as an anomaly. If an anomaly is found, the event is recorded in an anomaly event log.

[0462] Step 4: Generate notifications

[0463] When an anomaly is detected, the server consults the configured emergency contact information, which can include the user, family, friends, landlord, management company, etc. The server generates a notification message containing the anomaly, the date and time it was detected, and a recommended action to take.

[0464] Step 5: Sending notifications

[0465] The server then sends the generated notification message to each contact via SMS, email, push notification, etc. For example, email is sent using the SMTP protocol.

[0466] Step 6: User confirmation and response

[0467] The user receives a notification and can check the water usage data and details of any abnormalities through their device. If the user is a family member, they can contact them directly or visit them. Landlords and management companies can also check the situation and visit the site if necessary.

[0468] Step 7: Coordinating local support networks

[0469] If an abnormality is detected, the server also sends a notification to local support organizations, who then promptly consider how to respond and provide the necessary assistance, such as making regular visits or calling to check on the safety of the affected individuals.

[0470] Step 8: Follow up

[0471] After an abnormality is notified, the server tracks the response status and notifies again if necessary. For example, if the abnormality continues or no response is taken, it is possible to send another alert. The user can check the support status through their device and request any additional support needed.

[0472] This allows the system to detect abnormalities in water usage early and prompt a quick response, preventing lonely deaths and other emergencies.

[0473] Example 1

[0474] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0475] In modern society, there are increasing cases of elderly people living alone or people working away from home being unable to respond quickly to abnormal situations, putting their lives at risk. To address these situations, a system is needed that can detect abnormalities in water usage, which is a part of daily life, in real time and quickly notify appropriate contacts and support organizations. Existing systems have issues that are not fully addressed in terms of the accuracy of abnormality detection, the speed of notification, and the coordination of responses.

[0476] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0477] In this invention, the server includes means for receiving data in real time from sensors that measure water usage, means for storing the received data in a database, means for modeling normal usage patterns using a machine learning algorithm based on the stored data and detecting abnormal usage patterns, means for sending a notification to a set emergency contact when an abnormal usage pattern is detected, and means for coordinating with local support organizations to promote support activities. This makes it possible to quickly and accurately detect abnormalities in water usage and immediately notify necessary support.

[0478] A "sensor" is a device that measures water usage and transmits the data in real time.

[0479] A "database" is a system for storing and managing collected data.

[0480] A "machine learning algorithm" is a set of mathematical techniques that use historical data to model normal usage patterns and detect anomalous patterns.

[0481] An "abnormal usage pattern" refers to fluctuations in water usage that deviate significantly from normal usage patterns.

[0482] "Emergency contacts" are pre-defined contacts to whom notifications are sent when an abnormality is detected, and include family members, friends, and administrators.

[0483] A "community support organization" is an organization made up of local groups and institutions that provide support activities in emergencies.

[0484] "Real time" means processing an event at the exact moment it occurs.

[0485] MODE FOR CARRYING OUT THE INVENTION

[0486] This invention is a system that monitors water usage and detects abnormal patterns. The system collects data in real time and notifies emergency contacts if an abnormality is detected. It also includes a mechanism to link with local support networks to facilitate relief efforts.

[0487] System configuration

[0488] The system mainly consists of the following components:

[0489] 1. Sensor

[0490] It is attached to the water meter of each home or facility to measure water usage.

[0491] 2. Server

[0492] It collects, stores, and analyzes data sent from sensors in real time.

[0493] Model normal usage patterns and detect anomalies.

[0494] 3. Terminal

[0495] Provides an interface for users to check water usage data and anomaly detection status.

[0496] 4. Emergency Notification System

[0497] If an abnormality is detected, a notification is sent to a pre-registered emergency contact.

[0498] 5. Regional Support Collaboration System

[0499] Work with local support organizations and request their cooperation when necessary.

[0500] Data collection and storage

[0501] The server receives real-time water usage data sent from the sensors. Specifically, sensors installed in each home and facility measure usage data every minute and send it wirelessly to the server. For example, if the sensor in home A sends data such as "3 liters used at 2023-10-01 08:00:00," the server receives this data. The server receives the data and stores it in a database. The stored data includes a timestamp, usage amount, sensor ID, etc., and is saved in a format such as "3 liters used by sensor ID: A123 at 2023-10-01 08:00:00."

[0502] Anomaly detection

[0503] The server analyzes past usage data stored in a database and models normal usage patterns using a machine learning algorithm (e.g., using TensorFlow). Specifically, it uses data from the past year to set a baseline for normal usage. If the current data deviates significantly from this baseline, it is determined to be abnormal. For example, if person A's normal daily usage is 40 liters, but has been less than 5 liters for the past three days, it is determined to be abnormal.

[0504] emergency notification

[0505] If an abnormality is detected, the server automatically sends a notification to emergency contacts. The notification can be sent in the form of SMS, email, or push notification. For example, an SMS message saying "Mom's water usage is abnormally low. Please check it" is sent to Mr. A's daughter. Specifically, the message is sent to registered contacts using the Twilio API.

[0506] Support collaboration

[0507] Based on the information about the detected abnormality, the server also sends a notification to local support organizations. For example, an email may be sent to the local welfare service saying, "Water usage at Mr. A's house on xxxx-chome has dropped abnormally. Urgent action is required." Users can also request support using their devices (smartphones or PCs). When a user opens a dedicated app and presses the "Request Support" button, a notification is automatically sent to the local support organization.

[0508] Hardware and software used

[0509] Hardware: sensors, servers, user devices (smartphones, PCs)

[0510] Software: Database systems (e.g., MySQL, PostgreSQL), machine learning models (e.g., TensorFlow, Scikit-learn), notification systems (e.g., Twilio for SMS, SendGrid for Email)

[0511] Specific examples

[0512] Example 1: Elderly people living alone

[0513] The server collects water usage data from Mr. A's home. Normally, Mr. A uses 40 liters of water per day, but for the past three days, it has been less than 5 liters per day. This is deemed abnormal, and the server sends a notification to Mr. A's daughter and the management agency. Upon receiving the notification, Mr. A's daughter tries to contact Mr. A, but receives no response, so she visits him in person. Meanwhile, the management agency also dispatches staff to check the situation.

[0514] Example 2: Worker living away from home

[0515] The server collects water usage data from Mr. B's residence. Mr. B usually uses 60 liters of water on weekends, but this weekend he used less than 10 liters, which is considered abnormal. The server sends a notification to his registered friends and the management agency. The friend receives the notification and contacts Mr. B. Since there is no response, the friend visits Mr. B's residence, and the management agency also begins to take action.

[0516] Prompt Sentence Examples

[0517] "Mr. A, an elderly person living alone, has noticed that his water usage has dropped from the usual 40 liters to less than 5 liters. Please write code that will treat this as an abnormality and send a notification to an emergency contact."

[0518] Example of prompt input:

[0519] "Please explain in detail the processing steps of a program in which a server detects anomalies in water usage data collected from sensors and sends a notification to emergency contacts if an abnormality is detected. Also, please recall the case of an elderly person living alone as a concrete example."

[0520] This system ensures the safety and security of users by sending data collected by sensors to a server in real time and quickly sending emergency notifications if an abnormality is detected.

[0521] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0522] Program processing

[0523] Step 1: Data collection

[0524] The server receives real-time data sent from the sensors. The input is water usage data measured by sensors attached to water meters in each home or facility. The data includes a timestamp, the amount used, and the sensor ID. The output is raw data transferred to the server in real time. Specifically, the sensor sends data to the server such as "3 liters used with sensor ID: A123 on 2023-10-01 08:00:00."

[0525] Step 2: Save data

[0526] The server stores the received data in a database. The input is the real-time data received in step 1. When stored in the database, the data is structured in the format of a timestamp, amount used, and sensor ID. As an output, the stored data is accumulated in the database. Specifically, the data "3 liters used with sensor ID: A123 on 2023-10-01 08:00:00" is registered in the database.

[0527] Step 3: Data analysis

[0528] The server analyzes past water usage data stored in a database. The inputs are past usage data and current real-time data. A machine learning algorithm is used to model normal usage patterns and perform analysis to detect anomalies. The output is the baseline usage pattern and an anomaly determination result when current usage deviates from the baseline. Specifically, the server sets a baseline based on data from the past year, such as "Person A's normal usage is 40 liters per day," and compares this with current usage to detect anomalies.

[0529] Step 4: Anomaly detection

[0530] The server detects anomalies based on the results of the data analysis in step 3. The inputs are the analyzed usage pattern and the current usage amount. A certain threshold is set, and if the current usage amount exceeds that threshold, it is determined to be an anomaly. The output is a flag indicating whether an anomaly has been detected. Specifically, it determines that an anomaly has occurred if "usage amount for the past three days has been less than 5 liters per day."

[0531] Step 5: Emergency Notification

[0532] If an anomaly is detected, the server sends a notification to the emergency contact. The inputs are the anomaly detection result and the pre-defined emergency contact information. The notification is sent in the form of SMS, email, push notification, etc. The output is the notification message that was sent. Specifically, the Twilio API is used to send a message to Mr. A's daughter saying, "Mom's water usage is abnormally low. Please check."

[0533] Step 6: Support collaboration

[0534] Based on the detected anomaly, the server also sends a notification to local support organizations. The inputs are the anomaly detection results and the support organization's contact information. The notification is sent via email or other communication method. The output is the notification sent to the support organization. Specifically, SendGrid is used to send an email to welfare services stating, "Water usage at Mr. A's residence on xxxx-chome has dropped abnormally. Urgent action is required."

[0535] In this way, a series of processes is carried out, from monitoring water usage to detecting abnormalities, sending emergency notifications, and coordinating support, through each step.

[0536] (Application example 1)

[0537] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0538] For elderly people living alone or those working away from home, it is important to detect abnormalities in water usage early and take appropriate action. However, conventional systems often lack the ability to detect abnormalities in real time or provide prompt notification. Furthermore, there was insufficient collaboration with local support organizations, which sometimes led to delayed early response. Furthermore, there was a lack of a way for users to easily understand their own water usage using smart devices. To solve these problems, a more efficient and reliable water usage monitoring system is needed.

[0539] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0540] In this invention, the server includes means for measuring water usage with a sensor and collecting data in real time, means for detecting abnormal usage patterns based on the collected data, means for sending a notification to a set emergency contact when an abnormal usage pattern is detected, means for promoting support activities in cooperation with local support organizations, as well as means for displaying water usage in real time on a smart device, means for detecting abnormalities using a machine learning algorithm, and means for providing a user interface through the smart device. This enables real-time monitoring of water usage, highly accurate detection of abnormalities using machine learning, and rapid notification and support collaboration.

[0541] "Water usage" is data measuring the amount of water used in homes and facilities.

[0542] A "sensor" is a device that is attached to a water meter and measures water usage in real time.

[0543] "Means for collecting data in real time" refers to the function of instantly receiving and storing water usage data sent from sensors.

[0544] An "abnormal usage pattern" is a unique data pattern that indicates usage that significantly deviates from normal water usage.

[0545] "Means for sending notifications to emergency contacts" is a function that immediately notifies the set contacts via email, SMS, etc. when an abnormality is detected.

[0546] "Means to promote support activities in cooperation with local support organizations" refers to a system that cooperates with local support groups and collaborators to ensure that necessary support can be provided quickly.

[0547] "Smart devices" refers to information devices that can connect to the Internet, such as smartphones, tablets, and smartwatches.

[0548] A "machine learning algorithm" is a computational method that learns patterns based on large amounts of data and makes automatic decisions.

[0549] A "user interface" is the screen or means by which a user operates an application and inputs and obtains information.

[0550] "Historical Data" refers to historical water usage data previously collected.

[0551] "Current data" refers to the latest ongoing water usage data.

[0552] "Multiple contacts" refers to multiple contact information (family, friends, administrator, etc.) registered in advance for sending notifications in the event of an abnormality.

[0553] A "local support network" is a network of support formed by collaborators and organizations within the local area.

[0554] MODE FOR CARRYING OUT THE INVENTION

[0555] The configuration and operation of a specific system for realizing this invention will be described. This system includes smart water meters installed in homes and facilities, as well as a server, cloud storage, a notification system, and smart devices.

[0556] Hardware and software used

[0557] Hardware

[0558] Smart water meter: A device that uses sensors to measure water usage in homes and facilities.

[0559] Server: Installed in the cloud, it collects data, analyzes it, and sends notifications. It uses Amazon EC2 instances.

[0560] Smart Device: The device used by the user, such as a smartphone or tablet.

[0561] software

[0562] Database: Data is stored using Amazon RDS and PostgreSQL.

[0563] AI algorithms: Anomaly detection models are built using TensorFlow and Scikit-learn.

[0564] Smartphone app: Develop cross-platform applications using Flutter.

[0565] Notification system: Uses Amazon SNS to send notifications.

[0566] Data collection

[0567] The sensor measures water usage in real time and sends the data to AWS IoT Core via MQTT protocol. The received data is stored in Amazon RDS via AWS Lambda. This data includes a timestamp and usage amount.

[0568] Anomaly detection

[0569] The server analyzes the collected data in real time and compares it with historical data to model normal usage patterns. Machine learning algorithms (such as Scikit-learn's Isolation Forest) are used to detect anomalies. If an anomaly is detected, the server sends a notification to emergency contacts and local assistance networks.

[0570] notification

[0571] If an anomaly is detected, AWS IoT Core will trigger a notification using Amazon SNS, which can be delivered via push notification, SMS, or email.

[0572] User Interface

[0573] Users can use the smartphone app to view past water usage, anomaly detection history, and real-time usage. The application was developed using Flutter and is compatible with both iOS and Android.

[0574] Specific examples

[0575] Cases of elderly people living alone

[0576] The server regularly monitors the water usage at Mr. A's home. Normally, Mr. A uses 40 liters of water per day, but for the past three days, it has been less than 5 liters per day. Detecting this abnormality, the server sends a notification to Mr. A's family, who are his emergency contacts, and to the management company. Upon receiving the notification, the family attempts to contact Mr. A, but receives no response, so they visit him in person. The management company also dispatches staff to check on the situation.

[0577] Prompt Sentence Examples

[0578] User registration prompt:

[0579] Welcome to Safe Water Check! This app monitors your water usage in real time and automatically notifies you if there are any irregularities. To use it, please enter the following information:

[0580] Emergency contact information (email address or phone number)

[0581] Local support network preference (e.g., local government or neighbors)

[0582] Pairing information for your home's water meter and smartphone

[0583] If you have any questions regarding usage, please feel free to let us know.

[0584] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0585] Program processing flow

[0586] Step 1: Collect water usage data

[0587] Sensors measure water usage in each home or facility in real time. The measured data is sent to AWS IoT Core via the MQTT protocol. The input is the measurement data (timestamp and usage amount), and the output is data passed to AWS Lambda.

[0588] Input: Timestamp and usage data measured by sensors

[0589] Data processing: Send data to AWS IoT Core via MQTT protocol

[0590] Output: Measurement data sent to AWS IoT Core

[0591] Step 2: Save your data

[0592] AWS Lambda receives the received data in real time and stores it in Amazon RDS (e.g., PostgreSQL). The input is the data sent from AWS IoT Core, and the output is a message that the data was successfully stored in the database.

[0593] Input: Timestamp and usage data sent from AWS IoT Core

[0594] Data processing: AWS Lambda receives the data, formats it, and stores it in Amazon RDS

[0595] Output: Message that saving to database was successful

[0596] Step 3: Analyze the data

[0597] The server analyzes the collected data in real time, comparing historical data with current data and using machine learning algorithms (e.g., Scikit-learn's Isolation Forest) to model normal usage patterns. The input is the stored data, and the output is the anomaly detection results.

