System

Abstract

A system is provided.SOLUTION: A system includes a means for a user to photograph and transmit an image of a plant, a means for a server to execute an image recognition model for analyzing the received image, a means for the server to determine a state of the plant based on a result of image recognition, a means for the server to inquire additional information of the user based on a determination result, a means for the user to provide the additional information, a means for the server to refer to a database based on the provided additional information, and a means for the server to generate and transmit an optimal growth advice to the user.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] Gardening enthusiasts face challenges such as plant withering and not knowing how to properly care for each plant. In particular, it is difficult to accurately determine the appropriate watering frequency, sunlight conditions, and signs of disease and pests. As a result, plants do not grow healthily, and the enjoyment of gardening is diminished. The present invention aims to solve these problems by providing a system that accurately diagnoses the health of plants and provides users with appropriate cultivation advice. [Means for solving the problem]

[0005] This system includes a means for a user to take an image of a plant and send it through a chatbot app. The server has a means for executing an image recognition model to analyze the received image and includes a means for determining the condition of the plant. Based on the determination result, the server queries the user for additional information, and the user provides the additional information in response. The server references a database based on the provided additional information, generates optimal plant cultivation advice, and sends it to the user. In this way, the user can grow healthy plants based on appropriate advice.

[0006] "User" refers to a person who provides information about plant cultivation and receives advice from the system.

[0007] "Plant images" refers to photographs and other visual media used to visually record the type and condition of plants.

[0008] "Submit" refers to a user submitting an image of a plant to the system.

[0009] "Server" refers to the central processing unit that receives images, analyzes them, performs database lookups, and generates advice.

[0010] "Image recognition model" refers to a program that uses machine learning algorithms to identify plant species and health conditions.

[0011] "Plant condition" refers to information indicating the health and growing conditions of a plant.

[0012] "Additional information" refers to supplemental information that the server asks the user for to further determine the condition of the plant.

[0013] The "database" refers to an information warehouse that stores cultivation guidelines and problem-solving solutions for each plant.

[0014] "Growth advice" refers to specific instructions and suggestions provided to the user by the server for healthy plant growth.

[0015] "Generation" refers to the server creating training advice based on the analysis results and additional information.

[0016] "Send (to user)" refers to delivering the development advice generated by the server to the user. [Brief explanation of the drawings]

[0017] [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

[0018] 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.

[0019] First, the terms used in the following description will be explained.

[0020] 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).

[0021] 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.

[0022] 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.

[0023] 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.

[0024] 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."

[0025] [First embodiment]

[0026] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0027] 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.

[0028] 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).

[0029] 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.

[0030] 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.

[0031] 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.

[0032] 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.

[0033] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0034] 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.

[0035] 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.

[0036] 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.

[0037] 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."

[0038] The present invention relates to a system that combines image analysis of plants with the collection of additional information to provide users with optimal plant cultivation advice. This system is composed of a user, a server, and a terminal. Below, the program processing of this system is explained in natural language, and a detailed description of the mode for carrying out the invention is given with specific examples.

[0039] System Overview

[0040] In this system, users take pictures of plants and send them to a server via an application. The server inputs the received images into an AI image recognition model to identify the plant's species and its health condition. The server then queries the user for any additional information needed based on the analysis results. By integrating the additional information provided by the user with information from a database referenced by the server, the server generates optimal cultivation advice and sends it to the user.

[0041] Program processing explanation

[0042] 1. The user takes and sends a photo of the plant

[0043] Users use a smartphone or tablet to take a photo of the plant's current condition, and the image is sent to the server via the application.

[0044] 2. The server receives and analyzes the image

[0045] The server receives the images sent by the user, which are then fed into an AI image recognition model that uses machine learning algorithms to identify the plant's type and health status.

[0046] 3. The server queries for additional information based on the analysis results

[0047] Based on the analysis results of the image recognition model, the server queries the user for additional information needed to gain a detailed understanding of the current state of the plant.

[0048] 4. User provides additional information

[0049] In response to a query from the server, the user provides additional information such as exposure to sunlight, frequency of watering, recent weather conditions, etc. This information is sent to the server.

[0050] 5. The server references the database

[0051] The server uses the additional information provided to retrieve relevant information from a database, which includes plant-specific growing guidelines and solutions to problems.

[0052] 6. The server generates and sends the training advice

[0053] The server combines the information retrieved from the database, the additional information provided, and the analysis results to generate optimal breeding advice, which is then sent to the user.

[0054] Specific examples

[0055] Example 1: When the leaves of a houseplant turn brown

[0056] 1. A user takes a photo of a houseplant whose leaves are turning brown and sends it to the server through the application.

[0057] 2. The server receives the photo and inputs it into an AI image recognition model.

