system

Abstract

We provide the system. [Solution] It is a system for monitoring a dog's health status. A means of collecting data on a dog's health and behavior from sensors, A means of sending the collected data to the server, A method using a generative AI model to analyze data received on a server and determine health status, A means of visualizing the analysis results and displaying them in the form of graphs, It includes a chatbot function to receive user questions and a means to answer questions using analysis results and existing data. A system that includes this.

Description

Technical Field

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] [[ID=�5]]For many pet owners, it is difficult to appropriately understand the health status of their beloved dogs and detect early signs of illness. Also, the high medical costs and the economic burden of pet insurance are major issues. There is a need for a system that solves these problems and extends the time for pet owners to spend a long and healthy life with their beloved dogs.

Means for Solving the Problems

[0005] To solve the above problems, the present invention provides a system for understanding the health status of dogs. This system includes means for collecting data on the dog's physical condition and behavior from sensors, means for transmitting the collected data to a server, means for analyzing the received data on the server and using a generative AI model to determine the health status, means for visualizing the analysis results and displaying them in the form of graphs, and means for a chatbot function that accepts user questions and answers the questions using the analysis results and existing data. As a result, owners can understand their dog's health status in real time and take appropriate measures.

[0006] A "sensor" is a device or apparatus used to collect data about a dog's health and behavior.

[0007] "Data" refers to information about the dog's health, personality, behavior, and diet collected through sensors.

[0008] A "server" is a computing system or network used to receive, analyze, store, and provide collected data to user terminals.

[0009] A "generative AI model" is a model that incorporates artificial intelligence technology used to analyze collected data and determine the health status of dogs.

[0010] "Visualization" is the process of displaying analysis results in the form of graphs, alert messages, and other formats, making them easy for users to understand visually.

[0011] A "chatbot function" is an interface that receives user questions, generates answers using a generative AI model, and responds to users in real time.

[0012] "Health status" refers to the overall condition of a dog, including its physical condition, activity level, stress level, and dietary intake.

[0013] A "user" refers to a person who uses this system to monitor their dog's health and obtain necessary information and feedback. [Brief explanation of the drawing]

[0014] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Figure 11] This is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] This is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] This is a sequence diagram showing the processing flow of the data processing system in Example 2, which incorporates an emotion engine. [Figure 14]It is a sequence diagram showing the processing flow of a data processing system in Application Example 2 when a sentiment engine is combined.

Embodiments for Carrying Out the Invention

[0015] Hereinafter, an example of an embodiment of a system according to the technology of the present disclosure will be described with reference to the accompanying drawings.

[0016] First, the terms used in the following description will be explained.

[0017] In the following embodiments, a processor with a reference number (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of a plurality of arithmetic units. Also, the processor may be a single type of arithmetic unit or a combination of a plurality of types of arithmetic units. Examples of arithmetic units include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), and the like.

[0018] In the following embodiments, a RAM (Random Access Memory) with a reference number is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0019] In the following embodiments, a storage with a reference number is one or more non-volatile storage devices that store various programs and various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes, and the like.

[0020] In the following embodiments, the signed communication interface (I / F) is an interface that includes a communication processor and an antenna, etc. The communication interface manages communication between multiple computers. Examples of communication standards applicable to the communication interface include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0021] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." That is, "A and / or B" means that it may be A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or."

[0022] [First Embodiment]

[0023] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0024] As shown in Figure 1, the data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0025] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0026] The smart device 14 comprises a computer 36, a reception device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The reception device 38, output device 40, and camera 42 are also connected to the bus 52.

[0027] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0028] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form perceptible to the user 20 (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0029] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

[0030] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0031] As shown in Figure 2, in the data processing device 12, a specific processing is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" related to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0032] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0033] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with a specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0034] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0035] This invention relates to a system for monitoring the health status of pet dogs. Specific embodiments of this system are described below.

[0036] System Overview

[0037] This system collects data from sensors attached to dogs and from the user's device, analyzes it on a server to visualize the dog's health status, and provides this information to the owner. In addition, it is equipped with a chatbot function that provides appropriate feedback in response to user questions.

[0038] Data collection and transmission

[0039] The device collects health and behavioral data, such as heart rate, activity level, food intake, and elimination timing, from smart collars and sensors attached to the dog. This collected data is periodically encrypted in batches and sent to a server.

[0040] Data Analysis

[0041] The server stores the received data in a database. The database manages the data using a unique ID that identifies each dog. A generative AI model then analyzes the data, determining stress levels from heart rate and assessing whether the dog is getting enough exercise based on activity levels. It also compares the data with past data to check for any anomalies.

[0042] Visualization of the process

[0043] The analysis results are converted into visual formats such as graphs and alert messages. The server stores this visualization data in a database and sends it upon request from the terminal. The terminal displays this data in its user interface, allowing the user to visually understand the dog's health status.

[0044] Chatbot function

[0045] Users enter questions through the in-app chatbot interface. For example, if a user asks "Why is my dog ​​lethargic?", the question is sent from the device to the server. The server analyzes the question using a natural language processing (NLP) module and generates an appropriate answer. The generated answer is sent to the device and displayed to the user.

[0046] Explanation of specific examples

[0047] Specific examples of data collection and display.

[0048] 1. As an example, the user attaches a smart collar to a dog.

[0049] 2. The device collects data on the dog's heart rate and activity level from the smart collar.

[0050] 3. The device sends the collected data to the server.

[0051] 4. The server analyzes the data to determine the dog's stress level and activity level.

[0052] 5. The server converts the analysis results into a graph format and sends it to the terminal.

[0053] 6. The device displays the analysis results to the user, allowing them to visually understand the dog's health status.

[0054] Examples of chatbots

[0055] 1. The user notices that their dog is lethargic and enters the question, "Why is my dog ​​lethargic?" into the chatbot.

[0056] 2. The terminal sends the question to the server.

[0057] 3. The server analyzes the question and generates an answer using a generative AI model.

[0058] 4. The server generates a response stating, "Recent data indicates an increase in stress levels; please review your environment and diet," and sends it to the device.

[0059] 5. The terminal displays the generated response to the user.

[0060] In this way, the system can monitor a dog's health in real time and provide appropriate feedback to the user. This allows pet owners to detect health problems in their dogs early and take appropriate action.

[0061] The following describes the processing flow.

[0062] Step 1:

[0063] The device (smartphone app) collects data from a smart collar or sensor attached to the dog. The collected data includes heart rate, activity level, food intake, and timing of elimination.

[0064] Step 2:

[0065] The terminal collects data, groups it into batches at regular intervals, and sends it to the server using an encryption protocol.

[0066] Step 3:

[0067] Before analyzing the received data, the server first stores it in a database. The database manages the data using a unique ID that can identify each dog.

[0068] Step 4:

[0069] The server retrieves data from the database and inputs it into the generative AI model. The generative AI model uses heart rate data to assess stress levels and activity data to determine whether or not the user is getting enough exercise. It also compares the current data with past data to check for any anomalies.

[0070] Step 5:

[0071] The server converts the analysis results of the generated AI model into visualized data such as graphs and alert messages. This visualized data is then stored again in the database.

[0072] Step 6:

[0073] The device periodically sends requests to the server to retrieve the latest visualization data. These requests include the dog's unique ID.

[0074] Step 7:

[0075] The server receives the request, extracts the relevant visualization data from the database, and sends it to the terminal.

[0076] Step 8:

[0077] The device displays the received visualization data on the user interface. Users can then visually understand their dog's health status by viewing this data.

[0078] Step 9:

[0079] The user enters a question about their dog's health into the chatbot. Example: "Why is my dog ​​lethargic?"

[0080] Step 10:

[0081] The terminal sends the user's question as text data to the server. This transmission also uses an encryption protocol.

[0082] Step 11:

[0083] The server analyzes the received question using a natural language processing (NLP) module. It understands the intent of the question and extracts the information necessary to provide an appropriate response.

[0084] Step 12:

[0085] The server generates responses using a generative AI model based on the analysis results, historical records in the database, and current health data.

[0086] Step 13:

[0087] The server sends the generated response as text data to the terminal.

[0088] Step 14:

[0089] The device displays the received response in the chatbot interface, providing the user with relevant information. For example, it might display a response such as, "Recent data shows your stress levels are rising, so please check for changes in your environment and your diet."

[0090] This allows users to monitor their dog's health in real time and take swift action as needed.

[0091] (Example 1)

[0092] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0093] Monitoring and analyzing a dog's health in real time and providing easily understandable feedback to owners was not easy with conventional technology. In particular, accurately collecting diverse data on a dog's physical condition and behavior, and appropriately analyzing it to detect abnormalities early was difficult. Providing immediate answers to specific questions and problems faced by owners was also a challenge.

[0094] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0095] In this invention, the server includes means for collecting data on the dog's physical condition and behavior from sensors, means for encrypting the collected data and transmitting it to the server, means for storing the received data in a database on the server, analyzing the data using a generative AI model to determine the dog's health status, means for visualizing the analysis results and displaying them in a visual format such as a graph, and means for a chatbot function that accepts user questions and answers the questions using the analysis results and existing data. This enables a detailed understanding of the dog's health status, real-time analysis, and immediate feedback.

[0096] A "sensor" is a device used to collect data about a dog's health and behavior.

[0097] "Health data" refers to information about a dog's physiological state, such as its heart rate, body temperature, and stress level.

[0098] "Behavioral data" refers to information about a dog's daily activities, such as the amount of exercise it gets, the distance it walks, and its activity level.

[0099] "Encryption" is the process of converting data into a format that cannot be understood by a third party in order to transmit it securely.

[0100] A "server" is a computer system used to store and analyze received data.

[0101] A "database" is a system for systematically storing and managing received data.

[0102] A "generative AI model" is an artificial intelligence model that analyzes collected data to diagnose and predict the health status of dogs.

[0103] "Visualization" is the process of converting analysis results into visual formats such as graphs and charts.

[0104] A "chatbot" is an interactive interface that receives user questions and provides appropriate answers.

[0105] A "Natural Language Processing (NLP) module" is a technology that understands user questions and requests and generates appropriate responses.

[0106] This invention is a system that monitors and analyzes a dog's health status in real time and provides user-friendly feedback. The system is implemented by combining a series of hardware and software components, including sensors, terminals, and a server.

[0107] Data collection and transmission

[0108] The device collects health and behavioral data, such as heart rate, activity level, food intake, and elimination timing, from sensors attached to the dog. These sensors include smart collars. The collected data is encrypted by the device and sent to the server periodically in batches. For example, AES-256 encryption is used, and data is sent every hour.

[0109] Data storage and analysis

[0110] The server stores the transmitted data in a database. Each dog is assigned a unique ID, and the data is managed in association with that ID. The server then analyzes the data using a generative AI model, estimating stress levels from heart rate and determining insufficient exercise from activity levels. An algorithm also operates to detect anomalies by comparing them with past data.

[0111] Visualization of the process

[0112] The analysis results are converted into visual formats such as graphs and charts by the server. For example, a line graph showing the dog's stress level and a bar graph showing its activity level are generated. The server stores this visualized data back into the database and sends it to the user's terminal upon request.

[0113] User Interface

[0114] The device displays the visualized data received from the server on the user interface. This allows users to visually understand their dog's health status on the screen of their smartphone or tablet. For example, if a user sends a request such as "I want to see my dog's activity level for this month," the device retrieves the data from the server and displays it.

[0115] Chatbot function

[0116] Users can enter questions using the in-app chatbot interface. For example, "Why is my dog ​​lethargic?" The device sends this question to the server, which uses a natural language processing (NLP) module to analyze the question. It then uses a generative AI model to construct an appropriate answer and sends that answer to the device. The device then displays the generated answer to the user.

[0117] Specific example

[0118] 1. The user puts a smart collar on the dog.

[0119] 2. The device collects data on the dog's heart rate and activity level from the smart collar.

[0120] 3. The device encrypts the data it collects and sends it to the server.

[0121] 4. The server analyzes the data to determine the dog's stress level and activity level.

[0122] 5. The server converts the analysis results into a graph format and sends it to the terminal.

[0123] 6. The device displays the analysis results to the user, allowing them to visually understand the dog's health status.

[0124] 7. The user enters the question "Why is my dog ​​lethargic?" into the chatbot.

[0125] 8. The server analyzes the question and generates a response, "Recent data shows your stress levels are rising, so please check for changes in your environment and your diet," and sends it to the terminal.

[0126] 9. The device displays the generated response to the user.

[0127] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0128] Step 1:

[0129] Data collection

[0130] The device collects data from smart collars and various sensors attached to the dog. The sensors measure data such as heart rate, activity level, food intake, and elimination timing. Input is raw data from the sensors, and output is provided in an appropriately formatted form. For example, the smart collar measures the heart rate every 10 seconds and transmits that data to the device.

[0131] Step 2:

[0132] Data transmission

[0133] The device performs an encryption process on the collected data. Specifically, it protects the data using encryption algorithms such as AES-256, and then periodically sends it to the server in batches. The input is formatted data, and the output is encrypted, transferable data. For example, the device sends all the data to the server every hour.

[0134] Step 3:

[0135] Data storage

[0136] The server decrypts the received encrypted data and stores it in the database. Each dog is identified by a unique ID, and the data is stored associated with that ID. The input is encrypted data sent to the server, and the output is the decrypted data stored in the database. For example, the server registers the data for DogID1234 in the database.

[0137] Step 4:

[0138] Data Analysis

[0139] The server analyzes stored data using a generative AI model. Specifically, it estimates stress levels from heart rate data and determines whether or not a person is getting enough exercise from activity level data. It also detects outliers by comparing them with past data. The input is data stored in a database, and the output is the stress level and exercise deficiency determination results as analysis results. For example, the server compares and analyzes heart rate data from the past week to determine the stress level.

[0140] Step 5:

[0141] Data visualization

[0142] The server converts the analysis results into visual formats such as graphs and charts. Based on the analysis results, it formats the data in a visually easy-to-understand form (e.g., line graphs, bar graphs, alert messages). The input is the analysis results, and the output is the generated visualized data. For example, the server creates a line graph showing the changes in a dog's stress level over time.

[0143] Step 6:

[0144] Data Request Processing

[0145] The user sends a request from their device, and the server provides data accordingly. The device sends a request to the server based on the user's request, for example, "I want to see my dog's activity level for this month." The server receives the request, searches the database for the necessary data, and sends the visualized data to the device. The input is the user's request, and the output is the visualized data displayed on the device.

[0146] Step 7:

[0147] Chatbot function

[0148] The user enters a question using the in-app chatbot interface. For example, "Why is my dog ​​lethargic?" The device sends this question to the server, which uses a natural language processing (NLP) module to analyze the question. It then uses a generative AI model to generate an appropriate answer and sends it to the device. The device displays the generated answer to the user. For example, it might generate an answer such as, "Recent data shows an increase in stress levels, so please check for changes in the environment and your dog's diet."

[0149] (Application Example 1)

[0150] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0151] Conventional systems for monitoring a dog's health primarily focused on providing collected data to owners, limiting how this information could be utilized in physical stores. Furthermore, they lacked specific recommendations based on the dog's health and effective coordination with veterinary hospitals in case of abnormalities, making it difficult for owners to take prompt action. Therefore, more comprehensive monitoring and immediate response are needed.

[0152] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0153] In this invention, the server includes means for collecting data on the dog's physical condition and behavior from sensors; means for transmitting the collected data to the server; means for analyzing the received data on the server and using a generative AI model to determine the dog's health status; means for visualizing the analysis results and displaying them in the form of graphs or the like; means for a chatbot function to receive user questions and answer those questions using the analysis results and existing data; means for displaying the dog's health data when the dog visits a pet supply store or veterinary hospital; means for recommending appropriate pet food and supplements based on the health data; and means for making an appointment in cooperation with a veterinary hospital if an abnormality is detected. This enables comprehensive monitoring of the dog's health status and immediate response.

[0154] A "sensor" is a device used to collect data about a dog's physical condition and behavior.

[0155] A "server" is a computer system that receives collected data, analyzes it, and provides the necessary information.

[0156] A "generative AI model" is an artificial intelligence model used to assess a dog's health status, deriving analysis results from multiple data points.

[0157] "Visualization" is a technique that makes information easier to understand intuitively by displaying data and analysis results in graphs and other visual formats.

[0158] A "chatbot function" is a feature that receives questions from users and automatically generates answers based on analysis results and existing data.

[0159] A "pet supply store" is a physical store that sells products related to pets.

[0160] A "veterinary hospital" is a medical facility that specializes in the health management and treatment of animals.

[0161] "Health data" is a general term for information about a dog's physical condition, behavior, diet, etc.

[0162] "Recommendation" refers to recommending appropriate products or services to users based on analysis results.

[0163] "Collaboration" refers to a means of directly communicating with animal hospitals and taking appropriate action when an abnormality is detected.

[0164] A "reservation" is the process of setting a date and time in advance to use a service.

[0165] This invention is a system for monitoring a dog's health status, intended for use in pet supply stores and veterinary clinics. Specific embodiments of this system are described below.

[0166] Hardware and software to use

[0167] Hardware:

[0168] Smartphone (user's device)

[0169] Smart collar (a sensor worn on a dog)

[0170] software:

[0171] Flask (Web framework)

[0172] Python (a programming language)

[0173] Generative AI models (data analysis and chatbot functionality)

[0174] Data collection and transmission

[0175] The device collects health and behavioral data, such as heart rate, activity level, food intake, and elimination timing, from smart collars and sensors attached to the dog. This collected data is periodically encrypted in batches and sent to a server.

[0176] Data Analysis

[0177] The server stores the received data in a database. The database manages the data using a unique ID that identifies each dog. A generative AI model then analyzes the data, determining stress levels from heart rate and assessing whether the dog is getting enough exercise based on activity levels. It also compares the data with past data to check for any anomalies.

[0178] Visualization of the process

[0179] The analysis results are converted into visual formats such as graphs and alert messages. The server stores this visualization data in a database and sends it upon request from the terminal. The terminal displays this data in its user interface, allowing the user to visually understand the dog's health status.

[0180] Use at physical stores

[0181] When pet owners visit pet supply stores or veterinary clinics, health data is collected from smart collars and sensors worn by their dogs. The analysis results are instantly displayed on a terminal and provided to the owner. Based on the analysis results, there is a function to recommend appropriate pet food and supplements. In addition, if an abnormality is detected, it is possible to make an appointment directly through a linkage function with the veterinary clinic.

[0182] Chatbot function

[0183] Users enter questions through the in-app chatbot interface. For example, if a user asks "Why is my dog ​​lethargic?", the question is sent from the device to the server. The server analyzes the question using a natural language processing (NLP) module and generates an appropriate answer. The generated answer is sent to the device and displayed to the user.

[0184] Specific example

[0185] A user visits a pet shop and uses a smartphone app to read data from a dog wearing a smart collar.

[0186] When you enter "Please tell me about your recent health status" into the app, your health data is sent to the server, and the analysis results are returned to the app.

[0187] The app provides advice such as, "Your recent heart rate has been high, which may indicate you are experiencing a lot of stress. Please create a stress-free environment for yourself."

[0188] Examples of prompt messages include, "My dog's activity level is low. What are the possible causes and solutions?" and "Based on recent data, please recommend a suitable food for my pet."

[0189] In this way, the system can monitor a dog's health in real time and provide appropriate feedback to the user. This allows pet owners to detect health problems in their dogs early and take appropriate action.

[0190] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0191] Step 1:

[0192] The user collects data from a smart collar attached to the dog.

[0193] Input: Dog's health and behavioral data

[0194] Output: The collected data is stored on the device.

[0195] Specific operation: The device collects data such as heart rate, activity level, and food intake from the smart color's sensors via Bluetooth.

[0196] Step 2:

[0197] The device encrypts the collected data and sends it to the server.

[0198] Input: Collected health and behavioral data of dogs

[0199] Output: Encrypted data is sent to the server.

[0200] Specific operation: The terminal encrypts the data using AES and sends it to the server using the HTTPS protocol.

[0201] Step 3:

[0202] The server stores the received data in the database.

[0203] Input: Encrypted dog health and behavior data

[0204] Output: Data stored in the database

[0205] Specific operation: The server releases the incoming data and stores it in the database, identifying each dog with a unique ID.

[0206] Step 4:

[0207] The server uses a generative AI model to analyze the data.

[0208] Input: Dog health and behavioral data stored in the database

[0209] Output: Analysis results of health status

[0210] Specific operation: The server uses a generated AI model to analyze heart rate and activity data to determine the dog's stress level and lack of exercise.

[0211] Step 5:

[0212] The server visualizes the analysis results in graphs and alert messages.

[0213] Input: Analysis results of health status

[0214] Output: Visualized data (graphs, alert messages)

[0215] Specific operation: The server converts the analysis results into graphs using visualization libraries such as D3.js, and also generates alert messages if necessary.

[0216] Step 6:

[0217] The server sends the visualized data to the terminal.

[0218] Input: Visualized data

[0219] Output: Visualized data delivered to the terminal

[0220] Specific operation: The server converts the visualization data into JSON format and sends it to the terminal using the HTTPS protocol.

[0221] Step 7:

[0222] The terminal displays visualized data in its user interface.

[0223] Input: Visualization data

[0224] Output: Graphs and alert messages displayed in the user interface

[0225] Specific operation: The terminal parses the received JSON data and displays the data in the user interface using HTML and JavaScript (registered trademark).

