System

Abstract

A system is provided.SOLUTION: A system comprising: means for collecting behavior information of animals by using sensors; means for transmitting the collected behavior information to a server; means for analyzing the behavior information by using a generative AI model in the server to evaluate health conditions and behaviors of the animals; and means for notifying a user of evaluation results.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] Currently, it is difficult for pet owners to keep detailed track of their pets' daily health and behavioral patterns, especially their dogs, and take immediate action. Early detection of specific health problems, such as loss of appetite, decreased activity, and poor behavior while away from home, and appropriate measures to address these issues are a major concern for pet owners. While regular data monitoring and appropriate advice are necessary to prevent deterioration of health, the current system does not efficiently address this issue. Furthermore, there are limited options for quickly consulting a veterinarian when necessary. [Means for solving the problem]

[0005] The present invention is a system that collects animal behavioral data, analyzes it using a generative AI model, and provides the results to the user. Specifically, it includes a means for collecting animal behavioral data using sensors, a means for transmitting the collected data to a server, a means for analyzing the data on the server using a generative AI model to evaluate the animal's health and behavior, and a means for notifying the user of the evaluation results. It also provides a means for collecting dietary data and calculating optimal dietary intake using a generative AI model, and a means for suggesting optimal exercise methods and times based on exercise data. It also includes a means for detecting accidental ingestion or abnormal behavior while the owner is away and issuing an alert notification, and a means for the user to easily schedule an online consultation with a veterinarian. This allows owners to understand their animal's health in detail and in real time and take appropriate measures.

[0006] "Animals" is a general term for living organisms, including mammals and birds kept as pets.

[0007] "Behavioral data" is a collection of information related to an animal's behavior and state, such as its activity level, sleep patterns, and food intake.

[0008] A "sensor" is an electronic device used to measure and collect animal behavioral data.

[0009] A "server" is a computer system for receiving, storing, and analyzing data.

[0010] A "generative AI model" is an artificial intelligence model adapted to a specific task, and in this invention a generative model (e.g., GPT) is used.

[0011] "Analysis" is the process of understanding and evaluating the content of collected data.

[0012] "Health status" is the overall state of an animal's physical and mental well-being.

[0013] "Evaluation results" are conclusions or recommendations regarding the current health or behavior of an animal that are reached through analysis.

[0014] "Notification" is a communication method for conveying important information from the server to the user.

[0015] "Dietary data" is information regarding the type and amount of food consumed by an animal.

[0016] "Movement data" is information about the amount and intensity of activity an animal engages in over a certain period of time.

[0017] "Accidental ingestion" is when an animal accidentally puts a substance other than food into its mouth and swallows it.

[0018] "Abnormal behavior" is any movement or response that is different from normal behavior and may pose a threat to the health or safety of an animal.

[0019] An "alert notification" is a notification method for quickly informing a user of a highly urgent situation.

[0020] "Online consultation" is a service that allows users to consult with experts (e.g., veterinarians) over the Internet. [Brief explanation of the drawings]

[0021] [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

[0022] 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.

[0023] First, the terms used in the following description will be explained.

[0024] 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).

[0025] 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.

[0026] 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.

[0027] 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.

[0028] 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."

[0029] [First embodiment]

[0030] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0031] 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.

[0032] 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).

[0033] 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.

[0034] 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.

[0035] 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.

[0036] 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.

[0037] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0038] 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.

[0039] 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.

[0040] 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.

[0041] 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."

[0042] The present invention is a system that collects behavioral data of animals, particularly dogs, and analyzes it using generative artificial intelligence (generative AI model). The present invention manages the health of animals by collecting data using sensors, transmitting it to a server for analysis, and providing the results to a user. Specific embodiments of the present invention will be described below.

[0043] Overall overview

[0044] The system consists of the following main components:

[0045] 1. Sensors that collect animal behavior data

[0046] 2. An application that sends data to a server

[0047] 3. Server that analyzes data and generates AI models

[0048] 4. Interface for notifying users of evaluation results

[0049] Sensors and Data Collection

[0050] Terminal (sensor) side:

[0051] Sensors attached to the animal's collar or harness monitor real-time behavioral data such as activity levels, sleep patterns, and food intake. These sensors combine accelerometers, gravity sensors, and GPS. Data is periodically sent to a server via an application.

[0052] Data transmission and storage

[0053] App (device) side:

[0054] The application periodically collects data from the sensors and sends it to a server via the Internet. The data is encrypted to ensure security. The application records the success or failure of data transmission and notifies the user if there is a problem.

[0055] Server side:

[0056] The server temporarily stores the received data in a buffer and then refines it. The refined data is then stored in a database for subsequent analysis. The database is designed for query efficiency, allowing for quick access even to large amounts of data.

[0057] Data analysis

[0058] Server side:

[0059] The server inputs the behavioral data stored in the database into a generative AI model for analysis. The generative AI model identifies behavioral patterns and detects anomalies, generating results such as optimizing food intake, suggesting exercise amounts, and evaluating health status. These analysis results are then stored back in the database and made available via the user interface.

[0060] Notification of results and actions

[0061] Server side:

[0062] The server generates appropriate notifications for users based on the analysis results. The notification system operates in real time, and immediate notifications are sent for urgent matters. The content of the notifications is conveyed to users via push notifications, email, or social media.

[0063] App (device) side:

[0064] The application displays notifications and advice sent from the server to the user. Notifications include suggestions for optimal meal portions, exercise advice, and warnings about abnormal behavior while away from home. The application provides an interface for the user to take action in response to these notifications.

[0065] User Actions

[0066] User side:

[0067] Based on the information provided through the app, users can adjust their pet's feeding and exercise schedules, receive alerts about abnormal behavior while away from home, take steps to respond quickly, and, if necessary, use the application to book an online consultation with a veterinarian to receive appropriate medical treatment.

[0068] Specific examples

[0069] Example 1: Optimizing food portion size

[0070] If a user's dog has recently shown a decreased appetite, the sensor collects food data and sends it to a server. The server then uses a generative AI model to calculate optimal feeding amounts and generate recommendations, such as "200 grams of food per day is appropriate for a 10kg dog." The application then notifies the user of this information, allowing them to adjust their feeding accordingly.

[0071] Example 2: Exercise advice

[0072] If the user's dog has recently shown a decline in exercise, the sensor collects activity data and sends it to the server. The server analyzes the data and uses a generative AI model to calculate the optimal amount of exercise. The result, such as "Two 30-minute walks per day or free exercise at a dog park is recommended," is generated and notified to the user via the app. The user can then create an exercise plan based on this information.

[0073] Example 3: Detecting abnormal behavior while away from home

[0074] If the dog swallows something or exhibits abnormal behavior while the user is away, the sensor will collect the data and send it to the server. The server will immediately analyze it and generate an alert notification if it detects abnormal behavior. The application will then send a push notification to the user with detailed information, allowing the user to take necessary measures.

[0075] In this way, the system of the present invention manages the health status of animals in detail and in real time, supporting owners in responding quickly and appropriately.

[0076] The processing flow will be explained below.

[0077] Data Collection Phase

[0078] Device (sensor, app) side

[0079] Step 1: Monitoring data with sensors

[0080] The sensors measure the animals' activity levels, sleep patterns and food intake in real time.

[0081] The measured data is temporarily stored inside the sensor.

[0082] Step 2: Prepare your data for transfer

[0083] The sensor prepares to send the collected data to the app at regular intervals.

[0084] Set up the communication protocol for data transmission and format the data appropriately.

[0085] Step 3: Sending data

[0086] The app receives the data sent from the sensor and temporarily stores it in the internal storage.

[0087] Batch processing is performed at regular intervals and the data is sent to the server.

[0088] Data transmission and storage

[0089] Server side

[0090] Step 4: Receiving the data

[0091] The server has an API for receiving data sent from the app.

[0092] The received data is temporarily stored in a buffer.

[0093] Step 5: Save your data

[0094] The server pre-processes and formats the buffered data.

[0095] The preprocessed data is stored in the database.

[0096] Data analysis

[0097] Server side

[0098] Step 6: Preprocessing the data

[0099] The server retrieves the data that needs to be analyzed from the database.

[0100] The acquired data is filled in with missing values ​​and noise is removed, and it is then formatted in a form suitable for analysis.

[0101] Step 7: Input to the generative AI model

[0102] The server inputs the preprocessed data into a generative AI model (e.g., GPT).

[0103] The model analyzes the animal's behavioral patterns and extracts features.

[0104] Step 8: Generate analysis results

[0105] The generative AI model generates evaluation results such as optimizing food intake, giving exercise advice, and detecting abnormal behavior.

[0106] Store the generated results in a database.

[0107] Notification of results and actions

[0108] Server side

[0109] Step 9: Prepare for notifications

[0110] The server periodically checks the analysis results and extracts information that should be notified to the user.

[0111] Information with high urgency will be given priority.

[0112] Step 10: Sending notifications

[0113] The server uses an appropriate notification system (e.g., Firebase Cloud Messaging) to send a notification to the user.

[0114] App (device) side

[0115] Step 11: Receive notifications

[0116] The app receives notifications sent from the server.

[0117] Received notifications are displayed to the user in a visually understandable format.

[0118] User side

[0119] Step 12: Review and respond to notifications

[0120] Users can check the notification content through the app and take necessary action.

[0121] For example, it adjusts food and creates exercise plans based on optimal feeding amounts.

[0122] Step 13: Online consultation with a veterinarian

[0123] If necessary, users can use the app to book an online consultation with a veterinarian.

[0124] Online consultations are conducted via video calls and text chats.

[0125] This is the specific flow of the program's processing. This process manages the animal's health condition in real time and supports the owner in taking appropriate action.

[0126] Example 1

[0127] 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."

[0128] Currently, many pet owners face the challenge of understanding their pets' health and behavior in detail and in real time. Manually recording behavioral data and assessing health status is time-consuming and often requires specialized knowledge. Furthermore, standards for calculating appropriate amounts of food and exercise are often unclear, making it difficult for pet owners to properly manage their pets. This leads to inadequate health management for their animals and ultimately increases the risk of ill health.

[0129] 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.

[0130] In this invention, the server

[0131] means for transmitting the animal's behavior data to a server via an application;

[0132] a means for temporarily storing the data, subjecting the data to a refinement process, and storing the data in a database;

[0133] A means to analyze data using generative AI models to assess animal health and behavior;

[0134] This enables the collection, transmission, and analysis of animal behavior data in real time. Based on the analysis results, users can receive specific advice, develop appropriate dietary and exercise plans, and respond quickly to abnormal behavior.

[0135] "Animal behavioral data" refers to information about the activities that animals engage in in their daily lives, and specifically includes data such as activity levels, sleep patterns, and food intake.

[0136] The term "sensor" refers to a device that detects physical or environmental conditions and converts them into data, and in the present invention includes an acceleration sensor or GPS that is attached to an animal's collar, etc.

[0137] "Application" refers to software that runs on the device and transmits data collected from the sensor to the server.

[0138] "Server" refers to a computer system for receiving, storing, and analyzing data over a network.

[0139] "Temporary storage" refers to data that is temporarily stored in a storage device before being stored in a permanent database.

[0140] "Refining" refers to the process of correcting duplications and missing data in the collected data and preparing it in a format suitable for analysis.

[0141] A "database" refers to a collection of data that is structured to store information systematically and enable quick search and access.

[0142] A "generative AI model" is an artificial intelligence model that uses pre-trained algorithms to analyze new data and make predictions or suggestions.

[0143] "Analysis" refers to the act of making inferences and calculations based on collected data to assess the health and behavior of animals.

[0144] "Evaluation results" refer to conclusions about the health and behavior of animals drawn through analysis.

[0145] "Notification" refers to the act of transmitting information to inform users of the evaluation results, and includes push notifications, emails, social media, etc.

[0146] "User interface" refers to the means or screens that allow a user to interact with a system, and is provided through an application.

[0147] The present invention is a system that collects behavioral data of animals, particularly dogs, and analyzes it using a generative AI model. This system collects data using sensors, transmits it to a server for analysis, and provides the results to a user to manage the health of the animal. Below, specific embodiments of the present invention are described.

[0148] Hardware and software used

[0149] Sensor (terminal) side:

[0150] The sensors, which are attached to the animal's collar or harness, combine accelerometers, gravity sensors, GPS, and other sensors to monitor the animal's activity, sleep patterns, food intake, and other behavioral data in real time.

[0151] Application (device) side:

[0152] An application installed on a smartphone or tablet collects data from the sensors and periodically transmits it to a server over the Internet using the encrypted HTTPS protocol.

[0153] Server side:

[0154] The server is a high-performance computing system that temporarily buffers received data, then refines and stores it in a database. The database on the server is designed for query efficiency, allowing for quick access to large amounts of data. Additionally, generative AI models (e.g., deep learning models for anomaly detection and pattern recognition) are installed and used for data analysis.

[0155] Data processing and calculation

[0156] Data collection and transmission:

[0157] The sensors monitor animal behavior data in real time and transmit it to a smartphone application, which then compiles the data, sends it to a server, and logs the success or failure of the transmission.

[0158] Data storage and refinement:

[0159] The server temporarily stores the received data in a buffer and performs refinement processes such as deleting duplicate data and filling in missing data. The refined data is then stored in a database such as MySQL.

[0160] Data Analysis:

[0161] The server uses the generative AI model to analyze the behavioral data stored in the database, including identifying activity patterns, detecting abnormal behavior, and suggesting optimal diet and exercise amounts. The analysis results are then stored back in the database and made available through the user interface.

[0162] Notification of results:

[0163] The server generates notifications for users based on the analysis results. The notification system operates in real time, and immediate notifications are sent to users for urgent matters. Notifications are sent to users via push notifications, email, and social media.

[0164] Specific examples

[0165] Example 1: Optimizing food portion size

[0166] If a user's dog has recently shown a decreased appetite, the sensor collects food data and sends it to a server. The server then uses a generative AI model to calculate the optimal amount of food, suggesting, for example, that a 10kg dog should eat 200g of food per day. The app then notifies the user of this information, allowing them to adjust their dog's food intake accordingly.

[0167] Example prompt: "What is the appropriate daily amount of food for a dog weighing 10 kg?"

[0168] Example 2: Exercise advice

[0169] If the user's dog has recently shown a decline in exercise, the sensor collects activity data and sends it to the server. The server analyzes the data and uses a generative AI model to calculate the optimal amount of exercise. The result is "recommended to take two 30-minute walks per day or exercise freely at a dog park," and the result is notified to the user via the application. The user can then create an exercise plan based on this.

[0170] Example prompt: "What activities do you recommend to increase my dog's exercise?"

[0171] Example 3: Detecting abnormal behavior while away from home

[0172] If the dog exhibits abnormal behavior while the user is away, the sensor collects the data and sends it to the server. The server immediately analyzes it and generates an alert notification if abnormal behavior is detected. The application then sends a push notification to the user with detailed information, allowing them to take prompt action.

[0173] Example prompt: "What is the appropriate course of action if my dog ​​exhibits abnormal behavior while I'm away?"

[0174] In this way, the system of the present invention manages the health status of animals in detail and supports owners in responding promptly and appropriately.

[0175] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0176] Step 1: Data collection

[0177] Terminal (sensor) side:

[0178] The sensors collect real-time behavioral data of the animals. Specifically, an accelerometer measures activity and posture at rest, and a GPS acquires location information. This data is collected from the sensors and recorded at regular intervals.

[0179] Input: Animal activity data (e.g., activity level, location information)

[0180] Output: raw data collected

[0181] Step 2: Send data

[0182] App (device) side:

[0183] The application periodically collects data collected from sensors and sends it to a server via the Internet. The encrypted HTTPS protocol is used for transmission. The success or failure of the transmission is recorded in a log. For example, if the transmission is successful, a "transmission completed" log is recorded, and if it fails, a "retransmission" flag is set.

[0184] Input: Raw data collected

[0185] Output: Data transferred to the server

[0186] Step 3: Temporarily store and refine data

[0187] Server side:

[0188] The server temporarily stores the received data in a buffer and performs refinement processes such as removing duplicate data and filling in missing data. Duplicate data is removed using SQL queries, and missing GPS data is filled in using a fill-in algorithm. The refined data is then stored in a database such as MySQL.

[0189] Input: Raw data transferred to the server

[0190] Output: Refinement data stored in a database

[0191] Step 4: Data analysis

[0192] Server side:

[0193] The server inputs the refined data into a generative AI model for analysis. The generative AI model identifies behavioral patterns and detects anomalies, and generates results such as recommendations for optimizing food intake and exercise. The analysis process is performed using a Python script.

[0194] Input: Refining data stored in the database

[0195] Output: Analysis results (e.g., recommendations for optimal food intake and exercise)

[0196] Step 5: Notification of results

[0197] Server side:

[0198] The server converts the analysis results into notifications and sends them to the user. For example, a push notification containing information such as a decrease in the dog's activity level or a recommendation for optimal feeding is generated. These notifications are sent to the user in real time.

[0199] Input: Analysis results

[0200] Output: Notification message (e.g. push notification, email)

[0201] Step 6: Display in the user interface

[0202] App (device) side:

[0203] The application displays notifications and advice sent from the server to the user, such as "200 grams of food per day" or "Take two 30-minute walks per day." Users can tap to view more information.

[0204] Input: Notification message

[0205] Output: Notifications and advice displayed on the user interface

[0206] Step 7: User Actions

[0207] User side:

[0208] Users can take action based on the provided notifications, such as adjusting the amount of food to the suggested 200 grams per day and creating a daily walking schedule. If they receive a notification of abnormal behavior, they can consult with a veterinarian through the app's online appointment system for prompt action.

[0209] Input: User interface notifications and advice

[0210] Output: Actual behavior (e.g., adjusting food intake, executing exercise plan)

[0211] (Application example 1)

[0212] 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."

[0213] In modern society, pet health management is an important issue for pet owners. Detecting abnormal pet behavior and responding quickly when the owner is away is particularly important for maintaining the pet's safety and health. However, existing technology does not adequately provide a system that can monitor pet behavior in real time, detect abnormal behavior, and provide prompt notification. Therefore, the present invention aims to provide a system that can detect abnormal pet behavior in real time while the owner is away and promptly notify the owner.

[0214] 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.

[0215] In this invention, the server includes means for collecting animal behavior data using a sensor, means for transmitting the collected data to the server, means for analyzing the data using a generative AI model in the server and evaluating the health condition and behavior of the animal, means for notifying the user of the evaluation results, and means for detecting abnormal behavior of animals, including dogs, while the user is away and notifying the user in real time. This makes it possible to quickly detect abnormal behavior of pets and notify the owner in real time.

[0216] "Animal" is a broad term that refers to any pet or livestock animal, including dogs.

[0217] "Behavioral data" is a general term for various data that indicate an animal's health and behavior, such as its activity level, sleep patterns, and food intake.

[0218] "Sensors" are devices used to collect animal behavioral data, and include acceleration sensors, gravity sensors, GPS, etc.

[0219] "Server" means a computer system that stores, analyzes, and manages collected data.

[0220] A "generative AI model" is a machine learning model used to analyze collected behavioral data and evaluate the health and behavior of animals.

[0221] "Means for assessing health and behavior" refers to a method for analyzing behavioral data using a generative AI model and assessing the health and behavior of animals based on the results.

[0222] "Means of notifying users" refers to methods for providing information to users based on the analysis results, and includes means such as push notifications, emails, and social media.

[0223] "Abnormal behavior" refers to animal behavior that deviates from normal patterns, including, for example, accidental ingestion, abnormal wandering, and anxiety.

[0224] "Real-time" refers to data processing and notification occurring almost immediately.

[0225] "Away" refers to the time when the user is away, and specifically refers to the time when the animal is alone.

[0226] Overall overview

[0227] The system of the present invention consists of the following main components: a sensor that collects animal behavior data, a means for transmitting the data to a server, a generative AI model that analyzes the behavior data on the server, a means for notifying the user of the analysis results, and a means for detecting abnormal behavior in real time.

[0228] Sensors and Data Collection

[0229] Terminal (sensor) side:

[0230] Sensors attached to the animal's collar or harness monitor real-time behavioral data such as activity levels, sleep patterns, and food intake. These sensors combine accelerometers, gravity sensors, and GPS. The collected data is periodically sent to a server via an application.

[0231] Data transmission and storage

[0232] App (device) side:

[0233] The application periodically collects data from the sensors and sends it to a server via the Internet. The data is encrypted to ensure security. The application logs the success or failure of data transmission and notifies the user if there is a problem.

[0234] Server side:

[0235] The server temporarily stores the received data in a buffer and then performs a data refinement process. The refined data is stored in a database and used for subsequent analysis processes. The database is designed with query efficiency in mind, allowing for quick access even to large amounts of data.

[0236] Data analysis

[0237] Server side:

[0238] The server inputs the behavioral data stored in the database into a generative AI model for analysis. The generative AI model identifies behavioral patterns and detects anomalies, and generates results such as optimizing food intake, suggesting exercise amounts, and evaluating health status. The analysis results are then saved back into the database and made available in the user interface.

[0239] Notification of results and actions

[0240] Server side:

[0241] The server generates appropriate notifications for users based on the analysis results. The notification system operates in real time, and immediate notifications are sent for urgent matters. Notifications are sent to users via push notifications, email, or social media.

[0242] App (device) side:

[0243] The application displays notifications and advice sent from the server to the user, such as recommendations for optimal meal size, exercise advice, and warnings about abnormal behavior while away from home. It also provides an interface for the user to take action based on these notifications.

[0244] User Actions

[0245] User side:

[0246] Based on the information provided through the app, users can adjust their animal's feeding and exercise schedule, take steps to respond quickly if they receive alerts about abnormal behavior while away from home, and, if necessary, use the application to schedule an online consultation with a veterinarian to obtain appropriate medical treatment.

[0247] Specific examples

[0248] Example 1: Optimizing food portion size

[0249] If a user's dog has recently shown a decreased appetite, the sensor collects food data and sends it to a server. The server then uses a generative AI model to calculate optimal feeding amounts and generate recommendations, such as "200 grams of food per day is appropriate for a 10kg dog." The application then notifies the user of this information, allowing them to adjust their feeding accordingly.

[0250] Example 2: Exercise advice

[0251] If the user's dog has recently shown a decline in exercise, the sensor collects activity data and sends it to the server. The server then uses a generative AI model to calculate the optimal amount of exercise, generating a recommendation such as "two 30-minute walks per day or free exercise at a dog park." The result is then sent to the user via the app, allowing the user to create an exercise plan based on this information.

[0252] Example 3: Detecting abnormal behavior while away from home

[0253] If the dog swallows something or exhibits abnormal behavior while the user is away, the sensor will collect the data and send it to the server. The server will immediately analyze it and generate an alert notification if it detects abnormal behavior. The application will then send a push notification to the user with detailed information, allowing the user to take necessary measures.

[0254] Example prompts to input to the generative AI model

[0255] "Enter your dog's activity levels and patterns. Generate alerts if abnormal behavior is detected."

[0256] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0257] Step 1:

[0258] The device collects real-time behavioral data from sensors attached to the animal's collar. Specifically, it uses accelerometers, gravity sensors, and GPS to collect data on the animal's activity, sleep patterns, food intake, etc. This data is temporarily stored in the device's memory.

[0259] Input: Raw data from sensors (acceleration, position).

[0260] Output: Collected behavioral data.

[0261] Specific operation: The device acquires data from the sensor at regular intervals and stores it in local memory.

[0262] Step 2:

[0263] The device periodically collects and sends the collected data to a server, where it is encrypted and securely transferred to the server via the Internet.

[0264] Input: Behavioral data stored in local memory.

