system

Abstract

Provide a system. [Solution] A system for managing the health condition of a pet, comprising: means for receiving an image of the pet; means for analyzing the received image and identifying the type of pet; A means for extracting health risk data based on the analyzed pet species; A means to enter basic information about your pet; means for generating excretion status and health risk data based on the basic information and the health risk data; means for generating and transmitting a notification message based on the generated data; A system including:

Description

[Technical Field]

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

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

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

[0004] Pet health conditions change frequently, placing a significant burden on owners. As pets continue to age, it is becoming increasingly important to detect health risks early and take appropriate measures. Furthermore, there is a lack of information available to help owners select appropriate pet food and medical care, creating a need for comprehensive methods of managing pet health. [Means for solving the problem]

[0005] The present invention provides the following means for effectively managing a pet's daily health condition. First, it includes a means for receiving an image of the pet and analyzing the image to identify the pet's species. Next, it includes a means for extracting health risk data based on the analyzed pet's species. It also includes a means for inputting basic information about the pet, and for generating excretion status and health risk data based on the basic information and health risk data. It also includes a means for generating a notification message based on the generated data and sending it to the user, thereby enabling real-time management of the pet's health condition and providing necessary advice and care. It also includes a means for generating and proposing an optimal food plan based on the health risk assessment results, supporting appropriate nutritional management for the pet. Finally, it provides a system that allows the pet's health condition to be visually understood by including a means for recording changes in the pet's physical condition and symptoms and visualizing them in graphs and charts.

[0006] "Pets" are animals that are primarily kept at home, and refer to mammals such as dogs and cats.

[0007] "Health status" is a concept that indicates the physical condition of a pet, such as its physical condition, whether it is sick, and its nutritional status.

[0008] "Images" refers to photos of pets taken with a device such as a camera or smartphone.

[0009] "Analysis" is the process of using calculations and algorithms to extract and understand information from received images or input data.

[0010] "Pet type" refers to the specific breed or type of animal to which the pet belongs, such as "Shiba Inu" or "American Shorthair."

[0011] "Health risk data" is data that expresses potential risks and problems related to pet health in numerical and textual form.

[0012] "Basic information" refers to basic attribute information such as the pet's age, weight, and walking time.

[0013] "Excretion status" refers to information such as the condition, frequency, and amount of your pet's excrement.

[0014] "Notification message" refers to a message that informs the user of the pet's health status, risk assessment results, suggestions, etc.

[0015] "Food plan" refers to the recommended diet and product combination for maintaining a pet's health.

[0016] "Changes in physical condition or symptoms" refers to changes in your pet's health, such as new onset of symptoms or worsening or improvement of existing symptoms.

[0017] "Graphs and charts" refers to diagrams that visually represent pet health data.

[0018] "Notification" refers to the means or action of conveying information to a user.

[0019] "Sending" refers to the act of sending data or a message to a specific recipient.

[0020] A "system" refers to a set of devices or software that operate in combination with multiple means or processes.

[0021] "Real-time" refers to processing or reaction occurring immediately, without delay.

[0022] "Advice" refers to suggestions or recommendations regarding pet health care.

[0023] "Care" refers to actions and services to support the health and lifestyle of pets.

[0024] "Visual understanding" refers to making data and information intuitively understandable using graphs, charts, etc.

[0025] An "algorithm" refers to a set of steps or a computational method for solving a problem. [Brief explanation of the drawings]

[0026] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 11] FIG. 3 is a sequence diagram showing a processing flow of the data processing system according to the first embodiment. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14]FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0027] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

[0028] First, the terms used in the following description will be explained.

[0029] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), and an APU (Accelerated Processing Unit).

[0030] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

[0031] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0032] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0033] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0034] [First embodiment]

[0035] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0036] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0037] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0038] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0039] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0040] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0041] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

[0042] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0043] 2, in the data processing device 12, a specific process is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0044] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0045] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with the specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0046] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0047] The system of the present invention is designed to effectively manage the health of pets and is configured as follows. The main components are a smartphone app used by the user, a central server, and an analytical AI model. The specific functions and operations of the system are described in detail below.

[0048] Data Entry

[0049] Users use a smartphone app to take photos of their pet's excrement and the pet itself, and then upload them to the app. For example, a user can take a photo of their pet's excrement after a morning walk, then take a photo of their pet's face and upload it to the app. At this time, the user also enters basic information about the pet (age, weight, walking time, etc.). This allows users to easily record the health status of their pet.

[0050] Data transmission

[0051] The device collects the data entered by the user into a single packet and sends it to the central server. Specifically, the device generates a data packet that combines two photos and text data (age, weight, and walking time) and sends it to the server as an HTTP POST request.

[0052] AI analysis

[0053] The server sends the received data to an AI model for analysis. First, the image analysis AI analyzes the received image data to identify the type of pet. In this case, the image analysis AI recognizes specific breeds such as "Shiba Inu." Next, the basic information analysis model analyzes the input data, such as age, weight, and walking time, and generates health risk data. This results in an assessment such as "high risk of obesity" or "medium risk of arthritis."

[0054] Health Risk Assessment

[0055] The server integrates these analysis results to assess overall health risk. Specifically, it integrates information on "mild obesity" and "arthritis risk" to perform a comprehensive risk assessment. It then generates a notification message based on the health risk and sends it to the user. For example, a notification might say, "Obesity has been detected. We recommend high-fiber foods. We also suggest supplements that are good for joint health."

[0056] Food plan proposal

[0057] The server generates an optimal food plan based on the health risk assessment results for the user's pet. For example, it lists and suggests "high-fiber foods" and "joint support supplements." This allows users to accurately manage their pet's nutrition.

[0058] Notifications and Reporting

[0059] The server then sends notification messages and reports to the user. The notification messages include information about the analysis results and recommended feeding plans. Additionally, the server generates graphs and charts based on past and current data, allowing the user to visually understand their pet's health status. For example, graphs can be displayed showing weight changes and health risk trends.

[0060] Hospital collaboration

[0061] The server will then connect with hospitals as needed based on the health risk assessment results. For example, if the user is assessed as having a high risk of arthritis, the server will notify the user of a list of nearby affiliated hospitals. It will also send data to hospitals as needed to ensure the user receives appropriate medical services.

[0062] As described above, the system of the present invention aims to comprehensively manage the health status of pets and support early detection and treatment, thereby reducing the burden on owners and contributing to the health and longevity of pets.

[0063] The processing flow will be explained below.

[0064] Step 1:

[0065] The user launches the smartphone app. Using the app's built-in camera function, the user takes a photo of their pet's excrement, then a photo of their pet's face. Each photo is then uploaded to the app. The user also enters basic information about their pet (age, weight, walking time, etc.).

[0066] For example, a user taps the app's "upload image" button, takes a photo of the pet's excrement, then takes a photo of the pet's face, and uploads both to the app.

[0067] Step 2:

[0068] The device collects the data entered by the user (two images and basic information) into a single packet. After generating the data packet, the device sends an HTTP POST request to the central server.

[0069] As a specific example, a terminal generates a JSON-formatted data packet that combines image data and text data, and executes a request called "POST / analyze HTTP / 1.1."

[0070] Step 3:

[0071] The server processes the data received from the device and sends it to an AI model for analysis. First, the server uses image analysis AI to analyze the received pet image and identify the pet's type. In this process, the image analysis AI recognizes specific dog or cat breeds, such as "Shiba Inu." Next, the server uses a basic information analysis model to analyze the input data, such as age, weight, and walking time, and generates health risk data.

[0072] As a specific example, an image analysis AI may determine that "this image is of a Shiba Inu," and a basic information analysis model may assess the animal as "high risk of obesity" and "medium risk of arthritis."

[0073] Step 4:

[0074] The server integrates the image analysis results with the basic information analysis results to assess the overall health risk, and then generates a notification message based on the assessment results and sends it to the user.

[0075] As a specific example, the server integrates data such as "mild obesity" and "risk of arthritis" and generates a notification message saying, "Obesity has been detected. We recommend high-fiber foods. We also suggest supplements that are good for joint health."

[0076] Step 5:

[0077] Based on the health risk assessment results, the server generates an optimal food plan for the user's pet, which may include high-fiber foods and joint support supplements.

[0078] As a specific example, the server lists specific suggestions such as "recommended food: high fiber food" and "recommended supplement: joint support supplement."

[0079] Step 6:

[0080] The server generates a report containing notification messages and a recommended food plan and sends it to the device, where the user can check the received report in the app.

[0081] As a specific example, the server generates a detailed food plan report and sends it to the device along with the message, "Please check the latest analysis results. Obesity has been detected. Try the food plan below."

[0082] Step 7:

[0083] The server generates graphs and charts based on past and current data, visually displaying the pet's health status, which the user can view within the app.

[0084] As a specific example, graphs showing changes in weight and health risks are generated and displayed within the app.

[0085] Step 8:

[0086] If necessary, the server will connect with hospitals based on the health risk assessment results and notify the user of a list of nearby affiliated hospitals, enabling them to receive appropriate medical services.

[0087] As a specific example, a notification message saying "You are at high risk of developing arthritis. Please consult the affiliated hospital below" is sent along with the contact information of the affiliated hospital.

[0088] The above is a specific processing flow of the pet health management system, which allows users to effectively manage the health of their pets.

[0089] Example 1

[0090] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0091] Today, many pets suffer from various health problems due to inadequate health management by their owners. For example, it is difficult to determine the appropriate amount of food and exercise, which can result in problems such as obesity and arthritis. However, there is no easy-to-use system for monitoring pet health on a daily basis and taking appropriate measures. For this reason, there is a need for the development of a system that assesses health risks based on pet photos and basic information and proposes an appropriate food plan.

[0092] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0093] In this invention, the server includes a means for receiving images of the pet from the terminal used by the user, a means for collecting the received images and basic information of the pet into a single data packet and transmitting it, and a means for providing the data packet to an AI model that analyzes the data packet in the central server. This makes it possible to evaluate health risks based on the received image analysis results and the basic information of the pet, and to generate notification messages, propose optimal food plans, and even generate graphs and charts based on past data.

[0094] "User" refers to a person who uses the system.

[0095] "Terminal" refers to an electronic device used by a user, such as a personal digital assistant or computer.

[0096] "Central Server" refers to a central computer system that receives, analyzes, and stores data.

[0097] "Image analysis AI" refers to an artificial intelligence model that analyzes received image data and extracts specific information.

[0098] "Basic information" refers to basic data about your pet, such as age, weight, and walking time.

[0099] "Health risk data" refers to assessment data regarding the health status of pets obtained from the analysis results.

[0100] "Data packet" refers to a unit of information that contains image data and basic information packaged for transmission.

[0101] "Notification message" refers to an information message sent to the user based on the analysis results.

[0102] "Food Plan" refers to a suggested dietary plan for your pet based on health risk data.

[0103] "Graphs and charts" refer to diagrams that visually display changes in a pet's physical condition or symptoms.

[0104] MODE FOR CARRYING OUT THE INVENTION

[0105] The system of the present invention is designed to effectively manage the health of pets, and is composed of a terminal used by the user (e.g., a smartphone), a central server, and an analytical AI model.

[0106] Data entry and submission

[0107] Users can use a smartphone app to take photos of their pet's feces and face and upload them within the app. For example, a user can take photos of their pet's feces and face after a morning walk and upload the photos. At this time, users also enter basic information about their pet (age, weight, walking time, etc.) into the app. This basic information can be easily added through a text input form.

[0108] The device (smartphone) combines the data entered by the user (two photos and text data) into a single data packet and sends it to the central server as an HTTP POST request.

[0109] Data analysis and health risk assessment

[0110] The server sends the received data packet to an AI model for analysis. First, an image analysis AI (such as the TENSORFLOW (registered trademark) model) analyzes the received image data and identifies the type of pet. For example, it may identify the image as a "Shiba Inu." Next, a basic information analysis model analyzes the input data, such as age, weight, and walking time, to generate health risk data. This results in an assessment such as "high risk of obesity" or "medium risk of arthritis."

[0111] The server integrates the analysis results and evaluates the overall health risk. Specifically, it integrates "mild obesity" and "arthritis risk" to perform a comprehensive risk assessment. It then generates a notification message based on the assessment results and sends it to the user. For example, a notification may be generated that reads, "Obesity has been detected. We recommend high-fiber foods. We also suggest supplements that are good for joint health."

[0112] Food plan proposal

[0113] The server generates an optimal food plan based on the health risk assessment results. For example, it retrieves information on "high-fiber foods" and "joint support supplements" from the database, lists them, and suggests them to the user. This suggestion is sent to the user's smartphone as a push notification.

[0114] Notifications and Reporting

[0115] The server generates graphs and charts based on past and latest data along with notification messages and sends them to the user, allowing the user to visually understand the health status of their pet. For example, graphs showing changes in weight and health risks are displayed.

[0116] Hospital collaboration

[0117] The server will then connect with hospitals as needed based on the health risk assessment results. For example, if the user is assessed as having a high risk of arthritis, the server will notify the user of a list of nearby affiliated hospitals. Based on this information, the user can receive appropriate medical services. If necessary, the server will securely transmit data to the hospital.

[0118] Examples and prompts

[0119] Examples:

[0120] After a morning walk, users take photos of their pet's feces and face, and upload them to a smartphone app. They then enter information such as age (3 years), weight (10 kg), and walk time (30 minutes).

[0121] You will receive a notification message saying, "Obesity detected. We recommend high-fiber foods. We also suggest supplements for joint health."

[0122] Check for recommended "high fiber foods" and "joint support supplements."

[0123] Example prompt sentence:

[0124] "Users take photos of their pet's feces and face after their morning walk and upload them through a smartphone app. They also enter their age, weight, and walking time."

[0125] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0126] Step 1:

[0127] The user uses a smartphone app to take photos of their pet's excrement and face, and uploads them within the app. The input is a photo of the pet's excrement, a photo of the face, and basic information (age, weight, walking time). The output is a set of the uploaded photo and the input text data. Specifically, the user takes a photo using the app's camera function, and then enters information such as "3 years old," "10 kg," and "30 minutes" into the input form.

[0128] Step 2:

[0129] The device combines the data entered by the user (two photos and text data) into a single data packet and sends it to the central server as an HTTP POST request. The input is the data uploaded by the user from the app, and the output is the data packet sent as an HTTP POST request. Specifically, the smartphone app generates the data packet in the background and sends an HTTP request to the specified server URL.

[0130] Step 3:

[0131] The server provides the received data packets to the AI ​​model for analysis. The input is the data packet sent from the device, and the output is the data passed to the AI ​​model for analysis. Specifically, the server converts the received data into an analytical format and passes it to the image analysis AI and basic information analysis model.

[0132] Step 4:

[0133] The server uses image analysis AI to analyze the received image data and identify the type of pet. The input is the image data in the data packet, and the output is the identification result of the pet type. For example, the image is analyzed and identified as a "Shiba Inu." The specific operation is to execute image analysis AI (for example, a TensorFlow model).

[0134] Step 5:

[0135] The server uses a basic information analysis model to analyze the input text data and generate health risk data. The input is the age, weight, and walking time data in the data packet, and the output is health risk data. Specifically, the basic information analysis model generates an assessment such as "high risk of obesity" or "medium risk of arthritis."

[0136] Step 6:

[0137] The server integrates the analysis results and performs an overall health risk assessment. The input is the image analysis results and basic information analysis results, and the output is the integrated health risk assessment results. Specifically, a Python script integrates "mild obesity" and "arthritis risk."

[0138] Step 7:

[0139] The server generates a notification message based on the assessment results and sends it to the user. The input is the health risk assessment result, and the output is the generated notification message. Specifically, the Python script generates a message saying, "Obesity has been detected. High-fiber foods are recommended. Supplements that are good for joint health are also suggested." and sends a push notification.

[0140] Step 8:

[0141] The server generates and proposes an optimal food plan based on the health risk assessment results. The input is the health risk assessment results, and the output is a recommended food plan. Specifically, it retrieves information on "high fiber foods" and "joint support supplements" from the database and creates a list.

[0142] Step 9:

[0143] The server generates graphs and charts based on past and latest data along with notification messages and sends them to the user. The input is past and latest data, and the output is the generated graphs and charts. Specifically, the graphs are generated using libraries such as Matplotlib and Seaborn and displayed in the app.

[0144] Step 10:

[0145] The server will communicate with hospitals as needed based on the health risk assessment results. The input is the health risk assessment results, and the output is a list of affiliated hospitals and the transmission of necessary medical data. Specifically, if the user is assessed as having a "high risk of arthritis," the server retrieves a list of nearby affiliated hospitals from the database and notifies the user. It also executes an API to securely send data to hospitals as needed.

[0146] (Application example 1)

[0147] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0148] Existing methods for managing pet health make it difficult for owners to accurately record their pet's waste and physical condition and take appropriate health measures. It is also time-consuming to select food and suggest supplements based on the pet's health condition. Furthermore, there is a lack of integration with food delivery services that address pet health risks. Therefore, there is a need for a system that provides comprehensive and efficient pet health management.

[0149] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0150] In this invention, the server includes means for receiving images of the pet, means for analyzing the received images to identify the type of pet, means for extracting health risk data based on the analyzed type of pet, means for inputting basic information about the pet, means for generating excretion status and health risk data based on the basic information and the health risk data, means for generating and sending a notification message based on the generated data, and means for generating a food plan based on the health risks and linking with a food delivery service, thereby enabling comprehensive and efficient management of the pet's health status and the recommendation and delivery of appropriate food and supplements.

[0151] The "means for receiving pet images" is a device or system that allows a user to send images of a pet taken using a smartphone or camera to a server.

[0152] "Means for analyzing the received image and identifying the type of pet" refers to a device or system that includes an algorithm or software for identifying the type or breed of pet by analyzing the received image data.

[0153] The "means for extracting health risk data" is a device or system for extracting health risk data related to pets based on the type and basic information of the pets.

[0154] The "means for inputting basic information about a pet" refers to a device or system that allows a user to input basic information about a pet, such as age, weight, and walking time.

[0155] The "means for generating data on excretion status and health risks" refers to a device or system for generating information on a pet's excretion status and health risks based on basic information about the pet and analyzed health risk data.

[0156] "Means for generating and transmitting notification messages" refers to a device or system for creating and transmitting notification messages to users on smartphones or other devices based on the generated health risk data.

[0157] "Means for generating food plans and linking with food delivery services" refers to a device or system for creating an appropriate food plan based on the results of a pet's health risk assessment and providing the selected food and supplements in collaboration with a food delivery service.

[0158] "Means for recording changes in a pet's physical condition and symptoms and visualizing them in graphs and charts" refers to a device or system that records changes in a pet's physical condition and symptoms as data, converts that data into graphs and charts, and visually displays them to the user.

[0159] This invention is a system for effectively managing the health of pets, and is composed of the following main components: a smartphone app used by the user, a central server, and an analytical AI model.

[0160] Data Entry

[0161] Users use a smartphone app to take pictures of their pet's feces and the pet itself, and upload them to the app. At the same time, users can also enter basic information about their pet (age, weight, walking time, etc.).

[0162] Data transmission

[0163] The device collects the data entered by the user into a single packet and sends it to the central server. Specifically, the device generates a data packet that combines two photos and text data (age, weight, and walking time) and sends it to the server as an HTTP POST request.

[0164] AI analysis

[0165] The server sends the received data to an AI model for analysis. The image analysis AI analyzes the received image data and identifies the type of pet. The basic information analysis model analyzes the input data, such as age, weight, and walking time, and generates health risk data. For example, it can provide assessment results such as "high risk of obesity" or "medium risk of arthritis."

[0166] Health Risk Assessment

[0167] The server integrates these analysis results and evaluates the overall health risk. Based on the evaluation, it generates a notification message according to the health risk and sends it to the user.

[0168] Food plan proposal

[0169] The server generates an optimal food plan based on the health risk assessment results for the user's pet. For example, the server lists and recommends "high-fiber foods" and "joint support supplements" to the user. The system works in conjunction with a food delivery service to deliver the selected foods and supplements to the user.

[0170] Notifications and Reporting

[0171] The server sends notification messages and reports to the user, including analysis results and recommended feeding plans. The server generates graphs and charts based on past and current data, allowing the user to visually understand the health status of their pet.

[0172] Hardware and Software Used

[0173] Smartphone (for users to take pictures and enter data)

[0174] Central server (for data analysis and results transmission)

[0175] AI model (using Python libraries such as PIL and requests for image analysis and basic information analysis)

[0176] FastAPI (for server-side APIs)

[0177] Processing examples and prompt statements

[0178] For example, a user can take photos of their dog's excrement and face with their smartphone and upload them to the app. This data is then analyzed on a central server and classified as "Shiba Inu," "high risk of obesity," or "medium risk of arthritis." The app then recommends "high-fiber food" and "joint support supplements" to the user, who can then purchase them and use the food delivery service.

[0179] Example prompt sentence:

[0180] Take photos of your dog's feces and face, and enter your pet's age, weight, and walking time. Based on that data, we will provide you with an appropriate health risk assessment and food plan suggestions.

[0181] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0182] Step 1:

[0183] Users use a smartphone app to take photos of their pet's feces and face, upload them to the app, and then enter basic information about their pet (age, weight, walking time).

[0184] Input: Photo of pet's waste, face photo, age, weight, walking time

[0185] Output: Image data, basic information data

[0186] What happens: A user opens the app, takes a photo using the camera, fills in basic information in a form, and presses the submit button.

[0187] Step 2:

[0188] The device collects the data received from the user into a single data packet and sends it to the central server using an HTTP POST request.

[0189] Input: Image data, basic information data

[0190] Output: HTTP POST request to the server

[0191] Specific operation: The smartphone app packs two photos and text data into a packet and sends it to the server's API endpoint.

[0192] Step 3:

[0193] The server sends the received data to an AI model for analysis. The image analysis AI analyzes the received image data and identifies the type of pet.

[0194] Input: Data packet (image data, basic information data)

[0195] Output: Pet type (e.g. Shiba Inu)

[0196] Specific operation: After receiving the data, the server passes the image data to the AI ​​model, which performs image analysis and obtains the pet's type as a result.

[0197] Step 4:

[0198] The server uses a basic information analysis model to analyze the entered age, weight, and walking time, and generates health risk data.

[0199] Input: Age, weight, walking time

[0200] Output: Health risk data (e.g., high risk of obesity, medium risk of arthritis)

[0201] Specific operation: The server passes basic information to the analysis model, performs data calculations, and generates health risk data.

[0202] Step 5:

[0203] The server aggregates the analysis results, assesses the overall health risk, and generates notification messages based on the assessment.

[0204] Input: Pet type, health risk data

[0205] Output: Health risk assessment results, notification message

[0206] Specific operation: The server integrates pet type and health risk data, uses AI models to assess the overall health risk, and generates a notification message.

