System

Abstract

A system is provided.SOLUTION: A system including sensor means for collecting daily life data of a pet, communication means for periodically transmitting the daily life data to a server, preprocessing means for storing the daily life data received in the server in a database and performing preprocessing, analysis means for inputting the preprocessed data to a generation model and evaluating a health condition of the pet, alert generation means for generating an alert message when an abnormality is detected by the analysis means, and notification means for transmitting the alert message to a terminal of a user.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] The present invention relates to a system that supports pet health management. Specifically, because pets cannot speak, it is difficult for owners to detect their pets' illnesses early on. This can lead to owners being unable to detect changes in their pets' health early on, which can delay appropriate treatment. Furthermore, when it is difficult to take pets to the veterinary clinic regularly, their health status is often not adequately monitored. To solve this problem, a system is needed that collects and analyzes daily pet data and monitors their health status in real time. [Means for solving the problem]

[0005] The present invention provides a system for monitoring the health condition of pets in real time by collecting and analyzing daily data of the pets.

[0006] 1. Use sensory means to collect daily data about your pet. Specifically, use cameras and temperature sensors to monitor your pet's behavior and body temperature.

[0007] 2. Equipped with a communication means to send collected daily data to a server, which allows data to be managed centrally and improves the accuracy of analysis.

[0008] 3. The server receives the daily data, stores it in a database, and has a preprocessing means for performing preprocessing such as noise removal and missing data completion.

[0009] 4. The pre-processed data is fed into the generative model to provide an analytical means for assessing the pet's health status, which detects abnormal patterns by comparing past and current data.

[0010] 5. The device includes an alert generating means for generating an alert message when an abnormality is detected, and a notification means for sending this alert message to the user's terminal.

[0011] These measures will enable owners to detect changes in their pet's physical condition early and take necessary measures promptly, improving pet health management and increasing the owner's peace of mind.

[0012] "Sensor means" refers to a device used to collect daily data about a pet, and includes sensors such as a camera and a body temperature sensor.

[0013] "Communication means" refers to devices or functions for periodically transmitting collected data to a server, and is primarily done via wireless communication such as Wi-Fi or Bluetooth.

[0014] The "server" is a centralized management device that receives daily pet data, stores it in a database, and performs preprocessing and analysis.

[0015] A "database" is a system for systematically storing and managing received daily data.

[0016] The "preprocessing means" is a function for preprocessing received data, and performs noise removal, missing data complementation, and the like.

[0017] A "generative model" is an artificial intelligence model or analytical algorithm used to assess a pet's health.

[0018] "Analysis means" refers to a device or function that inputs preprocessed data into a generative model and evaluates the health condition of a pet.

[0019] The "alert generation means" is a device or function for generating an alert message when an abnormality is detected in the health condition of the pet.

[0020] The "notification means" is a function for sending the generated alert message to the user's terminal, and is mainly done in the form of a push notification or email.

[0021] The "user terminal" refers to a device for receiving an alert message via a notification means, such as a smartphone or tablet. [Brief explanation of the drawings]

[0022] [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

[0023] 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.

[0024] First, the terms used in the following description will be explained.

[0025] 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).

[0026] 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.

[0027] 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.

[0028] 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.

[0029] 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."

[0030] [First embodiment]

[0031] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0032] 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.

[0033] 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).

[0034] 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.

[0035] 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.

[0036] 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.

[0037] 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.

[0038] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0039] 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.

[0040] 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.

[0041] 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.

[0042] 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."

[0043] As an embodiment of the present invention, a system will be described that monitors the health condition of a pet in real time and sends an alert to the owner if an abnormality is detected. This system is mainly composed of a terminal, a server, and a user.

[0044] Overview of program processing

[0045] Data collection:

[0046] Device: Cameras and temperature sensors installed in smart glasses and other wearable devices collect daily data about your pet (video, body temperature, amount of food eaten, activity time, etc.).

[0047] Data transmission:

[0048] On the device: Collected data is periodically batched and sent to a server via Wi-Fi or Bluetooth.

[0049] Data accumulation and preprocessing:

[0050] Server: Receives data sent from the device and stores it in a database. Then, it performs preprocessing such as noise removal and missing data completion.

[0051] Data Analysis:

[0052] Server: The preprocessed data is input into a generative model (artificial intelligence model or analytical algorithm) to assess the pet's health condition.

[0053] Anomaly detection:

[0054] Server: Compares the analysis results with past data to detect abnormal patterns. For example, if the body temperature continues to rise from 38.5°C to 39.2°C, it is determined to be abnormal.

[0055] Alert generation:

[0056] Server: If an abnormality is detected, generate an alert message with appropriate advice. For example, generate an alert saying "Temperature is high. Increase fluid intake and move to a cooler place."

[0057] Alert sending:

[0058] Server: The generated alert message is sent to the user's device (smartphone or tablet) via push notification.

[0059] Take Action:

[0060] User: The user receives a notification on a device such as a smartphone, checks the alert message, and then takes appropriate action for their pet based on the content of the notification.

[0061] Specific examples

[0062] 1. Device: The smart glasses capture video of your pet, measure its temperature with a thermometer, and record its feeding by weighing its food.

[0063] 2. Terminal: Based on the registered schedule, the collected data is sent to the server via Wi-Fi.

[0064] 3. Server: Receives the data, stores it in a database, and then performs preprocessing such as noise removal and missing data imputation.

[0065] 4. Server: The preprocessed data is input into the generative model and analysis begins. For example, if the body temperature data exceeds a certain range, it is recognized as an abnormal pattern.

[0066] 5. Server: If an abnormality is detected, generate an alert message. For example, generate an alert saying "Your pet has a high temperature and needs to be cooled."

[0067] 6. Server: Sends an alert message to the user's smartphone.

[0068] 7. User: Check the notification on your smartphone and take measures such as moving your pet to a cooler place and giving them water.

[0069] The above is the overall flow and specific processing contents of the system according to the embodiment of the present invention. The system of the present invention enables pet owners to grasp the health condition of their pets in real time and to promptly take appropriate measures.

[0070] The processing flow will be explained below.

[0071] Step 1:

[0072] Device: The smart glasses' camera captures images of your pet in real time, the temperature sensor measures your pet's temperature, and the weight sensor measures the amount of food your pet eats. The collected data is temporarily stored in the device's memory.

[0073] Step 2:

[0074] Terminal: Collected data is batch processed at regular intervals and compiled. The batched data is sent to the server via Wi-Fi or Bluetooth.

[0075] Step 3:

[0076] Server: Receives data sent from the device and stores it in a database. The database contains information such as date and time, type of data (body temperature, activity level, meal amount, etc.), and sensor information.

[0077] Step 4:

[0078] Server: Performs data preprocessing. Specifically, it applies a noise reduction algorithm to remove outliers and fills in missing data. For example, if a body temperature sensor temporarily loses data, it fills in the missing data using data from before and after.

[0079] Step 5:

[0080] Server: The preprocessed data is input into a generative model (an artificial intelligence model or analytical algorithm). The generative model analyzes the data and evaluates the pet's health condition.

[0081] Step 6:

[0082] Server: Detects abnormal patterns by comparing the analysis results with past health data. For example, if the current temperature is abnormally high compared with the temperature data from the past week, this is detected.

[0083] Step 7:

[0084] Server: If an abnormality is detected, the alert generation means generates an alert message. The message includes specific advice. For example, it could say, "Your pet's temperature is high and needs to be cooled."

[0085] Step 8:

[0086] Server: Sends the generated alert message to the user's device via push notification.

[0087] Step 9:

[0088] User: Receives an alert message on their smartphone or tablet. The message describes the pet's health status and specific measures to take. The user checks the message and takes the necessary measures.

[0089] The above are the processing steps in the system of the present invention, which allows for seamless processing from data collection to anomaly detection and notification to the user.

[0090] Example 1

[0091] 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."

[0092] Conventional pet health management systems lack the functionality to monitor minute-by-minute changes in body temperature and activity in real time, which means it takes a long time for abnormalities to be detected. Furthermore, there are insufficient methods for quickly communicating information to owners when an abnormality is detected, which can delay appropriate measures. This increases the risk of a pet's health deteriorating.

[0093] 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.

[0094] In this invention, the server includes a sensor means for collecting daily data of the pet, a communication means for periodically transmitting the daily data to the server, a preprocessing means for storing the daily data received by the server in a database and preprocessing the data, an analysis means for inputting the preprocessed data into an artificial intelligence model and evaluating the health condition of the pet, an alert generation means for generating an alert message including appropriate advice if the analysis means detects an abnormality, and a notification means for transmitting the alert message to a user's terminal. This makes it possible to monitor the health condition of the pet in real time, and to promptly notify the owner if an abnormality is detected so that appropriate measures can be taken.

[0095] The "sensor means" is a device for collecting daily data such as the pet's body temperature, activity status, and amount of food eaten.

[0096] "Communication means" refers to a network communication technology for periodically transmitting collected data to a server.

[0097] The "preprocessing means" is a technology that stores the daily data received by the server in a database and performs preprocessing such as noise removal and missing data completion.

[0098] The "analysis means" refers to a technology that inputs pre-processed data into an artificial intelligence model to assess the health status of a pet.

[0099] The "alert generation means" is a technique for generating an alert message containing appropriate advice when an abnormality is detected by the analysis means.

[0100] The "notification means" is a technique for sending the alert message to the user's terminal.

[0101] An "artificial intelligence model" is a machine learning algorithm used in data analysis to assess the health status of pets.

[0102] A "database" is an electronic information management system for organizing and storing collected routine data.

[0103] This invention relates to a system that monitors the health status of pets in real time and sends an alert to the owner if an abnormality is detected. This system is mainly composed of a terminal, a server, and a user.

[0104] Hardware and software used

[0105] Devices: Smart glasses and other wearable devices include the following hardware:

[0106] Camera: Capture footage of your pet.

[0107] Body temperature sensor: Measure your pet's body temperature.

[0108] Communication module: Sends data to the server using Wi-Fi or Bluetooth.

[0109] Server: The server includes the following software and hardware:

[0110] Database: Organizes and stores collected routine data.

[0111] Preprocessing software: Remove noise and fill in missing data.

[0112] Generative AI model: Analyzes pre-processed data and assesses the pet's health.

[0113] Alert generation software: Generates an alert message when an anomaly is detected.

[0114] Notification system: Pushes alert messages to user devices.

[0115] Data collection and transmission

[0116] Device: Smart glasses or other wearable devices collect your pet's daily data (video, body temperature, food intake, activity time, etc.) For example, smart glasses can capture video of your pet's activity at 8 a.m. and measure its temperature with a body temperature sensor.

[0117] Device: The collected data is periodically batched and sent to the server via Wi-Fi or Bluetooth. For example, at 9:00 a.m., the device can send the video and temperature data from the previous hour to the server via Wi-Fi.

[0118] Data accumulation and preprocessing

[0119] Server: Stores the received data in a database and then performs preprocessing. This includes noise removal and missing data completion. For example, the server can store the received data in a database and remove noise from the video data.

[0120] Data analysis and anomaly detection

[0121] Server: Inputs preprocessed data into a generative AI model to evaluate health status. For example, preprocessed body temperature data can be input into a generative AI model to analyze a pet's health status in real time. The analysis results can also be compared with past data to detect abnormal patterns. For example, the server can compare the analysis results with past data and detect an abnormality when the body temperature rises to 39.2 degrees.

[0122] Alerting and Notifications

[0123] Server: If an abnormality is detected, an alert message containing appropriate advice for the owner is generated and sent to the user's device (smartphone or tablet) via push notification. For example, an alert message stating "The pet's temperature is high and cooling is required" can be generated and sent to the user's smartphone.

[0124] Action Execution

[0125] User: The user receives a notification on their smartphone and checks the alert message. They can then take prompt action, such as moving their pet to a cooler place and providing water. For example, the user can check the notification on their smartphone and take prompt action, such as moving their pet to a cooler place and providing water.

[0126] Specific examples

[0127] 1. Device: The smart glasses capture video of your pet at 8 a.m., measure its temperature with a thermometer, and record how much it has eaten.

[0128] 2. Device: Based on the registered schedule, the collected data is sent to the server via Wi-Fi every hour.

[0129] 3. Server: Stores the received data in a database and performs preprocessing such as noise removal and missing data completion.

[0130] 4. Server: The preprocessed data is input into the generative AI model and analysis begins. For example, if the body temperature data exceeds a certain range, it is recognized as an abnormal pattern.

[0131] 5. Server: If an abnormality is detected, generate an alert message. Generate an alert saying "Your pet has a high temperature and needs to be cooled."

[0132] 6. Server: Sends an alert message to the user's smartphone.

[0133] 7. User: Check the notification on your smartphone and take measures such as moving your pet to a cooler place and giving them water.

[0134] As described above, the pet health monitoring system according to the present invention allows owners to grasp the health condition of their pets in real time and take prompt action.

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

[0136] Step 1: Data collection

[0137] Devices: Smart glasses and other wearable devices collect daily data about your pet.

[0138] Input: Pet activity, temperature, food intake, activity time, etc.

[0139] How it works: The camera in the smart glasses periodically captures images of your pet, the temperature sensor captures temperature data every minute and logs it, and the weight of food is measured to collect data on how much food your pet eats.

[0140] Output: Collected daily data (video data, body temperature data, food intake data, activity data).

[0141] Step 2: Send data

[0142] Terminal: Collected data is periodically batch processed and sent over the network to the server.

[0143] Input: Collected routine data.

[0144] How it works: The smart glasses batch process all collected data every hour and upload it to a server via Wi-Fi or Bluetooth.

[0145] Output: The batched data sent to the server.

[0146] Step 3: Data accumulation and preprocessing

[0147] Server: Stores the received data in a database and then performs preprocessing.

[0148] Input: Batch data sent from the terminal.

[0149] Specific operation: The server stores the received data in an orderly database, applies a noise reduction algorithm to eliminate unnecessary information, and fills in missing data from past data.

[0150] Output: Preprocessed data (denoised data, imputed data).

[0151] Step 4: Data analysis

[0152] Server: Inputs preprocessed data into a generative AI model to assess health status.

[0153] Input: Preprocessed data.

[0154] Specific operation: The server provides preprocessed data to the generative model, which then analyzes the data and calculates health indicators.

[0155] Output: Analysis results (health assessment data).

[0156] Step 5: Anomaly detection

[0157] Server: Compares the analysis results with historical data to detect abnormal patterns.

[0158] Input: Analysis results, historical baseline data.

[0159] How it works: The output of the generative AI model is compared with historical baseline data to identify abnormal patterns, such as when body temperature exceeds the normal range.

[0160] Output: Anomaly detection results.

[0161] Step 6: Alert Generation

[0162] Server: If an anomaly is detected, generate an alert message with appropriate advice.

[0163] Input: Anomaly detection results.

[0164] Specific actions: The server will create appropriate advice based on the type of abnormality and generate a specific alert message such as "Your body temperature is high. Increase your fluid intake and move to a cooler place."

[0165] Output: The generated alert message.

[0166] Step 7: Sending an alert

[0167] Server: Sends the generated alert message to the user's device (smartphone or tablet).

[0168] Input: The generated alert message.

[0169] Specific operation: The server sends the generated alert message to the user's smartphone as a push notification, and the notification is received in real time via the network.

[0170] Output: The alert message sent to the user's terminal.

[0171] Step 8: Take Action

[0172] User: Take appropriate action based on the alert message received.

[0173] Input: The alert message received on the user's smartphone.

[0174] Specific actions: The user checks the alert message on their smartphone and takes measures such as moving the pet to a cooler place and giving it water.

[0175] Output: Implementing specific measures for pets.

[0176] Through the above processing steps, this system monitors the health condition of pets in real time, notifies the user promptly if an abnormality is detected, and enables the user to take appropriate measures.

[0177] (Application example 1)

[0178] 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."

[0179] In the conventional food delivery industry, there were few means to monitor in real time whether food was being maintained at the appropriate temperature during delivery, which led to a risk of a decline in food quality and safety. It was also difficult to respond immediately to abnormal temperature changes. Thus, the lack of real-time monitoring and immediate response in temperature management of food during delivery is a serious issue.

[0180] 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.

[0181] In this invention, the server includes a sensor means for collecting daily data of the pet, a communication means for periodically transmitting the daily data to the server, a preprocessing means for storing the daily data received by the server in a database and preprocessing it, an analysis means for inputting the preprocessed data into a generative model and evaluating the health condition of the pet, an alert generation means for generating an alert message if an abnormality is detected by the analysis means, a notification means for transmitting the alert message to a user's terminal, and a temperature monitoring means for collecting food temperature data in real time and analyzing abnormal temperatures. This enables real-time monitoring and immediate response in food temperature management in the food delivery industry.

[0182] "Sensor means" is a general term for an apparatus or device used to collect data from an object, and examples include cameras and temperature sensors.

[0183] "Communication means" is a general term for methods and technologies for periodically sending collected data to a server, including Wi-Fi and Bluetooth.

[0184] The "preprocessing means" is a device or system that has the function of storing data sent to the server and performing basic data processing such as noise removal and missing data completion.

[0185] An "analysis means" is a device or system that has the ability to use preprocessed data to input into a generative model or artificial intelligence algorithm to evaluate the state of an object.

[0186] The "alert generation means" is a device or system that has the function of generating a warning message or instructions based on the information when an abnormality is detected by the analysis means.

[0187] "Notification means" is a general term for methods and techniques for sending the generated alert message to the user's terminal and promptly notifying the user of its contents.

[0188] A "temperature monitoring means" is a device or system that has the function of collecting the temperature of an object in real time and analyzing whether it is within the appropriate temperature range.

[0189] The present invention relates to a system for monitoring the temperature of food being delivered in real time and sending an alert message if an abnormal temperature is detected. Specific embodiments for carrying out the present invention will be described below.

[0190] Hardware and Software Used

[0191] Hardware:

[0192] Smart glasses: The general term is smart glasses.

[0193] Delivery robot: The general term is delivery robot.

[0194] Temperature sensor: The general term is digital temperature sensor.

[0195] software:

[0196] Data transmission: Using Bluetooth Low Energy (BLE) or Wi-Fi Direct.

[0197] Data storage: Use Amazon Relational Database Service (RDS) as a cloud database.

[0198] Data preprocessing and analysis: Using Python's Pandas and Scikit-learn libraries.

[0199] Notification method: Uses Firebase Cloud Messaging (FCM).

[0200] System Configuration and Operation

[0201] Device behavior

[0202] Digital temperature sensors mounted on smart glasses and delivery robots collect real-time temperature data on food during delivery.

[0203] The collected temperature data is periodically transmitted to a server using Bluetooth Low Energy (BLE) or Wi-Fi Direct.

[0204] Server Operation

[0205] The server receives the transmitted temperature data and stores it in a database using Amazon RDS.

[0206] The stored temperature data is preprocessed using the Pandas library, including noise removal and missing data completion.

[0207] The preprocessed data is analyzed using the Scikit-learn library to assess whether the food temperature is within normal range.

[0208] If an abnormal temperature is detected as a result of the analysis, the server uses an alert generation means to generate an alert message such as "The food temperature is outside the appropriate range. Please check the cooling."

[0209] The generated alert message is sent to the user's (delivery worker's) smartphone using Firebase Cloud Messaging (FCM).

[0210] User Actions

[0211] Users will receive an alert message via push notification on their smartphone.

[0212] After checking the notification, the user follows the instructions to properly manage the temperature of the food.

[0213] Specific examples

[0214] 1. Terminal: During delivery, the temperature sensor in the smart glasses measures the food temperature as 48°C.

[0215] 2. Data transmission: Temperature data is transmitted to a server via Wi-Fi at relay points along the delivery route.

[0216] 3. Server operation: The server receives the data, stores it in a database, and then performs missing data imputation using the Python Pandas library.

[0217] 4. Data analysis: A model trained with Scikit-learn analyzes the temperature data and determines that 48°C is abnormal.

[0218] 5. Alert Generation: Generate an alert message saying "Food temperature is out of the appropriate range. Check cooling."

[0219] 6. Send alerts: Use Firebase Cloud Messaging to push alerts to the delivery person's smartphone.

[0220] 7. User Action: The delivery person receives a notification, checks that the food is cooled, and takes prompt action.

[0221] Prompt Sentence Examples

[0222] "Monitor whether food temperatures are within the appropriate range (e.g., below 60°C). Temperature data of 48°C is sent in real time. Use this data to detect abnormalities and generate appropriate alert messages."

[0223] The above is a specific embodiment for carrying out the present invention.

[0224] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0225] Step 1:

[0226] The device (smart glasses or delivery robot) collects food temperature data. The temperature sensor measures the temperature in real time and records it as temperature data. The input is the temperature value obtained from the temperature sensor, and the output is temperature data.

[0227] Step 2:

[0228] The temperature data collected by the device is periodically sent to the server using Bluetooth Low Energy (BLE) or Wi-Fi Direct. The input is the temperature data, and the output is the temperature data sent to the server.

[0229] Step 3:

[0230] The server stores the received temperature data in a database. The database used is Amazon Relational Database Service (RDS), which stores the received data. The input is the transmitted temperature data, and the output is the temperature data stored in the database.

[0231] Step 4:

[0232] The server preprocesses the stored temperature data. Specifically, it uses the Python Pandas library to remove noise and fill in missing data. The input is the temperature data read from the database, and the output is the preprocessed temperature data.

[0233] Step 5:

[0234] The server performs analysis based on the preprocessed temperature data. The preprocessed data is used as input for a generative AI model (using the Scikit-learn library) to detect abnormal temperatures. The input is the preprocessed temperature data, and the output is the analysis results.