[0265] Output: The encrypted data sent to the server.

[0266] Specific operation: The device converts the collected data into JSON format, encrypts it, and then sends the data to the server using an HTTP request.

[0267] Step 3:

[0268] The server temporarily stores the received data in a buffer and performs a data refinement process, which removes noise and standardizes the format. The refined data is then saved in a database.

[0269] Input: The received encrypted data.

[0270] Output: Refined behavioral data.

[0271] Specific operation: The server decrypts the encrypted data, performs preprocessing such as noise removal and missing value completion, and then stores it in the database.

[0272] Step 4:

[0273] The server inputs the behavioral data stored in the database into the generative AI model for analysis. The generative AI model detects abnormal behavior from the behavioral data and optimizes the amount of food and exercise.

[0274] Input: Refined behavioral data stored in a database.

[0275] Output: Analysis results (detection of abnormal behavior, optimization of food intake and exercise).

[0276] Specific operation: The server inputs behavioral data into the generative AI model using prompts to analyze it. For example, the prompt might say, "Enter the dog's activity level and patterns. Generate an alert if abnormal behavior is detected."

[0277] Step 5:

[0278] The server generates appropriate notifications for users based on the analysis results. Urgent matters are notified immediately. Notifications are sent to users via push notifications, email, or social media.

[0279] Input: Analysis results.

[0280] Output: A notification message to the user.

[0281] Specific operation: The server generates a notification message from the analysis results and sends a push notification or email via an HTTP request or various APIs.

[0282] Step 6:

[0283] The device displays notifications and advice sent from the server to the user, who can then adjust their behavior based on the information, such as adjusting their food intake, developing an exercise plan, or quickly responding to abnormal behavior.

[0284] Input: Notification message.

[0285] Output: Specific instructions or advice for the user to adjust their behavior.

[0286] Specific behavior: The device receives the notification message and displays it on the user interface. The user can take appropriate measures based on the notification content.

[0287] 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.

[0288] The present invention is a system that collects behavioral data of animals, particularly dogs, and analyzes it using generative artificial intelligence (generative AI model) and an emotion engine. The present invention manages the health of animals by collecting data using sensors, transmitting it to a server for analysis, and providing information based on the results and the user's emotions. Specific embodiments of the present invention will be described below.

[0289] Overall overview

[0290] The system consists of the following main components:

[0291] 1. Sensors that collect animal behavior data

[0292] 2. An application that sends data to a server

[0293] 3. Server that analyzes data and generates AI models

[0294] 4. Emotion engine that recognizes user emotions

[0295] 5. Interface for notifying users of evaluation results

[0296] Sensors and Data Collection

[0297] Terminal (sensor) side:

[0298] Sensors attached to the animal's collar or harness monitor real-time behavioral data such as activity levels, sleep patterns, and food intake. These sensors combine accelerometers, gravity sensors, and GPS. Data is periodically sent to a server via an application.

[0299] Data transmission and storage

[0300] App (device) side:

[0301] The application periodically collects data from the sensors and sends it to a server via the Internet. The data is encrypted to ensure security. The application records the success or failure of data transmission and notifies the user if there is a problem.

[0302] Server side:

[0303] The server temporarily stores the received data in a buffer and then refines it. The refined data is then stored in a database for subsequent analysis. The database is designed for query efficiency, allowing for quick access even to large amounts of data.

[0304] Data analysis

[0305] Server side:

[0306] The server inputs the behavioral data stored in the database into a generative AI model for analysis. The generative AI model identifies behavioral patterns and detects anomalies, generating results such as optimizing food intake, suggesting exercise amounts, and evaluating health status. These analysis results are then stored back in the database and made available via the user interface.

[0307] Emotion engine integration

[0308] Server side:

[0309] The server integrates an emotion engine that collects users' emotional data. The emotion data is analyzed in real time based on the user's facial expressions, voice, and text input. The emotion engine evaluates the user's stress level and emotional state and stores the results in a well-being database.

[0310] Emotion Engine in action:

[0311] The emotion engine analyzes the user's emotional data to assess stress levels and emotional fluctuations. The assessment results are then used in conjunction with a generative AI model to incorporate emotional elements into the analysis of animal health data and provide personalized notifications and advice to the user.

[0312] Notification of results and actions

[0313] Server side:

[0314] The server generates appropriate notifications for the user based on the analysis results. The notification system operates in real time, and immediate notifications are sent for urgent matters. The content of the notifications is conveyed to the user via push notifications, email, or social media. Based on the evaluation results of the emotion engine, the content of the notifications is optimized to the user's emotional state.

[0315] App (device) side:

[0316] The application displays notifications and advice sent from the server to the user. Notifications include suggestions for optimal meal sizes, exercise advice, and warnings about abnormal behavior while away from home. The application provides an interface for the user to take action based on these notifications. It also includes advice and reminders to reduce the user's stress based on information from the emotion engine.

[0317] User side:

[0318] Based on the information provided through the app, users can adjust their pet's feeding and exercise schedule. If they receive alerts about abnormal behavior while away from home, they can take steps to respond quickly. If necessary, they can also use the application to book an online consultation with a veterinarian to receive appropriate medical treatment. Furthermore, they can manage stress levels and receive emotional support by implementing advice based on the user's emotional state.

[0319] Specific examples

[0320] Example 1: Optimizing food portion size

[0321] If a user's dog has recently shown a decrease in appetite, the sensor collects food data and sends it to the server. The server then uses a generative AI model to calculate the optimal amount of food and generates recommendations such as "200 grams of food per day is appropriate for a 10kg dog." In addition, the emotion engine evaluates the user's stress level and provides advice such as "Because your current stress level is high, be careful about changing your dog's food intake."

[0322] Example 2: Exercise advice

[0323] If a user's dog has recently shown a decline in activity, sensors collect activity data and send it to a server. The server analyzes the data and uses a generative AI model to calculate the optimal amount of exercise. Results such as "recommended two 30-minute walks per day or free exercise at a dog park" are generated and notified to the user through the app. An emotion engine is also used to add encouraging messages based on the user's emotional state.

[0324] Example 3: Detecting abnormal behavior while away from home

[0325] If the dog swallows something or exhibits abnormal behavior while the user is away, the sensor collects the data and sends it to the server. The server immediately analyzes it and generates an alert notification if it detects abnormal behavior. The application then sends a push notification with detailed information to the user, allowing the user to take necessary measures. The emotion engine also provides reminders and support messages to reduce the user's impatience and anxiety.

[0326] In this way, the system of the present invention manages the animal's health condition in detail and in real time, supporting the owner in taking prompt and appropriate action. By integrating an emotion engine, it becomes possible to provide information that takes into account the user's emotional state, thereby realizing even greater user support.

[0327] The processing flow will be explained below.

[0328] Data Collection Phase

[0329] Device (sensor, app) side

[0330] Step 1: Monitoring data with sensors

[0331] The sensors measure the animals' activity levels, sleep patterns and food intake in real time.

[0332] The measured data is temporarily stored inside the sensor.

[0333] Step 2: Prepare your data for transfer

[0334] The sensor prepares to send the collected data to the app at regular intervals.

[0335] Set up the communication protocol for data transmission and format the data appropriately.

[0336] Step 3: Sending data

[0337] The app receives the data sent from the sensor and temporarily stores it in the internal storage.

[0338] Batch processing is performed at regular intervals and the data is sent to the server.

[0339] Data transmission and storage

[0340] Server side

[0341] Step 4: Receiving the data

[0342] The server has an API for receiving data sent from the app.

[0343] The received data is temporarily stored in a buffer.

[0344] Step 5: Save your data

[0345] The server pre-processes and formats the buffered data.

[0346] The preprocessed data is stored in the database.

[0347] Data analysis

[0348] Server side

[0349] Step 6: Preprocessing the data

[0350] The server retrieves the data that needs to be analyzed from the database.

[0351] The acquired data is filled in with missing values ​​and noise is removed, and it is then formatted in a form suitable for analysis.

[0352] Step 7: Input to the generative AI model

[0353] The server inputs the preprocessed data into a generative AI model.

[0354] The model analyzes the animal's behavioral patterns and extracts features.

[0355] Step 8: Generate analysis results

[0356] The generative AI model generates evaluation results such as optimizing food intake, giving exercise advice, and detecting abnormal behavior.

[0357] Store the generated results in a database.

[0358] Emotion engine integration

[0359] Server side

[0360] Step 9: Collect emotion data

[0361] The server receives the user's emotion data from the app.

[0362] Emotional data is collected in real time based on the user's facial expressions, voice, text input, etc.

[0363] Step 10: Analyze the sentiment data

[0364] The server analyzes the user's emotion data using an emotion engine.

[0365] The analysis results (stress level, emotional state) are stored in a well-being database.

[0366] Step 11: Integrating Emotional and Health Data

[0367] The server integrates the analysis results of the generative AI model and the evaluation results of the emotion engine to adjust the content of the notification.

[0368] The integration results are stored in a database and an optimized notification is generated for the user.

[0369] Notification of results and actions

[0370] Server side

[0371] Step 12: Prepare for notifications

[0372] The server periodically checks the analysis results and extracts information that should be notified to the user.

[0373] Urgent information will be given priority and immediate notification will be prepared.

[0374] Step 13: Sending notifications

[0375] The server sends notifications to the user using an appropriate notification system (e.g., Firebase Cloud Messaging).

[0376] App (device) side

[0377] Step 14: Receive notifications

[0378] The app receives notifications sent from the server.

[0379] Received notifications are displayed to the user in a visually understandable format.

[0380] User Actions

[0381] User side

[0382] Step 15: Review and respond to notifications

[0383] The user can check the notification content through the app and take the necessary action.

[0384] Adjust food and create exercise plans based on optimal feeding amounts.

[0385] Step 16: Emotionally Based Responses

[0386] The user can implement stress management and emotional support by referring to the advice provided by the emotion engine.

[0387] For example, if you have high stress levels, try relaxation techniques.

[0388] Step 17: Online consultation with your veterinarian

[0389] If necessary, users can use the app to book an online consultation with a veterinarian.

[0390] Online consultations are conducted via video calls and text chats.

[0391] This is the specific processing flow of the program. This process manages the animal's health condition in real time and supports the owner in taking appropriate action. By combining it with an emotion engine, it is possible to provide information that takes the user's emotional state into consideration.

[0392] Example 2

[0393] 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."

[0394] Currently, animal health management relies heavily on owner observation, making it difficult to manage based on objective data. Additionally, while the owner's emotional state can affect animal health management, no system exists that fully takes this into account. This can lead to delayed appropriate responses or inappropriate management. Furthermore, optimizing exercise and dietary intake requires detailed data analysis, which is unrealistic to perform manually.

[0395] The identification process 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 means for collecting animal behavior data using a sensor, means for transmitting the collected data to the server via a terminal, means for performing data refinement processing in the server and then storing the data in a database, means for analyzing the data using a generative AI model and evaluating the animal's health condition and behavior, means for notifying the user of the evaluation results, means for collecting the user's emotion data and analyzing it using an emotion engine, and means for personalizing and notifying the evaluation results based on the emotion analysis results. This makes it possible to manage the animal's health condition in detail and in real time, and to provide personalized responses that also take the owner's emotional state into consideration.

[0396] The "sensor" is a device for collecting animal behavior data in real time, and is equipped with multiple functions such as an acceleration sensor, gravity sensor, and GPS.

[0397] A "terminal" is a relay device for transmitting collected data to a server, and has functions such as encrypting data and maintaining a transmission log.

[0398] A "server" is a computer system that processes, stores, and analyzes received data, and is responsible for running generative AI models and emotion engines.

[0399] "Data refinement processing" is a process for improving the quality of collected data by removing outliers and standardizing the format.

[0400] A "database" is a system for efficiently storing and accessing refined data and analytical results.

[0401] A "generative AI model" is an artificial intelligence model that analyzes behavioral data based on machine learning algorithms to evaluate an animal's health and behavioral patterns.

[0402] The "emotion engine" is a system that collects and analyzes emotional data from users' facial expressions, voice, text input, etc., and is responsible for assessing the user's stress level and emotional state.

[0403] "Evaluation results" refer to an assessment of the animal's health and behavioral patterns, as well as the user's emotional state, based on data analyzed by the generative AI model and emotion engine.

[0404] "Personalization" means adjusting information and service content according to each user's characteristics and emotional state.

[0405] The present invention is a system that collects animal behavior data and analyzes it using a generative AI model and an emotion engine. The present invention manages the animal's health by collecting data using sensors, transmitting it to a server for analysis, and providing information based on the results and the user's emotions. Below, specific embodiments of the present invention are described.

[0406] Overall system configuration

[0407] sensor

[0408] On the terminal (sensor) side, various sensors attached to the animal's collar or harness monitor behavioral data such as activity level, sleep patterns, and food intake in real time. Hardware such as accelerometers, gravity sensors, and GPS are used.

[0409] application

[0410] The application periodically compiles data collected from sensors and sends it to a server via the Internet. This data is encrypted to ensure security. The application records the success and failure of transmissions in a log and notifies the user if an error occurs.

[0411] server

[0412] The server temporarily stores the received data in a buffer and then performs a data refinement process, which involves removing outliers and converting formats. The refined data is then stored in a database. The data is then analyzed by a generative AI model, which analyzes behavioral patterns, detects anomalies, and evaluates health status, and stores the results in a database.

[0413] Emotion Engine

[0414] The emotion engine collects and analyzes emotional data from users' facial expressions, voice, and text input in real time. The results of the emotion analysis evaluate the user's stress level and emotional state and are stored in a well-being database. This makes it possible to integrate animal health data with emotional data.

[0415] Notifications and Actions

[0416] The server combines the results of the animal's health data analysis with the user's emotional data and generates appropriate notifications. These notifications are sent to the user via push notifications, email, social media, etc. The application displays these notifications to the user and supports them in taking necessary actions. Based on the information provided through the application, users can adjust the amount of food their animal eats and create exercise plans. They can also manage their own stress by taking advice from the emotion engine.

[0417] Specific examples

[0418] Example 1: Optimizing food portion size

[0419] If a user's dog has recently lost its appetite, the sensor collects dietary data and sends it to the server. The server then uses a generative AI model to generate a recommendation such as, "200 grams of food per day is appropriate for a 10 kg dog." In addition, the emotion engine provides advice such as, "Because your current stress level is high, be careful about changing your dog's food intake."

[0420] Example prompt: Analyze your dog's recent feeding data and suggest appropriate feeding amounts. The advice should also take into account the user's emotional state.

[0421] Example 2: Exercise advice

[0422] If a user's dog has recently shown a decline in its activity level, sensors collect activity data and send it to the server. The server then uses a generative AI model to calculate the optimal amount of exercise and recommends two 30-minute walks per day or free exercise at a dog park. An emotion engine is also used to add encouraging messages based on the user's emotional state.

[0423] Example prompt: Based on the dog's exercise data, suggest the optimal amount and specific exercise method. Please also take into account the user's emotional state.

[0424] Example 3: Detecting abnormal behavior while away from home

[0425] If the dog exhibits abnormal behavior while the user is away, the sensor collects the data and sends it to the server. The server immediately analyzes the data and generates an alert if it detects abnormal behavior. The application then sends a push notification to the user with detailed information, allowing them to take necessary measures. The emotion engine also provides advice to reduce the user's impatience and anxiety.

[0426] Example prompt: Detect abnormal dog behavior while you're away and immediately generate an alert to notify the user. Include a message to ease the user's anxiety.

[0427] As described above, the system of the present invention manages the health status of animals in detail and in real time, and enables personalized measures that also take into account the user's stress level.

[0428] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0429] Step 1:

[0430] Data collection

[0431] Subject: Terminal (sensor)

[0432] Sensors attached to the device monitor the animal's activity levels, sleep patterns, food intake, and other behavioral data in real time.

[0433] Input: Raw data from sensors (acceleration, gravity, position).

[0434] Specific behavior:

[0435] The accelerometer detects animal movements.

[0436] Gravity sensors are used to determine the animal's position.

[0437] GPS sensors track the location of animals.

[0438] Output: Collected behavioral data.

[0439] Step 2:

[0440] Data transmission and storage

[0441] Subject: Terminal (application)

[0442] The application compiles the data collected from the sensors at regular intervals (e.g., every 5 minutes) and sends it to a server via the Internet.

[0443] Input: Behavioral data collected from sensors.

[0444] Specific behavior:

[0445] The data is encrypted.

[0446] Establish communication with the server and send data.

[0447] The transmission result is recorded as a log, and if it fails, a retransmission attempt is made.

[0448] Output: Behavioral data sent to the server.

[0449] Step 3:

[0450] Data refinement

[0451] Subject: Server

[0452] The server temporarily stores the received data in a buffer and performs a data refinement process.

[0453] Input: Raw behavioral data sent from the device.

[0454] Specific behavior:

[0455] Outlier detection and removal.

[0456] Format conversion and data standardization.

[0457] Correcting time lag.

[0458] Output: Refined behavioral data.

[0459] Step 4:

[0460] Data storage

[0461] Subject: Server

[0462] The server stores the refined data in a database.

[0463] Input: Refined behavioral data.

[0464] Specific behavior:

[0465] Inserts data into the database.

[0466] Data saving confirmation process.

[0467] Output: Behavioral data stored in a database.

[0468] Step 5:

[0469] Data analysis

[0470] Subject: Server

[0471] The server inputs the behavioral data stored in the database into the generative AI model and performs analysis.

[0472] Input: Behavioral data stored in a database.

[0473] Specific behavior:

[0474] Load behavioral data into a generative AI model.

[0475] Machine learning algorithms are applied to analyze behavioral patterns, detect anomalies, and assess health status.

[0476] Output: Analysis results (e.g., health status assessment results).

[0477] Step 6:

[0478] Emotional data collection and analysis

[0479] Subject: Server

[0480] The server uses an emotion engine to collect and analyze emotional data from the user's facial expressions, voice, text input, etc.

[0481] Input: User's facial expression data, voice data, and text data.

[0482] Specific behavior:

[0483] Collect emotional data from input devices such as cameras and microphones.

[0484] Input data into the emotion engine and perform analysis.

[0485] Output: Sentiment analysis results (e.g. stress level, emotional state).

[0486] Step 7:

[0487] Consolidating assessment results and generating personalized notifications

[0488] Subject: Server

[0489] The server integrates the analysis results from the generative AI model and the emotion engine to generate notifications optimized for the user.

[0490] Input: Analysis results of the generative AI model, analysis results of the emotion engine.

[0491] Specific behavior:

[0492] Integrating health and emotional assessment results.

[0493] Generate notifications (e.g., suggestions for optimal exercise and dietary intake, warnings about abnormal behavior).

[0494] Output: Personalized notification.

[0495] Step 8:

[0496] Notifications and User Actions

[0497] Subject: Server and terminal (application)

[0498] The server generates a notification and sends it to the device, where the application displays it to the user, who can then take appropriate action based on the notification content.

[0499] Enter: Personalized Notifications.

[0500] Specific behavior:

[0501] Send notifications (push notifications, email, social media).

[0502] Notification display in the application.

[0503] The user takes action based on the notification (e.g., adjusting food intake, creating an exercise plan).

[0504] Output: User actions (e.g., changing food intake, starting exercise), emotional stability.

[0505] (Application example 2)

[0506] 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."

[0507] In modern society, pet health management and safety measures are important issues for pet owners. However, it has been difficult to accurately manage pet behavior data and health status in real time and quickly detect abnormal behavior. Furthermore, there has been a lack of appropriate notifications and advice that take into account the owner's emotional state, which can increase stress for the owner. Therefore, there is a need for a system that can accurately evaluate pet health and behavior, quickly detect abnormal behavior, and provide appropriate information to the owner.

[0508] The identification processing by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting animal behavior data using a sensor, means for transmitting the collected data to the server, means for analyzing the data using a generative AI model in the server and evaluating the animal's health condition and behavior, means for notifying the user of the evaluation results, means for detecting abnormal behavior, means for notifying the user of the results of the abnormal behavior detection, an emotion engine for evaluating the user's emotional state, and means for optimizing the notification content based on the evaluation results by the emotion engine. This enables real-time management of the pet's health condition and behavior and rapid detection of abnormal behavior, and makes it possible to provide the owner with appropriate notifications and advice that take the emotional state into consideration.

[0509] "Animal behavior data" refers to various data related to animal behavior, such as animal activity levels, location information, and abnormal behavior.

[0510] A "sensor" is a device that is attached to an animal's harness and is used to collect behavioral data about the animal.

[0511] "Server" refers to a computer system that analyzes collected data and manages and stores evaluation results.

[0512] A "generative AI model" is an artificial intelligence algorithm that analyzes an animal's health and behavior based on collected data.

[0513] An "emotion engine" is a system for assessing a user's emotional state and optimizing notification content based on that.

[0514] "Abnormal behavior" refers to peculiar behavior of an animal that deviates from its normal behavioral pattern.

[0515] "Notification means" refers to a method or device for notifying the user of the analysis results or abnormal behavior detection results.

[0516] "Dietary data" refers to data relating to an animal's dietary intake and eating patterns.

[0517] "Movement data" refers to data that indicates quantities and patterns related to animal movement.

[0518] "Optimization" is the adjustment of data and processes to achieve the best results for a particular purpose.

[0519] This invention is a system that collects animal behavior data and analyzes it using a generative AI model and emotion engine to manage animal health and abnormal behavior, and provides appropriate notifications to users.

[0520] Sensors and Data Collection

[0521] The sensors are attached to the animal's clothing (such as a collar) and collect real-time data on activity, location, abnormal behavior, etc. These sensors include an accelerometer, gravity sensor, and GPS.

[0522] Data transmission and storage

[0523] The device (smartphone app) periodically sends data collected from the sensors to a server. The data is encrypted and sent securely via the Internet. The server temporarily stores the received data, performs any preprocessing necessary for analysis, and then stores it in a database.

[0524] Data analysis

[0525] The server analyzes the behavioral data stored in the database using a generative AI model. The generative AI model performs the following processes:

[0526] Identifying behavioral patterns

[0527] Abnormal behavior detection

[0528] Health assessment

[0529] The server stores the analysis results in a database and makes them available via a user interface as needed.

[0530] Emotion engine integration

[0531] The server integrates an emotion engine to analyze the user's emotion data. This emotion data is analyzed in real time based on the user's facial expressions, voice, text input, etc. The emotion engine evaluates the user's stress level and emotional state and optimizes the notification content based on the results.

[0532] Notification of results and actions

[0533] The server generates appropriate notifications for users based on the analysis results and abnormal behavior detection results. The notification system operates in real time, and immediate notifications are sent for matters of high urgency. The content of the notifications is communicated to users via push notifications, email, and social media, and the content of the notifications is optimized based on the evaluation results of the emotion engine.

[0534] Specific examples

[0535] Dog Abnormal Behavior Detection: When a dog barks excessively or exhibits abnormal behavior, sensors collect the data and send it to a server, which uses a generative AI model to detect abnormal behavior and immediately notify the user.

[0536] Optimizing food intake: Collecting dog food data and using a generative AI model to calculate the optimal food intake. The results are then communicated to the user, enabling appropriate dietary management.

[0537] Emotional state-based notifications: If the emotion engine assesses that the user is feeling stressed, the notification content will be optimized accordingly and advice will be provided to reduce the user's stress.

[0538] Prompt Sentence Examples

[0539] "Please use the generative AI model to analyze abnormal behavior based on the following data. Generate notification content based on activity data, location data, behavior data, and the results, and notify the user immediately if abnormal behavior is detected."

[0540] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0541] Step 1:

[0542] The device (smartphone app) collects behavioral data from sensors attached to the animal's harness. The sensors measure the animal's activity level, location information, abnormal behavior, etc. in real time and send the data to the device. The input data is raw data collected by the various sensors, and the output is data temporarily stored on the device.