[0226] Step 8:

[0227] Users enter their questions through a chatbot interface.

[0228] Input: Question for the chatbot (e.g., "Why is my dog ​​lethargic?")

[0229] Output: Question data to send to the server

[0230] Specific operation: The terminal uses a natural language processing module to initially process the question entered by the user and then sends it to the server.

[0231] Step 9:

[0232] The server analyzes the question using a natural language processing module and generates an answer.

[0233] Input: Question data

[0234] Output: Generated answer

[0235] Specific operation: The server analyzes the question using the natural language processing module of the generative AI model and generates an appropriate answer based on health data.

[0236] Step 10:

[0237] The server sends the generated response to the terminal.

[0238] Input: Generated answer

[0239] Output: Response data received on the device

[0240] Specific operation: The server converts the generated response into JSON format and sends it to the terminal using the HTTPS protocol.

[0241] Step 11:

[0242] The terminal displays the generated response to the user.

[0243] Input: Response data

[0244] Output: Answer displayed in the user interface

[0245] Specific operation: The device analyzes the received response data and displays the response in the chatbot interface using HTML and JavaScript.

[0246] Through the above processing steps, it is possible to monitor the dog's health status in real time and provide appropriate feedback to the user.

[0247] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0248] This invention provides a system for understanding the health status of pet dogs and taking appropriate measures, and in particular, by combining it with an emotion engine that recognizes the user's emotions, it achieves more accurate feedback. Specific embodiments of this system are described below.

[0249] System Overview

[0250] This system collects data from sensors attached to dogs and from the user's device, analyzes it on a server, and visualizes the dog's health status. It also features an emotion engine that recognizes the user's emotional state, and the chatbot adjusts its responses accordingly.

[0251] Data collection and transmission

[0252] The device (smartphone app) collects data from smart collars and sensors attached to the dog. This data includes heart rate, activity level, food intake, and elimination timing. This collected data is periodically encrypted in batches and sent to the server.

[0253] Data Analysis

[0254] The server stores the received data in a database. The database manages the data using a unique ID that can identify each dog. A generative AI model then analyzes the data, using heart rate data to assess stress levels and activity data to determine if the dog is getting enough exercise. It also compares the data with past data to check for any anomalies.

[0255] Visualization of the process

[0256] The analysis results are converted into visual formats such as graphs and alert messages. The server stores this visualization data back into a database and sends it upon request from the terminal. The terminal displays this data in its user interface, allowing the user to visually understand the dog's health status.

[0257] Chatbot function

[0258] Users enter questions through the in-app chatbot interface. For example, if a user asks, "Why is my dog ​​lethargic?", the question is sent from the device to the server. The server analyzes the question using a natural language processing (NLP) module and generates an appropriate answer. The generated answer is sent to the device and displayed to the user.

[0259] User emotion recognition

[0260] The device inputs the user's voice data and facial expression data into the emotion engine. The emotion engine uses voice analysis and image analysis to determine the user's emotional state.

[0261] Emotion-based feedback

[0262] The server adjusts the chatbot's responses based on emotional data obtained from the emotion engine. For example, if the user is feeling anxious, it will generate a response in a gentler tone to provide more reassurance. This allows the user to receive more appropriate feedback.

[0263] Explanation of specific examples

[0264] Specific examples of data collection and display.

[0265] 1. As an example, the user attaches a smart collar to a dog.

[0266] 2. The device collects data on the dog's heart rate and activity level from the smart collar.

[0267] 3. The device sends the collected data to the server.

[0268] 4. The server analyzes the data to determine the dog's stress level and activity level.

[0269] 5. The server converts the analysis results into a graph format and sends it to the terminal.

[0270] 6. The terminal displays the analysis results on the user interface, allowing the user to visually understand the dog's health status.

[0271] Concrete examples of emotional engines

[0272] 1. The user enters a question into the chatbot about their dog's lethargy.

[0273] 2. The device inputs the user's voice and facial expression data into the emotion engine.

[0274] 3. The emotion engine analyzes the user's emotional state and determines that they are anxious.

[0275] 4. The device sends the question and sentiment data to the server.

[0276] 5. The server generates appropriate responses that take emotional data into account. For example, it might generate a gentle-toned response such as, "Recent data shows your stress levels are rising, so please review your environment and diet."

[0277] 6. The terminal displays the generated response in the chatbot interface, providing the user with appropriate information.

[0278] This allows users to monitor their dog's health in real time and receive appropriate feedback tailored to their emotions.

[0279] The following describes the processing flow.

[0280] Step 1:

[0281] The terminal (smartphone app) collects data such as heart rate, activity level, food intake, and excretion timing from the smart collar and sensors worn by the dog. The collected data includes information regarding the dog's physical condition and behavior.

[0282] Step 2:

[0283] The terminal batches the collected data at regular intervals and transmits it to the server using a secure encryption protocol. This transmission process is carried out to ensure the real-time nature and security of the data. [[ID=十六]] [[ID=十七]]

[0284] [[ID=十八]] Step 3:

[0285] Before analyzing the received data, the server first stores it in the database. The database adopts a mechanism where data is managed with a unique ID that can identify each dog.

[0286] Step 4:

[0287] The server inputs the data from the database into the generative AI model for data analysis. The generative AI model evaluates the stress level from the heart rate data, determines the presence or absence of lack of exercise from the activity level data, and also checks for any outliers compared to past data.

[0288] Step 5:

[0289] The server converts the analysis results of the generative AI model into visualization data such as graphs and alert messages. These visualization data are stored in the database again.

[0290] Step 6:

[0291] The device periodically sends requests to the server to retrieve the latest visualization data. Because these requests include the dog's ID, the appropriate data is obtained.

[0292] Step 7:

[0293] The server receives the request, extracts the relevant visualization data from the database, and sends it to the terminal.

[0294] Step 8:

[0295] The device displays the received visualization data on the user interface. The user can then visually understand the dog's health condition by viewing this data.

[0296] Step 9:

[0297] The user enters questions about their dog's health into the chatbot. These questions are specific, such as, "Why is my dog ​​lethargic?"

[0298] Step 10:

[0299] The terminal sends the user's questions to the server as text data. Encryption protocols are used during this process to ensure data security.

[0300] Step 11:

[0301] The server inputs the received question into a natural language processing (NLP) module to analyze the intent of the question. It then extracts the information necessary to generate an appropriate answer.

[0302] Step 12:

[0303] The server generates answers to questions using a generative AI model. The generated answers are adjusted as needed based on the user's question.

[0304] Step 13:

[0305] The server transmits the generated answer to the terminal as text data.

[0306] Step 14:

[0307] The terminal displays the received answer on the chatbot interface and provides appropriate information to the user. For example, specific advice such as "In recent data, the stress level has been rising, so please check the environmental changes and the content of your diet" is displayed.

[0308] Step 15:

[0309] The terminal inputs the user's voice data and facial expression data into the emotion engine. The emotion engine uses voice analysis and image analysis to judge the user's emotional state.

[0310] [[ID=�22]] Step 16:

[0311] Based on the data obtained from the emotion engine, the server adjusts the chatbot's answer. For example, when the user is feeling anxious, an answer in a gentle tone that gives more of a sense of security is generated.

[0312] Step 17:

[0313] The terminal displays the answer according to the emotion on the chatbot interface and conveys it to the user. As a result, the user can receive optimal feedback according to the situation.

[0314] In this way, this system can monitor the health status of the dog in real time and provide appropriate feedback based on the user's emotion.

[0315] (Example 2)

[0316] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0317] Traditional dog health management systems have limitations in analyzing collected data and providing feedback to users. Furthermore, they fail to consider user emotions, resulting in an inadequate user experience. Additionally, they lack a clear means of providing detailed analysis results based on the dog's health and behavior, making it difficult for users to take appropriate action.

[0318] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0319] In this invention, the server includes means for collecting data on the dog's physical condition and behavior from sensors, means for transmitting the collected data to the server, means for analyzing the received data on the server and using a generative AI model to determine the dog's health status, means for visualizing the analysis results and displaying them in the form of a graph or the like, a chatbot function that accepts user questions and answers the questions using the analysis results and existing data, and means for adjusting the chatbot's responses using an emotion engine that recognizes the user's emotions. This enables detailed analysis of the dog's health status and provides the user with appropriate feedback that responds to their emotions.

[0320] A "sensor" is a device attached to a dog to collect data about its physical condition and behavior.

[0321] "Health data" refers to physiological data such as heart rate and body temperature collected to evaluate a dog's health status.

[0322] "Behavioral data" includes data such as the dog's activity level, distance traveled, food intake, and timing of elimination.

[0323] A "terminal" is a communication device used to collect and transmit data, and primarily refers to mobile devices such as smartphones and tablets.

[0324] A "server" is a computer system that receives collected data, performs analysis, and provides the results.

[0325] A "generative AI model" is a model that includes an algorithm that uses machine learning to analyze received data and determine a person's health status.

[0326] "Visualization" refers to converting the results of data analysis into visual formats such as graphs and alert messages, and displaying them in a way that is easy for users to understand.

[0327] A "graph" is a graphic representation used to visually display analysis results, and includes line graphs, pie charts, and other similar types of graphs.

[0328] A "chatbot" is a conversational system that receives user questions and automatically generates answers.

[0329] A "natural language processing module" is a module that includes technology for analyzing user-inputted questions and generating appropriate answers.

[0330] An "emotion engine" is a system that includes technology to determine a user's emotional state from their voice and facial expressions and respond accordingly.

[0331] "Feedback" refers to information provided based on analysis results and user questions, particularly responses that take into account the user's emotional state.

[0332] This invention is a system that monitors a dog's health and provides appropriate feedback to the user. The system comprises sensors attached to the dog, a terminal that collects and transmits data, a server that analyzes the data, and multiple modules for visualizing the analysis results and interacting with the user.

[0333] Hardware configuration

[0334] The sensors collect data such as the dog's heart rate, activity level, food intake, and timing of urination and defecation.

[0335] The device takes the form of a smartphone or tablet, receives data from sensors, and transmits it to a server. It is equipped with data communication capabilities using Bluetooth or Wi-Fi.

[0336] A server is a computer system for storing and analyzing received data, and it runs an analysis engine that uses a database and a generative AI model.

[0337] Software Configuration

[0338] The terminal application has the function of collecting data from sensors, encrypting it, and sending it to the server. It also provides a user interface, displaying visualized data and allowing interaction through a chatbot.

[0339] The server software receives, stores, and analyzes data. The generated AI model is implemented using Python and TENSORFLOW®. The analysis results are visualized using a JavaScript graph plotting library (e.g., Chart.js).

[0340] The emotion engine analyzes user emotions from voice data and facial expression data using Microsoft® Azure® Emotion API and other tools.

[0341] The natural language processing module uses the Google® Cloud Natural Language API to analyze user questions and generate appropriate answers.

[0342] Specific example

[0343] Data collection

[0344] The user attaches a smart collar to their dog.

[0345] The device collects heart rate and activity data from the smart color, encrypts it, and sends it to the server.

[0346] Data analysis and visualization

[0347] The server analyzes the received data using a generating AI model, assessing stress levels from heart rate data and determining whether or not there is a lack of exercise from activity level data. It also checks for anomalies by comparing them with past data.

[0348] The analysis results are visualized as graphs and alert messages. For example, if a dog's activity level drops sharply, an alert will be displayed.

[0349] Emotion recognition and feedback

[0350] The user enters a question through the chatbot. For example, they might ask, "Why is my dog ​​lethargic?"

[0351] The device inputs voice data and facial expression data into an emotion engine to analyze the user's emotions.

[0352] The server adjusts the chatbot's responses based on emotional data to generate reassuring answers. For example, it might respond with something like, "Recent data shows your stress levels are rising, so please check your environment and diet."

[0353] Example of a prompt

[0354] "What data is needed to understand a dog's health status?"

[0355] "How can I adjust responses based on user sentiment?"

[0356] This system allows users to gain a detailed understanding of their dog's health and receive appropriate feedback tailored to their emotions.

[0357] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0358] Step 1:

[0359] The user attaches sensors to the dog. The sensors measure heart rate, activity level, food intake, and timing of elimination, etc. This becomes the input data.

[0360] Step 2:

[0361] The device collects data from sensors via Bluetooth or Wi-Fi. This collected data includes heart rate, activity level, food intake, and timing of bowel movements. The data is encrypted within the device. The encryption process ensures the confidentiality of the data. This is then processed and output as data.

[0362] Step 3:

[0363] The terminal periodically sends encrypted data to the server in batches. The input is encrypted data, ensuring that the data reaches the server securely.

[0364] Step 4:

[0365] The server decrypts the received encrypted data and stores it in the database. Each dog is assigned a unique ID, and the data is managed based on this ID. The input data is encrypted data, and the output is data correctly stored in the database.

[0366] Step 5:

[0367] The server uses a generative AI model to analyze data. Specifically, it assesses stress levels from heart rate data and determines whether or not the user is not getting enough exercise from activity level data. It also compares current data with past data to detect anomalies. The input is data read from a database, and the output is the analysis results.

[0368] Step 6:

[0369] The server converts the analysis results into graphs and alert messages. For example, it can generate graphs using a JavaScript graph plotting library (e.g., Chart.js). The input is the analysis results, and the output is the visualized graphs and messages.

[0370] Step 7:

[0371] The server restores the visualized data in the database and sends it in response to requests from the terminal. The input is the visualized data, and the output is the data sent to the terminal.

[0372] Step 8:

[0373] The terminal displays the analysis results on the user interface. This allows the user to visually understand the dog's health status. The input is visualized data received from the server, and the output is the display on the user interface.

[0374] Step 9:

[0375] The user enters a question through the chatbot interface. For example, they might ask, "Why is my dog ​​lethargic?" The input is the user's question.

[0376] Step 10:

[0377] The terminal sends the user's question to the server. The input is the user's question, and the output is the question data sent to the server.

[0378] Step 11:

[0379] The server uses a natural language processing module to analyze the user's question and generate an appropriate answer. For example, it might respond with, "Recent data indicates that your dog's stress level has increased. Please check for changes in its environment and its diet." The input is the user's question, and the output is the generated answer.

[0380] Step 12:

[0381] The server sends the generated response to the terminal. The input is the generated response, and the output is the data sent to the terminal.

[0382] Step 13:

[0383] The terminal displays the response in the chatbot interface, providing the user with appropriate feedback. The input is the response received from the server, and the output is the display on the user interface.

[0384] Step 14:

[0385] The device inputs the user's voice data and facial expression data into the emotion engine. This initiates the analysis of emotions. The input consists of the user's voice data and facial expression data.

[0386] Step 15:

[0387] The emotion engine uses voice and image analysis to determine the user's emotional state. For example, it can check whether the user is feeling anxious. The input is voice data and facial expression data, and the output is the user's emotional state.

[0388] Step 16:

[0389] The device sends emotional data to the server. The input is emotional data, and the output is the data sent to the server.

[0390] Step 17:

[0391] The server adjusts the chatbot's responses based on emotional data. For example, if the user is feeling anxious, it will generate a reassuring response in a gentle tone. The input is emotional data, and the output is the adjusted response.

[0392] Step 18:

[0393] The server sends the adjusted response to the terminal. The input is the adjusted response, and the output is the data sent to the terminal.

[0394] Step 19:

[0395] The device displays the adjusted response in the chatbot interface. This allows the user to receive emotion-sensitive feedback. The input is the adjusted response received from the server, and the output is the display on the user interface.

[0396] Step 20:

[0397] Users can receive feedback and take appropriate action.

[0398] (Application Example 2)

[0399] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as a "server" and the smart device 14 as a "terminal".

[0400] In recent years, interest in pet health management has increased, but there is a lack of integrated systems that allow owners to understand their dog's health status and respond appropriately if suspicious situations arise. Furthermore, pet health management and security monitoring are often handled by separate systems, making unified management difficult. Additionally, the lack of means for users to check their dog's health status and behavior in real time has also been pointed out.

[0401] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting data on the dog's physical condition and behavior from sensors, means for transmitting the collected data to software, means for using a generative AI model in the software to analyze the received data and determine the health status, means for visualizing the analysis results and displaying them in the form of a graph or the like, means for a chatbot function that accepts user questions and answers the questions using the analysis results and existing data, means for monitoring the dog's behavior and environment and notifying the user if a suspicious situation occurs, and means for the user to check the dog's real-time data using a smart device. This makes it possible to provide a system that integrates pet health management and security monitoring.

[0402] A "system" refers to an integrated group of devices that monitor a dog's health and behavior, analyze the collected data, and provide the results to the user.

[0403] A "sensor" is a device attached to a dog to collect data about its health and behavior.

[0404] "Software" refers to a series of programs that receive and analyze data transmitted from sensors.

[0405] A "generative AI model" is an artificial intelligence technology used to analyze received data and determine the health status of a dog.

[0406] "Visualization" refers to the process of displaying analysis results in a visual format, such as a graph.

[0407] A "chatbot" is an automated response system that receives questions from users and generates answers using analysis results and existing data.

[0408] A "notification" is a message sent to the user to inform them if there are any suspicious circumstances regarding the dog's behavior or environment.

[0409] A "smart device" is an interactive electronic device that allows users to check their dog's data in real time.

[0410] This invention is an integrated system for monitoring a dog's health and behavior and providing that information to the user. The system includes sensors attached to the dog, software to receive and analyze the data, a generative AI model, a chatbot to interact with the user, and a smart device.

[0411] Data collection

[0412] Sensors attached to the dog collect data such as heart rate, activity level, food intake, and elimination timing. The sensors transmit this data to software at regular intervals.

[0413] Data transmission and analysis

[0414] The software sends the collected data to the software, and a generating AI model analyzes that data. This analysis includes comparing it with historical data stored in a database to identify anomalies and health risks. For example, if an abnormal heart rate or decreased activity level is detected, a corresponding notification is generated.

[0415] Data visualization and notification

[0416] The analysis results are converted into visual formats such as graphs and alert messages. The software stores this visualization data in a database and sends it upon request from a smart device. The smart device, such as smart glasses, displays this data on a user interface, allowing the user to monitor their dog's health in real time.

[0417] The system also monitors the dog's behavior and environment, and notifies the user if any suspicious situations are detected. For example, if the dog stays in an unusual location for an extended period, or if unusual noises are heard, an alert is immediately sent to the user.

[0418] Chatbot functionality and emotion recognition

[0419] Users can enter questions through the in-app chatbot. These questions are sent to the software, and a generative AI model generates appropriate answers. The software inputs the user's voice and facial expression data into an emotion engine to analyze the user's emotional state. The chatbot's answers are then adjusted based on the emotional state. For example, if the user is feeling anxious, a gentle tone of voice will be used to provide the answer.

[0420] Specific example

[0421] As a concrete example, consider a scenario where a user attaches a smart collar to their dog, and data such as heart rate and activity levels are collected from this collar. The collected data is sent to software and analyzed by a generative AI model. The analysis results are displayed in graph format on smart glasses, allowing the user to visually check the dog's health status. Furthermore, if there is an abnormality in the dog's behavior, for example, if the dog remains still for an unusually long period, the user will be notified. In this case, a message such as, "Your dog's heart rate is higher than normal. Recent data indicates an increased stress level, so please check for changes in the environment and its diet," will be provided via a chatbot.

[0422] Examples of prompts for a generative AI model:

[0423] Please help with the "Pet Health Management Security System." Based on the following information, please create a notification message for the user when displayed in real time on smart glasses: Dog's heart rate: 120, activity level: low. Related information: Suggests lack of exercise. Please make the message specific and in a gentle tone.

[0424] Thus, this invention enables the provision of a system that integrates dog health management and security monitoring, providing users with a means to check their dog's data in real time and take appropriate action.

[0425] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0426] Step 1:

[0427] The device collects data such as heart rate, activity level, food intake, and elimination timing from sensors attached to the dog. In this data collection process, the device periodically receives the biometric data acquired by the sensors and stores it in digital format. The input is biometric data from the sensors, and the output is digital data stored in the device.

[0428] Step 2:

[0429] The device transmits the collected data to the software. At this time, the device encrypts the data before transmission to ensure communication security. The input is digital data stored on the device, and the output is encrypted data packets. Specifically, the device encrypts the data using the pet sensor SDK and sends it to the server as an HTTP request.

[0430] Step 3:

[0431] The server receives data sent from the terminal and stores it in a database. The server then analyzes the received data and prepares it for input into the generated AI model. The input is encrypted data packets, and the output is digital data stored in the database.

[0432] Step 4:

[0433] The server analyzes data using a generative AI model. Specifically, the AI ​​model analyzes heart rate and activity level data stored in the database to determine the user's health status. The generative AI model detects anomalies by comparing current data with past data. The input is digital data stored in the database, and the output is the health status assessment result.

[0434] Step 5:

[0435] The server visualizes the analysis results. The analysis results are converted into formats such as graphs and alert messages, making them easy to understand visually. The input is the health status assessment results analyzed by the generative AI model, and the output is visualized data (e.g., graphs and alert messages).

[0436] Step 6:

[0437] The server stores the visualized data back into the database and sends it in response to requests from the terminal. The input is the visualized data, and the output is the data sent to the terminal. Specifically, the server sends graph data and alert messages to the terminal as an HTTP response.