[0207] Step 6:

[0208] The server generates an optimal food plan based on the health risk assessment results and proposes it to the user. It also works with food delivery services to deliver food to the user.

[0209] Input: Health risk assessment results

[0210] Output: Food plan, food delivery request

[0211] What it does: The server uses the AI ​​model to generate an appropriate food plan and sends a delivery request using the food delivery service's API.

[0212] Step 7:

[0213] The server sends notification messages and reports to the user. The server displays a message to the user containing information about the analysis results and recommended food plan.

[0214] Input: Health risk assessment results, food plan

[0215] Output: Notification messages, reports

[0216] Specific operation: The server generates notification messages and reports based on the analysis results and food plans, and sends them to a smartphone app, where users can view them.

[0217] Furthermore, an emotion engine that estimates the user's emotion may be combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0218] The system of the present invention is for managing the health of pets and incorporates an emotion engine that provides notification messages and suggests food plans that take into account the user's emotional state. The system consists of a smartphone app, a central server, an analytical AI model, and an emotion engine.

[0219] Data Entry

[0220] A user uses a smartphone app to take photos of their pet's excrement and the pet itself, and uploads them to the app. At this time, the user enters basic information about the pet (age, weight, walking time, etc.). For example, a user might take a photo of their pet's excrement after a morning walk, then take a photo of the pet's face and upload it to the app. In addition, an emotion recognition function is activated within the app to capture the user's emotional state and record the user's current emotional state.

[0221] Data transmission

[0222] The device collects the data input by the user (two images, basic information, and emotion data) into a single packet and sends it to the central server. Specifically, the device generates a data packet that combines image data and text data (age, weight, walking time, and the user's emotional state) and sends it to the server as an HTTP POST request.

[0223] AI analysis

[0224] The server sends the received data to an AI model for analysis. First, the image analysis AI analyzes the pet's image and identifies the pet's type (e.g., "Shiba Inu"). Next, the basic information analysis model analyzes data such as age, weight, and walking time to generate health risk data (e.g., "high risk of obesity" or "medium risk of arthritis"). Furthermore, the emotion engine analyzes the user's emotional state and prepares to provide advice based on that emotional state.

[0225] Health Risk Assessment

[0226] The server combines the results of image analysis and basic information analysis to assess overall health risk. It also generates notification messages based on the assessed health risk data and adjusts the content according to the user's emotional state. For example, if the user appears anxious, it will send a message that reassures them, such as, "Obesity has been detected, but please rest assured that there are measures in place. We recommend high-fiber foods."

[0227] Food plan proposal

[0228] The server generates an optimal food plan based on the health risk assessment results and proposes it to the user. The content of the food plan proposal is also adjusted taking into account the user's emotional state. For example, if the user is in a state of high interest, the server will proactively suggest, "Why not try high-fiber foods? We also have joint support supplements."

[0229] Notifications and Reporting

[0230] The server generates a report containing a notification message and a recommended food plan and sends it to the device. The report reflects the user's emotional state and is presented in a format that is easy for the user to understand. For example, a notification message may be generated that reads, "Please check the latest analysis results. We have prepared a food plan that you can follow with confidence."

[0231] Graph and chart generation

[0232] The server generates graphs and charts based on past and recent data to visually display the pet's health status. These visualized data are also configured taking into account the user's emotional state. For example, if the user is feeling nervous, the data will be displayed in a simple design with easy-to-read colors that give a sense of security.

[0233] Hospital collaboration

[0234] The server will then connect with hospitals as needed based on the health risk assessment results. For example, if the user is assessed as having a high risk of arthritis, the server will send a message based on the user's emotional state, providing a list of nearby affiliated hospitals. If necessary, the server will also send data to hospitals to ensure the user receives appropriate medical services.

[0235] As described above, the system of the present invention comprehensively manages the health condition of pets and takes into account the emotional state of the user to provide more effective support, thereby reducing the burden on owners and contributing to the health and longevity of pets.

[0236] The processing flow will be explained below.

[0237] Step 1:

[0238] The user launches the smartphone app. They take photos of their pet's excrement and face and upload them within the app. They also enter basic information about their pet (age, weight, walking time, etc.). Taking a photo of the user's facial expression triggers the emotion engine to recognize the user's emotions.

[0239] For example, after a morning walk, a user takes a photo of their pet's excrement, then takes a photo of their pet's face, and uploads both to the app. The app then captures the user's current facial expression and obtains emotional data.

[0240] Step 2:

[0241] The device collects the data input by the user (two images, basic information, and emotion data) into a single packet and sends it to the central server. The data packet contains image data, text data (age, weight, walking time), and emotion data obtained by the emotion engine.

[0242] As a specific example, the device generates a JSON-formatted data packet that includes an image, basic information, and emotion data, and executes "POST / analyze HTTP / 1.1."

[0243] Step 3:

[0244] The server starts the process of sending the received data to an AI model for analysis. First, the image analysis AI analyzes the pet's image and identifies the pet's species. Next, the basic information analysis model analyzes the input data and generates health risk data. Finally, the emotion engine analyzes the user's emotion data.

[0245] For example, the image analysis AI identifies the dog as a "Shiba Inu," and the basic information analysis model evaluates it as "high risk of obesity" and "medium risk of arthritis." The emotion engine recognizes the user's emotion as "anxiety."

[0246] Step 4:

[0247] The server integrates the results of image analysis, basic information analysis, and the emotion engine to assess the overall health risk, and generates a notification message based on the assessment results, tailoring the message content to the user's emotional state.

[0248] As a specific example, the server combines "mild obesity" and "arthritis risk" and generates a notification message saying, "Obesity has been detected, but there are measures you can take. We recommend high-fiber foods."

[0249] Step 5:

[0250] The server generates an optimal food plan based on the health risk assessment results and proposes it to the user. The generated food plan is also adjusted according to the user's emotional state.

[0251] As a concrete example, if the emotion engine recognizes that the user's emotion is "curious," it will make a proactive suggestion such as, "Why not try some high-fiber foods? We also recommend some joint support supplements."

[0252] Step 6:

[0253] The server generates a report containing notification messages and recommended food plans and sends it to the device, where the user can check the report and understand the health status of their pet.

[0254] As a specific example, the server sends a message saying, "Please check the latest analysis results. We have prepared a food plan that you can follow with confidence," and attaches a detailed food plan report.

[0255] Step 7:

[0256] The server generates graphs and charts based on past and current data to visually display the pet's health status, and these graphs and charts are also displayed in a way that reflects the user's emotional state.

[0257] As a specific example, a graph showing changes in weight and health risks is generated, and if the user is feeling "tense," it is displayed in a color that is easy to see and gives a sense of security.

[0258] Step 8:

[0259] If necessary, the server will connect with hospitals based on the health risk assessment results. The emotion engine will notify the user of a list of nearby affiliated hospitals via a message based on the user's emotional state. It will also send relevant data to the hospitals as needed.

[0260] As a specific example, a notification message stating, "You are at high risk of arthritis. Rest assured, you can consult with the affiliated hospitals listed below," along with contact information for the affiliated hospitals, may be sent.

[0261] The above is a specific processing flow for incorporating an emotion engine into a pet health management system, and this system enables better health management for both users and pets.

[0262] Example 2

[0263] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0264] Conventional pet health management systems support image analysis and basic information input as a means of monitoring pet health, but do not take into account the user's psychological state. This can cause mental stress when users receive notifications or suggestions from the system. Furthermore, health risk assessments and food plan suggestions are uniform, lacking flexibility to respond to the user's emotional state. There is a need to improve this and provide more user-friendly support.

[0265] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0266] In this invention, the server includes means for receiving an image of the pet, means for analyzing the received image and identifying the type of pet, means for extracting health risk data based on the analyzed type of pet, means for inputting basic information about the pet, means for generating excretion status and health risk data based on the basic information and the health risk data, means for generating and sending a notification message based on the generated data, means for acquiring and analyzing the user's emotional state, means for adjusting the content of the notification message based on the emotional state, means for generating and proposing an optimal food plan based on the health risk assessment results, means for adjusting the content of the proposed food plan based on the user's emotional state, means for recording changes in the pet's physical condition and symptoms and visualizing them in graphs or charts, and means for configuring the visualized data according to the user's emotional state.

[0267] This makes it possible to provide appropriate support that is in line with the user's emotional state. Specifically, it is possible to provide notification messages and food plan suggestions that take the user's emotional state into account, as well as visualize the pet's health status, thereby reducing the burden on the user and achieving better health management for their pet.

[0268] The "means for receiving pet images" is a method for importing pet image data taken using a smartphone or camera into an application or server.

[0269] "Means for analyzing images and identifying the type of pet" refers to a method of identifying the type of pet (such as dog breed or cat breed) based on the received image using image recognition technology such as deep learning.

[0270] The "means for extracting health risk data" refers to a method for deriving the relevant health risks based on the identified pet species, with reference to statistical data and medical data.

[0271] "Means for inputting basic information" refers to a method by which a user inputs basic information such as the pet's age, weight, and walking time via a smartphone, computer, etc.

[0272] The "means for generating excretion status and health risk data" is a method for calculating a pet's excretion status and overall health risk based on basic information input by the user and analyzed health risk data.

[0273] The "means for generating and transmitting a notification message" is a method for generating an appropriate notification message for the user based on the generated health risk data and excretion status, and transmitting the message to a designated terminal.

[0274] "Means for acquiring and analyzing the user's emotional state" refers to a method of detecting the user's current emotional state using a camera or voice analysis function and analyzing it as data.

[0275] The "means for adjusting the content of the notification message based on the emotional state" is a method for optimizing the content of the notification message in accordance with various emotions such as tension and anxiety based on the acquired emotional state of the user.

[0276] "Means for generating and proposing an optimal food plan" is a method for calculating an optimal food plan for the relevant pet based on the health risk assessment results and proposing that plan to the user.

[0277] The "means for adjusting the proposed content based on the user's emotional state" is a method for adjusting the content of the generated food plan in a way that is more effectively accepted by the user in accordance with the user's emotional state.

[0278] "Means for recording changes in physical condition and symptoms and visualizing them in graphs and charts" refers to a method for recording changes in a pet's physical condition and symptoms as time-series data and visually displaying them as graphs and charts.

[0279] "Means for configuring visualized data according to the user's emotional state" refers to a method for adjusting the design and color scheme of generated graphs and charts according to the user's emotional state, and providing them in a format that is easy to read and gives a sense of security.

[0280] The system of the present invention is a system that comprehensively manages the health condition of a pet and proposes notification messages and food plans based on the emotional state of the user. Hereinafter, embodiments of the present invention will be described in detail.

[0281] System Configuration

[0282] The system consists of a smartphone app, a central server, an image analysis AI model, an emotion engine, and a data transmission and reception infrastructure. Users mainly use their smartphones to input their pet's health information, and the central server is responsible for data analysis.

[0283] Data Entry

[0284] Users use a smartphone app to take photos of their pet's excrement and face and upload them to the app. At the same time, they also enter basic information about their pet (such as age, weight, and walking time). In particular, an emotion recognition function is activated within the app and records the user's current emotional state using a camera or voice input. For example, a user can take a photo of their pet's excrement after a morning walk, then take a photo of their pet's face and upload it to the app. The emotion recognition function analyzes the user's facial scan and voice tone to record emotions such as "anxiety" or "excitement."

[0285] Data transmission

[0286] The data collected by the device (two images, basic information about the pet, and the user's emotional data) is compiled into a data packet and sent as an HTTP POST request to the central server. This packet is in JSON format and contains the following example data: "Pet image," "Pet's age: 5 years," "Pet's weight: 10 kg," "Walking time: 30 minutes," and "User's emotion: nervous."

[0287] AI analysis

[0288] The data received by the server is first sent to an image analysis AI model to identify the type of pet. For example, it may be identified as a "Shiba Inu." A basic information analysis model then analyzes data such as age, weight, and walking time to generate health risk data. For example, it may predict a "high risk of obesity" or "medium risk of arthritis." Next, an emotion engine analyzes the user's emotional state and prepares to adjust the content of notification messages and advice.

[0289] Health Risk Assessment and Notification

[0290] The server combines the results of image analysis and basic information analysis to assess overall health risks. Notification messages are generated based on the assessment results, and the content is adjusted according to the user's emotional state. For example, a user who is feeling nervous might receive a message such as, "Obesity has been detected, but please rest assured that we have measures in place." This allows the user to feel reassured and take appropriate measures.

[0291] Food plan proposal

[0292] The server generates an optimal food plan based on the health risk assessment results, making specific suggestions such as "Try high-fiber foods." These suggestions are also adjusted based on the user's emotional state. For example, a proactive suggestion might be "Try high-fiber foods, and there are also joint support supplements."

[0293] Data visualization and hospital collaboration

[0294] The server generates graphs and charts based on past and recent data to visually display the pet's health condition. These visualized data are also displayed in a way that takes the user's emotional state into consideration. For example, if the user is feeling nervous, the system will use colors and a simple design that will give a sense of security. The system will also connect with hospitals as needed based on a health risk assessment to help provide appropriate medical services.

[0295] This system allows for more efficient health management of pets by responding to the user's emotional state, thereby reducing the burden on owners and supporting the longevity and health of pets.

[0296] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0297] Step 1:

[0298] The user uses a smartphone app to take photos of their pet's excrement and face, and uploads them to the app. The user then uses a form within the app to enter basic information about the pet (age, weight, walking time). At this time, the app uses the camera and voice input functions to obtain the user's emotional state using an emotion recognition engine. All entered data is temporarily stored in the smartphone's local storage.

[0299] Input: Pet excrement image, face photo, pet basic information, user emotion data

[0300] Data processing: taking image data, inputting text data, and recognizing emotional data

[0301] Output: Data stored in the smartphone's local storage

[0302] Step 2:

[0303] All data collected by the device (smartphone) (two images, basic information about the pet, and the user's emotional data) is compiled into a single data packet. The data packet is generated in JSON format and sent to the central server as an HTTP POST request.

[0304] Input: Data stored in local storage

[0305] Data processing: Generate data packets in JSON format

[0306] Output: HTTP POST request sent to the central server

[0307] Step 3:

[0308] The server receives the data packet sent from the device. The received data packet is first sent to an image analysis AI model, which analyzes the pet image and identifies the pet's type. This uses image recognition technology (e.g., deep learning). The pet's type (e.g., Shiba Inu) is output as the image analysis result.

[0309] Input: Data packets sent from the device

[0310] Data processing: Identifying pet species using image analysis AI models

[0311] Output: Pet type (e.g. Shiba Inu)

[0312] Step 4:

[0313] The server then uses a basic information analysis model to analyze data such as the pet's age, weight, and walking time to extract health risk data. The model evaluates risk by referencing statistical and medical data. For example, it can produce results such as "high risk of obesity" or "medium risk of arthritis."

[0314] Input: Basic information about your pet

[0315] Data processing: Calculation of health risks using basic information analysis models

[0316] Output: Health risk data (e.g., "High risk of obesity," "Medium risk of arthritis")

[0317] Step 5:

[0318] The server uses an emotion engine to analyze the user's emotional state. Emotional data (e.g., facial expressions and vocal tone) are analyzed to identify the user's emotional state (e.g., nervousness, excitement).

[0319] Input: User emotion data

[0320] Data processing: Identifying emotional states with an emotion engine

[0321] Output: User's emotional state (e.g., nervousness)

[0322] Step 6:

[0323] The server combines the results of image analysis and basic information analysis to assess overall health risks. A notification message is generated based on this assessment. The message content is adjusted according to the user's emotional state. For example, for a nervous user, a message such as "Obesity has been detected, but please rest assured that there are measures in place." is generated.

[0324] Input: Image analysis results, basic information analysis results, user emotional state

[0325] Data processing: Integrated assessment of health risks, generation of notification messages

[0326] Output: Adjusted notification message

[0327] Step 7:

[0328] The server then sends the generated notification message to the device (smartphone), which includes the pet's health risk assessment results and information corresponding to the user's emotional state.

[0329] Input: Adjusted notification message

[0330] Data processing: Sending messages from the server to the device

[0331] Output: Notification message displayed on the terminal

[0332] Step 8:

[0333] The server generates an optimal food plan based on the health risk assessment results. The content of the food plan is also adjusted according to the user's emotional state. For example, a user who is feeling nervous may receive specific suggestions such as "Try high-fiber foods."

[0334] Input: Health risk assessment results, user emotional state

[0335] Data processing: Food plan generation and adjustment

[0336] Output: Adjusted food plan

[0337] Step 9:

[0338] The server sends a notification message containing the food plan proposal to the terminal. This notification message provides the user with the most suitable food plan information and serves as a reference for implementation.

[0339] Input: Adjusted Food Plan

[0340] Data processing: Sending messages from the server to the device

[0341] Output: Food plan notification displayed on device

[0342] Step 10:

[0343] The server generates graphs and charts based on past and current data to visually display the pet's health status. These graphs and charts are designed with the user's emotional state in mind and are presented in an easy-to-read format.

[0344] Input: Historical and current data

[0345] Data processing: generating graphs and charts, adjusting design based on emotional state

[0346] Output: Visualized health care data

[0347] Step 11:

[0348] The server will then coordinate with hospitals as necessary based on the health risk assessment results. For example, if the user is assessed as having a high risk of arthritis, the server will notify the user of a list of nearby affiliated hospitals. It will also send data to specific hospitals so that the user can receive appropriate medical services.

[0349] Input: Health risk assessment results

[0350] Data processing: Generating hospital linkage information and sending necessary data

[0351] Output: Linkage information and data transmission to hospital

[0352] (Application example 2)

[0353] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0354] Conventional pet health management systems provide advice and food plan recommendations based on the pet's health condition in a one-way manner, without taking into account the owner's emotional state. As a result, even if the information the owner receives is appropriate, it can cause stress and anxiety in the owner, potentially reducing their motivation to maintain their pet's health. Furthermore, it is difficult to provide real-time advice tailored to each individual owner and pet in a physical store, making it difficult to provide a personalized service.

[0355] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for receiving a pet image, means for analyzing the received image to identify the pet's type, means for extracting health risk data based on the analyzed pet's type, means for inputting basic information about the pet, means for generating excretion status and health risk data based on the basic information and the health risk data, means for generating and transmitting a notification message based on the generated data, means for acquiring the owner's emotional state, and means for adjusting the content of the notification message based on the owner's emotional state. This enables personalized notification messages and food plans to be proposed taking the owner's emotional state into consideration. Furthermore, by using the health management system in physical stores, appropriate and flexible services can be provided to owners and pets on-site.

[0356] The "means for receiving pet images" refers to a device or software component for acquiring photographs or video data of a pet and inputting it into the system.

[0357] The "means for identifying the type of pet" is an algorithm or system that analyzes the received image data and identifies the type of pet (for example, dog, cat, breed, etc.).

[0358] A "means for extracting health risk data" is a process or system that identifies potential health risks for pets based on the type of pet and basic information about the pet, and extracts that data.

[0359] "Means for inputting basic information about pets" refers to an interface or component that allows owners to input information about their pets (age, weight, walking time, etc.).

[0360] "Means for generating data on excretion status and health risks" refers to a system or process that creates data on pet excretion status and health risks based on basic information about the pet and analysis results.

[0361] The "means for generating and transmitting notification messages" is a mechanism for creating and transmitting messages to notify owners of advice and information based on the generated data.

[0362] "Means for acquiring the owner's emotional state" refers to devices or software that analyze and determine the owner's emotional state from their facial expressions and input information.

[0363] The "means for adjusting the content of the notification message based on the emotional state of the owner" refers to an algorithm or system for appropriately adjusting the expression and content of the notification message, taking into account the emotional state of the owner.

[0364] The "means for generating and proposing a food plan" is a system for creating an appropriate meal plan based on the results of a health risk assessment and proposing it to the owner.

[0365] The "means for adjusting the contents of the food plan" refers to a system that allows the specific contents of the proposed meal plan to be flexibly changed based on the owner's emotional state and the pet's health condition.

[0366] "Means for visualization using graphs and charts" refers to a system that generates graphs and charts to visually display pet health data in an easy-to-understand manner.

[0367] The "means for adjusting the display format" is an algorithm or system that changes the display format of graphs and charts based on the owner's emotional state to make them easier to understand.

[0368] The system for implementing this invention manages the health status of pets and proposes notification messages and food plans that take the user's emotional state into account. The system consists of a smartphone app, a central server, an analytical AI model, and an emotion engine.

[0369] Hardware and software used

[0370] Hardware: Smartphones, tablets, digital signage

[0371] Software: ANDROID® / iOS application, central server, image analysis AI model (e.g., TensorFlow-based model), emotion recognition library (e.g., Microsoft® Azure® Face API, Google® Cloud Vision API)

[0372] Specific processing of the system

[0373] 1. Data Entry

[0374] The user uses a smartphone app to take pictures of their pet's feces and the pet itself and upload them to the app. In addition, the user enters basic information about the pet (age, weight, walking time, etc.). The app also activates a facial recognition camera to capture the user's emotional state and records the user's current emotional state.

[0375] 2. Data Transmission

[0376] The smartphone assembles the collected data (two images, basic information, and emotion data) into a single packet and sends it to a central server as an HTTP POST request.

[0377] 3. AI analysis

[0378] The central server sends the received data to an AI model for analysis. First, the image analysis AI analyzes the pet's image to identify its species. Then, the basic information analysis model analyzes data such as age, weight, and walking time to generate health risk data. Furthermore, the emotion engine analyzes the user's emotional state and prepares to provide advice based on that emotional state.

[0379] 4. Health Risk Assessment and Notification

[0380] The central server integrates the image analysis results with the basic information analysis results to assess the overall health risk, and generates notification messages based on the assessed health risk data, adjusting the content according to the user's emotional state.

[0381] 5. Food plan suggestions

[0382] The central server generates an optimal diet plan based on the health risk assessment results and proposes it to the user, and the proposal is also adjusted taking into account the user's emotional state.

[0383] 6. Notifications and Reporting

[0384] The central server generates a report containing notification messages and recommended food plans and sends it to the smartphone, which reflects the user's emotional state and is presented in an easy-to-understand format.

[0385] 7. Data Visualization

[0386] The central server generates graphs and charts based on past and current data to visually display the pet's health status, and these visualizations are also configured taking into account the user's emotional state.

[0387] 8. In-store use

[0388] In-store use tablet devices and digital signage to provide real-time advice tailored to pet owners and their pets, and the system will be used as a support tool to help store staff explain things to pet owners more effectively.

[0389] Examples of concrete examples and prompts

[0390] For example, if the owner is feeling stressed, the notification message will be tailored to reassure the owner.

[0391] Example prompt for generative AI model:

[0392] Use the following data to analyze your pet's health and your emotional state and suggest an appropriate food plan.