[0543] Step 2:

[0544] The device periodically sends the collected data to a server. The data is encrypted and securely transferred over the Internet. The input is the behavioral data stored on the device, and the output is the encrypted data sent to the server. This process uses an Internet connection and a data encryption algorithm.

[0545] Step 3:

[0546] The server temporarily stores the received data in a buffer memory. The input data is the encrypted behavioral data, and the output is the decrypted original data. The server decrypts the data using a decryption algorithm.

[0547] Step 4:

[0548] The server performs preprocessing on the decrypted data, which includes data shaping, missing value imputation, outlier removal, etc. The input data is the decrypted raw data, and the output is the preprocessed clean data. The server uses preprocessing algorithms and data shaping functions.

[0549] Step 5:

[0550] The server inputs the preprocessed data into the generative AI model for analysis. The generative AI model identifies behavioral patterns from the data, detects abnormal behavior, and evaluates health status. The input data is the preprocessed data, and the output is the analysis results. The server performs data analysis using the generative AI model.

[0551] Step 6:

[0552] The server stores the analysis results in a database for further processing. The input data are the analysis results and the output is the stored data. The server uses a database management system to store the data.

[0553] Step 7:

[0554] The server collects the user's emotional data and analyzes it using an emotion engine. The emotional data can be obtained from the user's facial expressions, voice, text input, etc. The input data is the emotional data, and the output is the evaluation result of the emotional state. The server uses an emotion analysis algorithm.

[0555] Step 8:

[0556] The server optimizes the notification content to be provided to the user based on the evaluation results of the emotion engine. The input data are the evaluation results and analysis results of the emotional state, and the output is the optimized notification content. The server generates the notification content by integrating the evaluation results and analysis results of the emotion engine.

[0557] Step 9:

[0558] The server sends the optimized notification content to the user. The notification is sent via push notification, email, or SNS. The input data is the optimized notification content, and the output is the notification message to the user. The server sends the message using the notification system.

[0559] 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.

[0560] 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.

[0561] 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.

[0562] [Second embodiment]

[0563] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0564] 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.

[0565] 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).

[0566] 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.

[0567] 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.

[0568] 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).

[0569] 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.

[0570] 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.

[0571] 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.

[0572] 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.

[0573] 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.

[0574] 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."

[0575] The present invention is a system that collects behavioral data of animals, particularly dogs, and analyzes it using generative artificial intelligence (generative AI model). The present invention manages the health of animals by collecting data using sensors, transmitting it to a server for analysis, and providing the results to a user. Specific embodiments of the present invention will be described below.

[0576] Overall overview

[0577] The system consists of the following main components:

[0578] 1. Sensors that collect animal behavior data

[0579] 2. An application that sends data to a server

[0580] 3. Server that analyzes data and generates AI models

[0581] 4. Interface for notifying users of evaluation results

[0582] Sensors and Data Collection

[0583] Terminal (sensor) side:

[0584] Sensors attached to the animal's collar or harness monitor real-time behavioral data such as activity levels, sleep patterns, and food intake. These sensors combine accelerometers, gravity sensors, and GPS. Data is periodically sent to a server via an application.

[0585] Data transmission and storage

[0586] App (device) side:

[0587] The application periodically collects data from the sensors and sends it to a server via the Internet. The data is encrypted to ensure security. The application records the success or failure of data transmission and notifies the user if there is a problem.

[0588] Server side:

[0589] The server temporarily stores the received data in a buffer and then refines it. The refined data is then stored in a database for subsequent analysis. The database is designed for query efficiency, allowing for quick access even to large amounts of data.

[0590] Data analysis

[0591] Server side:

[0592] The server inputs the behavioral data stored in the database into a generative AI model for analysis. The generative AI model identifies behavioral patterns and detects anomalies, generating results such as optimizing food intake, suggesting exercise amounts, and evaluating health status. These analysis results are then stored back in the database and made available via the user interface.

[0593] Notification of results and actions

[0594] Server side:

[0595] The server generates appropriate notifications for users based on the analysis results. The notification system operates in real time, and immediate notifications are sent for urgent matters. The content of the notifications is conveyed to users via push notifications, email, or social media.

[0596] App (device) side:

[0597] The application displays notifications and advice sent from the server to the user. Notifications include suggestions for optimal meal portions, exercise advice, and warnings about abnormal behavior while away from home. The application provides an interface for the user to take action in response to these notifications.

[0598] User Actions

[0599] User side:

[0600] Based on the information provided through the app, users can adjust their pet's feeding and exercise schedules, receive alerts about abnormal behavior while away from home, take steps to respond quickly, and, if necessary, use the application to book an online consultation with a veterinarian to receive appropriate medical treatment.

[0601] Specific examples

[0602] Example 1: Optimizing food portion size

[0603] If a user's dog has recently shown a decreased appetite, the sensor collects food data and sends it to a server. The server then uses a generative AI model to calculate optimal feeding amounts and generate recommendations, such as "200 grams of food per day is appropriate for a 10kg dog." The application then notifies the user of this information, allowing them to adjust their feeding accordingly.

[0604] Example 2: Exercise advice

[0605] If the user's dog has recently shown a decline in exercise, the sensor collects activity data and sends it to the server. The server analyzes the data and uses a generative AI model to calculate the optimal amount of exercise. The result, such as "Two 30-minute walks per day or free exercise at a dog park is recommended," is generated and notified to the user via the app. The user can then create an exercise plan based on this information.

[0606] Example 3: Detecting abnormal behavior while away from home

[0607] If the dog swallows something or exhibits abnormal behavior while the user is away, the sensor will collect the data and send it to the server. The server will immediately analyze it and generate an alert notification if it detects abnormal behavior. The application will then send a push notification to the user with detailed information, allowing the user to take necessary measures.

[0608] In this way, the system of the present invention manages the health status of animals in detail and in real time, supporting owners in responding quickly and appropriately.

[0609] The processing flow will be explained below.

[0610] Data Collection Phase

[0611] Device (sensor, app) side

[0612] Step 1: Monitoring data with sensors

[0613] The sensors measure the animals' activity levels, sleep patterns and food intake in real time.

[0614] The measured data is temporarily stored inside the sensor.

[0615] Step 2: Prepare your data for transfer

[0616] The sensor prepares to send the collected data to the app at regular intervals.

[0617] Set up the communication protocol for data transmission and format the data appropriately.

[0618] Step 3: Sending data

[0619] The app receives the data sent from the sensor and temporarily stores it in the internal storage.

[0620] Batch processing is performed at regular intervals and the data is sent to the server.

[0621] Data transmission and storage

[0622] Server side

[0623] Step 4: Receiving the data

[0624] The server has an API for receiving data sent from the app.

[0625] The received data is temporarily stored in a buffer.

[0626] Step 5: Save your data

[0627] The server pre-processes and formats the buffered data.

[0628] The preprocessed data is stored in the database.

[0629] Data analysis

[0630] Server side

[0631] Step 6: Preprocessing the data

[0632] The server retrieves the data that needs to be analyzed from the database.

[0633] The acquired data is filled in with missing values ​​and noise is removed, and it is then formatted in a form suitable for analysis.

[0634] Step 7: Input to the generative AI model

[0635] The server inputs the preprocessed data into a generative AI model (e.g., GPT).

[0636] The model analyzes the animal's behavioral patterns and extracts features.

[0637] Step 8: Generate analysis results

[0638] The generative AI model generates evaluation results such as optimizing food intake, giving exercise advice, and detecting abnormal behavior.

[0639] Store the generated results in a database.

[0640] Notification of results and actions

[0641] Server side

[0642] Step 9: Prepare for notifications

[0643] The server periodically checks the analysis results and extracts information that should be notified to the user.

[0644] Information with high urgency will be given priority.

[0645] Step 10: Sending notifications

[0646] The server uses an appropriate notification system (e.g., Firebase Cloud Messaging) to send a notification to the user.

[0647] App (device) side

[0648] Step 11: Receive notifications

[0649] The app receives notifications sent from the server.

[0650] Received notifications are displayed to the user in a visually understandable format.

[0651] User side

[0652] Step 12: Review and respond to notifications

[0653] Users can check the notification content through the app and take necessary action.

[0654] For example, it adjusts food and creates exercise plans based on optimal feeding amounts.

[0655] Step 13: Online consultation with a veterinarian

[0656] If necessary, users can use the app to book an online consultation with a veterinarian.

[0657] Online consultations are conducted via video calls and text chats.

[0658] This is the specific flow of the program's processing. This process manages the animal's health condition in real time and supports the owner in taking appropriate action.

[0659] Example 1

[0660] 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."

[0661] Currently, many pet owners face the challenge of understanding their pets' health and behavior in detail and in real time. Manually recording behavioral data and assessing health status is time-consuming and often requires specialized knowledge. Furthermore, standards for calculating appropriate amounts of food and exercise are often unclear, making it difficult for pet owners to properly manage their pets. This leads to inadequate health management for their animals and ultimately increases the risk of ill health.

[0662] 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.

[0663] In this invention, the server

[0664] means for transmitting the animal's behavior data to a server via an application;

[0665] a means for temporarily storing the data, subjecting the data to a refinement process, and storing the data in a database;

[0666] A means to analyze data using generative AI models to assess animal health and behavior;

[0667] This enables the collection, transmission, and analysis of animal behavior data in real time. Based on the analysis results, users can receive specific advice, develop appropriate dietary and exercise plans, and respond quickly to abnormal behavior.

[0668] "Animal behavioral data" refers to information about the activities that animals engage in in their daily lives, and specifically includes data such as activity levels, sleep patterns, and food intake.

[0669] The term "sensor" refers to a device that detects physical or environmental conditions and converts them into data, and in the present invention includes an acceleration sensor or GPS that is attached to an animal's collar, etc.

[0670] "Application" refers to software that runs on the device and transmits data collected from the sensor to the server.

[0671] "Server" refers to a computer system for receiving, storing, and analyzing data over a network.

[0672] "Temporary storage" refers to data that is temporarily stored in a storage device before being stored in a permanent database.

[0673] "Refining" refers to the process of correcting duplications and missing data in the collected data and preparing it in a format suitable for analysis.

[0674] A "database" refers to a collection of data that is structured to store information systematically and enable quick search and access.

[0675] A "generative AI model" is an artificial intelligence model that uses pre-trained algorithms to analyze new data and make predictions or suggestions.

[0676] "Analysis" refers to the act of making inferences and calculations based on collected data to assess the health and behavior of animals.

[0677] "Evaluation results" refer to conclusions about the health and behavior of animals drawn through analysis.

[0678] "Notification" refers to the act of transmitting information to inform users of the evaluation results, and includes push notifications, emails, social media, etc.

[0679] "User interface" refers to the means or screens that allow a user to interact with a system, and is provided through an application.

[0680] The present invention is a system that collects behavioral data of animals, particularly dogs, and analyzes it using a generative AI model. This system collects data using sensors, transmits it to a server for analysis, and provides the results to a user to manage the health of the animal. Below, specific embodiments of the present invention are described.

[0681] Hardware and software used

[0682] Sensor (terminal) side:

[0683] The sensors, which are attached to the animal's collar or harness, combine accelerometers, gravity sensors, GPS, and other sensors to monitor the animal's activity, sleep patterns, food intake, and other behavioral data in real time.

[0684] Application (device) side:

[0685] An application installed on a smartphone or tablet collects data from the sensors and periodically transmits it to a server over the Internet using the encrypted HTTPS protocol.

[0686] Server side:

[0687] The server is a high-performance computing system that temporarily buffers received data, then refines and stores it in a database. The database on the server is designed for query efficiency, allowing for quick access to large amounts of data. Additionally, generative AI models (e.g., deep learning models for anomaly detection and pattern recognition) are installed and used for data analysis.

[0688] Data processing and calculation

[0689] Data collection and transmission:

[0690] The sensors monitor animal behavior data in real time and transmit it to a smartphone application, which then compiles the data, sends it to a server, and logs the success or failure of the transmission.

[0691] Data storage and refinement:

[0692] The server temporarily stores the received data in a buffer and performs refinement processes such as deleting duplicate data and filling in missing data. The refined data is then stored in a database such as MySQL.

[0693] Data Analysis:

[0694] The server uses the generative AI model to analyze the behavioral data stored in the database, including identifying activity patterns, detecting abnormal behavior, and suggesting optimal diet and exercise amounts. The analysis results are then stored back in the database and made available through the user interface.

[0695] Notification of results:

[0696] The server generates notifications for users based on the analysis results. The notification system operates in real time, and immediate notifications are sent to users for urgent matters. Notifications are sent to users via push notifications, email, and social media.

[0697] Specific examples

[0698] Example 1: Optimizing food portion size

[0699] If a user's dog has recently shown a decreased appetite, the sensor collects food data and sends it to a server. The server then uses a generative AI model to calculate the optimal amount of food, suggesting, for example, that a 10kg dog should eat 200g of food per day. The app then notifies the user of this information, allowing them to adjust their dog's food intake accordingly.

[0700] Example prompt: "What is the appropriate daily amount of food for a dog weighing 10 kg?"

[0701] Example 2: Exercise advice

[0702] If the user's dog has recently shown a decline in exercise, the sensor collects activity data and sends it to the server. The server analyzes the data and uses a generative AI model to calculate the optimal amount of exercise. The result is "recommended to take two 30-minute walks per day or exercise freely at a dog park," and the result is notified to the user via the application. The user can then create an exercise plan based on this.

[0703] Example prompt: "What activities do you recommend to increase my dog's exercise?"

[0704] Example 3: Detecting abnormal behavior while away from home

[0705] If the dog exhibits abnormal behavior while the user is away, the sensor collects the data and sends it to the server. The server immediately analyzes it and generates an alert notification if abnormal behavior is detected. The application then sends a push notification to the user with detailed information, allowing them to take prompt action.

[0706] Example prompt: "What is the appropriate course of action if my dog ​​exhibits abnormal behavior while I'm away?"

[0707] In this way, the system of the present invention manages the health status of animals in detail and supports owners in responding promptly and appropriately.

[0708] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0709] Step 1: Data collection

[0710] Terminal (sensor) side:

[0711] The sensors collect real-time behavioral data of the animals. Specifically, an accelerometer measures activity and posture at rest, and a GPS acquires location information. This data is collected from the sensors and recorded at regular intervals.

[0712] Input: Animal activity data (e.g., activity level, location information)

[0713] Output: raw data collected

[0714] Step 2: Send data

[0715] App (device) side:

[0716] The application periodically collects data collected from sensors and sends it to a server via the Internet. The encrypted HTTPS protocol is used for transmission. The success or failure of the transmission is recorded in a log. For example, if the transmission is successful, a "transmission completed" log is recorded, and if it fails, a "retransmission" flag is set.

[0717] Input: Raw data collected

[0718] Output: Data transferred to the server

[0719] Step 3: Temporarily store and refine data

[0720] Server side:

[0721] The server temporarily stores the received data in a buffer and performs refinement processes such as removing duplicate data and filling in missing data. Duplicate data is removed using SQL queries, and missing GPS data is filled in using a fill-in algorithm. The refined data is then stored in a database such as MySQL.

[0722] Input: Raw data transferred to the server

[0723] Output: Refinement data stored in a database

[0724] Step 4: Data analysis

[0725] Server side:

[0726] The server inputs the refined data into a generative AI model for analysis. The generative AI model identifies behavioral patterns and detects anomalies, and generates results such as recommendations for optimizing food intake and exercise. The analysis process is performed using a Python script.

[0727] Input: Refining data stored in the database

[0728] Output: Analysis results (e.g., recommendations for optimal food intake and exercise)

[0729] Step 5: Notification of results

[0730] Server side:

[0731] The server converts the analysis results into notifications and sends them to the user. For example, a push notification containing information such as a decrease in the dog's activity level or a recommendation for optimal feeding is generated. These notifications are sent to the user in real time.

[0732] Input: Analysis results

[0733] Output: Notification message (e.g. push notification, email)

[0734] Step 6: Display in the user interface

[0735] App (device) side:

[0736] The application displays notifications and advice sent from the server to the user, such as "200 grams of food per day" or "Take two 30-minute walks per day." Users can tap to view more information.

[0737] Input: Notification message

[0738] Output: Notifications and advice displayed on the user interface

[0739] Step 7: User Actions

[0740] User side:

[0741] Users can take action based on the provided notifications, such as adjusting the amount of food to the suggested 200 grams per day and creating a daily walking schedule. If they receive a notification of abnormal behavior, they can consult with a veterinarian through the app's online appointment system for prompt action.

[0742] Input: User interface notifications and advice

[0743] Output: Actual behavior (e.g., adjusting food intake, executing exercise plan)

[0744] (Application example 1)

[0745] 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."

[0746] In modern society, pet health management is an important issue for pet owners. Detecting abnormal pet behavior and responding quickly when the owner is away is particularly important for maintaining the pet's safety and health. However, existing technology does not adequately provide a system that can monitor pet behavior in real time, detect abnormal behavior, and provide prompt notification. Therefore, the present invention aims to provide a system that can detect abnormal pet behavior in real time while the owner is away and promptly notify the owner.

[0747] 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.

[0748] In this invention, the server includes means for collecting animal behavior data using a sensor, means for transmitting the collected data to the server, means for analyzing the data using a generative AI model in the server and evaluating the health condition and behavior of the animal, means for notifying the user of the evaluation results, and means for detecting abnormal behavior of animals, including dogs, while the user is away and notifying the user in real time. This makes it possible to quickly detect abnormal behavior of pets and notify the owner in real time.

[0749] "Animal" is a broad term that refers to any pet or livestock animal, including dogs.

[0750] "Behavioral data" is a general term for various data that indicate an animal's health and behavior, such as its activity level, sleep patterns, and food intake.

[0751] "Sensors" are devices used to collect animal behavioral data, and include acceleration sensors, gravity sensors, GPS, etc.

[0752] "Server" means a computer system that stores, analyzes, and manages collected data.

[0753] A "generative AI model" is a machine learning model used to analyze collected behavioral data and evaluate the health and behavior of animals.

[0754] "Means for assessing health and behavior" refers to a method for analyzing behavioral data using a generative AI model and assessing the health and behavior of animals based on the results.

[0755] "Means of notifying users" refers to methods for providing information to users based on the analysis results, and includes means such as push notifications, emails, and social media.

[0756] "Abnormal behavior" refers to animal behavior that deviates from normal patterns, including, for example, accidental ingestion, abnormal wandering, and anxiety.

[0757] "Real-time" refers to data processing and notification occurring almost immediately.

[0758] "Away" refers to the time when the user is away, and specifically refers to the time when the animal is alone.

[0759] Overall overview

[0760] The system of the present invention consists of the following main components: a sensor that collects animal behavior data, a means for transmitting the data to a server, a generative AI model that analyzes the behavior data on the server, a means for notifying the user of the analysis results, and a means for detecting abnormal behavior in real time.

[0761] Sensors and Data Collection

[0762] Terminal (sensor) side:

[0763] Sensors attached to the animal's collar or harness monitor real-time behavioral data such as activity levels, sleep patterns, and food intake. These sensors combine accelerometers, gravity sensors, and GPS. The collected data is periodically sent to a server via an application.

[0764] Data transmission and storage

[0765] App (device) side:

[0766] The application periodically collects data from the sensors and sends it to a server via the Internet. The data is encrypted to ensure security. The application logs the success or failure of data transmission and notifies the user if there is a problem.

[0767] Server side:

[0768] The server temporarily stores the received data in a buffer and then performs a data refinement process. The refined data is stored in a database and used for subsequent analysis processes. The database is designed with query efficiency in mind, allowing for quick access even to large amounts of data.

[0769] Data analysis

[0770] Server side:

[0771] The server inputs the behavioral data stored in the database into a generative AI model for analysis. The generative AI model identifies behavioral patterns and detects anomalies, and generates results such as optimizing food intake, suggesting exercise amounts, and evaluating health status. The analysis results are then saved back into the database and made available in the user interface.

[0772] Notification of results and actions

[0773] Server side:

[0774] The server generates appropriate notifications for users based on the analysis results. The notification system operates in real time, and immediate notifications are sent for urgent matters. Notifications are sent to users via push notifications, email, or social media.

[0775] App (device) side:

[0776] The application displays notifications and advice sent from the server to the user, such as recommendations for optimal meal size, exercise advice, and warnings about abnormal behavior while away from home. It also provides an interface for the user to take action based on these notifications.

[0777] User Actions

[0778] User side:

[0779] Based on the information provided through the app, users can adjust their animal's feeding and exercise schedule, take steps to respond quickly if they receive alerts about abnormal behavior while away from home, and, if necessary, use the application to schedule an online consultation with a veterinarian to obtain appropriate medical treatment.

[0780] Specific examples

[0781] Example 1: Optimizing food portion size

[0782] If a user's dog has recently shown a decreased appetite, the sensor collects food data and sends it to a server. The server then uses a generative AI model to calculate optimal feeding amounts and generate recommendations, such as "200 grams of food per day is appropriate for a 10kg dog." The application then notifies the user of this information, allowing them to adjust their feeding accordingly.

[0783] Example 2: Exercise advice

[0784] If the user's dog has recently shown a decline in exercise, the sensor collects activity data and sends it to the server. The server then uses a generative AI model to calculate the optimal amount of exercise, generating a recommendation such as "two 30-minute walks per day or free exercise at a dog park." The result is then sent to the user via the app, allowing the user to create an exercise plan based on this information.

[0785] Example 3: Detecting abnormal behavior while away from home

[0786] If the dog swallows something or exhibits abnormal behavior while the user is away, the sensor will collect the data and send it to the server. The server will immediately analyze it and generate an alert notification if it detects abnormal behavior. The application will then send a push notification to the user with detailed information, allowing the user to take necessary measures.

[0787] Example prompts to input to the generative AI model

[0788] "Enter your dog's activity levels and patterns. Generate alerts if abnormal behavior is detected."

[0789] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0790] Step 1:

[0791] The device collects real-time behavioral data from sensors attached to the animal's collar. Specifically, it uses accelerometers, gravity sensors, and GPS to collect data on the animal's activity, sleep patterns, food intake, etc. This data is temporarily stored in the device's memory.

[0792] Input: Raw data from sensors (acceleration, position).

[0793] Output: Collected behavioral data.

[0794] Specific operation: The device acquires data from the sensor at regular intervals and stores it in local memory.

[0795] Step 2:

[0796] The device periodically collects and sends the collected data to a server, where it is encrypted and securely transferred to the server via the Internet.

[0797] Input: Behavioral data stored in local memory.

[0798] Output: The encrypted data sent to the server.

[0799] Specific operation: The device converts the collected data into JSON format, encrypts it, and then sends the data to the server using an HTTP request.

[0800] Step 3:

[0801] The server temporarily stores the received data in a buffer and performs a data refinement process, which removes noise and standardizes the format. The refined data is then saved in a database.

[0802] Input: The received encrypted data.

[0803] Output: Refined behavioral data.

[0804] Specific operation: The server decrypts the encrypted data, performs preprocessing such as noise removal and missing value completion, and then stores it in the database.

[0805] Step 4:

[0806] The server inputs the behavioral data stored in the database into the generative AI model for analysis. The generative AI model detects abnormal behavior from the behavioral data and optimizes the amount of food and exercise.

[0807] Input: Refined behavioral data stored in a database.

[0808] Output: Analysis results (detection of abnormal behavior, optimization of food intake and exercise).

[0809] Specific operation: The server inputs behavioral data into the generative AI model using prompts to analyze it. For example, the prompt might say, "Enter the dog's activity level and patterns. Generate an alert if abnormal behavior is detected."