[0438] Step 7:

[0439] The terminal displays visualized data on a user interface, allowing users to check their dog's health status. The input is visualized data received from the server, and the output is graphs and alert messages displayed on the user interface.

[0440] Step 8:

[0441] When a user enters a question through the in-app chatbot interface, that question is sent from the device to the server. The input is the user's question, and the output is the data sent to the server.

[0442] Step 9:

[0443] The server analyzes the question using a natural language processing (NLP) module and generates an appropriate answer using a generative AI model. The input is the user's question, and the output is the generated answer.

[0444] Step 10:

[0445] The server sends the generated response to the terminal and displays it in the chatbot interface. The input is the generated response, and the output is the data sent to the terminal. The terminal displays the response in the user interface for the user to confirm.

[0446] Step 11:

[0447] The device inputs the user's voice data and facial expression data into an emotion engine to determine their emotional state. The input is voice data and facial expression data, and the output is the analyzed emotion data.

[0448] Step 12:

[0449] The server adjusts the chatbot's responses based on emotional data obtained from the emotion engine. The input is the analyzed emotional data and the generated response, and the output is the adjusted, gentle-toned response.

[0450] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0451] Data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0452] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart device 14.

[0453] [Second Embodiment]

[0454] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0455] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0456] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0457] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0458] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0459] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0460] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0461] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0462] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0463] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0464] In the smart glasses 214, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0465] Next, the identification processing performed by the identification processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0466] This invention relates to a system for monitoring the health status of pet dogs. Specific embodiments of this system are described below.

[0467] System Overview

[0468] This system collects data from sensors attached to dogs and from the user's device, analyzes it on a server to visualize the dog's health status, and provides this information to the owner. In addition, it is equipped with a chatbot function that provides appropriate feedback in response to user questions.

[0469] Data collection and transmission

[0470] The device collects health and behavioral data, such as heart rate, activity level, food intake, and elimination timing, from smart collars and sensors attached to the dog. This collected data is periodically encrypted in batches and sent to a server.

[0471] Data Analysis

[0472] The server stores the received data in a database. The database manages the data using a unique ID that identifies each dog. A generative AI model then analyzes the data, determining stress levels from heart rate and assessing whether the dog is getting enough exercise based on activity levels. It also compares the data with past data to check for any anomalies.

[0473] Visualization of the process

[0474] The analysis results are converted into visual formats such as graphs and alert messages. The server stores this visualization data in a database and sends it upon request from the terminal. The terminal displays this data in its user interface, allowing the user to visually understand the dog's health status.

[0475] Chatbot function

[0476] Users enter questions through the in-app chatbot interface. For example, if a user asks "Why is my dog ​​lethargic?", the question is sent from the device to the server. The server analyzes the question using a natural language processing (NLP) module and generates an appropriate answer. The generated answer is sent to the device and displayed to the user.

[0477] Explanation of specific examples

[0478] Specific examples of data collection and display.

[0479] 1. As an example, the user attaches a smart collar to a dog.

[0480] 2. The device collects data on the dog's heart rate and activity level from the smart collar.

[0481] 3. The device sends the collected data to the server.

[0482] 4. The server analyzes the data to determine the dog's stress level and activity level.

[0483] 5. The server converts the analysis results into a graph format and sends it to the terminal.

[0484] 6. The device displays the analysis results to the user, allowing them to visually understand the dog's health status.

[0485] Examples of chatbots

[0486] 1. The user notices that their dog is lethargic and enters the question, "Why is my dog ​​lethargic?" into the chatbot.

[0487] 2. The terminal sends the question to the server.

[0488] 3. The server analyzes the question and generates an answer using a generative AI model.

[0489] 4. The server generates a response stating, "Recent data indicates an increase in stress levels; please review your environment and diet," and sends it to the device.

[0490] 5. The terminal displays the generated response to the user.

[0491] In this way, the system can monitor a dog's health in real time and provide appropriate feedback to the user. This allows pet owners to detect health problems in their dogs early and take appropriate action.

[0492] The following describes the processing flow.

[0493] Step 1:

[0494] The device (smartphone app) collects data from a smart collar or sensor attached to the dog. The collected data includes heart rate, activity level, food intake, and timing of elimination.

[0495] Step 2:

[0496] The terminal collects data, groups it into batches at regular intervals, and sends it to the server using an encryption protocol.

[0497] Step 3:

[0498] Before analyzing the received data, the server first stores it in a database. The database manages the data using a unique ID that can identify each dog.

[0499] Step 4:

[0500] The server retrieves data from the database and inputs it into the generative AI model. The generative AI model uses heart rate data to assess stress levels and activity data to determine whether or not the user is getting enough exercise. It also compares the current data with past data to check for any anomalies.

[0501] Step 5:

[0502] The server converts the analysis results of the generated AI model into visualized data such as graphs and alert messages. This visualized data is then stored again in the database.

[0503] Step 6:

[0504] The device periodically sends requests to the server to retrieve the latest visualization data. These requests include the dog's unique ID.

[0505] Step 7:

[0506] The server receives the request, extracts the relevant visualization data from the database, and sends it to the terminal.

[0507] Step 8:

[0508] The device displays the received visualization data on the user interface. Users can then visually understand their dog's health status by viewing this data.

[0509] Step 9:

[0510] The user enters a question about their dog's health into the chatbot. Example: "Why is my dog ​​lethargic?"

[0511] Step 10:

[0512] The terminal sends the user's question as text data to the server. This transmission also uses an encryption protocol.

[0513] Step 11:

[0514] The server analyzes the received question using a natural language processing (NLP) module. It understands the intent of the question and extracts the information necessary to provide an appropriate response.

[0515] Step 12:

[0516] The server generates responses using a generative AI model based on the analysis results, historical records in the database, and current health data.

[0517] Step 13:

[0518] The server sends the generated response as text data to the terminal.

[0519] Step 14:

[0520] The device displays the received response in the chatbot interface, providing the user with relevant information. For example, it might display a response such as, "Recent data shows your stress levels are rising, so please check for changes in your environment and your diet."

[0521] This allows users to monitor their dog's health in real time and take swift action as needed.

[0522] (Example 1)

[0523] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0524] Monitoring and analyzing a dog's health in real time and providing easily understandable feedback to owners was not easy with conventional technology. In particular, accurately collecting diverse data on a dog's physical condition and behavior, and appropriately analyzing it to detect abnormalities early was difficult. Providing immediate answers to specific questions and problems faced by owners was also a challenge.

[0525] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0526] In this invention, the server includes means for collecting data on the dog's physical condition and behavior from sensors, means for encrypting the collected data and transmitting it to the server, means for storing the received data in a database on the server, analyzing the data using a generative AI model to determine the dog's health status, means for visualizing the analysis results and displaying them in a visual format such as a graph, and means for a chatbot function that accepts user questions and answers the questions using the analysis results and existing data. This enables a detailed understanding of the dog's health status, real-time analysis, and immediate feedback.

[0527] A "sensor" is a device used to collect data about a dog's health and behavior.

[0528] "Health data" refers to information about a dog's physiological state, such as its heart rate, body temperature, and stress level.

[0529] "Behavioral data" refers to information about a dog's daily activities, such as the amount of exercise it gets, the distance it walks, and its activity level.

[0530] "Encryption" is the process of converting data into a format that cannot be understood by a third party in order to transmit it securely.

[0531] A "server" is a computer system used to store and analyze received data.

[0532] A "database" is a system for systematically storing and managing received data.

[0533] A "generative AI model" is an artificial intelligence model that analyzes collected data to diagnose and predict the health status of dogs.

[0534] "Visualization" is the process of converting analysis results into visual formats such as graphs and charts.

[0535] A "chatbot" is an interactive interface that receives user questions and provides appropriate answers.

[0536] A "Natural Language Processing (NLP) module" is a technology that understands user questions and requests and generates appropriate responses.

[0537] This invention is a system that monitors and analyzes a dog's health status in real time and provides user-friendly feedback. The system is implemented by combining a series of hardware and software components, including sensors, terminals, and a server.

[0538] Data collection and transmission

[0539] The device collects health and behavioral data, such as heart rate, activity level, food intake, and elimination timing, from sensors attached to the dog. These sensors include smart collars. The collected data is encrypted by the device and sent to the server periodically in batches. For example, AES-256 encryption is used, and data is sent every hour.

[0540] Data storage and analysis

[0541] The server stores the transmitted data in a database. Each dog is assigned a unique ID, and the data is managed in association with that ID. The server then analyzes the data using a generative AI model, estimating stress levels from heart rate and determining insufficient exercise from activity levels. An algorithm also operates to detect anomalies by comparing them with past data.

[0542] Visualization of the process

[0543] The analysis results are converted into visual formats such as graphs and charts by the server. For example, a line graph showing the dog's stress level and a bar graph showing its activity level are generated. The server stores this visualized data back into the database and sends it to the user's terminal upon request.

[0544] User Interface

[0545] The device displays the visualized data received from the server on the user interface. This allows users to visually understand their dog's health status on the screen of their smartphone or tablet. For example, if a user sends a request such as "I want to see my dog's activity level for this month," the device retrieves the data from the server and displays it.

[0546] Chatbot function

[0547] Users can enter questions using the in-app chatbot interface. For example, "Why is my dog ​​lethargic?" The device sends this question to the server, which uses a natural language processing (NLP) module to analyze the question. It then uses a generative AI model to construct an appropriate answer and sends that answer to the device. The device then displays the generated answer to the user.

[0548] Specific example

[0549] 1. The user puts a smart collar on the dog.

[0550] 2. The device collects data on the dog's heart rate and activity level from the smart collar.

[0551] 3. The device encrypts the data it collects and sends it to the server.

[0552] 4. The server analyzes the data to determine the dog's stress level and activity level.

[0553] 5. The server converts the analysis results into a graph format and sends it to the terminal.

[0554] 6. The device displays the analysis results to the user, allowing them to visually understand the dog's health status.

[0555] 7. The user enters the question "Why is my dog ​​lethargic?" into the chatbot.

[0556] 8. The server analyzes the question and generates a response, "Recent data shows your stress levels are rising, so please check for changes in your environment and your diet," and sends it to the terminal.

[0557] 9. The device displays the generated response to the user.

[0558] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0559] Step 1:

[0560] Data collection

[0561] The device collects data from smart collars and various sensors attached to the dog. The sensors measure data such as heart rate, activity level, food intake, and elimination timing. Input is raw data from the sensors, and output is provided in an appropriately formatted form. For example, the smart collar measures the heart rate every 10 seconds and transmits that data to the device.

[0562] Step 2:

[0563] Data transmission

[0564] The device performs an encryption process on the collected data. Specifically, it protects the data using encryption algorithms such as AES-256, and then periodically sends it to the server in batches. The input is formatted data, and the output is encrypted, transferable data. For example, the device sends all the data to the server every hour.

[0565] Step 3:

[0566] Data storage

[0567] The server decrypts the received encrypted data and stores it in the database. Each dog is identified by a unique ID, and the data is stored associated with that ID. The input is encrypted data sent to the server, and the output is the decrypted data stored in the database. For example, the server registers the data for DogID1234 in the database.

[0568] Step 4:

[0569] Data Analysis

[0570] The server analyzes stored data using a generative AI model. Specifically, it estimates stress levels from heart rate data and determines whether or not a person is getting enough exercise from activity level data. It also detects outliers by comparing them with past data. The input is data stored in a database, and the output is the stress level and exercise deficiency determination results as analysis results. For example, the server compares and analyzes heart rate data from the past week to determine the stress level.

[0571] Step 5:

[0572] Data visualization

[0573] The server converts the analysis results into visual formats such as graphs and charts. Based on the analysis results, it formats the data in a visually easy-to-understand form (e.g., line graphs, bar graphs, alert messages). The input is the analysis results, and the output is the generated visualized data. For example, the server creates a line graph showing the changes in a dog's stress level over time.

[0574] Step 6:

[0575] Data Request Processing

[0576] The user sends a request from their device, and the server provides data accordingly. The device sends a request to the server based on the user's request, for example, "I want to see my dog's activity level for this month." The server receives the request, searches the database for the necessary data, and sends the visualized data to the device. The input is the user's request, and the output is the visualized data displayed on the device.

[0577] Step 7:

[0578] Chatbot function

[0579] The user enters a question using the in-app chatbot interface. For example, "Why is my dog ​​lethargic?" The device sends this question to the server, which uses a natural language processing (NLP) module to analyze the question. It then uses a generative AI model to generate an appropriate answer and sends it to the device. The device displays the generated answer to the user. For example, it might generate an answer such as, "Recent data shows an increase in stress levels, so please check for changes in the environment and your dog's diet."

[0580] (Application Example 1)

[0581] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0582] Conventional systems for monitoring a dog's health primarily focused on providing collected data to owners, limiting how this information could be utilized in physical stores. Furthermore, they lacked specific recommendations based on the dog's health and effective coordination with veterinary hospitals in case of abnormalities, making it difficult for owners to take prompt action. Therefore, more comprehensive monitoring and immediate response are needed.

[0583] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0584] In this invention, the server includes means for collecting data on the dog's physical condition and behavior from sensors; means for transmitting the collected data to the server; means for analyzing the received data on the server and using a generative AI model to determine the dog's health status; means for visualizing the analysis results and displaying them in the form of graphs or the like; means for a chatbot function to receive user questions and answer those questions using the analysis results and existing data; means for displaying the dog's health data when the dog visits a pet supply store or veterinary hospital; means for recommending appropriate pet food and supplements based on the health data; and means for making an appointment in cooperation with a veterinary hospital if an abnormality is detected. This enables comprehensive monitoring of the dog's health status and immediate response.

[0585] A "sensor" is a device used to collect data about a dog's physical condition and behavior.

[0586] A "server" is a computer system that receives collected data, analyzes it, and provides the necessary information.

[0587] A "generative AI model" is an artificial intelligence model used to assess a dog's health status, deriving analysis results from multiple data points.

[0588] "Visualization" is a technique that makes information easier to understand intuitively by displaying data and analysis results in graphs and other visual formats.

[0589] A "chatbot function" is a feature that receives questions from users and automatically generates answers based on analysis results and existing data.

[0590] A "pet supply store" is a physical store that sells products related to pets.

[0591] A "veterinary hospital" is a medical facility that specializes in the health management and treatment of animals.

[0592] "Health data" is a general term for information about a dog's physical condition, behavior, diet, etc.

[0593] "Recommendation" refers to recommending appropriate products or services to users based on analysis results.

[0594] "Collaboration" refers to a means of directly communicating with animal hospitals and taking appropriate action when an abnormality is detected.

[0595] A "reservation" is the process of setting a date and time in advance to use a service.

[0596] This invention is a system for monitoring a dog's health status, intended for use in pet supply stores and veterinary clinics. Specific embodiments of this system are described below.

[0597] Hardware and software to use

[0598] Hardware:

[0599] Smartphone (user's device)

[0600] Smart collar (a sensor worn on a dog)

[0601] software:

[0602] Flask (Web framework)

[0603] Python (a programming language)

[0604] Generative AI models (data analysis and chatbot functionality)

[0605] Data collection and transmission

[0606] The device collects health and behavioral data, such as heart rate, activity level, food intake, and elimination timing, from smart collars and sensors attached to the dog. This collected data is periodically encrypted in batches and sent to a server.

[0607] Data Analysis

[0608] The server stores the received data in a database. The database manages the data using a unique ID that identifies each dog. A generative AI model then analyzes the data, determining stress levels from heart rate and assessing whether the dog is getting enough exercise based on activity levels. It also compares the data with past data to check for any anomalies.

[0609] Visualization of the process

[0610] The analysis results are converted into visual formats such as graphs and alert messages. The server stores this visualization data in a database and sends it upon request from the terminal. The terminal displays this data in its user interface, allowing the user to visually understand the dog's health status.

[0611] Use at physical stores

[0612] When pet owners visit pet supply stores or veterinary clinics, health data is collected from smart collars and sensors worn by their dogs. The analysis results are instantly displayed on a terminal and provided to the owner. Based on the analysis results, there is a function to recommend appropriate pet food and supplements. In addition, if an abnormality is detected, it is possible to make an appointment directly through a linkage function with the veterinary clinic.

[0613] Chatbot function

[0614] Users enter questions through the in-app chatbot interface. For example, if a user asks "Why is my dog ​​lethargic?", the question is sent from the device to the server. The server analyzes the question using a natural language processing (NLP) module and generates an appropriate answer. The generated answer is sent to the device and displayed to the user.

[0615] Specific example

[0616] A user visits a pet shop and uses a smartphone app to read data from a dog wearing a smart collar.

[0617] When you enter "Please tell me about your recent health status" into the app, your health data is sent to the server, and the analysis results are returned to the app.

[0618] The app provides advice such as, "Your recent heart rate has been high, which may indicate you are experiencing a lot of stress. Please create a stress-free environment for yourself."

[0619] Examples of prompt messages include, "My dog's activity level is low. What are the possible causes and solutions?" and "Based on recent data, please recommend a suitable food for my pet."

[0620] In this way, the system can monitor a dog's health in real time and provide appropriate feedback to the user. This allows pet owners to detect health problems in their dogs early and take appropriate action.

[0621] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0622] Step 1:

[0623] The user collects data from a smart collar attached to the dog.

[0624] Input: Dog's health and behavioral data

[0625] Output: The collected data is stored on the device.

[0626] Specific operation: The device collects data such as heart rate, activity level, and food intake from the smart color's sensors via Bluetooth.

[0627] Step 2:

[0628] The device encrypts the collected data and sends it to the server.

[0629] Input: Collected health and behavioral data of dogs

[0630] Output: Encrypted data is sent to the server.

[0631] Specific operation: The terminal encrypts the data using AES and sends it to the server using the HTTPS protocol.

[0632] Step 3:

[0633] The server stores the received data in the database.

[0634] Input: Encrypted dog health and behavior data

[0635] Output: Data stored in the database

[0636] Specific operation: The server releases the incoming data and stores it in the database, identifying each dog with a unique ID.

[0637] Step 4:

[0638] The server uses a generative AI model to analyze the data.

[0639] Input: Dog health and behavioral data stored in the database

[0640] Output: Analysis results of health status

[0641] Specific operation: The server uses a generated AI model to analyze heart rate and activity data to determine the dog's stress level and lack of exercise.

[0642] Step 5:

[0643] The server visualizes the analysis results in graphs and alert messages.

[0644] Input: Analysis results of health status

[0645] Output: Visualized data (graphs, alert messages)

[0646] Specific operation: The server converts the analysis results into graphs using visualization libraries such as D3.js, and also generates alert messages if necessary.

[0647] Step 6:

[0648] The server sends the visualized data to the terminal.

[0649] Input: Visualized data

[0650] Output: Visualized data delivered to the terminal

[0651] Specific operation: The server converts the visualization data into JSON format and sends it to the terminal using the HTTPS protocol.

[0652] Step 7:

[0653] The terminal displays visualized data in its user interface.

[0654] Input: Visualization data

[0655] Output: Graphs and alert messages displayed in the user interface

[0656] Specific operation: The terminal parses the received JSON data and displays the data in the user interface using HTML and JavaScript.

[0657] Step 8:

[0658] Users enter their questions through a chatbot interface.

[0659] Input: Question for the chatbot (e.g., "Why is my dog ​​lethargic?")

[0660] Output: Question data to send to the server

[0661] Specific operation: The terminal uses a natural language processing module to initially process the question entered by the user and then sends it to the server.

[0662] Step 9:

[0663] The server analyzes the question using a natural language processing module and generates an answer.

[0664] Input: Question data

[0665] Output: Generated answer

[0666] Specific operation: The server analyzes the question using the natural language processing module of the generative AI model and generates an appropriate answer based on health data.

[0667] Step 10:

[0668] The server sends the generated response to the terminal.

[0669] Input: Generated answer

[0670] Output: Response data received on the device

[0671] Specific operation: The server converts the generated response into JSON format and sends it to the terminal using the HTTPS protocol.

[0672] Step 11:

[0673] The terminal displays the generated response to the user.

[0674] Input: Response data

[0675] Output: Answer displayed in the user interface

[0676] Specific operation: The device analyzes the received response data and displays the response in the chatbot interface using HTML and JavaScript.

[0677] Through the above processing steps, it is possible to monitor the dog's health status in real time and provide appropriate feedback to the user.

[0678] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0679] This invention provides a system for understanding the health status of pet dogs and taking appropriate measures, and in particular, by combining it with an emotion engine that recognizes the user's emotions, it achieves more accurate feedback. Specific embodiments of this system are described below.

[0680] System Overview

[0681] This system collects data from sensors attached to dogs and from the user's device, analyzes it on a server, and visualizes the dog's health status. It also features an emotion engine that recognizes the user's emotional state, and the chatbot adjusts its responses accordingly.

[0682] Data collection and transmission

[0683] The device (smartphone app) collects data from smart collars and sensors attached to the dog. This data includes heart rate, activity level, food intake, and elimination timing. This collected data is periodically encrypted in batches and sent to the server.

[0684] Data Analysis

[0685] The server stores the received data in a database. The database manages the data using a unique ID that can identify each dog. A generative AI model then analyzes the data, using heart rate data to assess stress levels and activity data to determine if the dog is getting enough exercise. It also compares the data with past data to check for any anomalies.

[0686] Visualization of the process

[0687] The analysis results are converted into visual formats such as graphs and alert messages. The server stores this visualization data back into a database and sends it upon request from the terminal. The terminal displays this data in its user interface, allowing the user to visually understand the dog's health status.