[0598] Input: Historical and Current Data

[0599] Data processing: Anomaly detection using Scikit-learn's Isolation Forest

[0600] Output: Anomaly detection results (presence or absence of anomaly, type of anomaly)

[0601] Step 4: Anomaly detection

[0602] If the server detects an anomaly based on the analysis results, it summarizes the details of the anomaly. If the anomaly threshold is exceeded, it proceeds to the next step. The input is the anomaly detection result, and the output is notification information.

[0603] Input: Anomaly detection result

[0604] Data processing: Summarizing details of anomalies

[0605] Output: Notification information (details of the abnormality, detection date and time, recommended action)

[0606] Step 5: Sending notifications

[0607] The server uses Amazon SNS to send notifications to emergency contacts and local support networks when an anomaly is detected. The input is the notification information, and the output is a message that the notification has been sent.

[0608] Input: Notification information (details of the abnormality, detection date and time, recommended action)

[0609] Data processing: Format the notification content and send it via Amazon SNS

[0610] Output: Notification sent message

[0611] Step 6: Update the User Interface

[0612] The terminal (smart device) receives notifications from the server and updates the application interface. The user can check abnormality notifications and past data history through the app. The input is notification information and past data, and the output is an updated user interface.

[0613] Input: Notification information, past data

[0614] Data processing: updating and displaying the user interface

[0615] Output: Updated user interface

[0616] Step 7: Request assistance

[0617] The user can request additional assistance through the application. When assistance is requested, the information is sent to the server, which notifies the local assistance network. The input is the user's request for assistance, and the output is a notification to the local assistance network.

[0618] Input: User's request for assistance

[0619] Data processing: Send support request information to the server

[0620] Output: Notification to local support network

[0621] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0622] This invention is a system that not only monitors water usage and detects abnormal patterns, but also utilizes user emotional data to improve the accuracy of anomaly detection and emergency response. The system collects data in real time and has the ability to notify emergency contacts if an abnormality is detected. It also includes a mechanism to promote relief activities by linking with local support networks.

[0623] System configuration

[0624] The system mainly consists of the following components:

[0625] 1. Sensor

[0626] It is attached to the water meter of each home or facility to measure water usage.

[0627] 2. Emotion Engine

[0628] Emotions are assessed by analyzing the user's voice, facial expressions, and behavioral data.

[0629] 3. Server

[0630] Water usage data sent from sensors is collected, stored, and analyzed in real time.

[0631] The emotional data sent from the emotion engine is also analyzed.

[0632] Model normal usage patterns and detect anomalies.

[0633] 4. Terminal

[0634] It provides an interface for users to check water usage data, emotion data, and anomaly detection status.

[0635] 5. Emergency Notification System

[0636] If an abnormality is detected, a notification is sent to a pre-registered emergency contact.

[0637] 6. Regional Support Collaboration System

[0638] Work with local support organizations and request their cooperation when necessary.

[0639] Program processing

[0640] Data collection

[0641] The server receives water usage data sent from the sensors in real time and stores it in a database. Each data is time-stamped, and emotion data from the emotion engine is also collected at the same time.

[0642] Anomaly detection

[0643] The server uses the water usage data and emotion data to model typical usage and emotion patterns, comparing them with data from previous years and similar households, and uses machine learning algorithms to establish a baseline and determine whether the current data significantly deviates from this baseline.

[0644] notification

[0645] If an anomaly is detected, the server evaluates the urgency based on the emotion data and sends a notification to the configured emergency contacts. The notification includes the details of the anomaly, the emotion rating, the date and time of detection, and a recommended response. Notifications are sent via SMS, email, or push notification.

[0646] Specific examples

[0647] Example 1: Elderly people living alone

[0648] The server collects water usage data from Mr. A's home. Normally, Mr. A uses 40 liters of water per day, but for the past three days, he has used less than 5 liters per day. Furthermore, the emotion engine detects increased anxiety and stress from Mr. A's voice and behavior. This is deemed an abnormality, and the server sends a notification to Mr. A's daughter and the management company. Upon receiving the notification, the daughter attempts to contact Mr. A, but receives no response, so she visits him in person. Meanwhile, the management company also dispatches staff to check on the situation.

[0649] Example 2: Worker living away from home

[0650] The server collects water usage data from Mr. B's residence. Mr. B normally uses 60 liters of water on weekends, but this weekend it was less than 10 liters, which is determined to be abnormal. The emotion engine also detects that Mr. B looks tired from his facial expression. The server then sends a notification to his registered friends and his company's management department. The friend receives the notification and contacts Mr. B, but receives no response, so he visits his residence, and at the same time, the company's management department also begins to take action.

[0651] Local Support Network

[0652] When an abnormality is detected, the server combines the information with emotion data and sends a notification to local support organizations to prompt a prompt response. Support organizations will then carry out support activities such as visiting or making phone calls depending on the situation. Users can also request support via their devices.

[0653] This allows the system to detect anomalies by combining water usage data and user emotional data, and by prompting a quick response, it can prevent lonely deaths and other emergencies.

[0654] The processing flow will be explained below.

[0655] Step 1: Data collection

[0656] The server receives real-time water usage data sent from sensors. The sensors are attached to the water meters in each home and send the measurement data to the server at regular intervals (e.g., every minute). The received data is stored in a database, and each data is given a timestamp.

[0657] Step 2: Collecting Emotional Data

[0658] The emotion engine receives the user's voice, facial expression, and behavioral data from sensors and devices, and evaluates their emotions. The evaluated emotion data is sent to the server and also stored in a database.

[0659] Step 3: Modeling normal patterns

[0660] The server uses collected water usage and sentiment data to model typical usage and sentiment patterns using data from the previous year and similar households, and uses machine learning algorithms to establish a baseline.

[0661] Step 4: Anomaly detection

[0662] The server compares current usage and emotion data with baselines and uses statistical analysis to detect anomalies. For example, a persistently low water usage combined with stress or anxiety detected by the emotion engine is considered an anomaly. When an anomaly is detected, the event is recorded in an anomaly event log.

[0663] Step 5: Assess the severity

[0664] When an abnormality is detected, the server evaluates the urgency based on the emotional data. For example, if the intensity of anxiety or stress level is high, the urgency is judged to be high.

[0665] Step 6: Generate notifications

[0666] The server generates a notification message based on the severity rating, which includes the anomaly description, sentiment rating, detection date and time, and recommended action.

[0667] Step 7: Sending notifications

[0668] The server then sends the generated notification message to multiple emergency contacts, including the user, family, friends, landlords, management companies, etc. Notifications can be sent via SMS, email, or push notification.

[0669] Step 8: User confirmation and response

[0670] The user receives a notification and can check the water usage data, emotional data, and details of any abnormalities through their device. If the user is a family member, they can contact or visit the person directly. The landlord or management company can also respond in the same way.

[0671] Step 9: Linking local support networks

[0672] If an abnormality is detected, the server also sends a notification to local support organizations, who then promptly consider how to respond and provide the necessary assistance, such as by making regular visits or phone calls to check on the safety of the affected individuals.

[0673] Step 10: Follow up

[0674] After notification, the server continuously monitors the response status and notifies again as necessary. If the abnormality persists or no response is taken, it is possible to send another alert. The user can check the progress of support through their device and request any additional support that is required.

[0675] This allows the system to detect anomalies by combining water usage data with user emotional data, and by prompting a quick response, it can prevent lonely deaths and other emergencies.

[0676] Example 2

[0677] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0678] In modern society, the number of individuals whose health and safety are a concern is increasing, such as elderly people living alone and people working away from home. Under these circumstances, monitoring their lifestyle habits, detecting abnormalities early, and taking appropriate action is a major challenge. In particular, it is becoming increasingly important to detect emergencies from abnormalities in water usage, but existing systems still have issues with the accuracy of anomaly detection and the speed of response. In addition, there is a need for more accurate anomaly detection and emergency response by combining not only water usage data but also user emotional data.

[0679] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0680] In this invention, the server includes means for measuring water usage with a sensor and collecting data in real time, means for detecting abnormal usage patterns based on the collected data, means for sending a notification to a set emergency contact when an abnormal usage pattern is detected, means for analyzing the user's voice, facial expression, and behavior data to evaluate their emotions, means for improving the accuracy of anomaly detection and emergency response based on the emotion data, and means for collaborating with local support organizations to promote support activities. This not only improves the accuracy of anomaly detection, but also enables quick and appropriate responses.

[0681] "Water usage data" is information that indicates the amount of water consumed by each household or facility, and is measured in real time using sensors.

[0682] A "sensor" is a device that is attached to a water meter, measures water usage, and sends the data to a server.

[0683] The "server" is a computer system that receives water usage data and emotion data sent from the sensor, analyzes them, and detects abnormalities.

[0684] "Emotion data" is information that evaluates a user's emotions by analyzing their voice, facial expressions, and behavior, and is used to improve the accuracy of anomaly detection.

[0685] An "abnormal usage pattern" refers to fluctuations in water usage that deviate significantly from normal usage patterns, and refers to usage patterns that deviate from a baseline modeled based on data from the previous year or similar households.

[0686] "Emergency Contacts" are pre-configured contacts to send notifications when an abnormality is detected based on water usage data or emotion data.

[0687] "Local support organizations" are local groups and institutions that receive notifications when abnormalities are detected and work together to provide rapid response and support activities.

[0688] "Notifications" are messages that send warnings or information to emergency contacts or local support organizations when an anomaly is detected.

[0689] "Modeling" is the process of statistically representing normal usage patterns based on data from the previous year and similar households, and setting criteria for anomaly detection.

[0690] "Abnormality detection accuracy" refers to the ability to accurately detect abnormalities by combining water usage data and emotion data.

[0691] This invention is a system that not only monitors water usage and detects abnormal patterns, but also utilizes user emotional data to improve the accuracy of anomaly detection and emergency response. The system collects data in real time and has the ability to notify emergency contacts if an abnormality is detected. It also includes a mechanism to promote relief activities in collaboration with local relief organizations.

[0692] System configuration

[0693] The system mainly consists of the following components:

[0694] 1. Sensor

[0695] It is installed in the water meter of each home or facility to measure water usage, and transmits data using, for example, a LoRa module or Wi-Fi module.

[0696] 2. Emotion Engine

[0697] Emotions are assessed by analyzing the user's voice, facial expressions, and behavioral data. Specifically, emotion analysis is performed using the Emotion SDK.

[0698] 3. Server

[0699] Water usage data sent from sensors is collected, stored, and analyzed in real time.

[0700] The emotion data sent from the emotion engine is also analyzed, using machine learning algorithms such as TensorFlow and PyTorch.

[0701] Model normal usage patterns and detect anomalies.

[0702] 4. Terminal

[0703] It provides an interface for users to check water usage data, emotion data, and anomaly detection status using a smartphone app or web interface.

[0704] 5. Emergency Notification System

[0705] If an abnormality is detected, a notification will be sent to pre-registered emergency contacts using services such as Amazon SNS (Simple Notification Service).

[0706] 6. Regional Support Collaboration System

[0707] Work with local support organizations and request their cooperation when necessary.

[0708] Specific examples

[0709] Example 1: Elderly people living alone

[0710] The server collects water usage data from Mr. A's home. Normally, Mr. A uses 40 liters of water per day, but for the past three days, he has used less than 5 liters per day. Furthermore, the emotion engine detects increased anxiety and stress from Mr. A's voice and behavior. This is deemed an abnormality, and the server sends a notification to Mr. A's daughter and the management company. Upon receiving the notification, the daughter attempts to contact Mr. A, but receives no response, so she visits him in person. Meanwhile, the management company also dispatches staff to check on the situation.

[0711] Example 2: Worker living away from home

[0712] The server collects water usage data from Mr. B's residence. Mr. B normally uses 60 liters of water on weekends, but this weekend it was less than 10 liters, which is determined to be abnormal. The emotion engine also detects that Mr. B looks tired from his facial expression. The server then sends a notification to his registered friends and his company's management department. The friend receives the notification and contacts Mr. B, but receives no response, so he visits his residence, and at the same time, the company's management department also begins to take action.

[0713] Example prompts for generative AI models

[0714] Prompt statement example 1:

[0715] "Mr. A, an elderly person living alone, has been using significantly less water than usual for the past three days, and the emotion engine has detected increased anxiety and stress. What is the appropriate response for Mr. A in this situation?"

[0716] Prompt statement example 2:

[0717] "Mr. B, who is working away from home, used significantly less water than usual over the weekend, and the emotion engine detected his fatigue. Please advise whether an emergency response is required and what action would you recommend?"

[0718] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0719] Step 1: Data collection

[0720] The server receives water usage data sent from sensors in real time. The input is water usage data from sensors installed in each home or facility. Specifically, the sensors measure water usage every minute or every hour and send the data to the server via a LoRa module or Wi-Fi module. The server receives this data and assigns a timestamp to each data point. This allows the water usage data to be organized chronologically.

[0721] Step 2: Data storage and organization

[0722] The server stores the received data in a database. The input is water usage data with a timestamp. Specifically, the server uses a database (e.g., PostgreSQL) to store the data and organizes it based on the timestamp. The emotion data is also stored in the database. This allows for quick data access and analysis in subsequent analysis steps.

[0723] Step 3: Data analysis and anomaly detection

[0724] The server performs anomaly detection based on the stored data. The inputs are time-stamped water usage data and emotion data. Specifically, the server uses a machine learning algorithm (e.g., TensorFlow or PyTorch) to model normal usage patterns based on data from the previous year and data from similar households. It then analyzes whether the current water usage data significantly deviates from this baseline and detects anomalies. The output is the anomaly detection result (normal or abnormal).

[0725] Step 4: Evaluate the emotional data

[0726] The server improves the accuracy of anomaly detection based on emotion data. The input is emotion data obtained from the emotion engine. Specifically, it uses the emotion engine (e.g., Emotion SDK) to analyze the user's voice, facial expression, and behavioral data to evaluate their emotions. As a result, it outputs the user's stress level and anxiety as a numerical value. This allows the server to combine abnormalities in water usage with emotion data to evaluate the overall urgency.

[0727] Step 5: Notification Processing

[0728] If an anomaly is detected, the server sends a notification to the configured emergency contacts. The input is the anomaly detection result and emotion data. Specific behavior is to use an emergency notification system (e.g., Amazon SNS) to send a notification that includes the anomaly description, emotion rating, detection date and time, and recommended action. The output is a communication sent via SMS, email, or push notification.

[0729] Step 6: User Interface

[0730] Users can check water usage data and emotion data through a terminal. The input is the water usage data and emotion data stored in a database. Specifically, this data is displayed visually using a smartphone app or web interface. The output is a data display in a format that is easy for users to view. This allows users to easily check the anomaly detection status and past history data.

[0731] Step 7: Regional support collaboration

[0732] When an anomaly is detected, the server also sends a notification to the local support organization. The input is the anomaly detection result and emotion data. Specifically, the notification system is used to send information including the nature of the anomaly and its urgency to the local support organization. The output is a notification to the local support organization. This encourages a rapid response and ensures effective support activities.

[0733] (Application example 2)

[0734] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0735] To strengthen monitoring of elderly people and those living alone, it is necessary to not only monitor water usage but also to consider the user's emotional state. Current systems only detect abnormalities in water usage and require emergency responses based on changes in usage patterns, but this alone does not fully grasp the user's psychological and physical state. This also poses the risk of delaying emergency responses. To solve this problem, it is necessary to achieve more accurate monitoring and faster support.

[0736] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting and analyzing emotion data and water usage data, means for detecting abnormal usage patterns and combining them with the emotion data to determine the abnormality, means for assessing the urgency and sending a notification when an abnormality is detected, and means for promoting support activities in cooperation with local support organizations. This makes it possible to more accurately grasp the user's physical and psychological condition and to respond appropriately and quickly in an emergency.

[0737] "Water usage" means the amount of water consumed in a household or facility.

[0738] "Sensor" refers to a device used to measure water usage.

[0739] "Real-time" refers to the instantaneous collection and analysis of data.

[0740] "Data collection means" refers to the technological means for collecting water usage data through sensors.