[0235] Step 6:

[0236] If the server detects an anomaly based on the analysis results, it generates an alert message. Specifically, it uses Firebase Cloud Messaging (FCM) to create a message in the specified format. The input is the analysis results, and the output is the generated alert message.

[0237] Step 7:

[0238] The server sends an alert message to the user's (delivery worker's) device. The generated alert message is sent as a push notification using Firebase Cloud Messaging (FCM). The input is the generated alert message, and the output is a notification sent to the user's device.

[0239] Step 8:

[0240] The user receives a push notification and takes appropriate action based on the content of the notification. For example, the user might check the notification message and recheck the temperature of the food. The input is the alert message, and the output is the user's action.

[0241] 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.

[0242] A pet health monitoring system according to an embodiment of the present invention not only collects daily data of pets and sends alerts when abnormalities are detected, but also recognizes the user's emotions and customizes the content of the alert message based on the emotions. This system consists of three main components: a terminal, a server, and a user.

[0243] Overview of program processing

[0244] Data collection:

[0245] Device: Smart glasses or another wearable device uses a camera and temperature sensor to collect daily data about your pet (video, temperature, amount of food eaten, activity time, etc.).

[0246] Data transmission:

[0247] Device: Collected data is periodically batched and sent to a server via Wi-Fi or Bluetooth.

[0248] Data accumulation and preprocessing:

[0249] Server: Receives data sent from the device and stores it in a database. It then performs preprocessing such as noise removal and missing data completion.

[0250] Data Analysis:

[0251] Server: The preprocessed data is fed into a generative model to assess the pet's health. The generative model compares the past data with the current data and detects abnormal patterns.

[0252] Alert generation:

[0253] Server: When an anomaly is detected, the alert generation means is activated to generate an alert message, which includes appropriate advice.

[0254] Emotion recognition:

[0255] Server: The emotion engine analyzes the user's emotions before generating an alert message. The emotion engine uses a camera and microphone to analyze emotions from the user's facial expressions and voice.

[0256] Message customization:

[0257] Server: Customize the alert message content based on the user's emotional data. For example, if the user is feeling stressed, soften the message content.

[0258] Alert sending:

[0259] Server: Sends a customized alert message to the user's device via push notification.

[0260] Take Action:

[0261] User: The user receives a notification on their device (smartphone or tablet) and checks the alert message. A message that takes into consideration the user's feelings is displayed, and the user can manage their pet's health based on that message.

[0262] Specific examples

[0263] 1. Device: The smart glasses monitor your pet, collecting video and temperature data in real time, and even recording feeding intake by weighing food.

[0264] 2. Terminal: Collected data is periodically sent to the server via Wi-Fi.

[0265] 3. Server: Receives the data and stores it in a database. Then, it performs noise removal and missing data imputation.

[0266] 4. Server: Input the preprocessed data into the generative model and start the analysis. Detect anomalies when the body temperature data exceeds a certain range.

[0267] 5. Server: Prepare to generate an alert message if an anomaly is detected.

[0268] 6. Server (Emotion Engine): Analyzes the user's emotions using a camera and microphone before generating an alert message, e.g., detects whether the user is in a stressed state.

[0269] 7. Server: Customize the content of the alert message based on the user's emotional state. If the user is stressed, use a gentler message such as "Please stay calm and move your pet to a cooler place first."

[0270] 8. Server: Sends customized alert messages to users' smartphones.

[0271] 9. User: The user checks the notification on their smartphone and takes measures to improve their pet's health based on the advice.

[0272] In this way, the system of the present invention not only monitors the health status of pets in real time, but also takes into account the user's emotions and provides optimal alert messages, making pet health management more effective and user-friendly.

[0273] The processing flow will be explained below.

[0274] Step 1:

[0275] Device: The smart glasses' camera captures images of your pet in real time, the temperature sensor measures your pet's temperature, and the weight sensor measures food loss and records the amount of food your pet eats. The collected data is temporarily stored.

[0276] Step 2:

[0277] Terminal: Batch processing is performed at regular intervals (e.g., every 5 minutes) to consolidate the collected data, which is then sent to the server via Wi-Fi or Bluetooth.

[0278] Step 3:

[0279] Server: Receives data sent from the device and stores it in a database, which records the date, time, and type of data (e.g., body temperature, activity level).

[0280] Step 4:

[0281] Server: Data pre-processing measures are run to improve the quality of the data, specifically removing noise, filling in missing data, and correcting outliers.

[0282] Step 5:

[0283] Server: Inputs the preprocessed data into a generative model (e.g., a machine learning algorithm), which analyzes the data to assess the pet's health.

[0284] Step 6:

[0285] Server: Detects abnormal patterns by comparing the analysis results with past data. For example, if a normal body temperature is 38.5°C, but the recent temperature is over 39°C, it is considered abnormal.

[0286] Step 7:

[0287] Server: If an abnormality is detected, it generates an alert message and provides specific advice, such as "Your body temperature is high and you need to cool down."

[0288] Step 8:

[0289] Server (emotion engine): When generating an alert, the server uses a camera and microphone to recognize the user's emotions. For example, it determines whether the user is under stress based on their facial expressions and voice.

[0290] Step 9:

[0291] Server: Customize the tone and content of the alert message based on the user's emotional data. For example, for a stressed user, use a gentler message such as "Please stay calm."

[0292] Step 10:

[0293] Server: Sends customized alert messages to users' smartphones via push notifications.

[0294] Step 11:

[0295] User: Receives a notification on their smartphone, checks the alert message, and takes appropriate action to manage their pet's health (e.g., move the pet to a cooler place, provide water, etc.).

[0296] In this way, each step works seamlessly together to create a system that monitors a pet's health in real time and provides appropriate alert messages that take the user's emotions into consideration.

[0297] Example 2

[0298] 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."

[0299] In today's world, pet health management is an important issue, but conventional systems often have a slow response time to detect abnormalities in pets. Furthermore, alert messages may not be effectively received if the user is under high stress. Therefore, it is necessary to monitor pet health in real time and provide alert messages that take the user's emotions into consideration.

[0300] The identification processing by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes: sensor means for collecting vital data of the pet; communication means for periodically transmitting the vital data to the information processing device; data processing means for storing the vital data received by the information processing device in a data storage device and performing preprocessing; analysis means for inputting the preprocessed data into a generative AI model and evaluating the health status of the pet; notification generation means for generating alert information when an abnormality is detected by the analysis means; notification means for transmitting the alert information to the user's terminal; emotion recognition means for analyzing user emotion data before the notification generation means generates the alert information; and information customization means for customizing the alert information based on the analysis result of the emotion recognition means. This makes it possible to monitor the health status of the pet in real time and provide an appropriate alert message that takes into consideration the user's emotions.

[0301] The "sensor means" is a device for collecting daily data about pets, and includes a camera, a thermometer, and the like as a sensing device.

[0302] The "communication means" refers to the devices and technologies for periodically transmitting collected data to the information processing device, and uses wireless communication methods such as Wi-Fi and Bluetooth.

[0303] "Data processing means" refers to devices and technologies that have the function of storing data received by an information processing device in a data storage device and performing preprocessing, such as noise removal and missing data completion.

[0304] A "generative AI model" is an artificial intelligence model that inputs pre-processed data and evaluates the pet's health status, comparing past and current data to detect abnormal patterns.

[0305] "Analysis means" refers to systems and technologies for inputting pre-processed data into a generative AI model and assessing the health status of a pet based on the results.

[0306] The "notification generating means" is a system having a function for generating alert information when an abnormality is detected by the analyzing means.

[0307] The "notification means" refers to a system and technology for transmitting the generated alert information to the user's terminal, and includes functions such as push notification.

[0308] "Emotion recognition means" refers to systems and techniques for analyzing a user's emotion data and assessing the user's emotional state before generating alert information.

[0309] The "information customization means" refers to a system and technology for customizing alert information to suit the emotional state of the user based on the analysis results of the emotion recognition means.

[0310] The pet health monitoring system according to an embodiment of the present invention is implemented using the following hardware and software: The system consists of three main components: a terminal, a server, and a user.

[0311] Hardware and Software Configuration

[0312] Device: Smart glasses or other wearable devices are used to collect daily data about pets. Specifically, these devices have built-in cameras and temperature sensors, and include a communication module that transmits data to a server via Wi-Fi or Bluetooth.

[0313] Server: An information processing device for data storage and preprocessing, utilizing SQL databases, Python's Pandas library, and deep learning frameworks such as TENSORFLOW (registered trademark) and PyTorch. The generative AI model compares past data with current data and detects abnormal patterns.

[0314] User device: A smartphone or tablet used by a user, which is a device for receiving alert messages. It also has the functionality to analyze user emotions using push notifications, cameras, and microphones.

[0315] Program processing

[0316] Data collection

[0317] The device uses the smart glasses' camera and temperature sensor to collect daily data about your pet (video, body temperature, food intake, activity time, etc.) in real time. For example, the smart glasses observe your pet and collect its body temperature data and activity data. At the same time, a digital scale is also used to measure the weight of food.

[0318] Data transmission

[0319] The device periodically processes the collected data in batches and sends them to a server via Wi-Fi. Bluetooth can also be used to transfer data over short distances. For example, the device can process data in batches every hour and send them to a server via Wi-Fi.

[0320] Data accumulation and preprocessing

[0321] The server receives the data sent from the device and stores it in an SQL database. Next, it uses the Python Pandas library to perform preprocessing such as removing noise from the data and filling in missing data. For example, filling in missing values ​​in sensor data and removing noise can improve analysis accuracy.

[0322] Data analysis

[0323] The server inputs the preprocessed data into a generative AI model to analyze the pet's health. Specifically, it uses a deep learning model (such as TensorFlow or PyTorch) to evaluate the pet's health based on the sales data and issues an alert if an abnormal pattern is detected. For example, an abnormality is detected when a pet's body temperature exceeds the normal acceptable range.

[0324] Alert Generation

[0325] If an abnormality is detected by the analysis means, the server generates alert information. When an abnormality is detected, the alert generation module is immediately activated and creates an appropriate alert message corresponding to the pet's condition.

[0326] emotion recognition

[0327] Before generating an alert message, the server uses emotion recognition to analyze the user's emotions. It analyzes the user's facial expressions and tone of voice captured by the camera and microphone to identify the user's emotional state. This is done using technologies such as OpenCV and DeepFace.

[0328] Message customization

[0329] Based on the analysis results of the emotion recognition means, the server customizes the alert message. For example, if the user is feeling stressed, the message will be softer and more friendly, such as "Please stay calm and first move your pet to a cooler place."

[0330] Sending alerts

[0331] The server sends customized alert messages to users' smartphones via push notifications, utilizing the push notification API to provide users with important information instantly.

[0332] Action Execution

[0333] The user can check the received notification and manage the pet's condition according to the alert message, for example, by moving the pet to a cooler place or contacting the appropriate medical institution if necessary.

[0334] Specific examples

[0335] 1. Device: The smart glasses monitor your pet, collecting video and temperature data in real time, and even recording feeding intake by weighing food.

[0336] 2. Terminal: Collected data is periodically sent to the server via Wi-Fi.

[0337] 3. Server: Receives the data and stores it in a database, then performs noise removal and missing data imputation.

[0338] 4. Server: Inputs the pre-processed data into the generative AI model and starts the analysis. If the body temperature data exceeds a certain range, an anomaly is detected.

[0339] 5. Server: Prepare to generate an alert message if an anomaly is detected.

[0340] 6. Server (Emotion Recognition Means): Before generating an alert message, analyze the user's emotions using a camera and microphone. For example, detect whether the user is in a stressed state.

[0341] 7. Server: Customize the content of the alert message based on the user's emotional state. If the user is stressed, use a gentler message such as "Please stay calm and move your pet to a cooler place first."

[0342] 8. Server: Sends customized alert messages to users' smartphones.

[0343] 9. User: The user checks the notification on their smartphone and takes measures to improve their pet's health based on the advice.

[0344] Prompt Sentence Examples

[0345] "Please give me some sample code for a Python program that analyzes pet temperature data and generates an alert message that takes user emotions into consideration if there is an abnormality."

[0346] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0347] Step 1: Data collection

[0348] Device: Smart glasses or other wearable devices use cameras and temperature sensors to collect daily data about your pet in real time (video, body temperature, food intake, activity time, etc.). Specifically, the camera in the smart glasses observes your pet and captures image data every second. At the same time, the temperature sensor measures your pet's temperature every few seconds, and a digital scale measures the weight of its food.

[0349] Input: Sensor data from the operating environment (pet surroundings, pet status).

[0350] Output: Collected raw sensor data (video data, body temperature data, food intake data, etc.).

[0351] Step 2: Send data

[0352] Device: Collected data is periodically batched and sent to a server via Wi-Fi or Bluetooth. Specifically, the device accumulates data collected every minute, batches each data set, and then sends it to the server via Wi-Fi.

[0353] Input: Raw collected sensor data.

[0354] Output: The batch data sent to the server.

[0355] Step 3: Data accumulation and preprocessing

[0356] Server: Receives data sent from the device and stores it in an SQL database. It then uses Python's Pandas library to perform preprocessing, such as removing noise from the data and filling in missing data. Specifically, it imports the received data into the database, fills in missing values ​​using linear interpolation or the average value, and removes noise through filtering.

[0357] Input: Batch data sent from the terminal.

[0358] Output: A preprocessed and clean dataset.

[0359] Step 4: Data analysis

[0360] Server: The preprocessed data is fed into a generative AI model to assess the pet's health. Specifically, a deep learning model (e.g., TensorFlow or PyTorch) is used to perform anomaly detection based on daily activity data and vital signs. For example, anomalies are detected when body temperature exceeds the normal acceptable range.

[0361] Input: The preprocessed dataset.

[0362] Output: Health status assessment result (normal or abnormal).

[0363] Step 5: Alert Generation

[0364] Server: If an abnormality is detected by the analysis means, it generates alert information. Specifically, it immediately launches the alert generation module upon detecting an abnormality and creates an alert message related to the pet's health condition.

[0365] Input: Health assessment result (abnormal).

[0366] Output: The initial alert message.

[0367] Step 6: Emotion Recognition

[0368] Server: Before generating an alert message, the server analyzes the user's emotional data. It acquires camera and microphone data from the user's device and inputs it into an emotion recognition engine. Specifically, it analyzes the user's facial expressions using OpenCV and DeepFace, and evaluates the tone of voice using voice analysis.

[0369] Input: Video and audio data obtained from the user's device.

[0370] Output: Evaluation of the user's emotional state.

[0371] Step 7: Customize your message

[0372] Server: Customize the alert message based on the emotion recognition results. For example, if the user is feeling stressed, change the usual alert message to something more gentle, such as "Please stay calm and move your pet to a cooler place first."

[0373] Input: Initial alert message, evaluation of the user's emotional state.

[0374] Output: The customized alert message.

[0375] Step 8: Sending an alert

[0376] Server: Sends customized alert messages to users' devices via push notifications. Specifically, the server uses the push notification API to instantly notify users on their smartphones or tablets.

[0377] Input: Your customized alert message.

[0378] Output: Push notification to user device.

[0379] Step 9: Take Action

[0380] User: The user checks the notification received on the device and takes care of the pet according to the alert message. For example, the user takes appropriate action to move the pet to a cooler place. If necessary, the user contacts a nearby veterinary clinic for further diagnosis.

[0381] Input: The pushed alert message.

[0382] Output: Specific actions to improve your pet's health.

[0383] (Application example 2)

[0384] 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."

[0385] Many systems exist for monitoring the health of pets in their daily lives, but these systems often send uniform alert messages without considering the user's psychological state. This can cause stress for users, making it difficult to take appropriate action. Furthermore, there are limitations to detecting anomalies based on the analysis of daily data, requiring further data analysis in the work environment. Therefore, there is a need for a system that takes the user's emotional state into account and encourages appropriate and flexible responses.

[0386] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0387] In this invention, the server includes sensor means for collecting daily data about the pet, communication means for periodically transmitting the daily data to the server, preprocessing means for storing the daily data received by the server in a database and preprocessing it, analysis means for inputting the preprocessed data into a generative model and evaluating the health condition of the pet, alert generation means for generating an alert message if an abnormality is detected by the analysis means, emotion recognition means for analyzing the user's facial expressions and voice to recognize their emotional state, message customization means for customizing the content of the alert message based on the emotion recognition means, and notification means for transmitting the customized alert message to the user's terminal. This makes it possible to provide an optimal alert message that takes into account the user's emotional state.

[0388] "Sensor means" refers to a device for collecting daily data about a pet, and includes a camera and a body temperature sensor.

[0389] "Communication means" refers to the technology used to periodically transmit collected daily data to a server, and uses communication protocols such as Wi-Fi and Bluetooth.

[0390] The "preprocessing means" refers to a function that stores the daily data received by the server in a database and performs noise removal and missing data completion.

[0391] The "analysis means" has the function of inputting preprocessed data into a generative model and evaluating the health condition of the pet.

[0392] The "alert generation means" is a mechanism for generating an alert message when an abnormality is detected by the analysis means.

[0393] "Emotion recognition means" is a technology for analyzing a user's facial expressions and voice to recognize their emotional state.

[0394] The "message customization means" is a function for customizing the contents of the alert message based on the emotion recognition means.

[0395] The "notification means" is a technique for sending the customized alert message to the user's terminal.

[0396] A system based on an embodiment of the present invention uses a smart band or smart glasses to collect daily data of factory workers, and if an abnormality is detected, sends an alert message customized based on the worker's emotion to the user's device. Specific embodiments are described below.

[0397] Data collection

[0398] The devices (smart band and smart glasses) collect daily data of factory workers (body temperature, heart rate, work environment data, etc.). The smart band collects data using heart rate and body temperature sensors, while the smart glasses use a built-in camera to capture images of the work environment and the facial expressions of workers.

[0399] Specific hardware examples include a smart band called "Fitbit" and smart glasses called "Google (registered trademark) Glass (registered trademark)."

[0400] Data transmission

[0401] The collected data is sent from the devices (smart band and smart glasses) to a server via Wi-Fi or Bluetooth. Data is sent periodically, enabling real-time anomaly detection.

[0402] Data accumulation and preprocessing

[0403] The server stores the received data in a database (e.g., MySQL®), and then uses Python scripts to perform preprocessing such as removing noise from the data and filling in missing data.

[0404] Data analysis

[0405] Once preprocessed, the data is input into a generative AI model (e.g., TensorFlow or PyTorch). This model compares past data with current data to detect abnormalities in body temperature and heart rate. Specifically, the analysis method determines that changes in heart rate or body temperature that exceed a certain range are abnormal.

[0406] Alert Generation

[0407] If the server detects an abnormality in the analysis, it generates an alert message using a Python script, which includes specific measures such as "Your temperature is too high. Please drink water and take a break."

[0408] emotion recognition

[0409] Before generating an alert, the server uses data acquired from the smart glasses' built-in camera and microphone to analyze the user's emotional state using an emotion recognition engine (e.g., OpenAI (registered trademark)). Stress, impatience, fatigue, etc. are recognized.

[0410] Message customization

[0411] Based on the analyzed emotional state, the server uses a message customization method to adjust the content of the alert message. For example, if the user is feeling stressed, the server softens the message and changes it to something like, "Relax. First, take a deep breath and calm down."

[0412] Sending alerts

[0413] The server sends a customized alert message to the user's device (smartphone or tablet) via push notification, allowing workers to check the notification and take appropriate action promptly.

[0414] Specific examples

[0415] Here are some examples of specific prompts:

[0416] Create a program that monitors the health data of factory workers in real time and generates customized alert messages based on emotion recognition when an abnormality is detected. Use a smart band and smart glasses to collect data, and generate alerts based on heart rate and body temperature data when an abnormality occurs, using a tone that matches the user's emotion.

[0417] In this way, it is possible to provide optimal alert messages that take into account the user's emotional state.This system allows factory workers to manage their health efficiently and without stress.

[0418] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0419] Step 1:

[0420] The devices (smart bands and smart glasses) collect daily data of factory workers (body temperature, heart rate, work environment data, etc.) in real time.

[0421] Specifically, the smart band's body temperature and heart rate sensors collect data at regular intervals, while the smart glasses' built-in camera captures the worker's work status and facial expressions.

[0422] Inputs include body temperature, heart rate, and video data.

[0423] As output, collected daily data is produced.

[0424] Step 2:

[0425] The collected daily data is periodically sent from the devices (smart band and smart glasses) to a server via Wi-Fi or Bluetooth.

[0426] Specifically, the smart band and smart glasses batch process data at regular intervals and send it to the server using a communication protocol.

[0427] As input, collected daily data.

[0428] The output is the daily data sent to the server.

[0429] Step 3:

[0430] The server stores the received daily data in a database and performs preprocessing (noise removal and missing data completion).

[0431] Specifically, data cleansing is performed using a Python script.

[0432] The raw data sent to the server as input.

[0433] The output is the cleansed pre-processed data.

[0434] Step 4:

[0435] Once preprocessed, the data is processed on the server and input into a generative AI model (using TensorFlow or PyTorch).

[0436] Specifically, the generative AI model compares past normal data with current data and runs an anomaly detection algorithm.

[0437] As input, preprocessed daily data.

[0438] The output is an anomaly detection result.

[0439] Step 5:

[0440] The server generates an alert message if an abnormality is detected.

[0441] Specifically, a Python script is used to create a specific alert message based on the abnormality (for example, "Your body temperature is too high. Please drink water and take a break").

[0442] As input, anomaly detection results.

[0443] As output, an alert message is generated.

[0444] Step 6:

[0445] Before generating an alert message, the server inputs the user's facial expressions and voice into an emotion recognition engine to analyze the user's emotional state.