[0810] Step 5:

[0811] The server generates appropriate notifications for users based on the analysis results. Urgent matters are notified immediately. Notifications are sent to users via push notifications, email, or social media.

[0812] Input: Analysis results.

[0813] Output: A notification message to the user.

[0814] Specific operation: The server generates a notification message from the analysis results and sends a push notification or email via an HTTP request or various APIs.

[0815] Step 6:

[0816] The device displays notifications and advice sent from the server to the user, who can then adjust their behavior based on the information, such as adjusting their food intake, developing an exercise plan, or quickly responding to abnormal behavior.

[0817] Input: Notification message.

[0818] Output: Specific instructions or advice for the user to adjust their behavior.

[0819] Specific behavior: The device receives the notification message and displays it on the user interface. The user can take appropriate measures based on the notification content.

[0820] 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.

[0821] The present invention is a system that collects behavioral data of animals, particularly dogs, and analyzes it using generative artificial intelligence (generative AI model) and an emotion engine. The present invention manages the health of animals by collecting data using sensors, transmitting it to a server for analysis, and providing information based on the results and the user's emotions. Specific embodiments of the present invention will be described below.

[0822] Overall overview

[0823] The system consists of the following main components:

[0824] 1. Sensors that collect animal behavior data

[0825] 2. An application that sends data to a server

[0826] 3. Server that analyzes data and generates AI models

[0827] 4. Emotion engine that recognizes user emotions

[0828] 5. Interface for notifying users of evaluation results

[0829] Sensors and Data Collection

[0830] Terminal (sensor) side:

[0831] Sensors attached to the animal's collar or harness monitor real-time behavioral data such as activity levels, sleep patterns, and food intake. These sensors combine accelerometers, gravity sensors, and GPS. Data is periodically sent to a server via an application.

[0832] Data transmission and storage

[0833] App (device) side:

[0834] The application periodically collects data from the sensors and sends it to a server via the Internet. The data is encrypted to ensure security. The application records the success or failure of data transmission and notifies the user if there is a problem.

[0835] Server side:

[0836] The server temporarily stores the received data in a buffer and then refines it. The refined data is then stored in a database for subsequent analysis. The database is designed for query efficiency, allowing for quick access even to large amounts of data.

[0837] Data analysis

[0838] Server side:

[0839] The server inputs the behavioral data stored in the database into a generative AI model for analysis. The generative AI model identifies behavioral patterns and detects anomalies, generating results such as optimizing food intake, suggesting exercise amounts, and evaluating health status. These analysis results are then stored back in the database and made available via the user interface.

[0840] Emotion engine integration

[0841] Server side:

[0842] The server integrates an emotion engine that collects users' emotional data. The emotion data is analyzed in real time based on the user's facial expressions, voice, and text input. The emotion engine evaluates the user's stress level and emotional state and stores the results in a well-being database.

[0843] Emotion Engine in action:

[0844] The emotion engine analyzes the user's emotional data to assess stress levels and emotional fluctuations. The assessment results are then used in conjunction with a generative AI model to incorporate emotional elements into the analysis of animal health data and provide personalized notifications and advice to the user.

[0845] Notification of results and actions

[0846] Server side:

[0847] The server generates appropriate notifications for the user based on the analysis results. The notification system operates in real time, and immediate notifications are sent for urgent matters. The content of the notifications is conveyed to the user via push notifications, email, or social media. Based on the evaluation results of the emotion engine, the content of the notifications is optimized to the user's emotional state.

[0848] App (device) side:

[0849] The application displays notifications and advice sent from the server to the user. Notifications include suggestions for optimal meal sizes, exercise advice, and warnings about abnormal behavior while away from home. The application provides an interface for the user to take action based on these notifications. It also includes advice and reminders to reduce the user's stress based on information from the emotion engine.

[0850] User side:

[0851] Based on the information provided through the app, users can adjust their pet's feeding and exercise schedule. If they receive alerts about abnormal behavior while away from home, they can take steps to respond quickly. If necessary, they can also use the application to book an online consultation with a veterinarian to receive appropriate medical treatment. Furthermore, they can manage stress levels and receive emotional support by implementing advice based on the user's emotional state.

[0852] Specific examples

[0853] Example 1: Optimizing food portion size

[0854] If a user's dog has recently shown a decrease in appetite, the sensor collects food data and sends it to the server. The server then uses a generative AI model to calculate the optimal amount of food and generates recommendations such as "200 grams of food per day is appropriate for a 10kg dog." In addition, the emotion engine evaluates the user's stress level and provides advice such as "Because your current stress level is high, be careful about changing your dog's food intake."

[0855] Example 2: Exercise advice

[0856] If a user's dog has recently shown a decline in activity, sensors collect activity data and send it to a server. The server analyzes the data and uses a generative AI model to calculate the optimal amount of exercise. Results such as "recommended two 30-minute walks per day or free exercise at a dog park" are generated and notified to the user through the app. An emotion engine is also used to add encouraging messages based on the user's emotional state.

[0857] Example 3: Detecting abnormal behavior while away from home

[0858] If the dog swallows something or exhibits abnormal behavior while the user is away, the sensor collects the data and sends it to the server. The server immediately analyzes it and generates an alert notification if it detects abnormal behavior. The application then sends a push notification with detailed information to the user, allowing the user to take necessary measures. The emotion engine also provides reminders and support messages to reduce the user's impatience and anxiety.

[0859] In this way, the system of the present invention manages the animal's health condition in detail and in real time, supporting the owner in taking prompt and appropriate action. By integrating an emotion engine, it becomes possible to provide information that takes into account the user's emotional state, thereby realizing even greater user support.

[0860] The processing flow will be explained below.

[0861] Data Collection Phase

[0862] Device (sensor, app) side

[0863] Step 1: Monitoring data with sensors

[0864] The sensors measure the animals' activity levels, sleep patterns and food intake in real time.

[0865] The measured data is temporarily stored inside the sensor.

[0866] Step 2: Prepare your data for transfer

[0867] The sensor prepares to send the collected data to the app at regular intervals.

[0868] Set up the communication protocol for data transmission and format the data appropriately.

[0869] Step 3: Sending data

[0870] The app receives the data sent from the sensor and temporarily stores it in the internal storage.

[0871] Batch processing is performed at regular intervals and the data is sent to the server.

[0872] Data transmission and storage

[0873] Server side

[0874] Step 4: Receiving the data

[0875] The server has an API for receiving data sent from the app.

[0876] The received data is temporarily stored in a buffer.

[0877] Step 5: Save your data

[0878] The server pre-processes and formats the buffered data.

[0879] The preprocessed data is stored in the database.

[0880] Data analysis

[0881] Server side

[0882] Step 6: Preprocessing the data

[0883] The server retrieves the data that needs to be analyzed from the database.

[0884] The acquired data is filled in with missing values ​​and noise is removed, and it is then formatted in a form suitable for analysis.

[0885] Step 7: Input to the generative AI model

[0886] The server inputs the preprocessed data into a generative AI model.

[0887] The model analyzes the animal's behavioral patterns and extracts features.

[0888] Step 8: Generate analysis results

[0889] The generative AI model generates evaluation results such as optimizing food intake, giving exercise advice, and detecting abnormal behavior.

[0890] Store the generated results in a database.

[0891] Emotion engine integration

[0892] Server side

[0893] Step 9: Collect emotion data

[0894] The server receives the user's emotion data from the app.

[0895] Emotional data is collected in real time based on the user's facial expressions, voice, text input, etc.

[0896] Step 10: Analyze the sentiment data

[0897] The server analyzes the user's emotion data using an emotion engine.

[0898] The analysis results (stress level, emotional state) are stored in a well-being database.

[0899] Step 11: Integrating Emotional and Health Data

[0900] The server integrates the analysis results of the generative AI model and the evaluation results of the emotion engine to adjust the content of the notification.

[0901] The integration results are stored in a database and an optimized notification is generated for the user.

[0902] Notification of results and actions

[0903] Server side

[0904] Step 12: Prepare for notifications

[0905] The server periodically checks the analysis results and extracts information that should be notified to the user.

[0906] Urgent information will be given priority and immediate notification will be prepared.

[0907] Step 13: Sending notifications

[0908] The server sends notifications to the user using an appropriate notification system (e.g., Firebase Cloud Messaging).

[0909] App (device) side

[0910] Step 14: Receive notifications

[0911] The app receives notifications sent from the server.

[0912] Received notifications are displayed to the user in a visually understandable format.

[0913] User Actions

[0914] User side

[0915] Step 15: Review and respond to notifications

[0916] The user can check the notification content through the app and take the necessary action.

[0917] Adjust food and create exercise plans based on optimal feeding amounts.

[0918] Step 16: Emotionally Based Responses

[0919] The user can implement stress management and emotional support by referring to the advice provided by the emotion engine.

[0920] For example, if you have high stress levels, try relaxation techniques.

[0921] Step 17: Online consultation with your veterinarian

[0922] If necessary, users can use the app to book an online consultation with a veterinarian.

[0923] Online consultations are conducted via video calls and text chats.

[0924] This is the specific processing flow of the program. This process manages the animal's health condition in real time and supports the owner in taking appropriate action. By combining it with an emotion engine, it is possible to provide information that takes the user's emotional state into consideration.

[0925] Example 2

[0926] 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."

[0927] Currently, animal health management relies heavily on owner observation, making it difficult to manage based on objective data. Additionally, while the owner's emotional state can affect animal health management, no system exists that fully takes this into account. This can lead to delayed appropriate responses or inappropriate management. Furthermore, optimizing exercise and dietary intake requires detailed data analysis, which is unrealistic to perform manually.

[0928] The identification process 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 means for collecting animal behavior data using a sensor, means for transmitting the collected data to the server via a terminal, means for performing data refinement processing in the server and then storing the data in a database, means for analyzing the data using a generative AI model and evaluating the animal's health condition and behavior, means for notifying the user of the evaluation results, means for collecting the user's emotion data and analyzing it using an emotion engine, and means for personalizing and notifying the evaluation results based on the emotion analysis results. This makes it possible to manage the animal's health condition in detail and in real time, and to provide personalized responses that also take the owner's emotional state into consideration.

[0929] The "sensor" is a device for collecting animal behavior data in real time, and is equipped with multiple functions such as an acceleration sensor, gravity sensor, and GPS.

[0930] A "terminal" is a relay device for transmitting collected data to a server, and has functions such as encrypting data and maintaining a transmission log.

[0931] A "server" is a computer system that processes, stores, and analyzes received data, and is responsible for running generative AI models and emotion engines.

[0932] "Data refinement processing" is a process for improving the quality of collected data by removing outliers and standardizing the format.

[0933] A "database" is a system for efficiently storing and accessing refined data and analytical results.

[0934] A "generative AI model" is an artificial intelligence model that analyzes behavioral data based on machine learning algorithms to evaluate an animal's health and behavioral patterns.

[0935] The "emotion engine" is a system that collects and analyzes emotional data from users' facial expressions, voice, text input, etc., and is responsible for assessing the user's stress level and emotional state.

[0936] "Evaluation results" refer to an assessment of the animal's health and behavioral patterns, as well as the user's emotional state, based on data analyzed by the generative AI model and emotion engine.

[0937] "Personalization" means adjusting information and service content according to each user's characteristics and emotional state.

[0938] The present invention is a system that collects animal behavior data and analyzes it using a generative AI model and an emotion engine. The present invention manages the animal's health by collecting data using sensors, transmitting it to a server for analysis, and providing information based on the results and the user's emotions. Below, specific embodiments of the present invention are described.

[0939] Overall system configuration

[0940] sensor

[0941] On the terminal (sensor) side, various sensors attached to the animal's collar or harness monitor behavioral data such as activity level, sleep patterns, and food intake in real time. Hardware such as accelerometers, gravity sensors, and GPS are used.

[0942] application

[0943] The application periodically compiles data collected from sensors and sends it to a server via the Internet. This data is encrypted to ensure security. The application records the success and failure of transmissions in a log and notifies the user if an error occurs.

[0944] server

[0945] The server temporarily stores the received data in a buffer and then performs a data refinement process, which involves removing outliers and converting formats. The refined data is then stored in a database. The data is then analyzed by a generative AI model, which analyzes behavioral patterns, detects anomalies, and evaluates health status, and stores the results in a database.

[0946] Emotion Engine

[0947] The emotion engine collects and analyzes emotional data from users' facial expressions, voice, and text input in real time. The results of the emotion analysis evaluate the user's stress level and emotional state and are stored in a well-being database. This makes it possible to integrate animal health data with emotional data.

[0948] Notifications and Actions

[0949] The server combines the results of the animal's health data analysis with the user's emotional data and generates appropriate notifications. These notifications are sent to the user via push notifications, email, social media, etc. The application displays these notifications to the user and supports them in taking necessary actions. Based on the information provided through the application, users can adjust the amount of food their animal eats and create exercise plans. They can also manage their own stress by taking advice from the emotion engine.

[0950] Specific examples

[0951] Example 1: Optimizing food portion size

[0952] If a user's dog has recently lost its appetite, the sensor collects dietary data and sends it to the server. The server then uses a generative AI model to generate a recommendation such as, "200 grams of food per day is appropriate for a 10 kg dog." In addition, the emotion engine provides advice such as, "Because your current stress level is high, be careful about changing your dog's food intake."

[0953] Example prompt: Analyze your dog's recent feeding data and suggest appropriate feeding amounts. The advice should also take into account the user's emotional state.

[0954] Example 2: Exercise advice

[0955] If a user's dog has recently shown a decline in its activity level, sensors collect activity data and send it to the server. The server then uses a generative AI model to calculate the optimal amount of exercise and recommends two 30-minute walks per day or free exercise at a dog park. An emotion engine is also used to add encouraging messages based on the user's emotional state.

[0956] Example prompt: Based on the dog's exercise data, suggest the optimal amount and specific exercise method. Please also take into account the user's emotional state.

[0957] Example 3: Detecting abnormal behavior while away from home

[0958] If the dog exhibits abnormal behavior while the user is away, the sensor collects the data and sends it to the server. The server immediately analyzes the data and generates an alert if it detects abnormal behavior. The application then sends a push notification to the user with detailed information, allowing them to take necessary measures. The emotion engine also provides advice to reduce the user's impatience and anxiety.

[0959] Example prompt: Detect abnormal dog behavior while you're away and immediately generate an alert to notify the user. Include a message to ease the user's anxiety.

[0960] As described above, the system of the present invention manages the health status of animals in detail and in real time, and enables personalized measures that also take into account the user's stress level.

[0961] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0962] Step 1:

[0963] Data collection

[0964] Subject: Terminal (sensor)

[0965] Sensors attached to the device monitor the animal's activity levels, sleep patterns, food intake, and other behavioral data in real time.

[0966] Input: Raw data from sensors (acceleration, gravity, position).

[0967] Specific behavior:

[0968] The accelerometer detects animal movements.

[0969] Gravity sensors are used to determine the animal's position.

[0970] GPS sensors track the location of animals.

[0971] Output: Collected behavioral data.

[0972] Step 2:

[0973] Data transmission and storage

[0974] Subject: Terminal (application)

[0975] The application compiles the data collected from the sensors at regular intervals (e.g., every 5 minutes) and sends it to a server via the Internet.

[0976] Input: Behavioral data collected from sensors.

[0977] Specific behavior:

[0978] The data is encrypted.

[0979] Establish communication with the server and send data.

[0980] The transmission result is recorded as a log, and if it fails, a retransmission attempt is made.

[0981] Output: Behavioral data sent to the server.

[0982] Step 3:

[0983] Data refinement

[0984] Subject: Server

[0985] The server temporarily stores the received data in a buffer and performs a data refinement process.

[0986] Input: Raw behavioral data sent from the device.

[0987] Specific behavior:

[0988] Outlier detection and removal.

[0989] Format conversion and data standardization.

[0990] Correcting time lag.

[0991] Output: Refined behavioral data.

[0992] Step 4:

[0993] Data storage

[0994] Subject: Server

[0995] The server stores the refined data in a database.

[0996] Input: Refined behavioral data.

[0997] Specific behavior:

[0998] Inserts data into the database.

[0999] Data saving confirmation process.

[1000] Output: Behavioral data stored in a database.

[1001] Step 5:

[1002] Data analysis

[1003] Subject: Server

[1004] The server inputs the behavioral data stored in the database into the generative AI model and performs analysis.

[1005] Input: Behavioral data stored in a database.

[1006] Specific behavior:

[1007] Load behavioral data into a generative AI model.

[1008] Machine learning algorithms are applied to analyze behavioral patterns, detect anomalies, and assess health status.

[1009] Output: Analysis results (e.g., health status assessment results).

[1010] Step 6:

[1011] Emotional data collection and analysis

[1012] Subject: Server

[1013] The server uses an emotion engine to collect and analyze emotional data from the user's facial expressions, voice, text input, etc.

[1014] Input: User's facial expression data, voice data, and text data.

[1015] Specific behavior:

[1016] Collect emotional data from input devices such as cameras and microphones.

[1017] Input data into the emotion engine and perform analysis.

[1018] Output: Sentiment analysis results (e.g. stress level, emotional state).

[1019] Step 7:

[1020] Consolidating assessment results and generating personalized notifications

[1021] Subject: Server

[1022] The server integrates the analysis results from the generative AI model and the emotion engine to generate notifications optimized for the user.

[1023] Input: Analysis results of the generative AI model, analysis results of the emotion engine.

[1024] Specific behavior:

[1025] Integrating health and emotional assessment results.

[1026] Generate notifications (e.g., suggestions for optimal exercise and dietary intake, warnings about abnormal behavior).

[1027] Output: Personalized notification.

[1028] Step 8:

[1029] Notifications and User Actions

[1030] Subject: Server and terminal (application)

[1031] The server generates a notification and sends it to the device, where the application displays it to the user, who can then take appropriate action based on the notification content.

[1032] Enter: Personalized Notifications.

[1033] Specific behavior:

[1034] Send notifications (push notifications, email, social media).

[1035] Notification display in the application.

[1036] The user takes action based on the notification (e.g., adjusting food intake, creating an exercise plan).

[1037] Output: User actions (e.g., changing food intake, starting exercise), emotional stability.

[1038] (Application example 2)

[1039] 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."

[1040] In modern society, pet health management and safety measures are important issues for pet owners. However, it has been difficult to accurately manage pet behavior data and health status in real time and quickly detect abnormal behavior. Furthermore, there has been a lack of appropriate notifications and advice that take into account the owner's emotional state, which can increase stress for the owner. Therefore, there is a need for a system that can accurately evaluate pet health and behavior, quickly detect abnormal behavior, and provide appropriate information to the owner.

[1041] The identification processing by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting animal behavior data using a sensor, means for transmitting the collected data to the server, means for analyzing the data using a generative AI model in the server and evaluating the animal's health condition and behavior, means for notifying the user of the evaluation results, means for detecting abnormal behavior, means for notifying the user of the results of the abnormal behavior detection, an emotion engine for evaluating the user's emotional state, and means for optimizing the notification content based on the evaluation results by the emotion engine. This enables real-time management of the pet's health condition and behavior and rapid detection of abnormal behavior, and makes it possible to provide the owner with appropriate notifications and advice that take the emotional state into consideration.

[1042] "Animal behavior data" refers to various data related to animal behavior, such as animal activity levels, location information, and abnormal behavior.

[1043] A "sensor" is a device that is attached to an animal's harness and is used to collect behavioral data about the animal.

[1044] "Server" refers to a computer system that analyzes collected data and manages and stores evaluation results.

[1045] A "generative AI model" is an artificial intelligence algorithm that analyzes an animal's health and behavior based on collected data.

[1046] An "emotion engine" is a system for assessing a user's emotional state and optimizing notification content based on that.

[1047] "Abnormal behavior" refers to peculiar behavior of an animal that deviates from its normal behavioral pattern.

[1048] "Notification means" refers to a method or device for notifying the user of the analysis results or abnormal behavior detection results.

[1049] "Dietary data" refers to data relating to an animal's dietary intake and eating patterns.

[1050] "Movement data" refers to data that indicates quantities and patterns related to animal movement.

[1051] "Optimization" is the adjustment of data and processes to achieve the best results for a particular purpose.

[1052] This invention is a system that collects animal behavior data and analyzes it using a generative AI model and emotion engine to manage animal health and abnormal behavior, and provides appropriate notifications to users.

[1053] Sensors and Data Collection

[1054] The sensors are attached to the animal's clothing (such as a collar) and collect real-time data on activity, location, abnormal behavior, etc. These sensors include an accelerometer, gravity sensor, and GPS.

[1055] Data transmission and storage

[1056] The device (smartphone app) periodically sends data collected from the sensors to a server. The data is encrypted and sent securely via the Internet. The server temporarily stores the received data, performs any preprocessing necessary for analysis, and then stores it in a database.

[1057] Data analysis

[1058] The server analyzes the behavioral data stored in the database using a generative AI model. The generative AI model performs the following processes:

[1059] Identifying behavioral patterns

[1060] Abnormal behavior detection

[1061] Health assessment

[1062] The server stores the analysis results in a database and makes them available via a user interface as needed.

[1063] Emotion engine integration

[1064] The server integrates an emotion engine to analyze the user's emotion data. This emotion data is analyzed in real time based on the user's facial expressions, voice, text input, etc. The emotion engine evaluates the user's stress level and emotional state and optimizes the notification content based on the results.

[1065] Notification of results and actions

[1066] The server generates appropriate notifications for users based on the analysis results and abnormal behavior detection results. The notification system operates in real time, and immediate notifications are sent for matters of high urgency. The content of the notifications is communicated to users via push notifications, email, and social media, and the content of the notifications is optimized based on the evaluation results of the emotion engine.

[1067] Specific examples

[1068] Dog Abnormal Behavior Detection: When a dog barks excessively or exhibits abnormal behavior, sensors collect the data and send it to a server, which uses a generative AI model to detect abnormal behavior and immediately notify the user.

[1069] Optimizing food intake: Collecting dog food data and using a generative AI model to calculate the optimal food intake. The results are then communicated to the user, enabling appropriate dietary management.

[1070] Emotional state-based notifications: If the emotion engine assesses that the user is feeling stressed, the notification content will be optimized accordingly and advice will be provided to reduce the user's stress.

[1071] Prompt Sentence Examples

[1072] "Please use the generative AI model to analyze abnormal behavior based on the following data. Generate notification content based on activity data, location data, behavior data, and the results, and notify the user immediately if abnormal behavior is detected."

[1073] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1074] Step 1:

[1075] The device (smartphone app) collects behavioral data from sensors attached to the animal's harness. The sensors measure the animal's activity level, location information, abnormal behavior, etc. in real time and send the data to the device. The input data is raw data collected by the various sensors, and the output is data temporarily stored on the device.

[1076] Step 2:

[1077] The device periodically sends the collected data to a server. The data is encrypted and securely transferred over the Internet. The input is the behavioral data stored on the device, and the output is the encrypted data sent to the server. This process uses an Internet connection and a data encryption algorithm.

[1078] Step 3:

[1079] The server temporarily stores the received data in a buffer memory. The input data is the encrypted behavioral data, and the output is the decrypted original data. The server decrypts the data using a decryption algorithm.

[1080] Step 4:

[1081] The server performs preprocessing on the decrypted data, which includes data shaping, missing value imputation, outlier removal, etc. The input data is the decrypted raw data, and the output is the preprocessed clean data. The server uses preprocessing algorithms and data shaping functions.

[1082] Step 5:

[1083] The server inputs the preprocessed data into the generative AI model for analysis. The generative AI model identifies behavioral patterns from the data, detects abnormal behavior, and evaluates health status. The input data is the preprocessed data, and the output is the analysis results. The server performs data analysis using the generative AI model.