[0058] 3. The image recognition model produces the analysis result that "the leaves are brown."

[0059] 4. The server sends a query to the user: "I've checked the condition of the leaves. When was the last time you watered them?"

[0060] 5. The user responds, "3 days ago."

[0061] 6. The server uses the user's answer to look up the appropriate watering frequency from the database.

[0062] 7. The server generates advice that says, "It is recommended that this plant be kept out of direct sunlight and watered once a week," and sends it to the user.

[0063] 8. Users take this advice and apply it in practice.

[0064] Example 2: When vegetable disease is suspected

[0065] 1. A user takes a photo of vegetables in their garden that have unnatural spots and sends it to the server through the application.

[0066] 2. The server receives the photo and inputs it into an AI image recognition model.

[0067] 3. The image recognition model produces the analysis result that "there are spots on the leaf."

[0068] 4. The server asks the user, "I noticed spots on the leaves. Please tell me about the sunlight and recent weather."

[0069] 5. The user responds, "It's sunny and it's been raining a lot lately."

[0070] 6. Based on the user's answers, the server references information from the database about diseases that are more likely to occur during rainy seasons.

[0071] 7. The server generates advice such as, "Mold disease is more likely to occur during rainy seasons. It is effective to improve ventilation and use fungicides as needed," and sends it to the user.

[0072] 8. The user takes the advice and applies it.

[0073] This system quickly and accurately diagnoses the health of plants, providing support to gardening enthusiasts to grow healthy plants.

[0074] The processing flow will be explained below.

[0075] Step 1:

[0076] Users take a photo of the plant and upload and send it to the chatbot app using their smartphone or tablet.

[0077] Step 2:

[0078] The server receives plant photos sent by users, converts them into a specific format, and prepares them for image analysis.

[0079] Step 3:

[0080] The server inputs the received images into an AI image recognition model, which identifies the plant's type and health status (e.g., changes in leaf color, signs of disease, etc.).

[0081] Step 4:

[0082] The server analyzes the output of the AI ​​image recognition model to determine the plant's condition, which involves formalizing the analysis results and comparing them with a database stored on the server.

[0083] Step 5:

[0084] Based on the analysis, the server generates a message asking the user for additional information, such as "How much sunlight does this plant get?"

[0085] Step 6:

[0086] The server generates a message and sends it to the user, which notifies the user's chatbot app and prompts for more information.

[0087] Step 7:

[0088] The user provides additional information in response to a question posed by the server, for example, "It's sunny and it's been raining a lot lately."

[0089] Step 8:

[0090] The server receives additional information from the user, which is stored in a database within the server and converted into the appropriate format.

[0091] Step 9:

[0092] The server references its internal database based on the additional information, searches for appropriate training advice and problem solutions, and extracts the most appropriate information.

[0093] Step 10:

[0094] The server integrates the information obtained from the database, the analysis results, and additional information provided by the user to generate optimal training advice.

[0095] Step 11:

[0096] The server sends the generated training advice to the user, who is then notified in their chatbot app and the advice is displayed.

[0097] Step 12:

[0098] The user receives advice from the server and puts into practice specific cultivation methods, such as moving the plant to avoid direct sunlight.

[0099] Example 1

[0100] 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."

[0101] In conventional plant cultivation, it is difficult for users to accurately grasp the health condition of plants and quickly take appropriate measures. In addition, since ordinary users do not have specialized knowledge of plants, it is difficult to accurately diagnose the condition of plants and find the optimal cultivation method.

[0102] 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.

[0103] In this invention, the server includes means for a user to acquire and transmit images of plants using a camera, means for the server to store the received images, means for running an AI image recognition model to analyze the stored images, means for the server to identify the state of the plant based on the image recognition results, means for the server to query the user for additional information based on the identification results, means for the user to input and transmit the additional information, means for the server to refer to a database based on the provided additional information, and means for the server to synthesize the information in the database, the additional information, and the analysis results to generate optimal instructions and communicate them to the user. This allows the user to easily diagnose the health of their plants and receive appropriate cultivation advice.

[0104] A "user" is an individual or organization that uses the system and is responsible for acquiring images of plants and transmitting them to the server.

[0105] A "photography device" is an electronic device, such as a smartphone or tablet, that captures images of plants and transmits those images to the system.

[0106] "Video" refers to images or videos of plants captured by a user using a camera.

[0107] "Server" is a central computer system that receives, stores, and analyzes user-submitted video.

[0108] An "AI image recognition model" is an artificial intelligence program that uses machine learning algorithms to identify plant species and health conditions.

[0109] A "database" is a collection of information that systematically stores information, including cultivation guidelines and solutions for each plant, and that can be referenced by a server.