[0446] Specifically, an emotion recognition engine (using OpenAI) uses data obtained from the smart glasses' camera and microphone to analyze the user's psychological state (stress, impatience, fatigue, etc.).

[0447] As input, facial expression data and voice data.

[0448] The output is the user's emotional state.

[0449] Step 7:

[0450] The server customizes the alert message based on the emotion recognition results.

[0451] Specifically, the message customization means adjusts the content of the alert message to match the user's emotional state (for example, if the user is feeling stressed, it will say, "Relax. First, take a deep breath and stay calm").

[0452] As input, the emotional state and the generated alert message.

[0453] As output, you get a customized alert message.

[0454] Step 8:

[0455] The server sends a customized alert message to the user's device (smartphone or tablet) via push notification.

[0456] Specifically, the notification method within the server sends a message using a push notification service (such as Firebase Cloud Messaging).

[0457] As input, a customized alert message.

[0458] The output is an alert message displayed on the user's terminal.

[0459] 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.

[0460] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (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.

[0461] 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.

[0462] [Second embodiment]

[0463] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0464] 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.

[0465] 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).

[0466] 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.

[0467] 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.

[0468] 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).

[0469] 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.

[0470] 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.

[0471] 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.

[0472] 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.

[0473] In the smart glasses 214, the 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.

[0474] 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."

[0475] As an embodiment of the present invention, a system will be described that monitors the health condition of a pet in real time and sends an alert to the owner if an abnormality is detected. This system is mainly composed of a terminal, a server, and a user.

[0476] Overview of program processing

[0477] Data collection:

[0478] Device: Cameras and temperature sensors installed in smart glasses and other wearable devices collect daily data about your pet (video, body temperature, amount of food eaten, activity time, etc.).

[0479] Data transmission:

[0480] On the device: Collected data is periodically batched and sent to a server via Wi-Fi or Bluetooth.

[0481] Data accumulation and preprocessing:

[0482] Server: Receives data sent from the device and stores it in a database. Then, it performs preprocessing such as noise removal and missing data completion.

[0483] Data Analysis:

[0484] Server: The preprocessed data is input into a generative model (artificial intelligence model or analytical algorithm) to assess the pet's health condition.

[0485] Anomaly detection:

[0486] Server: Compares the analysis results with past data to detect abnormal patterns. For example, if the body temperature continues to rise from 38.5°C to 39.2°C, it is determined to be abnormal.

[0487] Alert generation:

[0488] Server: If an abnormality is detected, generate an alert message with appropriate advice. For example, generate an alert saying "Temperature is high. Increase fluid intake and move to a cooler place."

[0489] Alert sending:

[0490] Server: The generated alert message is sent to the user's device (smartphone or tablet) via push notification.

[0491] Take Action:

[0492] User: The user receives a notification on a device such as a smartphone, checks the alert message, and then takes appropriate action for their pet based on the content of the notification.

[0493] Specific examples

[0494] 1. Device: The smart glasses capture video of your pet, measure its temperature with a thermometer, and record its feeding by weighing its food.

[0495] 2. Terminal: Based on the registered schedule, the collected data is sent to the server via Wi-Fi.

[0496] 3. Server: Receives the data, stores it in a database, and then performs preprocessing such as noise removal and missing data imputation.

[0497] 4. Server: The preprocessed data is input into the generative model and analysis begins. For example, if the body temperature data exceeds a certain range, it is recognized as an abnormal pattern.

[0498] 5. Server: If an abnormality is detected, generate an alert message. For example, generate an alert saying "Your pet has a high temperature and needs to be cooled."

[0499] 6. Server: Sends an alert message to the user's smartphone.

[0500] 7. User: Check the notification on your smartphone and take measures such as moving your pet to a cooler place and giving them water.

[0501] The above is the overall flow and specific processing contents of the system according to the embodiment of the present invention. The system of the present invention enables pet owners to grasp the health condition of their pets in real time and to promptly take appropriate measures.

[0502] The processing flow will be explained below.

[0503] Step 1:

[0504] Device: The smart glasses' camera captures images of your pet in real time, the temperature sensor measures your pet's temperature, and the weight sensor measures the amount of food your pet eats. The collected data is temporarily stored in the device's memory.

[0505] Step 2:

[0506] Terminal: Collected data is batch processed at regular intervals and compiled. The batched data is sent to the server via Wi-Fi or Bluetooth.

[0507] Step 3:

[0508] Server: Receives data sent from the device and stores it in a database. The database contains information such as date and time, type of data (body temperature, activity level, meal amount, etc.), and sensor information.

[0509] Step 4:

[0510] Server: Performs data preprocessing. Specifically, it applies a noise reduction algorithm to remove outliers and fills in missing data. For example, if a body temperature sensor temporarily loses data, it fills in the missing data using data from before and after.

[0511] Step 5:

[0512] Server: The preprocessed data is input into a generative model (an artificial intelligence model or analytical algorithm). The generative model analyzes the data and evaluates the pet's health condition.

[0513] Step 6:

[0514] Server: Detects abnormal patterns by comparing the analysis results with past health data. For example, if the current temperature is abnormally high compared with the temperature data from the past week, this is detected.

[0515] Step 7:

[0516] Server: If an abnormality is detected, the alert generation means generates an alert message. The message includes specific advice. For example, it could say, "Your pet's temperature is high and needs to be cooled."

[0517] Step 8:

[0518] Server: Sends the generated alert message to the user's device via push notification.

[0519] Step 9:

[0520] User: Receives an alert message on their smartphone or tablet. The message describes the pet's health status and specific measures to take. The user checks the message and takes the necessary measures.

[0521] The above are the processing steps in the system of the present invention, which allows for seamless processing from data collection to anomaly detection and notification to the user.

[0522] Example 1

[0523] 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."

[0524] Conventional pet health management systems lack the functionality to monitor minute-by-minute changes in body temperature and activity in real time, which means it takes a long time for abnormalities to be detected. Furthermore, there are insufficient methods for quickly communicating information to owners when an abnormality is detected, which can delay appropriate measures. This increases the risk of a pet's health deteriorating.

[0525] 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.

[0526] In this invention, the server includes a sensor means for collecting daily data of the pet, a communication means for periodically transmitting the daily data to the server, a preprocessing means for storing the daily data received by the server in a database and preprocessing the data, an analysis means for inputting the preprocessed data into an artificial intelligence model and evaluating the health condition of the pet, an alert generation means for generating an alert message including appropriate advice if the analysis means detects an abnormality, and a notification means for transmitting the alert message to a user's terminal. This makes it possible to monitor the health condition of the pet in real time, and to promptly notify the owner if an abnormality is detected so that appropriate measures can be taken.

[0527] The "sensor means" is a device for collecting daily data such as the pet's body temperature, activity status, and amount of food eaten.

[0528] "Communication means" refers to a network communication technology for periodically transmitting collected data to a server.

[0529] The "preprocessing means" is a technology that stores the daily data received by the server in a database and performs preprocessing such as noise removal and missing data completion.

[0530] The "analysis means" refers to a technology that inputs pre-processed data into an artificial intelligence model to assess the health status of a pet.

[0531] The "alert generation means" is a technique for generating an alert message containing appropriate advice when an abnormality is detected by the analysis means.

[0532] The "notification means" is a technique for sending the alert message to the user's terminal.

[0533] An "artificial intelligence model" is a machine learning algorithm used in data analysis to assess the health status of pets.

[0534] A "database" is an electronic information management system for organizing and storing collected routine data.

[0535] This invention relates to a system that monitors the health status of pets in real time and sends an alert to the owner if an abnormality is detected. This system is mainly composed of a terminal, a server, and a user.

[0536] Hardware and software used

[0537] Devices: Smart glasses and other wearable devices include the following hardware:

[0538] Camera: Capture footage of your pet.

[0539] Body temperature sensor: Measure your pet's body temperature.

[0540] Communication module: Sends data to the server using Wi-Fi or Bluetooth.

[0541] Server: The server includes the following software and hardware:

[0542] Database: Organizes and stores collected routine data.

[0543] Preprocessing software: Remove noise and fill in missing data.

[0544] Generative AI model: Analyzes pre-processed data and assesses the pet's health.

[0545] Alert generation software: Generates an alert message when an anomaly is detected.

[0546] Notification system: Pushes alert messages to user devices.

[0547] Data collection and transmission

[0548] Device: Smart glasses or other wearable devices collect your pet's daily data (video, body temperature, food intake, activity time, etc.) For example, smart glasses can capture video of your pet's activity at 8 a.m. and measure its temperature with a body temperature sensor.

[0549] Device: The collected data is periodically batched and sent to the server via Wi-Fi or Bluetooth. For example, at 9:00 a.m., the device can send the video and temperature data from the previous hour to the server via Wi-Fi.

[0550] Data accumulation and preprocessing

[0551] Server: Stores the received data in a database and then performs preprocessing. This includes noise removal and missing data completion. For example, the server can store the received data in a database and remove noise from the video data.

[0552] Data analysis and anomaly detection

[0553] Server: Inputs preprocessed data into a generative AI model to evaluate health status. For example, preprocessed body temperature data can be input into a generative AI model to analyze a pet's health status in real time. The analysis results can also be compared with past data to detect abnormal patterns. For example, the server can compare the analysis results with past data and detect an abnormality when the body temperature rises to 39.2 degrees.

[0554] Alerting and Notifications

[0555] Server: If an abnormality is detected, an alert message containing appropriate advice for the owner is generated and sent to the user's device (smartphone or tablet) via push notification. For example, an alert message stating "The pet's temperature is high and cooling is required" can be generated and sent to the user's smartphone.

[0556] Action Execution

[0557] User: The user receives a notification on their smartphone and checks the alert message. They can then take prompt action, such as moving their pet to a cooler place and providing water. For example, the user can check the notification on their smartphone and take prompt action, such as moving their pet to a cooler place and providing water.

[0558] Specific examples

[0559] 1. Device: The smart glasses capture video of your pet at 8 a.m., measure its temperature with a thermometer, and record how much it has eaten.

[0560] 2. Device: Based on the registered schedule, the collected data is sent to the server via Wi-Fi every hour.

[0561] 3. Server: Stores the received data in a database and performs preprocessing such as noise removal and missing data completion.

[0562] 4. Server: The preprocessed data is input into the generative AI model and analysis begins. For example, if the body temperature data exceeds a certain range, it is recognized as an abnormal pattern.

[0563] 5. Server: If an abnormality is detected, generate an alert message. Generate an alert saying "Your pet has a high temperature and needs to be cooled."

[0564] 6. Server: Sends an alert message to the user's smartphone.

[0565] 7. User: Check the notification on your smartphone and take measures such as moving your pet to a cooler place and giving them water.

[0566] As described above, the pet health monitoring system according to the present invention allows owners to grasp the health condition of their pets in real time and take prompt action.

[0567] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0568] Step 1: Data collection

[0569] Devices: Smart glasses and other wearable devices collect daily data about your pet.

[0570] Input: Pet activity, temperature, food intake, activity time, etc.

[0571] How it works: The camera in the smart glasses periodically captures images of your pet, the temperature sensor captures temperature data every minute and logs it, and the weight of food is measured to collect data on how much food your pet eats.

[0572] Output: Collected daily data (video data, body temperature data, food intake data, activity data).

[0573] Step 2: Send data

[0574] Terminal: Collected data is periodically batch processed and sent over the network to the server.

[0575] Input: Collected routine data.

[0576] How it works: The smart glasses batch process all collected data every hour and upload it to a server via Wi-Fi or Bluetooth.

[0577] Output: The batched data sent to the server.

[0578] Step 3: Data accumulation and preprocessing

[0579] Server: Stores the received data in a database and then performs preprocessing.

[0580] Input: Batch data sent from the terminal.

[0581] Specific operation: The server stores the received data in an orderly database, applies a noise reduction algorithm to eliminate unnecessary information, and fills in missing data from past data.

[0582] Output: Preprocessed data (denoised data, imputed data).

[0583] Step 4: Data analysis

[0584] Server: Inputs preprocessed data into a generative AI model to assess health status.

[0585] Input: Preprocessed data.

[0586] Specific operation: The server provides preprocessed data to the generative model, which then analyzes the data and calculates health indicators.

[0587] Output: Analysis results (health assessment data).

[0588] Step 5: Anomaly detection

[0589] Server: Compares the analysis results with historical data to detect abnormal patterns.

[0590] Input: Analysis results, historical baseline data.

[0591] How it works: The output of the generative AI model is compared with historical baseline data to identify abnormal patterns, such as when body temperature exceeds the normal range.

[0592] Output: Anomaly detection results.

[0593] Step 6: Alert Generation

[0594] Server: If an anomaly is detected, generate an alert message with appropriate advice.

[0595] Input: Anomaly detection results.

[0596] Specific actions: The server will create appropriate advice based on the type of abnormality and generate a specific alert message such as "Your body temperature is high. Increase your fluid intake and move to a cooler place."

[0597] Output: The generated alert message.

[0598] Step 7: Sending an alert

[0599] Server: Sends the generated alert message to the user's device (smartphone or tablet).

[0600] Input: The generated alert message.

[0601] Specific operation: The server sends the generated alert message to the user's smartphone as a push notification, and the notification is received in real time via the network.

[0602] Output: The alert message sent to the user's terminal.

[0603] Step 8: Take Action

[0604] User: Take appropriate action based on the alert message received.

[0605] Input: The alert message received on the user's smartphone.

[0606] Specific actions: The user checks the alert message on their smartphone and takes measures such as moving the pet to a cooler place and giving it water.

[0607] Output: Implementing specific measures for pets.

[0608] Through the above processing steps, this system monitors the health condition of pets in real time, notifies the user promptly if an abnormality is detected, and enables the user to take appropriate measures.

[0609] (Application example 1)

[0610] 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."

[0611] In the conventional food delivery industry, there were few means to monitor in real time whether food was being maintained at the appropriate temperature during delivery, which led to a risk of a decline in food quality and safety. It was also difficult to respond immediately to abnormal temperature changes. Thus, the lack of real-time monitoring and immediate response in temperature management of food during delivery is a serious issue.

[0612] 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.

[0613] In this invention, the server includes a sensor means for collecting daily data of the pet, a communication means for periodically transmitting the daily data to the server, a preprocessing means for storing the daily data received by the server in a database and preprocessing it, an analysis means for inputting the preprocessed data into a generative model and evaluating the health condition of the pet, an alert generation means for generating an alert message if an abnormality is detected by the analysis means, a notification means for transmitting the alert message to a user's terminal, and a temperature monitoring means for collecting food temperature data in real time and analyzing abnormal temperatures. This enables real-time monitoring and immediate response in food temperature management in the food delivery industry.

[0614] "Sensor means" is a general term for an apparatus or device used to collect data from an object, and examples include cameras and temperature sensors.

[0615] "Communication means" is a general term for methods and technologies for periodically sending collected data to a server, including Wi-Fi and Bluetooth.

[0616] The "preprocessing means" is a device or system that has the function of storing data sent to the server and performing basic data processing such as noise removal and missing data completion.

[0617] An "analysis means" is a device or system that has the ability to use preprocessed data to input into a generative model or artificial intelligence algorithm to evaluate the state of an object.

[0618] The "alert generation means" is a device or system that has the function of generating a warning message or instructions based on the information when an abnormality is detected by the analysis means.

[0619] "Notification means" is a general term for methods and techniques for sending the generated alert message to the user's terminal and promptly notifying the user of its contents.

[0620] A "temperature monitoring means" is a device or system that has the function of collecting the temperature of an object in real time and analyzing whether it is within the appropriate temperature range.

[0621] The present invention relates to a system for monitoring the temperature of food being delivered in real time and sending an alert message if an abnormal temperature is detected. Specific embodiments for carrying out the present invention will be described below.

[0622] Hardware and Software Used

[0623] Hardware:

[0624] Smart glasses: The general term is smart glasses.

[0625] Delivery robot: The general term is delivery robot.

[0626] Temperature sensor: The general term is digital temperature sensor.

[0627] software:

[0628] Data transmission: Using Bluetooth Low Energy (BLE) or Wi-Fi Direct.

[0629] Data storage: Use Amazon Relational Database Service (RDS) as a cloud database.

[0630] Data preprocessing and analysis: Using Python's Pandas and Scikit-learn libraries.

[0631] Notification method: Uses Firebase Cloud Messaging (FCM).

[0632] System Configuration and Operation

[0633] Device behavior

[0634] Digital temperature sensors mounted on smart glasses and delivery robots collect real-time temperature data on food during delivery.

[0635] The collected temperature data is periodically transmitted to a server using Bluetooth Low Energy (BLE) or Wi-Fi Direct.

[0636] Server Operation

[0637] The server receives the transmitted temperature data and stores it in a database using Amazon RDS.

[0638] The stored temperature data is preprocessed using the Pandas library, including noise removal and missing data completion.

[0639] The preprocessed data is analyzed using the Scikit-learn library to assess whether the food temperature is within normal range.

[0640] If an abnormal temperature is detected as a result of the analysis, the server uses an alert generation means to generate an alert message such as "The food temperature is outside the appropriate range. Please check the cooling."

[0641] The generated alert message is sent to the user's (delivery worker's) smartphone using Firebase Cloud Messaging (FCM).

[0642] User Actions

[0643] Users will receive an alert message via push notification on their smartphone.

[0644] After checking the notification, the user follows the instructions to properly manage the temperature of the food.

[0645] Specific examples

[0646] 1. Terminal: During delivery, the temperature sensor in the smart glasses measures the food temperature as 48°C.

[0647] 2. Data transmission: Temperature data is transmitted to a server via Wi-Fi at relay points along the delivery route.

[0648] 3. Server operation: The server receives the data, stores it in a database, and then performs missing data imputation using the Python Pandas library.

[0649] 4. Data analysis: A model trained with Scikit-learn analyzes the temperature data and determines that 48°C is abnormal.

[0650] 5. Alert Generation: Generate an alert message saying "Food temperature is out of the appropriate range. Check cooling."

[0651] 6. Send alerts: Use Firebase Cloud Messaging to push alerts to the delivery person's smartphone.

[0652] 7. User Action: The delivery person receives a notification, checks that the food is cooled, and takes prompt action.

[0653] Prompt Sentence Examples

[0654] "Monitor whether food temperatures are within the appropriate range (e.g., below 60°C). Temperature data of 48°C is sent in real time. Use this data to detect abnormalities and generate appropriate alert messages."

[0655] The above is a specific embodiment for carrying out the present invention.

[0656] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0657] Step 1:

[0658] The device (smart glasses or delivery robot) collects food temperature data. The temperature sensor measures the temperature in real time and records it as temperature data. The input is the temperature value obtained from the temperature sensor, and the output is temperature data.

[0659] Step 2:

[0660] The temperature data collected by the device is periodically sent to the server using Bluetooth Low Energy (BLE) or Wi-Fi Direct. The input is the temperature data, and the output is the temperature data sent to the server.

[0661] Step 3:

[0662] The server stores the received temperature data in a database. The database used is Amazon Relational Database Service (RDS), which stores the received data. The input is the transmitted temperature data, and the output is the temperature data stored in the database.

[0663] Step 4:

[0664] The server preprocesses the stored temperature data. Specifically, it uses the Python Pandas library to remove noise and fill in missing data. The input is the temperature data read from the database, and the output is the preprocessed temperature data.

[0665] Step 5:

[0666] The server performs analysis based on the preprocessed temperature data. The preprocessed data is used as input for a generative AI model (using the Scikit-learn library) to detect abnormal temperatures. The input is the preprocessed temperature data, and the output is the analysis results.

[0667] Step 6:

[0668] If the server detects an anomaly based on the analysis results, it generates an alert message. Specifically, it uses Firebase Cloud Messaging (FCM) to create a message in the specified format. The input is the analysis results, and the output is the generated alert message.

[0669] Step 7:

[0670] The server sends an alert message to the user's (delivery worker's) device. The generated alert message is sent as a push notification using Firebase Cloud Messaging (FCM). The input is the generated alert message, and the output is a notification sent to the user's device.

[0671] Step 8:

[0672] The user receives a push notification and takes appropriate action based on the content of the notification. For example, the user might check the notification message and recheck the temperature of the food. The input is the alert message, and the output is the user's action.

[0673] 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.

[0674] A pet health monitoring system according to an embodiment of the present invention not only collects daily data of pets and sends alerts when abnormalities are detected, but also recognizes the user's emotions and customizes the content of the alert message based on the emotions. This system consists of three main components: a terminal, a server, and a user.

[0675] Overview of program processing

[0676] Data collection:

[0677] Device: Smart glasses or another wearable device uses a camera and temperature sensor to collect daily data about your pet (video, temperature, amount of food eaten, activity time, etc.).

[0678] Data transmission:

[0679] Device: Collected data is periodically batched and sent to a server via Wi-Fi or Bluetooth.

[0680] Data accumulation and preprocessing:

[0681] Server: Receives data sent from the device and stores it in a database. It then performs preprocessing such as noise removal and missing data completion.

[0682] Data Analysis:

[0683] Server: The preprocessed data is fed into a generative model to assess the pet's health. The generative model compares the past data with the current data and detects abnormal patterns.

[0684] Alert generation:

[0685] Server: When an anomaly is detected, the alert generation means is activated to generate an alert message, which includes appropriate advice.

[0686] Emotion recognition:

[0687] Server: The emotion engine analyzes the user's emotions before generating an alert message. The emotion engine uses a camera and microphone to analyze emotions from the user's facial expressions and voice.

[0688] Message customization:

[0689] Server: Customize the alert message content based on the user's emotional data. For example, if the user is feeling stressed, soften the message content.