[0741] "Abnormal usage pattern" means usage that significantly deviates from normal water usage.

[0742] "Anomaly detection measures" refers to technical measures that analyze collected data and detect abnormal usage patterns.

[0743] "Emergency Contact" means a contact configured to receive notification if an Anomaly is detected.

[0744] "Notification means" refers to the technical means for sending a notification to an emergency contact when an abnormality is detected.

[0745] "Community support organization" means an organization established to provide support in the local community.

[0746] "Support promotion measures" refer to technical measures for coordinating with local support organizations and implementing rapid support activities.

[0747] "User" means any individual or entity that uses the System.

[0748] "Emotion data" refers to the emotional state of the user as assessed from their voice, facial expression, and behavior.

[0749] "Evaluation means" refers to a technical means for analyzing emotion data and evaluating the user's emotional state.

[0750] "Emotion analysis" refers to the process of assessing a user's state of mind based on their emotional data.

[0751] "Urgency assessment means" refers to a technical means for assessing the urgency based on emotional data when an abnormality is detected.

[0752] "Registered Contacts" means contacts that are pre-configured within the System to receive notifications.

[0753] This invention is a system that monitors water usage and user emotion data, detects abnormalities, and promotes emergency response. The system is composed of the following main components and processing means.

[0754] System configuration

[0755] 1. Sensor

[0756] This is a sensor that is attached to the water meter of each home or facility to measure water usage.

[0757] 2. Emotion Engine

[0758] This software collects the user's voice, facial expression, and behavioral data, and analyzes and evaluates their emotions.

[0759] 3. Server

[0760] The system receives, stores, and analyzes water usage data and emotion data in real time. It detects abnormal usage patterns and sends notifications to emergency contacts if an abnormality is detected. It also assesses the level of urgency based on emotion data and connects with local support organizations.

[0761] 4. Terminal

[0762] It provides an interface for users to check water usage data, emotion data, and anomaly detection status. The terminal is a smartphone application through which users can check and set data.

[0763] Data collection

[0764] The server collects water usage data in real time from sensors installed in each home and facility. In parallel with this, the emotion engine collects the user's voice, facial expressions, and behavioral data to generate data that evaluates their emotions. The collected data is time-stamped and stored in the server's database.

[0765] Anomaly detection

[0766] The server analyzes water usage data and sentiment data to model normal usage patterns, comparing them with data from previous years and similar households, and uses machine learning algorithms to establish a baseline and determine whether the current data significantly deviates from this baseline.

[0767] Notification and Emergency Response

[0768] If an anomaly is detected, the server evaluates the urgency level based on the emotion data and sends a notification to the configured emergency contacts. The notification includes the nature of the anomaly, the emotion rating, the date and time of detection, and a recommended response. The notification is sent via SMS, email, or push notification. In addition, the server sends similar information to local support organizations to encourage a prompt response.

[0769] Specific examples

[0770] Example 1: Elderly people living alone

[0771] The server collects water usage data for User A's home. User A normally uses 40 liters of water per day, but for the past three days, it has been less than 5 liters per day. Furthermore, the emotion engine detects increased anxiety and stress from User A's voice and behavior. This is deemed an abnormality, and the server sends a notification to User A's family and the administrator. The family members who receive the notification try to contact User A, but receive no response, so they visit in person. Meanwhile, the administrator also dispatches staff to check on the situation.

[0772] Example 2: Worker living away from home

[0773] The server collects water usage data from User B's home. User B normally uses 60 liters of water on weekends, but this weekend it was less than 10 liters, which is determined to be abnormal. The emotion engine also detects that User B looks tired from his facial expression. The server sends a notification to registered friends and the management department. The friend receives the notification and contacts User B, but receives no response, so the server visits User B's home, and the management department also begins to respond.

[0774] Generative AI model prompt example

[0775] Please provide your current and past water usage data. Also provide your emotional data. We will notify you if an abnormality is detected or if your emotional state indicates 'sadness' or 'stress'.

[0776] In this way, to implement the invention, it is necessary to build a system that properly links sensors, emotion engines, servers, and terminals to detect abnormalities and quickly respond to emergencies. This system comprehensively monitors the user's psychological and physical state, thereby enhancing safety.

[0777] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0778] Step 1:

[0779] Sensors are attached to water meters in homes and facilities and measure water usage in real time. The sensors collect measurement data at regular intervals and send it to a server. The input is water usage data, and the output is the measurement data sent to the server.

[0780] Step 2:

[0781] The emotion engine collects the user's voice, facial expression, and behavioral data, and analyzes and evaluates their emotions. The emotion engine acquires user data using devices such as cameras and microphones, and evaluates the user's emotions using an emotion analysis algorithm. The input is the user's voice, facial expression, and behavioral data, and the output is emotion evaluation data.

[0782] Step 3:

[0783] The server receives and stores water usage data sent from the sensor and emotion data sent from the emotion engine in real time. These data are recorded in a database with a timestamp. The input is water usage data and emotion data, and the output is the data stored in the database.

[0784] Step 4:

[0785] The server models normal usage patterns based on the collected data, references historical data and data from similar households, and uses machine learning algorithms to set a baseline. The input is historical and current data, and the output is the set baseline.

[0786] Step 5:

[0787] The server determines whether the current data significantly deviates from the baseline and detects anomalous usage patterns. The inputs are current water usage data and emotion data, and the output is the anomaly detection results.

[0788] Step 6:

[0789] When an anomaly is detected, the server evaluates the urgency level based on the emotion data. If the urgency level is high, a notification is sent to the configured emergency contacts. The notification includes the details of the anomaly, the emotion rating, the date and time of detection, and a recommended response. The input is the anomaly detection result and the emotion rating data, and the output is an emergency notification.

[0790] Step 7:

[0791] The server also connects with local support organizations and promotes support activities as needed. Support organizations are sent information on the nature of the abnormality along with an assessment of the level of urgency, and are required to respond quickly. The input is emergency notification information, and the output is information to connect to support organizations.

[0792] Step 8:

[0793] Users can use the terminal to check water usage data, emotion data, and anomaly detection status. An interface is provided on the terminal, allowing users to check their own data in real time and configure the system. The input is data sent from the server, and the output is information displayed on the user's terminal.

[0794] For specific actions, the following prompt sentence example is used:

[0795] Please provide your current and past water usage data. Also provide your emotional data. We will notify you if an abnormality is detected or if your emotional state indicates 'sadness' or 'stress'.

[0796] 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 a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0797] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0798] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the smart glasses 214.

[0799] [Third embodiment]

[0800] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0801] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0802] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0803] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0804] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0805] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0806] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0807] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0808] The specific processing program 56 is an example of a "program" according to the technology of the present 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.

[0809] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0810] In the headset type terminal 314, a reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. 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 process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0811] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. 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."

[0812] This invention is a system that monitors water usage and detects abnormal patterns. The system collects data in real time and notifies emergency contacts if an abnormality is detected. It also includes a mechanism to promote relief activities by linking with local support networks.

[0813] System configuration

[0814] The system mainly consists of the following components:

[0815] 1. Sensor

[0816] It is attached to the water meter of each home or facility to measure water usage.

[0817] 2. Server

[0818] It collects, stores, and analyzes data sent from sensors in real time.

[0819] Model normal usage patterns and detect anomalies.

[0820] 3. Terminal

[0821] Provides an interface for users to check water usage data and anomaly detection status.

[0822] 4. Emergency Notification System

[0823] If an abnormality is detected, a notification is sent to a pre-registered emergency contact.

[0824] 5. Regional Support Collaboration System

[0825] Work with local support organizations and request their cooperation when necessary.

[0826] Program processing

[0827] Data collection

[0828] The server receives real-time water usage data sent from the sensors and stores it in a database, including timestamps and usage amounts.

[0829] Anomaly detection

[0830] The server uses the collected data to model normal usage patterns, comparing it with data from the previous year and similar households, and uses machine learning algorithms to establish a baseline and determine whether current usage significantly deviates from this baseline.

[0831] notification

[0832] If an anomaly is detected, the server will send a notification to emergency contacts. The notification will include a description of the anomaly, the date and time it was detected, and a recommended action to take. Notifications can be sent via SMS, email, or push notification.

[0833] Specific examples

[0834] Example 1: Elderly people living alone

[0835] The server collects water usage data for Mr. A's home. Normally, Mr. A uses 40 liters of water per day, but for the past three days, it has been less than 5 liters per day. This is deemed abnormal, and the server sends a notification to Mr. A's daughter and the management company. Upon receiving the notification, the daughter tries to contact Mr. A, but receives no response, so she visits him in person. Meanwhile, the management company also dispatches staff to check the situation.

[0836] Example 2: Worker living away from home

[0837] The server collects water usage data from Mr. B's residence. Mr. B usually uses 60 liters of water on weekends, but this weekend he used less than 10 liters, which is considered abnormal. The server sends a notification to his registered friends and his company's management department. The friend receives the notification and contacts Mr. B. Since there is no response, the friend visits Mr. B's residence, and at the same time, the company's management department also begins to take action.

[0838] Local Support Network

[0839] When an abnormality is detected, the server also sends a notification to local support organizations to promptly respond. Support organizations will then carry out support activities such as visiting or making phone calls depending on the situation. Users can also request support via their devices.

[0840] This allows the system to detect abnormalities in real time and provide the ability to prompt a quick response, contributing to the prevention of lonely deaths.

[0841] The processing flow will be explained below.

[0842] Step 1: Data collection

[0843] The server receives real-time water usage data from sensors. In this system, sensors are attached to water meters in each home and transmit the measured data at regular intervals (e.g., every minute) to the server. The server stores the received data in a database and assigns a timestamp to each data point.

[0844] Step 2: Data analysis

[0845] The server models normal usage patterns based on the collected data, references data from previous years and similar households, and uses machine learning algorithms to establish a baseline. It then compares current data against the modeled normal patterns to detect abnormal usage patterns.

[0846] Step 3: Anomaly detection

[0847] The server uses statistical analysis techniques to determine whether current usage data deviates from a set baseline. For example, sustained low usage or sudden fluctuations are detected as an anomaly. If an anomaly is found, the event is recorded in an anomaly event log.

[0848] Step 4: Generate notifications

[0849] When an anomaly is detected, the server consults the configured emergency contact information, which can include the user, family, friends, landlord, management company, etc. The server generates a notification message containing the anomaly, the date and time it was detected, and a recommended action to take.

[0850] Step 5: Sending notifications

[0851] The server then sends the generated notification message to each contact via SMS, email, push notification, etc. For example, email is sent using the SMTP protocol.

[0852] Step 6: User confirmation and response

[0853] The user receives a notification and can check the water usage data and details of any abnormalities through their device. If the user is a family member, they can contact them directly or visit them. Landlords and management companies can also check the situation and visit the site if necessary.

[0854] Step 7: Coordinating local support networks

[0855] If an abnormality is detected, the server also sends a notification to local support organizations, who then promptly consider how to respond and provide the necessary assistance, such as making regular visits or calling to check on the safety of the affected individuals.

[0856] Step 8: Follow up

[0857] After an abnormality is notified, the server tracks the response status and notifies again if necessary. For example, if the abnormality continues or no response is taken, it is possible to send another alert. The user can check the support status through their device and request any additional support needed.

[0858] This allows the system to detect abnormalities in water usage early and prompt a quick response, preventing lonely deaths and other emergencies.

[0859] Example 1

[0860] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0861] In modern society, there are increasing cases of elderly people living alone or people working away from home being unable to respond quickly to abnormal situations, putting their lives at risk. To address these situations, a system is needed that can detect abnormalities in water usage, which is a part of daily life, in real time and quickly notify appropriate contacts and support organizations. Existing systems have issues that are not fully addressed in terms of the accuracy of abnormality detection, the speed of notification, and the coordination of responses.

[0862] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0863] In this invention, the server includes means for receiving data in real time from sensors that measure water usage, means for storing the received data in a database, means for modeling normal usage patterns using a machine learning algorithm based on the stored data and detecting abnormal usage patterns, means for sending a notification to a set emergency contact when an abnormal usage pattern is detected, and means for coordinating with local support organizations to promote support activities. This makes it possible to quickly and accurately detect abnormalities in water usage and immediately notify necessary support.

[0864] A "sensor" is a device that measures water usage and transmits the data in real time.

[0865] A "database" is a system for storing and managing collected data.

[0866] A "machine learning algorithm" is a set of mathematical techniques that use historical data to model normal usage patterns and detect anomalous patterns.

[0867] An "abnormal usage pattern" refers to fluctuations in water usage that deviate significantly from normal usage patterns.

[0868] "Emergency contacts" are pre-defined contacts to whom notifications are sent when an abnormality is detected, and include family members, friends, and administrators.

[0869] A "community support organization" is an organization made up of local groups and institutions that provide support activities in emergencies.

[0870] "Real time" means processing an event at the exact moment it occurs.

[0871] MODE FOR CARRYING OUT THE INVENTION

[0872] This invention is a system that monitors water usage and detects abnormal patterns. The system collects data in real time and notifies emergency contacts if an abnormality is detected. It also includes a mechanism to link with local support networks to facilitate relief efforts.

[0873] System configuration

[0874] The system mainly consists of the following components:

[0875] 1. Sensor

[0876] It is attached to the water meter of each home or facility to measure water usage.

[0877] 2. Server

[0878] It collects, stores, and analyzes data sent from sensors in real time.

[0879] Model normal usage patterns and detect anomalies.

[0880] 3. Terminal

[0881] Provides an interface for users to check water usage data and anomaly detection status.

[0882] 4. Emergency Notification System

[0883] If an abnormality is detected, a notification is sent to a pre-registered emergency contact.

[0884] 5. Regional Support Collaboration System

[0885] Work with local support organizations and request their cooperation when necessary.

[0886] Data collection and storage

[0887] The server receives real-time water usage data sent from the sensors. Specifically, sensors installed in each home and facility measure usage data every minute and send it wirelessly to the server. For example, if the sensor in home A sends data such as "3 liters used at 2023-10-01 08:00:00," the server receives this data. The server receives the data and stores it in a database. The stored data includes a timestamp, usage amount, sensor ID, etc., and is saved in a format such as "3 liters used by sensor ID: A123 at 2023-10-01 08:00:00."

[0888] Anomaly detection

[0889] The server analyzes past usage data stored in a database and models normal usage patterns using a machine learning algorithm (e.g., using TensorFlow). Specifically, it uses data from the past year to set a baseline for normal usage. If the current data deviates significantly from this baseline, it is determined to be abnormal. For example, if person A's normal daily usage is 40 liters, but has been less than 5 liters for the past three days, it is determined to be abnormal.

[0890] emergency notification

[0891] If an abnormality is detected, the server automatically sends a notification to emergency contacts. The notification can be sent in the form of SMS, email, or push notification. For example, an SMS message saying "Mom's water usage is abnormally low. Please check it" is sent to Mr. A's daughter. Specifically, the message is sent to registered contacts using the Twilio API.

[0892] Support and collaboration

[0893] Based on the information about the detected abnormality, the server also sends a notification to local support organizations. For example, an email may be sent to the local welfare service saying, "Water usage at Mr. A's house on xxxx-chome has dropped abnormally. Urgent action is required." Users can also request support using their devices (smartphones or PCs). When a user opens a dedicated app and presses the "Request Support" button, a notification is automatically sent to the local support organization.

[0894] Hardware and software used

[0895] Hardware: sensors, servers, user devices (smartphones, PCs)

[0896] Software: Database systems (e.g., MySQL, PostgreSQL), machine learning models (e.g., TensorFlow, Scikit-learn), notification systems (e.g., Twilio for SMS, SendGrid for Email)

[0897] Specific examples

[0898] Example 1: Elderly people living alone

[0899] The server collects water usage data from Mr. A's home. Normally, Mr. A uses 40 liters of water per day, but for the past three days, it has been less than 5 liters per day. This is deemed abnormal, and the server sends a notification to Mr. A's daughter and the management agency. Upon receiving the notification, Mr. A's daughter tries to contact Mr. A, but receives no response, so she visits him in person. Meanwhile, the management agency also dispatches staff to check the situation.