[0110] "Identification" is the process by which an AI image recognition model analyzes video footage, identifies the type of plant and its health condition, and generates a judgment result.

[0111] "Additional information" is detailed information related to plant cultivation that the user provides in response to a query from the server.

[0112] "Growth advice" is optimal instructions for keeping plants healthy, generated by the server by integrating information from the database, additional information, and analysis results.

[0113] The present invention is a system that combines image analysis of plants with the collection of additional information to provide users with optimal plant cultivation advice. This system is composed of users, a server, and terminals.

[0114] Users first capture images of plants using a camera such as a smartphone or tablet, and then send the images to the server via a dedicated application. The camera can be a standard smartphone or tablet equipped with a high-resolution camera.

[0115] The server temporarily stores the received video and runs an AI image recognition model using TENSORFLOW® via a Python script. This identifies the type of plant and its health condition from the video. This image recognition model is trained based on machine learning algorithms, enabling highly accurate analysis.

[0116] Next, the server queries the user for additional information based on the image recognition results, such as "How often have you watered your plants recently?" or "How sunny is the area?", and sends the questions to the user via the application.

[0117] The user enters detailed information in response to these questions and submits it back to the server, which then retrieves the additional information provided by the user.

[0118] The server then references a MySQL® database to obtain plant-specific cultivation guidelines and solutions. By combining the obtained information, additional information, and the results of image recognition, the server generates optimal cultivation advice and sends it to the user via the application.

[0119] This system is unique in that it allows users to easily diagnose the health of their plants and receive appropriate growing advice.

[0120] Specific examples

[0121] Example 1: When the leaves of a houseplant turn brown

[0122] 1. A user takes a photo of a houseplant whose leaves are turning brown and sends it to the server through the application.

[0123] 2. The server receives the photo and inputs it into an AI image recognition model using TensorFlow.

[0124] 3. The image recognition model produces the analysis result that "the leaves are brown."

[0125] 4. The server sends a query to the user: "I've checked the condition of the leaves. When was the last time you watered them?"

[0126] 5. The user responds, "3 days ago."

[0127] 6. The server looks up the appropriate watering frequency from the MySQL database based on the user's answer.

[0128] 7. The server generates advice such as "It is recommended that this plant be kept out of direct sunlight and watered once a week" and sends it to the user.

[0129] 8. Users take this advice and apply it in practice.

[0130] Example 2: When vegetable disease is suspected

[0131] 1. A user takes a photo of vegetables in their garden that have unnatural spots and sends it to the server through the application.

[0132] 2. The server receives the photo and inputs it into an AI image recognition model using TensorFlow.

[0133] 3. The image recognition model produces the analysis result that "there are spots on the leaf."

[0134] 4. The server asks the user, "I noticed spots on the leaves. Please tell me about the sunlight and recent weather."

[0135] 5. The user responds, "It's sunny and it's been raining a lot lately."

[0136] 6. Based on the user's response, the server retrieves information from a MySQL database about diseases that are more likely to occur during rainy seasons.

[0137] 7. The server generates advice such as "Mold disease is more likely to occur during rainy seasons. It is effective to improve ventilation and use fungicides as needed," and sends it to the user.

[0138] 8. The user takes the advice and applies it.

[0139] Prompt Sentence Examples

[0140] Prompt 1:

[0141] If your houseplant's leaves are turning brown, take a photo of the plant and send the image to an AI model to analyze its health and provide additional information and advice based on its health.

[0142] Prompt Statement 2:

[0143] If you notice spots on your vegetable leaves, take a photo and send the image to the AI ​​model, along with additional information like sunlight and weather conditions, to generate appropriate growing advice.

[0144] In this way, the system quickly and accurately diagnoses the health of plants, providing support to gardening enthusiasts in growing healthy plants.

[0145] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0146] Step 1:

[0147] Users take and send images of plants

[0148] The user captures a video of the plant using a smartphone or tablet. The user opens the dedicated application, selects the image they have taken, and presses the send button. At this time, the input data is the image file of the photographed plant, which is then sent to the server. Specifically, the user uses the camera function in the application to take a picture of the plant and upload it to the server.

[0149] Step 2:

[0150] The server receives and saves the image.

[0151] The server receives the image sent by the user and temporarily stores it. The received image is saved in a dedicated directory and assigned a unique ID. The input data is the image file sent by the user, and this image file is saved in the server's storage. Specifically, the server receives the image file, saves it in storage, and records the file path.

[0152] Step 3:

[0153] The server performs image analysis

[0154] The server inputs the received images into an AI image recognition model. This model uses TensorFlow via a Python script to identify the plant's type and health status based on machine learning algorithms. The input for this step is the path to the saved image file, and the output is the image analysis results in JSON format. Specifically, the server passes the path to the saved image file to the AI ​​image recognition model, which then parses and saves the results in JSON format.