[0690] Alert sending:

[0691] Server: Sends a customized alert message to the user's device via push notification.

[0692] Take Action:

[0693] User: The user receives a notification on their device (smartphone or tablet) and checks the alert message. A message that takes into consideration the user's feelings is displayed, and the user can manage their pet's health based on that message.

[0694] Specific examples

[0695] 1. Device: The smart glasses monitor your pet, collecting video and temperature data in real time, and even recording feeding intake by weighing food.

[0696] 2. Terminal: Collected data is periodically sent to the server via Wi-Fi.

[0697] 3. Server: Receives the data and stores it in a database. Then, it performs noise removal and missing data imputation.

[0698] 4. Server: Input the preprocessed data into the generative model and start the analysis. Detect anomalies when the body temperature data exceeds a certain range.

[0699] 5. Server: Prepare to generate an alert message if an anomaly is detected.

[0700] 6. Server (Emotion Engine): Analyzes the user's emotions using a camera and microphone before generating an alert message, e.g., detects whether the user is in a stressed state.

[0701] 7. Server: Customize the content of the alert message based on the user's emotional state. If the user is stressed, use a gentler message such as "Please stay calm and move your pet to a cooler place first."

[0702] 8. Server: Sends customized alert messages to users' smartphones.

[0703] 9. User: The user checks the notification on their smartphone and takes measures to improve their pet's health based on the advice.

[0704] In this way, the system of the present invention not only monitors the health status of pets in real time, but also takes into account the user's emotions and provides optimal alert messages, making pet health management more effective and user-friendly.

[0705] The processing flow will be explained below.

[0706] Step 1:

[0707] Device: The smart glasses' camera captures images of your pet in real time, the temperature sensor measures your pet's temperature, and the weight sensor measures food loss and records the amount of food your pet eats. The collected data is temporarily stored.

[0708] Step 2:

[0709] Terminal: Batch processing is performed at regular intervals (e.g., every 5 minutes) to consolidate the collected data, which is then sent to the server via Wi-Fi or Bluetooth.

[0710] Step 3:

[0711] Server: Receives data sent from the device and stores it in a database, which records the date, time, and type of data (e.g., body temperature, activity level).

[0712] Step 4:

[0713] Server: Data pre-processing measures are run to improve the quality of the data, specifically removing noise, filling in missing data, and correcting outliers.

[0714] Step 5:

[0715] Server: Inputs the preprocessed data into a generative model (e.g., a machine learning algorithm), which analyzes the data to assess the pet's health.

[0716] Step 6:

[0717] Server: Detects abnormal patterns by comparing the analysis results with past data. For example, if a normal body temperature is 38.5°C, but the recent temperature is over 39°C, it is considered abnormal.

[0718] Step 7:

[0719] Server: If an abnormality is detected, it generates an alert message and provides specific advice, such as "Your body temperature is high and you need to cool down."

[0720] Step 8:

[0721] Server (emotion engine): When generating an alert, the server uses a camera and microphone to recognize the user's emotions. For example, it determines whether the user is under stress based on their facial expressions and voice.

[0722] Step 9:

[0723] Server: Customize the tone and content of the alert message based on the user's emotional data. For example, for a stressed user, use a gentler message such as "Please stay calm."

[0724] Step 10:

[0725] Server: Sends customized alert messages to users' smartphones via push notifications.

[0726] Step 11:

[0727] User: Receives a notification on their smartphone, checks the alert message, and takes appropriate action to manage their pet's health (e.g., move the pet to a cooler place, provide water, etc.).

[0728] In this way, each step works seamlessly together to create a system that monitors a pet's health in real time and provides appropriate alert messages that take the user's emotions into consideration.

[0729] Example 2

[0730] 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."

[0731] In today's world, pet health management is an important issue, but conventional systems often have a slow response time to detect abnormalities in pets. Furthermore, alert messages may not be effectively received if the user is under high stress. Therefore, it is necessary to monitor pet health in real time and provide alert messages that take the user's emotions into consideration.

[0732] The identification processing by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes: sensor means for collecting vital data of the pet; communication means for periodically transmitting the vital data to the information processing device; data processing means for storing the vital data received by the information processing device in a data storage device and performing preprocessing; analysis means for inputting the preprocessed data into a generative AI model and evaluating the health status of the pet; notification generation means for generating alert information when an abnormality is detected by the analysis means; notification means for transmitting the alert information to the user's terminal; emotion recognition means for analyzing user emotion data before the notification generation means generates the alert information; and information customization means for customizing the alert information based on the analysis result of the emotion recognition means. This makes it possible to monitor the health status of the pet in real time and provide an appropriate alert message that takes into consideration the user's emotions.

[0733] The "sensor means" is a device for collecting daily data about pets, and includes a camera, a thermometer, and the like as a sensing device.

[0734] The "communication means" refers to the devices and technologies for periodically transmitting collected data to the information processing device, and uses wireless communication methods such as Wi-Fi and Bluetooth.

[0735] "Data processing means" refers to devices and technologies that have the function of storing data received by an information processing device in a data storage device and performing preprocessing, such as noise removal and missing data completion.

[0736] A "generative AI model" is an artificial intelligence model that inputs pre-processed data and evaluates the pet's health status, comparing past and current data to detect abnormal patterns.

[0737] "Analysis means" refers to systems and technologies for inputting pre-processed data into a generative AI model and assessing the health status of a pet based on the results.

[0738] The "notification generating means" is a system having a function for generating alert information when an abnormality is detected by the analyzing means.

[0739] The "notification means" refers to a system and technology for transmitting the generated alert information to the user's terminal, and includes functions such as push notification.

[0740] "Emotion recognition means" refers to systems and techniques for analyzing a user's emotion data and assessing the user's emotional state before generating alert information.

[0741] The "information customization means" refers to a system and technology for customizing alert information to suit the emotional state of the user based on the analysis results of the emotion recognition means.

[0742] The pet health monitoring system according to an embodiment of the present invention is implemented using the following hardware and software: The system consists of three main components: a terminal, a server, and a user.

[0743] Hardware and Software Configuration

[0744] Device: Smart glasses or other wearable devices are used to collect daily data about pets. Specifically, these devices have built-in cameras and temperature sensors, and include a communication module that transmits data to a server via Wi-Fi or Bluetooth.

[0745] Server: An information processing device for data storage and preprocessing, utilizing SQL databases, Python's Pandas library, and deep learning frameworks such as TensorFlow and PyTorch. Generative AI models compare past and present data to detect abnormal patterns.

[0746] User device: A smartphone or tablet used by a user, which is a device for receiving alert messages. It also has the functionality to analyze user emotions using push notifications, cameras, and microphones.

[0747] Program processing

[0748] Data collection

[0749] The device uses the smart glasses' camera and temperature sensor to collect daily data about your pet (video, body temperature, food intake, activity time, etc.) in real time. For example, the smart glasses observe your pet and collect its body temperature data and activity data. At the same time, a digital scale is also used to measure the weight of food.

[0750] Data transmission

[0751] The device periodically processes the collected data in batches and sends them to a server via Wi-Fi. Bluetooth can also be used to transfer data over short distances. For example, the device can process data in batches every hour and send them to a server via Wi-Fi.

[0752] Data accumulation and preprocessing

[0753] The server receives the data sent from the device and stores it in an SQL database. Next, it uses the Python Pandas library to perform preprocessing such as removing noise from the data and filling in missing data. For example, filling in missing values ​​in sensor data and removing noise can improve analysis accuracy.

[0754] Data analysis

[0755] The server inputs the preprocessed data into a generative AI model to analyze the pet's health. Specifically, it uses a deep learning model (such as TensorFlow or PyTorch) to evaluate the pet's health based on the sales data and issues an alert if an abnormal pattern is detected. For example, an abnormality is detected when a pet's body temperature exceeds the normal acceptable range.

[0756] Alert Generation

[0757] If an abnormality is detected by the analysis means, the server generates alert information. When an abnormality is detected, the alert generation module is immediately activated and creates an appropriate alert message corresponding to the pet's condition.

[0758] emotion recognition

[0759] Before generating an alert message, the server uses emotion recognition to analyze the user's emotions. It analyzes the user's facial expressions and tone of voice captured by the camera and microphone to identify the user's emotional state. This is done using technologies such as OpenCV and DeepFace.

[0760] Message customization

[0761] Based on the analysis results of the emotion recognition means, the server customizes the alert message. For example, if the user is feeling stressed, the message will be softer and more friendly, such as "Please stay calm and first move your pet to a cooler place."

[0762] Sending alerts

[0763] The server sends customized alert messages to users' smartphones via push notifications, utilizing the push notification API to provide users with important information instantly.

[0764] Action Execution

[0765] The user can check the received notification and manage the pet's condition according to the alert message, for example, by moving the pet to a cooler place or contacting the appropriate medical institution if necessary.

[0766] Specific examples

[0767] 1. Device: The smart glasses monitor your pet, collecting video and temperature data in real time, and even recording feeding intake by weighing food.

[0768] 2. Terminal: Collected data is periodically sent to the server via Wi-Fi.

[0769] 3. Server: Receives the data and stores it in a database, then performs noise removal and missing data imputation.

[0770] 4. Server: Inputs the pre-processed data into the generative AI model and starts the analysis. If the body temperature data exceeds a certain range, an anomaly is detected.

[0771] 5. Server: Prepare to generate an alert message if an anomaly is detected.

[0772] 6. Server (Emotion Recognition Means): Before generating an alert message, analyze the user's emotions using a camera and microphone. For example, detect whether the user is in a stressed state.

[0773] 7. Server: Customize the content of the alert message based on the user's emotional state. If the user is stressed, use a gentler message such as "Please stay calm and move your pet to a cooler place first."

[0774] 8. Server: Sends customized alert messages to users' smartphones.

[0775] 9. User: The user checks the notification on their smartphone and takes measures to improve their pet's health based on the advice.

[0776] Prompt Sentence Examples

[0777] "Please give me some sample code for a Python program that analyzes pet temperature data and generates an alert message that takes user emotions into consideration if there is an abnormality."

[0778] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0779] Step 1: Data collection

[0780] Device: Smart glasses or other wearable devices use cameras and temperature sensors to collect daily data about your pet in real time (video, body temperature, food intake, activity time, etc.). Specifically, the camera in the smart glasses observes your pet and captures image data every second. At the same time, the temperature sensor measures your pet's temperature every few seconds, and a digital scale measures the weight of its food.

[0781] Input: Sensor data from the operating environment (pet surroundings, pet status).

[0782] Output: Collected raw sensor data (video data, body temperature data, food intake data, etc.).

[0783] Step 2: Send data

[0784] Device: Collected data is periodically batched and sent to a server via Wi-Fi or Bluetooth. Specifically, the device accumulates data collected every minute, batches each data set, and then sends it to the server via Wi-Fi.

[0785] Input: Raw collected sensor data.

[0786] Output: The batch data sent to the server.

[0787] Step 3: Data accumulation and preprocessing

[0788] Server: Receives data sent from the device and stores it in an SQL database. It then uses Python's Pandas library to perform preprocessing, such as removing noise from the data and filling in missing data. Specifically, it imports the received data into the database, fills in missing values ​​using linear interpolation or the average value, and removes noise through filtering.

[0789] Input: Batch data sent from the terminal.

[0790] Output: A preprocessed and clean dataset.

[0791] Step 4: Data analysis

[0792] Server: The preprocessed data is fed into a generative AI model to assess the pet's health. Specifically, a deep learning model (e.g., TensorFlow or PyTorch) is used to perform anomaly detection based on daily activity data and vital signs. For example, anomalies are detected when body temperature exceeds the normal acceptable range.

[0793] Input: The preprocessed dataset.

[0794] Output: Health status assessment result (normal or abnormal).

[0795] Step 5: Alert Generation

[0796] Server: If an abnormality is detected by the analysis means, it generates alert information. Specifically, it immediately launches the alert generation module upon detecting an abnormality and creates an alert message related to the pet's health condition.

[0797] Input: Health assessment result (abnormal).

[0798] Output: The initial alert message.

[0799] Step 6: Emotion Recognition

[0800] Server: Before generating an alert message, the server analyzes the user's emotional data. It acquires camera and microphone data from the user's device and inputs it into an emotion recognition engine. Specifically, it analyzes the user's facial expressions using OpenCV and DeepFace, and evaluates the tone of voice using voice analysis.

[0801] Input: Video and audio data obtained from the user's device.

[0802] Output: Evaluation of the user's emotional state.

[0803] Step 7: Customize your message

[0804] Server: Customize the alert message based on the emotion recognition results. For example, if the user is feeling stressed, change the usual alert message to something more gentle, such as "Please stay calm and move your pet to a cooler place first."

[0805] Input: Initial alert message, evaluation of the user's emotional state.

[0806] Output: The customized alert message.

[0807] Step 8: Sending an alert

[0808] Server: Sends customized alert messages to users' devices via push notifications. Specifically, the server uses the push notification API to instantly notify users on their smartphones or tablets.

[0809] Input: Your customized alert message.

[0810] Output: Push notification to user device.

[0811] Step 9: Take Action

[0812] User: The user checks the notification received on the device and takes care of the pet according to the alert message. For example, the user takes appropriate action to move the pet to a cooler place. If necessary, the user contacts a nearby veterinary clinic for further diagnosis.

[0813] Input: The pushed alert message.

[0814] Output: Specific actions to improve your pet's health.

[0815] (Application example 2)

[0816] 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."

[0817] Many systems exist for monitoring the health of pets in their daily lives, but these systems often send uniform alert messages without considering the user's psychological state. This can cause stress for users, making it difficult to take appropriate action. Furthermore, there are limitations to detecting anomalies based on the analysis of daily data, requiring further data analysis in the work environment. Therefore, there is a need for a system that takes the user's emotional state into account and encourages appropriate and flexible responses.

[0818] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0819] In this invention, the server includes sensor means for collecting daily data about the pet, communication means for periodically transmitting the daily data to the server, preprocessing means for storing the daily data received by the server in a database and preprocessing it, analysis means for inputting the preprocessed data into a generative model and evaluating the health condition of the pet, alert generation means for generating an alert message if an abnormality is detected by the analysis means, emotion recognition means for analyzing the user's facial expressions and voice to recognize their emotional state, message customization means for customizing the content of the alert message based on the emotion recognition means, and notification means for transmitting the customized alert message to the user's terminal. This makes it possible to provide an optimal alert message that takes into account the user's emotional state.

[0820] "Sensor means" refers to a device for collecting daily data about a pet, and includes a camera and a body temperature sensor.

[0821] "Communication means" refers to the technology used to periodically transmit collected daily data to a server, and uses communication protocols such as Wi-Fi and Bluetooth.

[0822] The "preprocessing means" refers to a function that stores the daily data received by the server in a database and performs noise removal and missing data completion.

[0823] The "analysis means" has the function of inputting preprocessed data into a generative model and evaluating the health condition of the pet.

[0824] The "alert generation means" is a mechanism for generating an alert message when an abnormality is detected by the analysis means.

[0825] "Emotion recognition means" is a technology for analyzing a user's facial expressions and voice to recognize their emotional state.

[0826] The "message customization means" is a function for customizing the contents of the alert message based on the emotion recognition means.

[0827] The "notification means" is a technique for sending the customized alert message to the user's terminal.

[0828] A system based on an embodiment of the present invention uses a smart band or smart glasses to collect daily data of factory workers, and if an abnormality is detected, sends an alert message customized based on the worker's emotion to the user's device. Specific embodiments are described below.

[0829] Data collection

[0830] The devices (smart band and smart glasses) collect daily data of factory workers (body temperature, heart rate, work environment data, etc.). The smart band collects data using heart rate and body temperature sensors, while the smart glasses use a built-in camera to capture images of the work environment and the facial expressions of workers.

[0831] As specific hardware examples, the smart band will use "Fitbit" and the smart glasses will use "Google Glass."

[0832] Data transmission

[0833] The collected data is sent from the devices (smart band and smart glasses) to a server via Wi-Fi or Bluetooth. Data is sent periodically, enabling real-time anomaly detection.

[0834] Data accumulation and preprocessing

[0835] The server stores the received data in a database (e.g., MySQL), and then uses Python scripts to perform preprocessing such as denoising the data and imputing missing data.

[0836] Data analysis

[0837] Once preprocessed, the data is input into a generative AI model (e.g., TensorFlow or PyTorch). This model compares past data with current data to detect abnormalities in body temperature and heart rate. Specifically, the analysis method determines that changes in heart rate or body temperature that exceed a certain range are abnormal.

[0838] Alert Generation

[0839] If the server detects an abnormality in the analysis, it generates an alert message using a Python script, which includes specific measures such as "Your temperature is too high. Please drink water and take a break."

[0840] emotion recognition

[0841] Before generating an alert, the server uses data acquired from the camera and microphone built into the smart glasses to analyze the user's emotional state using an emotion recognition engine (e.g., OpenAI), which can recognize stress, impatience, fatigue, etc.

[0842] Message customization

[0843] Based on the analyzed emotional state, the server uses a message customization method to adjust the content of the alert message. For example, if the user is feeling stressed, the server softens the message and changes it to something like, "Relax. First, take a deep breath and calm down."

[0844] Sending alerts

[0845] The server sends a customized alert message to the user's device (smartphone or tablet) via push notification, allowing workers to check the notification and take appropriate action promptly.

[0846] Specific examples

[0847] Here are some examples of specific prompts:

[0848] Create a program that monitors the health data of factory workers in real time and generates customized alert messages based on emotion recognition when an abnormality is detected. Use a smart band and smart glasses to collect data, and generate alerts based on heart rate and body temperature data when an abnormality occurs, using a tone that matches the user's emotion.

[0849] In this way, it is possible to provide optimal alert messages that take into account the user's emotional state.This system allows factory workers to manage their health efficiently and without stress.

[0850] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0851] Step 1:

[0852] The devices (smart bands and smart glasses) collect daily data of factory workers (body temperature, heart rate, work environment data, etc.) in real time.

[0853] Specifically, the smart band's body temperature and heart rate sensors collect data at regular intervals, while the smart glasses' built-in camera captures the worker's work status and facial expressions.

[0854] Inputs include body temperature, heart rate, and video data.

[0855] As output, collected daily data is produced.

[0856] Step 2:

[0857] The collected daily data is periodically sent from the devices (smart band and smart glasses) to a server via Wi-Fi or Bluetooth.

[0858] Specifically, the smart band and smart glasses batch process data at regular intervals and send it to the server using a communication protocol.

[0859] As input, collected daily data.

[0860] The output is the daily data sent to the server.

[0861] Step 3:

[0862] The server stores the received daily data in a database and performs preprocessing (noise removal and missing data completion).

[0863] Specifically, data cleansing is performed using a Python script.

[0864] The raw data sent to the server as input.

[0865] The output is the cleansed pre-processed data.

[0866] Step 4:

[0867] Once preprocessed, the data is processed on the server and input into a generative AI model (using TensorFlow or PyTorch).

[0868] Specifically, the generative AI model compares past normal data with current data and runs an anomaly detection algorithm.

[0869] As input, preprocessed daily data.

[0870] The output is an anomaly detection result.

[0871] Step 5:

[0872] The server generates an alert message if an abnormality is detected.

[0873] Specifically, a Python script is used to create a specific alert message based on the abnormality (for example, "Your body temperature is too high. Please drink water and take a break").

[0874] As input, anomaly detection results.

[0875] As output, an alert message is generated.

[0876] Step 6:

[0877] Before generating an alert message, the server inputs the user's facial expressions and voice into an emotion recognition engine to analyze the user's emotional state.

[0878] Specifically, an emotion recognition engine (using OpenAI) uses data obtained from the smart glasses' camera and microphone to analyze the user's psychological state (stress, impatience, fatigue, etc.).

[0879] As input, facial expression data and voice data.

[0880] The output is the user's emotional state.

[0881] Step 7:

[0882] The server customizes the alert message based on the emotion recognition results.

[0883] Specifically, the message customization means adjusts the content of the alert message to match the user's emotional state (for example, if the user is feeling stressed, it will say, "Relax. First, take a deep breath and stay calm").

[0884] As input, the emotional state and the generated alert message.

[0885] As output, you get a customized alert message.

[0886] Step 8:

[0887] The server sends a customized alert message to the user's device (smartphone or tablet) via push notification.

[0888] Specifically, the notification method within the server sends a message using a push notification service (such as Firebase Cloud Messaging).

[0889] As input, a customized alert message.

[0890] The output is an alert message displayed on the user's terminal.

[0891] 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.

[0892] 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.

[0893] 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.

[0894] [Third embodiment]

[0895] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0896] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0897] 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).

[0898] 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.

[0899] 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.

[0900] 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).

[0901] 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.

[0902] 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.

[0903] 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.

[0904] 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.

[0905] 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.

[0906] 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."

[0907] As an embodiment of the present invention, a system will be described that monitors the health condition of a pet in real time and sends an alert to the owner if an abnormality is detected. This system is mainly composed of a terminal, a server, and a user.

[0908] Overview of program processing

[0909] Data collection:

[0910] Device: Cameras and temperature sensors installed in smart glasses and other wearable devices collect daily data about your pet (video, body temperature, amount of food eaten, activity time, etc.).

[0911] Data transmission:

[0912] On the device: Collected data is periodically batched and sent to a server via Wi-Fi or Bluetooth.

[0913] Data accumulation and preprocessing:

[0914] Server: Receives data sent from the device and stores it in a database. Then, it performs preprocessing such as noise removal and missing data completion.

[0915] Data Analysis:

[0916] Server: The preprocessed data is input into a generative model (artificial intelligence model or analytical algorithm) to assess the pet's health condition.