[0900] Example 2: Worker living away from home

[0901] The server collects water usage data from Mr. B's residence. Mr. B usually uses 60 liters of water on weekends, but this weekend he used less than 10 liters, which is considered abnormal. The server sends a notification to his registered friends and the management agency. The friend receives the notification and contacts Mr. B. Since there is no response, the friend visits Mr. B's residence, and the management agency also begins to take action.

[0902] Prompt Sentence Examples

[0903] "Mr. A, an elderly person living alone, has noticed that his water usage has dropped from the usual 40 liters to less than 5 liters. Please write code that will treat this as an abnormality and send a notification to an emergency contact."

[0904] Example of prompt input:

[0905] "Please explain in detail the processing steps of a program in which a server detects anomalies in water usage data collected from sensors and sends a notification to emergency contacts if an abnormality is detected. Also, please recall the case of an elderly person living alone as a concrete example."

[0906] This system ensures the safety and security of users by sending data collected by sensors to a server in real time and quickly sending emergency notifications if an abnormality is detected.

[0907] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0908] Program processing

[0909] Step 1: Data collection

[0910] The server receives real-time data sent from the sensors. The input is water usage data measured by sensors attached to water meters in each home or facility. The data includes a timestamp, the amount used, and the sensor ID. The output is raw data transferred to the server in real time. Specifically, the sensor sends data to the server such as "3 liters used with sensor ID: A123 on 2023-10-01 08:00:00."

[0911] Step 2: Save data

[0912] The server stores the received data in a database. The input is the real-time data received in step 1. When stored in the database, the data is structured in the format of a timestamp, amount used, and sensor ID. As an output, the stored data is accumulated in the database. Specifically, the data "3 liters used with sensor ID: A123 on 2023-10-01 08:00:00" is registered in the database.

[0913] Step 3: Data analysis

[0914] The server analyzes past water usage data stored in a database. The inputs are past usage data and current real-time data. A machine learning algorithm is used to model normal usage patterns and perform analysis to detect anomalies. The output is the baseline usage pattern and an anomaly determination result when current usage deviates from the baseline. Specifically, the server sets a baseline based on data from the past year, such as "Person A's normal usage is 40 liters per day," and compares this with current usage to detect anomalies.

[0915] Step 4: Anomaly detection

[0916] The server detects anomalies based on the results of the data analysis in step 3. The inputs are the analyzed usage pattern and the current usage amount. A certain threshold is set, and if the current usage amount exceeds that threshold, it is determined to be an anomaly. The output is a flag indicating whether an anomaly has been detected. Specifically, it determines that an anomaly has occurred if "usage amount for the past three days has been less than 5 liters per day."

[0917] Step 5: Emergency Notification

[0918] If an anomaly is detected, the server sends a notification to the emergency contact. The inputs are the anomaly detection result and the pre-defined emergency contact information. The notification is sent in the form of SMS, email, push notification, etc. The output is the notification message that was sent. Specifically, the Twilio API is used to send a message to Mr. A's daughter saying, "Mom's water usage is abnormally low. Please check."

[0919] Step 6: Support collaboration

[0920] Based on the detected anomaly, the server also sends a notification to local support organizations. The inputs are the anomaly detection results and the support organization's contact information. The notification is sent via email or other communication method. The output is the notification sent to the support organization. Specifically, SendGrid is used to send an email to welfare services stating, "Water usage at Mr. A's residence on xxxx-chome has dropped abnormally. Urgent action is required."

[0921] In this way, a series of processes is carried out, from monitoring water usage to detecting abnormalities, sending emergency notifications, and coordinating support, through each step.

[0922] (Application example 1)

[0923] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0924] For elderly people living alone or those working away from home, it is important to detect abnormalities in water usage early and take appropriate action. However, conventional systems often lack the ability to detect abnormalities in real time or provide prompt notification. Furthermore, there was insufficient collaboration with local support organizations, which sometimes led to delayed early response. Furthermore, there was a lack of a way for users to easily understand their own water usage using smart devices. To solve these problems, a more efficient and reliable water usage monitoring system is needed.

[0925] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0926] In this invention, the server includes means for measuring water usage with a sensor and collecting data in real time, means for detecting abnormal usage patterns based on the collected data, means for sending a notification to a set emergency contact when an abnormal usage pattern is detected, means for promoting support activities in cooperation with local support organizations, as well as means for displaying water usage in real time on a smart device, means for detecting abnormalities using a machine learning algorithm, and means for providing a user interface through the smart device. This enables real-time monitoring of water usage, highly accurate detection of abnormalities using machine learning, and rapid notification and support collaboration.

[0927] "Water usage" is data measuring the amount of water used in homes and facilities.

[0928] A "sensor" is a device that is attached to a water meter and measures water usage in real time.

[0929] "Means for collecting data in real time" refers to the function of instantly receiving and storing water usage data sent from sensors.

[0930] An "abnormal usage pattern" is a unique data pattern that indicates usage that significantly deviates from normal water usage.

[0931] "Means for sending notifications to emergency contacts" is a function that immediately notifies the set contacts via email, SMS, etc. when an abnormality is detected.

[0932] "Means to promote support activities in cooperation with local support organizations" refers to a system that cooperates with local support groups and collaborators to ensure that necessary support can be provided quickly.

[0933] "Smart devices" refers to information devices that can connect to the Internet, such as smartphones, tablets, and smartwatches.

[0934] A "machine learning algorithm" is a computational method that learns patterns based on large amounts of data and makes automatic decisions.

[0935] A "user interface" is the screen or means by which a user operates an application and inputs and obtains information.

[0936] "Historical Data" refers to historical water usage data previously collected.

[0937] "Current data" refers to the latest ongoing water usage data.

[0938] "Multiple contacts" refers to multiple contact information (family, friends, administrator, etc.) registered in advance for sending notifications in the event of an abnormality.

[0939] A "local support network" is a network of support formed by collaborators and organizations within the local area.

[0940] MODE FOR CARRYING OUT THE INVENTION

[0941] The configuration and operation of a specific system for realizing this invention will be described. This system includes smart water meters installed in homes and facilities, as well as a server, cloud storage, a notification system, and smart devices.

[0942] Hardware and software used

[0943] Hardware

[0944] Smart water meter: A device that uses sensors to measure water usage in homes and facilities.

[0945] Server: Installed in the cloud, it collects data, analyzes it, and sends notifications. It uses Amazon EC2 instances.

[0946] Smart Device: The device used by the user, such as a smartphone or tablet.

[0947] software

[0948] Database: Data is stored using Amazon RDS and PostgreSQL.

[0949] AI algorithms: Anomaly detection models are built using TensorFlow and Scikit-learn.

[0950] Smartphone app: Develop cross-platform applications using Flutter.

[0951] Notification system: Uses Amazon SNS to send notifications.

[0952] Data collection

[0953] The sensor measures water usage in real time and sends the data to AWS IoT Core via MQTT protocol. The received data is stored in Amazon RDS via AWS Lambda. This data includes a timestamp and usage amount.

[0954] Anomaly detection

[0955] The server analyzes the collected data in real time and compares it with historical data to model normal usage patterns. Machine learning algorithms (such as Scikit-learn's Isolation Forest) are used to detect anomalies. If an anomaly is detected, the server sends a notification to emergency contacts and local assistance networks.

[0956] notification

[0957] If an anomaly is detected, AWS IoT Core will trigger a notification using Amazon SNS, which can be delivered via push notification, SMS, or email.

[0958] User Interface

[0959] Users can use the smartphone app to view past water usage, anomaly detection history, and real-time usage. The application was developed using Flutter and is compatible with both iOS and Android.

[0960] Specific examples

[0961] Cases of elderly people living alone

[0962] The server regularly monitors the water usage at Mr. A's home. Normally, Mr. A uses 40 liters of water per day, but for the past three days, it has been less than 5 liters per day. Detecting this abnormality, the server sends a notification to Mr. A's family, who are his emergency contacts, and to the management company. Upon receiving the notification, the family attempts to contact Mr. A, but receives no response, so they visit him in person. The management company also dispatches staff to check on the situation.

[0963] Prompt Sentence Examples

[0964] User registration prompt:

[0965] Welcome to Safe Water Check! This app monitors your water usage in real time and automatically notifies you if there are any irregularities. To use it, please enter the following information:

[0966] Emergency contact information (email address or phone number)

[0967] Local support network preference (e.g., local government or neighbors)

[0968] Pairing information for your home's water meter and smartphone

[0969] If you have any questions regarding usage, please feel free to let us know.

[0970] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0971] Program processing flow

[0972] Step 1: Collect water usage data

[0973] Sensors measure water usage in each home or facility in real time. The measured data is sent to AWS IoT Core via the MQTT protocol. The input is the measurement data (timestamp and usage amount), and the output is data passed to AWS Lambda.

[0974] Input: Timestamp and usage data measured by sensors

[0975] Data processing: Send data to AWS IoT Core via MQTT protocol

[0976] Output: Measurement data sent to AWS IoT Core

[0977] Step 2: Save your data

[0978] AWS Lambda receives the received data in real time and stores it in Amazon RDS (e.g., PostgreSQL). The input is the data sent from AWS IoT Core, and the output is a message that the data was successfully stored in the database.

[0979] Input: Timestamp and usage data sent from AWS IoT Core

[0980] Data processing: AWS Lambda receives the data, formats it, and stores it in Amazon RDS

[0981] Output: Message that saving to database was successful

[0982] Step 3: Analyze the data

[0983] The server analyzes the collected data in real time, comparing historical data with current data and using machine learning algorithms (e.g., Scikit-learn's Isolation Forest) to model normal usage patterns. The input is the stored data, and the output is the anomaly detection results.

[0984] Input: Historical and Current Data

[0985] Data processing: Anomaly detection using Scikit-learn's Isolation Forest

[0986] Output: Anomaly detection results (presence or absence of anomaly, type of anomaly)

[0987] Step 4: Anomaly detection

[0988] If the server detects an anomaly based on the analysis results, it summarizes the details of the anomaly. If the anomaly threshold is exceeded, it proceeds to the next step. The input is the anomaly detection result, and the output is notification information.

[0989] Input: Anomaly detection result

[0990] Data processing: Summarizing details of anomalies

[0991] Output: Notification information (details of the abnormality, detection date and time, recommended action)

[0992] Step 5: Sending notifications

[0993] The server uses Amazon SNS to send notifications to emergency contacts and local support networks when an anomaly is detected. The input is the notification information, and the output is a message that the notification has been sent.

[0994] Input: Notification information (details of the abnormality, detection date and time, recommended action)

[0995] Data processing: Format the notification content and send it via Amazon SNS

[0996] Output: Notification sent message

[0997] Step 6: Update the User Interface

[0998] The terminal (smart device) receives notifications from the server and updates the application interface. The user can check abnormality notifications and past data history through the app. The input is notification information and past data, and the output is an updated user interface.

[0999] Input: Notification information, past data

[1000] Data processing: updating and displaying the user interface

[1001] Output: Updated user interface

[1002] Step 7: Request assistance

[1003] The user can request additional assistance through the application. When assistance is requested, the information is sent to the server, which notifies the local assistance network. The input is the user's request for assistance, and the output is a notification to the local assistance network.

[1004] Input: User's request for assistance

[1005] Data processing: Send support request information to the server

[1006] Output: Notification to local support network

[1007] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1008] This invention is a system that not only monitors water usage and detects abnormal patterns, but also utilizes user emotional data to improve the accuracy of anomaly detection and emergency response. The system collects data in real time and has the ability to notify emergency contacts if an abnormality is detected. It also includes a mechanism to promote relief activities by linking with local support networks.

[1009] System configuration

[1010] The system mainly consists of the following components:

[1011] 1. Sensor

[1012] It is attached to the water meter of each home or facility to measure water usage.

[1013] 2. Emotion Engine

[1014] Emotions are assessed by analyzing the user's voice, facial expressions, and behavioral data.

[1015] 3. Server

[1016] Water usage data sent from sensors is collected, stored, and analyzed in real time.

[1017] The emotional data sent from the emotion engine is also analyzed.

[1018] Model normal usage patterns and detect anomalies.

[1019] 4. Terminal

[1020] It provides an interface for users to check water usage data, emotion data, and anomaly detection status.

[1021] 5. Emergency Notification System

[1022] If an abnormality is detected, a notification is sent to a pre-registered emergency contact.

[1023] 6. Regional Support Collaboration System

[1024] Work with local support organizations and request their cooperation when necessary.

[1025] Program processing

[1026] Data collection

[1027] The server receives water usage data sent from the sensors in real time and stores it in a database. Each data is time-stamped, and emotion data from the emotion engine is also collected at the same time.

[1028] Anomaly detection

[1029] The server uses the water usage data and emotion data to model typical usage and emotion patterns, comparing them with data from previous years and similar households, and uses machine learning algorithms to establish a baseline and determine whether the current data significantly deviates from this baseline.

[1030] notification

[1031] If an anomaly is detected, the server evaluates the urgency based on the emotion data and sends a notification to the configured emergency contacts. The notification includes the details of the anomaly, the emotion rating, the date and time of detection, and a recommended response. Notifications are sent via SMS, email, or push notification.

[1032] Specific examples

[1033] Example 1: Elderly people living alone

[1034] The server collects water usage data from Mr. A's home. Normally, Mr. A uses 40 liters of water per day, but for the past three days, he has used less than 5 liters per day. Furthermore, the emotion engine detects increased anxiety and stress from Mr. A's voice and behavior. This is deemed an abnormality, and the server sends a notification to Mr. A's daughter and the management company. Upon receiving the notification, the daughter attempts to contact Mr. A, but receives no response, so she visits him in person. Meanwhile, the management company also dispatches staff to check on the situation.

[1035] Example 2: Worker living away from home

[1036] The server collects water usage data from Mr. B's residence. Mr. B normally uses 60 liters of water on weekends, but this weekend it was less than 10 liters, which is determined to be abnormal. The emotion engine also detects that Mr. B looks tired from his facial expression. The server then sends a notification to his registered friends and his company's management department. The friend receives the notification and contacts Mr. B, but receives no response, so he visits his residence, and at the same time, the company's management department also begins to take action.

[1037] Local Support Network

[1038] When an abnormality is detected, the server combines the information with emotion data and sends a notification to local support organizations to prompt a prompt response. Support organizations will then carry out support activities such as visiting or making phone calls depending on the situation. Users can also request support via their devices.

[1039] This allows the system to detect anomalies by combining water usage data and user emotional data, and by prompting a quick response, it can prevent lonely deaths and other emergencies.

[1040] The processing flow will be explained below.

[1041] Step 1: Data collection

[1042] The server receives real-time water usage data sent from sensors. The sensors are attached to the water meters in each home and send the measurement data to the server at regular intervals (e.g., every minute). The received data is stored in a database, and each data is given a timestamp.

[1043] Step 2: Collecting Emotional Data

[1044] The emotion engine receives the user's voice, facial expression, and behavioral data from sensors and devices, and evaluates their emotions. The evaluated emotion data is sent to the server and also stored in a database.

[1045] Step 3: Modeling normal patterns

[1046] The server uses collected water usage and sentiment data to model typical usage and sentiment patterns using data from the previous year and similar households, and uses machine learning algorithms to establish a baseline.

[1047] Step 4: Anomaly detection

[1048] The server compares current usage and emotion data with baselines and uses statistical analysis to detect anomalies. For example, a persistently low water usage combined with stress or anxiety detected by the emotion engine is considered an anomaly. When an anomaly is detected, the event is recorded in an anomaly event log.

[1049] Step 5: Assess the severity

[1050] When an abnormality is detected, the server evaluates the urgency based on the emotional data. For example, if the intensity of anxiety or stress level is high, the urgency is judged to be high.