[0688] Chatbot function

[0689] Users enter questions through the in-app chatbot interface. For example, if a user asks, "Why is my dog ​​lethargic?", the question is sent from the device to the server. The server analyzes the question using a natural language processing (NLP) module and generates an appropriate answer. The generated answer is sent to the device and displayed to the user.

[0690] User emotion recognition

[0691] The device inputs the user's voice data and facial expression data into the emotion engine. The emotion engine uses voice analysis and image analysis to determine the user's emotional state.

[0692] Emotion-based feedback

[0693] The server adjusts the chatbot's responses based on emotional data obtained from the emotion engine. For example, if the user is feeling anxious, it will generate a response in a gentler tone to provide more reassurance. This allows the user to receive more appropriate feedback.

[0694] Explanation of specific examples

[0695] Specific examples of data collection and display.

[0696] 1. As an example, the user attaches a smart collar to a dog.

[0697] 2. The device collects data on the dog's heart rate and activity level from the smart collar.

[0698] 3. The device sends the collected data to the server.

[0699] 4. The server analyzes the data to determine the dog's stress level and activity level.

[0700] 5. The server converts the analysis results into a graph format and sends it to the terminal.

[0701] 6. The terminal displays the analysis results on the user interface, allowing the user to visually understand the dog's health status.

[0702] Concrete examples of emotional engines

[0703] 1. The user enters a question into the chatbot about their dog's lethargy.

[0704] 2. The device inputs the user's voice and facial expression data into the emotion engine.

[0705] 3. The emotion engine analyzes the user's emotional state and determines that they are anxious.

[0706] 4. The device sends the question and sentiment data to the server.

[0707] 5. The server generates appropriate responses that take emotional data into account. For example, it might generate a gentle-toned response such as, "Recent data shows your stress levels are rising, so please review your environment and diet."

[0708] 6. The terminal displays the generated response in the chatbot interface, providing the user with appropriate information.

[0709] This allows users to monitor their dog's health in real time and receive appropriate feedback tailored to their emotions.

[0710] The following describes the processing flow.

[0711] Step 1:

[0712] The device (smartphone app) collects data such as heart rate, activity level, food intake, and elimination timing from smart collars and sensors attached to the dog. The collected data includes information about the dog's health and behavior.

[0713] Step 2:

[0714] The terminal collects data, groups it into batches at regular intervals, and sends it to the server using a secure encryption protocol. This transmission process is carried out to ensure the real-time nature and security of the data.

[0715] Step 3:

[0716] Before analyzing the received data, the server first stores it in a database. The database employs a system where data is managed using a unique ID that can identify each dog.

[0717] Step 4:

[0718] The server inputs data from the database into a generating AI model for data analysis. The generating AI model evaluates stress levels from heart rate data and determines whether or not the user is not getting enough exercise from activity level data. It also checks for any outliers by comparing the current data with past data.

[0719] Step 5:

[0720] The server converts the analysis results of the generated AI model into visualized data such as graphs and alert messages. This visualized data is then stored again in the database.

[0721] Step 6:

[0722] The device periodically sends requests to the server to retrieve the latest visualization data. Because these requests include the dog's ID, the appropriate data is obtained.

[0723] Step 7:

[0724] The server receives the request, extracts the relevant visualization data from the database, and sends it to the terminal.

[0725] Step 8:

[0726] The device displays the received visualization data on the user interface. The user can then visually understand the dog's health condition by viewing this data.

[0727] Step 9:

[0728] The user enters questions about their dog's health into the chatbot. These questions are specific, such as, "Why is my dog ​​lethargic?"

[0729] Step 10:

[0730] The terminal sends the user's questions to the server as text data. Encryption protocols are used during this process to ensure data security.

[0731] Step 11:

[0732] The server inputs the received question into a natural language processing (NLP) module to analyze the intent of the question. It then extracts the information necessary to generate an appropriate answer.

[0733] Step 12:

[0734] The server generates answers to questions using a generative AI model. The generated answers are adjusted as needed based on the user's question.

[0735] Step 13:

[0736] The server sends the generated response as text data to the terminal.

[0737] Step 14:

[0738] The device displays the received response in a chatbot interface, providing the user with relevant information. For example, it might display specific advice such as, "Recent data shows your stress levels are rising, so please check your environment and diet."

[0739] Step 15:

[0740] The device inputs the user's voice data and facial expression data into the emotion engine. The emotion engine uses voice analysis and image analysis to determine the user's emotional state.

[0741] Step 16:

[0742] The server adjusts the chatbot's responses based on data obtained from the emotion engine. For example, if the user is feeling anxious, it generates a response in a gentler tone to provide greater reassurance.

[0743] Step 17:

[0744] The device displays and communicates emotionally-sensitive responses to the user via a chatbot interface. This allows the user to receive optimal feedback tailored to the situation.

[0745] In this way, the system can monitor the dog's health in real time and provide appropriate feedback based on the user's emotions.

[0746] (Example 2)

[0747] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0748] Traditional dog health management systems have limitations in analyzing collected data and providing feedback to users. Furthermore, they fail to consider user emotions, resulting in an inadequate user experience. Additionally, they lack a clear means of providing detailed analysis results based on the dog's health and behavior, making it difficult for users to take appropriate action.

[0749] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0750] In this invention, the server includes means for collecting data on the dog's physical condition and behavior from sensors, means for transmitting the collected data to the server, means for analyzing the received data on the server and using a generative AI model to determine the dog's health status, means for visualizing the analysis results and displaying them in the form of a graph or the like, a chatbot function that accepts user questions and answers the questions using the analysis results and existing data, and means for adjusting the chatbot's responses using an emotion engine that recognizes the user's emotions. This enables detailed analysis of the dog's health status and provides the user with appropriate feedback that responds to their emotions.

[0751] A "sensor" is a device attached to a dog to collect data about its physical condition and behavior.

[0752] "Health data" refers to physiological data such as heart rate and body temperature collected to evaluate a dog's health status.

[0753] "Behavioral data" includes data such as the dog's activity level, distance traveled, food intake, and timing of elimination.

[0754] A "terminal" is a communication device used to collect and transmit data, and primarily refers to mobile devices such as smartphones and tablets.

[0755] A "server" is a computer system that receives collected data, performs analysis, and provides the results.

[0756] A "generative AI model" is a model that includes an algorithm that uses machine learning to analyze received data and determine a person's health status.

[0757] "Visualization" refers to converting the results of data analysis into visual formats such as graphs and alert messages, and displaying them in a way that is easy for users to understand.

[0758] A "graph" is a graphic representation used to visually display analysis results, and includes line graphs, pie charts, and other similar types of graphs.

[0759] A "chatbot" is a conversational system that receives user questions and automatically generates answers.

[0760] A "natural language processing module" is a module that includes technology for analyzing user-inputted questions and generating appropriate answers.

[0761] An "emotion engine" is a system that includes technology to determine a user's emotional state from their voice and facial expressions and respond accordingly.

[0762] "Feedback" refers to information provided based on analysis results and user questions, particularly responses that take into account the user's emotional state.

[0763] This invention is a system that monitors a dog's health and provides appropriate feedback to the user. The system comprises sensors attached to the dog, a terminal that collects and transmits data, a server that analyzes the data, and multiple modules for visualizing the analysis results and interacting with the user.

[0764] Hardware configuration

[0765] The sensors collect data such as the dog's heart rate, activity level, food intake, and timing of urination and defecation.

[0766] The device takes the form of a smartphone or tablet, receives data from sensors, and transmits it to a server. It is equipped with data communication capabilities using Bluetooth or Wi-Fi.

[0767] A server is a computer system for storing and analyzing received data, and it runs an analysis engine that uses a database and a generative AI model.

[0768] Software Configuration

[0769] The terminal application has the function of collecting data from sensors, encrypting it, and sending it to the server. It also provides a user interface, displaying visualized data and allowing interaction through a chatbot.

[0770] The server software receives, stores, and analyzes data. The generated AI model is implemented using Python or TensorFlow. The analysis results are visualized using a JavaScript graph plotting library (e.g., Chart.js).

[0771] The emotion engine analyzes user emotions from voice data and facial expression data using tools such as the Microsoft Azure Emotion API.

[0772] The natural language processing module uses the Google Cloud Natural Language API to analyze user questions and generate appropriate answers.

[0773] Specific example

[0774] Data collection

[0775] The user attaches a smart collar to their dog.

[0776] The device collects heart rate and activity data from the smart color, encrypts it, and sends it to the server.

[0777] Data analysis and visualization

[0778] The server analyzes the received data using a generating AI model, assessing stress levels from heart rate data and determining whether there is a lack of exercise from activity level data. It also compares this data with past data to identify any anomalies.

[0779] The analysis results are visualized as graphs and alert messages. For example, if a dog's activity level drops sharply, an alert will be displayed.

[0780] Emotion recognition and feedback

[0781] The user enters a question through the chatbot. For example, they might ask, "Why is my dog ​​lethargic?"

[0782] The device inputs voice data and facial expression data into an emotion engine to analyze the user's emotions.

[0783] The server adjusts the chatbot's responses based on emotional data to generate reassuring answers. For example, it might respond with something like, "Recent data shows your stress levels are rising, so please check your environment and diet."

[0784] Example of a prompt

[0785] "What data is needed to understand a dog's health status?"

[0786] "How can I adjust responses based on user sentiment?"

[0787] This system allows users to gain a detailed understanding of their dog's health and receive appropriate feedback tailored to their emotions.

[0788] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0789] Step 1:

[0790] The user attaches sensors to the dog. The sensors measure heart rate, activity level, food intake, and timing of elimination, etc. This becomes the input data.

[0791] Step 2:

[0792] The device collects data from sensors via Bluetooth or Wi-Fi. This collected data includes heart rate, activity level, food intake, and timing of bowel movements. The data is encrypted within the device. The encryption process ensures the confidentiality of the data. This is then processed and output as data.

[0793] Step 3:

[0794] The terminal periodically sends encrypted data to the server in batches. The input is encrypted data, ensuring that the data reaches the server securely.

[0795] Step 4:

[0796] The server decrypts the received encrypted data and stores it in the database. Each dog is assigned a unique ID, and the data is managed based on this ID. The input data is encrypted data, and the output is data correctly stored in the database.

[0797] Step 5:

[0798] The server uses a generative AI model to analyze data. Specifically, it assesses stress levels from heart rate data and determines whether or not the user is not getting enough exercise from activity level data. It also compares current data with past data to detect anomalies. The input is data read from a database, and the output is the analysis results.

[0799] Step 6:

[0800] The server converts the analysis results into graphs and alert messages. For example, it can generate graphs using a JavaScript graph plotting library (e.g., Chart.js). The input is the analysis results, and the output is the visualized graphs and messages.

[0801] Step 7:

[0802] The server restores the visualized data in the database and sends it in response to requests from the terminal. The input is the visualized data, and the output is the data sent to the terminal.

[0803] Step 8:

[0804] The terminal displays the analysis results on the user interface. This allows the user to visually understand the dog's health status. The input is visualized data received from the server, and the output is the display on the user interface.

[0805] Step 9:

[0806] The user enters a question through the chatbot interface. For example, they might ask, "Why is my dog ​​lethargic?" The input is the user's question.

[0807] Step 10:

[0808] The terminal sends the user's question to the server. The input is the user's question, and the output is the question data sent to the server.

[0809] Step 11:

[0810] The server uses a natural language processing module to analyze the user's question and generate an appropriate answer. For example, it might respond with, "Recent data indicates that your dog's stress level has increased. Please check for changes in its environment and its diet." The input is the user's question, and the output is the generated answer.

[0811] Step 12:

[0812] The server sends the generated response to the terminal. The input is the generated response, and the output is the data sent to the terminal.

[0813] Step 13:

[0814] The terminal displays the response in the chatbot interface, providing the user with appropriate feedback. The input is the response received from the server, and the output is the display on the user interface.

[0815] Step 14:

[0816] The device inputs the user's voice data and facial expression data into the emotion engine. This initiates the analysis of emotions. The input consists of the user's voice data and facial expression data.

[0817] Step 15:

[0818] The emotion engine uses voice and image analysis to determine the user's emotional state. For example, it can check whether the user is feeling anxious. The input is voice data and facial expression data, and the output is the user's emotional state.

[0819] Step 16:

[0820] The device sends emotional data to the server. The input is emotional data, and the output is the data sent to the server.

[0821] Step 17:

[0822] The server adjusts the chatbot's responses based on emotional data. For example, if the user is feeling anxious, it will generate a reassuring response in a gentle tone. The input is emotional data, and the output is the adjusted response.

[0823] Step 18:

[0824] The server sends the adjusted response to the terminal. The input is the adjusted response, and the output is the data sent to the terminal.

[0825] Step 19:

[0826] The device displays the adjusted response in the chatbot interface. This allows the user to receive emotion-sensitive feedback. The input is the adjusted response received from the server, and the output is the display on the user interface.

[0827] Step 20:

[0828] Users can receive feedback and take appropriate action.

[0829] (Application Example 2)

[0830] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the smart glasses 214 as the "terminal".

[0831] In recent years, interest in pet health management has increased, but there is a lack of integrated systems that allow owners to understand their dog's health status and respond appropriately if suspicious situations arise. Furthermore, pet health management and security monitoring are often handled by separate systems, making unified management difficult. Additionally, the lack of means for users to check their dog's health status and behavior in real time has also been pointed out.

[0832] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting data on the dog's physical condition and behavior from sensors, means for transmitting the collected data to software, means for using a generative AI model in the software to analyze the received data and determine the health status, means for visualizing the analysis results and displaying them in the form of a graph or the like, means for a chatbot function that accepts user questions and answers the questions using the analysis results and existing data, means for monitoring the dog's behavior and environment and notifying the user if a suspicious situation occurs, and means for the user to check the dog's real-time data using a smart device. This makes it possible to provide a system that integrates pet health management and security monitoring.

[0833] A "system" refers to an integrated group of devices that monitor a dog's health and behavior, analyze the collected data, and provide the results to the user.

[0834] A "sensor" is a device attached to a dog to collect data about its health and behavior.

[0835] "Software" refers to a series of programs that receive and analyze data transmitted from sensors.

[0836] A "generative AI model" is an artificial intelligence technology used to analyze received data and determine the health status of a dog.

[0837] "Visualization" refers to the process of displaying analysis results in a visual format, such as a graph.

[0838] A "chatbot" is an automated response system that receives questions from users and generates answers using analysis results and existing data.

[0839] A "notification" is a message sent to the user to inform them if there are any suspicious circumstances regarding the dog's behavior or environment.

[0840] A "smart device" is an interactive electronic device that allows users to check their dog's data in real time.

[0841] This invention is an integrated system for monitoring a dog's health and behavior and providing this information to the user. The system includes sensors attached to the dog, software to receive and analyze the data, a generative AI model, a chatbot to interact with the user, and a smart device.

[0842] Data collection

[0843] Sensors attached to the dog collect data such as heart rate, activity level, food intake, and elimination timing. The sensors transmit this data to software at regular intervals.

[0844] Data transmission and analysis

[0845] The software sends the collected data to the software, and a generating AI model analyzes that data. This analysis includes comparing it with historical data stored in a database to identify anomalies and health risks. For example, if an abnormal heart rate or decreased activity level is detected, a corresponding notification is generated.

[0846] Data visualization and notification

[0847] The analysis results are converted into visual formats such as graphs and alert messages. The software stores this visualization data in a database and sends it upon request from a smart device. The smart device, such as smart glasses, displays this data on a user interface, allowing the user to monitor their dog's health in real time.

[0848] The system also monitors the dog's behavior and environment, and notifies the user if any suspicious situations are detected. For example, if the dog stays in an unusual location for an extended period, or if unusual noises are heard, an alert is immediately sent to the user.

[0849] Chatbot functionality and emotion recognition

[0850] Users can enter questions through the in-app chatbot. These questions are sent to the software, and a generative AI model generates appropriate answers. The software inputs the user's voice and facial expression data into an emotion engine to analyze the user's emotional state. The chatbot's answers are then adjusted based on the emotional state. For example, if the user is feeling anxious, a gentle tone of voice will be used to provide the answer.

[0851] Specific example

[0852] As a concrete example, consider a scenario where a user attaches a smart collar to their dog, and data such as heart rate and activity levels are collected from this collar. The collected data is sent to software and analyzed by a generative AI model. The analysis results are displayed in graph format on smart glasses, allowing the user to visually check the dog's health status. Furthermore, if there is an abnormality in the dog's behavior, for example, if the dog remains still for an unusually long period, the user will be notified. In this case, a message such as, "Your dog's heart rate is higher than normal. Recent data indicates an increased stress level, so please check for changes in the environment and its diet," will be provided via a chatbot.

[0853] Examples of prompts for a generative AI model:

[0854] Please help with the "Pet Health Management Security System." Based on the following information, please create a notification message for the user when displayed in real time on smart glasses: Dog's heart rate: 120, activity level: low. Related information: Suggests lack of exercise. Please make the message specific and in a gentle tone.

[0855] Thus, this invention enables the provision of a system that integrates dog health management and security monitoring, providing users with a means to check their dog's data in real time and take appropriate action.

[0856] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0857] Step 1:

[0858] The device collects data such as heart rate, activity level, food intake, and elimination timing from sensors attached to the dog. In this data collection process, the device periodically receives the biometric data acquired by the sensors and stores it in digital format. The input is biometric data from the sensors, and the output is digital data stored in the device.

[0859] Step 2:

[0860] The device transmits the collected data to the software. At this time, the device encrypts the data before transmission to ensure communication security. The input is digital data stored on the device, and the output is encrypted data packets. Specifically, the device encrypts the data using the pet sensor SDK and sends it to the server as an HTTP request.

[0861] Step 3:

[0862] The server receives data sent from the terminal and stores it in a database. The server then analyzes the received data and prepares it for input into the generated AI model. The input is encrypted data packets, and the output is digital data stored in the database.

[0863] Step 4:

[0864] The server analyzes data using a generative AI model. Specifically, the AI ​​model analyzes heart rate and activity level data stored in the database to determine the user's health status. The generative AI model detects anomalies by comparing current data with past data. The input is digital data stored in the database, and the output is the health status assessment result.

[0865] Step 5:

[0866] The server visualizes the analysis results. The analysis results are converted into formats such as graphs and alert messages, making them easy to understand visually. The input is the health status assessment results analyzed by the generative AI model, and the output is visualized data (e.g., graphs and alert messages).

[0867] Step 6:

[0868] The server stores the visualized data back into the database and sends it in response to requests from the terminal. The input is the visualized data, and the output is the data sent to the terminal. Specifically, the server sends graph data and alert messages to the terminal as an HTTP response.

[0869] Step 7:

[0870] The terminal displays visualized data on a user interface, allowing users to check their dog's health status. The input is visualized data received from the server, and the output is graphs and alert messages displayed on the user interface.

[0871] Step 8:

[0872] When a user enters a question through the in-app chatbot interface, that question is sent from the device to the server. The input is the user's question, and the output is the data sent to the server.

[0873] Step 9:

[0874] The server analyzes the question using a natural language processing (NLP) module and generates an appropriate answer using a generative AI model. The input is the user's question, and the output is the generated answer.

[0875] Step 10:

[0876] The server sends the generated response to the terminal and displays it in the chatbot interface. The input is the generated response, and the output is the data sent to the terminal. The terminal displays the response in the user interface for the user to confirm.

[0877] Step 11:

[0878] The device inputs the user's voice data and facial expression data into an emotion engine to determine their emotional state. The input is voice data and facial expression data, and the output is the analyzed emotion data.

[0879] Step 12:

[0880] The server adjusts the chatbot's responses based on emotional data obtained from the emotion engine. The input is the analyzed emotional data and the generated response, and the output is the adjusted, gentle-toned response.

[0881] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0882] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0883] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart glasses 214.

[0884] [Third Embodiment]

[0885] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0886] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0887] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0888] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0889] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0890] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0891] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0892] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0893] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0894] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0895] In the headset terminal 314, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0896] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the headset terminal 314 will be referred to as the "terminal".

[0897] This invention relates to a system for monitoring the health status of pet dogs. Specific embodiments of this system are described below.

[0898] System Overview

[0899] This system collects data from sensors attached to dogs and from the user's device, analyzes it on a server to visualize the dog's health status, and provides this information to the owner. In addition, it is equipped with a chatbot function that provides appropriate feedback in response to user questions.

[0900] Data collection and transmission

[0901] The device collects health and behavioral data, such as heart rate, activity level, food intake, and elimination timing, from smart collars and sensors attached to the dog. This collected data is periodically encrypted in batches and sent to a server.

[0902] Data Analysis

[0903] The server stores the received data in a database. The database manages the data using a unique ID that identifies each dog. A generative AI model then analyzes the data, determining stress levels from heart rate and assessing whether the dog is getting enough exercise based on activity levels. It also compares the data with past data to check for any anomalies.

[0904] Visualization of the process

[0905] The analysis results are converted into visual formats such as graphs and alert messages. The server stores this visualization data in a database and sends it upon request from the terminal. The terminal displays this data in its user interface, allowing the user to visually understand the dog's health status.