[0917] Anomaly detection:

[0918] Server: Compares the analysis results with past data to detect abnormal patterns. For example, if the body temperature continues to rise from 38.5°C to 39.2°C, it is determined to be abnormal.

[0919] Alert generation:

[0920] Server: If an abnormality is detected, generate an alert message with appropriate advice. For example, generate an alert saying "Temperature is high. Increase fluid intake and move to a cooler place."

[0921] Alert sending:

[0922] Server: The generated alert message is sent to the user's device (smartphone or tablet) via push notification.

[0923] Take Action:

[0924] User: The user receives a notification on a device such as a smartphone, checks the alert message, and then takes appropriate action for their pet based on the content of the notification.

[0925] Specific examples

[0926] 1. Device: The smart glasses capture video of your pet, measure its temperature with a thermometer, and record its feeding by weighing its food.

[0927] 2. Terminal: Based on the registered schedule, the collected data is sent to the server via Wi-Fi.

[0928] 3. Server: Receives the data, stores it in a database, and then performs preprocessing such as noise removal and missing data imputation.

[0929] 4. Server: The preprocessed data is input into the generative model and analysis begins. For example, if the body temperature data exceeds a certain range, it is recognized as an abnormal pattern.

[0930] 5. Server: If an abnormality is detected, generate an alert message. For example, generate an alert saying "Your pet has a high temperature and needs to be cooled."

[0931] 6. Server: Sends an alert message to the user's smartphone.

[0932] 7. User: Check the notification on your smartphone and take measures such as moving your pet to a cooler place and giving them water.

[0933] The above is the overall flow and specific processing contents of the system according to the embodiment of the present invention. The system of the present invention enables pet owners to grasp the health condition of their pets in real time and to promptly take appropriate measures.

[0934] The processing flow will be explained below.

[0935] Step 1:

[0936] Device: The smart glasses' camera captures images of your pet in real time, the temperature sensor measures your pet's temperature, and the weight sensor measures the amount of food your pet eats. The collected data is temporarily stored in the device's memory.

[0937] Step 2:

[0938] Terminal: Collected data is batch processed at regular intervals and compiled. The batched data is sent to the server via Wi-Fi or Bluetooth.

[0939] Step 3:

[0940] Server: Receives data sent from the device and stores it in a database. The database contains information such as date and time, type of data (body temperature, activity level, meal amount, etc.), and sensor information.

[0941] Step 4:

[0942] Server: Performs data preprocessing. Specifically, it applies a noise reduction algorithm to remove outliers and fills in missing data. For example, if a body temperature sensor temporarily loses data, it fills in the missing data using data from before and after.

[0943] Step 5:

[0944] Server: The preprocessed data is input into a generative model (an artificial intelligence model or analytical algorithm). The generative model analyzes the data and evaluates the pet's health condition.

[0945] Step 6:

[0946] Server: Detects abnormal patterns by comparing the analysis results with past health data. For example, if the current temperature is abnormally high compared with the temperature data from the past week, this is detected.

[0947] Step 7:

[0948] Server: If an abnormality is detected, the alert generation means generates an alert message. The message includes specific advice. For example, it could say, "Your pet's temperature is high and needs to be cooled."

[0949] Step 8:

[0950] Server: Sends the generated alert message to the user's device via push notification.

[0951] Step 9:

[0952] User: Receives an alert message on their smartphone or tablet. The message describes the pet's health status and specific measures to take. The user checks the message and takes the necessary measures.

[0953] The above are the processing steps in the system of the present invention, which allows for seamless processing from data collection to anomaly detection and notification to the user.

[0954] Example 1

[0955] 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."

[0956] Conventional pet health management systems lack the functionality to monitor minute-by-minute changes in body temperature and activity in real time, which means it takes a long time for abnormalities to be detected. Furthermore, there are insufficient methods for quickly communicating information to owners when an abnormality is detected, which can delay appropriate measures. This increases the risk of a pet's health deteriorating.

[0957] 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.

[0958] In this invention, the server includes a sensor means for collecting daily data of the pet, a communication means for periodically transmitting the daily data to the server, a preprocessing means for storing the daily data received by the server in a database and preprocessing the data, an analysis means for inputting the preprocessed data into an artificial intelligence model and evaluating the health condition of the pet, an alert generation means for generating an alert message including appropriate advice if the analysis means detects an abnormality, and a notification means for transmitting the alert message to a user's terminal. This makes it possible to monitor the health condition of the pet in real time, and to promptly notify the owner if an abnormality is detected so that appropriate measures can be taken.

[0959] The "sensor means" is a device for collecting daily data such as the pet's body temperature, activity status, and amount of food eaten.

[0960] "Communication means" refers to a network communication technology for periodically transmitting collected data to a server.

[0961] The "preprocessing means" is a technology that stores the daily data received by the server in a database and performs preprocessing such as noise removal and missing data completion.

[0962] The "analysis means" refers to a technology that inputs pre-processed data into an artificial intelligence model to assess the health status of a pet.

[0963] The "alert generation means" is a technique for generating an alert message containing appropriate advice when an abnormality is detected by the analysis means.

[0964] The "notification means" is a technique for sending the alert message to the user's terminal.

[0965] An "artificial intelligence model" is a machine learning algorithm used in data analysis to assess the health status of pets.

[0966] A "database" is an electronic information management system for organizing and storing collected routine data.

[0967] This invention relates to a system that monitors the health status of pets in real time and sends an alert to the owner if an abnormality is detected. This system is mainly composed of a terminal, a server, and a user.

[0968] Hardware and software used

[0969] Devices: Smart glasses and other wearable devices include the following hardware:

[0970] Camera: Capture footage of your pet.

[0971] Body temperature sensor: Measure your pet's body temperature.

[0972] Communication module: Sends data to the server using Wi-Fi or Bluetooth.

[0973] Server: The server includes the following software and hardware:

[0974] Database: Organizes and stores collected routine data.

[0975] Preprocessing software: Remove noise and fill in missing data.

[0976] Generative AI model: Analyzes pre-processed data and assesses the pet's health.

[0977] Alert generation software: Generates an alert message when an anomaly is detected.

[0978] Notification system: Pushes alert messages to user devices.

[0979] Data collection and transmission

[0980] Device: Smart glasses or other wearable devices collect your pet's daily data (video, body temperature, food intake, activity time, etc.) For example, smart glasses can capture video of your pet's activity at 8 a.m. and measure its temperature with a body temperature sensor.

[0981] Device: The collected data is periodically batched and sent to the server via Wi-Fi or Bluetooth. For example, at 9:00 a.m., the device can send the video and temperature data from the previous hour to the server via Wi-Fi.

[0982] Data accumulation and preprocessing

[0983] Server: Stores the received data in a database and then performs preprocessing. This includes noise removal and missing data completion. For example, the server can store the received data in a database and remove noise from the video data.

[0984] Data analysis and anomaly detection

[0985] Server: Inputs preprocessed data into a generative AI model to evaluate health status. For example, preprocessed body temperature data can be input into a generative AI model to analyze a pet's health status in real time. The analysis results can also be compared with past data to detect abnormal patterns. For example, the server can compare the analysis results with past data and detect an abnormality when the body temperature rises to 39.2 degrees.

[0986] Alerting and Notifications

[0987] Server: If an abnormality is detected, an alert message containing appropriate advice for the owner is generated and sent to the user's device (smartphone or tablet) via push notification. For example, an alert message stating "The pet's temperature is high and cooling is required" can be generated and sent to the user's smartphone.

[0988] Action Execution

[0989] User: The user receives a notification on their smartphone and checks the alert message. They can then take prompt action, such as moving their pet to a cooler place and providing water. For example, the user can check the notification on their smartphone and take prompt action, such as moving their pet to a cooler place and providing water.

[0990] Specific examples

[0991] 1. Device: The smart glasses capture video of your pet at 8 a.m., measure its temperature with a thermometer, and record how much it has eaten.

[0992] 2. Device: Based on the registered schedule, the collected data is sent to the server via Wi-Fi every hour.

[0993] 3. Server: Stores the received data in a database and performs preprocessing such as noise removal and missing data completion.

[0994] 4. Server: The preprocessed data is input into the generative AI model and analysis begins. For example, if the body temperature data exceeds a certain range, it is recognized as an abnormal pattern.

[0995] 5. Server: If an abnormality is detected, generate an alert message. Generate an alert saying "Your pet has a high temperature and needs to be cooled."

[0996] 6. Server: Sends an alert message to the user's smartphone.

[0997] 7. User: Check the notification on your smartphone and take measures such as moving your pet to a cooler place and giving them water.

[0998] As described above, the pet health monitoring system according to the present invention allows owners to grasp the health condition of their pets in real time and take prompt action.

[0999] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1000] Step 1: Data collection

[1001] Devices: Smart glasses and other wearable devices collect daily data about your pet.

[1002] Input: Pet activity, temperature, food intake, activity time, etc.

[1003] How it works: The camera in the smart glasses periodically captures images of your pet, the temperature sensor captures temperature data every minute and logs it, and the weight of food is measured to collect data on how much food your pet eats.

[1004] Output: Collected daily data (video data, body temperature data, food intake data, activity data).

[1005] Step 2: Send data

[1006] Terminal: Collected data is periodically batch processed and sent over the network to the server.

[1007] Input: Collected routine data.

[1008] How it works: The smart glasses batch process all collected data every hour and upload it to a server via Wi-Fi or Bluetooth.

[1009] Output: The batched data sent to the server.

[1010] Step 3: Data accumulation and preprocessing

[1011] Server: Stores the received data in a database and then performs preprocessing.

[1012] Input: Batch data sent from the terminal.

[1013] Specific operation: The server stores the received data in an orderly database, applies a noise reduction algorithm to eliminate unnecessary information, and fills in missing data from past data.

[1014] Output: Preprocessed data (denoised data, imputed data).

[1015] Step 4: Data analysis

[1016] Server: Inputs preprocessed data into a generative AI model to assess health status.

[1017] Input: Preprocessed data.

[1018] Specific operation: The server provides preprocessed data to the generative model, which then analyzes the data and calculates health indicators.

[1019] Output: Analysis results (health assessment data).

[1020] Step 5: Anomaly detection

[1021] Server: Compares the analysis results with historical data to detect abnormal patterns.

[1022] Input: Analysis results, historical baseline data.

[1023] How it works: The output of the generative AI model is compared with historical baseline data to identify abnormal patterns, such as when body temperature exceeds the normal range.

[1024] Output: Anomaly detection results.

[1025] Step 6: Alert Generation

[1026] Server: If an anomaly is detected, generate an alert message with appropriate advice.

[1027] Input: Anomaly detection results.

[1028] Specific actions: The server will create appropriate advice based on the type of abnormality and generate a specific alert message such as "Your body temperature is high. Increase your fluid intake and move to a cooler place."

[1029] Output: The generated alert message.

[1030] Step 7: Sending an alert

[1031] Server: Sends the generated alert message to the user's device (smartphone or tablet).

[1032] Input: The generated alert message.

[1033] Specific operation: The server sends the generated alert message to the user's smartphone as a push notification, and the notification is received in real time via the network.

[1034] Output: The alert message sent to the user's terminal.

[1035] Step 8: Take Action

[1036] User: Take appropriate action based on the alert message received.

[1037] Input: The alert message received on the user's smartphone.

[1038] Specific actions: The user checks the alert message on their smartphone and takes measures such as moving the pet to a cooler place and giving it water.

[1039] Output: Implementing specific measures for pets.

[1040] Through the above processing steps, this system monitors the health condition of pets in real time, notifies the user promptly if an abnormality is detected, and enables the user to take appropriate measures.

[1041] (Application example 1)

[1042] 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."

[1043] In the conventional food delivery industry, there were few means to monitor in real time whether food was being maintained at the appropriate temperature during delivery, which led to a risk of a decline in food quality and safety. It was also difficult to respond immediately to abnormal temperature changes. Thus, the lack of real-time monitoring and immediate response in temperature management of food during delivery is a serious issue.

[1044] 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.

[1045] In this invention, the server includes a sensor means for collecting daily data of the pet, a communication means for periodically transmitting the daily data to the server, a preprocessing means for storing the daily data received by the server in a database and preprocessing it, an analysis means for inputting the preprocessed data into a generative model and evaluating the health condition of the pet, an alert generation means for generating an alert message if an abnormality is detected by the analysis means, a notification means for transmitting the alert message to a user's terminal, and a temperature monitoring means for collecting food temperature data in real time and analyzing abnormal temperatures. This enables real-time monitoring and immediate response in food temperature management in the food delivery industry.

[1046] "Sensor means" is a general term for an apparatus or device used to collect data from an object, and examples include cameras and temperature sensors.

[1047] "Communication means" is a general term for methods and technologies for periodically sending collected data to a server, including Wi-Fi and Bluetooth.

[1048] The "preprocessing means" is a device or system that has the function of storing data sent to the server and performing basic data processing such as noise removal and missing data completion.

[1049] An "analysis means" is a device or system that has the ability to use preprocessed data to input into a generative model or artificial intelligence algorithm to evaluate the state of an object.

[1050] The "alert generation means" is a device or system that has the function of generating a warning message or instructions based on the information when an abnormality is detected by the analysis means.

[1051] "Notification means" is a general term for methods and techniques for sending the generated alert message to the user's terminal and promptly notifying the user of its contents.

[1052] A "temperature monitoring means" is a device or system that has the function of collecting the temperature of an object in real time and analyzing whether it is within the appropriate temperature range.

[1053] The present invention relates to a system for monitoring the temperature of food being delivered in real time and sending an alert message if an abnormal temperature is detected. Specific embodiments for carrying out the present invention will be described below.

[1054] Hardware and Software Used

[1055] Hardware:

[1056] Smart glasses: The general term is smart glasses.

[1057] Delivery robot: The general term is delivery robot.

[1058] Temperature sensor: The general term is digital temperature sensor.

[1059] software:

[1060] Data transmission: Using Bluetooth Low Energy (BLE) or Wi-Fi Direct.

[1061] Data storage: Use Amazon Relational Database Service (RDS) as a cloud database.

[1062] Data preprocessing and analysis: Using Python's Pandas and Scikit-learn libraries.

[1063] Notification method: Uses Firebase Cloud Messaging (FCM).

[1064] System Configuration and Operation

[1065] Device behavior

[1066] Digital temperature sensors mounted on smart glasses and delivery robots collect real-time temperature data on food during delivery.

[1067] The collected temperature data is periodically transmitted to a server using Bluetooth Low Energy (BLE) or Wi-Fi Direct.

[1068] Server Operation

[1069] The server receives the transmitted temperature data and stores it in a database using Amazon RDS.

[1070] The stored temperature data is preprocessed using the Pandas library, including noise removal and missing data completion.

[1071] The preprocessed data is analyzed using the Scikit-learn library to assess whether the food temperature is within normal range.

[1072] If an abnormal temperature is detected as a result of the analysis, the server uses an alert generation means to generate an alert message such as "The food temperature is outside the appropriate range. Please check the cooling."

[1073] The generated alert message is sent to the user's (delivery worker's) smartphone using Firebase Cloud Messaging (FCM).

[1074] User Actions

[1075] Users will receive an alert message via push notification on their smartphone.

[1076] After checking the notification, the user follows the instructions to properly manage the temperature of the food.

[1077] Specific examples

[1078] 1. Terminal: During delivery, the temperature sensor in the smart glasses measures the food temperature as 48°C.

[1079] 2. Data transmission: Temperature data is transmitted to a server via Wi-Fi at relay points along the delivery route.

[1080] 3. Server operation: The server receives the data, stores it in a database, and then performs missing data imputation using the Python Pandas library.

[1081] 4. Data analysis: A model trained with Scikit-learn analyzes the temperature data and determines that 48°C is abnormal.

[1082] 5. Alert Generation: Generate an alert message saying "Food temperature is out of the appropriate range. Check cooling."

[1083] 6. Send alerts: Use Firebase Cloud Messaging to push alerts to the delivery person's smartphone.

[1084] 7. User Action: The delivery person receives a notification, checks that the food is cooled, and takes prompt action.

[1085] Prompt Sentence Examples

[1086] "Monitor whether food temperatures are within the appropriate range (e.g., below 60°C). Temperature data of 48°C is sent in real time. Use this data to detect abnormalities and generate appropriate alert messages."

[1087] The above is a specific embodiment for carrying out the present invention.

[1088] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1089] Step 1:

[1090] The device (smart glasses or delivery robot) collects food temperature data. The temperature sensor measures the temperature in real time and records it as temperature data. The input is the temperature value obtained from the temperature sensor, and the output is temperature data.

[1091] Step 2:

[1092] The temperature data collected by the device is periodically sent to the server using Bluetooth Low Energy (BLE) or Wi-Fi Direct. The input is the temperature data, and the output is the temperature data sent to the server.

[1093] Step 3:

[1094] The server stores the received temperature data in a database. The database used is Amazon Relational Database Service (RDS), which stores the received data. The input is the transmitted temperature data, and the output is the temperature data stored in the database.

[1095] Step 4:

[1096] The server preprocesses the stored temperature data. Specifically, it uses the Python Pandas library to remove noise and fill in missing data. The input is the temperature data read from the database, and the output is the preprocessed temperature data.

[1097] Step 5:

[1098] The server performs analysis based on the preprocessed temperature data. The preprocessed data is used as input for a generative AI model (using the Scikit-learn library) to detect abnormal temperatures. The input is the preprocessed temperature data, and the output is the analysis results.

[1099] Step 6:

[1100] If the server detects an anomaly based on the analysis results, it generates an alert message. Specifically, it uses Firebase Cloud Messaging (FCM) to create a message in the specified format. The input is the analysis results, and the output is the generated alert message.

[1101] Step 7:

[1102] The server sends an alert message to the user's (delivery worker's) device. The generated alert message is sent as a push notification using Firebase Cloud Messaging (FCM). The input is the generated alert message, and the output is a notification sent to the user's device.

[1103] Step 8:

[1104] The user receives a push notification and takes appropriate action based on the content of the notification. For example, the user might check the notification message and recheck the temperature of the food. The input is the alert message, and the output is the user's action.

[1105] 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.

[1106] A pet health monitoring system according to an embodiment of the present invention not only collects daily data of pets and sends alerts when abnormalities are detected, but also recognizes the user's emotions and customizes the content of the alert message based on the emotions. This system consists of three main components: a terminal, a server, and a user.

[1107] Overview of program processing

[1108] Data collection:

[1109] Device: Smart glasses or another wearable device uses a camera and temperature sensor to collect daily data about your pet (video, temperature, amount of food eaten, activity time, etc.).

[1110] Data transmission:

[1111] Device: Collected data is periodically batched and sent to a server via Wi-Fi or Bluetooth.

[1112] Data accumulation and preprocessing:

[1113] Server: Receives data sent from the device and stores it in a database. It then performs preprocessing such as noise removal and missing data completion.

[1114] Data Analysis:

[1115] Server: The preprocessed data is fed into a generative model to assess the pet's health. The generative model compares the past data with the current data and detects abnormal patterns.

[1116] Alert generation:

[1117] Server: When an anomaly is detected, the alert generation means is activated to generate an alert message, which includes appropriate advice.

[1118] Emotion recognition:

[1119] Server: The emotion engine analyzes the user's emotions before generating an alert message. The emotion engine uses a camera and microphone to analyze emotions from the user's facial expressions and voice.

[1120] Message customization:

[1121] Server: Customize the alert message content based on the user's emotional data. For example, if the user is feeling stressed, soften the message content.

[1122] Alert sending:

[1123] Server: Sends a customized alert message to the user's device via push notification.

[1124] Take Action:

[1125] User: The user receives a notification on their device (smartphone or tablet) and checks the alert message. A message that takes into consideration the user's feelings is displayed, and the user can manage their pet's health based on that message.

[1126] Specific examples

[1127] 1. Device: The smart glasses monitor your pet, collecting video and temperature data in real time, and even recording feeding intake by weighing food.

[1128] 2. Terminal: Collected data is periodically sent to the server via Wi-Fi.

[1129] 3. Server: Receives the data and stores it in a database. Then, it performs noise removal and missing data imputation.

[1130] 4. Server: Input the preprocessed data into the generative model and start the analysis. Detect anomalies when the body temperature data exceeds a certain range.

[1131] 5. Server: Prepare to generate an alert message if an anomaly is detected.

[1132] 6. Server (Emotion Engine): Analyzes the user's emotions using a camera and microphone before generating an alert message, e.g., detects whether the user is in a stressed state.

[1133] 7. Server: Customize the content of the alert message based on the user's emotional state. If the user is stressed, use a gentler message such as "Please stay calm and move your pet to a cooler place first."

[1134] 8. Server: Sends customized alert messages to users' smartphones.

[1135] 9. User: The user checks the notification on their smartphone and takes measures to improve their pet's health based on the advice.

[1136] In this way, the system of the present invention not only monitors the health status of pets in real time, but also takes into account the user's emotions and provides optimal alert messages, making pet health management more effective and user-friendly.

[1137] The processing flow will be explained below.

[1138] Step 1:

[1139] Device: The smart glasses' camera captures images of your pet in real time, the temperature sensor measures your pet's temperature, and the weight sensor measures food loss and records the amount of food your pet eats. The collected data is temporarily stored.

[1140] Step 2:

[1141] Terminal: Batch processing is performed at regular intervals (e.g., every 5 minutes) to consolidate the collected data, which is then sent to the server via Wi-Fi or Bluetooth.

[1142] Step 3:

[1143] Server: Receives data sent from the device and stores it in a database, which records the date, time, and type of data (e.g., body temperature, activity level).

[1144] Step 4:

[1145] Server: Data pre-processing measures are run to improve the quality of the data, specifically removing noise, filling in missing data, and correcting outliers.