[1051] Step 6: Generate notifications

[1052] The server generates a notification message based on the severity rating, which includes the anomaly description, sentiment rating, detection date and time, and recommended action.

[1053] Step 7: Sending notifications

[1054] The server then sends the generated notification message to multiple emergency contacts, including the user, family, friends, landlords, management companies, etc. Notifications can be sent via SMS, email, or push notification.

[1055] Step 8: User confirmation and response

[1056] The user receives a notification and can check the water usage data, emotional data, and details of any abnormalities through their device. If the user is a family member, they can contact or visit the person directly. The landlord or management company can also respond in the same way.

[1057] Step 9: Linking local support networks

[1058] If an abnormality is detected, the server also sends a notification to local support organizations, who then promptly consider how to respond and provide the necessary assistance, such as by making regular visits or phone calls to check on the safety of the affected individuals.

[1059] Step 10: Follow up

[1060] After notification, the server continuously monitors the response status and notifies again as necessary. If the abnormality persists or no response is taken, it is possible to send another alert. The user can check the progress of support through their device and request any additional support that is required.

[1061] This allows the system to detect anomalies by combining water usage data with user emotional data, and by prompting a quick response, it can prevent lonely deaths and other emergencies.

[1062] Example 2

[1063] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1064] In modern society, the number of individuals whose health and safety are a concern is increasing, such as elderly people living alone and people working away from home. Under these circumstances, monitoring their lifestyle habits, detecting abnormalities early, and taking appropriate action is a major challenge. In particular, it is becoming increasingly important to detect emergencies from abnormalities in water usage, but existing systems still have issues with the accuracy of anomaly detection and the speed of response. In addition, there is a need for more accurate anomaly detection and emergency response by combining not only water usage data but also user emotional data.

[1065] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1066] In this invention, the server includes means for measuring water usage with a sensor and collecting data in real time, means for detecting abnormal usage patterns based on the collected data, means for sending a notification to a set emergency contact when an abnormal usage pattern is detected, means for analyzing the user's voice, facial expression, and behavior data to evaluate their emotions, means for improving the accuracy of anomaly detection and emergency response based on the emotion data, and means for collaborating with local support organizations to promote support activities. This not only improves the accuracy of anomaly detection, but also enables quick and appropriate responses.

[1067] "Water usage data" is information that indicates the amount of water consumed by each household or facility, and is measured in real time using sensors.

[1068] A "sensor" is a device that is attached to a water meter, measures water usage, and sends the data to a server.

[1069] The "server" is a computer system that receives water usage data and emotion data sent from the sensor, analyzes them, and detects abnormalities.

[1070] "Emotion data" is information that evaluates a user's emotions by analyzing their voice, facial expressions, and behavior, and is used to improve the accuracy of anomaly detection.

[1071] An "abnormal usage pattern" refers to fluctuations in water usage that deviate significantly from normal usage patterns, and refers to usage patterns that deviate from a baseline modeled based on data from the previous year or similar households.

[1072] "Emergency Contacts" are pre-configured contacts to send notifications when an abnormality is detected based on water usage data or emotion data.

[1073] "Local support organizations" are local groups and institutions that receive notifications when abnormalities are detected and work together to provide rapid response and support activities.

[1074] "Notifications" are messages that send warnings or information to emergency contacts or local support organizations when an anomaly is detected.

[1075] "Modeling" is the process of statistically representing normal usage patterns based on data from the previous year and similar households, and setting criteria for anomaly detection.

[1076] "Abnormality detection accuracy" refers to the ability to accurately detect abnormalities by combining water usage data and emotion data.

[1077] This invention is a system that not only monitors water usage and detects abnormal patterns, but also utilizes user emotional data to improve the accuracy of anomaly detection and emergency response. The system collects data in real time and has the ability to notify emergency contacts if an abnormality is detected. It also includes a mechanism to promote relief activities in collaboration with local relief organizations.

[1078] System configuration

[1079] The system mainly consists of the following components:

[1080] 1. Sensor

[1081] It is installed in the water meter of each home or facility to measure water usage, and transmits data using, for example, a LoRa module or Wi-Fi module.

[1082] 2. Emotion Engine

[1083] Emotions are assessed by analyzing the user's voice, facial expressions, and behavioral data. Specifically, emotion analysis is performed using the Emotion SDK.

[1084] 3. Server

[1085] Water usage data sent from sensors is collected, stored, and analyzed in real time.

[1086] The emotion data sent from the emotion engine is also analyzed, using machine learning algorithms such as TensorFlow and PyTorch.

[1087] Model normal usage patterns and detect anomalies.

[1088] 4. Terminal

[1089] It provides an interface for users to check water usage data, emotion data, and anomaly detection status using a smartphone app or web interface.

[1090] 5. Emergency Notification System

[1091] If an abnormality is detected, a notification will be sent to pre-registered emergency contacts using services such as Amazon SNS (Simple Notification Service).

[1092] 6. Regional Support Collaboration System

[1093] Work with local support organizations and request their cooperation when necessary.

[1094] Specific examples

[1095] Example 1: Elderly people living alone

[1096] The server collects water usage data from Mr. A's home. Normally, Mr. A uses 40 liters of water per day, but for the past three days, he has used less than 5 liters per day. Furthermore, the emotion engine detects increased anxiety and stress from Mr. A's voice and behavior. This is deemed an abnormality, and the server sends a notification to Mr. A's daughter and the management company. Upon receiving the notification, the daughter attempts to contact Mr. A, but receives no response, so she visits him in person. Meanwhile, the management company also dispatches staff to check on the situation.

[1097] Example 2: Worker living away from home

[1098] The server collects water usage data from Mr. B's residence. Mr. B normally uses 60 liters of water on weekends, but this weekend it was less than 10 liters, which is determined to be abnormal. The emotion engine also detects that Mr. B looks tired from his facial expression. The server then sends a notification to his registered friends and his company's management department. The friend receives the notification and contacts Mr. B, but receives no response, so he visits his residence, and at the same time, the company's management department also begins to take action.

[1099] Example prompts for generative AI models

[1100] Prompt statement example 1:

[1101] "Mr. A, an elderly person living alone, has been using significantly less water than usual for the past three days, and the emotion engine has detected increased anxiety and stress. What is the appropriate response for Mr. A in this situation?"

[1102] Prompt statement example 2:

[1103] "Mr. B, who is working away from home, used significantly less water than usual over the weekend, and the emotion engine detected his fatigue. Please advise whether an emergency response is required and what action would you recommend?"

[1104] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1105] Step 1: Data collection

[1106] The server receives water usage data sent from sensors in real time. The input is water usage data from sensors installed in each home or facility. Specifically, the sensors measure water usage every minute or every hour and send the data to the server via a LoRa module or Wi-Fi module. The server receives this data and assigns a timestamp to each data point. This allows the water usage data to be organized chronologically.

[1107] Step 2: Data storage and organization

[1108] The server stores the received data in a database. The input is water usage data with a timestamp. Specifically, the server uses a database (e.g., PostgreSQL) to store the data and organizes it based on the timestamp. The emotion data is also stored in the database. This allows for quick data access and analysis in subsequent analysis steps.

[1109] Step 3: Data analysis and anomaly detection

[1110] The server performs anomaly detection based on the stored data. The inputs are time-stamped water usage data and emotion data. Specifically, the server uses a machine learning algorithm (e.g., TensorFlow or PyTorch) to model normal usage patterns based on data from the previous year and data from similar households. It then analyzes whether the current water usage data significantly deviates from this baseline and detects anomalies. The output is the anomaly detection result (normal or abnormal).

[1111] Step 4: Evaluate the emotional data

[1112] The server improves the accuracy of anomaly detection based on emotion data. The input is emotion data obtained from the emotion engine. Specifically, it uses the emotion engine (e.g., Emotion SDK) to analyze the user's voice, facial expression, and behavioral data to evaluate their emotions. As a result, it outputs the user's stress level and anxiety as a numerical value. This allows the server to combine abnormalities in water usage with emotion data to evaluate the overall urgency.

[1113] Step 5: Notification Processing

[1114] If an anomaly is detected, the server sends a notification to the configured emergency contacts. The input is the anomaly detection result and emotion data. Specific behavior is to use an emergency notification system (e.g., Amazon SNS) to send a notification that includes the anomaly description, emotion rating, detection date and time, and recommended action. The output is a communication sent via SMS, email, or push notification.

[1115] Step 6: User Interface

[1116] Users can check water usage data and emotion data through a terminal. The input is the water usage data and emotion data stored in a database. Specifically, this data is displayed visually using a smartphone app or web interface. The output is a data display in a format that is easy for users to view. This allows users to easily check the anomaly detection status and past history data.

[1117] Step 7: Regional support collaboration

[1118] When an anomaly is detected, the server also sends a notification to the local support organization. The input is the anomaly detection result and emotion data. Specifically, the notification system is used to send information including the nature of the anomaly and its urgency to the local support organization. The output is a notification to the local support organization. This encourages a rapid response and ensures effective support activities.

[1119] (Application example 2)

[1120] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1121] To strengthen monitoring of elderly people and those living alone, it is necessary to not only monitor water usage but also to consider the user's emotional state. Current systems only detect abnormalities in water usage and require emergency responses based on changes in usage patterns, but this alone does not fully grasp the user's psychological and physical state. This also poses the risk of delaying emergency responses. To solve this problem, it is necessary to achieve more accurate monitoring and faster support.

[1122] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting and analyzing emotion data and water usage data, means for detecting abnormal usage patterns and combining them with the emotion data to determine the abnormality, means for assessing the urgency and sending a notification when an abnormality is detected, and means for promoting support activities in cooperation with local support organizations. This makes it possible to more accurately grasp the user's physical and psychological condition and to respond appropriately and quickly in an emergency.

[1123] "Water usage" means the amount of water consumed in a household or facility.

[1124] "Sensor" refers to a device used to measure water usage.

[1125] "Real-time" refers to the instantaneous collection and analysis of data.

[1126] "Data collection means" refers to the technological means for collecting water usage data through sensors.

[1127] "Abnormal usage pattern" means usage that significantly deviates from normal water usage.

[1128] "Anomaly detection measures" refers to technical measures that analyze collected data and detect abnormal usage patterns.

[1129] "Emergency Contact" means a contact configured to receive notification if an Anomaly is detected.

[1130] "Notification means" refers to the technical means for sending a notification to an emergency contact when an abnormality is detected.

[1131] "Community support organization" means an organization established to provide support in the local community.

[1132] "Support promotion measures" refer to technical measures for coordinating with local support organizations and implementing rapid support activities.

[1133] "User" means any individual or entity that uses the System.

[1134] "Emotion data" refers to the emotional state of the user as assessed from their voice, facial expression, and behavior.

[1135] "Evaluation means" refers to a technical means for analyzing emotion data and evaluating the user's emotional state.

[1136] "Emotion analysis" refers to the process of assessing a user's state of mind based on their emotional data.

[1137] "Urgency assessment means" refers to a technical means for assessing the urgency based on emotional data when an abnormality is detected.

[1138] "Registered Contacts" means contacts that are pre-configured within the System to receive notifications.

[1139] This invention is a system that monitors water usage and user emotion data, detects abnormalities, and promotes emergency response. The system is composed of the following main components and processing means.

[1140] System configuration

[1141] 1. Sensor

[1142] This is a sensor that is attached to the water meter of each home or facility to measure water usage.

[1143] 2. Emotion Engine

[1144] This software collects the user's voice, facial expression, and behavioral data, and analyzes and evaluates their emotions.

[1145] 3. Server

[1146] The system receives, stores, and analyzes water usage data and emotion data in real time. It detects abnormal usage patterns and sends notifications to emergency contacts if an abnormality is detected. It also assesses the level of urgency based on emotion data and connects with local support organizations.

[1147] 4. Terminal

[1148] It provides an interface for users to check water usage data, emotion data, and anomaly detection status. The terminal is a smartphone application through which users can check and set data.

[1149] Data collection

[1150] The server collects water usage data in real time from sensors installed in each home and facility. In parallel with this, the emotion engine collects the user's voice, facial expressions, and behavioral data to generate data that evaluates their emotions. The collected data is time-stamped and stored in the server's database.

[1151] Anomaly detection

[1152] The server analyzes water usage data and sentiment data to model normal usage patterns, comparing them with data from previous years and similar households, and uses machine learning algorithms to establish a baseline and determine whether the current data significantly deviates from this baseline.

[1153] Notification and Emergency Response

[1154] If an anomaly is detected, the server evaluates the urgency level based on the emotion data and sends a notification to the configured emergency contacts. The notification includes the nature of the anomaly, the emotion rating, the date and time of detection, and a recommended response. The notification is sent via SMS, email, or push notification. In addition, the server sends similar information to local support organizations to encourage a prompt response.

[1155] Specific examples

[1156] Example 1: Elderly people living alone

[1157] The server collects water usage data for User A's home. User A normally uses 40 liters of water per day, but for the past three days, it has been less than 5 liters per day. Furthermore, the emotion engine detects increased anxiety and stress from User A's voice and behavior. This is deemed an abnormality, and the server sends a notification to User A's family and the administrator. The family members who receive the notification try to contact User A, but receive no response, so they visit in person. Meanwhile, the administrator also dispatches staff to check on the situation.

[1158] Example 2: Worker living away from home

[1159] The server collects water usage data from User B's home. User B normally uses 60 liters of water on weekends, but this weekend it was less than 10 liters, which is determined to be abnormal. The emotion engine also detects that User B looks tired from his facial expression. The server sends a notification to registered friends and the management department. The friend receives the notification and contacts User B, but receives no response, so the server visits User B's home, and the management department also begins to respond.

[1160] Generative AI model prompt example

[1161] Please provide your current and past water usage data. Also provide your emotional data. We will notify you if an abnormality is detected or if your emotional state indicates 'sadness' or 'stress'.

[1162] In this way, to implement the invention, it is necessary to build a system that properly links sensors, emotion engines, servers, and terminals to detect abnormalities and quickly respond to emergencies. This system comprehensively monitors the user's psychological and physical state, thereby enhancing safety.

[1163] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1164] Step 1:

[1165] Sensors are attached to water meters in homes and facilities and measure water usage in real time. The sensors collect measurement data at regular intervals and send it to a server. The input is water usage data, and the output is the measurement data sent to the server.

[1166] Step 2:

[1167] The emotion engine collects the user's voice, facial expression, and behavioral data, and analyzes and evaluates their emotions. The emotion engine acquires user data using devices such as cameras and microphones, and evaluates the user's emotions using an emotion analysis algorithm. The input is the user's voice, facial expression, and behavioral data, and the output is emotion evaluation data.

[1168] Step 3:

[1169] The server receives and stores water usage data sent from the sensor and emotion data sent from the emotion engine in real time. These data are recorded in a database with a timestamp. The input is water usage data and emotion data, and the output is the data stored in the database.

[1170] Step 4:

[1171] The server models normal usage patterns based on the collected data, references historical data and data from similar households, and uses machine learning algorithms to set a baseline. The input is historical and current data, and the output is the set baseline.

[1172] Step 5:

[1173] The server determines whether the current data significantly deviates from the baseline and detects anomalous usage patterns. The inputs are current water usage data and emotion data, and the output is the anomaly detection results.

[1174] Step 6:

[1175] When an anomaly is detected, the server evaluates the urgency level based on the emotion data. If the urgency level is high, a notification is sent to the configured emergency contacts. The notification includes the details of the anomaly, the emotion rating, the date and time of detection, and a recommended response. The input is the anomaly detection result and the emotion rating data, and the output is an emergency notification.

[1176] Step 7:

[1177] The server also connects with local support organizations and promotes support activities as needed. Support organizations are sent information on the nature of the abnormality along with an assessment of the level of urgency, and are required to respond quickly. The input is emergency notification information, and the output is information to connect to support organizations.