[0906] Chatbot function

[0907] Users enter questions through the in-app chatbot interface. For example, if a user asks "Why is my dog ​​lethargic?", the question is sent from the device to the server. The server analyzes the question using a natural language processing (NLP) module and generates an appropriate answer. The generated answer is sent to the device and displayed to the user.

[0908] Explanation of specific examples

[0909] Specific examples of data collection and display.

[0910] 1. As an example, the user attaches a smart collar to a dog.

[0911] 2. The device collects data on the dog's heart rate and activity level from the smart collar.

[0912] 3. The device sends the collected data to the server.

[0913] 4. The server analyzes the data to determine the dog's stress level and activity level.

[0914] 5. The server converts the analysis results into a graph format and sends it to the terminal.

[0915] 6. The device displays the analysis results to the user, allowing them to visually understand the dog's health status.

[0916] Examples of chatbots

[0917] 1. The user notices that their dog is lethargic and enters the question, "Why is my dog ​​lethargic?" into the chatbot.

[0918] 2. The terminal sends the question to the server.

[0919] 3. The server analyzes the question and generates an answer using a generative AI model.

[0920] 4. The server generates a response stating, "Recent data indicates an increase in stress levels; please review your environment and diet," and sends it to the device.

[0921] 5. The terminal displays the generated response to the user.

[0922] In this way, the system can monitor a dog's health in real time and provide appropriate feedback to the user. This allows pet owners to detect health problems in their dogs early and take appropriate action.

[0923] The following describes the processing flow.

[0924] Step 1:

[0925] The device (smartphone app) collects data from a smart collar or sensor attached to the dog. The collected data includes heart rate, activity level, food intake, and timing of elimination.

[0926] Step 2:

[0927] The terminal collects data, groups it into batches at regular intervals, and sends it to the server using an encryption protocol.

[0928] Step 3:

[0929] Before analyzing the received data, the server first stores it in a database. The database manages the data using a unique ID that can identify each dog.

[0930] Step 4:

[0931] The server retrieves data from the database and inputs it into the generative AI model. The generative AI model uses heart rate data to assess stress levels and activity data to determine whether or not the user is getting enough exercise. It also compares the current data with past data to check for any anomalies.

[0932] Step 5:

[0933] The server converts the analysis results of the generated AI model into visualized data such as graphs and alert messages. This visualized data is then stored again in the database.

[0934] Step 6:

[0935] The device periodically sends requests to the server to retrieve the latest visualization data. These requests include the dog's unique ID.

[0936] Step 7:

[0937] The server receives the request, extracts the relevant visualization data from the database, and sends it to the terminal.

[0938] Step 8:

[0939] The device displays the received visualization data on the user interface. Users can then visually understand their dog's health status by viewing this data.

[0940] Step 9:

[0941] The user enters a question about their dog's health into the chatbot. Example: "Why is my dog ​​lethargic?"

[0942] Step 10:

[0943] The terminal sends the user's question as text data to the server. This transmission also uses an encryption protocol.

[0944] Step 11:

[0945] The server analyzes the received question using a natural language processing (NLP) module. It understands the intent of the question and extracts the information necessary to provide an appropriate response.

[0946] Step 12:

[0947] The server generates responses using a generative AI model based on the analysis results, historical records in the database, and current health data.

[0948] Step 13:

[0949] The server sends the generated response as text data to the terminal.

[0950] Step 14:

[0951] The device displays the received response in the chatbot interface, providing the user with relevant information. For example, it might display a response such as, "Recent data shows your stress levels are rising, so please check for changes in your environment and your diet."

[0952] This allows users to monitor their dog's health in real time and take swift action as needed.

[0953] (Example 1)

[0954] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0955] Monitoring and analyzing a dog's health in real time and providing easily understandable feedback to owners was not easy with conventional technology. In particular, accurately collecting diverse data on a dog's physical condition and behavior, and appropriately analyzing it to detect abnormalities early was difficult. Providing immediate answers to specific questions and problems faced by owners was also a challenge.

[0956] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0957] In this invention, the server includes means for collecting data on the dog's physical condition and behavior from sensors, means for encrypting the collected data and transmitting it to the server, means for storing the received data in a database on the server, analyzing the data using a generative AI model to determine the dog's health status, means for visualizing the analysis results and displaying them in a visual format such as a graph, and means for a chatbot function that accepts user questions and answers the questions using the analysis results and existing data. This enables a detailed understanding of the dog's health status, real-time analysis, and immediate feedback.

[0958] A "sensor" is a device used to collect data about a dog's health and behavior.

[0959] "Health data" refers to information about a dog's physiological state, such as its heart rate, body temperature, and stress level.

[0960] "Behavioral data" refers to information about a dog's daily activities, such as the amount of exercise it gets, the distance it walks, and its activity level.

[0961] "Encryption" is the process of converting data into a format that cannot be understood by a third party in order to transmit it securely.

[0962] A "server" is a computer system used to store and analyze received data.

[0963] A "database" is a system for systematically storing and managing received data.

[0964] A "generative AI model" is an artificial intelligence model that analyzes collected data to diagnose and predict the health status of dogs.

[0965] "Visualization" is the process of converting analysis results into visual formats such as graphs and charts.

[0966] A "chatbot" is an interactive interface that receives user questions and provides appropriate answers.

[0967] A "Natural Language Processing (NLP) module" is a technology that understands user questions and requests and generates appropriate responses.

[0968] This invention is a system that monitors and analyzes a dog's health status in real time and provides user-friendly feedback. The system is implemented by combining a series of hardware and software components, including sensors, terminals, and a server.

[0969] Data collection and transmission

[0970] The device collects health and behavioral data, such as heart rate, activity level, food intake, and elimination timing, from sensors attached to the dog. These sensors include smart collars. The collected data is encrypted by the device and sent to the server periodically in batches. For example, AES-256 encryption is used, and data is sent every hour.

[0971] Data storage and analysis

[0972] The server stores the transmitted data in a database. Each dog is assigned a unique ID, and the data is managed in association with that ID. The server then analyzes the data using a generative AI model, estimating stress levels from heart rate and determining insufficient exercise from activity levels. An algorithm also operates to detect anomalies by comparing them with past data.

[0973] Visualization of the process

[0974] The analysis results are converted into visual formats such as graphs and charts by the server. For example, a line graph showing the dog's stress level and a bar graph showing its activity level are generated. The server stores this visualized data back into the database and sends it to the user's terminal upon request.

[0975] User Interface

[0976] The device displays the visualized data received from the server on the user interface. This allows users to visually understand their dog's health status on the screen of their smartphone or tablet. For example, if a user sends a request such as "I want to see my dog's activity level for this month," the device retrieves the data from the server and displays it.

[0977] Chatbot function

[0978] Users can enter questions using the in-app chatbot interface. For example, "Why is my dog ​​lethargic?" The device sends this question to the server, which uses a natural language processing (NLP) module to analyze the question. It then uses a generative AI model to construct an appropriate answer and sends that answer to the device. The device then displays the generated answer to the user.

[0979] Specific example

[0980] 1. The user puts a smart collar on the dog.

[0981] 2. The device collects data on the dog's heart rate and activity level from the smart collar.

[0982] 3. The device encrypts the data it collects and sends it to the server.

[0983] 4. The server analyzes the data to determine the dog's stress level and activity level.

[0984] 5. The server converts the analysis results into a graph format and sends it to the terminal.

[0985] 6. The device displays the analysis results to the user, allowing them to visually understand the dog's health status.

[0986] 7. The user enters the question "Why is my dog ​​lethargic?" into the chatbot.

[0987] 8. The server analyzes the question and generates a response, "Recent data shows your stress levels are rising, so please check for changes in your environment and your diet," and sends it to the terminal.

[0988] 9. The device displays the generated response to the user.

[0989] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0990] Step 1:

[0991] Data collection

[0992] The device collects data from smart collars and various sensors attached to the dog. The sensors measure data such as heart rate, activity level, food intake, and elimination timing. Input is raw data from the sensors, and output is provided in an appropriately formatted form. For example, the smart collar measures the heart rate every 10 seconds and transmits that data to the device.

[0993] Step 2:

[0994] Data transmission

[0995] The device performs an encryption process on the collected data. Specifically, it protects the data using encryption algorithms such as AES-256, and then periodically sends it to the server in batches. The input is formatted data, and the output is encrypted, transferable data. For example, the device sends all the data to the server every hour.

[0996] Step 3:

[0997] Data storage

[0998] The server decrypts the received encrypted data and stores it in the database. Each dog is identified by a unique ID, and the data is stored associated with that ID. The input is encrypted data sent to the server, and the output is the decrypted data stored in the database. For example, the server registers the data for DogID1234 in the database.

[0999] Step 4:

[1000] Data Analysis

[1001] The server analyzes stored data using a generative AI model. Specifically, it estimates stress levels from heart rate data and determines whether or not a person is getting enough exercise from activity level data. It also detects outliers by comparing them with past data. The input is data stored in a database, and the output is the stress level and exercise deficiency determination results as analysis results. For example, the server compares and analyzes heart rate data from the past week to determine the stress level.

[1002] Step 5:

[1003] Data visualization

[1004] The server converts the analysis results into visual formats such as graphs and charts. Based on the analysis results, it formats the data in a visually easy-to-understand form (e.g., line graphs, bar graphs, alert messages). The input is the analysis results, and the output is the generated visualized data. For example, the server creates a line graph showing the changes in a dog's stress level over time.

[1005] Step 6:

[1006] Data Request Processing

[1007] The user sends a request from their device, and the server provides data accordingly. The device sends a request to the server based on the user's request, for example, "I want to see my dog's activity level for this month." The server receives the request, searches the database for the necessary data, and sends the visualized data to the device. The input is the user's request, and the output is the visualized data displayed on the device.

[1008] Step 7:

[1009] Chatbot function

[1010] The user enters a question using the in-app chatbot interface. For example, "Why is my dog ​​lethargic?" The device sends this question to the server, which uses a natural language processing (NLP) module to analyze the question. It then uses a generative AI model to generate an appropriate answer and sends it to the device. The device displays the generated answer to the user. For example, it might generate an answer such as, "Recent data shows an increase in stress levels, so please check for changes in the environment and your dog's diet."

[1011] (Application Example 1)

[1012] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[1013] Conventional systems for monitoring a dog's health primarily focused on providing collected data to owners, limiting how this information could be utilized in physical stores. Furthermore, they lacked specific recommendations based on the dog's health and effective coordination with veterinary hospitals in case of abnormalities, making it difficult for owners to take prompt action. Therefore, more comprehensive monitoring and immediate response are needed.

[1014] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[1015] In this invention, the server includes means for collecting data on the dog's physical condition and behavior from sensors; means for transmitting the collected data to the server; means for analyzing the received data on the server and using a generative AI model to determine the dog's health status; means for visualizing the analysis results and displaying them in the form of graphs or the like; means for a chatbot function to receive user questions and answer those questions using the analysis results and existing data; means for displaying the dog's health data when the dog visits a pet supply store or veterinary hospital; means for recommending appropriate pet food and supplements based on the health data; and means for making an appointment in cooperation with a veterinary hospital if an abnormality is detected. This enables comprehensive monitoring of the dog's health status and immediate response.

[1016] A "sensor" is a device used to collect data about a dog's physical condition and behavior.

[1017] A "server" is a computer system that receives collected data, analyzes it, and provides the necessary information.

[1018] A "generative AI model" is an artificial intelligence model used to assess a dog's health status, deriving analysis results from multiple data points.

[1019] "Visualization" is a technique that makes information easier to understand intuitively by displaying data and analysis results in graphs and other visual formats.

[1020] A "chatbot function" is a feature that receives questions from users and automatically generates answers based on analysis results and existing data.

[1021] A "pet supply store" is a physical store that sells products related to pets.

[1022] A "veterinary hospital" is a medical facility that specializes in the health management and treatment of animals.

[1023] "Health data" is a general term for information about a dog's physical condition, behavior, diet, etc.

[1024] "Recommendation" refers to recommending appropriate products or services to users based on analysis results.

[1025] "Collaboration" refers to a means of directly communicating with animal hospitals and taking appropriate action when an abnormality is detected.

[1026] A "reservation" is the process of setting a date and time in advance to use a service.

[1027] This invention is a system for monitoring a dog's health status, intended for use in pet supply stores and veterinary clinics. Specific embodiments of this system are described below.

[1028] Hardware and software to use

[1029] Hardware:

[1030] Smartphone (user's device)

[1031] Smart collar (a sensor worn on a dog)

[1032] software:

[1033] Flask (Web framework)

[1034] Python (a programming language)

[1035] Generative AI models (data analysis and chatbot functionality)

[1036] Data collection and transmission

[1037] The device collects health and behavioral data, such as heart rate, activity level, food intake, and elimination timing, from smart collars and sensors attached to the dog. This collected data is periodically encrypted in batches and sent to a server.

[1038] Data Analysis

[1039] The server stores the received data in a database. The database manages the data using a unique ID that identifies each dog. A generative AI model then analyzes the data, determining stress levels from heart rate and assessing whether the dog is getting enough exercise based on activity levels. It also compares the data with past data to check for any anomalies.

[1040] Visualization of the process

[1041] The analysis results are converted into visual formats such as graphs and alert messages. The server stores this visualization data in a database and sends it upon request from the terminal. The terminal displays this data in its user interface, allowing the user to visually understand the dog's health status.

[1042] Use at physical stores

[1043] When pet owners visit pet supply stores or veterinary clinics, health data is collected from smart collars and sensors worn by their dogs. The analysis results are instantly displayed on a terminal and provided to the owner. Based on the analysis results, there is a function to recommend appropriate pet food and supplements. In addition, if an abnormality is detected, it is possible to make an appointment directly through a linkage function with the veterinary clinic.

[1044] Chatbot function

[1045] Users enter questions through the in-app chatbot interface. For example, if a user asks "Why is my dog ​​lethargic?", the question is sent from the device to the server. The server analyzes the question using a natural language processing (NLP) module and generates an appropriate answer. The generated answer is sent to the device and displayed to the user.

[1046] Specific example

[1047] A user visits a pet shop and uses a smartphone app to read data from a dog wearing a smart collar.

[1048] When you enter "Please tell me about your recent health status" into the app, your health data is sent to the server, and the analysis results are returned to the app.

[1049] The app provides advice such as, "Your recent heart rate has been high, which may indicate you are experiencing a lot of stress. Please create a stress-free environment for yourself."

[1050] Examples of prompt messages include, "My dog's activity level is low. What are the possible causes and solutions?" and "Based on recent data, please recommend a suitable food for my pet."

[1051] In this way, the system can monitor a dog's health in real time and provide appropriate feedback to the user. This allows pet owners to detect health problems in their dogs early and take appropriate action.

[1052] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[1053] Step 1:

[1054] The user collects data from a smart collar attached to the dog.

[1055] Input: Dog's health and behavioral data

[1056] Output: The collected data is stored on the device.

[1057] Specific operation: The device collects data such as heart rate, activity level, and food intake from the smart color's sensors via Bluetooth.

[1058] Step 2:

[1059] The device encrypts the collected data and sends it to the server.

[1060] Input: Collected health and behavioral data of dogs

[1061] Output: Encrypted data is sent to the server.

[1062] Specific operation: The terminal encrypts the data using AES and sends it to the server using the HTTPS protocol.

[1063] Step 3:

[1064] The server stores the received data in the database.

[1065] Input: Encrypted dog health and behavior data

[1066] Output: Data stored in the database

[1067] Specific operation: The server releases the incoming data and stores it in the database, identifying each dog with a unique ID.

[1068] Step 4:

[1069] The server uses a generative AI model to analyze the data.

[1070] Input: Dog health and behavioral data stored in the database

[1071] Output: Analysis results of health status

[1072] Specific operation: The server uses a generated AI model to analyze heart rate and activity data to determine the dog's stress level and lack of exercise.

[1073] Step 5:

[1074] The server visualizes the analysis results in graphs and alert messages.

[1075] Input: Analysis results of health status

[1076] Output: Visualized data (graphs, alert messages)

[1077] Specific operation: The server converts the analysis results into graphs using visualization libraries such as D3.js, and also generates alert messages if necessary.

[1078] Step 6:

[1079] The server sends the visualized data to the terminal.

[1080] Input: Visualized data

[1081] Output: Visualized data delivered to the terminal

[1082] Specific operation: The server converts the visualization data into JSON format and sends it to the terminal using the HTTPS protocol.

[1083] Step 7:

[1084] The terminal displays visualized data in its user interface.

[1085] Input: Visualization data

[1086] Output: Graphs and alert messages displayed in the user interface

[1087] Specific operation: The terminal parses the received JSON data and displays the data in the user interface using HTML and JavaScript.

[1088] Step 8:

[1089] Users enter their questions through a chatbot interface.

[1090] Input: Question for the chatbot (e.g., "Why is my dog ​​lethargic?")

[1091] Output: Question data to send to the server

[1092] Specific operation: The terminal uses a natural language processing module to initially process the question entered by the user and then sends it to the server.

[1093] Step 9:

[1094] The server analyzes the question using a natural language processing module and generates an answer.

[1095] Input: Question data

[1096] Output: Generated answer

[1097] Specific operation: The server analyzes the question using the natural language processing module of the generative AI model and generates an appropriate answer based on health data.

[1098] Step 10:

[1099] The server sends the generated response to the terminal.

[1100] Input: Generated answer

[1101] Output: Response data received on the device

[1102] Specific operation: The server converts the generated response into JSON format and sends it to the terminal using the HTTPS protocol.

[1103] Step 11:

[1104] The terminal displays the generated response to the user.

[1105] Input: Response data

[1106] Output: Answer displayed in the user interface

[1107] Specific operation: The device analyzes the received response data and displays the response in the chatbot interface using HTML and JavaScript.

[1108] Through the above processing steps, it is possible to monitor the dog's health status in real time and provide appropriate feedback to the user.

[1109] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[1110] This invention provides a system for understanding the health status of pet dogs and taking appropriate measures, and in particular, by combining it with an emotion engine that recognizes the user's emotions, it achieves more accurate feedback. Specific embodiments of this system are described below.

[1111] System Overview

[1112] This system collects data from sensors attached to dogs and from the user's device, analyzes it on a server, and visualizes the dog's health status. It also features an emotion engine that recognizes the user's emotional state, and the chatbot adjusts its responses accordingly.

[1113] Data collection and transmission

[1114] The device (smartphone app) collects data from smart collars and sensors attached to the dog. This data includes heart rate, activity level, food intake, and elimination timing. This collected data is periodically encrypted in batches and sent to the server.

[1115] Data Analysis

[1116] The server stores the received data in a database. The database manages the data using a unique ID that can identify each dog. A generative AI model then analyzes the data, using heart rate data to assess stress levels and activity data to determine if the dog is getting enough exercise. It also compares the data with past data to check for any anomalies.

[1117] Visualization of the process

[1118] The analysis results are converted into visual formats such as graphs and alert messages. The server stores this visualization data back into a database and sends it upon request from the terminal. The terminal displays this data in its user interface, allowing the user to visually understand the dog's health status.

[1119] Chatbot function

[1120] Users enter questions through the in-app chatbot interface. For example, if a user asks, "Why is my dog ​​lethargic?", the question is sent from the device to the server. The server analyzes the question using a natural language processing (NLP) module and generates an appropriate answer. The generated answer is sent to the device and displayed to the user.

[1121] User emotion recognition

[1122] The device inputs the user's voice data and facial expression data into the emotion engine. The emotion engine uses voice analysis and image analysis to determine the user's emotional state.

[1123] Emotion-based feedback

[1124] The server adjusts the chatbot's responses based on emotional data obtained from the emotion engine. For example, if the user is feeling anxious, it will generate a response in a gentler tone to provide more reassurance. This allows the user to receive more appropriate feedback.

[1125] Explanation of specific examples

[1126] Specific examples of data collection and display.

[1127] 1. As an example, the user attaches a smart collar to a dog.

[1128] 2. The device collects data on the dog's heart rate and activity level from the smart collar.

[1129] 3. The device sends the collected data to the server.

[1130] 4. The server analyzes the data to determine the dog's stress level and activity level.

[1131] 5. The server converts the analysis results into a graph format and sends it to the terminal.

[1132] 6. The terminal displays the analysis results on the user interface, allowing the user to visually understand the dog's health status.

[1133] Concrete examples of emotional engines

[1134] 1. The user enters a question into the chatbot about their dog's lethargy.

[1135] 2. The device inputs the user's voice and facial expression data into the emotion engine.

[1136] 3. The emotion engine analyzes the user's emotional state and determines that they are anxious.

[1137] 4. The device sends the question and sentiment data to the server.

[1138] 5. The server generates appropriate responses that take emotional data into account. For example, it might generate a gentle-toned response such as, "Recent data shows your stress levels are rising, so please review your environment and diet."

[1139] 6. The terminal displays the generated response in the chatbot interface, providing the user with appropriate information.

[1140] This allows users to monitor their dog's health in real time and receive appropriate feedback tailored to their emotions.

[1141] The following describes the processing flow.

[1142] Step 1:

[1143] The device (smartphone app) collects data such as heart rate, activity level, food intake, and elimination timing from smart collars and sensors attached to the dog. The collected data includes information about the dog's health and behavior.

[1144] Step 2:

[1145] The terminal collects data, groups it into batches at regular intervals, and sends it to the server using a secure encryption protocol. This transmission process is carried out to ensure the real-time nature and security of the data.