[1084] Step 6:

[1085] The server stores the analysis results in a database for further processing. The input data are the analysis results and the output is the stored data. The server uses a database management system to store the data.

[1086] Step 7:

[1087] The server collects the user's emotional data and analyzes it using an emotion engine. The emotional data can be obtained from the user's facial expressions, voice, text input, etc. The input data is the emotional data, and the output is the evaluation result of the emotional state. The server uses an emotion analysis algorithm.

[1088] Step 8:

[1089] The server optimizes the notification content to be provided to the user based on the evaluation results of the emotion engine. The input data are the evaluation results and analysis results of the emotional state, and the output is the optimized notification content. The server generates the notification content by integrating the evaluation results and analysis results of the emotion engine.

[1090] Step 9:

[1091] The server sends the optimized notification content to the user. The notification is sent via push notification, email, or SNS. The input data is the optimized notification content, and the output is the notification message to the user. The server sends the message using the notification system.

[1092] 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.

[1093] 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.

[1094] 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.

[1095] [Third embodiment]

[1096] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[1097] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[1098] 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).

[1099] 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.

[1100] 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.

[1101] 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).

[1102] 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.

[1103] 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.

[1104] 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.

[1105] 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.

[1106] 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.

[1107] 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."

[1108] The present invention is a system that collects behavioral data of animals, particularly dogs, and analyzes it using generative artificial intelligence (generative AI model). The present invention manages the health of animals by collecting data using sensors, transmitting it to a server for analysis, and providing the results to a user. Specific embodiments of the present invention will be described below.

[1109] Overall overview

[1110] The system consists of the following main components:

[1111] 1. Sensors that collect animal behavior data

[1112] 2. An application that sends data to a server

[1113] 3. Server that analyzes data and generates AI models

[1114] 4. Interface for notifying users of evaluation results

[1115] Sensors and Data Collection

[1116] Terminal (sensor) side:

[1117] Sensors attached to the animal's collar or harness monitor real-time behavioral data such as activity levels, sleep patterns, and food intake. These sensors combine accelerometers, gravity sensors, and GPS. Data is periodically sent to a server via an application.

[1118] Data transmission and storage

[1119] App (device) side:

[1120] The application periodically collects data from the sensors and sends it to a server via the Internet. The data is encrypted to ensure security. The application records the success or failure of data transmission and notifies the user if there is a problem.

[1121] Server side:

[1122] The server temporarily stores the received data in a buffer and then refines it. The refined data is then stored in a database for subsequent analysis. The database is designed for query efficiency, allowing for quick access even to large amounts of data.

[1123] Data analysis

[1124] Server side:

[1125] The server inputs the behavioral data stored in the database into a generative AI model for analysis. The generative AI model identifies behavioral patterns and detects anomalies, generating results such as optimizing food intake, suggesting exercise amounts, and evaluating health status. These analysis results are then stored back in the database and made available via the user interface.

[1126] Notification of results and actions

[1127] Server side:

[1128] The server generates appropriate notifications for users based on the analysis results. The notification system operates in real time, and immediate notifications are sent for urgent matters. The content of the notifications is conveyed to users via push notifications, email, or social media.

[1129] App (device) side:

[1130] The application displays notifications and advice sent from the server to the user. Notifications include suggestions for optimal meal portions, exercise advice, and warnings about abnormal behavior while away from home. The application provides an interface for the user to take action in response to these notifications.

[1131] User Actions

[1132] User side:

[1133] Based on the information provided through the app, users can adjust their pet's feeding and exercise schedules, receive alerts about abnormal behavior while away from home, take steps to respond quickly, and, if necessary, use the application to book an online consultation with a veterinarian to receive appropriate medical treatment.

[1134] Specific examples

[1135] Example 1: Optimizing food portion size

[1136] If a user's dog has recently shown a decreased appetite, the sensor collects food data and sends it to a server. The server then uses a generative AI model to calculate optimal feeding amounts and generate recommendations, such as "200 grams of food per day is appropriate for a 10kg dog." The application then notifies the user of this information, allowing them to adjust their feeding accordingly.

[1137] Example 2: Exercise advice

[1138] If the user's dog has recently shown a decline in exercise, the sensor collects activity data and sends it to the server. The server analyzes the data and uses a generative AI model to calculate the optimal amount of exercise. The result, such as "Two 30-minute walks per day or free exercise at a dog park is recommended," is generated and notified to the user via the app. The user can then create an exercise plan based on this information.

[1139] Example 3: Detecting abnormal behavior while away from home

[1140] If the dog swallows something or exhibits abnormal behavior while the user is away, the sensor will collect the data and send it to the server. The server will immediately analyze it and generate an alert notification if it detects abnormal behavior. The application will then send a push notification to the user with detailed information, allowing the user to take necessary measures.

[1141] In this way, the system of the present invention manages the health status of animals in detail and in real time, supporting owners in responding quickly and appropriately.

[1142] The processing flow will be explained below.

[1143] Data Collection Phase

[1144] Device (sensor, app) side

[1145] Step 1: Monitoring data with sensors

[1146] The sensors measure the animals' activity levels, sleep patterns and food intake in real time.

[1147] The measured data is temporarily stored inside the sensor.

[1148] Step 2: Prepare your data for transfer

[1149] The sensor prepares to send the collected data to the app at regular intervals.

[1150] Set up the communication protocol for data transmission and format the data appropriately.

[1151] Step 3: Sending data

[1152] The app receives the data sent from the sensor and temporarily stores it in the internal storage.

[1153] Batch processing is performed at regular intervals and the data is sent to the server.

[1154] Data transmission and storage

[1155] Server side

[1156] Step 4: Receiving the data

[1157] The server has an API for receiving data sent from the app.

[1158] The received data is temporarily stored in a buffer.

[1159] Step 5: Save your data

[1160] The server pre-processes and formats the buffered data.

[1161] The preprocessed data is stored in the database.

[1162] Data analysis

[1163] Server side

[1164] Step 6: Preprocessing the data

[1165] The server retrieves the data that needs to be analyzed from the database.

[1166] The acquired data is filled in with missing values ​​and noise is removed, and it is then formatted in a form suitable for analysis.

[1167] Step 7: Input to the generative AI model

[1168] The server inputs the preprocessed data into a generative AI model (e.g., GPT).

[1169] The model analyzes the animal's behavioral patterns and extracts features.

[1170] Step 8: Generate analysis results

[1171] The generative AI model generates evaluation results such as optimizing food intake, giving exercise advice, and detecting abnormal behavior.

[1172] Store the generated results in a database.

[1173] Notification of results and actions

[1174] Server side

[1175] Step 9: Prepare for notifications

[1176] The server periodically checks the analysis results and extracts information that should be notified to the user.

[1177] Information with high urgency will be given priority.

[1178] Step 10: Sending notifications

[1179] The server uses an appropriate notification system (e.g., Firebase Cloud Messaging) to send a notification to the user.

[1180] App (device) side

[1181] Step 11: Receive notifications

[1182] The app receives notifications sent from the server.

[1183] Received notifications are displayed to the user in a visually understandable format.

[1184] User side

[1185] Step 12: Review and respond to notifications

[1186] Users can check the notification content through the app and take necessary action.

[1187] For example, it adjusts food and creates exercise plans based on optimal feeding amounts.

[1188] Step 13: Online consultation with a veterinarian

[1189] If necessary, users can use the app to book an online consultation with a veterinarian.

[1190] Online consultations are conducted via video calls and text chats.

[1191] This is the specific flow of the program's processing. This process manages the animal's health condition in real time and supports the owner in taking appropriate action.

[1192] Example 1

[1193] 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."

[1194] Currently, many pet owners face the challenge of understanding their pets' health and behavior in detail and in real time. Manually recording behavioral data and assessing health status is time-consuming and often requires specialized knowledge. Furthermore, standards for calculating appropriate amounts of food and exercise are often unclear, making it difficult for pet owners to properly manage their pets. This leads to inadequate health management for their animals and ultimately increases the risk of ill health.

[1195] 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.

[1196] In this invention, the server

[1197] means for transmitting the animal's behavior data to a server via an application;

[1198] a means for temporarily storing the data, subjecting the data to a refinement process, and storing the data in a database;

[1199] A means to analyze data using generative AI models to assess animal health and behavior;

[1200] This enables the collection, transmission, and analysis of animal behavior data in real time. Based on the analysis results, users can receive specific advice, develop appropriate dietary and exercise plans, and respond quickly to abnormal behavior.

[1201] "Animal behavioral data" refers to information about the activities that animals engage in in their daily lives, and specifically includes data such as activity levels, sleep patterns, and food intake.

[1202] The term "sensor" refers to a device that detects physical or environmental conditions and converts them into data, and in the present invention includes an acceleration sensor or GPS that is attached to an animal's collar, etc.

[1203] "Application" refers to software that runs on the device and transmits data collected from the sensor to the server.

[1204] "Server" refers to a computer system for receiving, storing, and analyzing data over a network.

[1205] "Temporary storage" refers to data that is temporarily stored in a storage device before being stored in a permanent database.

[1206] "Refining" refers to the process of correcting duplications and missing data in the collected data and preparing it in a format suitable for analysis.

[1207] A "database" refers to a collection of data that is structured to store information systematically and enable quick search and access.

[1208] A "generative AI model" is an artificial intelligence model that uses pre-trained algorithms to analyze new data and make predictions or suggestions.

[1209] "Analysis" refers to the act of making inferences and calculations based on collected data to assess the health and behavior of animals.

[1210] "Evaluation results" refer to conclusions about the health and behavior of animals drawn through analysis.

[1211] "Notification" refers to the act of transmitting information to inform users of the evaluation results, and includes push notifications, emails, social media, etc.

[1212] "User interface" refers to the means or screens that allow a user to interact with a system, and is provided through an application.

[1213] The present invention is a system that collects behavioral data of animals, particularly dogs, and analyzes it using a generative AI model. This system collects data using sensors, transmits it to a server for analysis, and provides the results to a user to manage the health of the animal. Below, specific embodiments of the present invention are described.

[1214] Hardware and software used

[1215] Sensor (terminal) side:

[1216] The sensors, which are attached to the animal's collar or harness, combine accelerometers, gravity sensors, GPS, and other sensors to monitor the animal's activity, sleep patterns, food intake, and other behavioral data in real time.

[1217] Application (device) side:

[1218] An application installed on a smartphone or tablet collects data from the sensors and periodically transmits it to a server over the Internet using the encrypted HTTPS protocol.

[1219] Server side:

[1220] The server is a high-performance computing system that temporarily buffers received data, then refines and stores it in a database. The database on the server is designed for query efficiency, allowing for quick access to large amounts of data. Additionally, generative AI models (e.g., deep learning models for anomaly detection and pattern recognition) are installed and used for data analysis.

[1221] Data processing and calculation

[1222] Data collection and transmission:

[1223] The sensors monitor animal behavior data in real time and transmit it to a smartphone application, which then compiles the data, sends it to a server, and logs the success or failure of the transmission.

[1224] Data storage and refinement:

[1225] The server temporarily stores the received data in a buffer and performs refinement processes such as deleting duplicate data and filling in missing data. The refined data is then stored in a database such as MySQL.

[1226] Data Analysis:

[1227] The server uses the generative AI model to analyze the behavioral data stored in the database, including identifying activity patterns, detecting abnormal behavior, and suggesting optimal diet and exercise amounts. The analysis results are then stored back in the database and made available through the user interface.

[1228] Notification of results:

[1229] The server generates notifications for users based on the analysis results. The notification system operates in real time, and immediate notifications are sent to users for urgent matters. Notifications are sent to users via push notifications, email, and social media.

[1230] Specific examples

[1231] Example 1: Optimizing food portion size

[1232] If a user's dog has recently shown a decreased appetite, the sensor collects food data and sends it to a server. The server then uses a generative AI model to calculate the optimal amount of food, suggesting, for example, that a 10kg dog should eat 200g of food per day. The app then notifies the user of this information, allowing them to adjust their dog's food intake accordingly.

[1233] Example prompt: "What is the appropriate daily amount of food for a dog weighing 10 kg?"

[1234] Example 2: Exercise advice

[1235] If the user's dog has recently shown a decline in exercise, the sensor collects activity data and sends it to the server. The server analyzes the data and uses a generative AI model to calculate the optimal amount of exercise. The result is "recommended to take two 30-minute walks per day or exercise freely at a dog park," and the result is notified to the user via the application. The user can then create an exercise plan based on this.

[1236] Example prompt: "What activities do you recommend to increase my dog's exercise?"

[1237] Example 3: Detecting abnormal behavior while away from home

[1238] If the dog exhibits abnormal behavior while the user is away, the sensor collects the data and sends it to the server. The server immediately analyzes it and generates an alert notification if abnormal behavior is detected. The application then sends a push notification to the user with detailed information, allowing them to take prompt action.

[1239] Example prompt: "What is the appropriate course of action if my dog ​​exhibits abnormal behavior while I'm away?"

[1240] In this way, the system of the present invention manages the health status of animals in detail and supports owners in responding promptly and appropriately.

[1241] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1242] Step 1: Data collection

[1243] Terminal (sensor) side:

[1244] The sensors collect real-time behavioral data of the animals. Specifically, an accelerometer measures activity and posture at rest, and a GPS acquires location information. This data is collected from the sensors and recorded at regular intervals.

[1245] Input: Animal activity data (e.g., activity level, location information)

[1246] Output: raw data collected

[1247] Step 2: Send data

[1248] App (device) side:

[1249] The application periodically collects data collected from sensors and sends it to a server via the Internet. The encrypted HTTPS protocol is used for transmission. The success or failure of the transmission is recorded in a log. For example, if the transmission is successful, a "transmission completed" log is recorded, and if it fails, a "retransmission" flag is set.

[1250] Input: Raw data collected

[1251] Output: Data transferred to the server

[1252] Step 3: Temporarily store and refine data

[1253] Server side:

[1254] The server temporarily stores the received data in a buffer and performs refinement processes such as removing duplicate data and filling in missing data. Duplicate data is removed using SQL queries, and missing GPS data is filled in using a fill-in algorithm. The refined data is then stored in a database such as MySQL.

[1255] Input: Raw data transferred to the server

[1256] Output: Refinement data stored in a database

[1257] Step 4: Data analysis

[1258] Server side:

[1259] The server inputs the refined data into a generative AI model for analysis. The generative AI model identifies behavioral patterns and detects anomalies, and generates results such as recommendations for optimizing food intake and exercise. The analysis process is performed using a Python script.

[1260] Input: Refining data stored in the database

[1261] Output: Analysis results (e.g., recommendations for optimal food intake and exercise)

[1262] Step 5: Notification of results

[1263] Server side:

[1264] The server converts the analysis results into notifications and sends them to the user. For example, a push notification containing information such as a decrease in the dog's activity level or a recommendation for optimal feeding is generated. These notifications are sent to the user in real time.

[1265] Input: Analysis results

[1266] Output: Notification message (e.g. push notification, email)

[1267] Step 6: Display in the user interface

[1268] App (device) side:

[1269] The application displays notifications and advice sent from the server to the user, such as "200 grams of food per day" or "Take two 30-minute walks per day." Users can tap to view more information.

[1270] Input: Notification message

[1271] Output: Notifications and advice displayed on the user interface

[1272] Step 7: User Actions

[1273] User side:

[1274] Users can take action based on the provided notifications, such as adjusting the amount of food to the suggested 200 grams per day and creating a daily walking schedule. If they receive a notification of abnormal behavior, they can consult with a veterinarian through the app's online appointment system for prompt action.

[1275] Input: User interface notifications and advice

[1276] Output: Actual behavior (e.g., adjusting food intake, executing exercise plan)

[1277] (Application example 1)

[1278] 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."

[1279] In modern society, pet health management is an important issue for pet owners. Detecting abnormal pet behavior and responding quickly when the owner is away is particularly important for maintaining the pet's safety and health. However, existing technology does not adequately provide a system that can monitor pet behavior in real time, detect abnormal behavior, and provide prompt notification. Therefore, the present invention aims to provide a system that can detect abnormal pet behavior in real time while the owner is away and promptly notify the owner.

[1280] 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.

[1281] In this invention, the server includes means for collecting animal behavior data using a sensor, means for transmitting the collected data to the server, means for analyzing the data using a generative AI model in the server and evaluating the health condition and behavior of the animal, means for notifying the user of the evaluation results, and means for detecting abnormal behavior of animals, including dogs, while the user is away and notifying the user in real time. This makes it possible to quickly detect abnormal behavior of pets and notify the owner in real time.

[1282] "Animal" is a broad term that refers to any pet or livestock animal, including dogs.

[1283] "Behavioral data" is a general term for various data that indicate an animal's health and behavior, such as its activity level, sleep patterns, and food intake.

[1284] "Sensors" are devices used to collect animal behavioral data, and include acceleration sensors, gravity sensors, GPS, etc.

[1285] "Server" means a computer system that stores, analyzes, and manages collected data.

[1286] A "generative AI model" is a machine learning model used to analyze collected behavioral data and evaluate the health and behavior of animals.

[1287] "Means for assessing health and behavior" refers to a method for analyzing behavioral data using a generative AI model and assessing the health and behavior of animals based on the results.

[1288] "Means of notifying users" refers to methods for providing information to users based on the analysis results, and includes means such as push notifications, emails, and social media.

[1289] "Abnormal behavior" refers to animal behavior that deviates from normal patterns, including, for example, accidental ingestion, abnormal wandering, and anxiety.

[1290] "Real-time" refers to data processing and notification occurring almost immediately.

[1291] "Away" refers to the time when the user is away, and specifically refers to the time when the animal is alone.

[1292] Overall overview

[1293] The system of the present invention consists of the following main components: a sensor that collects animal behavior data, a means for transmitting the data to a server, a generative AI model that analyzes the behavior data on the server, a means for notifying the user of the analysis results, and a means for detecting abnormal behavior in real time.

[1294] Sensors and Data Collection

[1295] Terminal (sensor) side:

[1296] Sensors attached to the animal's collar or harness monitor real-time behavioral data such as activity levels, sleep patterns, and food intake. These sensors combine accelerometers, gravity sensors, and GPS. The collected data is periodically sent to a server via an application.

[1297] Data transmission and storage

[1298] App (device) side:

[1299] The application periodically collects data from the sensors and sends it to a server via the Internet. The data is encrypted to ensure security. The application logs the success or failure of data transmission and notifies the user if there is a problem.

[1300] Server side:

[1301] The server temporarily stores the received data in a buffer and then performs a data refinement process. The refined data is stored in a database and used for subsequent analysis processes. The database is designed with query efficiency in mind, allowing for quick access even to large amounts of data.

[1302] Data analysis

[1303] Server side:

[1304] The server inputs the behavioral data stored in the database into a generative AI model for analysis. The generative AI model identifies behavioral patterns and detects anomalies, and generates results such as optimizing food intake, suggesting exercise amounts, and evaluating health status. The analysis results are then saved back into the database and made available in the user interface.

[1305] Notification of results and actions

[1306] Server side:

[1307] The server generates appropriate notifications for users based on the analysis results. The notification system operates in real time, and immediate notifications are sent for urgent matters. Notifications are sent to users via push notifications, email, or social media.

[1308] App (device) side:

[1309] The application displays notifications and advice sent from the server to the user, such as recommendations for optimal meal size, exercise advice, and warnings about abnormal behavior while away from home. It also provides an interface for the user to take action based on these notifications.

[1310] User Actions

[1311] User side:

[1312] Based on the information provided through the app, users can adjust their animal's feeding and exercise schedule, take steps to respond quickly if they receive alerts about abnormal behavior while away from home, and, if necessary, use the application to schedule an online consultation with a veterinarian to obtain appropriate medical treatment.

[1313] Specific examples

[1314] Example 1: Optimizing food portion size

[1315] If a user's dog has recently shown a decreased appetite, the sensor collects food data and sends it to a server. The server then uses a generative AI model to calculate optimal feeding amounts and generate recommendations, such as "200 grams of food per day is appropriate for a 10kg dog." The application then notifies the user of this information, allowing them to adjust their feeding accordingly.

[1316] Example 2: Exercise advice

[1317] If the user's dog has recently shown a decline in exercise, the sensor collects activity data and sends it to the server. The server then uses a generative AI model to calculate the optimal amount of exercise, generating a recommendation such as "two 30-minute walks per day or free exercise at a dog park." The result is then sent to the user via the app, allowing the user to create an exercise plan based on this information.

[1318] Example 3: Detecting abnormal behavior while away from home

[1319] If the dog swallows something or exhibits abnormal behavior while the user is away, the sensor will collect the data and send it to the server. The server will immediately analyze it and generate an alert notification if it detects abnormal behavior. The application will then send a push notification to the user with detailed information, allowing the user to take necessary measures.

[1320] Example prompts to input to the generative AI model

[1321] "Enter your dog's activity levels and patterns. Generate alerts if abnormal behavior is detected."

[1322] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1323] Step 1:

[1324] The device collects real-time behavioral data from sensors attached to the animal's collar. Specifically, it uses accelerometers, gravity sensors, and GPS to collect data on the animal's activity, sleep patterns, food intake, etc. This data is temporarily stored in the device's memory.

[1325] Input: Raw data from sensors (acceleration, position).

[1326] Output: Collected behavioral data.

[1327] Specific operation: The device acquires data from the sensor at regular intervals and stores it in local memory.

[1328] Step 2:

[1329] The device periodically collects and sends the collected data to a server, where it is encrypted and securely transferred to the server via the Internet.

[1330] Input: Behavioral data stored in local memory.

[1331] Output: The encrypted data sent to the server.

[1332] Specific operation: The device converts the collected data into JSON format, encrypts it, and then sends the data to the server using an HTTP request.

[1333] Step 3:

[1334] The server temporarily stores the received data in a buffer and performs a data refinement process, which removes noise and standardizes the format. The refined data is then saved in a database.

[1335] Input: The received encrypted data.

[1336] Output: Refined behavioral data.

[1337] Specific operation: The server decrypts the encrypted data, performs preprocessing such as noise removal and missing value completion, and then stores it in the database.

[1338] Step 4:

[1339] The server inputs the behavioral data stored in the database into the generative AI model for analysis. The generative AI model detects abnormal behavior from the behavioral data and optimizes the amount of food and exercise.

[1340] Input: Refined behavioral data stored in a database.

[1341] Output: Analysis results (detection of abnormal behavior, optimization of food intake and exercise).

[1342] Specific operation: The server inputs behavioral data into the generative AI model using prompts to analyze it. For example, the prompt might say, "Enter the dog's activity level and patterns. Generate an alert if abnormal behavior is detected."

[1343] Step 5:

[1344] The server generates appropriate notifications for users based on the analysis results. Urgent matters are notified immediately. Notifications are sent to users via push notifications, email, or social media.

[1345] Input: Analysis results.

[1346] Output: A notification message to the user.

[1347] Specific operation: The server generates a notification message from the analysis results and sends a push notification or email via an HTTP request or various APIs.

[1348] Step 6:

[1349] The device displays notifications and advice sent from the server to the user, who can then adjust their behavior based on the information, such as adjusting their food intake, developing an exercise plan, or quickly responding to abnormal behavior.

[1350] Input: Notification message.

[1351] Output: Specific instructions or advice for the user to adjust their behavior.

[1352] Specific behavior: The device receives the notification message and displays it on the user interface. The user can take appropriate measures based on the notification content.

[1353] 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.