[0155] Step 4:

[0156] The server queries the user for additional information

[0157] Based on the results of image recognition, the server queries the user for more detailed information. The server generates questions such as "How often have you watered your plants recently?" or "How sunny is the area?" and sends them to the user through the application. The input to this step is the image analysis result data, and the output is a query message to be sent to the user. Specifically, the server determines the required information and sends the question to the user through the application.

[0158] Step 5:

[0159] User provides additional information

[0160] The user enters detailed information in response to the received question into the application and sends it to the server. The input data is additional information that the user entered into the application, and this is sent back to the server. A specific example of this is when the user enters information such as "I watered the plants three days ago" and sends it to the server.

[0161] Step 6:

[0162] The server references the database

[0163] The server references the database based on the additional information to obtain cultivation guidelines and problem-solving solutions for each plant. The database used is MySQL, and the required information is obtained using SQL queries. The input data is the user's additional information and the results of image analysis, and the output is the cultivation guidelines and problem-solving solutions obtained from the database. Specifically, the server creates an SQL query based on the user's information and obtains the relevant information from the database.

[0164] Step 7:

[0165] The server generates and sends training advice

[0166] The server integrates the information obtained from the database, the user's additional information, and the image analysis results to generate optimal breeding advice. This advice is then sent to the user through the application. The input data is the user's additional information, the database information, and the image analysis results, and the output is the breeding advice to be sent to the user. Specifically, the server generates advice and sends it to the user.

[0167] Step 8:

[0168] User receives advice and implements it

[0169] The user checks the advice received in the application and follows the instructions. The input data is the cultivation advice sent from the server, and the user performs the action based on this. Specifically, the user reads the advice and actually carries out the instructions, such as changing the location of the plant.

[0170] Through the above processing steps, the system allows users to easily diagnose the health of their plants and receive appropriate growing advice.

[0171] (Application example 1)

[0172] 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."

[0173] Gardening stores and home improvement centers face the problem of taking time to determine the type and health of plants, making it difficult to provide appropriate growing advice immediately, which can lead to lower customer satisfaction and affect the store's credibility.

[0174] 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.

[0175] In this invention, the server includes: a means for a user to take and send an image of a plant; a means for executing an image recognition model to analyze the image received by the server; a means for the server to determine the type and health of the plant based on the image recognition results; a means for the server to query the user for additional information based on the determination results; a means for the user to provide the additional information; a means for the server to refer to a database based on the provided additional information; a means for the server to generate optimal cultivation advice and send it to the user; and a means for a gardening store to allow store staff or visitors to take and send photos of plants and for the server to provide the plant diagnosis results and cultivation advice. This makes it possible for the gardening store to instantly diagnose the health of plants and provide appropriate cultivation advice.

[0176] A "user" is an individual or store staff member who accesses the system to diagnose the health of plants and obtain growing advice.

[0177] A "plant image" is a digital photograph taken by a user and sent to the system to represent the state of the plant.

[0178] The "transmission means" is a communication means by which the user transmits plant images and additional information to the server.

[0179] The "server" is a central computer system that performs plant image analysis, collects additional information, and generates cultivation advice.

[0180] An "image recognition model" is an artificial intelligence model for identifying plant species and health status based on machine learning algorithms.

[0181] The "analysis means" is a means for inputting the plant image received by the server into an image recognition model and analyzing it.

[0182] The "determination means" is a function of the server that determines the type and health condition of a plant based on the results of the image recognition model.

[0183] The "query means" is a function of the server that queries the user for additional information based on the determination result.

[0184] "Additional information" is information provided by the user to understand the current state of the plant in detail, and includes sunlight exposure, watering frequency, weather conditions, etc.

[0185] The "reference means" is a function that allows the server to obtain related information from a database based on the additional information provided.

[0186] The "database" is a collection of information that stores cultivation guidelines and solutions to problems for each plant.

[0187] The "development advice generating means" is a means by which the server integrates the information in the database with the additional information to generate optimal development advice.

[0188] A "gardening store" is a physical store that sells plants and related products, and is a place where users can use the plant diagnostic application.

[0189] "Store staff or visitors" refers to customers or store staff who use the plant diagnostic system at a gardening store.

[0190] System configuration

[0191] This invention is a system that provides plant cultivation advice by combining plant image analysis and additional information collection. This system receives plant images taken and sent by users, analyzes them using an AI image recognition model, and identifies the plant's species and health condition. It then queries the user for any additional information needed, and generates and provides optimal cultivation advice.