[1146] Step 3:

[1147] Before analyzing the received data, the server first stores it in a database. The database employs a system where data is managed using a unique ID that can identify each dog.

[1148] Step 4:

[1149] The server inputs data from the database into a generating AI model for data analysis. The generating AI model evaluates stress levels from heart rate data and determines whether or not the user is not getting enough exercise from activity level data. It also checks for any outliers by comparing the current data with past data.

[1150] Step 5:

[1151] The server converts the analysis results of the generated AI model into visualized data such as graphs and alert messages. This visualized data is then stored again in the database.

[1152] Step 6:

[1153] The device periodically sends requests to the server to retrieve the latest visualization data. Because these requests include the dog's ID, the appropriate data is obtained.

[1154] Step 7:

[1155] The server receives the request, extracts the relevant visualization data from the database, and sends it to the terminal.

[1156] Step 8:

[1157] The device displays the received visualization data on the user interface. The user can then visually understand the dog's health condition by viewing this data.

[1158] Step 9:

[1159] The user enters questions about their dog's health into the chatbot. These questions are specific, such as, "Why is my dog ​​lethargic?"

[1160] Step 10:

[1161] The terminal sends the user's questions to the server as text data. Encryption protocols are used during this process to ensure data security.

[1162] Step 11:

[1163] The server inputs the received question into a natural language processing (NLP) module to analyze the intent of the question. It then extracts the information necessary to generate an appropriate answer.

[1164] Step 12:

[1165] The server generates answers to questions using a generative AI model. The generated answers are adjusted as needed based on the user's question.

[1166] Step 13:

[1167] The server sends the generated response as text data to the terminal.

[1168] Step 14:

[1169] The device displays the received response in a chatbot interface, providing the user with relevant information. For example, it might display specific advice such as, "Recent data shows your stress levels are rising, so please check your environment and diet."

[1170] Step 15:

[1171] The device inputs the user's voice data and facial expression data into the emotion engine. The emotion engine uses voice analysis and image analysis to determine the user's emotional state.

[1172] Step 16:

[1173] The server adjusts the chatbot's responses based on data obtained from the emotion engine. For example, if the user is feeling anxious, it generates a response in a gentler tone to provide greater reassurance.

[1174] Step 17:

[1175] The device displays and communicates emotionally-sensitive responses to the user via a chatbot interface. This allows the user to receive optimal feedback tailored to the situation.

[1176] In this way, the system can monitor the dog's health in real time and provide appropriate feedback based on the user's emotions.

[1177] (Example 2)

[1178] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[1179] Traditional dog health management systems have limitations in analyzing collected data and providing feedback to users. Furthermore, they fail to consider user emotions, resulting in an inadequate user experience. Additionally, they lack a clear means of providing detailed analysis results based on the dog's health and behavior, making it difficult for users to take appropriate action.

[1180] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[1181] In this invention, the server includes means for collecting data on the dog's physical condition and behavior from sensors, means for transmitting the collected data to the server, means for analyzing the received data on the server and using a generative AI model to determine the dog's health status, means for visualizing the analysis results and displaying them in the form of a graph or the like, a chatbot function that accepts user questions and answers the questions using the analysis results and existing data, and means for adjusting the chatbot's responses using an emotion engine that recognizes the user's emotions. This enables detailed analysis of the dog's health status and provides the user with appropriate feedback that responds to their emotions.

[1182] A "sensor" is a device attached to a dog to collect data about its physical condition and behavior.

[1183] "Health data" refers to physiological data such as heart rate and body temperature collected to evaluate a dog's health status.

[1184] "Behavioral data" includes data such as the dog's activity level, distance traveled, food intake, and timing of elimination.

[1185] A "terminal" is a communication device used to collect and transmit data, and primarily refers to mobile devices such as smartphones and tablets.

[1186] A "server" is a computer system that receives collected data, performs analysis, and provides the results.

[1187] A "generative AI model" is a model that includes an algorithm that uses machine learning to analyze received data and determine a person's health status.

[1188] "Visualization" refers to converting the results of data analysis into visual formats such as graphs and alert messages, and displaying them in a way that is easy for users to understand.

[1189] A "graph" is a graphic representation used to visually display analysis results, and includes line graphs, pie charts, and other similar types of graphs.

[1190] A "chatbot" is a conversational system that receives user questions and automatically generates answers.

[1191] A "natural language processing module" is a module that includes technology for analyzing user-inputted questions and generating appropriate answers.

[1192] An "emotion engine" is a system that includes technology to determine a user's emotional state from their voice and facial expressions and respond accordingly.

[1193] "Feedback" refers to information provided based on analysis results and user questions, particularly responses that take into account the user's emotional state.

[1194] This invention is a system that monitors a dog's health and provides appropriate feedback to the user. The system comprises sensors attached to the dog, a terminal that collects and transmits data, a server that analyzes the data, and multiple modules for visualizing the analysis results and interacting with the user.

[1195] Hardware configuration

[1196] The sensors collect data such as the dog's heart rate, activity level, food intake, and timing of urination and defecation.

[1197] The device takes the form of a smartphone or tablet, receives data from sensors, and transmits it to a server. It is equipped with data communication capabilities using Bluetooth or Wi-Fi.

[1198] A server is a computer system for storing and analyzing received data, and it runs an analysis engine that uses a database and a generative AI model.

[1199] Software Configuration

[1200] The terminal application has the function of collecting data from sensors, encrypting it, and sending it to the server. It also provides a user interface, displaying visualized data and allowing interaction through a chatbot.

[1201] The server software receives, stores, and analyzes data. The generated AI model is implemented using Python or TensorFlow. The analysis results are visualized using a JavaScript graph plotting library (e.g., Chart.js).

[1202] The emotion engine analyzes user emotions from voice data and facial expression data using tools such as the Microsoft Azure Emotion API.

[1203] The natural language processing module uses the Google Cloud Natural Language API to analyze user questions and generate appropriate answers.

[1204] Specific example

[1205] Data collection

[1206] The user attaches a smart collar to their dog.

[1207] The device collects heart rate and activity data from the smart color, encrypts it, and sends it to the server.

[1208] Data analysis and visualization

[1209] The server analyzes the received data using a generating AI model, assessing stress levels from heart rate data and determining whether there is a lack of exercise from activity level data. It also compares this data with past data to identify any anomalies.

[1210] The analysis results are visualized as graphs and alert messages. For example, if a dog's activity level drops sharply, an alert will be displayed.

[1211] Emotion recognition and feedback

[1212] The user enters a question through the chatbot. For example, they might ask, "Why is my dog ​​lethargic?"

[1213] The device inputs voice data and facial expression data into an emotion engine to analyze the user's emotions.

[1214] The server adjusts the chatbot's responses based on emotional data to generate reassuring answers. For example, it might respond with something like, "Recent data shows your stress levels are rising, so please check your environment and diet."

[1215] Example of a prompt

[1216] "What data is needed to understand a dog's health status?"

[1217] "How can I adjust responses based on user sentiment?"

[1218] This system allows users to gain a detailed understanding of their dog's health and receive appropriate feedback tailored to their emotions.

[1219] The flow of the specific processing in Example 2 will be explained using Figure 13.

[1220] Step 1:

[1221] The user attaches sensors to the dog. The sensors measure heart rate, activity level, food intake, and timing of elimination, etc. This becomes the input data.

[1222] Step 2:

[1223] The device collects data from sensors via Bluetooth or Wi-Fi. This collected data includes heart rate, activity level, food intake, and timing of bowel movements. The data is encrypted within the device. The encryption process ensures the confidentiality of the data. This is then processed and output as data.

[1224] Step 3:

[1225] The terminal periodically sends encrypted data to the server in batches. The input is encrypted data, ensuring that the data reaches the server securely.

[1226] Step 4:

[1227] The server decrypts the received encrypted data and stores it in the database. Each dog is assigned a unique ID, and the data is managed based on this ID. The input data is encrypted data, and the output is data correctly stored in the database.

[1228] Step 5:

[1229] The server uses a generative AI model to analyze data. Specifically, it assesses stress levels from heart rate data and determines whether or not the user is not getting enough exercise from activity level data. It also compares current data with past data to detect anomalies. The input is data read from a database, and the output is the analysis results.

[1230] Step 6:

[1231] The server converts the analysis results into graphs and alert messages. For example, it can generate graphs using a JavaScript graph plotting library (e.g., Chart.js). The input is the analysis results, and the output is the visualized graphs and messages.

[1232] Step 7:

[1233] The server restores the visualized data in the database and sends it in response to requests from the terminal. The input is the visualized data, and the output is the data sent to the terminal.

[1234] Step 8:

[1235] The terminal displays the analysis results on the user interface. This allows the user to visually understand the dog's health status. The input is visualized data received from the server, and the output is the display on the user interface.

[1236] Step 9:

[1237] The user enters a question through the chatbot interface. For example, they might ask, "Why is my dog ​​lethargic?" The input is the user's question.

[1238] Step 10:

[1239] The terminal sends the user's question to the server. The input is the user's question, and the output is the question data sent to the server.

[1240] Step 11:

[1241] The server uses a natural language processing module to analyze the user's question and generate an appropriate answer. For example, it might respond with, "Recent data indicates that your dog's stress level has increased. Please check for changes in its environment and its diet." The input is the user's question, and the output is the generated answer.

[1242] Step 12:

[1243] The server sends the generated response to the terminal. The input is the generated response, and the output is the data sent to the terminal.

[1244] Step 13:

[1245] The terminal displays the response in the chatbot interface, providing the user with appropriate feedback. The input is the response received from the server, and the output is the display on the user interface.

[1246] Step 14:

[1247] The device inputs the user's voice data and facial expression data into the emotion engine. This initiates the analysis of emotions. The input consists of the user's voice data and facial expression data.

[1248] Step 15:

[1249] The emotion engine uses voice and image analysis to determine the user's emotional state. For example, it can check whether the user is feeling anxious. The input is voice data and facial expression data, and the output is the user's emotional state.

[1250] Step 16:

[1251] The device sends emotional data to the server. The input is emotional data, and the output is the data sent to the server.

[1252] Step 17:

[1253] The server adjusts the chatbot's responses based on emotional data. For example, if the user is feeling anxious, it will generate a reassuring response in a gentle tone. The input is emotional data, and the output is the adjusted response.

[1254] Step 18:

[1255] The server sends the adjusted response to the terminal. The input is the adjusted response, and the output is the data sent to the terminal.

[1256] Step 19:

[1257] The device displays the adjusted response in the chatbot interface. This allows the user to receive emotion-sensitive feedback. The input is the adjusted response received from the server, and the output is the display on the user interface.

[1258] Step 20:

[1259] Users can receive feedback and take appropriate action.

[1260] (Application Example 2)

[1261] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[1262] In recent years, interest in pet health management has increased, but there is a lack of integrated systems that allow owners to understand their dog's health status and respond appropriately if suspicious situations arise. Furthermore, pet health management and security monitoring are often handled by separate systems, making unified management difficult. Additionally, the lack of means for users to check their dog's health status and behavior in real time has also been pointed out.

[1263] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting data on the dog's physical condition and behavior from sensors, means for transmitting the collected data to software, means for using a generative AI model in the software to analyze the received data and determine the health status, means for visualizing the analysis results and displaying them in the form of a graph or the like, means for a chatbot function that accepts user questions and answers the questions using the analysis results and existing data, means for monitoring the dog's behavior and environment and notifying the user if a suspicious situation occurs, and means for the user to check the dog's real-time data using a smart device. This makes it possible to provide a system that integrates pet health management and security monitoring.

[1264] A "system" refers to an integrated group of devices that monitor a dog's health and behavior, analyze the collected data, and provide the results to the user.

[1265] A "sensor" is a device attached to a dog to collect data about its health and behavior.

[1266] "Software" refers to a series of programs that receive and analyze data transmitted from sensors.

[1267] A "generative AI model" is an artificial intelligence technology used to analyze received data and determine the health status of a dog.

[1268] "Visualization" refers to the process of displaying analysis results in a visual format, such as a graph.

[1269] A "chatbot" is an automated response system that receives questions from users and generates answers using analysis results and existing data.

[1270] A "notification" is a message sent to the user to inform them if there are any suspicious circumstances regarding the dog's behavior or environment.

[1271] A "smart device" is an interactive electronic device that allows users to check their dog's data in real time.

[1272] This invention is an integrated system for monitoring a dog's health and behavior and providing this information to the user. The system includes sensors attached to the dog, software to receive and analyze the data, a generative AI model, a chatbot to interact with the user, and a smart device.

[1273] Data collection

[1274] Sensors attached to the dog collect data such as heart rate, activity level, food intake, and elimination timing. The sensors transmit this data to software at regular intervals.

[1275] Data transmission and analysis

[1276] The software sends the collected data to the software, and a generating AI model analyzes that data. This analysis includes comparing it with historical data stored in a database to identify anomalies and health risks. For example, if an abnormal heart rate or decreased activity level is detected, a corresponding notification is generated.

[1277] Data visualization and notification

[1278] The analysis results are converted into visual formats such as graphs and alert messages. The software stores this visualization data in a database and sends it upon request from a smart device. The smart device, such as smart glasses, displays this data on a user interface, allowing the user to monitor their dog's health in real time.

[1279] The system also monitors the dog's behavior and environment, and notifies the user if any suspicious situations are detected. For example, if the dog stays in an unusual location for an extended period, or if unusual noises are heard, an alert is immediately sent to the user.

[1280] Chatbot functionality and emotion recognition

[1281] Users can enter questions through the in-app chatbot. These questions are sent to the software, and a generative AI model generates appropriate answers. The software inputs the user's voice and facial expression data into an emotion engine to analyze the user's emotional state. The chatbot's answers are then adjusted based on the emotional state. For example, if the user is feeling anxious, a gentle tone of voice will be used to provide the answer.

[1282] Specific example

[1283] As a concrete example, consider a scenario where a user attaches a smart collar to their dog, and data such as heart rate and activity levels are collected from this collar. The collected data is sent to software and analyzed by a generative AI model. The analysis results are displayed in graph format on smart glasses, allowing the user to visually check the dog's health status. Furthermore, if there is an abnormality in the dog's behavior, for example, if the dog remains still for an unusually long period, the user will be notified. In this case, a message such as, "Your dog's heart rate is higher than normal. Recent data indicates an increased stress level, so please check for changes in the environment and its diet," will be provided via a chatbot.

[1284] Examples of prompts for a generative AI model:

[1285] Please help with the "Pet Health Management Security System." Based on the following information, please create a notification message for the user when displayed in real time on smart glasses: Dog's heart rate: 120, activity level: low. Related information: Suggests lack of exercise. Please make the message specific and in a gentle tone.

[1286] Thus, this invention enables the provision of a system that integrates dog health management and security monitoring, providing users with a means to check their dog's data in real time and take appropriate action.

[1287] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[1288] Step 1:

[1289] The device collects data such as heart rate, activity level, food intake, and elimination timing from sensors attached to the dog. In this data collection process, the device periodically receives the biometric data acquired by the sensors and stores it in digital format. The input is biometric data from the sensors, and the output is digital data stored in the device.

[1290] Step 2:

[1291] The device transmits the collected data to the software. At this time, the device encrypts the data before transmission to ensure communication security. The input is digital data stored on the device, and the output is encrypted data packets. Specifically, the device encrypts the data using the pet sensor SDK and sends it to the server as an HTTP request.

[1292] Step 3:

[1293] The server receives data sent from the terminal and stores it in a database. The server then analyzes the received data and prepares it for input into the generated AI model. The input is encrypted data packets, and the output is digital data stored in the database.

[1294] Step 4:

[1295] The server analyzes data using a generative AI model. Specifically, the AI ​​model analyzes heart rate and activity level data stored in the database to determine the user's health status. The generative AI model detects anomalies by comparing current data with past data. The input is digital data stored in the database, and the output is the health status assessment result.

[1296] Step 5:

[1297] The server visualizes the analysis results. The analysis results are converted into formats such as graphs and alert messages, making them easy to understand visually. The input is the health status assessment results analyzed by the generative AI model, and the output is visualized data (e.g., graphs and alert messages).

[1298] Step 6:

[1299] The server stores the visualized data back into the database and sends it in response to requests from the terminal. The input is the visualized data, and the output is the data sent to the terminal. Specifically, the server sends graph data and alert messages to the terminal as an HTTP response.

[1300] Step 7:

[1301] The terminal displays visualized data on a user interface, allowing users to check their dog's health status. The input is visualized data received from the server, and the output is graphs and alert messages displayed on the user interface.

[1302] Step 8:

[1303] When a user enters a question through the in-app chatbot interface, that question is sent from the device to the server. The input is the user's question, and the output is the data sent to the server.

[1304] Step 9:

[1305] The server analyzes the question using a natural language processing (NLP) module and generates an appropriate answer using a generative AI model. The input is the user's question, and the output is the generated answer.

[1306] Step 10:

[1307] The server sends the generated response to the terminal and displays it in the chatbot interface. The input is the generated response, and the output is the data sent to the terminal. The terminal displays the response in the user interface for the user to confirm.

[1308] Step 11:

[1309] The device inputs the user's voice data and facial expression data into an emotion engine to determine their emotional state. The input is voice data and facial expression data, and the output is the analyzed emotion data.

[1310] Step 12:

[1311] The server adjusts the chatbot's responses based on emotional data obtained from the emotion engine. The input is the analyzed emotional data and the generated response, and the output is the adjusted, gentle-toned response.

[1312] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[1313] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1314] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and specific processing may also be performed by the headset terminal 314.

[1315] [Fourth Embodiment]

[1316] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[1317] As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[1318] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1319] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[1320] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[1321] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[1322] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[1323] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. Furthermore, the robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[1324] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[1325] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[1326] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1327] In robot 414, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[1328] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1329] This invention relates to a system for monitoring the health status of pet dogs. Specific embodiments of this system are described below.

[1330] System Overview

[1331] This system collects data from sensors attached to dogs and from the user's device, analyzes it on a server to visualize the dog's health status, and provides this information to the owner. In addition, it is equipped with a chatbot function that provides appropriate feedback in response to user questions.

[1332] Data collection and transmission

[1333] The device collects health and behavioral data, such as heart rate, activity level, food intake, and elimination timing, from smart collars and sensors attached to the dog. This collected data is periodically encrypted in batches and sent to a server.

[1334] Data Analysis

[1335] The server stores the received data in a database. The database manages the data using a unique ID that identifies each dog. A generative AI model then analyzes the data, determining stress levels from heart rate and assessing whether the dog is getting enough exercise based on activity levels. It also compares the data with past data to check for any anomalies.

[1336] Visualization of the process

[1337] The analysis results are converted into visual formats such as graphs and alert messages. The server stores this visualization data in a database and sends it upon request from the terminal. The terminal displays this data in its user interface, allowing the user to visually understand the dog's health status.

[1338] Chatbot function

[1339] Users enter questions through the in-app chatbot interface. For example, if a user asks "Why is my dog ​​lethargic?", the question is sent from the device to the server. The server analyzes the question using a natural language processing (NLP) module and generates an appropriate answer. The generated answer is sent to the device and displayed to the user.

[1340] Explanation of specific examples

[1341] Specific examples of data collection and display.

[1342] 1. As an example, the user attaches a smart collar to a dog.

[1343] 2. The device collects data on the dog's heart rate and activity level from the smart collar.

[1344] 3. The device sends the collected data to the server.

[1345] 4. The server analyzes the data to determine the dog's stress level and activity level.

[1346] 5. The server converts the analysis results into a graph format and sends it to the terminal.

[1347] 6. The device displays the analysis results to the user, allowing them to visually understand the dog's health status.

[1348] Examples of chatbots

[1349] 1. The user notices that their dog is lethargic and enters the question, "Why is my dog ​​lethargic?" into the chatbot.

[1350] 2. The terminal sends the question to the server.

[1351] 3. The server analyzes the question and generates an answer using a generative AI model.

[1352] 4. The server generates a response stating, "Recent data indicates an increase in stress levels; please review your environment and diet," and sends it to the device.

[1353] 5. The terminal displays the generated response to the user.

[1354] In this way, the system can monitor a dog's health in real time and provide appropriate feedback to the user. This allows pet owners to detect health problems in their dogs early and take appropriate action.

[1355] The following describes the processing flow.

[1356] Step 1:

[1357] The device (smartphone app) collects data from a smart collar or sensor attached to the dog. The collected data includes heart rate, activity level, food intake, and timing of elimination.

[1358] Step 2:

[1359] The terminal collects data, groups it into batches at regular intervals, and sends it to the server using an encryption protocol.

[1360] Step 3:

[1361] Before analyzing the received data, the server first stores it in a database. The database manages the data using a unique ID that can identify each dog.

[1362] Step 4:

[1363] The server retrieves data from the database and inputs it into the generative AI model. The generative AI model uses heart rate data to assess stress levels and activity data to determine whether or not the user is getting enough exercise. It also compares the current data with past data to check for any anomalies.

[1364] Step 5:

[1365] The server converts the analysis results of the generated AI model into visualized data such as graphs and alert messages. This visualized data is then stored again in the database.

[1366] Step 6:

[1367] The device periodically sends requests to the server to retrieve the latest visualization data. These requests include the dog's unique ID.

[1368] Step 7:

[1369] The server receives the request, extracts the relevant visualization data from the database, and sends it to the terminal.