[1178] Step 8:

[1179] Users can use the terminal to check water usage data, emotion data, and anomaly detection status. An interface is provided on the terminal, allowing users to check their own data in real time and configure the system. The input is data sent from the server, and the output is information displayed on the user's terminal.

[1180] For specific actions, the following prompt sentence example is used:

[1181] Please provide your current and past water usage data. Also provide your emotional data. We will notify you if an abnormality is detected or if your emotional state indicates 'sadness' or 'stress'.

[1182] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[1183] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1184] 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 the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314.

[1185] [Fourth embodiment]

[1186] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1187] 7, a 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.

[1188] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1189] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[1190] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[1191] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[1192] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1193] The control object 443 includes a display device, LEDs in the eyes, and motors for driving 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 emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[1194] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1195] The specific processing program 56 is an example of a "program" according to the technology of the present 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.

[1196] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1197] In the robot 414, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. 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 process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1198] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1199] This invention is a system that monitors water usage and detects abnormal patterns. The system collects data in real time and notifies emergency contacts if an abnormality is detected. It also includes a mechanism to promote relief activities by linking with local support networks.

[1200] System configuration

[1201] The system mainly consists of the following components:

[1202] 1. Sensor

[1203] It is attached to the water meter of each home or facility to measure water usage.

[1204] 2. Server

[1205] It collects, stores, and analyzes data sent from sensors in real time.

[1206] Model normal usage patterns and detect anomalies.

[1207] 3. Terminal

[1208] Provides an interface for users to check water usage data and anomaly detection status.

[1209] 4. Emergency Notification System

[1210] If an abnormality is detected, a notification is sent to a pre-registered emergency contact.

[1211] 5. Regional Support Collaboration System

[1212] Work with local support organizations and request their cooperation when necessary.

[1213] Program processing

[1214] Data collection

[1215] The server receives real-time water usage data sent from the sensors and stores it in a database, including timestamps and usage amounts.

[1216] Anomaly detection

[1217] The server uses the collected data to model normal usage patterns, comparing it with data from the previous year and similar households, and uses machine learning algorithms to establish a baseline and determine whether current usage significantly deviates from this baseline.

[1218] notification

[1219] If an anomaly is detected, the server will send a notification to emergency contacts. The notification will include a description of the anomaly, the date and time it was detected, and a recommended action to take. Notifications can be sent via SMS, email, or push notification.

[1220] Specific examples

[1221] Example 1: Elderly people living alone

[1222] The server collects water usage data for Mr. A's home. Normally, Mr. A uses 40 liters of water per day, but for the past three days, it has been less than 5 liters per day. This is deemed abnormal, and the server sends a notification to Mr. A's daughter and the management company. Upon receiving the notification, the daughter tries to contact Mr. A, but receives no response, so she visits him in person. Meanwhile, the management company also dispatches staff to check the situation.

[1223] Example 2: Worker living away from home

[1224] The server collects water usage data from Mr. B's residence. Mr. B usually uses 60 liters of water on weekends, but this weekend he used less than 10 liters, which is considered abnormal. The server sends a notification to his registered friends and his company's management department. The friend receives the notification and contacts Mr. B. Since there is no response, the friend visits Mr. B's residence, and at the same time, the company's management department also begins to take action.

[1225] Local Support Network

[1226] When an abnormality is detected, the server also sends a notification to local support organizations to promptly respond. Support organizations will then carry out support activities such as visiting or making phone calls depending on the situation. Users can also request support via their devices.

[1227] This allows the system to detect abnormalities in real time and provide the ability to prompt a quick response, contributing to the prevention of lonely deaths.

[1228] The processing flow will be explained below.

[1229] Step 1: Data collection

[1230] The server receives real-time water usage data from sensors. In this system, sensors are attached to water meters in each home and transmit the measured data at regular intervals (e.g., every minute) to the server. The server stores the received data in a database and assigns a timestamp to each data point.

[1231] Step 2: Data analysis

[1232] The server models normal usage patterns based on the collected data, references data from previous years and similar households, and uses machine learning algorithms to establish a baseline. It then compares current data against the modeled normal patterns to detect abnormal usage patterns.

[1233] Step 3: Anomaly detection

[1234] The server uses statistical analysis techniques to determine whether current usage data deviates from a set baseline. For example, sustained low usage or sudden fluctuations are detected as an anomaly. If an anomaly is found, the event is recorded in an anomaly event log.

[1235] Step 4: Generate notifications

[1236] When an anomaly is detected, the server consults the configured emergency contact information, which can include the user, family, friends, landlord, management company, etc. The server generates a notification message containing the anomaly, the date and time it was detected, and a recommended action to take.

[1237] Step 5: Sending notifications

[1238] The server then sends the generated notification message to each contact via SMS, email, push notification, etc. For example, email is sent using the SMTP protocol.

[1239] Step 6: User confirmation and response

[1240] The user receives a notification and can check the water usage data and details of any abnormalities through their device. If the user is a family member, they can contact them directly or visit them. Landlords and management companies can also check the situation and visit the site if necessary.

[1241] Step 7: Coordinating local support networks

[1242] If an abnormality is detected, the server also sends a notification to local support organizations, who then promptly consider how to respond and provide the necessary assistance, such as making regular visits or calling to check on the safety of the affected individuals.

[1243] Step 8: Follow up

[1244] After an abnormality is notified, the server tracks the response status and notifies again if necessary. For example, if the abnormality continues or no response is taken, it is possible to send another alert. The user can check the support status through their device and request any additional support needed.

[1245] This allows the system to detect abnormalities in water usage early and prompt a quick response, preventing lonely deaths and other emergencies.

[1246] Example 1

[1247] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1248] In modern society, there are increasing cases of elderly people living alone or people working away from home being unable to respond quickly to abnormal situations, putting their lives at risk. To address these situations, a system is needed that can detect abnormalities in water usage, which is a part of daily life, in real time and quickly notify appropriate contacts and support organizations. Existing systems have issues that are not fully addressed in terms of the accuracy of abnormality detection, the speed of notification, and the coordination of responses.

[1249] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1250] In this invention, the server includes means for receiving data in real time from sensors that measure water usage, means for storing the received data in a database, means for modeling normal usage patterns using a machine learning algorithm based on the stored data and detecting abnormal usage patterns, means for sending a notification to a set emergency contact when an abnormal usage pattern is detected, and means for coordinating with local support organizations to promote support activities. This makes it possible to quickly and accurately detect abnormalities in water usage and immediately notify necessary support.

[1251] A "sensor" is a device that measures water usage and transmits the data in real time.

[1252] A "database" is a system for storing and managing collected data.

[1253] A "machine learning algorithm" is a set of mathematical techniques that use historical data to model normal usage patterns and detect anomalous patterns.

[1254] An "abnormal usage pattern" refers to fluctuations in water usage that deviate significantly from normal usage patterns.

[1255] "Emergency contacts" are pre-defined contacts to whom notifications are sent when an abnormality is detected, and include family members, friends, and administrators.

[1256] A "community support organization" is an organization made up of local groups and institutions that provide support activities in emergencies.

[1257] "Real time" means processing an event at the exact moment it occurs.

[1258] MODE FOR CARRYING OUT THE INVENTION

[1259] This invention is a system that monitors water usage and detects abnormal patterns. The system collects data in real time and notifies emergency contacts if an abnormality is detected. It also includes a mechanism to link with local support networks to facilitate relief efforts.

[1260] System configuration

[1261] The system mainly consists of the following components:

[1262] 1. Sensor

[1263] It is attached to the water meter of each home or facility to measure water usage.

[1264] 2. Server

[1265] It collects, stores, and analyzes data sent from sensors in real time.

[1266] Model normal usage patterns and detect anomalies.

[1267] 3. Terminal

[1268] Provides an interface for users to check water usage data and anomaly detection status.

[1269] 4. Emergency Notification System

[1270] If an abnormality is detected, a notification is sent to a pre-registered emergency contact.

[1271] 5. Regional Support Collaboration System

[1272] Work with local support organizations and request their cooperation when necessary.

[1273] Data collection and storage

[1274] The server receives real-time water usage data sent from the sensors. Specifically, sensors installed in each home and facility measure usage data every minute and send it wirelessly to the server. For example, if the sensor in home A sends data such as "3 liters used at 2023-10-01 08:00:00," the server receives this data. The server receives the data and stores it in a database. The stored data includes a timestamp, usage amount, sensor ID, etc., and is saved in a format such as "3 liters used by sensor ID: A123 at 2023-10-01 08:00:00."

[1275] Anomaly detection

[1276] The server analyzes past usage data stored in a database and models normal usage patterns using a machine learning algorithm (e.g., using TensorFlow). Specifically, it uses data from the past year to set a baseline for normal usage. If the current data deviates significantly from this baseline, it is determined to be abnormal. For example, if person A's normal daily usage is 40 liters, but has been less than 5 liters for the past three days, it is determined to be abnormal.

[1277] emergency notification

[1278] If an abnormality is detected, the server automatically sends a notification to emergency contacts. The notification can be sent in the form of SMS, email, or push notification. For example, an SMS message saying "Mom's water usage is abnormally low. Please check it" is sent to Mr. A's daughter. Specifically, the message is sent to registered contacts using the Twilio API.

[1279] Support and collaboration

[1280] Based on the information about the detected abnormality, the server also sends a notification to local support organizations. For example, an email may be sent to the local welfare service saying, "Water usage at Mr. A's house on xxxx-chome has dropped abnormally. Urgent action is required." Users can also request support using their devices (smartphones or PCs). When a user opens a dedicated app and presses the "Request Support" button, a notification is automatically sent to the local support organization.

[1281] Hardware and software used

[1282] Hardware: sensors, servers, user devices (smartphones, PCs)

[1283] Software: Database systems (e.g., MySQL, PostgreSQL), machine learning models (e.g., TensorFlow, Scikit-learn), notification systems (e.g., Twilio for SMS, SendGrid for Email)

[1284] Specific examples

[1285] Example 1: Elderly people living alone

[1286] The server collects water usage data from Mr. A's home. Normally, Mr. A uses 40 liters of water per day, but for the past three days, it has been less than 5 liters per day. This is deemed abnormal, and the server sends a notification to Mr. A's daughter and the management agency. Upon receiving the notification, Mr. A's daughter tries to contact Mr. A, but receives no response, so she visits him in person. Meanwhile, the management agency also dispatches staff to check the situation.

[1287] Example 2: Worker living away from home

[1288] The server collects water usage data from Mr. B's residence. Mr. B usually uses 60 liters of water on weekends, but this weekend he used less than 10 liters, which is considered abnormal. The server sends a notification to his registered friends and the management agency. The friend receives the notification and contacts Mr. B. Since there is no response, the friend visits Mr. B's residence, and the management agency also begins to take action.

[1289] Prompt Sentence Examples

[1290] "Mr. A, an elderly person living alone, has noticed that his water usage has dropped from the usual 40 liters to less than 5 liters. Please write code that will treat this as an abnormality and send a notification to an emergency contact."

[1291] Example of prompt input:

[1292] "Please explain in detail the processing steps of a program in which a server detects anomalies in water usage data collected from sensors and sends a notification to emergency contacts if an abnormality is detected. Also, please recall the case of an elderly person living alone as a concrete example."

[1293] This system ensures the safety and security of users by sending data collected by sensors to a server in real time and quickly sending emergency notifications if an abnormality is detected.

[1294] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1295] Program processing

[1296] Step 1: Data collection

[1297] The server receives real-time data sent from the sensors. The input is water usage data measured by sensors attached to water meters in each home or facility. The data includes a timestamp, the amount used, and the sensor ID. The output is raw data transferred to the server in real time. Specifically, the sensor sends data to the server such as "3 liters used with sensor ID: A123 on 2023-10-01 08:00:00."

[1298] Step 2: Save data

[1299] The server stores the received data in a database. The input is the real-time data received in step 1. When stored in the database, the data is structured in the format of a timestamp, amount used, and sensor ID. As an output, the stored data is accumulated in the database. Specifically, the data "3 liters used with sensor ID: A123 on 2023-10-01 08:00:00" is registered in the database.

[1300] Step 3: Data analysis

[1301] The server analyzes past water usage data stored in a database. The inputs are past usage data and current real-time data. A machine learning algorithm is used to model normal usage patterns and perform analysis to detect anomalies. The output is the baseline usage pattern and an anomaly determination result when current usage deviates from the baseline. Specifically, the server sets a baseline based on data from the past year, such as "Person A's normal usage is 40 liters per day," and compares this with current usage to detect anomalies.

[1302] Step 4: Anomaly detection

[1303] The server detects anomalies based on the results of the data analysis in step 3. The inputs are the analyzed usage pattern and the current usage amount. A certain threshold is set, and if the current usage amount exceeds that threshold, it is determined to be an anomaly. The output is a flag indicating whether an anomaly has been detected. Specifically, it determines that an anomaly has occurred if "usage amount for the past three days has been less than 5 liters per day."

[1304] Step 5: Emergency Notification

[1305] If an anomaly is detected, the server sends a notification to the emergency contact. The inputs are the anomaly detection result and the pre-defined emergency contact information. The notification is sent in the form of SMS, email, push notification, etc. The output is the notification message that was sent. Specifically, the Twilio API is used to send a message to Mr. A's daughter saying, "Mom's water usage is abnormally low. Please check."

[1306] Step 6: Support collaboration

[1307] Based on the detected anomaly, the server also sends a notification to local support organizations. The inputs are the anomaly detection results and the support organization's contact information. The notification is sent via email or other communication method. The output is the notification sent to the support organization. Specifically, SendGrid is used to send an email to welfare services stating, "Water usage at Mr. A's residence on xxxx-chome has dropped abnormally. Urgent action is required."

[1308] In this way, a series of processes is carried out, from monitoring water usage to detecting abnormalities, sending emergency notifications, and coordinating support, through each step.

[1309] (Application example 1)

[1310] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1311] For elderly people living alone or those working away from home, it is important to detect abnormalities in water usage early and take appropriate action. However, conventional systems often lack the ability to detect abnormalities in real time or provide prompt notification. Furthermore, there was insufficient collaboration with local support organizations, which sometimes led to delayed early response. Furthermore, there was a lack of a way for users to easily understand their own water usage using smart devices. To solve these problems, a more efficient and reliable water usage monitoring system is needed.

[1312] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1313] In this invention, the server includes means for measuring water usage with a sensor and collecting data in real time, means for detecting abnormal usage patterns based on the collected data, means for sending a notification to a set emergency contact when an abnormal usage pattern is detected, means for promoting support activities in cooperation with local support organizations, as well as means for displaying water usage in real time on a smart device, means for detecting abnormalities using a machine learning algorithm, and means for providing a user interface through the smart device. This enables real-time monitoring of water usage, highly accurate detection of abnormalities using machine learning, and rapid notification and support collaboration.

[1314] "Water usage" is data measuring the amount of water used in homes and facilities.

[1315] A "sensor" is a device that is attached to a water meter and measures water usage in real time.

[1316] "Means for collecting data in real time" refers to the function of instantly receiving and storing water usage data sent from sensors.

[1317] An "abnormal usage pattern" is a unique data pattern that indicates usage that significantly deviates from normal water usage.

[1318] "Means for sending notifications to emergency contacts" is a function that immediately notifies the set contacts via email, SMS, etc. when an abnormality is detected.

[1319] "Means to promote support activities in cooperation with local support organizations" refers to a system that cooperates with local support groups and collaborators to ensure that necessary support can be provided quickly.

[1320] "Smart devices" refers to information devices that can connect to the Internet, such as smartphones, tablets, and smartwatches.

[1321] A "machine learning algorithm" is a computational method that learns patterns based on large amounts of data and makes automatic decisions.

[1322] A "user interface" is the screen or means by which a user operates an application and inputs and obtains information.

[1323] "Historical Data" refers to historical water usage data previously collected.

[1324] "Current data" refers to the latest ongoing water usage data.