[0192] Hardware and software used

[0193] Server: The server is built using a web framework such as Flask or Django. This server plays a central role in receiving images sent by users, analyzing them, querying necessary information, and generating and providing training advice.

[0194] Terminal (smartphone, tablet, etc.): A terminal on which a user takes pictures of plants and sends them to the server. It can be implemented as an ANDROID (registered trademark) or iOS application.

[0195] Generative AI models: These are machine learning models built using deep learning frameworks such as TensorFlow and PyTorch, and are used for image recognition to identify plant species and health.

[0196] Database: Use a database system such as MySQL or MongoDB to store growing guidelines and problem solutions for each plant.

[0197] Process Overview

[0198] The user takes an image of the plant and sends it to the server via the application. The received image is analyzed by an image recognition model run by the server. Based on the analysis results, the plant's type and health condition are determined, and the user is then queried for additional information based on that information. The additional information provided by the user is compared with a database, and optimal growing advice is generated. The generated advice is notified to the user, who can use it to grow the plant.

[0199] Specific examples

[0200] Example 1: When the leaves of a houseplant turn brown

[0201] 1. A user takes a photo of a houseplant whose leaves are turning brown and sends it to the server through the application.

[0202] 2. The server receives the photo and analyzes the image using a generative AI model.

[0203] 3. The image recognition model produces the analysis result that "the leaves are brown."

[0204] 4. The server sends the query to the user: "I've checked the condition of the leaves. When was the last time you watered them?"

[0205] 5. The user responds, "3 days ago."

[0206] 6. Based on the user's answer, the server looks up the appropriate watering frequency from the database.

[0207] 7. The server generates advice that says, "It is recommended that this plant be kept out of direct sunlight and watered once a week," and sends it to the user.

[0208] 8. Users take this advice and apply it in practice.

[0209] Example 2: When vegetable disease is suspected

[0210] 1. A user takes a photo of vegetables in their garden that have unnatural spots and sends it to the server through the application.

[0211] 2. The server receives the photo and analyzes the image using a generative AI model.

[0212] 3. The image recognition model produces the analysis result that "there are spots on the leaf."

[0213] 4. The server asks the user, "I noticed spots on the leaves. Please tell me about the sunlight and recent weather."

[0214] 5. The user responds, "It's sunny and it's been raining a lot lately."

[0215] 6. Based on the user's answers, the server references information from the database about diseases that are more likely to occur during rainy seasons.

[0216] 7. The server generates advice such as, "Mold disease is more likely to occur during rainy seasons. It is effective to improve ventilation and use fungicides as needed," and sends it to the user.

[0217] 8. The user takes the advice and applies it.

[0218] Prompt Sentence Examples

[0219] "My tomato leaves are turning yellow. When was the last time I watered them?"

[0220] "My rose leaves are turning brown. What's the weather like these days?"

[0221] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0222] Step 1:

[0223] The user takes a picture of a plant and sends it to the server through the application. The input is the image data of the plant taken by the user, and this data is sent to the server. The output is the image data that arrives at the server.

[0224] Step 2:

[0225] The server takes in the received image data and analyzes the image using a generative AI model. The input is the image data received by the server, and the output is the analysis results of the generative AI model, which include information on the plant's type and health condition. Specifically, the image is preprocessed and converted into an appropriate format before being input into the AI ​​model.

[0226] Step 3:

[0227] The server determines the type and health of the plant based on the analysis results of the generated AI model. The input is the analysis result from step 2, and the output is information about the determined plant type and its health condition. Specific operations include decoding the analysis results and converting them into meaningful information.

[0228] Step 4:

[0229] Based on the judgment result, the server queries the user for additional information. The input is the type and health condition of the plant judged in step 3, and the output is the question to be sent to the user. Specifically, the server generates an appropriate prompt sentence according to the plant's condition and sends it to the user's device.

[0230] Step 5:

[0231] The user provides the necessary additional information in response to a query from the server. The input is the question presented to the user, and the output is the additional information the user provides to the server. Specifically, text and options are entered through the terminal application and sent to the server.

[0232] Step 6:

[0233] The server references the database based on the additional information provided by the user. The input is the additional information obtained in step 5, and the output is related information retrieved from the database. Specifically, the server performs a database search using the additional information as a key to obtain the relevant training guidelines and problem solutions.

[0234] Step 7:

[0235] The server integrates the database information with the additional information to generate optimal training advice. The input is the database information obtained in step 6 and the additional information provided by the user, and the output is the generated training advice. Specifically, the information obtained from the database is combined with the user's input and an algorithm is used to generate optimal advice.

[0236] Step 8:

[0237] The server sends the generated training advice to the user. The input is the training advice generated in step 7, and the output is the advice content sent to the user's terminal. Specific operations include converting it into a message format and sending it to the user's terminal.