[1146] Step 5:

[1147] Server: Inputs the preprocessed data into a generative model (e.g., a machine learning algorithm), which analyzes the data to assess the pet's health.

[1148] Step 6:

[1149] Server: Detects abnormal patterns by comparing the analysis results with past data. For example, if a normal body temperature is 38.5°C, but the recent temperature is over 39°C, it is considered abnormal.

[1150] Step 7:

[1151] Server: If an abnormality is detected, it generates an alert message and provides specific advice, such as "Your body temperature is high and you need to cool down."

[1152] Step 8:

[1153] Server (emotion engine): When generating an alert, the server uses a camera and microphone to recognize the user's emotions. For example, it determines whether the user is under stress based on their facial expressions and voice.

[1154] Step 9:

[1155] Server: Customize the tone and content of the alert message based on the user's emotional data. For example, for a stressed user, use a gentler message such as "Please stay calm."

[1156] Step 10:

[1157] Server: Sends customized alert messages to users' smartphones via push notifications.

[1158] Step 11:

[1159] User: Receives a notification on their smartphone, checks the alert message, and takes appropriate action to manage their pet's health (e.g., move the pet to a cooler place, provide water, etc.).

[1160] In this way, each step works seamlessly together to create a system that monitors a pet's health in real time and provides appropriate alert messages that take the user's emotions into consideration.

[1161] Example 2

[1162] 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."

[1163] In today's world, pet health management is an important issue, but conventional systems often have a slow response time to detect abnormalities in pets. Furthermore, alert messages may not be effectively received if the user is under high stress. Therefore, it is necessary to monitor pet health in real time and provide alert messages that take the user's emotions into consideration.

[1164] The identification processing by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes: sensor means for collecting vital data of the pet; communication means for periodically transmitting the vital data to the information processing device; data processing means for storing the vital data received by the information processing device in a data storage device and performing preprocessing; analysis means for inputting the preprocessed data into a generative AI model and evaluating the health status of the pet; notification generation means for generating alert information when an abnormality is detected by the analysis means; notification means for transmitting the alert information to the user's terminal; emotion recognition means for analyzing user emotion data before the notification generation means generates the alert information; and information customization means for customizing the alert information based on the analysis result of the emotion recognition means. This makes it possible to monitor the health status of the pet in real time and provide an appropriate alert message that takes into consideration the user's emotions.

[1165] The "sensor means" is a device for collecting daily data about pets, and includes a camera, a thermometer, and the like as a sensing device.

[1166] The "communication means" refers to the devices and technologies for periodically transmitting collected data to the information processing device, and uses wireless communication methods such as Wi-Fi and Bluetooth.

[1167] "Data processing means" refers to devices and technologies that have the function of storing data received by an information processing device in a data storage device and performing preprocessing, such as noise removal and missing data completion.

[1168] A "generative AI model" is an artificial intelligence model that inputs pre-processed data and evaluates the pet's health status, comparing past and current data to detect abnormal patterns.

[1169] "Analysis means" refers to systems and technologies for inputting pre-processed data into a generative AI model and assessing the health status of a pet based on the results.

[1170] The "notification generating means" is a system having a function for generating alert information when an abnormality is detected by the analyzing means.

[1171] The "notification means" refers to a system and technology for transmitting the generated alert information to the user's terminal, and includes functions such as push notification.

[1172] "Emotion recognition means" refers to systems and techniques for analyzing a user's emotion data and assessing the user's emotional state before generating alert information.

[1173] The "information customization means" refers to a system and technology for customizing alert information to suit the emotional state of the user based on the analysis results of the emotion recognition means.

[1174] The pet health monitoring system according to an embodiment of the present invention is implemented using the following hardware and software: The system consists of three main components: a terminal, a server, and a user.

[1175] Hardware and Software Configuration

[1176] Device: Smart glasses or other wearable devices are used to collect daily data about pets. Specifically, these devices have built-in cameras and temperature sensors, and include a communication module that transmits data to a server via Wi-Fi or Bluetooth.

[1177] Server: An information processing device for data storage and preprocessing, utilizing SQL databases, Python's Pandas library, and deep learning frameworks such as TensorFlow and PyTorch. Generative AI models compare past and present data to detect abnormal patterns.

[1178] User device: A smartphone or tablet used by a user, which is a device for receiving alert messages. It also has the functionality to analyze user emotions using push notifications, cameras, and microphones.

[1179] Program processing

[1180] Data collection

[1181] The device uses the smart glasses' camera and temperature sensor to collect daily data about your pet (video, body temperature, food intake, activity time, etc.) in real time. For example, the smart glasses observe your pet and collect its body temperature data and activity data. At the same time, a digital scale is also used to measure the weight of food.

[1182] Data transmission

[1183] The device periodically processes the collected data in batches and sends them to a server via Wi-Fi. Bluetooth can also be used to transfer data over short distances. For example, the device can process data in batches every hour and send them to a server via Wi-Fi.

[1184] Data accumulation and preprocessing

[1185] The server receives the data sent from the device and stores it in an SQL database. Next, it uses the Python Pandas library to perform preprocessing such as removing noise from the data and filling in missing data. For example, filling in missing values ​​in sensor data and removing noise can improve analysis accuracy.

[1186] Data analysis

[1187] The server inputs the preprocessed data into a generative AI model to analyze the pet's health. Specifically, it uses a deep learning model (such as TensorFlow or PyTorch) to evaluate the pet's health based on the sales data and issues an alert if an abnormal pattern is detected. For example, an abnormality is detected when a pet's body temperature exceeds the normal acceptable range.

[1188] Alert Generation

[1189] If an abnormality is detected by the analysis means, the server generates alert information. When an abnormality is detected, the alert generation module is immediately activated and creates an appropriate alert message corresponding to the pet's condition.

[1190] emotion recognition

[1191] Before generating an alert message, the server uses emotion recognition to analyze the user's emotions. It analyzes the user's facial expressions and tone of voice captured by the camera and microphone to identify the user's emotional state. This is done using technologies such as OpenCV and DeepFace.

[1192] Message customization

[1193] Based on the analysis results of the emotion recognition means, the server customizes the alert message. For example, if the user is feeling stressed, the message will be softer and more friendly, such as "Please stay calm and first move your pet to a cooler place."

[1194] Sending alerts

[1195] The server sends customized alert messages to users' smartphones via push notifications, utilizing the push notification API to provide users with important information instantly.

[1196] Action Execution

[1197] The user can check the received notification and manage the pet's condition according to the alert message, for example, by moving the pet to a cooler place or contacting the appropriate medical institution if necessary.

[1198] Specific examples

[1199] 1. Device: The smart glasses monitor your pet, collecting video and temperature data in real time, and even recording feeding intake by weighing food.

[1200] 2. Terminal: Collected data is periodically sent to the server via Wi-Fi.

[1201] 3. Server: Receives the data and stores it in a database, then performs noise removal and missing data imputation.

[1202] 4. Server: Inputs the pre-processed data into the generative AI model and starts the analysis. If the body temperature data exceeds a certain range, an anomaly is detected.

[1203] 5. Server: Prepare to generate an alert message if an anomaly is detected.

[1204] 6. Server (Emotion Recognition Means): Before generating an alert message, analyze the user's emotions using a camera and microphone. For example, detect whether the user is in a stressed state.

[1205] 7. Server: Customize the content of the alert message based on the user's emotional state. If the user is stressed, use a gentler message such as "Please stay calm and move your pet to a cooler place first."

[1206] 8. Server: Sends customized alert messages to users' smartphones.

[1207] 9. User: The user checks the notification on their smartphone and takes measures to improve their pet's health based on the advice.

[1208] Prompt Sentence Examples

[1209] "Please give me some sample code for a Python program that analyzes pet temperature data and generates an alert message that takes user emotions into consideration if there is an abnormality."

[1210] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1211] Step 1: Data collection

[1212] Device: Smart glasses or other wearable devices use cameras and temperature sensors to collect daily data about your pet in real time (video, body temperature, food intake, activity time, etc.). Specifically, the camera in the smart glasses observes your pet and captures image data every second. At the same time, the temperature sensor measures your pet's temperature every few seconds, and a digital scale measures the weight of its food.

[1213] Input: Sensor data from the operating environment (pet surroundings, pet status).

[1214] Output: Collected raw sensor data (video data, body temperature data, food intake data, etc.).

[1215] Step 2: Send data

[1216] Device: Collected data is periodically batched and sent to a server via Wi-Fi or Bluetooth. Specifically, the device accumulates data collected every minute, batches each data set, and then sends it to the server via Wi-Fi.

[1217] Input: Raw collected sensor data.

[1218] Output: The batch data sent to the server.

[1219] Step 3: Data accumulation and preprocessing

[1220] Server: Receives data sent from the device and stores it in an SQL database. It then uses Python's Pandas library to perform preprocessing, such as removing noise from the data and filling in missing data. Specifically, it imports the received data into the database, fills in missing values ​​using linear interpolation or the average value, and removes noise through filtering.

[1221] Input: Batch data sent from the terminal.

[1222] Output: A preprocessed and clean dataset.

[1223] Step 4: Data analysis

[1224] Server: The preprocessed data is fed into a generative AI model to assess the pet's health. Specifically, a deep learning model (e.g., TensorFlow or PyTorch) is used to perform anomaly detection based on daily activity data and vital signs. For example, anomalies are detected when body temperature exceeds the normal acceptable range.

[1225] Input: The preprocessed dataset.

[1226] Output: Health status assessment result (normal or abnormal).

[1227] Step 5: Alert Generation

[1228] Server: If an abnormality is detected by the analysis means, it generates alert information. Specifically, it immediately launches the alert generation module upon detecting an abnormality and creates an alert message related to the pet's health condition.

[1229] Input: Health assessment result (abnormal).

[1230] Output: The initial alert message.

[1231] Step 6: Emotion Recognition

[1232] Server: Before generating an alert message, the server analyzes the user's emotional data. It acquires camera and microphone data from the user's device and inputs it into an emotion recognition engine. Specifically, it analyzes the user's facial expressions using OpenCV and DeepFace, and evaluates the tone of voice using voice analysis.

[1233] Input: Video and audio data obtained from the user's device.

[1234] Output: Evaluation of the user's emotional state.

[1235] Step 7: Customize your message

[1236] Server: Customize the alert message based on the emotion recognition results. For example, if the user is feeling stressed, change the usual alert message to something more gentle, such as "Please stay calm and move your pet to a cooler place first."

[1237] Input: Initial alert message, evaluation of the user's emotional state.

[1238] Output: The customized alert message.

[1239] Step 8: Sending an alert

[1240] Server: Sends customized alert messages to users' devices via push notifications. Specifically, the server uses the push notification API to instantly notify users on their smartphones or tablets.

[1241] Input: Your customized alert message.

[1242] Output: Push notification to user device.

[1243] Step 9: Take Action

[1244] User: The user checks the notification received on the device and takes care of the pet according to the alert message. For example, the user takes appropriate action to move the pet to a cooler place. If necessary, the user contacts a nearby veterinary clinic for further diagnosis.

[1245] Input: The pushed alert message.

[1246] Output: Specific actions to improve your pet's health.

[1247] (Application example 2)

[1248] 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."

[1249] Many systems exist for monitoring the health of pets in their daily lives, but these systems often send uniform alert messages without considering the user's psychological state. This can cause stress for users, making it difficult to take appropriate action. Furthermore, there are limitations to detecting anomalies based on the analysis of daily data, requiring further data analysis in the work environment. Therefore, there is a need for a system that takes the user's emotional state into account and encourages appropriate and flexible responses.

[1250] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1251] In this invention, the server includes sensor means for collecting daily data about the pet, communication means for periodically transmitting the daily data to the server, preprocessing means for storing the daily data received by the server in a database and preprocessing it, analysis means for inputting the preprocessed data into a generative model and evaluating the health condition of the pet, alert generation means for generating an alert message if an abnormality is detected by the analysis means, emotion recognition means for analyzing the user's facial expressions and voice to recognize their emotional state, message customization means for customizing the content of the alert message based on the emotion recognition means, and notification means for transmitting the customized alert message to the user's terminal. This makes it possible to provide an optimal alert message that takes into account the user's emotional state.

[1252] "Sensor means" refers to a device for collecting daily data about a pet, and includes a camera and a body temperature sensor.

[1253] "Communication means" refers to the technology used to periodically transmit collected daily data to a server, and uses communication protocols such as Wi-Fi and Bluetooth.

[1254] The "preprocessing means" refers to a function that stores the daily data received by the server in a database and performs noise removal and missing data completion.

[1255] The "analysis means" has the function of inputting preprocessed data into a generative model and evaluating the health condition of the pet.

[1256] The "alert generation means" is a mechanism for generating an alert message when an abnormality is detected by the analysis means.

[1257] "Emotion recognition means" is a technology for analyzing a user's facial expressions and voice to recognize their emotional state.

[1258] The "message customization means" is a function for customizing the contents of the alert message based on the emotion recognition means.

[1259] The "notification means" is a technique for sending the customized alert message to the user's terminal.

[1260] A system based on an embodiment of the present invention uses a smart band or smart glasses to collect daily data of factory workers, and if an abnormality is detected, sends an alert message customized based on the worker's emotion to the user's device. Specific embodiments are described below.

[1261] Data collection

[1262] The devices (smart band and smart glasses) collect daily data of factory workers (body temperature, heart rate, work environment data, etc.). The smart band collects data using heart rate and body temperature sensors, while the smart glasses use a built-in camera to capture images of the work environment and the facial expressions of workers.

[1263] As specific hardware examples, the smart band will use "Fitbit" and the smart glasses will use "Google Glass."

[1264] Data transmission

[1265] The collected data is sent from the devices (smart band and smart glasses) to a server via Wi-Fi or Bluetooth. Data is sent periodically, enabling real-time anomaly detection.

[1266] Data accumulation and preprocessing

[1267] The server stores the received data in a database (e.g., MySQL), and then uses Python scripts to perform preprocessing such as denoising the data and imputing missing data.

[1268] Data analysis

[1269] Once preprocessed, the data is input into a generative AI model (e.g., TensorFlow or PyTorch). This model compares past data with current data to detect abnormalities in body temperature and heart rate. Specifically, the analysis method determines that changes in heart rate or body temperature that exceed a certain range are abnormal.

[1270] Alert Generation

[1271] If the server detects an abnormality in the analysis, it generates an alert message using a Python script, which includes specific measures such as "Your temperature is too high. Please drink water and take a break."

[1272] emotion recognition

[1273] Before generating an alert, the server uses data acquired from the camera and microphone built into the smart glasses to analyze the user's emotional state using an emotion recognition engine (e.g., OpenAI), which can recognize stress, impatience, fatigue, etc.

[1274] Message customization

[1275] Based on the analyzed emotional state, the server uses a message customization method to adjust the content of the alert message. For example, if the user is feeling stressed, the server softens the message and changes it to something like, "Relax. First, take a deep breath and calm down."

[1276] Sending alerts

[1277] The server sends a customized alert message to the user's device (smartphone or tablet) via push notification, allowing workers to check the notification and take appropriate action promptly.

[1278] Specific examples

[1279] Here are some examples of specific prompts:

[1280] Create a program that monitors the health data of factory workers in real time and generates customized alert messages based on emotion recognition when an abnormality is detected. Use a smart band and smart glasses to collect data, and generate alerts based on heart rate and body temperature data when an abnormality occurs, using a tone that matches the user's emotion.

[1281] In this way, it is possible to provide optimal alert messages that take into account the user's emotional state.This system allows factory workers to manage their health efficiently and without stress.

[1282] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1283] Step 1:

[1284] The devices (smart bands and smart glasses) collect daily data of factory workers (body temperature, heart rate, work environment data, etc.) in real time.

[1285] Specifically, the smart band's body temperature and heart rate sensors collect data at regular intervals, while the smart glasses' built-in camera captures the worker's work status and facial expressions.

[1286] Inputs include body temperature, heart rate, and video data.

[1287] As output, collected daily data is produced.

[1288] Step 2:

[1289] The collected daily data is periodically sent from the devices (smart band and smart glasses) to a server via Wi-Fi or Bluetooth.

[1290] Specifically, the smart band and smart glasses batch process data at regular intervals and send it to the server using a communication protocol.

[1291] As input, collected daily data.

[1292] The output is the daily data sent to the server.

[1293] Step 3:

[1294] The server stores the received daily data in a database and performs preprocessing (noise removal and missing data completion).

[1295] Specifically, data cleansing is performed using a Python script.

[1296] The raw data sent to the server as input.

[1297] The output is the cleansed pre-processed data.

[1298] Step 4:

[1299] Once preprocessed, the data is processed on the server and input into a generative AI model (using TensorFlow or PyTorch).

[1300] Specifically, the generative AI model compares past normal data with current data and runs an anomaly detection algorithm.

[1301] As input, preprocessed daily data.

[1302] The output is an anomaly detection result.

[1303] Step 5:

[1304] The server generates an alert message if an abnormality is detected.

[1305] Specifically, a Python script is used to create a specific alert message based on the abnormality (for example, "Your body temperature is too high. Please drink water and take a break").

[1306] As input, anomaly detection results.

[1307] As output, an alert message is generated.

[1308] Step 6:

[1309] Before generating an alert message, the server inputs the user's facial expressions and voice into an emotion recognition engine to analyze the user's emotional state.

[1310] Specifically, an emotion recognition engine (using OpenAI) uses data obtained from the smart glasses' camera and microphone to analyze the user's psychological state (stress, impatience, fatigue, etc.).

[1311] As input, facial expression data and voice data.

[1312] The output is the user's emotional state.

[1313] Step 7:

[1314] The server customizes the alert message based on the emotion recognition results.

[1315] Specifically, the message customization means adjusts the content of the alert message to match the user's emotional state (for example, if the user is feeling stressed, it will say, "Relax. First, take a deep breath and stay calm").

[1316] As input, the emotional state and the generated alert message.

[1317] As output, you get a customized alert message.

[1318] Step 8:

[1319] The server sends a customized alert message to the user's device (smartphone or tablet) via push notification.

[1320] Specifically, the notification method within the server sends a message using a push notification service (such as Firebase Cloud Messaging).

[1321] As input, a customized alert message.

[1322] The output is an alert message displayed on the user's terminal.

[1323] 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.

[1324] 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.

[1325] 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.

[1326] [Fourth embodiment]

[1327] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1328] 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.

[1329] 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).

[1330] 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.

[1331] 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.

[1332] 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).

[1333] 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.

[1334] 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.

[1335] 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.

[1336] 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.

[1337] 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.

[1338] 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.

[1339] 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."

[1340] As an embodiment of the present invention, a system will be described that monitors the health condition of a pet in real time and sends an alert to the owner if an abnormality is detected. This system is mainly composed of a terminal, a server, and a user.

[1341] Overview of program processing

[1342] Data collection:

[1343] Device: Cameras and temperature sensors installed in smart glasses and other wearable devices collect daily data about your pet (video, body temperature, amount of food eaten, activity time, etc.).

[1344] Data transmission:

[1345] On the device: Collected data is periodically batched and sent to a server via Wi-Fi or Bluetooth.

[1346] Data accumulation and preprocessing:

[1347] Server: Receives data sent from the device and stores it in a database. Then, it performs preprocessing such as noise removal and missing data completion.

[1348] Data Analysis:

[1349] Server: The preprocessed data is input into a generative model (artificial intelligence model or analytical algorithm) to assess the pet's health condition.

[1350] Anomaly detection:

[1351] Server: Compares the analysis results with past data to detect abnormal patterns. For example, if the body temperature continues to rise from 38.5°C to 39.2°C, it is determined to be abnormal.

[1352] Alert generation:

[1353] Server: If an abnormality is detected, generate an alert message with appropriate advice. For example, generate an alert saying "Temperature is high. Increase fluid intake and move to a cooler place."

[1354] Alert sending:

[1355] Server: The generated alert message is sent to the user's device (smartphone or tablet) via push notification.

[1356] Take Action:

[1357] User: The user receives a notification on a device such as a smartphone, checks the alert message, and then takes appropriate action for their pet based on the content of the notification.

[1358] Specific examples

[1359] 1. Device: The smart glasses capture video of your pet, measure its temperature with a thermometer, and record its feeding by weighing its food.

[1360] 2. Terminal: Based on the registered schedule, the collected data is sent to the server via Wi-Fi.

[1361] 3. Server: Receives the data, stores it in a database, and then performs preprocessing such as noise removal and missing data imputation.

[1362] 4. Server: The preprocessed data is input into the generative model and analysis begins. For example, if the body temperature data exceeds a certain range, it is recognized as an abnormal pattern.

[1363] 5. Server: If an abnormality is detected, generate an alert message. For example, generate an alert saying "Your pet has a high temperature and needs to be cooled."

[1364] 6. Server: Sends an alert message to the user's smartphone.

[1365] 7. User: Check the notification on your smartphone and take measures such as moving your pet to a cooler place and giving them water.

[1366] The above is the overall flow and specific processing contents of the system according to the embodiment of the present invention. The system of the present invention enables pet owners to grasp the health condition of their pets in real time and to promptly take appropriate measures.

[1367] The processing flow will be explained below.

[1368] Step 1:

[1369] Device: The smart glasses' camera captures images of your pet in real time, the temperature sensor measures your pet's temperature, and the weight sensor measures the amount of food your pet eats. The collected data is temporarily stored in the device's memory.

[1370] Step 2:

[1371] Terminal: Collected data is batch processed at regular intervals and compiled. The batched data is sent to the server via Wi-Fi or Bluetooth.

[1372] Step 3:

[1373] Server: Receives data sent from the device and stores it in a database. The database contains information such as date and time, type of data (body temperature, activity level, meal amount, etc.), and sensor information.