[1354] The present invention is a system that collects behavioral data of animals, particularly dogs, and analyzes it using generative artificial intelligence (generative AI model) and an emotion engine. The present invention manages the health of animals by collecting data using sensors, transmitting it to a server for analysis, and providing information based on the results and the user's emotions. Specific embodiments of the present invention will be described below.

[1355] Overall overview

[1356] The system consists of the following main components:

[1357] 1. Sensors that collect animal behavior data

[1358] 2. An application that sends data to a server

[1359] 3. Server that analyzes data and generates AI models

[1360] 4. Emotion engine that recognizes user emotions

[1361] 5. Interface for notifying users of evaluation results

[1362] Sensors and Data Collection

[1363] Terminal (sensor) side:

[1364] Sensors attached to the animal's collar or harness monitor real-time behavioral data such as activity levels, sleep patterns, and food intake. These sensors combine accelerometers, gravity sensors, and GPS. Data is periodically sent to a server via an application.

[1365] Data transmission and storage

[1366] App (device) side:

[1367] The application periodically collects data from the sensors and sends it to a server via the Internet. The data is encrypted to ensure security. The application records the success or failure of data transmission and notifies the user if there is a problem.

[1368] Server side:

[1369] The server temporarily stores the received data in a buffer and then refines it. The refined data is then stored in a database for subsequent analysis. The database is designed for query efficiency, allowing for quick access even to large amounts of data.

[1370] Data analysis

[1371] Server side:

[1372] The server inputs the behavioral data stored in the database into a generative AI model for analysis. The generative AI model identifies behavioral patterns and detects anomalies, generating results such as optimizing food intake, suggesting exercise amounts, and evaluating health status. These analysis results are then stored back in the database and made available via the user interface.

[1373] Emotion engine integration

[1374] Server side:

[1375] The server integrates an emotion engine that collects users' emotional data. The emotion data is analyzed in real time based on the user's facial expressions, voice, and text input. The emotion engine evaluates the user's stress level and emotional state and stores the results in a well-being database.

[1376] Emotion Engine in action:

[1377] The emotion engine analyzes the user's emotional data to assess stress levels and emotional fluctuations. The assessment results are then used in conjunction with a generative AI model to incorporate emotional elements into the analysis of animal health data and provide personalized notifications and advice to the user.

[1378] Notification of results and actions

[1379] Server side:

[1380] The server generates appropriate notifications for the user based on the analysis results. The notification system operates in real time, and immediate notifications are sent for urgent matters. The content of the notifications is conveyed to the user via push notifications, email, or social media. Based on the evaluation results of the emotion engine, the content of the notifications is optimized to the user's emotional state.

[1381] App (device) side:

[1382] The application displays notifications and advice sent from the server to the user. Notifications include suggestions for optimal meal sizes, exercise advice, and warnings about abnormal behavior while away from home. The application provides an interface for the user to take action based on these notifications. It also includes advice and reminders to reduce the user's stress based on information from the emotion engine.

[1383] User side:

[1384] Based on the information provided through the app, users can adjust their pet's feeding and exercise schedule. If they receive alerts about abnormal behavior while away from home, they can take steps to respond quickly. If necessary, they can also use the application to book an online consultation with a veterinarian to receive appropriate medical treatment. Furthermore, they can manage stress levels and receive emotional support by implementing advice based on the user's emotional state.

[1385] Specific examples

[1386] Example 1: Optimizing food portion size

[1387] If a user's dog has recently shown a decrease in appetite, the sensor collects food data and sends it to the server. The server then uses a generative AI model to calculate the optimal amount of food and generates recommendations such as "200 grams of food per day is appropriate for a 10kg dog." In addition, the emotion engine evaluates the user's stress level and provides advice such as "Because your current stress level is high, be careful about changing your dog's food intake."

[1388] Example 2: Exercise advice

[1389] If a user's dog has recently shown a decline in activity, sensors collect activity data and send it to a server. The server analyzes the data and uses a generative AI model to calculate the optimal amount of exercise. Results such as "recommended two 30-minute walks per day or free exercise at a dog park" are generated and notified to the user through the app. An emotion engine is also used to add encouraging messages based on the user's emotional state.

[1390] Example 3: Detecting abnormal behavior while away from home

[1391] If the dog swallows something or exhibits abnormal behavior while the user is away, the sensor collects the data and sends it to the server. The server immediately analyzes it and generates an alert notification if it detects abnormal behavior. The application then sends a push notification with detailed information to the user, allowing the user to take necessary measures. The emotion engine also provides reminders and support messages to reduce the user's impatience and anxiety.

[1392] In this way, the system of the present invention manages the animal's health condition in detail and in real time, supporting the owner in taking prompt and appropriate action. By integrating an emotion engine, it becomes possible to provide information that takes into account the user's emotional state, thereby realizing even greater user support.

[1393] The processing flow will be explained below.

[1394] Data Collection Phase

[1395] Device (sensor, app) side

[1396] Step 1: Monitoring data with sensors

[1397] The sensors measure the animals' activity levels, sleep patterns and food intake in real time.

[1398] The measured data is temporarily stored inside the sensor.

[1399] Step 2: Prepare your data for transfer

[1400] The sensor prepares to send the collected data to the app at regular intervals.

[1401] Set up the communication protocol for data transmission and format the data appropriately.

[1402] Step 3: Sending data

[1403] The app receives the data sent from the sensor and temporarily stores it in the internal storage.

[1404] Batch processing is performed at regular intervals and the data is sent to the server.

[1405] Data transmission and storage

[1406] Server side

[1407] Step 4: Receiving the data

[1408] The server has an API for receiving data sent from the app.

[1409] The received data is temporarily stored in a buffer.

[1410] Step 5: Save your data

[1411] The server pre-processes and formats the buffered data.

[1412] The preprocessed data is stored in the database.

[1413] Data analysis

[1414] Server side

[1415] Step 6: Preprocessing the data

[1416] The server retrieves the data that needs to be analyzed from the database.

[1417] The acquired data is filled in with missing values ​​and noise is removed, and it is then formatted in a form suitable for analysis.

[1418] Step 7: Input to the generative AI model

[1419] The server inputs the preprocessed data into a generative AI model.

[1420] The model analyzes the animal's behavioral patterns and extracts features.

[1421] Step 8: Generate analysis results

[1422] The generative AI model generates evaluation results such as optimizing food intake, giving exercise advice, and detecting abnormal behavior.

[1423] Store the generated results in a database.

[1424] Emotion engine integration

[1425] Server side

[1426] Step 9: Collect emotion data

[1427] The server receives the user's emotion data from the app.

[1428] Emotional data is collected in real time based on the user's facial expressions, voice, text input, etc.

[1429] Step 10: Analyze the sentiment data

[1430] The server analyzes the user's emotion data using an emotion engine.

[1431] The analysis results (stress level, emotional state) are stored in a well-being database.

[1432] Step 11: Integrating Emotional and Health Data

[1433] The server integrates the analysis results of the generative AI model and the evaluation results of the emotion engine to adjust the content of the notification.

[1434] The integration results are stored in a database and an optimized notification is generated for the user.

[1435] Notification of results and actions

[1436] Server side

[1437] Step 12: Prepare for notifications

[1438] The server periodically checks the analysis results and extracts information that should be notified to the user.

[1439] Urgent information will be given priority and immediate notification will be prepared.

[1440] Step 13: Sending notifications

[1441] The server sends notifications to the user using an appropriate notification system (e.g., Firebase Cloud Messaging).

[1442] App (device) side

[1443] Step 14: Receive notifications

[1444] The app receives notifications sent from the server.

[1445] Received notifications are displayed to the user in a visually understandable format.

[1446] User Actions

[1447] User side

[1448] Step 15: Review and respond to notifications

[1449] The user can check the notification content through the app and take the necessary action.

[1450] Adjust food and create exercise plans based on optimal feeding amounts.

[1451] Step 16: Emotionally Based Responses

[1452] The user can implement stress management and emotional support by referring to the advice provided by the emotion engine.

[1453] For example, if you have high stress levels, try relaxation techniques.

[1454] Step 17: Online consultation with your veterinarian

[1455] If necessary, users can use the app to book an online consultation with a veterinarian.

[1456] Online consultations are conducted via video calls and text chats.

[1457] This is the specific processing flow of the program. This process manages the animal's health condition in real time and supports the owner in taking appropriate action. By combining it with an emotion engine, it is possible to provide information that takes the user's emotional state into consideration.

[1458] Example 2

[1459] 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."

[1460] Currently, animal health management relies heavily on owner observation, making it difficult to manage based on objective data. Additionally, while the owner's emotional state can affect animal health management, no system exists that fully takes this into account. This can lead to delayed appropriate responses or inappropriate management. Furthermore, optimizing exercise and dietary intake requires detailed data analysis, which is unrealistic to perform manually.

[1461] The identification process 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 means for collecting animal behavior data using a sensor, means for transmitting the collected data to the server via a terminal, means for performing data refinement processing in the server and then storing the data in a database, means for analyzing the data using a generative AI model and evaluating the animal's health condition and behavior, means for notifying the user of the evaluation results, means for collecting the user's emotion data and analyzing it using an emotion engine, and means for personalizing and notifying the evaluation results based on the emotion analysis results. This makes it possible to manage the animal's health condition in detail and in real time, and to provide personalized responses that also take the owner's emotional state into consideration.

[1462] The "sensor" is a device for collecting animal behavior data in real time, and is equipped with multiple functions such as an acceleration sensor, gravity sensor, and GPS.

[1463] A "terminal" is a relay device for transmitting collected data to a server, and has functions such as encrypting data and maintaining a transmission log.

[1464] A "server" is a computer system that processes, stores, and analyzes received data, and is responsible for running generative AI models and emotion engines.

[1465] "Data refinement processing" is a process for improving the quality of collected data by removing outliers and standardizing the format.

[1466] A "database" is a system for efficiently storing and accessing refined data and analytical results.

[1467] A "generative AI model" is an artificial intelligence model that analyzes behavioral data based on machine learning algorithms to evaluate an animal's health and behavioral patterns.

[1468] The "emotion engine" is a system that collects and analyzes emotional data from users' facial expressions, voice, text input, etc., and is responsible for assessing the user's stress level and emotional state.

[1469] "Evaluation results" refer to an assessment of the animal's health and behavioral patterns, as well as the user's emotional state, based on data analyzed by the generative AI model and emotion engine.

[1470] "Personalization" means adjusting information and service content according to each user's characteristics and emotional state.

[1471] The present invention is a system that collects animal behavior data and analyzes it using a generative AI model and an emotion engine. The present invention manages the animal's health by collecting data using sensors, transmitting it to a server for analysis, and providing information based on the results and the user's emotions. Below, specific embodiments of the present invention are described.

[1472] Overall system configuration

[1473] sensor

[1474] On the terminal (sensor) side, various sensors attached to the animal's collar or harness monitor behavioral data such as activity level, sleep patterns, and food intake in real time. Hardware such as accelerometers, gravity sensors, and GPS are used.

[1475] application

[1476] The application periodically compiles data collected from sensors and sends it to a server via the Internet. This data is encrypted to ensure security. The application records the success and failure of transmissions in a log and notifies the user if an error occurs.

[1477] server

[1478] The server temporarily stores the received data in a buffer and then performs a data refinement process, which involves removing outliers and converting formats. The refined data is then stored in a database. The data is then analyzed by a generative AI model, which analyzes behavioral patterns, detects anomalies, and evaluates health status, and stores the results in a database.

[1479] Emotion Engine

[1480] The emotion engine collects and analyzes emotional data from users' facial expressions, voice, and text input in real time. The results of the emotion analysis evaluate the user's stress level and emotional state and are stored in a well-being database. This makes it possible to integrate animal health data with emotional data.

[1481] Notifications and Actions

[1482] The server combines the results of the animal's health data analysis with the user's emotional data and generates appropriate notifications. These notifications are sent to the user via push notifications, email, social media, etc. The application displays these notifications to the user and supports them in taking necessary actions. Based on the information provided through the application, users can adjust the amount of food their animal eats and create exercise plans. They can also manage their own stress by taking advice from the emotion engine.

[1483] Specific examples

[1484] Example 1: Optimizing food portion size

[1485] If a user's dog has recently lost its appetite, the sensor collects dietary data and sends it to the server. The server then uses a generative AI model to generate a recommendation such as, "200 grams of food per day is appropriate for a 10 kg dog." In addition, the emotion engine provides advice such as, "Because your current stress level is high, be careful about changing your dog's food intake."

[1486] Example prompt: Analyze your dog's recent feeding data and suggest appropriate feeding amounts. The advice should also take into account the user's emotional state.

[1487] Example 2: Exercise advice

[1488] If a user's dog has recently shown a decline in its activity level, sensors collect activity data and send it to the server. The server then uses a generative AI model to calculate the optimal amount of exercise and recommends two 30-minute walks per day or free exercise at a dog park. An emotion engine is also used to add encouraging messages based on the user's emotional state.

[1489] Example prompt: Based on the dog's exercise data, suggest the optimal amount and specific exercise method. Please also take into account the user's emotional state.

[1490] Example 3: Detecting abnormal behavior while away from home

[1491] If the dog exhibits abnormal behavior while the user is away, the sensor collects the data and sends it to the server. The server immediately analyzes the data and generates an alert if it detects abnormal behavior. The application then sends a push notification to the user with detailed information, allowing them to take necessary measures. The emotion engine also provides advice to reduce the user's impatience and anxiety.

[1492] Example prompt: Detect abnormal dog behavior while you're away and immediately generate an alert to notify the user. Include a message to ease the user's anxiety.

[1493] As described above, the system of the present invention manages the health status of animals in detail and in real time, and enables personalized measures that also take into account the user's stress level.

[1494] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1495] Step 1:

[1496] Data collection

[1497] Subject: Terminal (sensor)

[1498] Sensors attached to the device monitor the animal's activity levels, sleep patterns, food intake, and other behavioral data in real time.

[1499] Input: Raw data from sensors (acceleration, gravity, position).

[1500] Specific behavior:

[1501] The accelerometer detects animal movements.

[1502] Gravity sensors are used to determine the animal's position.

[1503] GPS sensors track the location of animals.

[1504] Output: Collected behavioral data.

[1505] Step 2:

[1506] Data transmission and storage

[1507] Subject: Terminal (application)

[1508] The application compiles the data collected from the sensors at regular intervals (e.g., every 5 minutes) and sends it to a server via the Internet.

[1509] Input: Behavioral data collected from sensors.

[1510] Specific behavior:

[1511] The data is encrypted.

[1512] Establish communication with the server and send data.

[1513] The transmission result is recorded as a log, and if it fails, a retransmission attempt is made.

[1514] Output: Behavioral data sent to the server.

[1515] Step 3:

[1516] Data refinement

[1517] Subject: Server

[1518] The server temporarily stores the received data in a buffer and performs a data refinement process.

[1519] Input: Raw behavioral data sent from the device.

[1520] Specific behavior:

[1521] Outlier detection and removal.

[1522] Format conversion and data standardization.

[1523] Correcting time lag.

[1524] Output: Refined behavioral data.

[1525] Step 4:

[1526] Data storage

[1527] Subject: Server

[1528] The server stores the refined data in a database.

[1529] Input: Refined behavioral data.

[1530] Specific behavior:

[1531] Inserts data into the database.

[1532] Data saving confirmation process.

[1533] Output: Behavioral data stored in a database.

[1534] Step 5:

[1535] Data analysis

[1536] Subject: Server

[1537] The server inputs the behavioral data stored in the database into the generative AI model and performs analysis.

[1538] Input: Behavioral data stored in a database.

[1539] Specific behavior:

[1540] Load behavioral data into a generative AI model.

[1541] Machine learning algorithms are applied to analyze behavioral patterns, detect anomalies, and assess health status.

[1542] Output: Analysis results (e.g., health status assessment results).

[1543] Step 6:

[1544] Emotional data collection and analysis

[1545] Subject: Server

[1546] The server uses an emotion engine to collect and analyze emotional data from the user's facial expressions, voice, text input, etc.

[1547] Input: User's facial expression data, voice data, and text data.

[1548] Specific behavior:

[1549] Collect emotional data from input devices such as cameras and microphones.

[1550] Input data into the emotion engine and perform analysis.

[1551] Output: Sentiment analysis results (e.g. stress level, emotional state).

[1552] Step 7:

[1553] Consolidating assessment results and generating personalized notifications

[1554] Subject: Server

[1555] The server integrates the analysis results from the generative AI model and the emotion engine to generate notifications optimized for the user.

[1556] Input: Analysis results of the generative AI model, analysis results of the emotion engine.

[1557] Specific behavior:

[1558] Integrating health and emotional assessment results.

[1559] Generate notifications (e.g., suggestions for optimal exercise and dietary intake, warnings about abnormal behavior).

[1560] Output: Personalized notification.

[1561] Step 8:

[1562] Notifications and User Actions

[1563] Subject: Server and terminal (application)

[1564] The server generates a notification and sends it to the device, where the application displays it to the user, who can then take appropriate action based on the notification content.

[1565] Enter: Personalized Notifications.

[1566] Specific behavior:

[1567] Send notifications (push notifications, email, social media).

[1568] Notification display in the application.

[1569] The user takes action based on the notification (e.g., adjusting food intake, creating an exercise plan).

[1570] Output: User actions (e.g., changing food intake, starting exercise), emotional stability.

[1571] (Application example 2)

[1572] 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."

[1573] In modern society, pet health management and safety measures are important issues for pet owners. However, it has been difficult to accurately manage pet behavior data and health status in real time and quickly detect abnormal behavior. Furthermore, there has been a lack of appropriate notifications and advice that take into account the owner's emotional state, which can increase stress for the owner. Therefore, there is a need for a system that can accurately evaluate pet health and behavior, quickly detect abnormal behavior, and provide appropriate information to the owner.

[1574] The identification processing by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting animal behavior data using a sensor, means for transmitting the collected data to the server, means for analyzing the data using a generative AI model in the server and evaluating the animal's health condition and behavior, means for notifying the user of the evaluation results, means for detecting abnormal behavior, means for notifying the user of the results of the abnormal behavior detection, an emotion engine for evaluating the user's emotional state, and means for optimizing the notification content based on the evaluation results by the emotion engine. This enables real-time management of the pet's health condition and behavior and rapid detection of abnormal behavior, and makes it possible to provide the owner with appropriate notifications and advice that take the emotional state into consideration.

[1575] "Animal behavior data" refers to various data related to animal behavior, such as animal activity levels, location information, and abnormal behavior.

[1576] A "sensor" is a device that is attached to an animal's harness and is used to collect behavioral data about the animal.

[1577] "Server" refers to a computer system that analyzes collected data and manages and stores evaluation results.

[1578] A "generative AI model" is an artificial intelligence algorithm that analyzes an animal's health and behavior based on collected data.

[1579] An "emotion engine" is a system for assessing a user's emotional state and optimizing notification content based on that.

[1580] "Abnormal behavior" refers to peculiar behavior of an animal that deviates from its normal behavioral pattern.

[1581] "Notification means" refers to a method or device for notifying the user of the analysis results or abnormal behavior detection results.

[1582] "Dietary data" refers to data relating to an animal's dietary intake and eating patterns.

[1583] "Movement data" refers to data that indicates quantities and patterns related to animal movement.

[1584] "Optimization" is the adjustment of data and processes to achieve the best results for a particular purpose.

[1585] This invention is a system that collects animal behavior data and analyzes it using a generative AI model and emotion engine to manage animal health and abnormal behavior, and provides appropriate notifications to users.

[1586] Sensors and Data Collection

[1587] The sensors are attached to the animal's clothing (such as a collar) and collect real-time data on activity, location, abnormal behavior, etc. These sensors include an accelerometer, gravity sensor, and GPS.

[1588] Data transmission and storage

[1589] The device (smartphone app) periodically sends data collected from the sensors to a server. The data is encrypted and sent securely via the Internet. The server temporarily stores the received data, performs any preprocessing necessary for analysis, and then stores it in a database.

[1590] Data analysis

[1591] The server analyzes the behavioral data stored in the database using a generative AI model. The generative AI model performs the following processes:

[1592] Identifying behavioral patterns

[1593] Abnormal behavior detection

[1594] Health assessment

[1595] The server stores the analysis results in a database and makes them available via a user interface as needed.

[1596] Emotion engine integration

[1597] The server integrates an emotion engine to analyze the user's emotion data. This emotion data is analyzed in real time based on the user's facial expressions, voice, text input, etc. The emotion engine evaluates the user's stress level and emotional state and optimizes the notification content based on the results.

[1598] Notification of results and actions

[1599] The server generates appropriate notifications for users based on the analysis results and abnormal behavior detection results. The notification system operates in real time, and immediate notifications are sent for matters of high urgency. The content of the notifications is communicated to users via push notifications, email, and social media, and the content of the notifications is optimized based on the evaluation results of the emotion engine.

[1600] Specific examples

[1601] Dog Abnormal Behavior Detection: When a dog barks excessively or exhibits abnormal behavior, sensors collect the data and send it to a server, which uses a generative AI model to detect abnormal behavior and immediately notify the user.

[1602] Optimizing food intake: Collecting dog food data and using a generative AI model to calculate the optimal food intake. The results are then communicated to the user, enabling appropriate dietary management.

[1603] Emotional state-based notifications: If the emotion engine assesses that the user is feeling stressed, the notification content will be optimized accordingly and advice will be provided to reduce the user's stress.

[1604] Prompt Sentence Examples

[1605] "Please use the generative AI model to analyze abnormal behavior based on the following data. Generate notification content based on activity data, location data, behavior data, and the results, and notify the user immediately if abnormal behavior is detected."

[1606] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1607] Step 1:

[1608] The device (smartphone app) collects behavioral data from sensors attached to the animal's harness. The sensors measure the animal's activity level, location information, abnormal behavior, etc. in real time and send the data to the device. The input data is raw data collected by the various sensors, and the output is data temporarily stored on the device.

[1609] Step 2:

[1610] The device periodically sends the collected data to a server. The data is encrypted and securely transferred over the Internet. The input is the behavioral data stored on the device, and the output is the encrypted data sent to the server. This process uses an Internet connection and a data encryption algorithm.

[1611] Step 3:

[1612] The server temporarily stores the received data in a buffer memory. The input data is the encrypted behavioral data, and the output is the decrypted original data. The server decrypts the data using a decryption algorithm.

[1613] Step 4:

[1614] The server performs preprocessing on the decrypted data, which includes data shaping, missing value imputation, outlier removal, etc. The input data is the decrypted raw data, and the output is the preprocessed clean data. The server uses preprocessing algorithms and data shaping functions.

[1615] Step 5:

[1616] The server inputs the preprocessed data into the generative AI model for analysis. The generative AI model identifies behavioral patterns from the data, detects abnormal behavior, and evaluates health status. The input data is the preprocessed data, and the output is the analysis results. The server performs data analysis using the generative AI model.

[1617] Step 6:

[1618] The server stores the analysis results in a database for further processing. The input data are the analysis results and the output is the stored data. The server uses a database management system to store the data.

[1619] Step 7:

[1620] The server collects the user's emotional data and analyzes it using an emotion engine. The emotional data can be obtained from the user's facial expressions, voice, text input, etc. The input data is the emotional data, and the output is the evaluation result of the emotional state. The server uses an emotion analysis algorithm.

[1621] Step 8:

[1622] The server optimizes the notification content to be provided to the user based on the evaluation results of the emotion engine. The input data are the evaluation results and analysis results of the emotional state, and the output is the optimized notification content. The server generates the notification content by integrating the evaluation results and analysis results of the emotion engine.

[1623] Step 9:

[1624] The server sends the optimized notification content to the user. The notification is sent via push notification, email, or SNS. The input data is the optimized notification content, and the output is the notification message to the user. The server sends the message using the notification system.