[1370] Step 8:

[1371] The device displays the received visualization data on the user interface. Users can then visually understand their dog's health status by viewing this data.

[1372] Step 9:

[1373] The user enters a question about their dog's health into the chatbot. Example: "Why is my dog ​​lethargic?"

[1374] Step 10:

[1375] The terminal sends the user's question as text data to the server. This transmission also uses an encryption protocol.

[1376] Step 11:

[1377] The server analyzes the received question using a natural language processing (NLP) module. It understands the intent of the question and extracts the information necessary to provide an appropriate response.

[1378] Step 12:

[1379] The server generates responses using a generative AI model based on the analysis results, historical records in the database, and current health data.

[1380] Step 13:

[1381] The server sends the generated response as text data to the terminal.

[1382] Step 14:

[1383] The device displays the received response in the chatbot interface, providing the user with relevant information. For example, it might display a response such as, "Recent data shows your stress levels are rising, so please check for changes in your environment and your diet."

[1384] This allows users to monitor their dog's health in real time and take swift action as needed.

[1385] (Example 1)

[1386] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1387] Monitoring and analyzing a dog's health in real time and providing easily understandable feedback to owners was not easy with conventional technology. In particular, accurately collecting diverse data on a dog's physical condition and behavior, and appropriately analyzing it to detect abnormalities early was difficult. Providing immediate answers to specific questions and problems faced by owners was also a challenge.

[1388] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[1389] In this invention, the server includes means for collecting data on the dog's physical condition and behavior from sensors, means for encrypting the collected data and transmitting it to the server, means for storing the received data in a database on the server, analyzing the data using a generative AI model to determine the dog's health status, means for visualizing the analysis results and displaying them in a visual format such as a graph, and means for a chatbot function that accepts user questions and answers the questions using the analysis results and existing data. This enables a detailed understanding of the dog's health status, real-time analysis, and immediate feedback.

[1390] A "sensor" is a device used to collect data about a dog's health and behavior.

[1391] "Health data" refers to information about a dog's physiological state, such as its heart rate, body temperature, and stress level.

[1392] "Behavioral data" refers to information about a dog's daily activities, such as the amount of exercise it gets, the distance it walks, and its activity level.

[1393] "Encryption" is the process of converting data into a format that cannot be understood by a third party in order to transmit it securely.

[1394] A "server" is a computer system used to store and analyze received data.

[1395] A "database" is a system for systematically storing and managing received data.

[1396] A "generative AI model" is an artificial intelligence model that analyzes collected data to diagnose and predict the health status of dogs.

[1397] "Visualization" is the process of converting analysis results into visual formats such as graphs and charts.

[1398] A "chatbot" is an interactive interface that receives user questions and provides appropriate answers.

[1399] A "Natural Language Processing (NLP) module" is a technology that understands user questions and requests and generates appropriate responses.

[1400] This invention is a system that monitors and analyzes a dog's health status in real time and provides user-friendly feedback. The system is implemented by combining a series of hardware and software components, including sensors, terminals, and a server.

[1401] Data collection and transmission

[1402] The device collects health and behavioral data, such as heart rate, activity level, food intake, and elimination timing, from sensors attached to the dog. These sensors include smart collars. The collected data is encrypted by the device and sent to the server periodically in batches. For example, AES-256 encryption is used, and data is sent every hour.

[1403] Data storage and analysis

[1404] The server stores the transmitted data in a database. Each dog is assigned a unique ID, and the data is managed in association with that ID. The server then analyzes the data using a generative AI model, estimating stress levels from heart rate and determining insufficient exercise from activity levels. An algorithm also operates to detect anomalies by comparing them with past data.

[1405] Visualization of the process

[1406] The analysis results are converted into visual formats such as graphs and charts by the server. For example, a line graph showing the dog's stress level and a bar graph showing its activity level are generated. The server stores this visualized data back into the database and sends it to the user's terminal upon request.

[1407] User Interface

[1408] The device displays the visualized data received from the server on the user interface. This allows users to visually understand their dog's health status on the screen of their smartphone or tablet. For example, if a user sends a request such as "I want to see my dog's activity level for this month," the device retrieves the data from the server and displays it.

[1409] Chatbot function

[1410] Users can enter questions using the in-app chatbot interface. For example, "Why is my dog ​​lethargic?" The device sends this question to the server, which uses a natural language processing (NLP) module to analyze the question. It then uses a generative AI model to construct an appropriate answer and sends that answer to the device. The device then displays the generated answer to the user.

[1411] Specific example

[1412] 1. The user puts a smart collar on the dog.

[1413] 2. The device collects data on the dog's heart rate and activity level from the smart collar.

[1414] 3. The device encrypts the data it collects and sends it to the server.

[1415] 4. The server analyzes the data to determine the dog's stress level and activity level.

[1416] 5. The server converts the analysis results into a graph format and sends it to the terminal.

[1417] 6. The device displays the analysis results to the user, allowing them to visually understand the dog's health status.

[1418] 7. The user enters the question "Why is my dog ​​lethargic?" into the chatbot.

[1419] 8. The server analyzes the question and generates a response, "Recent data shows your stress levels are rising, so please check for changes in your environment and your diet," and sends it to the terminal.

[1420] 9. The device displays the generated response to the user.

[1421] The flow of the specific processing in Example 1 will be explained using Figure 11.

[1422] Step 1:

[1423] Data collection

[1424] The device collects data from smart collars and various sensors attached to the dog. The sensors measure data such as heart rate, activity level, food intake, and elimination timing. Input is raw data from the sensors, and output is provided in an appropriately formatted form. For example, the smart collar measures the heart rate every 10 seconds and transmits that data to the device.

[1425] Step 2:

[1426] Data transmission

[1427] The device performs an encryption process on the collected data. Specifically, it protects the data using encryption algorithms such as AES-256, and then periodically sends it to the server in batches. The input is formatted data, and the output is encrypted, transferable data. For example, the device sends all the data to the server every hour.

[1428] Step 3:

[1429] Data storage

[1430] The server decrypts the received encrypted data and stores it in the database. Each dog is identified by a unique ID, and the data is stored associated with that ID. The input is encrypted data sent to the server, and the output is the decrypted data stored in the database. For example, the server registers the data for DogID1234 in the database.

[1431] Step 4:

[1432] Data Analysis

[1433] The server analyzes stored data using a generative AI model. Specifically, it estimates stress levels from heart rate data and determines whether or not a person is getting enough exercise from activity level data. It also detects outliers by comparing them with past data. The input is data stored in a database, and the output is the stress level and exercise deficiency determination results as analysis results. For example, the server compares and analyzes heart rate data from the past week to determine the stress level.

[1434] Step 5:

[1435] Data visualization

[1436] The server converts the analysis results into visual formats such as graphs and charts. Based on the analysis results, it formats the data in a visually easy-to-understand form (e.g., line graphs, bar graphs, alert messages). The input is the analysis results, and the output is the generated visualized data. For example, the server creates a line graph showing the changes in a dog's stress level over time.

[1437] Step 6:

[1438] Data Request Processing

[1439] The user sends a request from their device, and the server provides data accordingly. The device sends a request to the server based on the user's request, for example, "I want to see my dog's activity level for this month." The server receives the request, searches the database for the necessary data, and sends the visualized data to the device. The input is the user's request, and the output is the visualized data displayed on the device.

[1440] Step 7:

[1441] Chatbot function

[1442] The user enters a question using the in-app chatbot interface. For example, "Why is my dog ​​lethargic?" The device sends this question to the server, which uses a natural language processing (NLP) module to analyze the question. It then uses a generative AI model to generate an appropriate answer and sends it to the device. The device displays the generated answer to the user. For example, it might generate an answer such as, "Recent data shows an increase in stress levels, so please check for changes in the environment and your dog's diet."

[1443] (Application Example 1)

[1444] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1445] Conventional systems for monitoring a dog's health primarily focused on providing collected data to owners, limiting how this information could be utilized in physical stores. Furthermore, they lacked specific recommendations based on the dog's health and effective coordination with veterinary hospitals in case of abnormalities, making it difficult for owners to take prompt action. Therefore, more comprehensive monitoring and immediate response are needed.

[1446] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[1447] In this invention, the server includes means for collecting data on the dog's physical condition and behavior from sensors; means for transmitting the collected data to the server; means for analyzing the received data on the server and using a generative AI model to determine the dog's health status; means for visualizing the analysis results and displaying them in the form of graphs or the like; means for a chatbot function to receive user questions and answer those questions using the analysis results and existing data; means for displaying the dog's health data when the dog visits a pet supply store or veterinary hospital; means for recommending appropriate pet food and supplements based on the health data; and means for making an appointment in cooperation with a veterinary hospital if an abnormality is detected. This enables comprehensive monitoring of the dog's health status and immediate response.

[1448] A "sensor" is a device used to collect data about a dog's physical condition and behavior.

[1449] A "server" is a computer system that receives collected data, analyzes it, and provides the necessary information.

[1450] A "generative AI model" is an artificial intelligence model used to assess a dog's health status, deriving analysis results from multiple data points.

[1451] "Visualization" is a technique that makes information easier to understand intuitively by displaying data and analysis results in graphs and other visual formats.

[1452] A "chatbot function" is a feature that receives questions from users and automatically generates answers based on analysis results and existing data.

[1453] A "pet supply store" is a physical store that sells products related to pets.

[1454] A "veterinary hospital" is a medical facility that specializes in the health management and treatment of animals.

[1455] "Health data" is a general term for information about a dog's physical condition, behavior, diet, etc.

[1456] "Recommendation" refers to recommending appropriate products or services to users based on analysis results.

[1457] "Collaboration" refers to a means of directly communicating with animal hospitals and taking appropriate action when an abnormality is detected.

[1458] A "reservation" is the process of setting a date and time in advance to use a service.

[1459] This invention is a system for monitoring a dog's health status, intended for use in pet supply stores and veterinary clinics. Specific embodiments of this system are described below.

[1460] Hardware and software to use

[1461] Hardware:

[1462] Smartphone (user's device)

[1463] Smart collar (a sensor worn on a dog)

[1464] software:

[1465] Flask (Web framework)

[1466] Python (a programming language)

[1467] Generative AI models (data analysis and chatbot functionality)

[1468] Data collection and transmission

[1469] The device collects health and behavioral data, such as heart rate, activity level, food intake, and elimination timing, from smart collars and sensors attached to the dog. This collected data is periodically encrypted in batches and sent to a server.

[1470] Data Analysis

[1471] The server stores the received data in a database. The database manages the data using a unique ID that identifies each dog. A generative AI model then analyzes the data, determining stress levels from heart rate and assessing whether the dog is getting enough exercise based on activity levels. It also compares the data with past data to check for any anomalies.

[1472] Visualization of the process

[1473] The analysis results are converted into visual formats such as graphs and alert messages. The server stores this visualization data in a database and sends it upon request from the terminal. The terminal displays this data in its user interface, allowing the user to visually understand the dog's health status.

[1474] Use at physical stores

[1475] When pet owners visit pet supply stores or veterinary clinics, health data is collected from smart collars and sensors worn by their dogs. The analysis results are instantly displayed on a terminal and provided to the owner. Based on the analysis results, there is a function to recommend appropriate pet food and supplements. In addition, if an abnormality is detected, it is possible to make an appointment directly through a linkage function with the veterinary clinic.

[1476] Chatbot function

[1477] Users enter questions through the in-app chatbot interface. For example, if a user asks "Why is my dog ​​lethargic?", the question is sent from the device to the server. The server analyzes the question using a natural language processing (NLP) module and generates an appropriate answer. The generated answer is sent to the device and displayed to the user.

[1478] Specific example

[1479] A user visits a pet shop and uses a smartphone app to read data from a dog wearing a smart collar.

[1480] When you enter "Please tell me about your recent health status" into the app, your health data is sent to the server, and the analysis results are returned to the app.

[1481] The app provides advice such as, "Your recent heart rate has been high, which may indicate you are experiencing a lot of stress. Please create a stress-free environment for yourself."

[1482] Examples of prompt messages include, "My dog's activity level is low. What are the possible causes and solutions?" and "Based on recent data, please recommend a suitable food for my pet."

[1483] In this way, the system can monitor a dog's health in real time and provide appropriate feedback to the user. This allows pet owners to detect health problems in their dogs early and take appropriate action.

[1484] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[1485] Step 1:

[1486] The user collects data from a smart collar attached to the dog.

[1487] Input: Dog's health and behavioral data

[1488] Output: The collected data is stored on the device.

[1489] Specific operation: The device collects data such as heart rate, activity level, and food intake from the smart color's sensors via Bluetooth.

[1490] Step 2:

[1491] The device encrypts the collected data and sends it to the server.

[1492] Input: Collected health and behavioral data of dogs

[1493] Output: Encrypted data is sent to the server.

[1494] Specific operation: The terminal encrypts the data using AES and sends it to the server using the HTTPS protocol.

[1495] Step 3:

[1496] The server stores the received data in the database.

[1497] Input: Encrypted dog health and behavior data

[1498] Output: Data stored in the database

[1499] Specific operation: The server releases the incoming data and stores it in the database, identifying each dog with a unique ID.

[1500] Step 4:

[1501] The server uses a generative AI model to analyze the data.

[1502] Input: Dog health and behavioral data stored in the database

[1503] Output: Analysis results of health status

[1504] Specific operation: The server uses a generated AI model to analyze heart rate and activity data to determine the dog's stress level and lack of exercise.

[1505] Step 5:

[1506] The server visualizes the analysis results in graphs and alert messages.

[1507] Input: Analysis results of health status

[1508] Output: Visualized data (graphs, alert messages)

[1509] Specific operation: The server converts the analysis results into graphs using visualization libraries such as D3.js, and also generates alert messages if necessary.

[1510] Step 6:

[1511] The server sends the visualized data to the terminal.

[1512] Input: Visualized data

[1513] Output: Visualized data delivered to the terminal

[1514] Specific operation: The server converts the visualization data into JSON format and sends it to the terminal using the HTTPS protocol.

[1515] Step 7:

[1516] The terminal displays visualized data in its user interface.

[1517] Input: Visualization data

[1518] Output: Graphs and alert messages displayed in the user interface

[1519] Specific operation: The terminal parses the received JSON data and displays the data in the user interface using HTML and JavaScript.

[1520] Step 8:

[1521] Users enter their questions through a chatbot interface.

[1522] Input: Question for the chatbot (e.g., "Why is my dog ​​lethargic?")

[1523] Output: Question data to send to the server

[1524] Specific operation: The terminal uses a natural language processing module to initially process the question entered by the user and then sends it to the server.

[1525] Step 9:

[1526] The server analyzes the question using a natural language processing module and generates an answer.

[1527] Input: Question data

[1528] Output: Generated answer

[1529] Specific operation: The server analyzes the question using the natural language processing module of the generative AI model and generates an appropriate answer based on health data.

[1530] Step 10:

[1531] The server sends the generated response to the terminal.

[1532] Input: Generated answer

[1533] Output: Response data received on the device

[1534] Specific operation: The server converts the generated response into JSON format and sends it to the terminal using the HTTPS protocol.

[1535] Step 11:

[1536] The terminal displays the generated response to the user.

[1537] Input: Response data

[1538] Output: Answer displayed in the user interface

[1539] Specific operation: The device analyzes the received response data and displays the response in the chatbot interface using HTML and JavaScript.

[1540] Through the above processing steps, it is possible to monitor the dog's health status in real time and provide appropriate feedback to the user.

[1541] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[1542] This invention provides a system for understanding the health status of pet dogs and taking appropriate measures, and in particular, by combining it with an emotion engine that recognizes the user's emotions, it achieves more accurate feedback. Specific embodiments of this system are described below.

[1543] System Overview

[1544] This system collects data from sensors attached to dogs and from the user's device, analyzes it on a server, and visualizes the dog's health status. It also features an emotion engine that recognizes the user's emotional state, and the chatbot adjusts its responses accordingly.

[1545] Data collection and transmission

[1546] The device (smartphone app) collects data from smart collars and sensors attached to the dog. This data includes heart rate, activity level, food intake, and elimination timing. This collected data is periodically encrypted in batches and sent to the server.

[1547] Data Analysis

[1548] The server stores the received data in a database. The database manages the data using a unique ID that can identify each dog. A generative AI model then analyzes the data, using heart rate data to assess stress levels and activity data to determine if the dog is getting enough exercise. It also compares the data with past data to check for any anomalies.

[1549] Visualization of the process

[1550] The analysis results are converted into visual formats such as graphs and alert messages. The server stores this visualization data back into a database and sends it upon request from the terminal. The terminal displays this data in its user interface, allowing the user to visually understand the dog's health status.

[1551] Chatbot function

[1552] Users enter questions through the in-app chatbot interface. For example, if a user asks, "Why is my dog ​​lethargic?", the question is sent from the device to the server. The server analyzes the question using a natural language processing (NLP) module and generates an appropriate answer. The generated answer is sent to the device and displayed to the user.

[1553] User emotion recognition

[1554] The device inputs the user's voice data and facial expression data into the emotion engine. The emotion engine uses voice analysis and image analysis to determine the user's emotional state.

[1555] Emotion-based feedback

[1556] The server adjusts the chatbot's responses based on emotional data obtained from the emotion engine. For example, if the user is feeling anxious, it will generate a response in a gentler tone to provide more reassurance. This allows the user to receive more appropriate feedback.

[1557] Explanation of specific examples

[1558] Specific examples of data collection and display.

[1559] 1. As an example, the user attaches a smart collar to a dog.

[1560] 2. The device collects data on the dog's heart rate and activity level from the smart collar.

[1561] 3. The device sends the collected data to the server.

[1562] 4. The server analyzes the data to determine the dog's stress level and activity level.

[1563] 5. The server converts the analysis results into a graph format and sends it to the terminal.

[1564] 6. The terminal displays the analysis results on the user interface, allowing the user to visually understand the dog's health status.

[1565] Concrete examples of emotional engines

[1566] 1. The user enters a question into the chatbot about their dog's lethargy.

[1567] 2. The device inputs the user's voice and facial expression data into the emotion engine.

[1568] 3. The emotion engine analyzes the user's emotional state and determines that they are anxious.

[1569] 4. The device sends the question and sentiment data to the server.

[1570] 5. The server generates appropriate responses that take emotional data into account. For example, it might generate a gentle-toned response such as, "Recent data shows your stress levels are rising, so please review your environment and diet."

[1571] 6. The terminal displays the generated response in the chatbot interface, providing the user with appropriate information.

[1572] This allows users to monitor their dog's health in real time and receive appropriate feedback tailored to their emotions.

[1573] The following describes the processing flow.

[1574] Step 1:

[1575] The device (smartphone app) collects data such as heart rate, activity level, food intake, and elimination timing from smart collars and sensors attached to the dog. The collected data includes information about the dog's health and behavior.

[1576] Step 2:

[1577] The terminal collects data, groups it into batches at regular intervals, and sends it to the server using a secure encryption protocol. This transmission process is carried out to ensure the real-time nature and security of the data.

[1578] Step 3:

[1579] Before analyzing the received data, the server first stores it in a database. The database employs a system where data is managed using a unique ID that can identify each dog.

[1580] Step 4:

[1581] The server inputs data from the database into a generating AI model for data analysis. The generating AI model evaluates stress levels from heart rate data and determines whether or not the user is not getting enough exercise from activity level data. It also checks for any outliers by comparing the current data with past data.

[1582] Step 5:

[1583] The server converts the analysis results of the generated AI model into visualized data such as graphs and alert messages. This visualized data is then stored again in the database.

[1584] Step 6:

[1585] The device periodically sends requests to the server to retrieve the latest visualization data. Because these requests include the dog's ID, the appropriate data is obtained.

[1586] Step 7:

[1587] The server receives the request, extracts the relevant visualization data from the database, and sends it to the terminal.

[1588] Step 8:

[1589] The device displays the received visualization data on the user interface. The user can then visually understand the dog's health condition by viewing this data.

[1590] Step 9:

[1591] The user enters questions about their dog's health into the chatbot. These questions are specific, such as, "Why is my dog ​​lethargic?"

[1592] Step 10:

[1593] The terminal sends the user's questions to the server as text data. Encryption protocols are used during this process to ensure data security.

[1594] Step 11:

[1595] The server inputs the received question into a natural language processing (NLP) module to analyze the intent of the question. It then extracts the information necessary to generate an appropriate answer.

[1596] Step 12:

[1597] The server generates answers to questions using a generative AI model. The generated answers are adjusted as needed based on the user's question.

[1598] Step 13:

[1599] The server sends the generated response as text data to the terminal.

[1600] Step 14:

[1601] The device displays the received response in a chatbot interface, providing the user with relevant information. For example, it might display specific advice such as, "Recent data shows your stress levels are rising, so please check your environment and diet."

[1602] Step 15:

[1603] The device inputs the user's voice data and facial expression data into the emotion engine. The emotion engine uses voice analysis and image analysis to determine the user's emotional state.

[1604] Step 16:

[1605] The server adjusts the chatbot's responses based on data obtained from the emotion engine. For example, if the user is feeling anxious, it generates a response in a gentler tone to provide greater reassurance.

[1606] Step 17:

[1607] The device displays and communicates emotionally-sensitive responses to the user via a chatbot interface. This allows the user to receive optimal feedback tailored to the situation.