[0393] Pet image (jpg)

[0394] Pet's age: 5 years

[0395] Pet weight: 20kg

[0396] Walking time: 30 minutes

[0397] Owner's emotion image (jpg)

[0398] A word of caution: If the owner is stressed, offer reassuring suggestions.

[0399] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0400] Step 1:

[0401] The user uses a smartphone app to take pictures of their pet's waste and the pet itself, and uploads them to the app. The input data here is the pet's image, basic information (age, weight, walking time, etc.), and a face image of the owner. The app then assembles this data into a single packet.

[0402] Step 2:

[0403] The device sends the combined data packet (two images, basic information, and emotion data) to the central server as an HTTP POST request. This transmission process takes place over the Internet, and the data arrives at the server.

[0404] Step 3:

[0405] The server sends the received data to an AI model for analysis. First, the image analysis AI analyzes the input data (images of pets) and identifies the pet's type. Specifically, the input image is passed to a TensorFlow-based image analysis model, which extracts the pet's type data as output.

[0406] Step 4:

[0407] The server uses a basic information analysis model to analyze basic information entered by the user (such as age, weight, and walking time). It then generates health risk data based on the input information. This analysis produces output data such as obesity risk and arthritis risk.

[0408] Step 5:

[0409] The server uses an emotion engine to analyze the user's emotion data. Specifically, it uses emotion recognition libraries such as Microsoft Azure Face API or Google Cloud Vision API to identify the user's emotional state from the user's facial image. The output of this step is the user's emotional state data.

[0410] Step 6:

[0411] The server integrates the results of image analysis, basic information analysis, and emotion analysis to assess the overall health risk. Based on the assessed health risk data, it generates a notification message. The content of this notification message is tailored according to the user's emotional state. The output is a personalized notification message.

[0412] Step 7:

[0413] The server generates and suggests an optimal food plan based on the health risk assessment results. The suggested food plan is also tailored to take into account the user's emotional state, for example by including reassuring messages. The output of this step is the tailored food plan.

[0414] Step 8:

[0415] The server generates a report containing a notification message and a food plan and sends it to the device. The report is then provided to the user, and its content reflects the user's emotional state. The output is a detailed report displayed on the smartphone.

[0416] Step 9:

[0417] The server generates graphs and charts based on past and current data to visually display the pet's health status. These graphs and charts are constructed taking into account the user's emotional state and are presented in an easy-to-understand format. The output is data in a visually easy-to-understand format.

[0418] Step 10:

[0419] In the physical store, tablet devices and digital signage display appropriate advice based on the data sent from the server. Store staff refer to this data and provide detailed explanations to pet owners. This enables flexible and effective on-site service provision. The output is customized advice provided in real time.

[0420] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0421] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0422] In the above embodiment, an example in which the specific process is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0423] [Second embodiment]

[0424] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0425] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0426] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0427] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0428] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0429] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0430] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0431] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0432] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0433] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0434] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0435] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal."

[0436] The system of the present invention is designed to effectively manage the health of pets and is configured as follows. The main components are a smartphone app used by the user, a central server, and an analytical AI model. The specific functions and operations of the system are described in detail below.

[0437] Data Entry

[0438] Users use a smartphone app to take photos of their pet's excrement and the pet itself, and then upload them to the app. For example, a user can take a photo of their pet's excrement after a morning walk, then take a photo of their pet's face and upload it to the app. At this time, the user also enters basic information about the pet (age, weight, walking time, etc.). This allows users to easily record the health status of their pet.

[0439] Data transmission

[0440] The device collects the data entered by the user into a single packet and sends it to the central server. Specifically, the device generates a data packet that combines two photos and text data (age, weight, and walking time) and sends it to the server as an HTTP POST request.

[0441] AI analysis

[0442] The server sends the received data to an AI model for analysis. First, the image analysis AI analyzes the received image data to identify the type of pet. In this case, the image analysis AI recognizes specific breeds such as "Shiba Inu." Next, the basic information analysis model analyzes the input data, such as age, weight, and walking time, and generates health risk data. This results in an assessment such as "high risk of obesity" or "medium risk of arthritis."

[0443] Health Risk Assessment

[0444] The server integrates these analysis results to assess overall health risk. Specifically, it integrates information on "mild obesity" and "arthritis risk" to perform a comprehensive risk assessment. It then generates a notification message based on the health risk and sends it to the user. For example, a notification might say, "Obesity has been detected. We recommend high-fiber foods. We also suggest supplements that are good for joint health."

[0445] Food plan proposal

[0446] The server generates an optimal food plan based on the health risk assessment results for the user's pet. For example, it lists and suggests "high-fiber foods" and "joint support supplements." This allows users to accurately manage their pet's nutrition.

[0447] Notifications and Reporting

[0448] The server then sends notification messages and reports to the user. The notification messages include information about the analysis results and recommended feeding plans. Additionally, the server generates graphs and charts based on past and current data, allowing the user to visually understand their pet's health status. For example, graphs can be displayed showing weight changes and health risk trends.

[0449] Hospital collaboration

[0450] The server will then connect with hospitals as needed based on the health risk assessment results. For example, if the user is assessed as having a high risk of arthritis, the server will notify the user of a list of nearby affiliated hospitals. It will also send data to hospitals as needed to ensure the user receives appropriate medical services.

[0451] As described above, the system of the present invention aims to comprehensively manage the health status of pets and support early detection and treatment, thereby reducing the burden on owners and contributing to the health and longevity of pets.

[0452] The processing flow will be explained below.

[0453] Step 1:

[0454] The user launches the smartphone app. Using the app's built-in camera function, the user takes a photo of their pet's excrement, then a photo of their pet's face. Each photo is then uploaded to the app. The user also enters basic information about their pet (age, weight, walking time, etc.).

[0455] For example, a user taps the app's "upload image" button, takes a photo of the pet's excrement, then takes a photo of the pet's face, and uploads both to the app.

[0456] Step 2:

[0457] The device collects the data entered by the user (two images and basic information) into a single packet. After generating the data packet, the device sends an HTTP POST request to the central server.

[0458] As a specific example, a terminal generates a JSON-formatted data packet that combines image data and text data, and executes a request called "POST / analyze HTTP / 1.1."

[0459] Step 3:

[0460] The server processes the data received from the device and sends it to an AI model for analysis. First, the server uses image analysis AI to analyze the received pet image and identify the pet's type. In this process, the image analysis AI recognizes specific dog or cat breeds, such as "Shiba Inu." Next, the server uses a basic information analysis model to analyze the input data, such as age, weight, and walking time, and generates health risk data.

[0461] As a specific example, an image analysis AI may determine that "this image is of a Shiba Inu," and a basic information analysis model may assess the animal as "high risk of obesity" and "medium risk of arthritis."

[0462] Step 4:

[0463] The server integrates the image analysis results with the basic information analysis results to assess the overall health risk, and then generates a notification message based on the assessment results and sends it to the user.

[0464] As a specific example, the server integrates data such as "mild obesity" and "risk of arthritis" and generates a notification message saying, "Obesity has been detected. We recommend high-fiber foods. We also suggest supplements that are good for joint health."

[0465] Step 5:

[0466] Based on the health risk assessment results, the server generates an optimal food plan for the user's pet, which may include high-fiber foods and joint support supplements.

[0467] As a specific example, the server lists specific suggestions such as "recommended food: high fiber food" and "recommended supplement: joint support supplement."

[0468] Step 6:

[0469] The server generates a report containing notification messages and a recommended food plan and sends it to the device, where the user can check the received report in the app.

[0470] As a specific example, the server generates a detailed food plan report and sends it to the device along with the message, "Please check the latest analysis results. Obesity has been detected. Try the food plan below."

[0471] Step 7:

[0472] The server generates graphs and charts based on past and current data, visually displaying the pet's health status, which the user can view within the app.

[0473] As a specific example, graphs showing changes in weight and health risks are generated and displayed within the app.

[0474] Step 8:

[0475] If necessary, the server will connect with hospitals based on the health risk assessment results and notify the user of a list of nearby affiliated hospitals, enabling them to receive appropriate medical services.

[0476] As a specific example, a notification message saying "You are at high risk of developing arthritis. Please consult the affiliated hospital below" is sent along with the contact information of the affiliated hospital.

[0477] The above is a specific processing flow of the pet health management system, which allows users to effectively manage the health of their pets.

[0478] Example 1

[0479] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0480] Today, many pets suffer from various health problems due to inadequate health management by their owners. For example, it is difficult to determine the appropriate amount of food and exercise, which can result in problems such as obesity and arthritis. However, there is no easy-to-use system for monitoring pet health on a daily basis and taking appropriate measures. For this reason, there is a need for the development of a system that assesses health risks based on pet photos and basic information and proposes an appropriate food plan.

[0481] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0482] In this invention, the server includes a means for receiving images of the pet from the terminal used by the user, a means for collecting the received images and basic information of the pet into a single data packet and transmitting it, and a means for providing the data packet to an AI model that analyzes the data packet in the central server. This makes it possible to evaluate health risks based on the received image analysis results and the basic information of the pet, and to generate notification messages, propose optimal food plans, and even generate graphs and charts based on past data.

[0483] "User" refers to a person who uses the system.

[0484] "Terminal" refers to an electronic device used by a user, such as a personal digital assistant or computer.

[0485] "Central Server" refers to a central computer system that receives, analyzes, and stores data.

[0486] "Image analysis AI" refers to an artificial intelligence model that analyzes received image data and extracts specific information.

[0487] "Basic information" refers to basic data about your pet, such as age, weight, and walking time.

[0488] "Health risk data" refers to assessment data regarding the health status of pets obtained from the analysis results.

[0489] "Data packet" refers to a unit of information that contains image data and basic information packaged for transmission.

[0490] "Notification message" refers to an information message sent to the user based on the analysis results.

[0491] "Food Plan" refers to a suggested dietary plan for your pet based on health risk data.

[0492] "Graphs and charts" refer to diagrams that visually display changes in a pet's physical condition or symptoms.

[0493] MODE FOR CARRYING OUT THE INVENTION

[0494] The system of the present invention is designed to effectively manage the health of pets, and is composed of a terminal used by the user (e.g., a smartphone), a central server, and an analytical AI model.

[0495] Data entry and submission

[0496] Users can use a smartphone app to take photos of their pet's feces and face and upload them within the app. For example, a user can take photos of their pet's feces and face after a morning walk and upload the photos. At this time, users also enter basic information about their pet (age, weight, walking time, etc.) into the app. This basic information can be easily added through a text input form.

[0497] The device (smartphone) combines the data entered by the user (two photos and text data) into a single data packet and sends it to the central server as an HTTP POST request.

[0498] Data analysis and health risk assessment

[0499] The server sends the received data packets to an AI model for analysis. First, an image analysis AI (for example, a TensorFlow model) analyzes the received image data and identifies the type of pet. For example, it might identify the image as a "Shiba Inu." Next, a basic information analysis model analyzes the input data, such as age, weight, and walking time, to generate health risk data. This results in an assessment such as "high risk of obesity" or "medium risk of arthritis."

[0500] The server integrates the analysis results and evaluates the overall health risk. Specifically, it integrates "mild obesity" and "arthritis risk" to perform a comprehensive risk assessment. It then generates a notification message based on the assessment results and sends it to the user. For example, a notification may be generated that reads, "Obesity has been detected. We recommend high-fiber foods. We also suggest supplements that are good for joint health."

[0501] Food plan proposal

[0502] The server generates an optimal food plan based on the health risk assessment results. For example, it retrieves information on "high-fiber foods" and "joint support supplements" from the database, lists them, and suggests them to the user. This suggestion is sent to the user's smartphone as a push notification.

[0503] Notifications and Reporting

[0504] The server generates graphs and charts based on past and latest data along with notification messages and sends them to the user, allowing the user to visually understand the health status of their pet. For example, graphs showing changes in weight and health risks are displayed.

[0505] Hospital collaboration

[0506] The server will then connect with hospitals as needed based on the health risk assessment results. For example, if the user is assessed as having a high risk of arthritis, the server will notify the user of a list of nearby affiliated hospitals. Based on this information, the user can receive appropriate medical services. If necessary, the server will securely transmit data to the hospital.

[0507] Examples and prompts

[0508] Examples:

[0509] After a morning walk, users take photos of their pet's feces and face, and upload them to a smartphone app. They then enter information such as age (3 years), weight (10 kg), and walk time (30 minutes).

[0510] You will receive a notification message saying, "Obesity detected. We recommend high-fiber foods. We also suggest supplements for joint health."

[0511] Check for recommended "high fiber foods" and "joint support supplements."

[0512] Example prompt sentence:

[0513] "Users take photos of their pet's feces and face after their morning walk and upload them through a smartphone app. They also enter their age, weight, and walking time."

[0514] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0515] Step 1:

[0516] The user uses a smartphone app to take photos of their pet's excrement and face, and uploads them within the app. The input is a photo of the pet's excrement, a photo of the face, and basic information (age, weight, walking time). The output is a set of the uploaded photo and the input text data. Specifically, the user takes a photo using the app's camera function, and then enters information such as "3 years old," "10 kg," and "30 minutes" into the input form.

[0517] Step 2:

[0518] The device combines the data entered by the user (two photos and text data) into a single data packet and sends it to the central server as an HTTP POST request. The input is the data uploaded by the user from the app, and the output is the data packet sent as an HTTP POST request. Specifically, the smartphone app generates the data packet in the background and sends an HTTP request to the specified server URL.

[0519] Step 3:

[0520] The server provides the received data packets to the AI ​​model for analysis. The input is the data packet sent from the device, and the output is the data passed to the AI ​​model for analysis. Specifically, the server converts the received data into an analytical format and passes it to the image analysis AI and basic information analysis model.

[0521] Step 4:

[0522] The server uses image analysis AI to analyze the received image data and identify the type of pet. The input is the image data in the data packet, and the output is the identification result of the pet type. For example, the image is analyzed and identified as a "Shiba Inu." The specific operation is to execute image analysis AI (for example, a TensorFlow model).

[0523] Step 5:

[0524] The server uses a basic information analysis model to analyze the input text data and generate health risk data. The input is the age, weight, and walking time data in the data packet, and the output is health risk data. Specifically, the basic information analysis model generates an assessment such as "high risk of obesity" or "medium risk of arthritis."

[0525] Step 6:

[0526] The server integrates the analysis results and performs an overall health risk assessment. The input is the image analysis results and basic information analysis results, and the output is the integrated health risk assessment results. Specifically, a Python script integrates "mild obesity" and "arthritis risk."

[0527] Step 7:

[0528] The server generates a notification message based on the assessment results and sends it to the user. The input is the health risk assessment result, and the output is the generated notification message. Specifically, the Python script generates a message saying, "Obesity has been detected. High-fiber foods are recommended. Supplements that are good for joint health are also suggested." and sends a push notification.

[0529] Step 8:

[0530] The server generates and proposes an optimal food plan based on the health risk assessment results. The input is the health risk assessment results, and the output is a recommended food plan. Specifically, it retrieves information on "high fiber foods" and "joint support supplements" from the database and creates a list.

[0531] Step 9:

[0532] The server generates graphs and charts based on past and latest data along with notification messages and sends them to the user. The input is past and latest data, and the output is the generated graphs and charts. Specifically, the graphs are generated using libraries such as Matplotlib and Seaborn and displayed in the app.

[0533] Step 10:

[0534] The server will communicate with hospitals as needed based on the health risk assessment results. The input is the health risk assessment results, and the output is a list of affiliated hospitals and the transmission of necessary medical data. Specifically, if the user is assessed as having a "high risk of arthritis," the server retrieves a list of nearby affiliated hospitals from the database and notifies the user. It also executes an API to securely send data to hospitals as needed.

[0535] (Application example 1)

[0536] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0537] Existing methods for managing pet health make it difficult for owners to accurately record their pet's waste and physical condition and take appropriate health measures. It is also time-consuming to select food and suggest supplements based on the pet's health condition. Furthermore, there is a lack of integration with food delivery services that address pet health risks. Therefore, there is a need for a system that provides comprehensive and efficient pet health management.

[0538] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0539] In this invention, the server includes means for receiving images of the pet, means for analyzing the received images to identify the type of pet, means for extracting health risk data based on the analyzed type of pet, means for inputting basic information about the pet, means for generating excretion status and health risk data based on the basic information and the health risk data, means for generating and sending a notification message based on the generated data, and means for generating a food plan based on the health risks and linking with a food delivery service, thereby enabling comprehensive and efficient management of the pet's health status and the recommendation and delivery of appropriate food and supplements.

[0540] The "means for receiving pet images" is a device or system that allows a user to send images of a pet taken using a smartphone or camera to a server.

[0541] "Means for analyzing the received image and identifying the type of pet" refers to a device or system that includes an algorithm or software for identifying the type or breed of pet by analyzing the received image data.

[0542] The "means for extracting health risk data" is a device or system for extracting health risk data related to pets based on the type and basic information of the pets.

[0543] The "means for inputting basic information about a pet" refers to a device or system that allows a user to input basic information about a pet, such as age, weight, and walking time.

[0544] The "means for generating data on excretion status and health risks" refers to a device or system for generating information on a pet's excretion status and health risks based on basic information about the pet and analyzed health risk data.

[0545] "Means for generating and transmitting notification messages" refers to a device or system for creating and transmitting notification messages to users on smartphones or other devices based on the generated health risk data.

[0546] "Means for generating food plans and linking with food delivery services" refers to a device or system for creating an appropriate food plan based on the results of a pet's health risk assessment and providing the selected food and supplements in collaboration with a food delivery service.

[0547] "Means for recording changes in a pet's physical condition and symptoms and visualizing them in graphs and charts" refers to a device or system that records changes in a pet's physical condition and symptoms as data, converts that data into graphs and charts, and visually displays them to the user.

[0548] This invention is a system for effectively managing the health of pets, and is composed of the following main components: a smartphone app used by the user, a central server, and an analytical AI model.

[0549] Data Entry

[0550] Users use a smartphone app to take pictures of their pet's feces and the pet itself, and upload them to the app. At the same time, users can also enter basic information about their pet (age, weight, walking time, etc.).

[0551] Data transmission

[0552] The device collects the data entered by the user into a single packet and sends it to the central server. Specifically, the device generates a data packet that combines two photos and text data (age, weight, and walking time) and sends it to the server as an HTTP POST request.

[0553] AI analysis

[0554] The server sends the received data to an AI model for analysis. The image analysis AI analyzes the received image data and identifies the type of pet. The basic information analysis model analyzes the input data, such as age, weight, and walking time, and generates health risk data. For example, it can provide assessment results such as "high risk of obesity" or "medium risk of arthritis."

[0555] Health Risk Assessment

[0556] The server integrates these analysis results and evaluates the overall health risk. Based on the evaluation, it generates a notification message according to the health risk and sends it to the user.

[0557] Food plan proposal

[0558] The server generates an optimal food plan based on the health risk assessment results for the user's pet. For example, the server lists and recommends "high-fiber foods" and "joint support supplements" to the user. The system works in conjunction with a food delivery service to deliver the selected foods and supplements to the user.

[0559] Notifications and Reporting

[0560] The server sends notification messages and reports to the user, including analysis results and recommended feeding plans. The server generates graphs and charts based on past and current data, allowing the user to visually understand the health status of their pet.

[0561] Hardware and Software Used

[0562] Smartphone (for users to take pictures and enter data)

[0563] Central server (for data analysis and results transmission)

[0564] AI model (using Python libraries such as PIL and requests for image analysis and basic information analysis)

[0565] FastAPI (for server-side APIs)

[0566] Processing examples and prompt statements

[0567] For example, a user can take photos of their dog's excrement and face with their smartphone and upload them to the app. This data is then analyzed on a central server and classified as "Shiba Inu," "high risk of obesity," or "medium risk of arthritis." The app then recommends "high-fiber food" and "joint support supplements" to the user, who can then purchase them and use the food delivery service.

[0568] Example prompt sentence:

[0569] Take photos of your dog's feces and face, and enter your pet's age, weight, and walking time. Based on that data, we will provide you with an appropriate health risk assessment and food plan suggestions.

[0570] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0571] Step 1:

[0572] Users use a smartphone app to take photos of their pet's feces and face, upload them to the app, and then enter basic information about their pet (age, weight, walking time).

[0573] Input: Photo of pet's waste, face photo, age, weight, walking time

[0574] Output: Image data, basic information data

[0575] What happens: A user opens the app, takes a photo using the camera, fills in basic information in a form, and presses the submit button.

[0576] Step 2:

[0577] The device collects the data received from the user into a single data packet and sends it to the central server using an HTTP POST request.

[0578] Input: Image data, basic information data

[0579] Output: HTTP POST request to the server

[0580] Specific operation: The smartphone app packs two photos and text data into a packet and sends it to the server's API endpoint.

[0581] Step 3:

[0582] The server sends the received data to an AI model for analysis. The image analysis AI analyzes the received image data and identifies the type of pet.

[0583] Input: Data packet (image data, basic information data)

[0584] Output: Pet type (e.g. Shiba Inu)

[0585] Specific operation: After receiving the data, the server passes the image data to the AI ​​model, which performs image analysis and obtains the pet's type as a result.

[0586] Step 4:

[0587] The server uses a basic information analysis model to analyze the entered age, weight, and walking time, and generates health risk data.

[0588] Input: Age, weight, walking time

[0589] Output: Health risk data (e.g., high risk of obesity, medium risk of arthritis)

[0590] Specific operation: The server passes basic information to the analysis model, performs data calculations, and generates health risk data.

[0591] Step 5:

[0592] The server aggregates the analysis results, assesses the overall health risk, and generates notification messages based on the assessment.

[0593] Input: Pet type, health risk data

[0594] Output: Health risk assessment results, notification message

[0595] Specific operation: The server integrates pet type and health risk data, uses AI models to assess the overall health risk, and generates a notification message.

[0596] Step 6:

[0597] The server generates an optimal food plan based on the health risk assessment results and proposes it to the user. It also works with food delivery services to deliver food to the user.

[0598] Input: Health risk assessment results

[0599] Output: Food plan, food delivery request

[0600] What it does: The server uses the AI ​​model to generate an appropriate food plan and sends a delivery request using the food delivery service's API.

[0601] Step 7:

[0602] The server sends notification messages and reports to the user. The server displays a message to the user containing information about the analysis results and recommended food plan.

[0603] Input: Health risk assessment results, food plan

[0604] Output: Notification messages, reports

[0605] Specific operation: The server generates notification messages and reports based on the analysis results and food plans, and sends them to a smartphone app, where users can view them.

[0606] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0607] The system of the present invention is for managing the health of pets and incorporates an emotion engine that provides notification messages and suggests food plans that take into account the user's emotional state. The system consists of a smartphone app, a central server, an analytical AI model, and an emotion engine.