[1625] 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.

[1626] 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.

[1627] 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.

[1628] [Fourth embodiment]

[1629] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1630] 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.

[1631] 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).

[1632] 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.

[1633] 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.

[1634] 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).

[1635] 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.

[1636] 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.

[1637] 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.

[1638] 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.

[1639] 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.

[1640] 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.

[1641] 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."

[1642] The present invention is a system that collects behavioral data of animals, particularly dogs, and analyzes it using generative artificial intelligence (generative AI model). The present invention manages the health of animals by collecting data using sensors, transmitting it to a server for analysis, and providing the results to a user. Specific embodiments of the present invention will be described below.

[1643] Overall overview

[1644] The system consists of the following main components:

[1645] 1. Sensors that collect animal behavior data

[1646] 2. An application that sends data to a server

[1647] 3. Server that analyzes data and generates AI models

[1648] 4. Interface for notifying users of evaluation results

[1649] Sensors and Data Collection

[1650] Terminal (sensor) side:

[1651] Sensors attached to the animal's collar or harness monitor real-time behavioral data such as activity levels, sleep patterns, and food intake. These sensors combine accelerometers, gravity sensors, and GPS. Data is periodically sent to a server via an application.

[1652] Data transmission and storage

[1653] App (device) side:

[1654] The application periodically collects data from the sensors and sends it to a server via the Internet. The data is encrypted to ensure security. The application records the success or failure of data transmission and notifies the user if there is a problem.

[1655] Server side:

[1656] The server temporarily stores the received data in a buffer and then refines it. The refined data is then stored in a database for subsequent analysis. The database is designed for query efficiency, allowing for quick access even to large amounts of data.

[1657] Data analysis

[1658] Server side:

[1659] The server inputs the behavioral data stored in the database into a generative AI model for analysis. The generative AI model identifies behavioral patterns and detects anomalies, generating results such as optimizing food intake, suggesting exercise amounts, and evaluating health status. These analysis results are then stored back in the database and made available via the user interface.

[1660] Notification of results and actions

[1661] Server side:

[1662] The server generates appropriate notifications for users based on the analysis results. The notification system operates in real time, and immediate notifications are sent for urgent matters. The content of the notifications is conveyed to users via push notifications, email, or social media.

[1663] App (device) side:

[1664] The application displays notifications and advice sent from the server to the user. Notifications include suggestions for optimal meal portions, exercise advice, and warnings about abnormal behavior while away from home. The application provides an interface for the user to take action in response to these notifications.

[1665] User Actions

[1666] User side:

[1667] Based on the information provided through the app, users can adjust their pet's feeding and exercise schedules, receive alerts about abnormal behavior while away from home, take steps to respond quickly, and, if necessary, use the application to book an online consultation with a veterinarian to receive appropriate medical treatment.

[1668] Specific examples

[1669] Example 1: Optimizing food portion size

[1670] If a user's dog has recently shown a decreased appetite, the sensor collects food data and sends it to a server. The server then uses a generative AI model to calculate optimal feeding amounts and generate recommendations, such as "200 grams of food per day is appropriate for a 10kg dog." The application then notifies the user of this information, allowing them to adjust their feeding accordingly.

[1671] Example 2: Exercise advice

[1672] If the user's dog has recently shown a decline in exercise, the sensor collects activity data and sends it to the server. The server analyzes the data and uses a generative AI model to calculate the optimal amount of exercise. The result, such as "Two 30-minute walks per day or free exercise at a dog park is recommended," is generated and notified to the user via the app. The user can then create an exercise plan based on this information.

[1673] Example 3: Detecting abnormal behavior while away from home

[1674] If the dog swallows something or exhibits abnormal behavior while the user is away, the sensor will collect the data and send it to the server. The server will immediately analyze it and generate an alert notification if it detects abnormal behavior. The application will then send a push notification to the user with detailed information, allowing the user to take necessary measures.

[1675] In this way, the system of the present invention manages the health status of animals in detail and in real time, supporting owners in responding quickly and appropriately.

[1676] The processing flow will be explained below.

[1677] Data Collection Phase

[1678] Device (sensor, app) side

[1679] Step 1: Monitoring data with sensors

[1680] The sensors measure the animals' activity levels, sleep patterns and food intake in real time.

[1681] The measured data is temporarily stored inside the sensor.

[1682] Step 2: Prepare your data for transfer

[1683] The sensor prepares to send the collected data to the app at regular intervals.

[1684] Set up the communication protocol for data transmission and format the data appropriately.

[1685] Step 3: Sending data

[1686] The app receives the data sent from the sensor and temporarily stores it in the internal storage.

[1687] Batch processing is performed at regular intervals and the data is sent to the server.

[1688] Data transmission and storage

[1689] Server side

[1690] Step 4: Receiving the data

[1691] The server has an API for receiving data sent from the app.

[1692] The received data is temporarily stored in a buffer.

[1693] Step 5: Save your data

[1694] The server pre-processes and formats the buffered data.

[1695] The preprocessed data is stored in the database.

[1696] Data analysis

[1697] Server side

[1698] Step 6: Preprocessing the data

[1699] The server retrieves the data that needs to be analyzed from the database.

[1700] The acquired data is filled in with missing values ​​and noise is removed, and it is then formatted in a form suitable for analysis.

[1701] Step 7: Input to the generative AI model

[1702] The server inputs the preprocessed data into a generative AI model (e.g., GPT).

[1703] The model analyzes the animal's behavioral patterns and extracts features.

[1704] Step 8: Generate analysis results

[1705] The generative AI model generates evaluation results such as optimizing food intake, giving exercise advice, and detecting abnormal behavior.

[1706] Store the generated results in a database.

[1707] Notification of results and actions

[1708] Server side

[1709] Step 9: Prepare for notifications

[1710] The server periodically checks the analysis results and extracts information that should be notified to the user.

[1711] Information with high urgency will be given priority.

[1712] Step 10: Sending notifications

[1713] The server uses an appropriate notification system (e.g., Firebase Cloud Messaging) to send a notification to the user.

[1714] App (device) side

[1715] Step 11: Receive notifications

[1716] The app receives notifications sent from the server.

[1717] Received notifications are displayed to the user in a visually understandable format.

[1718] User side

[1719] Step 12: Review and respond to notifications

[1720] Users can check the notification content through the app and take necessary action.

[1721] For example, it adjusts food and creates exercise plans based on optimal feeding amounts.

[1722] Step 13: Online consultation with a veterinarian

[1723] If necessary, users can use the app to book an online consultation with a veterinarian.

[1724] Online consultations are conducted via video calls and text chats.

[1725] This is the specific flow of the program's processing. This process manages the animal's health condition in real time and supports the owner in taking appropriate action.

[1726] Example 1

[1727] 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."

[1728] Currently, many pet owners face the challenge of understanding their pets' health and behavior in detail and in real time. Manually recording behavioral data and assessing health status is time-consuming and often requires specialized knowledge. Furthermore, standards for calculating appropriate amounts of food and exercise are often unclear, making it difficult for pet owners to properly manage their pets. This leads to inadequate health management for their animals and ultimately increases the risk of ill health.

[1729] 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.

[1730] In this invention, the server

[1731] means for transmitting the animal's behavior data to a server via an application;

[1732] a means for temporarily storing the data, subjecting the data to a refinement process, and storing the data in a database;

[1733] A means to analyze data using generative AI models to assess animal health and behavior;

[1734] This enables the collection, transmission, and analysis of animal behavior data in real time. Based on the analysis results, users can receive specific advice, develop appropriate dietary and exercise plans, and respond quickly to abnormal behavior.

[1735] "Animal behavioral data" refers to information about the activities that animals engage in in their daily lives, and specifically includes data such as activity levels, sleep patterns, and food intake.

[1736] The term "sensor" refers to a device that detects physical or environmental conditions and converts them into data, and in the present invention includes an acceleration sensor or GPS that is attached to an animal's collar, etc.

[1737] "Application" refers to software that runs on the device and transmits data collected from the sensor to the server.

[1738] "Server" refers to a computer system for receiving, storing, and analyzing data over a network.

[1739] "Temporary storage" refers to data that is temporarily stored in a storage device before being stored in a permanent database.

[1740] "Refining" refers to the process of correcting duplications and missing data in the collected data and preparing it in a format suitable for analysis.

[1741] A "database" refers to a collection of data that is structured to store information systematically and enable quick search and access.

[1742] A "generative AI model" is an artificial intelligence model that uses pre-trained algorithms to analyze new data and make predictions or suggestions.

[1743] "Analysis" refers to the act of making inferences and calculations based on collected data to assess the health and behavior of animals.

[1744] "Evaluation results" refer to conclusions about the health and behavior of animals drawn through analysis.

[1745] "Notification" refers to the act of transmitting information to inform users of the evaluation results, and includes push notifications, emails, social media, etc.

[1746] "User interface" refers to the means or screens that allow a user to interact with a system, and is provided through an application.

[1747] The present invention is a system that collects behavioral data of animals, particularly dogs, and analyzes it using a generative AI model. This system collects data using sensors, transmits it to a server for analysis, and provides the results to a user to manage the health of the animal. Below, specific embodiments of the present invention are described.

[1748] Hardware and software used

[1749] Sensor (terminal) side:

[1750] The sensors, which are attached to the animal's collar or harness, combine accelerometers, gravity sensors, GPS, and other sensors to monitor the animal's activity, sleep patterns, food intake, and other behavioral data in real time.

[1751] Application (device) side:

[1752] An application installed on a smartphone or tablet collects data from the sensors and periodically transmits it to a server over the Internet using the encrypted HTTPS protocol.

[1753] Server side:

[1754] The server is a high-performance computing system that temporarily buffers received data, then refines and stores it in a database. The database on the server is designed for query efficiency, allowing for quick access to large amounts of data. Additionally, generative AI models (e.g., deep learning models for anomaly detection and pattern recognition) are installed and used for data analysis.

[1755] Data processing and calculation

[1756] Data collection and transmission:

[1757] The sensors monitor animal behavior data in real time and transmit it to a smartphone application, which then compiles the data, sends it to a server, and logs the success or failure of the transmission.

[1758] Data storage and refinement:

[1759] The server temporarily stores the received data in a buffer and performs refinement processes such as deleting duplicate data and filling in missing data. The refined data is then stored in a database such as MySQL.

[1760] Data Analysis:

[1761] The server uses the generative AI model to analyze the behavioral data stored in the database, including identifying activity patterns, detecting abnormal behavior, and suggesting optimal diet and exercise amounts. The analysis results are then stored back in the database and made available through the user interface.

[1762] Notification of results:

[1763] The server generates notifications for users based on the analysis results. The notification system operates in real time, and immediate notifications are sent to users for urgent matters. Notifications are sent to users via push notifications, email, and social media.

[1764] Specific examples

[1765] Example 1: Optimizing food portion size

[1766] If a user's dog has recently shown a decreased appetite, the sensor collects food data and sends it to a server. The server then uses a generative AI model to calculate the optimal amount of food, suggesting, for example, that a 10kg dog should eat 200g of food per day. The app then notifies the user of this information, allowing them to adjust their dog's food intake accordingly.

[1767] Example prompt: "What is the appropriate daily amount of food for a dog weighing 10 kg?"

[1768] Example 2: Exercise advice

[1769] If the user's dog has recently shown a decline in exercise, the sensor collects activity data and sends it to the server. The server analyzes the data and uses a generative AI model to calculate the optimal amount of exercise. The result is "recommended to take two 30-minute walks per day or exercise freely at a dog park," and the result is notified to the user via the application. The user can then create an exercise plan based on this.

[1770] Example prompt: "What activities do you recommend to increase my dog's exercise?"

[1771] Example 3: Detecting abnormal behavior while away from home

[1772] If the dog exhibits abnormal behavior while the user is away, the sensor collects the data and sends it to the server. The server immediately analyzes it and generates an alert notification if abnormal behavior is detected. The application then sends a push notification to the user with detailed information, allowing them to take prompt action.

[1773] Example prompt: "What is the appropriate course of action if my dog ​​exhibits abnormal behavior while I'm away?"

[1774] In this way, the system of the present invention manages the health status of animals in detail and supports owners in responding promptly and appropriately.

[1775] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1776] Step 1: Data collection

[1777] Terminal (sensor) side:

[1778] The sensors collect real-time behavioral data of the animals. Specifically, an accelerometer measures activity and posture at rest, and a GPS acquires location information. This data is collected from the sensors and recorded at regular intervals.

[1779] Input: Animal activity data (e.g., activity level, location information)

[1780] Output: raw data collected

[1781] Step 2: Send data

[1782] App (device) side:

[1783] The application periodically collects data collected from sensors and sends it to a server via the Internet. The encrypted HTTPS protocol is used for transmission. The success or failure of the transmission is recorded in a log. For example, if the transmission is successful, a "transmission completed" log is recorded, and if it fails, a "retransmission" flag is set.

[1784] Input: Raw data collected

[1785] Output: Data transferred to the server

[1786] Step 3: Temporarily store and refine data

[1787] Server side:

[1788] The server temporarily stores the received data in a buffer and performs refinement processes such as removing duplicate data and filling in missing data. Duplicate data is removed using SQL queries, and missing GPS data is filled in using a fill-in algorithm. The refined data is then stored in a database such as MySQL.

[1789] Input: Raw data transferred to the server

[1790] Output: Refinement data stored in a database

[1791] Step 4: Data analysis

[1792] Server side:

[1793] The server inputs the refined data into a generative AI model for analysis. The generative AI model identifies behavioral patterns and detects anomalies, and generates results such as recommendations for optimizing food intake and exercise. The analysis process is performed using a Python script.

[1794] Input: Refining data stored in the database

[1795] Output: Analysis results (e.g., recommendations for optimal food intake and exercise)

[1796] Step 5: Notification of results

[1797] Server side:

[1798] The server converts the analysis results into notifications and sends them to the user. For example, a push notification containing information such as a decrease in the dog's activity level or a recommendation for optimal feeding is generated. These notifications are sent to the user in real time.

[1799] Input: Analysis results

[1800] Output: Notification message (e.g. push notification, email)

[1801] Step 6: Display in the user interface

[1802] App (device) side:

[1803] The application displays notifications and advice sent from the server to the user, such as "200 grams of food per day" or "Take two 30-minute walks per day." Users can tap to view more information.

[1804] Input: Notification message

[1805] Output: Notifications and advice displayed on the user interface

[1806] Step 7: User Actions

[1807] User side:

[1808] Users can take action based on the provided notifications, such as adjusting the amount of food to the suggested 200 grams per day and creating a daily walking schedule. If they receive a notification of abnormal behavior, they can consult with a veterinarian through the app's online appointment system for prompt action.

[1809] Input: User interface notifications and advice

[1810] Output: Actual behavior (e.g., adjusting food intake, executing exercise plan)

[1811] (Application example 1)

[1812] 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."

[1813] In modern society, pet health management is an important issue for pet owners. Detecting abnormal pet behavior and responding quickly when the owner is away is particularly important for maintaining the pet's safety and health. However, existing technology does not adequately provide a system that can monitor pet behavior in real time, detect abnormal behavior, and provide prompt notification. Therefore, the present invention aims to provide a system that can detect abnormal pet behavior in real time while the owner is away and promptly notify the owner.

[1814] 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.

[1815] In this invention, the server includes means for collecting animal behavior data using a sensor, means for transmitting the collected data to the server, means for analyzing the data using a generative AI model in the server and evaluating the health condition and behavior of the animal, means for notifying the user of the evaluation results, and means for detecting abnormal behavior of animals, including dogs, while the user is away and notifying the user in real time. This makes it possible to quickly detect abnormal behavior of pets and notify the owner in real time.

[1816] "Animal" is a broad term that refers to any pet or livestock animal, including dogs.

[1817] "Behavioral data" is a general term for various data that indicate an animal's health and behavior, such as its activity level, sleep patterns, and food intake.

[1818] "Sensors" are devices used to collect animal behavioral data, and include acceleration sensors, gravity sensors, GPS, etc.

[1819] "Server" means a computer system that stores, analyzes, and manages collected data.

[1820] A "generative AI model" is a machine learning model used to analyze collected behavioral data and evaluate the health and behavior of animals.

[1821] "Means for assessing health and behavior" refers to a method for analyzing behavioral data using a generative AI model and assessing the health and behavior of animals based on the results.

[1822] "Means of notifying users" refers to methods for providing information to users based on the analysis results, and includes means such as push notifications, emails, and social media.

[1823] "Abnormal behavior" refers to animal behavior that deviates from normal patterns, including, for example, accidental ingestion, abnormal wandering, and anxiety.

[1824] "Real-time" refers to data processing and notification occurring almost immediately.

[1825] "Away" refers to the time when the user is away, and specifically refers to the time when the animal is alone.

[1826] Overall overview

[1827] The system of the present invention consists of the following main components: a sensor that collects animal behavior data, a means for transmitting the data to a server, a generative AI model that analyzes the behavior data on the server, a means for notifying the user of the analysis results, and a means for detecting abnormal behavior in real time.

[1828] Sensors and Data Collection

[1829] Terminal (sensor) side:

[1830] Sensors attached to the animal's collar or harness monitor real-time behavioral data such as activity levels, sleep patterns, and food intake. These sensors combine accelerometers, gravity sensors, and GPS. The collected data is periodically sent to a server via an application.

[1831] Data transmission and storage

[1832] App (device) side:

[1833] The application periodically collects data from the sensors and sends it to a server via the Internet. The data is encrypted to ensure security. The application logs the success or failure of data transmission and notifies the user if there is a problem.

[1834] Server side:

[1835] The server temporarily stores the received data in a buffer and then performs a data refinement process. The refined data is stored in a database and used for subsequent analysis processes. The database is designed with query efficiency in mind, allowing for quick access even to large amounts of data.

[1836] Data analysis

[1837] Server side:

[1838] The server inputs the behavioral data stored in the database into a generative AI model for analysis. The generative AI model identifies behavioral patterns and detects anomalies, and generates results such as optimizing food intake, suggesting exercise amounts, and evaluating health status. The analysis results are then saved back into the database and made available in the user interface.

[1839] Notification of results and actions

[1840] Server side:

[1841] The server generates appropriate notifications for users based on the analysis results. The notification system operates in real time, and immediate notifications are sent for urgent matters. Notifications are sent to users via push notifications, email, or social media.

[1842] App (device) side:

[1843] The application displays notifications and advice sent from the server to the user, such as recommendations for optimal meal size, exercise advice, and warnings about abnormal behavior while away from home. It also provides an interface for the user to take action based on these notifications.

[1844] User Actions

[1845] User side:

[1846] Based on the information provided through the app, users can adjust their animal's feeding and exercise schedule, take steps to respond quickly if they receive alerts about abnormal behavior while away from home, and, if necessary, use the application to schedule an online consultation with a veterinarian to obtain appropriate medical treatment.

[1847] Specific examples

[1848] Example 1: Optimizing food portion size

[1849] If a user's dog has recently shown a decreased appetite, the sensor collects food data and sends it to a server. The server then uses a generative AI model to calculate optimal feeding amounts and generate recommendations, such as "200 grams of food per day is appropriate for a 10kg dog." The application then notifies the user of this information, allowing them to adjust their feeding accordingly.

[1850] Example 2: Exercise advice

[1851] If the user's dog has recently shown a decline in exercise, the sensor collects activity data and sends it to the server. The server then uses a generative AI model to calculate the optimal amount of exercise, generating a recommendation such as "two 30-minute walks per day or free exercise at a dog park." The result is then sent to the user via the app, allowing the user to create an exercise plan based on this information.

[1852] Example 3: Detecting abnormal behavior while away from home

[1853] If the dog swallows something or exhibits abnormal behavior while the user is away, the sensor will collect the data and send it to the server. The server will immediately analyze it and generate an alert notification if it detects abnormal behavior. The application will then send a push notification to the user with detailed information, allowing the user to take necessary measures.

[1854] Example prompts to input to the generative AI model

[1855] "Enter your dog's activity levels and patterns. Generate alerts if abnormal behavior is detected."

[1856] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1857] Step 1:

[1858] The device collects real-time behavioral data from sensors attached to the animal's collar. Specifically, it uses accelerometers, gravity sensors, and GPS to collect data on the animal's activity, sleep patterns, food intake, etc. This data is temporarily stored in the device's memory.

[1859] Input: Raw data from sensors (acceleration, position).

[1860] Output: Collected behavioral data.

[1861] Specific operation: The device acquires data from the sensor at regular intervals and stores it in local memory.

[1862] Step 2:

[1863] The device periodically collects and sends the collected data to a server, where it is encrypted and securely transferred to the server via the Internet.

[1864] Input: Behavioral data stored in local memory.

[1865] Output: The encrypted data sent to the server.

[1866] Specific operation: The device converts the collected data into JSON format, encrypts it, and then sends the data to the server using an HTTP request.

[1867] Step 3:

[1868] The server temporarily stores the received data in a buffer and performs a data refinement process, which removes noise and standardizes the format. The refined data is then saved in a database.

[1869] Input: The received encrypted data.

[1870] Output: Refined behavioral data.

[1871] Specific operation: The server decrypts the encrypted data, performs preprocessing such as noise removal and missing value completion, and then stores it in the database.

[1872] Step 4:

[1873] The server inputs the behavioral data stored in the database into the generative AI model for analysis. The generative AI model detects abnormal behavior from the behavioral data and optimizes the amount of food and exercise.

[1874] Input: Refined behavioral data stored in a database.

[1875] Output: Analysis results (detection of abnormal behavior, optimization of food intake and exercise).

[1876] Specific operation: The server inputs behavioral data into the generative AI model using prompts to analyze it. For example, the prompt might say, "Enter the dog's activity level and patterns. Generate an alert if abnormal behavior is detected."

[1877] Step 5:

[1878] The server generates appropriate notifications for users based on the analysis results. Urgent matters are notified immediately. Notifications are sent to users via push notifications, email, or social media.

[1879] Input: Analysis results.

[1880] Output: A notification message to the user.

[1881] Specific operation: The server generates a notification message from the analysis results and sends a push notification or email via an HTTP request or various APIs.

[1882] Step 6:

[1883] The device displays notifications and advice sent from the server to the user, who can then adjust their behavior based on the information, such as adjusting their food intake, developing an exercise plan, or quickly responding to abnormal behavior.

[1884] Input: Notification message.

[1885] Output: Specific instructions or advice for the user to adjust their behavior.

[1886] Specific behavior: The device receives the notification message and displays it on the user interface. The user can take appropriate measures based on the notification content.

[1887] 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.

[1888] The present invention is a system that collects behavioral data of animals, particularly dogs, and analyzes it using generative artificial intelligence (generative AI model) and an emotion engine. The present invention manages the health of animals by collecting data using sensors, transmitting it to a server for analysis, and providing information based on the results and the user's emotions. Specific embodiments of the present invention will be described below.

[1889] Overall overview

[1890] The system consists of the following main components:

[1891] 1. Sensors that collect animal behavior data

[1892] 2. An application that sends data to a server

[1893] 3. Server that analyzes data and generates AI models

[1894] 4. Emotion engine that recognizes user emotions

[1895] 5. Interface for notifying users of evaluation results

[1896] Sensors and Data Collection

[1897] Terminal (sensor) side:

[1898] Sensors attached to the animal's collar or harness monitor real-time behavioral data such as activity levels, sleep patterns, and food intake. These sensors combine accelerometers, gravity sensors, and GPS. Data is periodically sent to a server via an application.

[1899] Data transmission and storage

[1900] App (device) side:

[1901] The application periodically collects data from the sensors and sends it to a server via the Internet. The data is encrypted to ensure security. The application records the success or failure of data transmission and notifies the user if there is a problem.