[0238] 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.

[0239] The present invention relates to a system that combines plant image analysis, additional information collection, and an emotion engine that recognizes the user's emotions to provide optimal plant cultivation advice to the user. This system is composed of a user, a server, a terminal, and an emotion engine. Below, the program processing of this system is explained in natural language, and a detailed description of the embodiment of the invention is given with specific examples.

[0240] System Overview

[0241] In this system, users take pictures of plants and send them to a server via an application. The server inputs the received images into an AI image recognition model to identify the plant's species and its health condition. The server then queries the user for any additional information needed based on the analysis results, and uses an emotion engine to recognize the user's emotions. By integrating the additional information provided by the user, the emotion engine's analysis results, and information from a database referenced by the server, the server generates optimal cultivation advice and sends it to the user.

[0242] Program processing explanation

[0243] 1. The user takes and sends a photo of the plant

[0244] Users use a smartphone or tablet to take a photo of the plant's current condition, and the image is sent to the server via the application.

[0245] 2. The server receives and analyzes the image

[0246] The server receives the images sent by the user, which are then fed into an AI image recognition model that uses machine learning algorithms to identify the plant's type and health status.

[0247] 3. The server queries for additional information based on the analysis results

[0248] Based on the analysis results of the image recognition model, the server queries the user for additional information needed to gain a detailed understanding of the current state of the plant.

[0249] 4. User provides additional information

[0250] In response to a query from the server, the user provides additional information such as exposure to sunlight, frequency of watering, recent weather conditions, etc. This information is sent to the server.

[0251] 5. The server analyzes the user's emotions

[0252] The emotion engine installed on the server analyzes messages and voice data sent by users and recognizes their emotional state. For example, if a user sends a comment such as "My plants haven't been doing well lately, and I'm worried," the emotion is recognized as "worried."

[0253] 6. The server references the database

[0254] Based on the additional information provided and the results of the emotion engine's analysis, the server retrieves relevant information by referencing an internal database, which includes plant-specific cultivation guidelines and solutions to problems.

[0255] 7. The server generates and sends the training advice

[0256] The server combines the information retrieved from the database, the analysis results, and additional information provided by the user to generate optimal parenting advice. Based on the analysis results of the emotion engine, the content and tone of the advice may be adjusted to include softer language or encouraging messages. This advice is then sent to the user, who then notifies the user's chatbot app.

[0257] Specific examples

[0258] Example 1: When the leaves of a houseplant turn brown

[0259] 1. A user takes a photo of a houseplant whose leaves are turning brown and sends it to the server through the application.

[0260] 2. The server receives the photo and inputs it into an AI image recognition model.

[0261] 3. The image recognition model produces the analysis result that "the leaves are brown."

[0262] 4. The server sends a query to the user: "I've checked the condition of the leaves. When was the last time you watered them?"

[0263] 5. The user responds, "3 days ago."

[0264] 6. The emotion engine analyzes the user's message and recognizes that the user is "worried."

[0265] 7. The server consults the database to find the appropriate watering frequency.

[0266] 8. The server generates advice such as "It is recommended that you keep this plant out of direct sunlight and water it once a week. Also, there is no need to worry; if you follow this advice, it will recover its health" and sends it to the user.

[0267] 9. Users take this advice and apply it in practice.

[0268] Example 2: When vegetable disease is suspected

[0269] 1. A user takes a photo of vegetables in their garden that have unnatural spots and sends it to the server through the application.

[0270] 2. The server receives the photo and inputs it into an AI image recognition model.

[0271] 3. The image recognition model produces the analysis result that "there are spots on the leaf."

[0272] 4. The server asks the user, "I noticed spots on the leaves. Please tell me about the sunlight and recent weather."

[0273] 5. The user responds, "It's sunny and it's been raining a lot lately."

[0274] 6. The emotion engine analyzes the user's message and recognizes that the user is feeling "anxiety."

[0275] 7. The server references the database and retrieves information about diseases that are more likely to occur during rainy seasons.

[0276] 8. The server generates advice such as, "Mold disease is more likely to occur during rainy seasons. It is effective to improve ventilation and use fungicides as needed. Don't worry, the problem will be solved if you take action early." and sends it to the user.

[0277] 9. The user takes the advice and applies it.

[0278] In this way, the system quickly and accurately diagnoses the health of plants and provides support to gardeners to grow healthy plants while taking into account the user's emotions.

[0279] The processing flow will be explained below.

[0280] Step 1:

[0281] Users take photos of plants with their smartphones or tablets and use the chatbot app to send the photos to the server.

[0282] Step 2:

[0283] The server receives plant photos submitted by users and formats them in a way that makes them ready for image analysis.