[0608] Data Entry

[0609] A user uses a smartphone app to take photos of their pet's excrement and the pet itself, and uploads them to the app. At this time, the user enters basic information about the pet (age, weight, walking time, etc.). For example, a user might take a photo of their pet's excrement after a morning walk, then take a photo of the pet's face and upload it to the app. In addition, an emotion recognition function is activated within the app to capture the user's emotional state and record the user's current emotional state.

[0610] Data transmission

[0611] The device collects the data input by the user (two images, basic information, and emotion data) into a single packet and sends it to the central server. Specifically, the device generates a data packet that combines image data and text data (age, weight, walking time, and the user's emotional state) and sends it to the server as an HTTP POST request.

[0612] AI analysis

[0613] The server sends the received data to an AI model for analysis. First, the image analysis AI analyzes the pet's image and identifies the pet's type (e.g., "Shiba Inu"). Next, the basic information analysis model analyzes data such as age, weight, and walking time to generate health risk data (e.g., "high risk of obesity" or "medium risk of arthritis"). Furthermore, the emotion engine analyzes the user's emotional state and prepares to provide advice based on that emotional state.

[0614] Health Risk Assessment

[0615] The server combines the results of image analysis and basic information analysis to assess overall health risk. It also generates notification messages based on the assessed health risk data and adjusts the content according to the user's emotional state. For example, if the user appears anxious, it will send a message that reassures them, such as, "Obesity has been detected, but please rest assured that there are measures in place. We recommend high-fiber foods."

[0616] Food plan proposal

[0617] The server generates an optimal food plan based on the health risk assessment results and proposes it to the user. The content of the food plan proposal is also adjusted taking into account the user's emotional state. For example, if the user is in a state of high interest, the server will proactively suggest, "Why not try high-fiber foods? We also have joint support supplements."

[0618] Notifications and Reporting

[0619] The server generates a report containing a notification message and a recommended food plan and sends it to the device. The report reflects the user's emotional state and is presented in a format that is easy for the user to understand. For example, a notification message may be generated that reads, "Please check the latest analysis results. We have prepared a food plan that you can follow with confidence."

[0620] Graph and chart generation

[0621] The server generates graphs and charts based on past and recent data to visually display the pet's health status. These visualized data are also configured taking into account the user's emotional state. For example, if the user is feeling nervous, the data will be displayed in a simple design with easy-to-read colors that give a sense of security.

[0622] Hospital collaboration

[0623] The server will then connect with hospitals as needed based on the health risk assessment results. For example, if the user is assessed as having a high risk of arthritis, the server will send a message based on the user's emotional state, providing a list of nearby affiliated hospitals. If necessary, the server will also send data to hospitals to ensure the user receives appropriate medical services.

[0624] As described above, the system of the present invention comprehensively manages the health condition of pets and takes into account the emotional state of the user to provide more effective support, thereby reducing the burden on owners and contributing to the health and longevity of pets.

[0625] The processing flow will be explained below.

[0626] Step 1:

[0627] The user launches the smartphone app. They take photos of their pet's excrement and face and upload them within the app. They also enter basic information about their pet (age, weight, walking time, etc.). Taking a photo of the user's facial expression triggers the emotion engine to recognize the user's emotions.

[0628] For example, after a morning walk, a user takes a photo of their pet's excrement, then takes a photo of their pet's face, and uploads both to the app. The app then captures the user's current facial expression and obtains emotional data.

[0629] Step 2:

[0630] The device collects the data input by the user (two images, basic information, and emotion data) into a single packet and sends it to the central server. The data packet contains image data, text data (age, weight, walking time), and emotion data obtained by the emotion engine.

[0631] As a specific example, the device generates a JSON-formatted data packet that includes an image, basic information, and emotion data, and executes "POST / analyze HTTP / 1.1."

[0632] Step 3:

[0633] The server starts the process of sending the received data to an AI model for analysis. First, the image analysis AI analyzes the pet's image and identifies the pet's species. Next, the basic information analysis model analyzes the input data and generates health risk data. Finally, the emotion engine analyzes the user's emotion data.

[0634] For example, the image analysis AI identifies the dog as a "Shiba Inu," and the basic information analysis model evaluates it as "high risk of obesity" and "medium risk of arthritis." The emotion engine recognizes the user's emotion as "anxiety."

[0635] Step 4:

[0636] The server integrates the results of image analysis, basic information analysis, and the emotion engine to assess the overall health risk, and generates a notification message based on the assessment results, tailoring the message content to the user's emotional state.

[0637] As a specific example, the server combines "mild obesity" and "arthritis risk" and generates a notification message saying, "Obesity has been detected, but there are measures you can take. We recommend high-fiber foods."

[0638] Step 5:

[0639] The server generates an optimal food plan based on the health risk assessment results and proposes it to the user. The generated food plan is also adjusted according to the user's emotional state.

[0640] As a concrete example, if the emotion engine recognizes that the user's emotion is "curious," it will make a proactive suggestion such as, "Why not try some high-fiber foods? We also recommend some joint support supplements."

[0641] Step 6:

[0642] The server generates a report containing notification messages and recommended food plans and sends it to the device, where the user can check the report and understand the health status of their pet.

[0643] As a specific example, the server sends a message saying, "Please check the latest analysis results. We have prepared a food plan that you can follow with confidence," and attaches a detailed food plan report.

[0644] Step 7:

[0645] The server generates graphs and charts based on past and current data to visually display the pet's health status, and these graphs and charts are also displayed in a way that reflects the user's emotional state.

[0646] As a specific example, a graph showing changes in weight and health risks is generated, and if the user is feeling "tense," it is displayed in a color that is easy to see and gives a sense of security.

[0647] Step 8:

[0648] If necessary, the server will connect with hospitals based on the health risk assessment results. The emotion engine will notify the user of a list of nearby affiliated hospitals via a message based on the user's emotional state. It will also send relevant data to the hospitals as needed.

[0649] As a specific example, a notification message stating, "You are at high risk of arthritis. Rest assured, you can consult with the affiliated hospitals listed below," along with contact information for the affiliated hospitals, may be sent.

[0650] The above is a specific processing flow for incorporating an emotion engine into a pet health management system, and this system enables better health management for both users and pets.

[0651] Example 2

[0652] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0653] Conventional pet health management systems support image analysis and basic information input as a means of monitoring pet health, but do not take into account the user's psychological state. This can cause mental stress when users receive notifications or suggestions from the system. Furthermore, health risk assessments and food plan suggestions are uniform, lacking flexibility to respond to the user's emotional state. There is a need to improve this and provide more user-friendly support.

[0654] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0655] In this invention, the server includes means for receiving an image of the pet, means for analyzing the received image and identifying the type of pet, means for extracting health risk data based on the analyzed type of pet, means for inputting basic information about the pet, means for generating excretion status and health risk data based on the basic information and the health risk data, means for generating and sending a notification message based on the generated data, means for acquiring and analyzing the user's emotional state, means for adjusting the content of the notification message based on the emotional state, means for generating and proposing an optimal food plan based on the health risk assessment results, means for adjusting the content of the proposed food plan based on the user's emotional state, means for recording changes in the pet's physical condition and symptoms and visualizing them in graphs or charts, and means for configuring the visualized data according to the user's emotional state.

[0656] This makes it possible to provide appropriate support that is in line with the user's emotional state. Specifically, it is possible to provide notification messages and food plan suggestions that take the user's emotional state into account, as well as visualize the pet's health status, thereby reducing the burden on the user and achieving better health management for their pet.

[0657] The "means for receiving pet images" is a method for importing pet image data taken using a smartphone or camera into an application or server.

[0658] "Means for analyzing images and identifying the type of pet" refers to a method of identifying the type of pet (such as dog breed or cat breed) based on the received image using image recognition technology such as deep learning.

[0659] The "means for extracting health risk data" refers to a method for deriving the relevant health risks based on the identified pet species, with reference to statistical data and medical data.

[0660] "Means for inputting basic information" refers to a method by which a user inputs basic information such as the pet's age, weight, and walking time via a smartphone, computer, etc.

[0661] The "means for generating excretion status and health risk data" is a method for calculating a pet's excretion status and overall health risk based on basic information input by the user and analyzed health risk data.

[0662] The "means for generating and transmitting a notification message" is a method for generating an appropriate notification message for the user based on the generated health risk data and excretion status, and transmitting the message to a designated terminal.

[0663] "Means for acquiring and analyzing the user's emotional state" refers to a method of detecting the user's current emotional state using a camera or voice analysis function and analyzing it as data.

[0664] The "means for adjusting the content of the notification message based on the emotional state" is a method for optimizing the content of the notification message in accordance with various emotions such as tension and anxiety based on the acquired emotional state of the user.

[0665] "Means for generating and proposing an optimal food plan" is a method for calculating an optimal food plan for the relevant pet based on the health risk assessment results and proposing that plan to the user.

[0666] The "means for adjusting the proposed content based on the user's emotional state" is a method for adjusting the content of the generated food plan in a way that is more effectively accepted by the user in accordance with the user's emotional state.

[0667] "Means for recording changes in physical condition and symptoms and visualizing them in graphs and charts" refers to a method for recording changes in a pet's physical condition and symptoms as time-series data and visually displaying them as graphs and charts.

[0668] "Means for configuring visualized data according to the user's emotional state" refers to a method for adjusting the design and color scheme of generated graphs and charts according to the user's emotional state, and providing them in a format that is easy to read and gives a sense of security.

[0669] The system of the present invention is a system that comprehensively manages the health condition of a pet and proposes notification messages and food plans based on the emotional state of the user. Hereinafter, embodiments of the present invention will be described in detail.

[0670] System Configuration

[0671] The system consists of a smartphone app, a central server, an image analysis AI model, an emotion engine, and a data transmission and reception infrastructure. Users mainly use their smartphones to input their pet's health information, and the central server is responsible for data analysis.

[0672] Data Entry

[0673] Users use a smartphone app to take photos of their pet's excrement and face and upload them to the app. At the same time, they also enter basic information about their pet (such as age, weight, and walking time). In particular, an emotion recognition function is activated within the app and records the user's current emotional state using a camera or voice input. For example, a user can take a photo of their pet's excrement after a morning walk, then take a photo of their pet's face and upload it to the app. The emotion recognition function analyzes the user's facial scan and voice tone to record emotions such as "anxiety" or "excitement."

[0674] Data transmission

[0675] The data collected by the device (two images, basic information about the pet, and the user's emotional data) is compiled into a data packet and sent as an HTTP POST request to the central server. This packet is in JSON format and contains the following example data: "Pet image," "Pet's age: 5 years," "Pet's weight: 10 kg," "Walking time: 30 minutes," and "User's emotion: nervous."

[0676] AI analysis

[0677] The data received by the server is first sent to an image analysis AI model to identify the type of pet. For example, it may be identified as a "Shiba Inu." A basic information analysis model then analyzes data such as age, weight, and walking time to generate health risk data. For example, it may predict a "high risk of obesity" or "medium risk of arthritis." Next, an emotion engine analyzes the user's emotional state and prepares to adjust the content of notification messages and advice.

[0678] Health Risk Assessment and Notification

[0679] The server combines the results of image analysis and basic information analysis to assess overall health risks. Notification messages are generated based on the assessment results, and the content is adjusted according to the user's emotional state. For example, a user who is feeling nervous might receive a message such as, "Obesity has been detected, but please rest assured that we have measures in place." This allows the user to feel reassured and take appropriate measures.

[0680] Food plan proposal

[0681] The server generates an optimal food plan based on the health risk assessment results, making specific suggestions such as "Try high-fiber foods." These suggestions are also adjusted based on the user's emotional state. For example, a proactive suggestion might be "Try high-fiber foods, and there are also joint support supplements."

[0682] Data visualization and hospital collaboration

[0683] The server generates graphs and charts based on past and recent data to visually display the pet's health condition. These visualized data are also displayed in a way that takes the user's emotional state into consideration. For example, if the user is feeling nervous, the system will use colors and a simple design that will give a sense of security. The system will also connect with hospitals as needed based on a health risk assessment to help provide appropriate medical services.

[0684] This system allows for more efficient health management of pets by responding to the user's emotional state, thereby reducing the burden on owners and supporting the longevity and health of pets.

[0685] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0686] Step 1:

[0687] The user uses a smartphone app to take photos of their pet's excrement and face, and uploads them to the app. The user then uses a form within the app to enter basic information about the pet (age, weight, walking time). At this time, the app uses the camera and voice input functions to obtain the user's emotional state using an emotion recognition engine. All entered data is temporarily stored in the smartphone's local storage.

[0688] Input: Pet excrement image, face photo, pet basic information, user emotion data

[0689] Data processing: taking image data, inputting text data, and recognizing emotional data

[0690] Output: Data stored in the smartphone's local storage

[0691] Step 2:

[0692] All data collected by the device (smartphone) (two images, basic information about the pet, and the user's emotional data) is compiled into a single data packet. The data packet is generated in JSON format and sent to the central server as an HTTP POST request.

[0693] Input: Data stored in local storage

[0694] Data processing: Generate data packets in JSON format

[0695] Output: HTTP POST request sent to the central server

[0696] Step 3:

[0697] The server receives the data packet sent from the device. The received data packet is first sent to an image analysis AI model, which analyzes the pet image and identifies the pet's type. This uses image recognition technology (e.g., deep learning). The pet's type (e.g., Shiba Inu) is output as the image analysis result.

[0698] Input: Data packets sent from the device

[0699] Data processing: Identifying pet species using image analysis AI models

[0700] Output: Pet type (e.g. Shiba Inu)

[0701] Step 4:

[0702] The server then uses a basic information analysis model to analyze data such as the pet's age, weight, and walking time to extract health risk data. The model evaluates risk by referencing statistical and medical data. For example, it can produce results such as "high risk of obesity" or "medium risk of arthritis."

[0703] Input: Basic information about your pet

[0704] Data processing: Calculation of health risks using basic information analysis models

[0705] Output: Health risk data (e.g., "High risk of obesity," "Medium risk of arthritis")

[0706] Step 5:

[0707] The server uses an emotion engine to analyze the user's emotional state. Emotional data (e.g., facial expressions and vocal tone) are analyzed to identify the user's emotional state (e.g., nervousness, excitement).

[0708] Input: User emotion data

[0709] Data processing: Identifying emotional states with an emotion engine

[0710] Output: User's emotional state (e.g., nervousness)

[0711] Step 6:

[0712] The server combines the results of image analysis and basic information analysis to assess overall health risks. A notification message is generated based on this assessment. The message content is adjusted according to the user's emotional state. For example, for a nervous user, a message such as "Obesity has been detected, but please rest assured that there are measures in place." is generated.

[0713] Input: Image analysis results, basic information analysis results, user emotional state

[0714] Data processing: Integrated assessment of health risks, generation of notification messages

[0715] Output: Adjusted notification message

[0716] Step 7:

[0717] The server then sends the generated notification message to the device (smartphone), which includes the pet's health risk assessment results and information corresponding to the user's emotional state.

[0718] Input: Adjusted notification message

[0719] Data processing: Sending messages from the server to the device

[0720] Output: Notification message displayed on the terminal

[0721] Step 8:

[0722] The server generates an optimal food plan based on the health risk assessment results. The content of the food plan is also adjusted according to the user's emotional state. For example, a user who is feeling nervous may receive specific suggestions such as "Try high-fiber foods."

[0723] Input: Health risk assessment results, user emotional state

[0724] Data processing: Food plan generation and adjustment

[0725] Output: Adjusted food plan

[0726] Step 9:

[0727] The server sends a notification message containing the food plan proposal to the terminal. This notification message provides the user with the most suitable food plan information and serves as a reference for implementation.

[0728] Input: Adjusted Food Plan

[0729] Data processing: Sending messages from the server to the device

[0730] Output: Food plan notification displayed on device

[0731] Step 10:

[0732] The server generates graphs and charts based on past and current data to visually display the pet's health status. These graphs and charts are designed with the user's emotional state in mind and are presented in an easy-to-read format.

[0733] Input: Historical and current data

[0734] Data processing: generating graphs and charts, adjusting design based on emotional state

[0735] Output: Visualized health care data

[0736] Step 11:

[0737] The server will then coordinate with hospitals as necessary based on the health risk assessment results. For example, if the user is assessed as having a high risk of arthritis, the server will notify the user of a list of nearby affiliated hospitals. It will also send data to specific hospitals so that the user can receive appropriate medical services.

[0738] Input: Health risk assessment results

[0739] Data processing: Generating hospital linkage information and sending necessary data

[0740] Output: Linkage information and data transmission to hospital

[0741] (Application example 2)

[0742] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0743] Conventional pet health management systems provide advice and food plan recommendations based on the pet's health condition in a one-way manner, without taking into account the owner's emotional state. As a result, even if the information the owner receives is appropriate, it can cause stress and anxiety in the owner, potentially reducing their motivation to maintain their pet's health. Furthermore, it is difficult to provide real-time advice tailored to each individual owner and pet in a physical store, making it difficult to provide a personalized service.

[0744] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for receiving a pet image, means for analyzing the received image to identify the pet's type, means for extracting health risk data based on the analyzed pet's type, means for inputting basic information about the pet, means for generating excretion status and health risk data based on the basic information and the health risk data, means for generating and transmitting a notification message based on the generated data, means for acquiring the owner's emotional state, and means for adjusting the content of the notification message based on the owner's emotional state. This enables personalized notification messages and food plans to be proposed taking the owner's emotional state into consideration. Furthermore, by using the health management system in physical stores, appropriate and flexible services can be provided to owners and pets on-site.

[0745] The "means for receiving pet images" refers to a device or software component for acquiring photographs or video data of a pet and inputting it into the system.

[0746] The "means for identifying the type of pet" is an algorithm or system that analyzes the received image data and identifies the type of pet (for example, dog, cat, breed, etc.).

[0747] A "means for extracting health risk data" is a process or system that identifies potential health risks for pets based on the type of pet and basic information about the pet, and extracts that data.

[0748] "Means for inputting basic information about pets" refers to an interface or component that allows owners to input information about their pets (age, weight, walking time, etc.).

[0749] "Means for generating data on excretion status and health risks" refers to a system or process that creates data on pet excretion status and health risks based on basic information about the pet and analysis results.

[0750] The "means for generating and transmitting notification messages" is a mechanism for creating and transmitting messages to notify owners of advice and information based on the generated data.

[0751] "Means for acquiring the owner's emotional state" refers to devices or software that analyze and determine the owner's emotional state from their facial expressions and input information.

[0752] The "means for adjusting the content of the notification message based on the emotional state of the owner" refers to an algorithm or system for appropriately adjusting the expression and content of the notification message, taking into account the emotional state of the owner.

[0753] The "means for generating and proposing a food plan" is a system for creating an appropriate meal plan based on the results of a health risk assessment and proposing it to the owner.

[0754] The "means for adjusting the contents of the food plan" refers to a system that allows the specific contents of the proposed meal plan to be flexibly changed based on the owner's emotional state and the pet's health condition.

[0755] "Means for visualization using graphs and charts" refers to a system that generates graphs and charts to visually display pet health data in an easy-to-understand manner.

[0756] The "means for adjusting the display format" is an algorithm or system that changes the display format of graphs and charts based on the owner's emotional state to make them easier to understand.

[0757] The system for implementing this invention manages the health status of pets and proposes notification messages and food plans that take the user's emotional state into account. The system consists of a smartphone app, a central server, an analytical AI model, and an emotion engine.

[0758] Hardware and software used

[0759] Hardware: Smartphones, tablets, digital signage

[0760] Software: Android / iOS applications, central server, image analysis AI models (e.g., TensorFlow-based models), emotion recognition libraries (e.g., Microsoft Azure Face API, Google Cloud Vision API)

[0761] Specific processing of the system

[0762] 1. Data Entry

[0763] The user uses a smartphone app to take pictures of their pet's feces and the pet itself and upload them to the app. In addition, the user enters basic information about the pet (age, weight, walking time, etc.). The app also activates a facial recognition camera to capture the user's emotional state and records the user's current emotional state.

[0764] 2. Data Transmission

[0765] The smartphone assembles the collected data (two images, basic information, and emotion data) into a single packet and sends it to a central server as an HTTP POST request.

[0766] 3. AI analysis

[0767] The central server sends the received data to an AI model for analysis. First, the image analysis AI analyzes the pet's image to identify its species. Then, the basic information analysis model analyzes data such as age, weight, and walking time to generate health risk data. Furthermore, the emotion engine analyzes the user's emotional state and prepares to provide advice based on that emotional state.

[0768] 4. Health Risk Assessment and Notification

[0769] The central server integrates the image analysis results with the basic information analysis results to assess the overall health risk, and generates notification messages based on the assessed health risk data, adjusting the content according to the user's emotional state.

[0770] 5. Food plan suggestions

[0771] The central server generates an optimal diet plan based on the health risk assessment results and proposes it to the user, and the proposal is also adjusted taking into account the user's emotional state.

[0772] 6. Notifications and Reporting

[0773] The central server generates a report containing notification messages and recommended food plans and sends it to the smartphone, which reflects the user's emotional state and is presented in an easy-to-understand format.

[0774] 7. Data Visualization

[0775] The central server generates graphs and charts based on past and current data to visually display the pet's health status, and these visualizations are also configured taking into account the user's emotional state.

[0776] 8. In-store use

[0777] In-store use tablet devices and digital signage to provide real-time advice tailored to pet owners and their pets, and the system will be used as a support tool to help store staff explain things to pet owners more effectively.

[0778] Examples of concrete examples and prompts

[0779] For example, if the owner is feeling stressed, the notification message will be tailored to reassure the owner.

[0780] Example prompt for generative AI model:

[0781] Use the following data to analyze your pet's health and your emotional state and suggest an appropriate food plan.

[0782] Pet image (jpg)

[0783] Pet's age: 5 years

[0784] Pet weight: 20kg

[0785] Walking time: 30 minutes

[0786] Owner's emotion image (jpg)

[0787] A word of caution: If the owner is stressed, offer reassuring suggestions.

[0788] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0789] Step 1:

[0790] The user uses a smartphone app to take pictures of their pet's waste and the pet itself, and uploads them to the app. The input data here is the pet's image, basic information (age, weight, walking time, etc.), and a face image of the owner. The app then assembles this data into a single packet.

[0791] Step 2:

[0792] The device sends the combined data packet (two images, basic information, and emotion data) to the central server as an HTTP POST request. This transmission process takes place over the Internet, and the data arrives at the server.

[0793] Step 3:

[0794] The server sends the received data to an AI model for analysis. First, the image analysis AI analyzes the input data (images of pets) and identifies the pet's type. Specifically, the input image is passed to a TensorFlow-based image analysis model, which extracts the pet's type data as output.

[0795] Step 4:

[0796] The server uses a basic information analysis model to analyze basic information entered by the user (such as age, weight, and walking time). It then generates health risk data based on the input information. This analysis produces output data such as obesity risk and arthritis risk.