[1902] Server side:

[1903] The server temporarily stores the received data in a buffer and then refines it. The refined data is then stored in a database for subsequent analysis. The database is designed for query efficiency, allowing for quick access even to large amounts of data.

[1904] Data analysis

[1905] Server side:

[1906] The server inputs the behavioral data stored in the database into a generative AI model for analysis. The generative AI model identifies behavioral patterns and detects anomalies, generating results such as optimizing food intake, suggesting exercise amounts, and evaluating health status. These analysis results are then stored back in the database and made available via the user interface.

[1907] Emotion engine integration

[1908] Server side:

[1909] The server integrates an emotion engine that collects users' emotional data. The emotion data is analyzed in real time based on the user's facial expressions, voice, and text input. The emotion engine evaluates the user's stress level and emotional state and stores the results in a well-being database.

[1910] Emotion Engine in action:

[1911] The emotion engine analyzes the user's emotional data to assess stress levels and emotional fluctuations. The assessment results are then used in conjunction with a generative AI model to incorporate emotional elements into the analysis of animal health data and provide personalized notifications and advice to the user.

[1912] Notification of results and actions

[1913] Server side:

[1914] The server generates appropriate notifications for the user based on the analysis results. The notification system operates in real time, and immediate notifications are sent for urgent matters. The content of the notifications is conveyed to the user via push notifications, email, or social media. Based on the evaluation results of the emotion engine, the content of the notifications is optimized to the user's emotional state.

[1915] App (device) side:

[1916] The application displays notifications and advice sent from the server to the user. Notifications include suggestions for optimal meal sizes, exercise advice, and warnings about abnormal behavior while away from home. The application provides an interface for the user to take action based on these notifications. It also includes advice and reminders to reduce the user's stress based on information from the emotion engine.

[1917] User side:

[1918] Based on the information provided through the app, users can adjust their pet's feeding and exercise schedule. If they receive alerts about abnormal behavior while away from home, they can take steps to respond quickly. If necessary, they can also use the application to book an online consultation with a veterinarian to receive appropriate medical treatment. Furthermore, they can manage stress levels and receive emotional support by implementing advice based on the user's emotional state.

[1919] Specific examples

[1920] Example 1: Optimizing food portion size

[1921] If a user's dog has recently shown a decrease in appetite, the sensor collects food data and sends it to the server. The server then uses a generative AI model to calculate the optimal amount of food and generates recommendations such as "200 grams of food per day is appropriate for a 10kg dog." In addition, the emotion engine evaluates the user's stress level and provides advice such as "Because your current stress level is high, be careful about changing your dog's food intake."

[1922] Example 2: Exercise advice

[1923] If a user's dog has recently shown a decline in activity, sensors collect activity data and send it to a server. The server analyzes the data and uses a generative AI model to calculate the optimal amount of exercise. Results such as "recommended two 30-minute walks per day or free exercise at a dog park" are generated and notified to the user through the app. An emotion engine is also used to add encouraging messages based on the user's emotional state.

[1924] Example 3: Detecting abnormal behavior while away from home

[1925] If the dog swallows something or exhibits abnormal behavior while the user is away, the sensor collects the data and sends it to the server. The server immediately analyzes it and generates an alert notification if it detects abnormal behavior. The application then sends a push notification with detailed information to the user, allowing the user to take necessary measures. The emotion engine also provides reminders and support messages to reduce the user's impatience and anxiety.

[1926] In this way, the system of the present invention manages the animal's health condition in detail and in real time, supporting the owner in taking prompt and appropriate action. By integrating an emotion engine, it becomes possible to provide information that takes into account the user's emotional state, thereby realizing even greater user support.

[1927] The processing flow will be explained below.

[1928] Data Collection Phase

[1929] Device (sensor, app) side

[1930] Step 1: Monitoring data with sensors

[1931] The sensors measure the animals' activity levels, sleep patterns and food intake in real time.

[1932] The measured data is temporarily stored inside the sensor.

[1933] Step 2: Prepare your data for transfer

[1934] The sensor prepares to send the collected data to the app at regular intervals.

[1935] Set up the communication protocol for data transmission and format the data appropriately.

[1936] Step 3: Sending data

[1937] The app receives the data sent from the sensor and temporarily stores it in the internal storage.

[1938] Batch processing is performed at regular intervals and the data is sent to the server.

[1939] Data transmission and storage

[1940] Server side

[1941] Step 4: Receiving the data

[1942] The server has an API for receiving data sent from the app.

[1943] The received data is temporarily stored in a buffer.

[1944] Step 5: Save your data

[1945] The server pre-processes and formats the buffered data.

[1946] The preprocessed data is stored in the database.

[1947] Data analysis

[1948] Server side

[1949] Step 6: Preprocessing the data

[1950] The server retrieves the data that needs to be analyzed from the database.

[1951] The acquired data is filled in with missing values ​​and noise is removed, and it is then formatted in a form suitable for analysis.

[1952] Step 7: Input to the generative AI model

[1953] The server inputs the preprocessed data into a generative AI model.

[1954] The model analyzes the animal's behavioral patterns and extracts features.

[1955] Step 8: Generate analysis results

[1956] The generative AI model generates evaluation results such as optimizing food intake, giving exercise advice, and detecting abnormal behavior.

[1957] Store the generated results in a database.

[1958] Emotion engine integration

[1959] Server side

[1960] Step 9: Collect emotion data

[1961] The server receives the user's emotion data from the app.

[1962] Emotional data is collected in real time based on the user's facial expressions, voice, text input, etc.

[1963] Step 10: Analyze the sentiment data

[1964] The server analyzes the user's emotion data using an emotion engine.

[1965] The analysis results (stress level, emotional state) are stored in a well-being database.

[1966] Step 11: Integrating Emotional and Health Data

[1967] The server integrates the analysis results of the generative AI model and the evaluation results of the emotion engine to adjust the content of the notification.

[1968] The integration results are stored in a database and an optimized notification is generated for the user.

[1969] Notification of results and actions

[1970] Server side

[1971] Step 12: Prepare for notifications

[1972] The server periodically checks the analysis results and extracts information that should be notified to the user.

[1973] Urgent information will be given priority and immediate notification will be prepared.

[1974] Step 13: Sending notifications

[1975] The server sends notifications to the user using an appropriate notification system (e.g., Firebase Cloud Messaging).

[1976] App (device) side

[1977] Step 14: Receive notifications

[1978] The app receives notifications sent from the server.

[1979] Received notifications are displayed to the user in a visually understandable format.

[1980] User Actions

[1981] User side

[1982] Step 15: Review and respond to notifications

[1983] The user can check the notification content through the app and take the necessary action.

[1984] Adjust food and create exercise plans based on optimal feeding amounts.

[1985] Step 16: Emotionally Based Responses

[1986] The user can implement stress management and emotional support by referring to the advice provided by the emotion engine.

[1987] For example, if you have high stress levels, try relaxation techniques.

[1988] Step 17: Online consultation with your veterinarian

[1989] If necessary, users can use the app to book an online consultation with a veterinarian.

[1990] Online consultations are conducted via video calls and text chats.

[1991] This is the specific processing flow of the program. This process manages the animal's health condition in real time and supports the owner in taking appropriate action. By combining it with an emotion engine, it is possible to provide information that takes the user's emotional state into consideration.

[1992] Example 2

[1993] 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."

[1994] Currently, animal health management relies heavily on owner observation, making it difficult to manage based on objective data. Additionally, while the owner's emotional state can affect animal health management, no system exists that fully takes this into account. This can lead to delayed appropriate responses or inappropriate management. Furthermore, optimizing exercise and dietary intake requires detailed data analysis, which is unrealistic to perform manually.

[1995] The identification process 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 means for collecting animal behavior data using a sensor, means for transmitting the collected data to the server via a terminal, means for performing data refinement processing in the server and then storing the data in a database, means for analyzing the data using a generative AI model and evaluating the animal's health condition and behavior, means for notifying the user of the evaluation results, means for collecting the user's emotion data and analyzing it using an emotion engine, and means for personalizing and notifying the evaluation results based on the emotion analysis results. This makes it possible to manage the animal's health condition in detail and in real time, and to provide personalized responses that also take the owner's emotional state into consideration.

[1996] The "sensor" is a device for collecting animal behavior data in real time, and is equipped with multiple functions such as an acceleration sensor, gravity sensor, and GPS.

[1997] A "terminal" is a relay device for transmitting collected data to a server, and has functions such as encrypting data and maintaining a transmission log.

[1998] A "server" is a computer system that processes, stores, and analyzes received data, and is responsible for running generative AI models and emotion engines.

[1999] "Data refinement processing" is a process for improving the quality of collected data by removing outliers and standardizing the format.

[2000] A "database" is a system for efficiently storing and accessing refined data and analytical results.

[2001] A "generative AI model" is an artificial intelligence model that analyzes behavioral data based on machine learning algorithms to evaluate an animal's health and behavioral patterns.

[2002] The "emotion engine" is a system that collects and analyzes emotional data from users' facial expressions, voice, text input, etc., and is responsible for assessing the user's stress level and emotional state.

[2003] "Evaluation results" refer to an assessment of the animal's health and behavioral patterns, as well as the user's emotional state, based on data analyzed by the generative AI model and emotion engine.

[2004] "Personalization" means adjusting information and service content according to each user's characteristics and emotional state.

[2005] The present invention is a system that collects animal behavior data and analyzes it using a generative AI model and an emotion engine. The present invention manages the animal's health by collecting data using sensors, transmitting it to a server for analysis, and providing information based on the results and the user's emotions. Below, specific embodiments of the present invention are described.

[2006] Overall system configuration

[2007] sensor

[2008] On the terminal (sensor) side, various sensors attached to the animal's collar or harness monitor behavioral data such as activity level, sleep patterns, and food intake in real time. Hardware such as accelerometers, gravity sensors, and GPS are used.

[2009] application

[2010] The application periodically compiles data collected from sensors and sends it to a server via the Internet. This data is encrypted to ensure security. The application records the success and failure of transmissions in a log and notifies the user if an error occurs.

[2011] server

[2012] The server temporarily stores the received data in a buffer and then performs a data refinement process, which involves removing outliers and converting formats. The refined data is then stored in a database. The data is then analyzed by a generative AI model, which analyzes behavioral patterns, detects anomalies, and evaluates health status, and stores the results in a database.

[2013] Emotion Engine

[2014] The emotion engine collects and analyzes emotional data from users' facial expressions, voice, and text input in real time. The results of the emotion analysis evaluate the user's stress level and emotional state and are stored in a well-being database. This makes it possible to integrate animal health data with emotional data.

[2015] Notifications and Actions

[2016] The server combines the results of the animal's health data analysis with the user's emotional data and generates appropriate notifications. These notifications are sent to the user via push notifications, email, social media, etc. The application displays these notifications to the user and supports them in taking necessary actions. Based on the information provided through the application, users can adjust the amount of food their animal eats and create exercise plans. They can also manage their own stress by taking advice from the emotion engine.

[2017] Specific examples

[2018] Example 1: Optimizing food portion size

[2019] If a user's dog has recently lost its appetite, the sensor collects dietary data and sends it to the server. The server then uses a generative AI model to generate a recommendation such as, "200 grams of food per day is appropriate for a 10 kg dog." In addition, the emotion engine provides advice such as, "Because your current stress level is high, be careful about changing your dog's food intake."

[2020] Example prompt: Analyze your dog's recent feeding data and suggest appropriate feeding amounts. The advice should also take into account the user's emotional state.

[2021] Example 2: Exercise advice

[2022] If a user's dog has recently shown a decline in its activity level, sensors collect activity data and send it to the server. The server then uses a generative AI model to calculate the optimal amount of exercise and recommends two 30-minute walks per day or free exercise at a dog park. An emotion engine is also used to add encouraging messages based on the user's emotional state.

[2023] Example prompt: Based on the dog's exercise data, suggest the optimal amount and specific exercise method. Please also take into account the user's emotional state.

[2024] Example 3: Detecting abnormal behavior while away from home

[2025] If the dog exhibits abnormal behavior while the user is away, the sensor collects the data and sends it to the server. The server immediately analyzes the data and generates an alert if it detects abnormal behavior. The application then sends a push notification to the user with detailed information, allowing them to take necessary measures. The emotion engine also provides advice to reduce the user's impatience and anxiety.

[2026] Example prompt: Detect abnormal dog behavior while you're away and immediately generate an alert to notify the user. Include a message to ease the user's anxiety.

[2027] As described above, the system of the present invention manages the health status of animals in detail and in real time, and enables personalized measures that also take into account the user's stress level.

[2028] The flow of the identification process in the second embodiment will be described with reference to FIG.

[2029] Step 1:

[2030] Data collection

[2031] Subject: Terminal (sensor)

[2032] Sensors attached to the device monitor the animal's activity levels, sleep patterns, food intake, and other behavioral data in real time.

[2033] Input: Raw data from sensors (acceleration, gravity, position).

[2034] Specific behavior:

[2035] The accelerometer detects animal movements.

[2036] Gravity sensors are used to determine the animal's position.

[2037] GPS sensors track the location of animals.

[2038] Output: Collected behavioral data.

[2039] Step 2:

[2040] Data transmission and storage

[2041] Subject: Terminal (application)

[2042] The application compiles the data collected from the sensors at regular intervals (e.g., every 5 minutes) and sends it to a server via the Internet.

[2043] Input: Behavioral data collected from sensors.

[2044] Specific behavior:

[2045] The data is encrypted.

[2046] Establish communication with the server and send data.

[2047] The transmission result is recorded as a log, and if it fails, a retransmission attempt is made.

[2048] Output: Behavioral data sent to the server.

[2049] Step 3:

[2050] Data refinement

[2051] Subject: Server

[2052] The server temporarily stores the received data in a buffer and performs a data refinement process.

[2053] Input: Raw behavioral data sent from the device.

[2054] Specific behavior:

[2055] Outlier detection and removal.

[2056] Format conversion and data standardization.

[2057] Correcting time lag.

[2058] Output: Refined behavioral data.

[2059] Step 4:

[2060] Data storage

[2061] Subject: Server

[2062] The server stores the refined data in a database.

[2063] Input: Refined behavioral data.

[2064] Specific behavior:

[2065] Inserts data into the database.

[2066] Data saving confirmation process.

[2067] Output: Behavioral data stored in a database.

[2068] Step 5:

[2069] Data analysis

[2070] Subject: Server

[2071] The server inputs the behavioral data stored in the database into the generative AI model and performs analysis.

[2072] Input: Behavioral data stored in a database.

[2073] Specific behavior:

[2074] Load behavioral data into a generative AI model.

[2075] Machine learning algorithms are applied to analyze behavioral patterns, detect anomalies, and assess health status.

[2076] Output: Analysis results (e.g., health status assessment results).

[2077] Step 6:

[2078] Emotional data collection and analysis

[2079] Subject: Server

[2080] The server uses an emotion engine to collect and analyze emotional data from the user's facial expressions, voice, text input, etc.

[2081] Input: User's facial expression data, voice data, and text data.

[2082] Specific behavior:

[2083] Collect emotional data from input devices such as cameras and microphones.

[2084] Input data into the emotion engine and perform analysis.

[2085] Output: Sentiment analysis results (e.g. stress level, emotional state).

[2086] Step 7:

[2087] Consolidating assessment results and generating personalized notifications

[2088] Subject: Server

[2089] The server integrates the analysis results from the generative AI model and the emotion engine to generate notifications optimized for the user.

[2090] Input: Analysis results of the generative AI model, analysis results of the emotion engine.

[2091] Specific behavior:

[2092] Integrating health and emotional assessment results.

[2093] Generate notifications (e.g., suggestions for optimal exercise and dietary intake, warnings about abnormal behavior).

[2094] Output: Personalized notification.

[2095] Step 8:

[2096] Notifications and User Actions

[2097] Subject: Server and terminal (application)

[2098] The server generates a notification and sends it to the device, where the application displays it to the user, who can then take appropriate action based on the notification content.

[2099] Enter: Personalized Notifications.

[2100] Specific behavior:

[2101] Send notifications (push notifications, email, social media).

[2102] Notification display in the application.

[2103] The user takes action based on the notification (e.g., adjusting food intake, creating an exercise plan).

[2104] Output: User actions (e.g., changing food intake, starting exercise), emotional stability.

[2105] (Application example 2)

[2106] 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."

[2107] In modern society, pet health management and safety measures are important issues for pet owners. However, it has been difficult to accurately manage pet behavior data and health status in real time and quickly detect abnormal behavior. Furthermore, there has been a lack of appropriate notifications and advice that take into account the owner's emotional state, which can increase stress for the owner. Therefore, there is a need for a system that can accurately evaluate pet health and behavior, quickly detect abnormal behavior, and provide appropriate information to the owner.

[2108] The identification processing by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting animal behavior data using a sensor, means for transmitting the collected data to the server, means for analyzing the data using a generative AI model in the server and evaluating the animal's health condition and behavior, means for notifying the user of the evaluation results, means for detecting abnormal behavior, means for notifying the user of the results of the abnormal behavior detection, an emotion engine for evaluating the user's emotional state, and means for optimizing the notification content based on the evaluation results by the emotion engine. This enables real-time management of the pet's health condition and behavior and rapid detection of abnormal behavior, and makes it possible to provide the owner with appropriate notifications and advice that take the emotional state into consideration.

[2109] "Animal behavior data" refers to various data related to animal behavior, such as animal activity levels, location information, and abnormal behavior.

[2110] A "sensor" is a device that is attached to an animal's harness and is used to collect behavioral data about the animal.

[2111] "Server" refers to a computer system that analyzes collected data and manages and stores evaluation results.

[2112] A "generative AI model" is an artificial intelligence algorithm that analyzes an animal's health and behavior based on collected data.

[2113] An "emotion engine" is a system for assessing a user's emotional state and optimizing notification content based on that.

[2114] "Abnormal behavior" refers to peculiar behavior of an animal that deviates from its normal behavioral pattern.

[2115] "Notification means" refers to a method or device for notifying the user of the analysis results or abnormal behavior detection results.

[2116] "Dietary data" refers to data relating to an animal's dietary intake and eating patterns.

[2117] "Movement data" refers to data that indicates quantities and patterns related to animal movement.

[2118] "Optimization" is the adjustment of data and processes to achieve the best results for a particular purpose.

[2119] This invention is a system that collects animal behavior data and analyzes it using a generative AI model and emotion engine to manage animal health and abnormal behavior, and provides appropriate notifications to users.

[2120] Sensors and Data Collection

[2121] The sensors are attached to the animal's clothing (such as a collar) and collect real-time data on activity, location, abnormal behavior, etc. These sensors include an accelerometer, gravity sensor, and GPS.

[2122] Data transmission and storage

[2123] The device (smartphone app) periodically sends data collected from the sensors to a server. The data is encrypted and sent securely via the Internet. The server temporarily stores the received data, performs any preprocessing necessary for analysis, and then stores it in a database.

[2124] Data analysis

[2125] The server analyzes the behavioral data stored in the database using a generative AI model. The generative AI model performs the following processes:

[2126] Identifying behavioral patterns

[2127] Abnormal behavior detection

[2128] Health assessment

[2129] The server stores the analysis results in a database and makes them available via a user interface as needed.

[2130] Emotion engine integration

[2131] The server integrates an emotion engine to analyze the user's emotion data. This emotion data is analyzed in real time based on the user's facial expressions, voice, text input, etc. The emotion engine evaluates the user's stress level and emotional state and optimizes the notification content based on the results.

[2132] Notification of results and actions

[2133] The server generates appropriate notifications for users based on the analysis results and abnormal behavior detection results. The notification system operates in real time, and immediate notifications are sent for matters of high urgency. The content of the notifications is communicated to users via push notifications, email, and social media, and the content of the notifications is optimized based on the evaluation results of the emotion engine.

[2134] Specific examples

[2135] Dog Abnormal Behavior Detection: When a dog barks excessively or exhibits abnormal behavior, sensors collect the data and send it to a server, which uses a generative AI model to detect abnormal behavior and immediately notify the user.

[2136] Optimizing food intake: Collecting dog food data and using a generative AI model to calculate the optimal food intake. The results are then communicated to the user, enabling appropriate dietary management.

[2137] Emotional state-based notifications: If the emotion engine assesses that the user is feeling stressed, the notification content will be optimized accordingly and advice will be provided to reduce the user's stress.

[2138] Prompt Sentence Examples

[2139] "Please use the generative AI model to analyze abnormal behavior based on the following data. Generate notification content based on activity data, location data, behavior data, and the results, and notify the user immediately if abnormal behavior is detected."

[2140] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[2141] Step 1:

[2142] The device (smartphone app) collects behavioral data from sensors attached to the animal's harness. The sensors measure the animal's activity level, location information, abnormal behavior, etc. in real time and send the data to the device. The input data is raw data collected by the various sensors, and the output is data temporarily stored on the device.

[2143] Step 2:

[2144] The device periodically sends the collected data to a server. The data is encrypted and securely transferred over the Internet. The input is the behavioral data stored on the device, and the output is the encrypted data sent to the server. This process uses an Internet connection and a data encryption algorithm.

[2145] Step 3:

[2146] The server temporarily stores the received data in a buffer memory. The input data is the encrypted behavioral data, and the output is the decrypted original data. The server decrypts the data using a decryption algorithm.

[2147] Step 4:

[2148] The server performs preprocessing on the decrypted data, which includes data shaping, missing value imputation, outlier removal, etc. The input data is the decrypted raw data, and the output is the preprocessed clean data. The server uses preprocessing algorithms and data shaping functions.

[2149] Step 5:

[2150] The server inputs the preprocessed data into the generative AI model for analysis. The generative AI model identifies behavioral patterns from the data, detects abnormal behavior, and evaluates health status. The input data is the preprocessed data, and the output is the analysis results. The server performs data analysis using the generative AI model.

[2151] Step 6:

[2152] The server stores the analysis results in a database for further processing. The input data are the analysis results and the output is the stored data. The server uses a database management system to store the data.

[2153] Step 7:

[2154] The server collects the user's emotional data and analyzes it using an emotion engine. The emotional data can be obtained from the user's facial expressions, voice, text input, etc. The input data is the emotional data, and the output is the evaluation result of the emotional state. The server uses an emotion analysis algorithm.

[2155] Step 8:

[2156] The server optimizes the notification content to be provided to the user based on the evaluation results of the emotion engine. The input data are the evaluation results and analysis results of the emotional state, and the output is the optimized notification content. The server generates the notification content by integrating the evaluation results and analysis results of the emotion engine.

[2157] Step 9:

[2158] The server sends the optimized notification content to the user. The notification is sent via push notification, email, or SNS. The input data is the optimized notification content, and the output is the notification message to the user. The server sends the message using the notification system.

[2159] 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.

[2160] 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.

[2161] 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 robot 414.

[2162] 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.

[2163] 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.

[2164] 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 int...

Claims

1. a means for collecting animal behavior data using sensors; means for transmitting the collected data to a server; A means to analyze the data using the generated AI model on the server and evaluate the health and behavior of the animals. means for notifying the user of the evaluation result; A system including:

2. 10. The system of claim 1, further comprising means for collecting animal diet data and calculating optimal diet amounts using a generative AI model.

3. The system according to claim 1, further comprising means for suggesting an optimal exercise method and time using a generative AI model based on the animal's exercise data.

4. The system according to claim 1 , further comprising means for detecting accidental ingestion or abnormal behavior of the animal while the animal is away and issuing an alert notification.

5. 10. The system of claim 1, further comprising means for a user to schedule an online consultation with a veterinarian.

Images