[1608] In this way, the system can monitor the dog's health in real time and provide appropriate feedback based on the user's emotions.

[1609] (Example 2)

[1610] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1611] Traditional dog health management systems have limitations in analyzing collected data and providing feedback to users. Furthermore, they fail to consider user emotions, resulting in an inadequate user experience. Additionally, they lack a clear means of providing detailed analysis results based on the dog's health and behavior, making it difficult for users to take appropriate action.

[1612] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[1613] In this invention, the server includes means for collecting data on the dog's physical condition and behavior from sensors, means for transmitting the collected data to the server, means for analyzing the received data on the server and using a generative AI model to determine the dog's health status, means for visualizing the analysis results and displaying them in the form of a graph or the like, a chatbot function that accepts user questions and answers the questions using the analysis results and existing data, and means for adjusting the chatbot's responses using an emotion engine that recognizes the user's emotions. This enables detailed analysis of the dog's health status and provides the user with appropriate feedback that responds to their emotions.

[1614] A "sensor" is a device attached to a dog to collect data about its physical condition and behavior.

[1615] "Health data" refers to physiological data such as heart rate and body temperature collected to evaluate a dog's health status.

[1616] "Behavioral data" includes data such as the dog's activity level, distance traveled, food intake, and timing of elimination.

[1617] A "terminal" is a communication device used to collect and transmit data, and primarily refers to mobile devices such as smartphones and tablets.

[1618] A "server" is a computer system that receives collected data, performs analysis, and provides the results.

[1619] A "generative AI model" is a model that includes an algorithm that uses machine learning to analyze received data and determine a person's health status.

[1620] "Visualization" refers to converting the results of data analysis into visual formats such as graphs and alert messages, and displaying them in a way that is easy for users to understand.

[1621] A "graph" is a graphic representation used to visually display analysis results, and includes line graphs, pie charts, and other similar types of graphs.

[1622] A "chatbot" is a conversational system that receives user questions and automatically generates answers.

[1623] A "natural language processing module" is a module that includes technology for analyzing user-inputted questions and generating appropriate answers.

[1624] An "emotion engine" is a system that includes technology to determine a user's emotional state from their voice and facial expressions and respond accordingly.

[1625] "Feedback" refers to information provided based on analysis results and user questions, particularly responses that take into account the user's emotional state.

[1626] This invention is a system that monitors a dog's health and provides appropriate feedback to the user. The system comprises sensors attached to the dog, a terminal that collects and transmits data, a server that analyzes the data, and multiple modules for visualizing the analysis results and interacting with the user.

[1627] Hardware configuration

[1628] The sensors collect data such as the dog's heart rate, activity level, food intake, and timing of urination and defecation.

[1629] The device takes the form of a smartphone or tablet, receives data from sensors, and transmits it to a server. It is equipped with data communication capabilities using Bluetooth or Wi-Fi.

[1630] A server is a computer system for storing and analyzing received data, and it runs an analysis engine that uses a database and a generative AI model.

[1631] Software Configuration

[1632] The terminal application has the function of collecting data from sensors, encrypting it, and sending it to the server. It also provides a user interface, displaying visualized data and allowing interaction through a chatbot.

[1633] The server software receives, stores, and analyzes data. The generated AI model is implemented using Python or TensorFlow. The analysis results are visualized using a JavaScript graph plotting library (e.g., Chart.js).

[1634] The emotion engine analyzes user emotions from voice data and facial expression data using tools such as the Microsoft Azure Emotion API.

[1635] The natural language processing module uses the Google Cloud Natural Language API to analyze user questions and generate appropriate answers.

[1636] Specific example

[1637] Data collection

[1638] The user attaches a smart collar to their dog.

[1639] The device collects heart rate and activity data from the smart color, encrypts it, and sends it to the server.

[1640] Data analysis and visualization

[1641] The server analyzes the received data using a generating AI model, assessing stress levels from heart rate data and determining whether there is a lack of exercise from activity level data. It also compares this data with past data to identify any anomalies.

[1642] The analysis results are visualized as graphs and alert messages. For example, if a dog's activity level drops sharply, an alert will be displayed.

[1643] Emotion recognition and feedback

[1644] The user enters a question through the chatbot. For example, they might ask, "Why is my dog ​​lethargic?"

[1645] The device inputs voice data and facial expression data into an emotion engine to analyze the user's emotions.

[1646] The server adjusts the chatbot's responses based on emotional data to generate reassuring answers. For example, it might respond with something like, "Recent data shows your stress levels are rising, so please check your environment and diet."

[1647] Example of a prompt

[1648] "What data is needed to understand a dog's health status?"

[1649] "How can I adjust responses based on user sentiment?"

[1650] This system allows users to gain a detailed understanding of their dog's health and receive appropriate feedback tailored to their emotions.

[1651] The flow of the specific processing in Example 2 will be explained using Figure 13.

[1652] Step 1:

[1653] The user attaches sensors to the dog. The sensors measure heart rate, activity level, food intake, and timing of elimination, etc. This becomes the input data.

[1654] Step 2:

[1655] The device collects data from sensors via Bluetooth or Wi-Fi. This collected data includes heart rate, activity level, food intake, and timing of bowel movements. The data is encrypted within the device. The encryption process ensures the confidentiality of the data. This is then processed and output as data.

[1656] Step 3:

[1657] The terminal periodically sends encrypted data to the server in batches. The input is encrypted data, ensuring that the data reaches the server securely.

[1658] Step 4:

[1659] The server decrypts the received encrypted data and stores it in the database. Each dog is assigned a unique ID, and the data is managed based on this ID. The input data is encrypted data, and the output is data correctly stored in the database.

[1660] Step 5:

[1661] The server uses a generative AI model to analyze data. Specifically, it assesses stress levels from heart rate data and determines whether or not the user is not getting enough exercise from activity level data. It also compares current data with past data to detect anomalies. The input is data read from a database, and the output is the analysis results.

[1662] Step 6:

[1663] The server converts the analysis results into graphs and alert messages. For example, it can generate graphs using a JavaScript graph plotting library (e.g., Chart.js). The input is the analysis results, and the output is the visualized graphs and messages.

[1664] Step 7:

[1665] The server restores the visualized data in the database and sends it in response to requests from the terminal. The input is the visualized data, and the output is the data sent to the terminal.

[1666] Step 8:

[1667] The terminal displays the analysis results on the user interface. This allows the user to visually understand the dog's health status. The input is visualized data received from the server, and the output is the display on the user interface.

[1668] Step 9:

[1669] The user enters a question through the chatbot interface. For example, they might ask, "Why is my dog ​​lethargic?" The input is the user's question.

[1670] Step 10:

[1671] The terminal sends the user's question to the server. The input is the user's question, and the output is the question data sent to the server.

[1672] Step 11:

[1673] The server uses a natural language processing module to analyze the user's question and generate an appropriate answer. For example, it might respond with, "Recent data indicates that your dog's stress level has increased. Please check for changes in its environment and its diet." The input is the user's question, and the output is the generated answer.

[1674] Step 12:

[1675] The server sends the generated response to the terminal. The input is the generated response, and the output is the data sent to the terminal.

[1676] Step 13:

[1677] The terminal displays the response in the chatbot interface, providing the user with appropriate feedback. The input is the response received from the server, and the output is the display on the user interface.

[1678] Step 14:

[1679] The device inputs the user's voice data and facial expression data into the emotion engine. This initiates the analysis of emotions. The input consists of the user's voice data and facial expression data.

[1680] Step 15:

[1681] The emotion engine uses voice and image analysis to determine the user's emotional state. For example, it can check whether the user is feeling anxious. The input is voice data and facial expression data, and the output is the user's emotional state.

[1682] Step 16:

[1683] The device sends emotional data to the server. The input is emotional data, and the output is the data sent to the server.

[1684] Step 17:

[1685] The server adjusts the chatbot's responses based on emotional data. For example, if the user is feeling anxious, it will generate a reassuring response in a gentle tone. The input is emotional data, and the output is the adjusted response.

[1686] Step 18:

[1687] The server sends the adjusted response to the terminal. The input is the adjusted response, and the output is the data sent to the terminal.

[1688] Step 19:

[1689] The device displays the adjusted response in the chatbot interface. This allows the user to receive emotion-sensitive feedback. The input is the adjusted response received from the server, and the output is the display on the user interface.

[1690] Step 20:

[1691] Users can receive feedback and take appropriate action.

[1692] (Application Example 2)

[1693] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1694] In recent years, interest in pet health management has increased, but there is a lack of integrated systems that allow owners to understand their dog's health status and respond appropriately if suspicious situations arise. Furthermore, pet health management and security monitoring are often handled by separate systems, making unified management difficult. Additionally, the lack of means for users to check their dog's health status and behavior in real time has also been pointed out.

[1695] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting data on the dog's physical condition and behavior from sensors, means for transmitting the collected data to software, means for using a generative AI model in the software to analyze the received data and determine the health status, means for visualizing the analysis results and displaying them in the form of a graph or the like, means for a chatbot function that accepts user questions and answers the questions using the analysis results and existing data, means for monitoring the dog's behavior and environment and notifying the user if a suspicious situation occurs, and means for the user to check the dog's real-time data using a smart device. This makes it possible to provide a system that integrates pet health management and security monitoring.

[1696] A "system" refers to an integrated group of devices that monitor a dog's health and behavior, analyze the collected data, and provide the results to the user.

[1697] A "sensor" is a device attached to a dog to collect data about its health and behavior.

[1698] "Software" refers to a series of programs that receive and analyze data transmitted from sensors.

[1699] A "generative AI model" is an artificial intelligence technology used to analyze received data and determine the health status of a dog.

[1700] "Visualization" refers to the process of displaying analysis results in a visual format, such as a graph.

[1701] A "chatbot" is an automated response system that receives questions from users and generates answers using analysis results and existing data.

[1702] A "notification" is a message sent to the user to inform them if there are any suspicious circumstances regarding the dog's behavior or environment.

[1703] A "smart device" is an interactive electronic device that allows users to check their dog's data in real time.

[1704] This invention is an integrated system for monitoring a dog's health and behavior and providing this information to the user. The system includes sensors attached to the dog, software to receive and analyze the data, a generative AI model, a chatbot to interact with the user, and a smart device.

[1705] Data collection

[1706] Sensors attached to the dog collect data such as heart rate, activity level, food intake, and elimination timing. The sensors transmit this data to software at regular intervals.

[1707] Data transmission and analysis

[1708] The software sends the collected data to the software, and a generating AI model analyzes that data. This analysis includes comparing it with historical data stored in a database to identify anomalies and health risks. For example, if an abnormal heart rate or decreased activity level is detected, a corresponding notification is generated.

[1709] Data visualization and notification

[1710] The analysis results are converted into visual formats such as graphs and alert messages. The software stores this visualization data in a database and sends it upon request from a smart device. The smart device, such as smart glasses, displays this data on a user interface, allowing the user to monitor their dog's health in real time.

[1711] The system also monitors the dog's behavior and environment, and notifies the user if any suspicious situations are detected. For example, if the dog stays in an unusual location for an extended period, or if unusual noises are heard, an alert is immediately sent to the user.

[1712] Chatbot functionality and emotion recognition

[1713] Users can enter questions through the in-app chatbot. These questions are sent to the software, and a generative AI model generates appropriate answers. The software inputs the user's voice and facial expression data into an emotion engine to analyze the user's emotional state. The chatbot's answers are then adjusted based on the emotional state. For example, if the user is feeling anxious, a gentle tone of voice will be used to provide the answer.

[1714] Specific example

[1715] As a concrete example, consider a scenario where a user attaches a smart collar to their dog, and data such as heart rate and activity levels are collected from this collar. The collected data is sent to software and analyzed by a generative AI model. The analysis results are displayed in graph format on smart glasses, allowing the user to visually check the dog's health status. Furthermore, if there is an abnormality in the dog's behavior, for example, if the dog remains still for an unusually long period, the user will be notified. In this case, a message such as, "Your dog's heart rate is higher than normal. Recent data indicates an increased stress level, so please check for changes in the environment and its diet," will be provided via a chatbot.

[1716] Examples of prompts for a generative AI model:

[1717] Please help with the "Pet Health Management Security System." Based on the following information, please create a notification message for the user when displayed in real time on smart glasses: Dog's heart rate: 120, activity level: low. Related information: Suggests lack of exercise. Please make the message specific and in a gentle tone.

[1718] Thus, this invention enables the provision of a system that integrates dog health management and security monitoring, providing users with a means to check their dog's data in real time and take appropriate action.

[1719] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[1720] Step 1:

[1721] The device collects data such as heart rate, activity level, food intake, and elimination timing from sensors attached to the dog. In this data collection process, the device periodically receives the biometric data acquired by the sensors and stores it in digital format. The input is biometric data from the sensors, and the output is digital data stored in the device.

[1722] Step 2:

[1723] The device transmits the collected data to the software. At this time, the device encrypts the data before transmission to ensure communication security. The input is digital data stored on the device, and the output is encrypted data packets. Specifically, the device encrypts the data using the pet sensor SDK and sends it to the server as an HTTP request.

[1724] Step 3:

[1725] The server receives data sent from the terminal and stores it in a database. The server then analyzes the received data and prepares it for input into the generated AI model. The input is encrypted data packets, and the output is digital data stored in the database.

[1726] Step 4:

[1727] The server analyzes data using a generative AI model. Specifically, the AI ​​model analyzes heart rate and activity level data stored in the database to determine the user's health status. The generative AI model detects anomalies by comparing current data with past data. The input is digital data stored in the database, and the output is the health status assessment result.

[1728] Step 5:

[1729] The server visualizes the analysis results. The analysis results are converted into formats such as graphs and alert messages, making them easy to understand visually. The input is the health status assessment results analyzed by the generative AI model, and the output is visualized data (e.g., graphs and alert messages).

[1730] Step 6:

[1731] The server stores the visualized data back into the database and sends it in response to requests from the terminal. The input is the visualized data, and the output is the data sent to the terminal. Specifically, the server sends graph data and alert messages to the terminal as an HTTP response.

[1732] Step 7:

[1733] The terminal displays visualized data on a user interface, allowing users to check their dog's health status. The input is visualized data received from the server, and the output is graphs and alert messages displayed on the user interface.

[1734] Step 8:

[1735] When a user enters a question through the in-app chatbot interface, that question is sent from the device to the server. The input is the user's question, and the output is the data sent to the server.

[1736] Step 9:

[1737] The server analyzes the question using a natural language processing (NLP) module and generates an appropriate answer using a generative AI model. The input is the user's question, and the output is the generated answer.

[1738] Step 10:

[1739] The server sends the generated response to the terminal and displays it in the chatbot interface. The input is the generated response, and the output is the data sent to the terminal. The terminal displays the response in the user interface for the user to confirm.

[1740] Step 11:

[1741] The device inputs the user's voice data and facial expression data into an emotion engine to determine their emotional state. The input is voice data and facial expression data, and the output is the analyzed emotion data.

[1742] Step 12:

[1743] The server adjusts the chatbot's responses based on emotional data obtained from the emotion engine. The input is the analyzed emotional data and the generated response, and the output is the adjusted, gentle-toned response.

[1744] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[1745] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1746] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[1747] Furthermore, the emotion identification model 59, acting as an emotion engine, may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1748] Figure 9 shows an emotion map 400 in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[1749] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[1750] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[1751] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, motorcycles, etc., emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[1752] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[1753] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[1754] The above description primarily focuses on the functions of the data processing device 12 in relation to this disclosure. However, the system related to this disclosure is not necessarily implemented on a server. The system related to this disclosure may be implemented as a general information processing system. This disclosure may be implemented, for example, as a software program that runs on a personal computer or as an application that runs on a smartphone. The method related to this disclosure may be provided to users in SaaS (Software as a Service) format.

[1755] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing of the specific process may be performed by multiple computers, including computer 22. For example, a data generation model 58 may be provided in an external device of the data processing device 12, and the external device may generate data according to the input data.

[1756] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[1757] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[1758] Furthermore, it is not necessary to store the entirety of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[1759] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[1760] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[1761] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[1762] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[1763] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and the like that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[1764] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[1765] The following is further disclosed regarding the embodiments described above.

[1766] (Claim 1)

[1767] It is a system for monitoring a dog's health status.

[1768] A means of collecting data on a dog's health and behavior from sensors,

[1769] A means of sending the collected data to the server,

[1770] A method using a generative AI model to analyze data received on a server and determine health status,

[1771] A means of visualizing the analysis results and displaying them in the form of graphs,

[1772] It includes a chatbot function to receive user questions and a means to answer questions using analysis results and existing data.

[1773] A system that includes this.

[1774] (Claim 2)

[1775] The system according to claim 1, wherein data collection includes multiple parameters relating to the dog's physical condition, temperament, behavior, and diet.

[1776] (Claim 3)

[1777] The system according to claim 1, wherein the generative AI model includes a natural language processing module and has the function of analyzing and generating relevant information based on a user's question.

[1778] "Example 1"

[1779] (Claim 1)

[1780] It is a system for monitoring a dog's health status.

[1781] A means of collecting data on a dog's health and behavior from sensors,

[1782] A means of encrypting the collected data and sending it to the server,

[1783] A means of determining health status by storing data received on a server in a database, analyzing the data using a generated AI model, and

[1784] A means of visualizing the analysis results and displaying them in a visual format such as graphs,

[1785] It includes a chatbot function to receive user questions and a means to answer questions using analysis results and existing data.

[1786] A system that includes this.

[1787] (Claim 2)

[1788] The system according to claim 1, wherein data collection includes multiple parameters relating to the dog's physical condition, temperament, behavior, and diet.

[1789] (Claim 3)

[1790] The system according to claim 1, wherein the generative AI model includes a natural language processing module and has the function of analyzing and generating relevant information based on a user's question.

[1791] "Application Example 1"

[1792] (Claim 1)

[1793] It is a system for monitoring a dog's health status.

[1794] A means of collecting data on a dog's health and behavior from sensors,

[1795] A means of sending the collected data to the server,

[1796] A method using a generative AI model to analyze data received on a server and determine health status,

[1797] A means of visualizing the analysis results and displaying them in the form of graphs,

[1798] It includes a chatbot function to receive user questions and a means to answer questions using analysis results and existing data.

[1799] A means of displaying a dog's health data to customers at pet supply stores and veterinary clinics,

[1800] A means of recommending appropriate pet food and supplements based on health data,

[1801] If an abnormality is detected, a means of making an appointment will be established in cooperation with the animal hospital.

[1802] A system that includes this.

[1803] (Claim 2)

[1804] The system according to claim 1, wherein data collection includes multiple parameters relating to the dog's physical condition, temperament, behavior, and diet.

[1805] (Claim 3)

[1806] The system according to claim 1, wherein the generative AI model includes a natural language processing module and has the function of analyzing and generating relevant information based on a user's question.

[1807] "Example 2 of combining an emotion engine"

[1808] (Claim 1)

[1809] It is a system for monitoring a dog's health status.

[1810] A means of collecting data on a dog's health and behavior from sensors,

[1811] A means of sending the collected data to the server,

[1812] A method using a generative AI model to analyze data received on a server and determine health status,

[1813] A means of visualizing the analysis results and displaying them in the form of graphs,

[1814] It includes a chatbot function to receive user questions and a means to answer questions using analysis results and existing data.

[1815] A means of adjusting chatbot responses using an emotion engine that recognizes user emotions,

[1816] A system that includes this.

[1817] (Claim 2)

[1818] The system according to claim 1, wherein data collection includes multiple parameters relating to the dog's physical condition, temperament, behavior, and diet.

[1819] (Claim 3)

[1820] The system according to claim 1, wherein the generative AI model includes a natural language processing module and has the function of analyzing and generating relevant information based on a user's question.

[1821] "Application example 2 when combining with an emotional engine"

[1822] (Claim 1)

[1823] It is a system for monitoring a dog's health status.

[1824] A means of collecting data on a dog's health and behavior from sensors,

[1825] A means of transmitting the collected data to the software,

[1826] A means of using a generative AI model to analyze received data in software and determine health status,

[1827] A means of visualizing the analysis results and displaying them in the form of graphs,

[1828] It includes a chatbot function to receive user questions and a means to answer questions using analysis results and existing data.

[1829] A means of monitoring the dog's behavior and environment, and notifying the user if suspicious situations occur,

[1830] A means for users to check real-time data on their dogs using smart devices,

[1831] A system that includes this.

[1832] (Claim 2)

[1833] The system according to claim 1, wherein data collection includes multiple parameters relating to the dog's physical condition, temperament, behavior, and diet.

[1834] (Claim 3)

[1835] The system according to claim 1, wherein the generative AI model includes a natural language processing module and has the function of analyzing and generating relevant information based on a user's question. [Explanation of Symbols]

[1836] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. It is a system for monitoring a dog's health status. A means of collecting data on a dog's health and behavior from sensors, A means of sending the collected data to the server, A method using a generative AI model to analyze data received on a server and determine health status, A means of visualizing the analysis results and displaying them in the form of graphs, It includes a chatbot function to receive user questions and a means to answer questions using analysis results and existing data. A system that includes this.

2. The system according to claim 1, wherein data collection includes multiple parameters relating to the dog's physical condition, personality, behavior, and diet.

3. The system according to claim 1, wherein the generative AI model includes a natural language processing module and has the function of analyzing and generating relevant information based on a user's question.

Images