[0797] Step 5:

[0798] The server uses an emotion engine to analyze the user's emotion data. Specifically, it uses emotion recognition libraries such as Microsoft Azure Face API or Google Cloud Vision API to identify the user's emotional state from the user's facial image. The output of this step is the user's emotional state data.

[0799] Step 6:

[0800] The server integrates the results of image analysis, basic information analysis, and emotion analysis to assess the overall health risk. Based on the assessed health risk data, it generates a notification message. The content of this notification message is tailored according to the user's emotional state. The output is a personalized notification message.

[0801] Step 7:

[0802] The server generates and suggests an optimal food plan based on the health risk assessment results. The suggested food plan is also tailored to take into account the user's emotional state, for example by including reassuring messages. The output of this step is the tailored food plan.

[0803] Step 8:

[0804] The server generates a report containing a notification message and a food plan and sends it to the device. The report is then provided to the user, and its content reflects the user's emotional state. The output is a detailed report displayed on the smartphone.

[0805] Step 9:

[0806] The server generates graphs and charts based on past and current data to visually display the pet's health status. These graphs and charts are constructed taking into account the user's emotional state and are presented in an easy-to-understand format. The output is data in a visually easy-to-understand format.

[0807] Step 10:

[0808] In the physical store, tablet devices and digital signage display appropriate advice based on the data sent from the server. Store staff refer to this data and provide detailed explanations to pet owners. This enables flexible and effective on-site service provision. The output is customized advice provided in real time.

[0809] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0810] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0811] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the smart glasses 214.

[0812] [Third embodiment]

[0813] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0814] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0815] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0816] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0817] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0818] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0819] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0820] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0821] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0822] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0823] In the headset type terminal 314, a reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0824] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the headset type terminal 314 will be referred to as the "terminal."

[0825] The system of the present invention is designed to effectively manage the health of pets and is configured as follows. The main components are a smartphone app used by the user, a central server, and an analytical AI model. The specific functions and operations of the system are described in detail below.

[0826] Data Entry

[0827] Users use a smartphone app to take photos of their pet's excrement and the pet itself, and then upload them to the app. For example, a user can take a photo of their pet's excrement after a morning walk, then take a photo of their pet's face and upload it to the app. At this time, the user also enters basic information about the pet (age, weight, walking time, etc.). This allows users to easily record the health status of their pet.

[0828] Data transmission

[0829] The device collects the data entered by the user into a single packet and sends it to the central server. Specifically, the device generates a data packet that combines two photos and text data (age, weight, and walking time) and sends it to the server as an HTTP POST request.

[0830] AI analysis

[0831] The server sends the received data to an AI model for analysis. First, the image analysis AI analyzes the received image data to identify the type of pet. In this case, the image analysis AI recognizes specific breeds such as "Shiba Inu." Next, the basic information analysis model analyzes the input data, such as age, weight, and walking time, and generates health risk data. This results in an assessment such as "high risk of obesity" or "medium risk of arthritis."

[0832] Health Risk Assessment

[0833] The server integrates these analysis results to assess overall health risk. Specifically, it integrates information on "mild obesity" and "arthritis risk" to perform a comprehensive risk assessment. It then generates a notification message based on the health risk and sends it to the user. For example, a notification might say, "Obesity has been detected. We recommend high-fiber foods. We also suggest supplements that are good for joint health."

[0834] Food plan proposal

[0835] The server generates an optimal food plan based on the health risk assessment results for the user's pet. For example, it lists and suggests "high-fiber foods" and "joint support supplements." This allows users to accurately manage their pet's nutrition.

[0836] Notifications and Reporting

[0837] The server then sends notification messages and reports to the user. The notification messages include information about the analysis results and recommended feeding plans. Additionally, the server generates graphs and charts based on past and current data, allowing the user to visually understand their pet's health status. For example, graphs can be displayed showing weight changes and health risk trends.

[0838] Hospital collaboration

[0839] The server will then connect with hospitals as needed based on the health risk assessment results. For example, if the user is assessed as having a high risk of arthritis, the server will notify the user of a list of nearby affiliated hospitals. It will also send data to hospitals as needed to ensure the user receives appropriate medical services.

[0840] As described above, the system of the present invention aims to comprehensively manage the health status of pets and support early detection and treatment, thereby reducing the burden on owners and contributing to the health and longevity of pets.

[0841] The processing flow will be explained below.

[0842] Step 1:

[0843] The user launches the smartphone app. Using the app's built-in camera function, the user takes a photo of their pet's excrement, then a photo of their pet's face. Each photo is then uploaded to the app. The user also enters basic information about their pet (age, weight, walking time, etc.).

[0844] For example, a user taps the app's "upload image" button, takes a photo of the pet's excrement, then takes a photo of the pet's face, and uploads both to the app.

[0845] Step 2:

[0846] The device collects the data entered by the user (two images and basic information) into a single packet. After generating the data packet, the device sends an HTTP POST request to the central server.

[0847] As a specific example, a terminal generates a JSON-formatted data packet that combines image data and text data, and executes a request called "POST / analyze HTTP / 1.1."

[0848] Step 3:

[0849] The server processes the data received from the device and sends it to an AI model for analysis. First, the server uses image analysis AI to analyze the received pet image and identify the pet's type. In this process, the image analysis AI recognizes specific dog or cat breeds, such as "Shiba Inu." Next, the server uses a basic information analysis model to analyze the input data, such as age, weight, and walking time, and generates health risk data.

[0850] As a specific example, an image analysis AI may determine that "this image is of a Shiba Inu," and a basic information analysis model may assess the animal as "high risk of obesity" and "medium risk of arthritis."

[0851] Step 4:

[0852] The server integrates the image analysis results with the basic information analysis results to assess the overall health risk, and then generates a notification message based on the assessment results and sends it to the user.

[0853] As a specific example, the server integrates data such as "mild obesity" and "risk of arthritis" and generates a notification message saying, "Obesity has been detected. We recommend high-fiber foods. We also suggest supplements that are good for joint health."

[0854] Step 5:

[0855] Based on the health risk assessment results, the server generates an optimal food plan for the user's pet, which may include high-fiber foods and joint support supplements.

[0856] As a specific example, the server lists specific suggestions such as "recommended food: high fiber food" and "recommended supplement: joint support supplement."

[0857] Step 6:

[0858] The server generates a report containing notification messages and a recommended food plan and sends it to the device, where the user can check the received report in the app.

[0859] As a specific example, the server generates a detailed food plan report and sends it to the device along with the message, "Please check the latest analysis results. Obesity has been detected. Try the food plan below."

[0860] Step 7:

[0861] The server generates graphs and charts based on past and current data, visually displaying the pet's health status, which the user can view within the app.

[0862] As a specific example, graphs showing changes in weight and health risks are generated and displayed within the app.

[0863] Step 8:

[0864] If necessary, the server will connect with hospitals based on the health risk assessment results and notify the user of a list of nearby affiliated hospitals, enabling them to receive appropriate medical services.

[0865] As a specific example, a notification message saying "You are at high risk of developing arthritis. Please consult the affiliated hospital below" is sent along with the contact information of the affiliated hospital.

[0866] The above is a specific processing flow of the pet health management system, which allows users to effectively manage the health of their pets.

[0867] Example 1

[0868] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0869] Today, many pets suffer from various health problems due to inadequate health management by their owners. For example, it is difficult to determine the appropriate amount of food and exercise, which can result in problems such as obesity and arthritis. However, there is no easy-to-use system for monitoring pet health on a daily basis and taking appropriate measures. For this reason, there is a need for the development of a system that assesses health risks based on pet photos and basic information and proposes an appropriate food plan.

[0870] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0871] In this invention, the server includes a means for receiving images of the pet from the terminal used by the user, a means for collecting the received images and basic information of the pet into a single data packet and transmitting it, and a means for providing the data packet to an AI model that analyzes the data packet in the central server. This makes it possible to evaluate health risks based on the received image analysis results and the basic information of the pet, and to generate notification messages, propose optimal food plans, and even generate graphs and charts based on past data.

[0872] "User" refers to a person who uses the system.

[0873] "Terminal" refers to an electronic device used by a user, such as a personal digital assistant or computer.

[0874] "Central Server" refers to a central computer system that receives, analyzes, and stores data.

[0875] "Image analysis AI" refers to an artificial intelligence model that analyzes received image data and extracts specific information.

[0876] "Basic information" refers to basic data about your pet, such as age, weight, and walking time.

[0877] "Health risk data" refers to assessment data regarding the health status of pets obtained from the analysis results.

[0878] "Data packet" refers to a unit of information that contains image data and basic information packaged for transmission.

[0879] "Notification message" refers to an information message sent to the user based on the analysis results.

[0880] "Food Plan" refers to a suggested dietary plan for your pet based on health risk data.

[0881] "Graphs and charts" refer to diagrams that visually display changes in a pet's physical condition or symptoms.

[0882] MODE FOR CARRYING OUT THE INVENTION

[0883] The system of the present invention is designed to effectively manage the health of pets, and is composed of a terminal used by the user (e.g., a smartphone), a central server, and an analytical AI model.

[0884] Data entry and submission

[0885] Users can use a smartphone app to take photos of their pet's feces and face and upload them within the app. For example, a user can take photos of their pet's feces and face after a morning walk and upload the photos. At this time, users also enter basic information about their pet (age, weight, walking time, etc.) into the app. This basic information can be easily added through a text input form.

[0886] The device (smartphone) combines the data entered by the user (two photos and text data) into a single data packet and sends it to the central server as an HTTP POST request.

[0887] Data analysis and health risk assessment

[0888] The server sends the received data packets to an AI model for analysis. First, an image analysis AI (for example, a TensorFlow model) analyzes the received image data and identifies the type of pet. For example, it might identify the image as a "Shiba Inu." Next, a basic information analysis model analyzes the input data, such as age, weight, and walking time, to generate health risk data. This results in an assessment such as "high risk of obesity" or "medium risk of arthritis."

[0889] The server integrates the analysis results and evaluates the overall health risk. Specifically, it integrates "mild obesity" and "arthritis risk" to perform a comprehensive risk assessment. It then generates a notification message based on the assessment results and sends it to the user. For example, a notification may be generated that reads, "Obesity has been detected. We recommend high-fiber foods. We also suggest supplements that are good for joint health."

[0890] Food plan proposal

[0891] The server generates an optimal food plan based on the health risk assessment results. For example, it retrieves information on "high-fiber foods" and "joint support supplements" from the database, lists them, and suggests them to the user. This suggestion is sent to the user's smartphone as a push notification.

[0892] Notifications and Reporting

[0893] The server generates graphs and charts based on past and latest data along with notification messages and sends them to the user, allowing the user to visually understand the health status of their pet. For example, graphs showing changes in weight and health risks are displayed.

[0894] Hospital collaboration

[0895] The server will then connect with hospitals as needed based on the health risk assessment results. For example, if the user is assessed as having a high risk of arthritis, the server will notify the user of a list of nearby affiliated hospitals. Based on this information, the user can receive appropriate medical services. If necessary, the server will securely transmit data to the hospital.

[0896] Examples and prompts

[0897] Examples:

[0898] After a morning walk, users take photos of their pet's feces and face, and upload them to a smartphone app. They then enter information such as age (3 years), weight (10 kg), and walk time (30 minutes).

[0899] You will receive a notification message saying, "Obesity detected. We recommend high-fiber foods. We also suggest supplements for joint health."

[0900] Check for recommended "high fiber foods" and "joint support supplements."

[0901] Example prompt sentence:

[0902] "Users take photos of their pet's feces and face after their morning walk and upload them through a smartphone app. They also enter their age, weight, and walking time."

[0903] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0904] Step 1:

[0905] The user uses a smartphone app to take photos of their pet's excrement and face, and uploads them within the app. The input is a photo of the pet's excrement, a photo of the face, and basic information (age, weight, walking time). The output is a set of the uploaded photo and the input text data. Specifically, the user takes a photo using the app's camera function, and then enters information such as "3 years old," "10 kg," and "30 minutes" into the input form.

[0906] Step 2:

[0907] The device combines the data entered by the user (two photos and text data) into a single data packet and sends it to the central server as an HTTP POST request. The input is the data uploaded by the user from the app, and the output is the data packet sent as an HTTP POST request. Specifically, the smartphone app generates the data packet in the background and sends an HTTP request to the specified server URL.

[0908] Step 3:

[0909] The server provides the received data packets to the AI ​​model for analysis. The input is the data packet sent from the device, and the output is the data passed to the AI ​​model for analysis. Specifically, the server converts the received data into an analytical format and passes it to the image analysis AI and basic information analysis model.

[0910] Step 4:

[0911] The server uses image analysis AI to analyze the received image data and identify the type of pet. The input is the image data in the data packet, and the output is the identification result of the pet type. For example, the image is analyzed and identified as a "Shiba Inu." The specific operation is to execute image analysis AI (for example, a TensorFlow model).

[0912] Step 5:

[0913] The server uses a basic information analysis model to analyze the input text data and generate health risk data. The input is the age, weight, and walking time data in the data packet, and the output is health risk data. Specifically, the basic information analysis model generates an assessment such as "high risk of obesity" or "medium risk of arthritis."

[0914] Step 6:

[0915] The server integrates the analysis results and performs an overall health risk assessment. The input is the image analysis results and basic information analysis results, and the output is the integrated health risk assessment results. Specifically, a Python script integrates "mild obesity" and "arthritis risk."

[0916] Step 7:

[0917] The server generates a notification message based on the assessment results and sends it to the user. The input is the health risk assessment result, and the output is the generated notification message. Specifically, the Python script generates a message saying, "Obesity has been detected. High-fiber foods are recommended. Supplements that are good for joint health are also suggested." and sends a push notification.

[0918] Step 8:

[0919] The server generates and proposes an optimal food plan based on the health risk assessment results. The input is the health risk assessment results, and the output is a recommended food plan. Specifically, it retrieves information on "high fiber foods" and "joint support supplements" from the database and creates a list.

[0920] Step 9:

[0921] The server generates graphs and charts based on past and latest data along with notification messages and sends them to the user. The input is past and latest data, and the output is the generated graphs and charts. Specifically, the graphs are generated using libraries such as Matplotlib and Seaborn and displayed in the app.

[0922] Step 10:

[0923] The server will communicate with hospitals as needed based on the health risk assessment results. The input is the health risk assessment results, and the output is a list of affiliated hospitals and the transmission of necessary medical data. Specifically, if the user is assessed as having a "high risk of arthritis," the server retrieves a list of nearby affiliated hospitals from the database and notifies the user. It also executes an API to securely send data to hospitals as needed.

[0924] (Application example 1)

[0925] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0926] Existing methods for managing pet health make it difficult for owners to accurately record their pet's waste and physical condition and take appropriate health measures. It is also time-consuming to select food and suggest supplements based on the pet's health condition. Furthermore, there is a lack of integration with food delivery services that address pet health risks. Therefore, there is a need for a system that provides comprehensive and efficient pet health management.

[0927] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0928] In this invention, the server includes means for receiving images of the pet, means for analyzing the received images to identify the type of pet, means for extracting health risk data based on the analyzed type of pet, means for inputting basic information about the pet, means for generating excretion status and health risk data based on the basic information and the health risk data, means for generating and sending a notification message based on the generated data, and means for generating a food plan based on the health risks and linking with a food delivery service, thereby enabling comprehensive and efficient management of the pet's health status and the recommendation and delivery of appropriate food and supplements.

[0929] The "means for receiving pet images" is a device or system that allows a user to send images of a pet taken using a smartphone or camera to a server.

[0930] "Means for analyzing the received image and identifying the type of pet" refers to a device or system that includes an algorithm or software for identifying the type or breed of pet by analyzing the received image data.

[0931] The "means for extracting health risk data" is a device or system for extracting health risk data related to pets based on the type and basic information of the pets.

[0932] The "means for inputting basic information about a pet" refers to a device or system that allows a user to input basic information about a pet, such as age, weight, and walking time.

[0933] The "means for generating data on excretion status and health risks" refers to a device or system for generating information on a pet's excretion status and health risks based on basic information about the pet and analyzed health risk data.

[0934] "Means for generating and transmitting notification messages" refers to a device or system for creating and transmitting notification messages to users on smartphones or other devices based on the generated health risk data.

[0935] "Means for generating food plans and linking with food delivery services" refers to a device or system for creating an appropriate food plan based on the results of a pet's health risk assessment and providing the selected food and supplements in collaboration with a food delivery service.

[0936] "Means for recording changes in a pet's physical condition and symptoms and visualizing them in graphs and charts" refers to a device or system that records changes in a pet's physical condition and symptoms as data, converts that data into graphs and charts, and visually displays them to the user.

[0937] This invention is a system for effectively managing the health of pets, and is composed of the following main components: a smartphone app used by the user, a central server, and an analytical AI model.

[0938] Data Entry

[0939] Users use a smartphone app to take pictures of their pet's feces and the pet itself, and upload them to the app. At the same time, users can also enter basic information about their pet (age, weight, walking time, etc.).

[0940] Data transmission

[0941] The device collects the data entered by the user into a single packet and sends it to the central server. Specifically, the device generates a data packet that combines two photos and text data (age, weight, and walking time) and sends it to the server as an HTTP POST request.

[0942] AI analysis

[0943] The server sends the received data to an AI model for analysis. The image analysis AI analyzes the received image data and identifies the type of pet. The basic information analysis model analyzes the input data, such as age, weight, and walking time, and generates health risk data. For example, it can provide assessment results such as "high risk of obesity" or "medium risk of arthritis."

[0944] Health Risk Assessment

[0945] The server integrates these analysis results and evaluates the overall health risk. Based on the evaluation, it generates a notification message according to the health risk and sends it to the user.

[0946] Food plan proposal

[0947] The server generates an optimal food plan based on the health risk assessment results for the user's pet. For example, the server lists and recommends "high-fiber foods" and "joint support supplements" to the user. The system works in conjunction with a food delivery service to deliver the selected foods and supplements to the user.

[0948] Notifications and Reporting

[0949] The server sends notification messages and reports to the user, including analysis results and recommended feeding plans. The server generates graphs and charts based on past and current data, allowing the user to visually understand the health status of their pet.

[0950] Hardware and Software Used

[0951] Smartphone (for users to take pictures and enter data)

[0952] Central server (for data analysis and results transmission)

[0953] AI model (using Python libraries such as PIL and requests for image analysis and basic information analysis)

[0954] FastAPI (for server-side APIs)

[0955] Processing examples and prompt statements

[0956] For example, a user can take photos of their dog's excrement and face with their smartphone and upload them to the app. This data is then analyzed on a central server and classified as "Shiba Inu," "high risk of obesity," or "medium risk of arthritis." The app then recommends "high-fiber food" and "joint support supplements" to the user, who can then purchase them and use the food delivery service.

[0957] Example prompt sentence:

[0958] Take photos of your dog's feces and face, and enter your pet's age, weight, and walking time. Based on that data, we will provide you with an appropriate health risk assessment and food plan suggestions.

[0959] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0960] Step 1:

[0961] Users use a smartphone app to take photos of their pet's feces and face, upload them to the app, and then enter basic information about their pet (age, weight, walking time).

[0962] Input: Photo of pet's waste, face photo, age, weight, walking time

[0963] Output: Image data, basic information data

[0964] What happens: A user opens the app, takes a photo using the camera, fills in basic information in a form, and presses the submit button.

[0965] Step 2:

[0966] The device collects the data received from the user into a single data packet and sends it to the central server using an HTTP POST request.

[0967] Input: Image data, basic information data

[0968] Output: HTTP POST request to the server

[0969] Specific operation: The smartphone app packs two photos and text data into a packet and sends it to the server's API endpoint.

[0970] Step 3:

[0971] The server sends the received data to an AI model for analysis. The image analysis AI analyzes the received image data and identifies the type of pet.

[0972] Input: Data packet (image data, basic information data)

[0973] Output: Pet type (e.g. Shiba Inu)

[0974] Specific operation: After receiving the data, the server passes the image data to the AI ​​model, which performs image analysis and obtains the pet's type as a result.

[0975] Step 4:

[0976] The server uses a basic information analysis model to analyze the entered age, weight, and walking time, and generates health risk data.

[0977] Input: Age, weight, walking time

[0978] Output: Health risk data (e.g., high risk of obesity, medium risk of arthritis)

[0979] Specific operation: The server passes basic information to the analysis model, performs data calculations, and generates health risk data.

[0980] Step 5:

[0981] The server aggregates the analysis results, assesses the overall health risk, and generates notification messages based on the assessment.

[0982] Input: Pet type, health risk data

[0983] Output: Health risk assessment results, notification message

[0984] Specific operation: The server integrates pet type and health risk data, uses AI models to assess the overall health risk, and generates a notification message.

[0985] Step 6:

[0986] The server generates an optimal food plan based on the health risk assessment results and proposes it to the user. It also works with food delivery services to deliver food to the user.

[0987] Input: Health risk assessment results

[0988] Output: Food plan, food delivery request

[0989] What it does: The server uses the AI ​​model to generate an appropriate food plan and sends a delivery request using the food delivery service's API.

[0990] Step 7:

[0991] The server sends notification messages and reports to the user. The server displays a message to the user containing information about the analysis results and recommended food plan.

[0992] Input: Health risk assessment results, food plan

[0993] Output: Notification messages, reports

[0994] Specific operation: The server generates notification messages and reports based on the analysis results and food plans, and sends them to a smartphone app, where users can view them.

[0995] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0996] The system of the present invention is for managing the health of pets and incorporates an emotion engine that provides notification messages and suggests food plans that take into account the user's emotional state. The system consists of a smartphone app, a central server, an analytical AI model, and an emotion engine.

[0997] Data Entry

[0998] A user uses a smartphone app to take photos of their pet's excrement and the pet itself, and uploads them to the app. At this time, the user enters basic information about the pet (age, weight, walking time, etc.). For example, a user might take a photo of their pet's excrement after a morning walk, then take a photo of the pet's face and upload it to the app. In addition, an emotion recognition function is activated within the app to capture the user's emotional state and record the user's current emotional state.

[0999] Data transmission

[1000] The device collects the data input by the user (two images, basic information, and emotion data) into a single packet and sends it to the central server. Specifically, the device generates a data packet that combines image data and text data (age, weight, walking time, and the user's emotional state) and sends it to the server as an HTTP POST request.

[1001] AI analysis

[1002] The server sends the received data to an AI model for analysis. First, the image analysis AI analyzes the pet's image and identifies the pet's type (e.g., "Shiba Inu"). Next, the basic information analysis model analyzes data such as age, weight, and walking time to generate health risk data (e.g., "high risk of obesity" or "medium risk of arthritis"). Furthermore, the emotion engine analyzes the user's emotional state and prepares to provide advice based on that emotional state.