[1374] Step 4:

[1375] Server: Performs data preprocessing. Specifically, it applies a noise reduction algorithm to remove outliers and fills in missing data. For example, if a body temperature sensor temporarily loses data, it fills in the missing data using data from before and after.

[1376] Step 5:

[1377] Server: The preprocessed data is input into a generative model (an artificial intelligence model or analytical algorithm). The generative model analyzes the data and evaluates the pet's health condition.

[1378] Step 6:

[1379] Server: Detects abnormal patterns by comparing the analysis results with past health data. For example, if the current temperature is abnormally high compared with the temperature data from the past week, this is detected.

[1380] Step 7:

[1381] Server: If an abnormality is detected, the alert generation means generates an alert message. The message includes specific advice. For example, it could say, "Your pet's temperature is high and needs to be cooled."

[1382] Step 8:

[1383] Server: Sends the generated alert message to the user's device via push notification.

[1384] Step 9:

[1385] User: Receives an alert message on their smartphone or tablet. The message describes the pet's health status and specific measures to take. The user checks the message and takes the necessary measures.

[1386] The above are the processing steps in the system of the present invention, which allows for seamless processing from data collection to anomaly detection and notification to the user.

[1387] Example 1

[1388] 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."

[1389] Conventional pet health management systems lack the functionality to monitor minute-by-minute changes in body temperature and activity in real time, which means it takes a long time for abnormalities to be detected. Furthermore, there are insufficient methods for quickly communicating information to owners when an abnormality is detected, which can delay appropriate measures. This increases the risk of a pet's health deteriorating.

[1390] 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.

[1391] In this invention, the server includes a sensor means for collecting daily data of the pet, a communication means for periodically transmitting the daily data to the server, a preprocessing means for storing the daily data received by the server in a database and preprocessing the data, an analysis means for inputting the preprocessed data into an artificial intelligence model and evaluating the health condition of the pet, an alert generation means for generating an alert message including appropriate advice if the analysis means detects an abnormality, and a notification means for transmitting the alert message to a user's terminal. This makes it possible to monitor the health condition of the pet in real time, and to promptly notify the owner if an abnormality is detected so that appropriate measures can be taken.

[1392] The "sensor means" is a device for collecting daily data such as the pet's body temperature, activity status, and amount of food eaten.

[1393] "Communication means" refers to a network communication technology for periodically transmitting collected data to a server.

[1394] The "preprocessing means" is a technology that stores the daily data received by the server in a database and performs preprocessing such as noise removal and missing data completion.

[1395] The "analysis means" refers to a technology that inputs pre-processed data into an artificial intelligence model to assess the health status of a pet.

[1396] The "alert generation means" is a technique for generating an alert message containing appropriate advice when an abnormality is detected by the analysis means.

[1397] The "notification means" is a technique for sending the alert message to the user's terminal.

[1398] An "artificial intelligence model" is a machine learning algorithm used in data analysis to assess the health status of pets.

[1399] A "database" is an electronic information management system for organizing and storing collected routine data.

[1400] This invention relates to a system that monitors the health status of pets in real time and sends an alert to the owner if an abnormality is detected. This system is mainly composed of a terminal, a server, and a user.

[1401] Hardware and software used

[1402] Devices: Smart glasses and other wearable devices include the following hardware:

[1403] Camera: Capture footage of your pet.

[1404] Body temperature sensor: Measure your pet's body temperature.

[1405] Communication module: Sends data to the server using Wi-Fi or Bluetooth.

[1406] Server: The server includes the following software and hardware:

[1407] Database: Organizes and stores collected routine data.

[1408] Preprocessing software: Remove noise and fill in missing data.

[1409] Generative AI model: Analyzes pre-processed data and assesses the pet's health.

[1410] Alert generation software: Generates an alert message when an anomaly is detected.

[1411] Notification system: Pushes alert messages to user devices.

[1412] Data collection and transmission

[1413] Device: Smart glasses or other wearable devices collect your pet's daily data (video, body temperature, food intake, activity time, etc.) For example, smart glasses can capture video of your pet's activity at 8 a.m. and measure its temperature with a body temperature sensor.

[1414] Device: The collected data is periodically batched and sent to the server via Wi-Fi or Bluetooth. For example, at 9:00 a.m., the device can send the video and temperature data from the previous hour to the server via Wi-Fi.

[1415] Data accumulation and preprocessing

[1416] Server: Stores the received data in a database and then performs preprocessing. This includes noise removal and missing data completion. For example, the server can store the received data in a database and remove noise from the video data.

[1417] Data analysis and anomaly detection

[1418] Server: Inputs preprocessed data into a generative AI model to evaluate health status. For example, preprocessed body temperature data can be input into a generative AI model to analyze a pet's health status in real time. The analysis results can also be compared with past data to detect abnormal patterns. For example, the server can compare the analysis results with past data and detect an abnormality when the body temperature rises to 39.2 degrees.

[1419] Alerting and Notifications

[1420] Server: If an abnormality is detected, an alert message containing appropriate advice for the owner is generated and sent to the user's device (smartphone or tablet) via push notification. For example, an alert message stating "The pet's temperature is high and cooling is required" can be generated and sent to the user's smartphone.

[1421] Action Execution

[1422] User: The user receives a notification on their smartphone and checks the alert message. They can then take prompt action, such as moving their pet to a cooler place and providing water. For example, the user can check the notification on their smartphone and take prompt action, such as moving their pet to a cooler place and providing water.

[1423] Specific examples

[1424] 1. Device: The smart glasses capture video of your pet at 8 a.m., measure its temperature with a thermometer, and record how much it has eaten.

[1425] 2. Device: Based on the registered schedule, the collected data is sent to the server via Wi-Fi every hour.

[1426] 3. Server: Stores the received data in a database and performs preprocessing such as noise removal and missing data completion.

[1427] 4. Server: The preprocessed data is input into the generative AI model and analysis begins. For example, if the body temperature data exceeds a certain range, it is recognized as an abnormal pattern.

[1428] 5. Server: If an abnormality is detected, generate an alert message. Generate an alert saying "Your pet has a high temperature and needs to be cooled."

[1429] 6. Server: Sends an alert message to the user's smartphone.

[1430] 7. User: Check the notification on your smartphone and take measures such as moving your pet to a cooler place and giving them water.

[1431] As described above, the pet health monitoring system according to the present invention allows owners to grasp the health condition of their pets in real time and take prompt action.

[1432] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1433] Step 1: Data collection

[1434] Devices: Smart glasses and other wearable devices collect daily data about your pet.

[1435] Input: Pet activity, temperature, food intake, activity time, etc.

[1436] How it works: The camera in the smart glasses periodically captures images of your pet, the temperature sensor captures temperature data every minute and logs it, and the weight of food is measured to collect data on how much food your pet eats.

[1437] Output: Collected daily data (video data, body temperature data, food intake data, activity data).

[1438] Step 2: Send data

[1439] Terminal: Collected data is periodically batch processed and sent over the network to the server.

[1440] Input: Collected routine data.

[1441] How it works: The smart glasses batch process all collected data every hour and upload it to a server via Wi-Fi or Bluetooth.

[1442] Output: The batched data sent to the server.

[1443] Step 3: Data accumulation and preprocessing

[1444] Server: Stores the received data in a database and then performs preprocessing.

[1445] Input: Batch data sent from the terminal.

[1446] Specific operation: The server stores the received data in an orderly database, applies a noise reduction algorithm to eliminate unnecessary information, and fills in missing data from past data.

[1447] Output: Preprocessed data (denoised data, imputed data).

[1448] Step 4: Data analysis

[1449] Server: Inputs preprocessed data into a generative AI model to assess health status.

[1450] Input: Preprocessed data.

[1451] Specific operation: The server provides preprocessed data to the generative model, which then analyzes the data and calculates health indicators.

[1452] Output: Analysis results (health assessment data).

[1453] Step 5: Anomaly detection

[1454] Server: Compares the analysis results with historical data to detect abnormal patterns.

[1455] Input: Analysis results, historical baseline data.

[1456] How it works: The output of the generative AI model is compared with historical baseline data to identify abnormal patterns, such as when body temperature exceeds the normal range.

[1457] Output: Anomaly detection results.

[1458] Step 6: Alert Generation

[1459] Server: If an anomaly is detected, generate an alert message with appropriate advice.

[1460] Input: Anomaly detection results.

[1461] Specific actions: The server will create appropriate advice based on the type of abnormality and generate a specific alert message such as "Your body temperature is high. Increase your fluid intake and move to a cooler place."

[1462] Output: The generated alert message.

[1463] Step 7: Sending an alert

[1464] Server: Sends the generated alert message to the user's device (smartphone or tablet).

[1465] Input: The generated alert message.

[1466] Specific operation: The server sends the generated alert message to the user's smartphone as a push notification, and the notification is received in real time via the network.

[1467] Output: The alert message sent to the user's terminal.

[1468] Step 8: Take Action

[1469] User: Take appropriate action based on the alert message received.

[1470] Input: The alert message received on the user's smartphone.

[1471] Specific actions: The user checks the alert message on their smartphone and takes measures such as moving the pet to a cooler place and giving it water.

[1472] Output: Implementing specific measures for pets.

[1473] Through the above processing steps, this system monitors the health condition of pets in real time, notifies the user promptly if an abnormality is detected, and enables the user to take appropriate measures.

[1474] (Application example 1)

[1475] 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."

[1476] In the conventional food delivery industry, there were few means to monitor in real time whether food was being maintained at the appropriate temperature during delivery, which led to a risk of a decline in food quality and safety. It was also difficult to respond immediately to abnormal temperature changes. Thus, the lack of real-time monitoring and immediate response in temperature management of food during delivery is a serious issue.

[1477] 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.

[1478] In this invention, the server includes a sensor means for collecting daily data of the pet, a communication means for periodically transmitting the daily data to the server, a preprocessing means for storing the daily data received by the server in a database and preprocessing it, an analysis means for inputting the preprocessed data into a generative model and evaluating the health condition of the pet, an alert generation means for generating an alert message if an abnormality is detected by the analysis means, a notification means for transmitting the alert message to a user's terminal, and a temperature monitoring means for collecting food temperature data in real time and analyzing abnormal temperatures. This enables real-time monitoring and immediate response in food temperature management in the food delivery industry.

[1479] "Sensor means" is a general term for an apparatus or device used to collect data from an object, and examples include cameras and temperature sensors.

[1480] "Communication means" is a general term for methods and technologies for periodically sending collected data to a server, including Wi-Fi and Bluetooth.

[1481] The "preprocessing means" is a device or system that has the function of storing data sent to the server and performing basic data processing such as noise removal and missing data completion.

[1482] An "analysis means" is a device or system that has the ability to use preprocessed data to input into a generative model or artificial intelligence algorithm to evaluate the state of an object.

[1483] The "alert generation means" is a device or system that has the function of generating a warning message or instructions based on the information when an abnormality is detected by the analysis means.

[1484] "Notification means" is a general term for methods and techniques for sending the generated alert message to the user's terminal and promptly notifying the user of its contents.

[1485] A "temperature monitoring means" is a device or system that has the function of collecting the temperature of an object in real time and analyzing whether it is within the appropriate temperature range.

[1486] The present invention relates to a system for monitoring the temperature of food being delivered in real time and sending an alert message if an abnormal temperature is detected. Specific embodiments for carrying out the present invention will be described below.

[1487] Hardware and Software Used

[1488] Hardware:

[1489] Smart glasses: The general term is smart glasses.

[1490] Delivery robot: The general term is delivery robot.

[1491] Temperature sensor: The general term is digital temperature sensor.

[1492] software:

[1493] Data transmission: Using Bluetooth Low Energy (BLE) or Wi-Fi Direct.

[1494] Data storage: Use Amazon Relational Database Service (RDS) as a cloud database.

[1495] Data preprocessing and analysis: Using Python's Pandas and Scikit-learn libraries.

[1496] Notification method: Uses Firebase Cloud Messaging (FCM).

[1497] System Configuration and Operation

[1498] Device behavior

[1499] Digital temperature sensors mounted on smart glasses and delivery robots collect real-time temperature data on food during delivery.

[1500] The collected temperature data is periodically transmitted to a server using Bluetooth Low Energy (BLE) or Wi-Fi Direct.

[1501] Server Operation

[1502] The server receives the transmitted temperature data and stores it in a database using Amazon RDS.

[1503] The stored temperature data is preprocessed using the Pandas library, including noise removal and missing data completion.

[1504] The preprocessed data is analyzed using the Scikit-learn library to assess whether the food temperature is within normal range.

[1505] If an abnormal temperature is detected as a result of the analysis, the server uses an alert generation means to generate an alert message such as "The food temperature is outside the appropriate range. Please check the cooling."

[1506] The generated alert message is sent to the user's (delivery worker's) smartphone using Firebase Cloud Messaging (FCM).

[1507] User Actions

[1508] Users will receive an alert message via push notification on their smartphone.

[1509] After checking the notification, the user follows the instructions to properly manage the temperature of the food.

[1510] Specific examples

[1511] 1. Terminal: During delivery, the temperature sensor in the smart glasses measures the food temperature as 48°C.

[1512] 2. Data transmission: Temperature data is transmitted to a server via Wi-Fi at relay points along the delivery route.

[1513] 3. Server operation: The server receives the data, stores it in a database, and then performs missing data imputation using the Python Pandas library.

[1514] 4. Data analysis: A model trained with Scikit-learn analyzes the temperature data and determines that 48°C is abnormal.

[1515] 5. Alert Generation: Generate an alert message saying "Food temperature is out of the appropriate range. Check cooling."

[1516] 6. Send alerts: Use Firebase Cloud Messaging to push alerts to the delivery person's smartphone.

[1517] 7. User Action: The delivery person receives a notification, checks that the food is cooled, and takes prompt action.

[1518] Prompt Sentence Examples

[1519] "Monitor whether food temperatures are within the appropriate range (e.g., below 60°C). Temperature data of 48°C is sent in real time. Use this data to detect abnormalities and generate appropriate alert messages."

[1520] The above is a specific embodiment for carrying out the present invention.

[1521] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1522] Step 1:

[1523] The device (smart glasses or delivery robot) collects food temperature data. The temperature sensor measures the temperature in real time and records it as temperature data. The input is the temperature value obtained from the temperature sensor, and the output is temperature data.

[1524] Step 2:

[1525] The temperature data collected by the device is periodically sent to the server using Bluetooth Low Energy (BLE) or Wi-Fi Direct. The input is the temperature data, and the output is the temperature data sent to the server.

[1526] Step 3:

[1527] The server stores the received temperature data in a database. The database used is Amazon Relational Database Service (RDS), which stores the received data. The input is the transmitted temperature data, and the output is the temperature data stored in the database.

[1528] Step 4:

[1529] The server preprocesses the stored temperature data. Specifically, it uses the Python Pandas library to remove noise and fill in missing data. The input is the temperature data read from the database, and the output is the preprocessed temperature data.

[1530] Step 5:

[1531] The server performs analysis based on the preprocessed temperature data. The preprocessed data is used as input for a generative AI model (using the Scikit-learn library) to detect abnormal temperatures. The input is the preprocessed temperature data, and the output is the analysis results.

[1532] Step 6:

[1533] If the server detects an anomaly based on the analysis results, it generates an alert message. Specifically, it uses Firebase Cloud Messaging (FCM) to create a message in the specified format. The input is the analysis results, and the output is the generated alert message.

[1534] Step 7:

[1535] The server sends an alert message to the user's (delivery worker's) device. The generated alert message is sent as a push notification using Firebase Cloud Messaging (FCM). The input is the generated alert message, and the output is a notification sent to the user's device.

[1536] Step 8:

[1537] The user receives a push notification and takes appropriate action based on the content of the notification. For example, the user might check the notification message and recheck the temperature of the food. The input is the alert message, and the output is the user's action.

[1538] 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.

[1539] A pet health monitoring system according to an embodiment of the present invention not only collects daily data of pets and sends alerts when abnormalities are detected, but also recognizes the user's emotions and customizes the content of the alert message based on the emotions. This system consists of three main components: a terminal, a server, and a user.

[1540] Overview of program processing

[1541] Data collection:

[1542] Device: Smart glasses or another wearable device uses a camera and temperature sensor to collect daily data about your pet (video, temperature, amount of food eaten, activity time, etc.).

[1543] Data transmission:

[1544] Device: Collected data is periodically batched and sent to a server via Wi-Fi or Bluetooth.

[1545] Data accumulation and preprocessing:

[1546] Server: Receives data sent from the device and stores it in a database. It then performs preprocessing such as noise removal and missing data completion.

[1547] Data Analysis:

[1548] Server: The preprocessed data is fed into a generative model to assess the pet's health. The generative model compares the past data with the current data and detects abnormal patterns.

[1549] Alert generation:

[1550] Server: When an anomaly is detected, the alert generation means is activated to generate an alert message, which includes appropriate advice.

[1551] Emotion recognition:

[1552] Server: The emotion engine analyzes the user's emotions before generating an alert message. The emotion engine uses a camera and microphone to analyze emotions from the user's facial expressions and voice.

[1553] Message customization:

[1554] Server: Customize the alert message content based on the user's emotional data. For example, if the user is feeling stressed, soften the message content.

[1555] Alert sending:

[1556] Server: Sends a customized alert message to the user's device via push notification.

[1557] Take Action:

[1558] User: The user receives a notification on their device (smartphone or tablet) and checks the alert message. A message that takes into consideration the user's feelings is displayed, and the user can manage their pet's health based on that message.

[1559] Specific examples

[1560] 1. Device: The smart glasses monitor your pet, collecting video and temperature data in real time, and even recording feeding intake by weighing food.

[1561] 2. Terminal: Collected data is periodically sent to the server via Wi-Fi.

[1562] 3. Server: Receives the data and stores it in a database. Then, it performs noise removal and missing data imputation.

[1563] 4. Server: Input the preprocessed data into the generative model and start the analysis. Detect anomalies when the body temperature data exceeds a certain range.

[1564] 5. Server: Prepare to generate an alert message if an anomaly is detected.

[1565] 6. Server (Emotion Engine): Analyzes the user's emotions using a camera and microphone before generating an alert message, e.g., detects whether the user is in a stressed state.

[1566] 7. Server: Customize the content of the alert message based on the user's emotional state. If the user is stressed, use a gentler message such as "Please stay calm and move your pet to a cooler place first."

[1567] 8. Server: Sends customized alert messages to users' smartphones.

[1568] 9. User: The user checks the notification on their smartphone and takes measures to improve their pet's health based on the advice.

[1569] In this way, the system of the present invention not only monitors the health status of pets in real time, but also takes into account the user's emotions and provides optimal alert messages, making pet health management more effective and user-friendly.

[1570] The processing flow will be explained below.

[1571] Step 1:

[1572] Device: The smart glasses' camera captures images of your pet in real time, the temperature sensor measures your pet's temperature, and the weight sensor measures food loss and records the amount of food your pet eats. The collected data is temporarily stored.

[1573] Step 2:

[1574] Terminal: Batch processing is performed at regular intervals (e.g., every 5 minutes) to consolidate the collected data, which is then sent to the server via Wi-Fi or Bluetooth.

[1575] Step 3:

[1576] Server: Receives data sent from the device and stores it in a database, which records the date, time, and type of data (e.g., body temperature, activity level).

[1577] Step 4:

[1578] Server: Data pre-processing measures are run to improve the quality of the data, specifically removing noise, filling in missing data, and correcting outliers.

[1579] Step 5:

[1580] Server: Inputs the preprocessed data into a generative model (e.g., a machine learning algorithm), which analyzes the data to assess the pet's health.

[1581] Step 6:

[1582] Server: Detects abnormal patterns by comparing the analysis results with past data. For example, if a normal body temperature is 38.5°C, but the recent temperature is over 39°C, it is considered abnormal.

[1583] Step 7:

[1584] Server: If an abnormality is detected, it generates an alert message and provides specific advice, such as "Your body temperature is high and you need to cool down."

[1585] Step 8:

[1586] Server (emotion engine): When generating an alert, the server uses a camera and microphone to recognize the user's emotions. For example, it determines whether the user is under stress based on their facial expressions and voice.

[1587] Step 9:

[1588] Server: Customize the tone and content of the alert message based on the user's emotional data. For example, for a stressed user, use a gentler message such as "Please stay calm."

[1589] Step 10:

[1590] Server: Sends customized alert messages to users' smartphones via push notifications.

[1591] Step 11:

[1592] User: Receives a notification on their smartphone, checks the alert message, and takes appropriate action to manage their pet's health (e.g., move the pet to a cooler place, provide water, etc.).

[1593] In this way, each step works seamlessly together to create a system that monitors a pet's health in real time and provides appropriate alert messages that take the user's emotions into consideration.

[1594] Example 2

[1595] 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."

[1596] In today's world, pet health management is an important issue, but conventional systems often have a slow response time to detect abnormalities in pets. Furthermore, alert messages may not be effectively received if the user is under high stress. Therefore, it is necessary to monitor pet health in real time and provide alert messages that take the user's emotions into consideration.

[1597] The identification processing by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes: sensor means for collecting vital data of the pet; communication means for periodically transmitting the vital data to the information processing device; data processing means for storing the vital data received by the information processing device in a data storage device and performing preprocessing; analysis means for inputting the preprocessed data into a generative AI model and evaluating the health status of the pet; notification generation means for generating alert information when an abnormality is detected by the analysis means; notification means for transmitting the alert information to the user's terminal; emotion recognition means for analyzing user emotion data before the notification generation means generates the alert information; and information customization means for customizing the alert information based on the analysis result of the emotion recognition means. This makes it possible to monitor the health status of the pet in real time and provide an appropriate alert message that takes into consideration the user's emotions.