[0284] Step 3:

[0285] The server inputs the received photos into an AI image recognition model, which uses machine learning algorithms to identify the plant's type and health status (e.g., changes in leaf color or signs of disease).

[0286] Step 4:

[0287] The server analyzes the output of the AI ​​image recognition model to determine the plant's current condition, and the analyzed data is compared with the server's internal database.

[0288] Step 5:

[0289] Based on the analysis results, the server generates a message to ask the user for additional information, such as "How much sunlight does the plant get?"

[0290] Step 6:

[0291] The server generates a message and sends it to the user, which notifies the user's chatbot app and prompts for more information.

[0292] Step 7:

[0293] The user responds to queries from the server and provides additional information such as exposure to sunlight, watering frequency, recent weather conditions, etc. This information is sent to the server through the application.

[0294] Step 8:

[0295] The server receives the additional information sent by the user, converts it into a specific format, and stores it in an internal database.

[0296] Step 9:

[0297] An emotion engine implemented on the server analyzes text messages and voice data sent by the user and recognizes the user's emotional state (e.g., anxiety, worry, joy).

[0298] Step 10:

[0299] The server refers to an internal database based on the additional information and the analysis results of the emotion engine to search for appropriate development guidelines and solutions to problems.

[0300] Step 11:

[0301] The server combines information obtained from the database, the results of image analysis, additional information provided by the user, and the results of the emotion engine analysis to generate optimal training advice. The content and tone of the advice are also adjusted based on the results of the emotion engine.

[0302] Step 12:

[0303] The server sends the generated training advice to the user, who is then notified in their chatbot app and given specific advice.

[0304] Step 13:

[0305] The user receives advice from the server and puts the specific cultivation methods suggested into practice, such as changing the location of the plant to avoid direct sunlight or reviewing the frequency of watering.

[0306] Example 2

[0307] 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."

[0308] Conventional plant growing systems have incomplete processes for accurately identifying the condition of plants and providing appropriate growing advice to users. In particular, they lack consideration for identifying the plant's health and the user's emotional state, making it difficult to provide satisfying growing support. Furthermore, there are problems with the systems' ineffective management of additional information provided by users and the ineffective personalization of advice based on emotional analysis. The purpose of this invention is to solve these problems and provide optimal growing advice to users.

[0309] 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.

[0310] In this invention, the server includes a means for a user to take and send an image of a plant, a means for analyzing the image by executing a generative AI model, and a means for identifying the plant's type and health condition based on the results of the image recognition model. This allows the plant's condition to be accurately identified and the user to be asked for detailed additional information based on the analysis results. Furthermore, the server includes a means for analyzing the user's emotions using a sentiment analysis engine and a means for referencing a database based on the provided additional information and sentiment analysis information, making it possible to provide personalized, optimal plant-growing advice to the user. Furthermore, by including a means for generating prompt sentences that provide specific examples when generating plant-growing advice, the server can provide the user with more specific advice and is useful for troubleshooting. This enhances overall support for plant cultivation and is expected to improve user satisfaction.

[0311] "User" refers to an individual who uses the system to take images of plants and transmit the information.

[0312] A "server" refers to a device that analyzes received image data, references a database, and generates and transmits optimal training advice.

[0313] "Generative AI model" refers to a model that uses machine learning algorithms to analyze image data and identify plant species and health conditions.

[0314] "Image recognition model" refers to an algorithm or software that analyzes received image data to identify the type of plant and its health condition.

[0315] "Additional information" refers to information such as sunlight exposure, watering frequency, and recent weather conditions provided by the user to further analyze the health of the plant.

[0316] "Emotion analysis engine" refers to an engine that analyzes text data and voice data provided by a user to recognize the user's emotional state.

[0317] The "database" refers to a collection of information that stores plant-specific growing guidelines, problem-solving solutions, and other related information.

[0318] "Growth advice" refers to instructions and advice on the correct way to grow plants that are generated by the server based on the database and analysis results and provided to the user.

[0319] A "prompt sentence" refers to an advice sentence containing specific examples generated by a generative AI model.

[0320] The present invention relates to a system that combines plant image analysis, additional information collection, and an emotion engine that recognizes the user's emotions to provide optimal plant cultivation advice to the user. This system is composed of a user, a server, a terminal, and an emotion engine.

[0321] System Overview

[0322] The user takes a photo of a plant and sends it to the server via the application. The server inputs the received image into a generative AI model to identify the plant's species and its health condition. The server then queries the user for any additional information needed based on the analysis results and recognizes the user's emotions using an emotion engine. Finally, the server combines the additional information provided by the user, the analysis results of the emotion engine, and information from a database referenced by the server to generate optimal planting advice and send it to the user.