[1003] Health Risk Assessment

[1004] The server combines the results of image analysis and basic information analysis to assess overall health risk. It also generates notification messages based on the assessed health risk data and adjusts the content according to the user's emotional state. For example, if the user appears anxious, it will send a message that reassures them, such as, "Obesity has been detected, but please rest assured that there are measures in place. We recommend high-fiber foods."

[1005] Food plan proposal

[1006] The server generates an optimal food plan based on the health risk assessment results and proposes it to the user. The content of the food plan proposal is also adjusted taking into account the user's emotional state. For example, if the user is in a state of high interest, the server will proactively suggest, "Why not try high-fiber foods? We also have joint support supplements."

[1007] Notifications and Reporting

[1008] The server generates a report containing a notification message and a recommended food plan and sends it to the device. The report reflects the user's emotional state and is presented in a format that is easy for the user to understand. For example, a notification message may be generated that reads, "Please check the latest analysis results. We have prepared a food plan that you can follow with confidence."

[1009] Graph and chart generation

[1010] The server generates graphs and charts based on past and recent data to visually display the pet's health status. These visualized data are also configured taking into account the user's emotional state. For example, if the user is feeling nervous, the data will be displayed in a simple design with easy-to-read colors that give a sense of security.

[1011] Hospital collaboration

[1012] The server will then connect with hospitals as needed based on the health risk assessment results. For example, if the user is assessed as having a high risk of arthritis, the server will send a message based on the user's emotional state, providing a list of nearby affiliated hospitals. If necessary, the server will also send data to hospitals to ensure the user receives appropriate medical services.

[1013] As described above, the system of the present invention comprehensively manages the health condition of pets and takes into account the emotional state of the user to provide more effective support, thereby reducing the burden on owners and contributing to the health and longevity of pets.

[1014] The processing flow will be explained below.

[1015] Step 1:

[1016] The user launches the smartphone app. They take photos of their pet's excrement and face and upload them within the app. They also enter basic information about their pet (age, weight, walking time, etc.). Taking a photo of the user's facial expression triggers the emotion engine to recognize the user's emotions.

[1017] For example, after a morning walk, a user takes a photo of their pet's excrement, then takes a photo of their pet's face, and uploads both to the app. The app then captures the user's current facial expression and obtains emotional data.

[1018] Step 2:

[1019] The device collects the data input by the user (two images, basic information, and emotion data) into a single packet and sends it to the central server. The data packet contains image data, text data (age, weight, walking time), and emotion data obtained by the emotion engine.

[1020] As a specific example, the device generates a JSON-formatted data packet that includes an image, basic information, and emotion data, and executes "POST / analyze HTTP / 1.1."

[1021] Step 3:

[1022] The server starts the process of sending the received data to an AI model for analysis. First, the image analysis AI analyzes the pet's image and identifies the pet's species. Next, the basic information analysis model analyzes the input data and generates health risk data. Finally, the emotion engine analyzes the user's emotion data.

[1023] For example, the image analysis AI identifies the dog as a "Shiba Inu," and the basic information analysis model evaluates it as "high risk of obesity" and "medium risk of arthritis." The emotion engine recognizes the user's emotion as "anxiety."

[1024] Step 4:

[1025] The server integrates the results of image analysis, basic information analysis, and the emotion engine to assess the overall health risk, and generates a notification message based on the assessment results, tailoring the message content to the user's emotional state.

[1026] As a specific example, the server combines "mild obesity" and "arthritis risk" and generates a notification message saying, "Obesity has been detected, but there are measures you can take. We recommend high-fiber foods."

[1027] Step 5:

[1028] The server generates an optimal food plan based on the health risk assessment results and proposes it to the user. The generated food plan is also adjusted according to the user's emotional state.

[1029] As a concrete example, if the emotion engine recognizes that the user's emotion is "curious," it will make a proactive suggestion such as, "Why not try some high-fiber foods? We also recommend some joint support supplements."

[1030] Step 6:

[1031] The server generates a report containing notification messages and recommended food plans and sends it to the device, where the user can check the report and understand the health status of their pet.

[1032] As a specific example, the server sends a message saying, "Please check the latest analysis results. We have prepared a food plan that you can follow with confidence," and attaches a detailed food plan report.

[1033] Step 7:

[1034] The server generates graphs and charts based on past and current data to visually display the pet's health status, and these graphs and charts are also displayed in a way that reflects the user's emotional state.

[1035] As a specific example, a graph showing changes in weight and health risks is generated, and if the user is feeling "tense," it is displayed in a color that is easy to see and gives a sense of security.

[1036] Step 8:

[1037] If necessary, the server will connect with hospitals based on the health risk assessment results. The emotion engine will notify the user of a list of nearby affiliated hospitals via a message based on the user's emotional state. It will also send relevant data to the hospitals as needed.

[1038] As a specific example, a notification message stating, "You are at high risk of arthritis. Rest assured, you can consult with the affiliated hospitals listed below," along with contact information for the affiliated hospitals, may be sent.

[1039] The above is a specific processing flow for incorporating an emotion engine into a pet health management system, and this system enables better health management for both users and pets.

[1040] Example 2

[1041] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1042] Conventional pet health management systems support image analysis and basic information input as a means of monitoring pet health, but do not take into account the user's psychological state. This can cause mental stress when users receive notifications or suggestions from the system. Furthermore, health risk assessments and food plan suggestions are uniform, lacking flexibility to respond to the user's emotional state. There is a need to improve this and provide more user-friendly support.

[1043] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1044] In this invention, the server includes means for receiving an image of the pet, means for analyzing the received image and identifying the type of pet, means for extracting health risk data based on the analyzed type of pet, means for inputting basic information about the pet, means for generating excretion status and health risk data based on the basic information and the health risk data, means for generating and sending a notification message based on the generated data, means for acquiring and analyzing the user's emotional state, means for adjusting the content of the notification message based on the emotional state, means for generating and proposing an optimal food plan based on the health risk assessment results, means for adjusting the content of the proposed food plan based on the user's emotional state, means for recording changes in the pet's physical condition and symptoms and visualizing them in graphs or charts, and means for configuring the visualized data according to the user's emotional state.

[1045] This makes it possible to provide appropriate support that is in line with the user's emotional state. Specifically, it is possible to provide notification messages and food plan suggestions that take the user's emotional state into account, as well as visualize the pet's health status, thereby reducing the burden on the user and achieving better health management for their pet.

[1046] The "means for receiving pet images" is a method for importing pet image data taken using a smartphone or camera into an application or server.

[1047] "Means for analyzing images and identifying the type of pet" refers to a method of identifying the type of pet (such as dog breed or cat breed) based on the received image using image recognition technology such as deep learning.

[1048] The "means for extracting health risk data" refers to a method for deriving the relevant health risks based on the identified pet species, with reference to statistical data and medical data.

[1049] "Means for inputting basic information" refers to a method by which a user inputs basic information such as the pet's age, weight, and walking time via a smartphone, computer, etc.

[1050] The "means for generating excretion status and health risk data" is a method for calculating a pet's excretion status and overall health risk based on basic information input by the user and analyzed health risk data.

[1051] The "means for generating and transmitting a notification message" is a method for generating an appropriate notification message for the user based on the generated health risk data and excretion status, and transmitting the message to a designated terminal.

[1052] "Means for acquiring and analyzing the user's emotional state" refers to a method of detecting the user's current emotional state using a camera or voice analysis function and analyzing it as data.

[1053] The "means for adjusting the content of the notification message based on the emotional state" is a method for optimizing the content of the notification message in accordance with various emotions such as tension and anxiety based on the acquired emotional state of the user.

[1054] "Means for generating and proposing an optimal food plan" is a method for calculating an optimal food plan for the relevant pet based on the health risk assessment results and proposing that plan to the user.

[1055] The "means for adjusting the proposed content based on the user's emotional state" is a method for adjusting the content of the generated food plan in a way that is more effectively accepted by the user in accordance with the user's emotional state.

[1056] "Means for recording changes in physical condition and symptoms and visualizing them in graphs and charts" refers to a method for recording changes in a pet's physical condition and symptoms as time-series data and visually displaying them as graphs and charts.

[1057] "Means for configuring visualized data according to the user's emotional state" refers to a method for adjusting the design and color scheme of generated graphs and charts according to the user's emotional state, and providing them in a format that is easy to read and gives a sense of security.

[1058] The system of the present invention is a system that comprehensively manages the health condition of a pet and proposes notification messages and food plans based on the emotional state of the user. Hereinafter, embodiments of the present invention will be described in detail.

[1059] System Configuration

[1060] The system consists of a smartphone app, a central server, an image analysis AI model, an emotion engine, and a data transmission and reception infrastructure. Users mainly use their smartphones to input their pet's health information, and the central server is responsible for data analysis.

[1061] Data Entry

[1062] Users use a smartphone app to take photos of their pet's excrement and face and upload them to the app. At the same time, they also enter basic information about their pet (such as age, weight, and walking time). In particular, an emotion recognition function is activated within the app and records the user's current emotional state using a camera or voice input. For example, a user can take a photo of their pet's excrement after a morning walk, then take a photo of their pet's face and upload it to the app. The emotion recognition function analyzes the user's facial scan and voice tone to record emotions such as "anxiety" or "excitement."

[1063] Data transmission

[1064] The data collected by the device (two images, basic information about the pet, and the user's emotional data) is compiled into a data packet and sent as an HTTP POST request to the central server. This packet is in JSON format and contains the following example data: "Pet image," "Pet's age: 5 years," "Pet's weight: 10 kg," "Walking time: 30 minutes," and "User's emotion: nervous."

[1065] AI analysis

[1066] The data received by the server is first sent to an image analysis AI model to identify the type of pet. For example, it may be identified as a "Shiba Inu." A basic information analysis model then analyzes data such as age, weight, and walking time to generate health risk data. For example, it may predict a "high risk of obesity" or "medium risk of arthritis." Next, an emotion engine analyzes the user's emotional state and prepares to adjust the content of notification messages and advice.

[1067] Health Risk Assessment and Notification

[1068] The server combines the results of image analysis and basic information analysis to assess overall health risks. Notification messages are generated based on the assessment results, and the content is adjusted according to the user's emotional state. For example, a user who is feeling nervous might receive a message such as, "Obesity has been detected, but please rest assured that we have measures in place." This allows the user to feel reassured and take appropriate measures.

[1069] Food plan proposal

[1070] The server generates an optimal food plan based on the health risk assessment results, making specific suggestions such as "Try high-fiber foods." These suggestions are also adjusted based on the user's emotional state. For example, a proactive suggestion might be "Try high-fiber foods, and there are also joint support supplements."

[1071] Data visualization and hospital collaboration

[1072] The server generates graphs and charts based on past and recent data to visually display the pet's health condition. These visualized data are also displayed in a way that takes the user's emotional state into consideration. For example, if the user is feeling nervous, the system will use colors and a simple design that will give a sense of security. The system will also connect with hospitals as needed based on a health risk assessment to help provide appropriate medical services.

[1073] This system allows for more efficient health management of pets by responding to the user's emotional state, thereby reducing the burden on owners and supporting the longevity and health of pets.

[1074] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1075] Step 1:

[1076] The user uses a smartphone app to take photos of their pet's excrement and face, and uploads them to the app. The user then uses a form within the app to enter basic information about the pet (age, weight, walking time). At this time, the app uses the camera and voice input functions to obtain the user's emotional state using an emotion recognition engine. All entered data is temporarily stored in the smartphone's local storage.

[1077] Input: Pet excrement image, face photo, pet basic information, user emotion data

[1078] Data processing: taking image data, inputting text data, and recognizing emotional data

[1079] Output: Data stored in the smartphone's local storage

[1080] Step 2:

[1081] All data collected by the device (smartphone) (two images, basic information about the pet, and the user's emotional data) is compiled into a single data packet. The data packet is generated in JSON format and sent to the central server as an HTTP POST request.

[1082] Input: Data stored in local storage

[1083] Data processing: Generate data packets in JSON format

[1084] Output: HTTP POST request sent to the central server

[1085] Step 3:

[1086] The server receives the data packet sent from the device. The received data packet is first sent to an image analysis AI model, which analyzes the pet image and identifies the pet's type. This uses image recognition technology (e.g., deep learning). The pet's type (e.g., Shiba Inu) is output as the image analysis result.

[1087] Input: Data packets sent from the device

[1088] Data processing: Identifying pet species using image analysis AI models

[1089] Output: Pet type (e.g. Shiba Inu)

[1090] Step 4:

[1091] The server then uses a basic information analysis model to analyze data such as the pet's age, weight, and walking time to extract health risk data. The model evaluates risk by referencing statistical and medical data. For example, it can produce results such as "high risk of obesity" or "medium risk of arthritis."

[1092] Input: Basic information about your pet

[1093] Data processing: Calculation of health risks using basic information analysis models

[1094] Output: Health risk data (e.g., "High risk of obesity," "Medium risk of arthritis")

[1095] Step 5:

[1096] The server uses an emotion engine to analyze the user's emotional state. Emotional data (e.g., facial expressions and vocal tone) are analyzed to identify the user's emotional state (e.g., nervousness, excitement).

[1097] Input: User emotion data

[1098] Data processing: Identifying emotional states with an emotion engine

[1099] Output: User's emotional state (e.g., nervousness)

[1100] Step 6:

[1101] The server combines the results of image analysis and basic information analysis to assess overall health risks. A notification message is generated based on this assessment. The message content is adjusted according to the user's emotional state. For example, for a nervous user, a message such as "Obesity has been detected, but please rest assured that there are measures in place." is generated.

[1102] Input: Image analysis results, basic information analysis results, user emotional state

[1103] Data processing: Integrated assessment of health risks, generation of notification messages

[1104] Output: Adjusted notification message

[1105] Step 7:

[1106] The server then sends the generated notification message to the device (smartphone), which includes the pet's health risk assessment results and information corresponding to the user's emotional state.

[1107] Input: Adjusted notification message

[1108] Data processing: Sending messages from the server to the device

[1109] Output: Notification message displayed on the terminal

[1110] Step 8:

[1111] The server generates an optimal food plan based on the health risk assessment results. The content of the food plan is also adjusted according to the user's emotional state. For example, a user who is feeling nervous may receive specific suggestions such as "Try high-fiber foods."

[1112] Input: Health risk assessment results, user emotional state

[1113] Data processing: Food plan generation and adjustment

[1114] Output: Adjusted food plan

[1115] Step 9:

[1116] The server sends a notification message containing the food plan proposal to the terminal. This notification message provides the user with the most suitable food plan information and serves as a reference for implementation.

[1117] Input: Adjusted Food Plan

[1118] Data processing: Sending messages from the server to the device

[1119] Output: Food plan notification displayed on device

[1120] Step 10:

[1121] The server generates graphs and charts based on past and current data to visually display the pet's health status. These graphs and charts are designed with the user's emotional state in mind and are presented in an easy-to-read format.

[1122] Input: Historical and current data

[1123] Data processing: generating graphs and charts, adjusting design based on emotional state

[1124] Output: Visualized health care data

[1125] Step 11:

[1126] The server will then coordinate with hospitals as necessary based on the health risk assessment results. For example, if the user is assessed as having a high risk of arthritis, the server will notify the user of a list of nearby affiliated hospitals. It will also send data to specific hospitals so that the user can receive appropriate medical services.

[1127] Input: Health risk assessment results

[1128] Data processing: Generating hospital linkage information and sending necessary data

[1129] Output: Linkage information and data transmission to hospital

[1130] (Application example 2)

[1131] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1132] Conventional pet health management systems provide advice and food plan recommendations based on the pet's health condition in a one-way manner, without taking into account the owner's emotional state. As a result, even if the information the owner receives is appropriate, it can cause stress and anxiety in the owner, potentially reducing their motivation to maintain their pet's health. Furthermore, it is difficult to provide real-time advice tailored to each individual owner and pet in a physical store, making it difficult to provide a personalized service.

[1133] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for receiving a pet image, means for analyzing the received image to identify the pet's type, means for extracting health risk data based on the analyzed pet's type, means for inputting basic information about the pet, means for generating excretion status and health risk data based on the basic information and the health risk data, means for generating and transmitting a notification message based on the generated data, means for acquiring the owner's emotional state, and means for adjusting the content of the notification message based on the owner's emotional state. This enables personalized notification messages and food plans to be proposed taking the owner's emotional state into consideration. Furthermore, by using the health management system in physical stores, appropriate and flexible services can be provided to owners and pets on-site.

[1134] The "means for receiving pet images" refers to a device or software component for acquiring photographs or video data of a pet and inputting it into the system.

[1135] The "means for identifying the type of pet" is an algorithm or system that analyzes the received image data and identifies the type of pet (for example, dog, cat, breed, etc.).

[1136] A "means for extracting health risk data" is a process or system that identifies potential health risks for pets based on the type of pet and basic information about the pet, and extracts that data.

[1137] "Means for inputting basic information about pets" refers to an interface or component that allows owners to input information about their pets (age, weight, walking time, etc.).

[1138] "Means for generating data on excretion status and health risks" refers to a system or process that creates data on pet excretion status and health risks based on basic information about the pet and analysis results.

[1139] The "means for generating and transmitting notification messages" is a mechanism for creating and transmitting messages to notify owners of advice and information based on the generated data.

[1140] "Means for acquiring the owner's emotional state" refers to devices or software that analyze and determine the owner's emotional state from their facial expressions and input information.

[1141] The "means for adjusting the content of the notification message based on the emotional state of the owner" refers to an algorithm or system for appropriately adjusting the expression and content of the notification message, taking into account the emotional state of the owner.

[1142] The "means for generating and proposing a food plan" is a system for creating an appropriate meal plan based on the results of a health risk assessment and proposing it to the owner.

[1143] The "means for adjusting the contents of the food plan" refers to a system that allows the specific contents of the proposed meal plan to be flexibly changed based on the owner's emotional state and the pet's health condition.

[1144] "Means for visualization using graphs and charts" refers to a system that generates graphs and charts to visually display pet health data in an easy-to-understand manner.

[1145] The "means for adjusting the display format" is an algorithm or system that changes the display format of graphs and charts based on the owner's emotional state to make them easier to understand.

[1146] The system for implementing this invention manages the health status of pets and proposes notification messages and food plans that take the user's emotional state into account. The system consists of a smartphone app, a central server, an analytical AI model, and an emotion engine.

[1147] Hardware and software used

[1148] Hardware: Smartphones, tablets, digital signage

[1149] Software: Android / iOS applications, central server, image analysis AI models (e.g., TensorFlow-based models), emotion recognition libraries (e.g., Microsoft Azure Face API, Google Cloud Vision API)

[1150] Specific processing of the system

[1151] 1. Data Entry

[1152] The user uses a smartphone app to take pictures of their pet's feces and the pet itself and upload them to the app. In addition, the user enters basic information about the pet (age, weight, walking time, etc.). The app also activates a facial recognition camera to capture the user's emotional state and records the user's current emotional state.

[1153] 2. Data Transmission

[1154] The smartphone assembles the collected data (two images, basic information, and emotion data) into a single packet and sends it to a central server as an HTTP POST request.

[1155] 3. AI analysis

[1156] The central server sends the received data to an AI model for analysis. First, the image analysis AI analyzes the pet's image to identify its species. Then, the basic information analysis model analyzes data such as age, weight, and walking time to generate health risk data. Furthermore, the emotion engine analyzes the user's emotional state and prepares to provide advice based on that emotional state.

[1157] 4. Health Risk Assessment and Notification

[1158] The central server integrates the image analysis results with the basic information analysis results to assess the overall health risk, and generates notification messages based on the assessed health risk data, adjusting the content according to the user's emotional state.

[1159] 5. Food plan suggestions

[1160] The central server generates an optimal diet plan based on the health risk assessment results and proposes it to the user, and the proposal is also adjusted taking into account the user's emotional state.

[1161] 6. Notifications and Reporting

[1162] The central server generates a report containing notification messages and recommended food plans and sends it to the smartphone, which reflects the user's emotional state and is presented in an easy-to-understand format.

[1163] 7. Data Visualization

[1164] The central server generates graphs and charts based on past and current data to visually display the pet's health status, and these visualizations are also configured taking into account the user's emotional state.

[1165] 8. In-store use

[1166] In-store use tablet devices and digital signage to provide real-time advice tailored to pet owners and their pets, and the system will be used as a support tool to help store staff explain things to pet owners more effectively.

[1167] Examples of concrete examples and prompts

[1168] For example, if the owner is feeling stressed, the notification message will be tailored to reassure the owner.

[1169] Example prompt for generative AI model:

[1170] Use the following data to analyze your pet's health and your emotional state and suggest an appropriate food plan.

[1171] Pet image (jpg)

[1172] Pet's age: 5 years

[1173] Pet weight: 20kg

[1174] Walking time: 30 minutes

[1175] Owner's emotion image (jpg)

[1176] A word of caution: If the owner is stressed, offer reassuring suggestions.

[1177] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1178] Step 1:

[1179] The user uses a smartphone app to take pictures of their pet's waste and the pet itself, and uploads them to the app. The input data here is the pet's image, basic information (age, weight, walking time, etc.), and a face image of the owner. The app then assembles this data into a single packet.

[1180] Step 2:

[1181] The device sends the combined data packet (two images, basic information, and emotion data) to the central server as an HTTP POST request. This transmission process takes place over the Internet, and the data arrives at the server.

[1182] Step 3:

[1183] The server sends the received data to an AI model for analysis. First, the image analysis AI analyzes the input data (images of pets) and identifies the pet's type. Specifically, the input image is passed to a TensorFlow-based image analysis model, which extracts the pet's type data as output.

[1184] Step 4:

[1185] The server uses a basic information analysis model to analyze basic information entered by the user (such as age, weight, and walking time). It then generates health risk data based on the input information. This analysis produces output data such as obesity risk and arthritis risk.

[1186] Step 5:

[1187] The server uses an emotion engine to analyze the user's emotion data. Specifically, it uses emotion recognition libraries such as Microsoft Azure Face API or Google Cloud Vision API to identify the user's emotional state from the user's facial image. The output of this step is the user's emotional state data.

[1188] Step 6:

[1189] The server integrates the results of image analysis, basic information analysis, and emotion analysis to assess the overall health risk. Based on the assessed health risk data, it generates a notification message. The content of this notification message is tailored according to the user's emotional state. The output is a personalized notification message.

[1190] Step 7:

[1191] The server generates and suggests an optimal food plan based on the health risk assessment results. The suggested food plan is also tailored to take into account the user's emotional state, for example by including reassuring messages. The output of this step is the tailored food plan.

[1192] Step 8:

[1193] The server generates a report containing a notification message and a food plan and sends it to the device. The report is then provided to the user, and its content reflects the user's emotional state. The output is a detailed report displayed on the smartphone.

[1194] Step 9:

[1195] The server generates graphs and charts based on past and current data to visually display the pet's health status. These graphs and charts are constructed taking into account the user's emotional state and are presented in an easy-to-understand format. The output is data in a visually easy-to-understand format.