[1598] The "sensor means" is a device for collecting daily data about pets, and includes a camera, a thermometer, and the like as a sensing device.

[1599] The "communication means" refers to the devices and technologies for periodically transmitting collected data to the information processing device, and uses wireless communication methods such as Wi-Fi and Bluetooth.

[1600] "Data processing means" refers to devices and technologies that have the function of storing data received by an information processing device in a data storage device and performing preprocessing, such as noise removal and missing data completion.

[1601] A "generative AI model" is an artificial intelligence model that inputs pre-processed data and evaluates the pet's health status, comparing past and current data to detect abnormal patterns.

[1602] "Analysis means" refers to systems and technologies for inputting pre-processed data into a generative AI model and assessing the health status of a pet based on the results.

[1603] The "notification generating means" is a system having a function for generating alert information when an abnormality is detected by the analyzing means.

[1604] The "notification means" refers to a system and technology for transmitting the generated alert information to the user's terminal, and includes functions such as push notification.

[1605] "Emotion recognition means" refers to systems and techniques for analyzing a user's emotion data and assessing the user's emotional state before generating alert information.

[1606] The "information customization means" refers to a system and technology for customizing alert information to suit the emotional state of the user based on the analysis results of the emotion recognition means.

[1607] The pet health monitoring system according to an embodiment of the present invention is implemented using the following hardware and software: The system consists of three main components: a terminal, a server, and a user.

[1608] Hardware and Software Configuration

[1609] Device: Smart glasses or other wearable devices are used to collect daily data about pets. Specifically, these devices have built-in cameras and temperature sensors, and include a communication module that transmits data to a server via Wi-Fi or Bluetooth.

[1610] Server: An information processing device for data storage and preprocessing, utilizing SQL databases, Python's Pandas library, and deep learning frameworks such as TensorFlow and PyTorch. Generative AI models compare past and present data to detect abnormal patterns.

[1611] User device: A smartphone or tablet used by a user, which is a device for receiving alert messages. It also has the functionality to analyze user emotions using push notifications, cameras, and microphones.

[1612] Program processing

[1613] Data collection

[1614] The device uses the smart glasses' camera and temperature sensor to collect daily data about your pet (video, body temperature, food intake, activity time, etc.) in real time. For example, the smart glasses observe your pet and collect its body temperature data and activity data. At the same time, a digital scale is also used to measure the weight of food.

[1615] Data transmission

[1616] The device periodically processes the collected data in batches and sends them to a server via Wi-Fi. Bluetooth can also be used to transfer data over short distances. For example, the device can process data in batches every hour and send them to a server via Wi-Fi.

[1617] Data accumulation and preprocessing

[1618] The server receives the data sent from the device and stores it in an SQL database. Next, it uses the Python Pandas library to perform preprocessing such as removing noise from the data and filling in missing data. For example, filling in missing values ​​in sensor data and removing noise can improve analysis accuracy.

[1619] Data analysis

[1620] The server inputs the preprocessed data into a generative AI model to analyze the pet's health. Specifically, it uses a deep learning model (such as TensorFlow or PyTorch) to evaluate the pet's health based on the sales data and issues an alert if an abnormal pattern is detected. For example, an abnormality is detected when a pet's body temperature exceeds the normal acceptable range.

[1621] Alert Generation

[1622] If an abnormality is detected by the analysis means, the server generates alert information. When an abnormality is detected, the alert generation module is immediately activated and creates an appropriate alert message corresponding to the pet's condition.

[1623] emotion recognition

[1624] Before generating an alert message, the server uses emotion recognition to analyze the user's emotions. It analyzes the user's facial expressions and tone of voice captured by the camera and microphone to identify the user's emotional state. This is done using technologies such as OpenCV and DeepFace.

[1625] Message customization

[1626] Based on the analysis results of the emotion recognition means, the server customizes the alert message. For example, if the user is feeling stressed, the message will be softer and more friendly, such as "Please stay calm and first move your pet to a cooler place."

[1627] Sending alerts

[1628] The server sends customized alert messages to users' smartphones via push notifications, utilizing the push notification API to provide users with important information instantly.

[1629] Action Execution

[1630] The user can check the received notification and manage the pet's condition according to the alert message, for example, by moving the pet to a cooler place or contacting the appropriate medical institution if necessary.

[1631] Specific examples

[1632] 1. Device: The smart glasses monitor your pet, collecting video and temperature data in real time, and even recording feeding intake by weighing food.

[1633] 2. Terminal: Collected data is periodically sent to the server via Wi-Fi.

[1634] 3. Server: Receives the data and stores it in a database, then performs noise removal and missing data imputation.

[1635] 4. Server: Inputs the pre-processed data into the generative AI model and starts the analysis. If the body temperature data exceeds a certain range, an anomaly is detected.

[1636] 5. Server: Prepare to generate an alert message if an anomaly is detected.

[1637] 6. Server (Emotion Recognition Means): Before generating an alert message, analyze the user's emotions using a camera and microphone. For example, detect whether the user is in a stressed state.

[1638] 7. Server: Customize the content of the alert message based on the user's emotional state. If the user is stressed, use a gentler message such as "Please stay calm and move your pet to a cooler place first."

[1639] 8. Server: Sends customized alert messages to users' smartphones.

[1640] 9. User: The user checks the notification on their smartphone and takes measures to improve their pet's health based on the advice.

[1641] Prompt Sentence Examples

[1642] "Please give me some sample code for a Python program that analyzes pet temperature data and generates an alert message that takes user emotions into consideration if there is an abnormality."

[1643] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1644] Step 1: Data collection

[1645] Device: Smart glasses or other wearable devices use cameras and temperature sensors to collect daily data about your pet in real time (video, body temperature, food intake, activity time, etc.). Specifically, the camera in the smart glasses observes your pet and captures image data every second. At the same time, the temperature sensor measures your pet's temperature every few seconds, and a digital scale measures the weight of its food.

[1646] Input: Sensor data from the operating environment (pet surroundings, pet status).

[1647] Output: Collected raw sensor data (video data, body temperature data, food intake data, etc.).

[1648] Step 2: Send data

[1649] Device: Collected data is periodically batched and sent to a server via Wi-Fi or Bluetooth. Specifically, the device accumulates data collected every minute, batches each data set, and then sends it to the server via Wi-Fi.

[1650] Input: Raw collected sensor data.

[1651] Output: The batch data sent to the server.

[1652] Step 3: Data accumulation and preprocessing

[1653] Server: Receives data sent from the device and stores it in an SQL database. It then uses Python's Pandas library to perform preprocessing, such as removing noise from the data and filling in missing data. Specifically, it imports the received data into the database, fills in missing values ​​using linear interpolation or the average value, and removes noise through filtering.

[1654] Input: Batch data sent from the terminal.

[1655] Output: A preprocessed and clean dataset.

[1656] Step 4: Data analysis

[1657] Server: The preprocessed data is fed into a generative AI model to assess the pet's health. Specifically, a deep learning model (e.g., TensorFlow or PyTorch) is used to perform anomaly detection based on daily activity data and vital signs. For example, anomalies are detected when body temperature exceeds the normal acceptable range.

[1658] Input: The preprocessed dataset.

[1659] Output: Health status assessment result (normal or abnormal).

[1660] Step 5: Alert Generation

[1661] Server: If an abnormality is detected by the analysis means, it generates alert information. Specifically, it immediately launches the alert generation module upon detecting an abnormality and creates an alert message related to the pet's health condition.

[1662] Input: Health assessment result (abnormal).

[1663] Output: The initial alert message.

[1664] Step 6: Emotion Recognition

[1665] Server: Before generating an alert message, the server analyzes the user's emotional data. It acquires camera and microphone data from the user's device and inputs it into an emotion recognition engine. Specifically, it analyzes the user's facial expressions using OpenCV and DeepFace, and evaluates the tone of voice using voice analysis.

[1666] Input: Video and audio data obtained from the user's device.

[1667] Output: Evaluation of the user's emotional state.

[1668] Step 7: Customize your message

[1669] Server: Customize the alert message based on the emotion recognition results. For example, if the user is feeling stressed, change the usual alert message to something more gentle, such as "Please stay calm and move your pet to a cooler place first."

[1670] Input: Initial alert message, evaluation of the user's emotional state.

[1671] Output: The customized alert message.

[1672] Step 8: Sending an alert

[1673] Server: Sends customized alert messages to users' devices via push notifications. Specifically, the server uses the push notification API to instantly notify users on their smartphones or tablets.

[1674] Input: Your customized alert message.

[1675] Output: Push notification to user device.

[1676] Step 9: Take Action

[1677] User: The user checks the notification received on the device and takes care of the pet according to the alert message. For example, the user takes appropriate action to move the pet to a cooler place. If necessary, the user contacts a nearby veterinary clinic for further diagnosis.

[1678] Input: The pushed alert message.

[1679] Output: Specific actions to improve your pet's health.

[1680] (Application example 2)

[1681] 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."

[1682] Many systems exist for monitoring the health of pets in their daily lives, but these systems often send uniform alert messages without considering the user's psychological state. This can cause stress for users, making it difficult to take appropriate action. Furthermore, there are limitations to detecting anomalies based on the analysis of daily data, requiring further data analysis in the work environment. Therefore, there is a need for a system that takes the user's emotional state into account and encourages appropriate and flexible responses.

[1683] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1684] In this invention, the server includes sensor means for collecting daily data about the pet, communication means for periodically transmitting the daily data to the server, preprocessing means for storing the daily data received by the server in a database and preprocessing it, analysis means for inputting the preprocessed data into a generative model and evaluating the health condition of the pet, alert generation means for generating an alert message if an abnormality is detected by the analysis means, emotion recognition means for analyzing the user's facial expressions and voice to recognize their emotional state, message customization means for customizing the content of the alert message based on the emotion recognition means, and notification means for transmitting the customized alert message to the user's terminal. This makes it possible to provide an optimal alert message that takes into account the user's emotional state.

[1685] "Sensor means" refers to a device for collecting daily data about a pet, and includes a camera and a body temperature sensor.

[1686] "Communication means" refers to the technology used to periodically transmit collected daily data to a server, and uses communication protocols such as Wi-Fi and Bluetooth.

[1687] The "preprocessing means" refers to a function that stores the daily data received by the server in a database and performs noise removal and missing data completion.

[1688] The "analysis means" has the function of inputting preprocessed data into a generative model and evaluating the health condition of the pet.

[1689] The "alert generation means" is a mechanism for generating an alert message when an abnormality is detected by the analysis means.

[1690] "Emotion recognition means" is a technology for analyzing a user's facial expressions and voice to recognize their emotional state.

[1691] The "message customization means" is a function for customizing the contents of the alert message based on the emotion recognition means.

[1692] The "notification means" is a technique for sending the customized alert message to the user's terminal.

[1693] A system based on an embodiment of the present invention uses a smart band or smart glasses to collect daily data of factory workers, and if an abnormality is detected, sends an alert message customized based on the worker's emotion to the user's device. Specific embodiments are described below.

[1694] Data collection

[1695] The devices (smart band and smart glasses) collect daily data of factory workers (body temperature, heart rate, work environment data, etc.). The smart band collects data using heart rate and body temperature sensors, while the smart glasses use a built-in camera to capture images of the work environment and the facial expressions of workers.

[1696] As specific hardware examples, the smart band will use "Fitbit" and the smart glasses will use "Google Glass."

[1697] Data transmission

[1698] The collected data is sent from the devices (smart band and smart glasses) to a server via Wi-Fi or Bluetooth. Data is sent periodically, enabling real-time anomaly detection.

[1699] Data accumulation and preprocessing

[1700] The server stores the received data in a database (e.g., MySQL), and then uses Python scripts to perform preprocessing such as denoising the data and imputing missing data.

[1701] Data analysis

[1702] Once preprocessed, the data is input into a generative AI model (e.g., TensorFlow or PyTorch). This model compares past data with current data to detect abnormalities in body temperature and heart rate. Specifically, the analysis method determines that changes in heart rate or body temperature that exceed a certain range are abnormal.

[1703] Alert Generation

[1704] If the server detects an abnormality in the analysis, it generates an alert message using a Python script, which includes specific measures such as "Your temperature is too high. Please drink water and take a break."

[1705] emotion recognition

[1706] Before generating an alert, the server uses data acquired from the camera and microphone built into the smart glasses to analyze the user's emotional state using an emotion recognition engine (e.g., OpenAI), which can recognize stress, impatience, fatigue, etc.

[1707] Message customization

[1708] Based on the analyzed emotional state, the server uses a message customization method to adjust the content of the alert message. For example, if the user is feeling stressed, the server softens the message and changes it to something like, "Relax. First, take a deep breath and calm down."

[1709] Sending alerts

[1710] The server sends a customized alert message to the user's device (smartphone or tablet) via push notification, allowing workers to check the notification and take appropriate action promptly.

[1711] Specific examples

[1712] Here are some examples of specific prompts:

[1713] Create a program that monitors the health data of factory workers in real time and generates customized alert messages based on emotion recognition when an abnormality is detected. Use a smart band and smart glasses to collect data, and generate alerts based on heart rate and body temperature data when an abnormality occurs, using a tone that matches the user's emotion.

[1714] In this way, it is possible to provide optimal alert messages that take into account the user's emotional state.This system allows factory workers to manage their health efficiently and without stress.

[1715] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1716] Step 1:

[1717] The devices (smart bands and smart glasses) collect daily data of factory workers (body temperature, heart rate, work environment data, etc.) in real time.

[1718] Specifically, the smart band's body temperature and heart rate sensors collect data at regular intervals, while the smart glasses' built-in camera captures the worker's work status and facial expressions.

[1719] Inputs include body temperature, heart rate, and video data.

[1720] As output, collected daily data is produced.

[1721] Step 2:

[1722] The collected daily data is periodically sent from the devices (smart band and smart glasses) to a server via Wi-Fi or Bluetooth.

[1723] Specifically, the smart band and smart glasses batch process data at regular intervals and send it to the server using a communication protocol.

[1724] As input, collected daily data.

[1725] The output is the daily data sent to the server.

[1726] Step 3:

[1727] The server stores the received daily data in a database and performs preprocessing (noise removal and missing data completion).

[1728] Specifically, data cleansing is performed using a Python script.

[1729] The raw data sent to the server as input.

[1730] The output is the cleansed pre-processed data.

[1731] Step 4:

[1732] Once preprocessed, the data is processed on the server and input into a generative AI model (using TensorFlow or PyTorch).

[1733] Specifically, the generative AI model compares past normal data with current data and runs an anomaly detection algorithm.

[1734] As input, preprocessed daily data.

[1735] The output is an anomaly detection result.

[1736] Step 5:

[1737] The server generates an alert message if an abnormality is detected.

[1738] Specifically, a Python script is used to create a specific alert message based on the abnormality (for example, "Your body temperature is too high. Please drink water and take a break").

[1739] As input, anomaly detection results.

[1740] As output, an alert message is generated.

[1741] Step 6:

[1742] Before generating an alert message, the server inputs the user's facial expressions and voice into an emotion recognition engine to analyze the user's emotional state.

[1743] Specifically, an emotion recognition engine (using OpenAI) uses data obtained from the smart glasses' camera and microphone to analyze the user's psychological state (stress, impatience, fatigue, etc.).

[1744] As input, facial expression data and voice data.

[1745] The output is the user's emotional state.

[1746] Step 7:

[1747] The server customizes the alert message based on the emotion recognition results.

[1748] Specifically, the message customization means adjusts the content of the alert message to match the user's emotional state (for example, if the user is feeling stressed, it will say, "Relax. First, take a deep breath and stay calm").

[1749] As input, the emotional state and the generated alert message.

[1750] As output, you get a customized alert message.

[1751] Step 8:

[1752] The server sends a customized alert message to the user's device (smartphone or tablet) via push notification.

[1753] Specifically, the notification method within the server sends a message using a push notification service (such as Firebase Cloud Messaging).

[1754] As input, a customized alert message.

[1755] The output is an alert message displayed on the user's terminal.

[1756] 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.

[1757] 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.

[1758] 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.

[1759] 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.

[1760] 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.

[1761] 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.

[1762] 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).

[1763] 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.

[1764] 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."

[1765] 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.

[1766] 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).

[1767] 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.

[1768] 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.

[1769] 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.

[1770] 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.

[1771] The hardware resource for executing a specific process can be any of the following types of processors: A processor, for example, 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 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.

[1772] 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.

[1773] 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.

[1774] 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.

[1775] 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.

[1776] 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.

[1777] The following is further disclosed regarding the above embodiment.

[1778] (Claim 1)

[1779] a sensor means for collecting daily data of the pet;

[1780] a communication means for periodically transmitting the daily data to a server;

[1781] a pre-processing means for storing the received daily data in a database and performing pre-processing in the server;

[1782] an analytical means for inputting the preprocessed data into a generative model to evaluate the health status of the pet;

[1783] an alert generating means for generating an alert message when an abnormality is detected by the analyzing means;

[1784] The system includes a notification means for sending the alert message to a user's terminal.

[1785] (Claim 2)

[1786] 10. The system of claim 1, wherein the sensor means includes a camera and a body temperature sensor.

[1787] (Claim 3)

[1788] 10. The system of claim 1, wherein the analyzing means detects abnormal patterns by comparing past data with current data.

[1789] "Example 1"

[1790] (Claim 1)

[1791] a sensor means for collecting daily data of the pet;

[1792] a communication means for periodically transmitting the daily data to a server;

[1793] a pre-processing means for storing the received daily data in a database and performing pre-processing in the server;

[1794] an analytical means for inputting the pre-processed data into an artificial intelligence model to evaluate the health status of the pet;

[1795] an alert generating means for generating an alert message including appropriate advice when an abnormality is detected by the analyzing means;

[1796] The system includes a notification means for sending the alert message to a user's terminal.

[1797] (Claim 2)

[1798] 10. The system of claim 1, wherein the sensor means includes a camera for capturing video and a temperature sensor for measuring body temperature.

[1799] (Claim 3)

[1800] 10. The system of claim 1, wherein the analysis means detects abnormal patterns by comparing past baseline data with current data.

[1801] "Application Example 1"

[1802] (Claim 1)

[1803] a sensor means for collecting daily data of the pet;

[1804] a communication means for periodically transmitting the daily data to a server;

[1805] a pre-processing means for storing the received daily data in a database and performing pre-processing in the server;

[1806] an analytical means for inputting the preprocessed data into a generative model to evaluate the health status of the pet;

[1807] an alert generating means for generating an alert message when an abnormality is detected by the analyzing means;

[1808] notification means for transmitting the alert message to a user's terminal;

[1809] A system that includes a temperature monitoring means that collects food temperature data in real time and analyzes abnormal temperatures.

[1810] (Claim 2)

[1811] 10. The system of claim 1, wherein the sensor means includes a camera and a body temperature sensor.

[1812] (Claim 3)

[1813] 10. The system of claim 1, wherein the analyzing means detects abnormal patterns by comparing past data with current data.

[1814] "Example 2: Combining Emotion Engines"

[1815] (Claim 1)

[1816] a sensor means for collecting vital data of the pet;

[1817] a communication means for periodically transmitting the vital data to an information processing device;

[1818] a data processing means for storing the vital data received by the information processing device in a data storage device and performing preprocessing;

[1819] An analytical method to input pre-processed data into a generative AI model to evaluate the health status of pets;

[1820] a notification generating means for generating alert information when an abnormality is detected by the analyzing means;

[1821] notification means for transmitting the alert information to a user's terminal;

[1822] emotion recognition means for analyzing emotion data of a user before the notification generation means generates alert information;

[1823] an information customization means for customizing alert information based on an analysis result of the emotion recognition means;

[1824] A system including:

[1825] (Claim 2)

[1826] 10. The system of claim 1, wherein the sensor means includes an imaging device and a body temperature measuring device.

[1827] (Claim 3)

[1828] 10. The system of claim 1, wherein the analyzing means detects abnormal patterns by comparing past data with current data.

[1829] "Application example 2 when combining emotion engines"

[1830] (Claim 1)

[1831] a sensor means for collecting daily data of the pet;

[1832] a communication means for periodically transmitting the daily data to a server;

[1833] a pre-processing means for storing the received daily data in a database and performing pre-processing in the server;

[1834] an analytical means for inputting the preprocessed data into a generative model to evaluate the health status of the pet;

[1835] an alert generating means for generating an alert message when an abnormality is detected by the analyzing means;

[1836] emotion recognition means for analyzing a user's facial expression and voice to recognize the user's emotional state;

[1837] a message customization means for customizing the content of the alert message based on the emotion recognition means;

[1838] The system includes a notification means for sending the customized alert message to a user's terminal.

[1839] (Claim 2)

[1840] 10. The system of claim 1, wherein the sensor means includes a camera and a body temperature sensor.

[1841] (Claim 3)

[1842] 10. The system of claim 1, wherein the analyzing means detects abnormal patterns by comparing past data with current data. [Explanation of symbols]

[1843] 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 sensor means for collecting daily data of the pet; a communication means for periodically transmitting the daily data to a server; a pre-processing means for storing the received daily data in a database and performing pre-processing in the server; an analytical means for inputting the preprocessed data into a generative model to evaluate the health status of the pet; an alert generating means for generating an alert message when an abnormality is detected by the analyzing means; The system includes a notification means for sending the alert message to a user's terminal.

2. 2. The system of claim 1, wherein said sensor means includes a camera and a temperature sensor.

3. 2. The system of claim 1, wherein said analyzing means detects abnormal patterns by comparing past data with current data.

Images