[1325] "Multiple contacts" refers to multiple contact information (family, friends, administrator, etc.) registered in advance for sending notifications in the event of an abnormality.

[1326] A "local support network" is a network of support formed by collaborators and organizations within the local area.

[1327] MODE FOR CARRYING OUT THE INVENTION

[1328] The configuration and operation of a specific system for realizing this invention will be described. This system includes smart water meters installed in homes and facilities, as well as a server, cloud storage, a notification system, and smart devices.

[1329] Hardware and software used

[1330] Hardware

[1331] Smart water meter: A device that uses sensors to measure water usage in homes and facilities.

[1332] Server: Installed in the cloud, it collects data, analyzes it, and sends notifications. It uses Amazon EC2 instances.

[1333] Smart Device: The device used by the user, such as a smartphone or tablet.

[1334] software

[1335] Database: Data is stored using Amazon RDS and PostgreSQL.

[1336] AI algorithms: Anomaly detection models are built using TensorFlow and Scikit-learn.

[1337] Smartphone app: Develop cross-platform applications using Flutter.

[1338] Notification system: Uses Amazon SNS to send notifications.

[1339] Data collection

[1340] The sensor measures water usage in real time and sends the data to AWS IoT Core via MQTT protocol. The received data is stored in Amazon RDS via AWS Lambda. This data includes a timestamp and usage amount.

[1341] Anomaly detection

[1342] The server analyzes the collected data in real time and compares it with historical data to model normal usage patterns. Machine learning algorithms (such as Scikit-learn's Isolation Forest) are used to detect anomalies. If an anomaly is detected, the server sends a notification to emergency contacts and local assistance networks.

[1343] notification

[1344] If an anomaly is detected, AWS IoT Core will trigger a notification using Amazon SNS, which can be delivered via push notification, SMS, or email.

[1345] User Interface

[1346] Users can use the smartphone app to view past water usage, anomaly detection history, and real-time usage. The application was developed using Flutter and is compatible with both iOS and Android.

[1347] Specific examples

[1348] Cases of elderly people living alone

[1349] The server regularly monitors the water usage at Mr. A's home. Normally, Mr. A uses 40 liters of water per day, but for the past three days, it has been less than 5 liters per day. Detecting this abnormality, the server sends a notification to Mr. A's family, who are his emergency contacts, and to the management company. Upon receiving the notification, the family attempts to contact Mr. A, but receives no response, so they visit him in person. The management company also dispatches staff to check on the situation.

[1350] Prompt Sentence Examples

[1351] User registration prompt:

[1352] Welcome to Safe Water Check! This app monitors your water usage in real time and automatically notifies you if there are any irregularities. To use it, please enter the following information:

[1353] Emergency contact information (email address or phone number)

[1354] Local support network preference (e.g., local government or neighbors)

[1355] Pairing information for your home's water meter and smartphone

[1356] If you have any questions regarding usage, please feel free to let us know.

[1357] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1358] Program processing flow

[1359] Step 1: Collect water usage data

[1360] Sensors measure water usage in each home or facility in real time. The measured data is sent to AWS IoT Core via the MQTT protocol. The input is the measurement data (timestamp and usage amount), and the output is data passed to AWS Lambda.

[1361] Input: Timestamp and usage data measured by sensors

[1362] Data processing: Send data to AWS IoT Core via MQTT protocol

[1363] Output: Measurement data sent to AWS IoT Core

[1364] Step 2: Save your data

[1365] AWS Lambda receives the received data in real time and stores it in Amazon RDS (e.g., PostgreSQL). The input is the data sent from AWS IoT Core, and the output is a message that the data was successfully stored in the database.

[1366] Input: Timestamp and usage data sent from AWS IoT Core

[1367] Data processing: AWS Lambda receives the data, formats it, and stores it in Amazon RDS

[1368] Output: Message that saving to database was successful

[1369] Step 3: Analyze the data

[1370] The server analyzes the collected data in real time, comparing historical data with current data and using machine learning algorithms (e.g., Scikit-learn's Isolation Forest) to model normal usage patterns. The input is the stored data, and the output is the anomaly detection results.

[1371] Input: Historical and Current Data

[1372] Data processing: Anomaly detection using Scikit-learn's Isolation Forest

[1373] Output: Anomaly detection results (presence or absence of anomaly, type of anomaly)

[1374] Step 4: Anomaly detection

[1375] If the server detects an anomaly based on the analysis results, it summarizes the details of the anomaly. If the anomaly threshold is exceeded, it proceeds to the next step. The input is the anomaly detection result, and the output is notification information.

[1376] Input: Anomaly detection result

[1377] Data processing: Summarizing details of anomalies

[1378] Output: Notification information (details of the abnormality, detection date and time, recommended action)

[1379] Step 5: Sending notifications

[1380] The server uses Amazon SNS to send notifications to emergency contacts and local support networks when an anomaly is detected. The input is the notification information, and the output is a message that the notification has been sent.

[1381] Input: Notification information (details of the abnormality, detection date and time, recommended action)

[1382] Data processing: Format the notification content and send it via Amazon SNS

[1383] Output: Notification sent message

[1384] Step 6: Update the User Interface

[1385] The terminal (smart device) receives notifications from the server and updates the application interface. The user can check abnormality notifications and past data history through the app. The input is notification information and past data, and the output is an updated user interface.

[1386] Input: Notification information, past data

[1387] Data processing: updating and displaying the user interface

[1388] Output: Updated user interface

[1389] Step 7: Request assistance

[1390] The user can request additional assistance through the application. When assistance is requested, the information is sent to the server, which notifies the local assistance network. The input is the user's request for assistance, and the output is a notification to the local assistance network.

[1391] Input: User's request for assistance

[1392] Data processing: Send support request information to the server

[1393] Output: Notification to local support network

[1394] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1395] This invention is a system that not only monitors water usage and detects abnormal patterns, but also utilizes user emotional data to improve the accuracy of anomaly detection and emergency response. The system collects data in real time and has the ability to notify emergency contacts if an abnormality is detected. It also includes a mechanism to promote relief activities by linking with local support networks.

[1396] System configuration

[1397] The system mainly consists of the following components:

[1398] 1. Sensor

[1399] It is attached to the water meter of each home or facility to measure water usage.

[1400] 2. Emotion Engine

[1401] Emotions are assessed by analyzing the user's voice, facial expressions, and behavioral data.

[1402] 3. Server

[1403] Water usage data sent from sensors is collected, stored, and analyzed in real time.

[1404] The emotional data sent from the emotion engine is also analyzed.

[1405] Model normal usage patterns and detect anomalies.

[1406] 4. Terminal

[1407] It provides an interface for users to check water usage data, emotion data, and anomaly detection status.

[1408] 5. Emergency Notification System

[1409] If an abnormality is detected, a notification is sent to a pre-registered emergency contact.

[1410] 6. Regional Support Collaboration System

[1411] Work with local support organizations and request their cooperation when necessary.

[1412] Program processing

[1413] Data collection

[1414] The server receives water usage data sent from the sensors in real time and stores it in a database. Each data is time-stamped, and emotion data from the emotion engine is also collected at the same time.

[1415] Anomaly detection

[1416] The server uses the water usage data and emotion data to model typical usage and emotion patterns, comparing them with data from previous years and similar households, and uses machine learning algorithms to establish a baseline and determine whether the current data significantly deviates from this baseline.

[1417] notification

[1418] If an anomaly is detected, the server evaluates the urgency based on the emotion data and sends a notification to the configured emergency contacts. The notification includes the details of the anomaly, the emotion rating, the date and time of detection, and a recommended response. Notifications are sent via SMS, email, or push notification.

[1419] Specific examples

[1420] Example 1: Elderly people living alone

[1421] The server collects water usage data from Mr. A's home. Normally, Mr. A uses 40 liters of water per day, but for the past three days, he has used less than 5 liters per day. Furthermore, the emotion engine detects increased anxiety and stress from Mr. A's voice and behavior. This is deemed an abnormality, and the server sends a notification to Mr. A's daughter and the management company. Upon receiving the notification, the daughter attempts to contact Mr. A, but receives no response, so she visits him in person. Meanwhile, the management company also dispatches staff to check on the situation.

[1422] Example 2: Worker living away from home

[1423] The server collects water usage data from Mr. B's residence. Mr. B normally uses 60 liters of water on weekends, but this weekend it was less than 10 liters, which is determined to be abnormal. The emotion engine also detects that Mr. B looks tired from his facial expression. The server then sends a notification to his registered friends and his company's management department. The friend receives the notification and contacts Mr. B, but receives no response, so he visits his residence, and at the same time, the company's management department also begins to take action.

[1424] Local Support Network

[1425] When an abnormality is detected, the server combines the information with emotion data and sends a notification to local support organizations to prompt a prompt response. Support organizations will then carry out support activities such as visiting or making phone calls depending on the situation. Users can also request support via their devices.

[1426] This allows the system to detect anomalies by combining water usage data and user emotional data, and by prompting a quick response, it can prevent lonely deaths and other emergencies.

[1427] The processing flow will be explained below.

[1428] Step 1: Data collection

[1429] The server receives real-time water usage data sent from sensors. The sensors are attached to the water meters in each home and send the measurement data to the server at regular intervals (e.g., every minute). The received data is stored in a database, and each data is given a timestamp.

[1430] Step 2: Collecting Emotional Data

[1431] The emotion engine receives the user's voice, facial expression, and behavioral data from sensors and devices, and evaluates their emotions. The evaluated emotion data is sent to the server and also stored in a database.

[1432] Step 3: Modeling normal patterns

[1433] The server uses collected water usage and sentiment data to model typical usage and sentiment patterns using data from the previous year and similar households, and uses machine learning algorithms to establish a baseline.

[1434] Step 4: Anomaly detection

[1435] The server compares current usage and emotion data with baselines and uses statistical analysis to detect anomalies. For example, a persistently low water usage combined with stress or anxiety detected by the emotion engine is considered an anomaly. When an anomaly is detected, the event is recorded in an anomaly event log.

[1436] Step 5: Assess the severity

[1437] When an abnormality is detected, the server evaluates the urgency based on the emotional data. For example, if the intensity of anxiety or stress level is high, the urgency is judged to be high.

[1438] Step 6: Generate notifications

[1439] The server generates a notification message based on the severity rating, which includes the anomaly description, sentiment rating, detection date and time, and recommended action.

[1440] Step 7: Sending notifications

[1441] The server then sends the generated notification message to multiple emergency contacts, including the user, family, friends, landlords, management companies, etc. Notifications can be sent via SMS, email, or push notification.

[1442] Step 8: User confirmation and response

[1443] The user receives a notification and can check the water usage data, emotional data, and details of any abnormalities through their device. If the user is a family member, they can contact or visit the person directly. The landlord or management company can also respond in the same way.

[1444] Step 9: Linking local support networks

[1445] If an abnormality is detected, the server also sends a notification to local support organizations, who then promptly consider how to respond and provide the necessary assistance, such as by making regular visits or phone calls to check on the safety of the affected individuals.

[1446] Step 10: Follow up

[1447] After notification, the server continuously monitors the response status and notifies again as necessary. If the abnormality persists or no response is taken, it is possible to send another alert. The user can check the progress of support through their device and request any additional support that is required.

[1448] This allows the system to detect anomalies by combining water usage data with user emotional data, and by prompting a quick response, it can prevent lonely deaths and other emergencies.

[1449] Example 2

[1450] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1451] In modern society, the number of individuals whose health and safety are a concern is increasing, such as elderly people living alone and people working away from home. Under these circumstances, monitoring their lifestyle habits, detecting abnormalities early, and taking appropriate action is a major challenge. In particular, it is becoming increasingly important to detect emergencies from abnormalities in water usage, but existing systems still have issues with the accuracy of anomaly detection and the speed of response. In addition, there is a need for more accurate anomaly detection and emergency response by combining not only water usage data but also user emotional data.

[1452] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1453] In this invention, the server includes means for measuring water usage with a sensor and collecting data in real time, means for detecting abnormal usage patterns based on the collected data, means for sending a notification to a set emergency contact when an abnormal usage pattern is detected, means for analyzing the user's voice, facial expression, and behavior data to evaluate their emotions, means for improving the accuracy of anomaly detection and emergency response based on the emotion data, and means for collaborating with local support organizations to promote support activities. This not only improves the accuracy of anomaly detection, but also enables quick and appropriate responses.

[1454] "Water usage data" is information that indicates the amount of water consumed by each household or facility, and is measured in real time using sensors.

[1455] A "sensor" is a device that is attached to a water meter, measures water usage, and sends the data to a server.

[1456] The "server" is a computer system that receives water usage data and emotion data sent from the sensor, analyzes them, and detects abnormalities.

[1457] "Emotion data" is information that evaluates a user's emotions by analyzing their voice, facial expressions, and behavior, and is used to improve the accuracy of anomaly detection.

[1458] An "abnormal usage pattern" refers to fluctuations in water usage that deviate significantly from normal usage patterns, and refers to usage patterns that deviate from a baseline modeled based on data from the previous year or similar households.

[1459] "Emergency Contacts" are pre-configured contacts to send notifications when an abnormality is detected based on water usage data or emotion data.

[1460] "Local support organizations" are local groups and institutions that receive notifications when abnormalities are detected and work together to provide rapid response and support activities.

[1461] "Notifications" are messages that send warnings or information to emergency contacts or local support organizations when an anomaly is detected.

[1462] "Modeling" is the process of statistically representing normal usage patterns based on data from the previous year and similar households, and setting criteria for anomaly detection.

[1463] "Abnormality detection accuracy" refers to the ability to accurately detect abnormalities by combining water usage data and emotion data.

[1464] This invention is a system that not only monitors water usage and detects abnormal patterns, but also utilizes user emotional data to improve the accuracy of anomaly detection and emergency response. The system collects data in real time and has the ability to notify emergency contacts if an abnormality is detected. It also includes a mechanism to promote relief activities in collaboration with local relief organizations.

[1465] System configuration

[1466] The system mainly consists of the following components:

[1467] 1. Sensor

[1468] It is installed in the water meter of each home or facility to measure water usage, and transmits data using, for example, a LoRa module or Wi-Fi module.

[1469] 2. Emotion Engine

[1470] Emotions are assessed by analyzing the user's voice, facial expressions, and behavioral data. Specifically, emotion analysis is performed using the Emotion SDK.

[1471] 3. Server

[1472] Water usage data sent from sensors is collected, stored, and analyzed in real time.

[1473] The emotion data sent from the emotion engine is also analyzed, using machine learning algorithms such as TensorFlow and PyTorch.

[1474] Model normal usage patterns and detect anomalies.

[1475] 4. Terminal

[1476] It provides an interface for users to check water usage data, emotion data, and anomaly detection status using a smartphone app or web interface.

[1477] 5. Emergency Notification System

[1478] If an abnormality is detected, a notification will be sent to pre-registered emergency contacts using services such as Amazon SNS (Simple Notification Service).

[1479] 6. Regional Support Collaboration System

[1480] Work with local support organizations and request their cooperation when necessary.

[1481] Specific examples

[1482] Example 1: Elderly people living alone

[1483] The server collects water usage data from Mr. A's home. Normally, Mr. A uses 40 liters of water per day, but for the past three days, he has used less than 5 liters per day. Furthermore, the emotion engine detects increased anxiety and stress from Mr. A's voice and behavior. This is deemed an abnormality, and the server sends a notification to Mr. A's daughter and the management company. Upon receiving the notification, the daughter attempts to contact Mr. A, but receives no response, so she visits him in person. Meanwhile, the management company also dispatches staff to check on the situation.

[1484] Example 2: Worker living away from home

[1485] The server collects water usage data from Mr. B's residence. Mr. B normally uses 60 liters of water on weekends, but this weekend it was less than 10 liters, which is determined to be abnormal. The emotion engine also detects that Mr. B looks tired from his facial expression. The server then sends a notification to his registered friends and his company's management department. The friend receives the notification and contacts Mr. B, but receives no response, so he visits his residence, and at the same time, the company's management department also begins to take action.