[1196] Step 10:

[1197] In the physical store, tablet devices and digital signage display appropriate advice based on the data sent from the server. Store staff refer to this data and provide detailed explanations to pet owners. This enables flexible and effective on-site service provision. The output is customized advice provided in real time.

[1198] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[1199] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1200] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314.

[1201] [Fourth embodiment]

[1202] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1203] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[1204] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1205] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[1206] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[1207] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[1208] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1209] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[1210] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1211] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[1212] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1213] In the robot 414, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1214] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1215] The system of the present invention is designed to effectively manage the health of pets and is configured as follows. The main components are a smartphone app used by the user, a central server, and an analytical AI model. The specific functions and operations of the system are described in detail below.

[1216] Data Entry

[1217] Users use a smartphone app to take photos of their pet's excrement and the pet itself, and then upload them to the app. For example, a user can take a photo of their pet's excrement after a morning walk, then take a photo of their pet's face and upload it to the app. At this time, the user also enters basic information about the pet (age, weight, walking time, etc.). This allows users to easily record the health status of their pet.

[1218] Data transmission

[1219] The device collects the data entered by the user into a single packet and sends it to the central server. Specifically, the device generates a data packet that combines two photos and text data (age, weight, and walking time) and sends it to the server as an HTTP POST request.

[1220] AI analysis

[1221] The server sends the received data to an AI model for analysis. First, the image analysis AI analyzes the received image data to identify the type of pet. In this case, the image analysis AI recognizes specific breeds such as "Shiba Inu." Next, the basic information analysis model analyzes the input data, such as age, weight, and walking time, and generates health risk data. This results in an assessment such as "high risk of obesity" or "medium risk of arthritis."

[1222] Health Risk Assessment

[1223] The server integrates these analysis results to assess overall health risk. Specifically, it integrates information on "mild obesity" and "arthritis risk" to perform a comprehensive risk assessment. It then generates a notification message based on the health risk and sends it to the user. For example, a notification might say, "Obesity has been detected. We recommend high-fiber foods. We also suggest supplements that are good for joint health."

[1224] Food plan proposal

[1225] The server generates an optimal food plan based on the health risk assessment results for the user's pet. For example, it lists and suggests "high-fiber foods" and "joint support supplements." This allows users to accurately manage their pet's nutrition.

[1226] Notifications and Reporting

[1227] The server then sends notification messages and reports to the user. The notification messages include information about the analysis results and recommended feeding plans. Additionally, the server generates graphs and charts based on past and current data, allowing the user to visually understand their pet's health status. For example, graphs can be displayed showing weight changes and health risk trends.

[1228] Hospital collaboration

[1229] The server will then connect with hospitals as needed based on the health risk assessment results. For example, if the user is assessed as having a high risk of arthritis, the server will notify the user of a list of nearby affiliated hospitals. It will also send data to hospitals as needed to ensure the user receives appropriate medical services.

[1230] As described above, the system of the present invention aims to comprehensively manage the health status of pets and support early detection and treatment, thereby reducing the burden on owners and contributing to the health and longevity of pets.

[1231] The processing flow will be explained below.

[1232] Step 1:

[1233] The user launches the smartphone app. Using the app's built-in camera function, the user takes a photo of their pet's excrement, then a photo of their pet's face. Each photo is then uploaded to the app. The user also enters basic information about their pet (age, weight, walking time, etc.).

[1234] For example, a user taps the app's "upload image" button, takes a photo of the pet's excrement, then takes a photo of the pet's face, and uploads both to the app.

[1235] Step 2:

[1236] The device collects the data entered by the user (two images and basic information) into a single packet. After generating the data packet, the device sends an HTTP POST request to the central server.

[1237] As a specific example, a terminal generates a JSON-formatted data packet that combines image data and text data, and executes a request called "POST / analyze HTTP / 1.1."

[1238] Step 3:

[1239] The server processes the data received from the device and sends it to an AI model for analysis. First, the server uses image analysis AI to analyze the received pet image and identify the pet's type. In this process, the image analysis AI recognizes specific dog or cat breeds, such as "Shiba Inu." Next, the server uses a basic information analysis model to analyze the input data, such as age, weight, and walking time, and generates health risk data.

[1240] As a specific example, an image analysis AI may determine that "this image is of a Shiba Inu," and a basic information analysis model may assess the animal as "high risk of obesity" and "medium risk of arthritis."

[1241] Step 4:

[1242] The server integrates the image analysis results with the basic information analysis results to assess the overall health risk, and then generates a notification message based on the assessment results and sends it to the user.

[1243] As a specific example, the server integrates data such as "mild obesity" and "risk of arthritis" and generates a notification message saying, "Obesity has been detected. We recommend high-fiber foods. We also suggest supplements that are good for joint health."

[1244] Step 5:

[1245] Based on the health risk assessment results, the server generates an optimal food plan for the user's pet, which may include high-fiber foods and joint support supplements.

[1246] As a specific example, the server lists specific suggestions such as "recommended food: high fiber food" and "recommended supplement: joint support supplement."

[1247] Step 6:

[1248] The server generates a report containing notification messages and a recommended food plan and sends it to the device, where the user can check the received report in the app.

[1249] As a specific example, the server generates a detailed food plan report and sends it to the device along with the message, "Please check the latest analysis results. Obesity has been detected. Try the food plan below."

[1250] Step 7:

[1251] The server generates graphs and charts based on past and current data, visually displaying the pet's health status, which the user can view within the app.

[1252] As a specific example, graphs showing changes in weight and health risks are generated and displayed within the app.

[1253] Step 8:

[1254] If necessary, the server will connect with hospitals based on the health risk assessment results and notify the user of a list of nearby affiliated hospitals, enabling them to receive appropriate medical services.

[1255] As a specific example, a notification message saying "You are at high risk of developing arthritis. Please consult the affiliated hospital below" is sent along with the contact information of the affiliated hospital.

[1256] The above is a specific processing flow of the pet health management system, which allows users to effectively manage the health of their pets.

[1257] Example 1

[1258] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1259] Today, many pets suffer from various health problems due to inadequate health management by their owners. For example, it is difficult to determine the appropriate amount of food and exercise, which can result in problems such as obesity and arthritis. However, there is no easy-to-use system for monitoring pet health on a daily basis and taking appropriate measures. For this reason, there is a need for the development of a system that assesses health risks based on pet photos and basic information and proposes an appropriate food plan.

[1260] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1261] In this invention, the server includes a means for receiving images of the pet from the terminal used by the user, a means for collecting the received images and basic information of the pet into a single data packet and transmitting it, and a means for providing the data packet to an AI model that analyzes the data packet in the central server. This makes it possible to evaluate health risks based on the received image analysis results and the basic information of the pet, and to generate notification messages, propose optimal food plans, and even generate graphs and charts based on past data.

[1262] "User" refers to a person who uses the system.

[1263] "Terminal" refers to an electronic device used by a user, such as a personal digital assistant or computer.

[1264] "Central Server" refers to a central computer system that receives, analyzes, and stores data.

[1265] "Image analysis AI" refers to an artificial intelligence model that analyzes received image data and extracts specific information.

[1266] "Basic information" refers to basic data about your pet, such as age, weight, and walking time.

[1267] "Health risk data" refers to assessment data regarding the health status of pets obtained from the analysis results.

[1268] "Data packet" refers to a unit of information that contains image data and basic information packaged for transmission.

[1269] "Notification message" refers to an information message sent to the user based on the analysis results.

[1270] "Food Plan" refers to a suggested dietary plan for your pet based on health risk data.

[1271] "Graphs and charts" refer to diagrams that visually display changes in a pet's physical condition or symptoms.

[1272] MODE FOR CARRYING OUT THE INVENTION

[1273] The system of the present invention is designed to effectively manage the health of pets, and is composed of a terminal used by the user (e.g., a smartphone), a central server, and an analytical AI model.

[1274] Data entry and submission

[1275] Users can use a smartphone app to take photos of their pet's feces and face and upload them within the app. For example, a user can take photos of their pet's feces and face after a morning walk and upload the photos. At this time, users also enter basic information about their pet (age, weight, walking time, etc.) into the app. This basic information can be easily added through a text input form.

[1276] The device (smartphone) combines the data entered by the user (two photos and text data) into a single data packet and sends it to the central server as an HTTP POST request.

[1277] Data analysis and health risk assessment

[1278] The server sends the received data packets to an AI model for analysis. First, an image analysis AI (for example, a TensorFlow model) analyzes the received image data and identifies the type of pet. For example, it might identify the image as a "Shiba Inu." Next, a basic information analysis model analyzes the input data, such as age, weight, and walking time, to generate health risk data. This results in an assessment such as "high risk of obesity" or "medium risk of arthritis."

[1279] The server integrates the analysis results and evaluates the overall health risk. Specifically, it integrates "mild obesity" and "arthritis risk" to perform a comprehensive risk assessment. It then generates a notification message based on the assessment results and sends it to the user. For example, a notification may be generated that reads, "Obesity has been detected. We recommend high-fiber foods. We also suggest supplements that are good for joint health."

[1280] Food plan proposal

[1281] The server generates an optimal food plan based on the health risk assessment results. For example, it retrieves information on "high-fiber foods" and "joint support supplements" from the database, lists them, and suggests them to the user. This suggestion is sent to the user's smartphone as a push notification.

[1282] Notifications and Reporting

[1283] The server generates graphs and charts based on past and latest data along with notification messages and sends them to the user, allowing the user to visually understand the health status of their pet. For example, graphs showing changes in weight and health risks are displayed.

[1284] Hospital collaboration

[1285] The server will then connect with hospitals as needed based on the health risk assessment results. For example, if the user is assessed as having a high risk of arthritis, the server will notify the user of a list of nearby affiliated hospitals. Based on this information, the user can receive appropriate medical services. If necessary, the server will securely transmit data to the hospital.

[1286] Examples and prompts

[1287] Examples:

[1288] After a morning walk, users take photos of their pet's feces and face, and upload them to a smartphone app. They then enter information such as age (3 years), weight (10 kg), and walk time (30 minutes).

[1289] You will receive a notification message saying, "Obesity detected. We recommend high-fiber foods. We also suggest supplements for joint health."

[1290] Check for recommended "high fiber foods" and "joint support supplements."

[1291] Example prompt sentence:

[1292] "Users take photos of their pet's feces and face after their morning walk and upload them through a smartphone app. They also enter their age, weight, and walking time."

[1293] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1294] Step 1:

[1295] The user uses a smartphone app to take photos of their pet's excrement and face, and uploads them within the app. The input is a photo of the pet's excrement, a photo of the face, and basic information (age, weight, walking time). The output is a set of the uploaded photo and the input text data. Specifically, the user takes a photo using the app's camera function, and then enters information such as "3 years old," "10 kg," and "30 minutes" into the input form.

[1296] Step 2:

[1297] The device combines the data entered by the user (two photos and text data) into a single data packet and sends it to the central server as an HTTP POST request. The input is the data uploaded by the user from the app, and the output is the data packet sent as an HTTP POST request. Specifically, the smartphone app generates the data packet in the background and sends an HTTP request to the specified server URL.

[1298] Step 3:

[1299] The server provides the received data packets to the AI ​​model for analysis. The input is the data packet sent from the device, and the output is the data passed to the AI ​​model for analysis. Specifically, the server converts the received data into an analytical format and passes it to the image analysis AI and basic information analysis model.

[1300] Step 4:

[1301] The server uses image analysis AI to analyze the received image data and identify the type of pet. The input is the image data in the data packet, and the output is the identification result of the pet type. For example, the image is analyzed and identified as a "Shiba Inu." The specific operation is to execute image analysis AI (for example, a TensorFlow model).

[1302] Step 5:

[1303] The server uses a basic information analysis model to analyze the input text data and generate health risk data. The input is the age, weight, and walking time data in the data packet, and the output is health risk data. Specifically, the basic information analysis model generates an assessment such as "high risk of obesity" or "medium risk of arthritis."

[1304] Step 6:

[1305] The server integrates the analysis results and performs an overall health risk assessment. The input is the image analysis results and basic information analysis results, and the output is the integrated health risk assessment results. Specifically, a Python script integrates "mild obesity" and "arthritis risk."

[1306] Step 7:

[1307] The server generates a notification message based on the assessment results and sends it to the user. The input is the health risk assessment result, and the output is the generated notification message. Specifically, the Python script generates a message saying, "Obesity has been detected. High-fiber foods are recommended. Supplements that are good for joint health are also suggested." and sends a push notification.

[1308] Step 8:

[1309] The server generates and proposes an optimal food plan based on the health risk assessment results. The input is the health risk assessment results, and the output is a recommended food plan. Specifically, it retrieves information on "high fiber foods" and "joint support supplements" from the database and creates a list.

[1310] Step 9:

[1311] The server generates graphs and charts based on past and latest data along with notification messages and sends them to the user. The input is past and latest data, and the output is the generated graphs and charts. Specifically, the graphs are generated using libraries such as Matplotlib and Seaborn and displayed in the app.

[1312] Step 10:

[1313] The server will communicate with hospitals as needed based on the health risk assessment results. The input is the health risk assessment results, and the output is a list of affiliated hospitals and the transmission of necessary medical data. Specifically, if the user is assessed as having a "high risk of arthritis," the server retrieves a list of nearby affiliated hospitals from the database and notifies the user. It also executes an API to securely send data to hospitals as needed.

[1314] (Application example 1)

[1315] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1316] Existing methods for managing pet health make it difficult for owners to accurately record their pet's waste and physical condition and take appropriate health measures. It is also time-consuming to select food and suggest supplements based on the pet's health condition. Furthermore, there is a lack of integration with food delivery services that address pet health risks. Therefore, there is a need for a system that provides comprehensive and efficient pet health management.

[1317] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1318] In this invention, the server includes means for receiving images of the pet, means for analyzing the received images to identify the type of pet, means for extracting health risk data based on the analyzed type of pet, means for inputting basic information about the pet, means for generating excretion status and health risk data based on the basic information and the health risk data, means for generating and sending a notification message based on the generated data, and means for generating a food plan based on the health risks and linking with a food delivery service, thereby enabling comprehensive and efficient management of the pet's health status and the recommendation and delivery of appropriate food and supplements.

[1319] The "means for receiving pet images" is a device or system that allows a user to send images of a pet taken using a smartphone or camera to a server.

[1320] "Means for analyzing the received image and identifying the type of pet" refers to a device or system that includes an algorithm or software for identifying the type or breed of pet by analyzing the received image data.

[1321] The "means for extracting health risk data" is a device or system for extracting health risk data related to pets based on the type and basic information of the pets.

[1322] The "means for inputting basic information about a pet" refers to a device or system that allows a user to input basic information about a pet, such as age, weight, and walking time.

[1323] The "means for generating data on excretion status and health risks" refers to a device or system for generating information on a pet's excretion status and health risks based on basic information about the pet and analyzed health risk data.

[1324] "Means for generating and transmitting notification messages" refers to a device or system for creating and transmitting notification messages to users on smartphones or other devices based on the generated health risk data.

[1325] "Means for generating food plans and linking with food delivery services" refers to a device or system for creating an appropriate food plan based on the results of a pet's health risk assessment and providing the selected food and supplements in collaboration with a food delivery service.

[1326] "Means for recording changes in a pet's physical condition and symptoms and visualizing them in graphs and charts" refers to a device or system that records changes in a pet's physical condition and symptoms as data, converts that data into graphs and charts, and visually displays them to the user.

[1327] This invention is a system for effectively managing the health of pets, and is composed of the following main components: a smartphone app used by the user, a central server, and an analytical AI model.

[1328] Data Entry

[1329] Users use a smartphone app to take pictures of their pet's feces and the pet itself, and upload them to the app. At the same time, users can also enter basic information about their pet (age, weight, walking time, etc.).

[1330] Data transmission

[1331] The device collects the data entered by the user into a single packet and sends it to the central server. Specifically, the device generates a data packet that combines two photos and text data (age, weight, and walking time) and sends it to the server as an HTTP POST request.

[1332] AI analysis

[1333] The server sends the received data to an AI model for analysis. The image analysis AI analyzes the received image data and identifies the type of pet. The basic information analysis model analyzes the input data, such as age, weight, and walking time, and generates health risk data. For example, it can provide assessment results such as "high risk of obesity" or "medium risk of arthritis."

[1334] Health Risk Assessment

[1335] The server integrates these analysis results and evaluates the overall health risk. Based on the evaluation, it generates a notification message according to the health risk and sends it to the user.

[1336] Food plan proposal

[1337] The server generates an optimal food plan based on the health risk assessment results for the user's pet. For example, the server lists and recommends "high-fiber foods" and "joint support supplements" to the user. The system works in conjunction with a food delivery service to deliver the selected foods and supplements to the user.

[1338] Notifications and Reporting

[1339] The server sends notification messages and reports to the user, including analysis results and recommended feeding plans. The server generates graphs and charts based on past and current data, allowing the user to visually understand the health status of their pet.

[1340] Hardware and Software Used

[1341] Smartphone (for users to take pictures and enter data)

[1342] Central server (for data analysis and results transmission)

[1343] AI model (using Python libraries such as PIL and requests for image analysis and basic information analysis)

[1344] FastAPI (for server-side APIs)

[1345] Processing examples and prompt statements

[1346] For example, a user can take photos of their dog's excrement and face with their smartphone and upload them to the app. This data is then analyzed on a central server and classified as "Shiba Inu," "high risk of obesity," or "medium risk of arthritis." The app then recommends "high-fiber food" and "joint support supplements" to the user, who can then purchase them and use the food delivery service.

[1347] Example prompt sentence:

[1348] Take photos of your dog's feces and face, and enter your pet's age, weight, and walking time. Based on that data, we will provide you with an appropriate health risk assessment and food plan suggestions.

[1349] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1350] Step 1:

[1351] Users use a smartphone app to take photos of their pet's feces and face, upload them to the app, and then enter basic information about their pet (age, weight, walking time).

[1352] Input: Photo of pet's waste, face photo, age, weight, walking time

[1353] Output: Image data, basic information data

[1354] What happens: A user opens the app, takes a photo using the camera, fills in basic information in a form, and presses the submit button.

[1355] Step 2:

[1356] The device collects the data received from the user into a single data packet and sends it to the central server using an HTTP POST request.

[1357] Input: Image data, basic information data

[1358] Output: HTTP POST request to the server

[1359] Specific operation: The smartphone app packs two photos and text data into a packet and sends it to the server's API endpoint.

[1360] Step 3:

[1361] The server sends the received data to an AI model for analysis. The image analysis AI analyzes the received image data and identifies the type of pet.

[1362] Input: Data packet (image data, basic information data)

[1363] Output: Pet type (e.g. Shiba Inu)

[1364] Specific operation: After receiving the data, the server passes the image data to the AI ​​model, which performs image analysis and obtains the pet's type as a result.

[1365] Step 4:

[1366] The server uses a basic information analysis model to analyze the entered age, weight, and walking time, and generates health risk data.

[1367] Input: Age, weight, walking time

[1368] Output: Health risk data (e.g., high risk of obesity, medium risk of arthritis)

[1369] Specific operation: The server passes basic information to the analysis model, performs data calculations, and generates health risk data.

[1370] Step 5:

[1371] The server aggregates the analysis results, assesses the overall health risk, and generates notification messages based on the assessment.

[1372] Input: Pet type, health risk data

[1373] Output: Health risk assessment results, notification message

[1374] Specific operation: The server integrates pet type and health risk data, uses AI models to assess the overall health risk, and generates a notification message.

[1375] Step 6:

[1376] The server generates an optimal food plan based on the health risk assessment results and proposes it to the user. It also works with food delivery services to deliver food to the user.

[1377] Input: Health risk assessment results

[1378] Output: Food plan, food delivery request

[1379] What it does: The server uses the AI ​​model to generate an appropriate food plan and sends a delivery request using the food delivery service's API.

[1380] Step 7:

[1381] The server sends notification messages and reports to the user. The server displays a message to the user containing information about the analysis results and recommended food plan.

[1382] Input: Health risk assessment results, food plan

[1383] Output: Notification messages, reports

[1384] Specific operation: The server generates notification messages and reports based on the analysis results and food plans, and sends them to a smartphone app, where users can view them.

[1385] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1386] The system of the present invention is for managing the health of pets and incorporates an emotion engine that provides notification messages and suggests food plans that take into account the user's emotional state. The system consists of a smartphone app, a central server, an analytical AI model, and an emotion engine.

[1387] Data Entry

[1388] A user uses a smartphone app to take photos of their pet's excrement and the pet itself, and uploads them to the app. At this time, the user enters basic information about the pet (age, weight, walking time, etc.). For example, a user might take a photo of their pet's excrement after a morning walk, then take a photo of the pet's face and upload it to the app. In addition, an emotion recognition function is activated within the app to capture the user's emotional state and record the user's current emotional state.

[1389] Data transmission

[1390] The device collects the data input by the user (two images, basic information, and emotion data) into a single packet and sends it to the central server. Specifically, the device generates a data packet that combines image data and text data (age, weight, walking time, and the user's emotional state) and sends it to the server as an HTTP POST request.

[1391] AI analysis

[1392] The server sends the received data to an AI model for analysis. First, the image analysis AI analyzes the pet's image and identifies the pet's type (e.g., "Shiba Inu"). Next, the basic information analysis model analyzes data such as age, weight, and walking time to generate health risk data (e.g., "high risk of obesity" or "medium risk of arthritis"). Furthermore, the emotion engine analyzes the user's emotional state and prepares to provide advice based on that emotional state.

[1393] Health Risk Assessment

[1394] The server combines the results of image analysis and basic information analysis to assess overall health risk. It also generates notification messages based on the assessed health risk data and adjusts the content according to the user's emotional state. For example, if the user appears anxious, it will send a message that reassures them, such as, "Obesity has been detected, but please rest assured that there are measures in place. We recommend high-fiber foods."

[1395] Food plan proposal

[1396] The server generates an optimal food plan based on the health risk assessment results and proposes it to the user. The content of the food plan proposal is also adjusted taking into account the user's emotional state. For example, if the user is in a state of high interest, the server will proactively suggest, "Why not try high-fiber foods? We also have joint support supplements."

[1397] Notifications and Reporting

[1398] The server generates a report containing a notification message and a recommended food plan and sends it to the device. The report reflects the user's emotional state and is presented in a format that is easy for the user to understand. For example, a notification message may be generated that reads, "Please check the latest analysis results. We have prepared a food plan that you can follow with confidence."

[1399] Graph and chart generation

[1400] The server generates graphs and charts based on past and recent data to visually display the pet's health status. These visualized data are also configured taking into account the user's emotional state. For example, if the user is feeling nervous, the data will be displayed in a simple design with easy-to-read colors that give a sense of security.

[1401] Hospital collaboration

[1402] The server will then connect with hospitals as needed based on the health risk assessment results. For example, if the user is assessed as having a high risk of arthritis, the server will send a message based on the user's emotional state, providing a list of nearby affiliated hospitals. If necessary, the server will also send data to hospitals to ensure the user receives appropriate medical services.

[1403] As described above, the system of the present invention comprehensively manages the health condition of pets and takes into account the emotional state of the user to provide more effective support, thereby reducing the burden on owners and contributing to the health and longevity of pets.

[1404] The processing flow will be explained below.

[1405] Step 1:

[1406] The user launches the smartphone app. They take photos of their pet's excrement and face and upload them within the app. They also enter basic information about their pet (age, weight, walking time, etc.). Taking a photo of the user's facial expression triggers the emotion engine to recognize the user's emotions.

[1407] For example, after a morning walk, a user takes a photo of their pet's excrement, then takes a photo of their pet's face, and uploads both to the app. The app then captures the user's current facial expression and obtains emotional data.

[1408] Step 2:

[1409] The device collects the data input by the user (two images, basic information, and emotion data) into a single packet and sends it to the central server. The data packet contains image data, text data (age, weight, walking time), and emotion data obtained by the emotion engine.

[1410] As a specific example, the device generates a JSON-formatted data packet that includes an image, basic information, and emotion data, and executes "POST / analyze HTTP / 1.1."

[1411] Step 3:

[1412] The server starts the process of sending the received data to an AI model for analysis. First, the image analysis AI analyzes the pet's image and identifies the pet's species. Next, the basic information analysis model analyzes the input data and generates health risk data. Finally, the emotion engine analyzes the user's emotion data.

[1413] For example, the image analysis AI identifies the dog as a "Shiba Inu," and the basic information analysis model evaluates it as "high risk of obesity" and "medium risk of arthritis." The emotion engine recognizes the user's emotion as "anxiety."

[1414] Step 4:

[1415] The server integrates the results of image analysis, basic information analysis, and the emotion engine to assess the overall health risk, and generates a notification message based on the assessment results, tailoring the message content to the user's emotional state.

[1416] As a specific example, the server combines "mild obesity" and "arthritis risk" and generates a notification message saying, "Obesity has been detected, but there are measures you can take. We recommend high-fiber foods."

[1417] Step 5:

[1418] The server generates an optimal food plan based on the health risk assessment results and proposes it to the user. The generated food plan is also adjusted according to the user's emotional state.

[1419] As a concrete example, if the emotion engine recognizes that the user's emotion is "curious," it will make a proactive suggestion such as, "Why not try some high-fiber foods? We also recommend some joint support supplements."

[1420] Step 6:

[1421] The server generates a report containing notification messages and recommended food plans and sends it to the device, where the user can check the report and understand the health status of their pet.

[1422] As a specific example, the server sends a message saying, "Please check the latest analysis results. We have prepared a food plan that you can follow with confidence," and attaches a detailed food plan report.

[1423] Step 7:

[1424] The server generates graphs and charts based on past and current data to visually display the pet's health status, and these graphs and charts are also displayed in a way that reflects the user's emotional state.

[1425] As a specific example, a graph showing changes in weight and health risks is generated, and if the user is feeling "tense," it is displayed in a color that is easy to see and gives a sense of security.

[1426] Step 8:

[1427] If necessary, the server will connect with hospitals based on the health risk assessment results. The emotion engine will notify the user of a list of nearby affiliated hospitals via a message based on the user's emotional state. It will also send relevant data to the hospitals as needed.

[1428] As a specific example, a notification message stating, "You are at high risk of arthritis. Rest assured, you can consult with the affiliated hospitals listed below," along with contact information for the affiliated hospitals, may be sent.

[1429] The above is a specific processing flow for incorporating an emotion engine into a pet health management system, and this system enables better health management for both users and pets.

[1430] Example 2

[1431] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1432] Conventional pet health management systems support image analysis and basic information input as a means of monitoring pet health, but do not take into account the user's psychological state. This can cause mental stress when users receive notifications or suggestions from the system. Furthermore, health risk assessments and food plan suggestions are uniform, lacking flexibility to respond to the user's emotional state. There is a need to improve this and provide more user-friendly support.

[1433] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1434] In this invention, the server includes means for receiving an image of the pet, means for analyzing the received image and identifying the type of pet, means for extracting health risk data based on the analyzed type of pet, means for inputting basic information about the pet, means for generating excretion status and health risk data based on the basic information and the health risk data, means for generating and sending a notification message based on the generated data, means for acquiring and analyzing the user's emotional state, means for adjusting the content of the notification message based on the emotional state, means for generating and proposing an optimal food plan based on the health risk assessment results, means for adjusting the content of the proposed food plan based on the user's emotional state, means for recording changes in the pet's physical condition and symptoms and visualizing them in graphs or charts, and means for configuring the visualized data according to the user's emotional state.

[1435] This makes it possible to provide appropriate support that is in line with the user's emotional state. Specifically, it is possible to provide notification messages and food plan suggestions that take the user's emotional state into account, as well as visualize the pet's health status, thereby reducing the burden on the user and achieving better health management for their pet.

[1436] The "means for receiving pet images" is a method for importing pet image data taken using a smartphone or camera into an application or server.

[1437] "Means for analyzing images and identifying the type of pet" refers to a method of identifying the type of pet (such as dog breed or cat breed) based on the received image using image recognition technology such as deep learning.

[1438] The "means for extracting health risk data" refers to a method for deriving the relevant health risks based on the identified pet species, with reference to statistical data and medical data.

[1439] "Means for inputting basic information" refers to a method by which a user inputs basic information such as the pet's age, weight, and walking time via a smartphone, computer, etc.

[1440] The "means for generating excretion status and health risk data" is a method for calculating a pet's excretion status and overall health risk based on basic information input by the user and analyzed health risk data.

[1441] The "means for generating and transmitting a notification message" is a method for generating an appropriate notification message for the user based on the generated health risk data and excretion status, and transmitting the message to a designated terminal.

[1442] "Means for acquiring and analyzing the user's emotional state" refers to a method of detecting the user's current emotional state using a camera or voice analysis function and analyzing it as data.

[1443] The "means for adjusting the content of the notification message based on the emotional state" is a method for optimizing the content of the notification message in accordance with various emotions such as tension and anxiety based on the acquired emotional state of the user.

[1444] "Means for generating and proposing an optimal food plan" is a method for calculating an optimal food plan for the relevant pet based on the health risk assessment results and proposing that plan to the user.

[1445] The "means for adjusting the proposed content based on the user's emotional state" is a method for adjusting the content of the generated food plan in a way that is more effectively accepted by the user in accordance with the user's emotional state.

[1446] "Means for recording changes in physical condition and symptoms and visualizing them in graphs and charts" refers to a method for recording changes in a pet's physical condition and symptoms as time-series data and visually displaying them as graphs and charts.

[1447] "Means for configuring visualized data according to the user's emotional state" refers to a method for adjusting the design and color scheme of generated graphs and charts according to the user's emotional state, and providing them in a format that is easy to read and gives a sense of security.

[1448] The system of the present invention is a system that comprehensively manages the health condition of a pet and proposes notification messages and food plans based on the emotional state of the user. Hereinafter, embodiments of the present invention will be described in detail.

[1449] System Configuration

[1450] The system consists of a smartphone app, a central server, an image analysis AI model, an emotion engine, and a data transmission and reception infrastructure. Users mainly use their smartphones to input their pet's health information, and the central server is responsible for data analysis.

[1451] Data Entry

[1452] Users use a smartphone app to take photos of their pet's excrement and face and upload them to the app. At the same time, they also enter basic information about their pet (such as age, weight, and walking time). In particular, an emotion recognition function is activated within the app and records the user's current emotional state using a camera or voice input. For example, a user can take a photo of their pet's excrement after a morning walk, then take a photo of their pet's face and upload it to the app. The emotion recognition function analyzes the user's facial scan and voice tone to record emotions such as "anxiety" or "excitement."

[1453] Data transmission

[1454] The data collected by the device (two images, basic information about the pet, and the user's emotional data) is compiled into a data packet and sent as an HTTP POST request to the central server. This packet is in JSON format and contains the following example data: "Pet image," "Pet's age: 5 years," "Pet's weight: 10 kg," "Walking time: 30 minutes," and "User's emotion: nervous."

[1455] AI analysis

[1456] The data received by the server is first sent to an image analysis AI model to identify the type of pet. For example, it may be identified as a "Shiba Inu." A basic information analysis model then analyzes data such as age, weight, and walking time to generate health risk data. For example, it may predict a "high risk of obesity" or "medium risk of arthritis." Next, an emotion engine analyzes the user's emotional state and prepares to adjust the content of notification messages and advice.

[1457] Health Risk Assessment and Notification

[1458] The server combines the results of image analysis and basic information analysis to assess overall health risks. Notification messages are generated based on the assessment results, and the content is adjusted according to the user's emotional state. For example, a user who is feeling nervous might receive a message such as, "Obesity has been detected, but please rest assured that we have measures in place." This allows the user to feel reassured and take appropriate measures.

[1459] Food plan proposal

[1460] The server generates an optimal food plan based on the health risk assessment results, making specific suggestions such as "Try high-fiber foods." These suggestions are also adjusted based on the user's emotional state. For example, a proactive suggestion might be "Try high-fiber foods, and there are also joint support supplements."

[1461] Data visualization and hospital collaboration

[1462] The server generates graphs and charts based on past and recent data to visually display the pet's health condition. These visualized data are also displayed in a way that takes the user's emotional state into consideration. For example, if the user is feeling nervous, the system will use colors and a simple design that will give a sense of security. The system will also connect with hospitals as needed based on a health risk assessment to help provide appropriate medical services.

[1463] This system allows for more efficient health management of pets by responding to the user's emotional state, thereby reducing the burden on owners and supporting the longevity and health of pets.

[1464] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1465] Step 1:

[1466] The user uses a smartphone app to take photos of their pet's excrement and face, and uploads them to the app. The user then uses a form within the app to enter basic information about the pet (age, weight, walking time). At this time, the app uses the camera and voice input functions to obtain the user's emotional state using an emotion recognition engine. All entered data is temporarily stored in the smartphone's local storage.

[1467] Input: Pet excrement image, face photo, pet basic information, user emotion data

[1468] Data processing: taking image data, inputting text data, and recognizing emotional data

[1469] Output: Data stored in the smartphone's local storage

[1470] Step 2:

[1471] All data collected by the device (smartphone) (two images, basic information about the pet, and the user's emotional data) is compiled into a single data packet. The data packet is generated in JSON format and sent to the central server as an HTTP POST request.

[1472] Input: Data stored in local storage

[1473] Data processing: Generate data packets in JSON format

[1474] Output: HTTP POST request sent to the central server

[1475] Step 3:

[1476] The server receives the data packet sent from the device. The received data packet is first sent to an image analysis AI model, which analyzes the pet image and identifies the pet's type. This uses image recognition technology (e.g., deep learning). The pet's type (e.g., Shiba Inu) is output as the image analysis result.

[1477] Input: Data packets sent from the device

[1478] Data processing: Identifying pet species using image analysis AI models

[1479] Output: Pet type (e.g. Shiba Inu)

[1480] Step 4:

[1481] The server then uses a basic information analysis model to analyze data such as the pet's age, weight, and walking time to extract health risk data. The model evaluates risk by referencing statistical and medical data. For example, it can produce results such as "high risk of obesity" or "medium risk of arthritis."

[1482] Input: Basic information about your pet

[1483] Data processing: Calculation of health risks using basic information analysis models

[1484] Output: Health risk data (e.g., "High risk of obesity," "Medium risk of arthritis")

[1485] Step 5:

[1486] The server uses an emotion engine to analyze the user's emotional state. Emotional data (e.g., facial expressions and vocal tone) are analyzed to identify the user's emotional state (e.g., nervousness, excitement).

[1487] Input: User emotion data

[1488] Data processing: Identifying emotional states with an emotion engine

[1489] Output: User's emotional state (e.g., nervousness)

[1490] Step 6:

[1491] The server combines the results of image analysis and basic information analysis to assess overall health risks. A notification message is generated based on this assessment. The message content is adjusted according to the user's emotional state. For example, for a nervous user, a message such as "Obesity has been detected, but please rest assured that there are measures in place." is generated.

[1492] Input: Image analysis results, basic information analysis results, user emotional state

[1493] Data processing: Integrated assessment of health risks, generation of notification messages

[1494] Output: Adjusted notification message

[1495] Step 7:

[1496] The server then sends the generated notification message to the device (smartphone), which includes the pet's health risk assessment results and information corresponding to the user's emotional state.

[1497] Input: Adjusted notification message

[1498] Data processing: Sending messages from the server to the device

[1499] Output: Notification message displayed on the terminal

[1500] Step 8:

[1501] The server generates an optimal food plan based on the health risk assessment results. The content of the food plan is also adjusted according to the user's emotional state. For example, a user who is feeling nervous may receive specific suggestions such as "Try high-fiber foods."

[1502] Input: Health risk assessment results, user emotional state

[1503] Data processing: Food plan generation and adjustment

[1504] Output: Adjusted food plan

[1505] Step 9:

[1506] The server sends a notification message containing the food plan proposal to the terminal. This notification message provides the user with the most suitable food plan information and serves as a reference for implementation.

[1507] Input: Adjusted Food Plan

[1508] Data processing: Sending messages from the server to the device

[1509] Output: Food plan notification displayed on device

[1510] Step 10:

[1511] The server generates graphs and charts based on past and current data to visually display the pet's health status. These graphs and charts are designed with the user's emotional state in mind and are presented in an easy-to-read format.

[1512] Input: Historical and current data

[1513] Data processing: generating graphs and charts, adjusting design based on emotional state

[1514] Output: Visualized health care data

[1515] Step 11:

[1516] The server will then coordinate with hospitals as necessary based on the health risk assessment results. For example, if the user is assessed as having a high risk of arthritis, the server will notify the user of a list of nearby affiliated hospitals. It will also send data to specific hospitals so that the user can receive appropriate medical services.

[1517] Input: Health risk assessment results

[1518] Data processing: Generating hospital linkage information and sending necessary data

[1519] Output: Linkage information and data transmission to hospital

[1520] (Application example 2)

[1521] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1522] Conventional pet health management systems provide advice and food plan recommendations based on the pet's health condition in a one-way manner, without taking into account the owner's emotional state. As a result, even if the information the owner receives is appropriate, it can cause stress and anxiety in the owner, potentially reducing their motivation to maintain their pet's health. Furthermore, it is difficult to provide real-time advice tailored to each individual owner and pet in a physical store, making it difficult to provide a personalized service.

[1523] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for receiving a pet image, means for analyzing the received image to identify the pet's type, means for extracting health risk data based on the analyzed pet's type, means for inputting basic information about the pet, means for generating excretion status and health risk data based on the basic information and the health risk data, means for generating and transmitting a notification message based on the generated data, means for acquiring the owner's emotional state, and means for adjusting the content of the notification message based on the owner's emotional state. This enables personalized notification messages and food plans to be proposed taking the owner's emotional state into consideration. Furthermore, by using the health management system in physical stores, appropriate and flexible services can be provided to owners and pets on-site.

[1524] The "means for receiving pet images" refers to a device or software component for acquiring photographs or video data of a pet and inputting it into the system.

[1525] The "means for identifying the type of pet" is an algorithm or system that analyzes the received image data and identifies the type of pet (for example, dog, cat, breed, etc.).

[1526] A "means for extracting health risk data" is a process or system that identifies potential health risks for pets based on the type of pet and basic information about the pet, and extracts that data.

[1527] "Means for inputting basic information about pets" refers to an interface or component that allows owners to input information about their pets (age, weight, walking time, etc.).

[1528] "Means for generating data on excretion status and health risks" refers to a system or process that creates data on pet excretion status and health risks based on basic information about the pet and analysis results.

[1529] The "means for generating and transmitting notification messages" is a mechanism for creating and transmitting messages to notify owners of advice and information based on the generated data.

[1530] "Means for acquiring the owner's emotional state" refers to devices or software that analyze and determine the owner's emotional state from their facial expressions and input information.

[1531] The "means for adjusting the content of the notification message based on the emotional state of the owner" refers to an algorithm or system for appropriately adjusting the expression and content of the notification message, taking into account the emotional state of the owner.

[1532] The "means for generating and proposing a food plan" is a system for creating an appropriate meal plan based on the results of a health risk assessment and proposing it to the owner.

[1533] The "means for adjusting the contents of the food plan" refers to a system that allows the specific contents of the proposed meal plan to be flexibly changed based on the owner's emotional state and the pet's health condition.

[1534] "Means for visualization using graphs and charts" refers to a system that generates graphs and charts to visually display pet health data in an easy-to-understand manner.

[1535] The "means for adjusting the display format" is an algorithm or system that changes the display format of graphs and charts based on the owner's emotional state to make them easier to understand.

[1536] The system for implementing this invention manages the health status of pets and proposes notification messages and food plans that take the user's emotional state into account. The system consists of a smartphone app, a central server, an analytical AI model, and an emotion engine.

[1537] Hardware and software used

[1538] Hardware: Smartphones, tablets, digital signage

[1539] Software: Android / iOS applications, central server, image analysis AI models (e.g., TensorFlow-based models), emotion recognition libraries (e.g., Microsoft Azure Face API, Google Cloud Vision API)

[1540] Specific processing of the system

[1541] 1. Data Entry

[1542] The user uses a smartphone app to take pictures of their pet's feces and the pet itself and upload them to the app. In addition, the user enters basic information about the pet (age, weight, walking time, etc.). The app also activates a facial recognition camera to capture the user's emotional state and records the user's current emotional state.

[1543] 2. Data Transmission

[1544] The smartphone assembles the collected data (two images, basic information, and emotion data) into a single packet and sends it to a central server as an HTTP POST request.

[1545] 3. AI analysis

[1546] The central server sends the received data to an AI model for analysis. First, the image analysis AI analyzes the pet's image to identify its species. Then, the basic information analysis model analyzes data such as age, weight, and walking time to generate health risk data. Furthermore, the emotion engine analyzes the user's emotional state and prepares to provide advice based on that emotional state.

[1547] 4. Health Risk Assessment and Notification

[1548] The central server integrates the image analysis results with the basic information analysis results to assess the overall health risk, and generates notification messages based on the assessed health risk data, adjusting the content according to the user's emotional state.

[1549] 5. Food plan suggestions

[1550] The central server generates an optimal diet plan based on the health risk assessment results and proposes it to the user, and the proposal is also adjusted taking into account the user's emotional state.

[1551] 6. Notifications and Reporting

[1552] The central server generates a report containing notification messages and recommended food plans and sends it to the smartphone, which reflects the user's emotional state and is presented in an easy-to-understand format.

[1553] 7. Data Visualization

[1554] The central server generates graphs and charts based on past and current data to visually display the pet's health status, and these visualizations are also configured taking into account the user's emotional state.

[1555] 8. In-store use

[1556] In-store use tablet devices and digital signage to provide real-time advice tailored to pet owners and their pets, and the system will be used as a support tool to help store staff explain things to pet owners more effectively.

[1557] Examples of concrete examples and prompts

[1558] For example, if the owner is feeling stressed, the notification message will be tailored to reassure the owner.

[1559] Example prompt for generative AI model:

[1560] Use the following data to analyze your pet's health and your emotional state and suggest an appropriate food plan.

[1561] Pet image (jpg)

[1562] Pet's age: 5 years

[1563] Pet weight: 20kg

[1564] Walking time: 30 minutes

[1565] Owner's emotion image (jpg)

[1566] A word of caution: If the owner is stressed, offer reassuring suggestions.

[1567] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1568] Step 1:

[1569] The user uses a smartphone app to take pictures of their pet's waste and the pet itself, and uploads them to the app. The input data here is the pet's image, basic information (age, weight, walking time, etc.), and a face image of the owner. The app then assembles this data into a single packet.

[1570] Step 2:

[1571] The device sends the combined data packet (two images, basic information, and emotion data) to the central server as an HTTP POST request. This transmission process takes place over the Internet, and the data arrives at the server.

[1572] Step 3:

[1573] The server sends the received data to an AI model for analysis. First, the image analysis AI analyzes the input data (images of pets) and identifies the pet's type. Specifically, the input image is passed to a TensorFlow-based image analysis model, which extracts the pet's type data as output.

[1574] Step 4:

[1575] The server uses a basic information analysis model to analyze basic information entered by the user (such as age, weight, and walking time). It then generates health risk data based on the input information. This analysis produces output data such as obesity risk and arthritis risk.

[1576] Step 5:

[1577] The server uses an emotion engine to analyze the user's emotion data. Specifically, it uses emotion recognition libraries such as Microsoft Azure Face API or Google Cloud Vision API to identify the user's emotional state from the user's facial image. The output of this step is the user's emotional state data.

[1578] Step 6:

[1579] The server integrates the results of image analysis, basic information analysis, and emotion analysis to assess the overall health risk. Based on the assessed health risk data, it generates a notification message. The content of this notification message is tailored according to the user's emotional state. The output is a personalized notification message.

[1580] Step 7:

[1581] The server generates and suggests an optimal food plan based on the health risk assessment results. The suggested food plan is also tailored to take into account the user's emotional state, for example by including reassuring messages. The output of this step is the tailored food plan.

[1582] Step 8:

[1583] The server generates a report containing a notification message and a food plan and sends it to the device. The report is then provided to the user, and its content reflects the user's emotional state. The output is a detailed report displayed on the smartphone.

[1584] Step 9:

[1585] The server generates graphs and charts based on past and current data to visually display the pet's health status. These graphs and charts are constructed taking into account the user's emotional state and are presented in an easy-to-understand format. The output is data in a visually easy-to-understand format.

[1586] Step 10:

[1587] In the physical store, tablet devices and digital signage display appropriate advice based on the data sent from the server. Store staff refer to this data and provide detailed explanations to pet owners. This enables flexible and effective on-site service provision. The output is customized advice provided in real time.

[1588] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[1589] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1590] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1591] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1592] FIG. 9 is a diagram illustrating an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1593] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[1594] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[1595] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[1596] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[1597] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[1598] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[1599] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device...

Claims

1. A system for managing the health condition of a pet, comprising: means for receiving an image of the pet; means for analyzing the received image and identifying the type of pet; A means for extracting health risk data based on the analyzed pet species; A means to enter basic information about your pet; means for generating excretion status and health risk data based on the basic information and the health risk data; means for generating and transmitting a notification message based on the generated data; A system including:

2. A system for managing the health condition of a pet, comprising:

10. The system of claim 1, A means for generating and proposing an optimal food plan based on the health risk assessment results; A system including:

3. A system for managing the health condition of a pet, comprising:

10. The system of claim 1, A way to record changes in your pet's health and symptoms and visualize them in graphs and charts. A system including:

Images