[1486] Example prompts for generative AI models

[1487] Prompt statement example 1:

[1488] "Mr. A, an elderly person living alone, has been using significantly less water than usual for the past three days, and the emotion engine has detected increased anxiety and stress. What is the appropriate response for Mr. A in this situation?"

[1489] Prompt statement example 2:

[1490] "Mr. B, who is working away from home, used significantly less water than usual over the weekend, and the emotion engine detected his fatigue. Please advise whether an emergency response is required and what action would you recommend?"

[1491] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1492] Step 1: Data collection

[1493] The server receives water usage data sent from sensors in real time. The input is water usage data from sensors installed in each home or facility. Specifically, the sensors measure water usage every minute or every hour and send the data to the server via a LoRa module or Wi-Fi module. The server receives this data and assigns a timestamp to each data point. This allows the water usage data to be organized chronologically.

[1494] Step 2: Data storage and organization

[1495] The server stores the received data in a database. The input is water usage data with a timestamp. Specifically, the server uses a database (e.g., PostgreSQL) to store the data and organizes it based on the timestamp. The emotion data is also stored in the database. This allows for quick data access and analysis in subsequent analysis steps.

[1496] Step 3: Data analysis and anomaly detection

[1497] The server performs anomaly detection based on the stored data. The inputs are time-stamped water usage data and emotion data. Specifically, the server uses a machine learning algorithm (e.g., TensorFlow or PyTorch) to model normal usage patterns based on data from the previous year and data from similar households. It then analyzes whether the current water usage data significantly deviates from this baseline and detects anomalies. The output is the anomaly detection result (normal or abnormal).

[1498] Step 4: Evaluate the emotional data

[1499] The server improves the accuracy of anomaly detection based on emotion data. The input is emotion data obtained from the emotion engine. Specifically, it uses the emotion engine (e.g., Emotion SDK) to analyze the user's voice, facial expression, and behavioral data to evaluate their emotions. As a result, it outputs the user's stress level and anxiety as a numerical value. This allows the server to combine abnormalities in water usage with emotion data to evaluate the overall urgency.

[1500] Step 5: Notification Processing

[1501] If an anomaly is detected, the server sends a notification to the configured emergency contacts. The input is the anomaly detection result and emotion data. Specific behavior is to use an emergency notification system (e.g., Amazon SNS) to send a notification that includes the anomaly description, emotion rating, detection date and time, and recommended action. The output is a communication sent via SMS, email, or push notification.

[1502] Step 6: User Interface

[1503] Users can check water usage data and emotion data through a terminal. The input is the water usage data and emotion data stored in a database. Specifically, this data is displayed visually using a smartphone app or web interface. The output is a data display in a format that is easy for users to view. This allows users to easily check the anomaly detection status and past history data.

[1504] Step 7: Regional support collaboration

[1505] When an anomaly is detected, the server also sends a notification to the local support organization. The input is the anomaly detection result and emotion data. Specifically, the notification system is used to send information including the nature of the anomaly and its urgency to the local support organization. The output is a notification to the local support organization. This encourages a rapid response and ensures effective support activities.

[1506] (Application example 2)

[1507] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1508] To strengthen monitoring of elderly people and those living alone, it is necessary to not only monitor water usage but also to consider the user's emotional state. Current systems only detect abnormalities in water usage and require emergency responses based on changes in usage patterns, but this alone does not fully grasp the user's psychological and physical state. This also poses the risk of delaying emergency responses. To solve this problem, it is necessary to achieve more accurate monitoring and faster support.

[1509] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting and analyzing emotion data and water usage data, means for detecting abnormal usage patterns and combining them with the emotion data to determine the abnormality, means for assessing the urgency and sending a notification when an abnormality is detected, and means for promoting support activities in cooperation with local support organizations. This makes it possible to more accurately grasp the user's physical and psychological condition and to respond appropriately and quickly in an emergency.

[1510] "Water usage" means the amount of water consumed in a household or facility.

[1511] "Sensor" refers to a device used to measure water usage.

[1512] "Real-time" refers to the instantaneous collection and analysis of data.

[1513] "Data collection means" refers to the technological means for collecting water usage data through sensors.

[1514] "Abnormal usage pattern" means usage that significantly deviates from normal water usage.

[1515] "Anomaly detection measures" refers to technical measures that analyze collected data and detect abnormal usage patterns.

[1516] "Emergency Contact" means a contact configured to receive notification if an Anomaly is detected.

[1517] "Notification means" refers to the technical means for sending a notification to an emergency contact when an abnormality is detected.

[1518] "Community support organization" means an organization established to provide support in the local community.

[1519] "Support promotion measures" refer to technical measures for coordinating with local support organizations and implementing rapid support activities.

[1520] "User" means any individual or entity that uses the System.

[1521] "Emotion data" refers to the emotional state of the user as assessed from their voice, facial expression, and behavior.

[1522] "Evaluation means" refers to a technical means for analyzing emotion data and evaluating the user's emotional state.

[1523] "Emotion analysis" refers to the process of assessing a user's state of mind based on their emotional data.

[1524] "Urgency assessment means" refers to a technical means for assessing the urgency based on emotional data when an abnormality is detected.

[1525] "Registered Contacts" means contacts that are pre-configured within the System to receive notifications.

[1526] This invention is a system that monitors water usage and user emotion data, detects abnormalities, and promotes emergency response. The system is composed of the following main components and processing means.

[1527] System configuration

[1528] 1. Sensor

[1529] This is a sensor that is attached to the water meter of each home or facility to measure water usage.

[1530] 2. Emotion Engine

[1531] This software collects the user's voice, facial expression, and behavioral data, and analyzes and evaluates their emotions.

[1532] 3. Server

[1533] The system receives, stores, and analyzes water usage data and emotion data in real time. It detects abnormal usage patterns and sends notifications to emergency contacts if an abnormality is detected. It also assesses the level of urgency based on emotion data and connects with local support organizations.

[1534] 4. Terminal

[1535] It provides an interface for users to check water usage data, emotion data, and anomaly detection status. The terminal is a smartphone application through which users can check and set data.

[1536] Data collection

[1537] The server collects water usage data in real time from sensors installed in each home and facility. In parallel with this, the emotion engine collects the user's voice, facial expressions, and behavioral data to generate data that evaluates their emotions. The collected data is time-stamped and stored in the server's database.

[1538] Anomaly detection

[1539] The server analyzes water usage data and sentiment data to model normal usage patterns, comparing them with data from previous years and similar households, and uses machine learning algorithms to establish a baseline and determine whether the current data significantly deviates from this baseline.

[1540] Notification and Emergency Response

[1541] If an anomaly is detected, the server evaluates the urgency level based on the emotion data and sends a notification to the configured emergency contacts. The notification includes the nature of the anomaly, the emotion rating, the date and time of detection, and a recommended response. The notification is sent via SMS, email, or push notification. In addition, the server sends similar information to local support organizations to encourage a prompt response.

[1542] Specific examples

[1543] Example 1: Elderly people living alone

[1544] The server collects water usage data for User A's home. User A normally uses 40 liters of water per day, but for the past three days, it has been less than 5 liters per day. Furthermore, the emotion engine detects increased anxiety and stress from User A's voice and behavior. This is deemed an abnormality, and the server sends a notification to User A's family and the administrator. The family members who receive the notification try to contact User A, but receive no response, so they visit in person. Meanwhile, the administrator also dispatches staff to check on the situation.

[1545] Example 2: Worker living away from home

[1546] The server collects water usage data from User B's home. User B normally uses 60 liters of water on weekends, but this weekend it was less than 10 liters, which is determined to be abnormal. The emotion engine also detects that User B looks tired from his facial expression. The server sends a notification to registered friends and the management department. The friend receives the notification and contacts User B, but receives no response, so the server visits User B's home, and the management department also begins to respond.

[1547] Generative AI model prompt example

[1548] Please provide your current and past water usage data. Also provide your emotional data. We will notify you if an abnormality is detected or if your emotional state indicates 'sadness' or 'stress'.

[1549] In this way, to implement the invention, it is necessary to build a system that properly links sensors, emotion engines, servers, and terminals to detect abnormalities and quickly respond to emergencies. This system comprehensively monitors the user's psychological and physical state, thereby enhancing safety.

[1550] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1551] Step 1:

[1552] Sensors are attached to water meters in homes and facilities and measure water usage in real time. The sensors collect measurement data at regular intervals and send it to a server. The input is water usage data, and the output is the measurement data sent to the server.

[1553] Step 2:

[1554] The emotion engine collects the user's voice, facial expression, and behavioral data, and analyzes and evaluates their emotions. The emotion engine acquires user data using devices such as cameras and microphones, and evaluates the user's emotions using an emotion analysis algorithm. The input is the user's voice, facial expression, and behavioral data, and the output is emotion evaluation data.

[1555] Step 3:

[1556] The server receives and stores water usage data sent from the sensor and emotion data sent from the emotion engine in real time. These data are recorded in a database with a timestamp. The input is water usage data and emotion data, and the output is the data stored in the database.

[1557] Step 4:

[1558] The server models normal usage patterns based on the collected data, references historical data and data from similar households, and uses machine learning algorithms to set a baseline. The input is historical and current data, and the output is the set baseline.

[1559] Step 5:

[1560] The server determines whether the current data significantly deviates from the baseline and detects anomalous usage patterns. The inputs are current water usage data and emotion data, and the output is the anomaly detection results.

[1561] Step 6:

[1562] When an anomaly is detected, the server evaluates the urgency level based on the emotion data. If the urgency level is high, a notification is sent to the configured emergency contacts. The notification includes the details of the anomaly, the emotion rating, the date and time of detection, and a recommended response. The input is the anomaly detection result and the emotion rating data, and the output is an emergency notification.

[1563] Step 7:

[1564] The server also connects with local support organizations and promotes support activities as needed. Support organizations are sent information on the nature of the abnormality along with an assessment of the level of urgency, and are required to respond quickly. The input is emergency notification information, and the output is information to connect to support organizations.

[1565] Step 8:

[1566] Users can use the terminal to check water usage data, emotion data, and anomaly detection status. An interface is provided on the terminal, allowing users to check their own data in real time and configure the system. The input is data sent from the server, and the output is information displayed on the user's terminal.

[1567] For specific actions, the following prompt sentence example is used:

[1568] Please provide your current and past water usage data. Also provide your emotional data. We will notify you if an abnormality is detected or if your emotional state indicates 'sadness' or 'stress'.

[1569] 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 control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[1570] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1571] 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 the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1572] The emotion identification model 59 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 an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1573] FIG. 9 is a diagram illustrating an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1574] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[1575] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[1576] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[1577] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs 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 a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[1578] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[1579] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[1580] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[1581] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[1582] 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.

[1583] It is not necessary to store all 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 all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[1584] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[1585] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with 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). Also, the hardware resource that executes the specific processing may be a single processor.

[1586] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[1587] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[1588] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[1589] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[1590] The following is further disclosed regarding the above embodiment.

[1591] (Claim 1)

[1592] A means of measuring water usage with sensors and collecting data in real time,

[1593] a means for detecting anomalous usage patterns based on the collected data; and

[1594] means for sending notifications to configured emergency contacts when abnormal usage patterns are detected;

[1595] A system that includes means to promote support activities in collaboration with local support organizations.

[1596] (Claim 2)

[1597] 10. The system of claim 1, further comprising means for modeling typical usage patterns by reference to data from previous years and data from similar households.

[1598] (Claim 3)

[1599] 10. The system of claim 1, further comprising means for simultaneously sending notifications to multiple registered contacts (family, friends, landlord, management company) when an abnormal usage pattern threshold is exceeded.

[1600] "Example 1"

[1601] (Claim 1)

[1602] A means of receiving real-time data from sensors measuring water usage;

[1603] a means for storing the received data in a database;

[1604] a means for modeling normal usage patterns based on the stored data using machine learning algorithms to detect anomalous usage patterns; and

[1605] means for sending notifications to configured emergency contacts when abnormal usage patterns are detected;

[1606] A system that includes means to promote support activities in collaboration with local support organizations.

[1607] (Claim 2)

[1608] 10. The system of claim 1, further comprising means for modeling typical usage patterns by reference to data from previous years and data from similar households.

[1609] (Claim 3)

[1610] 10. The system of claim 1, further comprising means for simultaneously sending notifications to multiple registered contacts (family, friends, administrators) when an abnormal usage pattern threshold is exceeded.

[1611] "Application Example 1"

[1612] Claims

[1613] (Claim 1)

[1614] A means of measuring water usage with sensors and collecting data in real time,

[1615] a means for detecting anomalous usage patterns based on the collected data; and

[1616] means for sending notifications to configured emergency contacts when abnormal usage patterns are detected;

[1617] In addition to working with local support organizations to promote support activities,

[1618] A means to display real-time water usage on a smart device;

[1619] a means for detecting anomalies using machine learning algorithms;

[1620] A system including means for providing a user interface through a smart device.

[1621] (Claim 2)

[1622] In addition to measures to model normal usage patterns by looking at data from previous years and data from similar households.

[1623] 10. The system of claim 1, further comprising means for comparative analysis of past data and current data.

[1624] (Claim 3)

[1625] In addition to the means to simultaneously send notifications to multiple registered contacts (family, friends, landlord, management company) when abnormal usage patterns exceed thresholds,

[1626] 10. The system of claim 1, further comprising means for sending a notification to a local support network.

[1627] "Example 2: Combining Emotion Engines"

[1628] (Claim 1)

[1629] A means of measuring water usage with sensors and collecting data in real time,

[1630] a means for detecting anomalous usage patterns based on the collected data; and

[1631] means for sending notifications to configured emergency contacts when abnormal usage patterns are detected;

[1632] A means for evaluating emotions by analyzing the user's voice, facial expression, and behavioral data;

[1633] A means to improve the accuracy of anomaly detection and emergency response based on emotion data,

[1634] A system that includes means to promote support activities in collaboration with local support organizations.

[1635] (Claim 2)

[1636] 10. The system of claim 1, further comprising means for modeling typical usage patterns by reference to data from previous years and data from similar households.

[1637] (Claim 3)

[1638] 10. The system of claim 1, further comprising means for simultaneously sending notifications to multiple registered contacts (family, friends, administrative authorities) when a threshold for abnormal usage patterns is exceeded.

[1639] "Application example 2 when combining emotion engines"

[1640] (Claim 1)

[1641] A means of measuring water usage with sensors and collecting data in real time,

[1642] a means for detecting anomalous usage patterns based on the collected data; and

[1643] means for sending notifications to configured emergency contacts when abnormal usage patterns are detected;

[1644] A means of facilitating support activities in collaboration with local support organizations;

[1645] A means for evaluating emotions by analyzing the user's voice, facial expression, and behavioral data;

[1646] A means for determining abnormalities by combining emotion data and water usage data;

[1647] A system that includes a means for assessing urgency and sending notifications when an anomaly is detected.

[1648] (Claim 2)

[1649] 10. The system of claim 1, further comprising means for modeling typical usage patterns by reference to data from previous years and data from similar households.

[1650] (Claim 3)

[1651] 10. The system of claim 1, further comprising means for simultaneously sending notifications to multiple registered contacts (family, friends, administrators, support organizations) when an abnormal usage pattern threshold is exceeded. [Explanation of symbols]

[1652] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. A means of measuring water usage with sensors and collecting data in real time, a means for detecting anomalous usage patterns based on the collected data; and means for sending notifications to configured emergency contacts when abnormal usage patterns are detected; A system that includes means to promote support activities in collaboration with local support organizations.

2. 10. The system of claim 1, further comprising means for modeling typical usage patterns by reference to data from previous years and data from similar households.

3. 10. The system of claim 1, further comprising means for simultaneously sending notifications to multiple registered contacts (family, friends, landlord, management company) when an abnormal usage pattern threshold is exceeded.

Images