[0323] Hardware and software used

[0324] User device: A smartphone or tablet is used to take pictures of plants and send them to the server via the application.

[0325] Server: A computer system with powerful processing power where the generative AI model and sentiment analysis engine run.

[0326] Generative AI models: Image recognition software based on machine learning algorithms (e.g., TensorFlow, PyTorch).

[0327] Sentiment analysis engine: Software that analyzes a user's emotional state from text or voice (e.g., OpenAI® GPT-3®, IBM Watson®).

[0328] Database: Information storage for plant growing guidelines and problem solutions.

[0329] Specific examples

[0330] Example 1: When the leaves of a houseplant turn brown

[0331] 1. A user takes a photo of a houseplant whose leaves are turning brown and sends it to the server through the application.

[0332] 2. The server receives the photo and inputs it into a generative AI model (using TensorFlow, for example).

[0333] 3. The generative AI model produces the analysis result that "the leaves are turning brown."

[0334] 4. The server sends a query to the user: "I've checked the condition of the leaves. When was the last time you watered them?"

[0335] 5. The user responds, "3 days ago."

[0336] 6. The sentiment analysis engine analyzes the user's message ("I'm worried because my plants haven't been doing well lately") and recognizes that the user is "worried."

[0337] 7. The server consults the database to find the appropriate watering frequency.

[0338] 8. The server generates advice to the user: "It is recommended that you keep this plant out of direct sunlight and water it once a week. There is no need to worry; if you follow this advice, it will recover."

[0339] 9. Users take this advice and apply it in practice.

[0340] Example 2: When vegetable disease is suspected

[0341] 1. A user takes a photo of vegetables in their garden that have unnatural spots and sends it to the server through the application.

[0342] 2. The server receives the photos and inputs them into a generative AI model (using, for example, PyTorch).

[0343] 3. The generative AI model produces the analysis result that "the leaf has spots."

[0344] 4. The server asks the user, "I noticed spots on the leaves. Please tell me about the sunlight and recent weather."

[0345] 5. The user responds, "It's sunny and it's been raining a lot lately."

[0346] 6. The sentiment analysis engine analyzes the user's message ("It's been raining a lot lately, and I'm worried that my vegetables might get sick") and recognizes that the user is feeling "anxious."

[0347] 7. The server references the database and retrieves information about diseases that are more likely to occur during rainy seasons.

[0348] 8. The server generates advice such as, "Mold disease is more likely to occur during rainy seasons. It is effective to improve ventilation and use fungicides as needed. Don't worry, the problem will be solved if you take action early." and sends it to the user.

[0349] 9. The user takes the advice and applies it.

[0350] By taking these steps into consideration, the system can provide highly accurate training advice by comprehensively considering the information provided by the user and their emotional state.

[0351] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0352] Step 1:

[0353] The user takes a picture of the plant and sends it.

[0354] Specific operation: The user takes a photo of a plant using a smartphone or tablet, and the image is sent to the server via the application.

[0355] Input: Plant image data.

[0356] Output: Image data sent to the server.

[0357] Step 2:

[0358] The server receives the images and analyzes them using a generative AI model.

[0359] How it works: The server inputs the received image data into a generative AI model such as TensorFlow or PyTorch, which processes the data to identify the plant species and its health status.

[0360] Input: Received plant image data.

[0361] Output: Analysis of plant type and health.

[0362] Step 3:

[0363] The server queries the user for additional information based on the results of image recognition.

[0364] How it works: Based on the results of the generative AI model's analysis, the server generates additional information to understand the plant's current condition in more detail. This additional information is sent to the user as a text message. For example, it may ask, "I've checked the condition of the leaves. When was the last time you watered them?"

[0365] Input: Analysis results of the image recognition model.

[0366] Output: A message asking the user for more information.

[0367] Step 4:

[0368] The user provides additional information.

[0369] Specific operation: In response to queries from the server, the user inputs information such as sunlight exposure, watering frequency, and recent weather conditions, and sends it to the server via the application.

[0370] Input: A query message from the server as a trigger.

[0371] Output: Additional information sent to the server.

[0372] Step 5:

[0373] The server receives the additional information provided by the user and analyzes the user's emotions using a sentiment analysis engine.

[0374] Specific operation: The server inputs the text and voice included in the additional information into an emotion analysis engine (e.g., OpenAI GPT-3 or IBM Watson) to analyze the user's emotional state. For example, if a user sends a message saying, "My plants haven't been doing well lately, and I'm worried," this message will be recognized as expressing "worry."

[0375] Input: Additional information provided by the user.

[0376] Output: Analysis results about the user's emotional state.

[0377] Step 6:

[0378] The server references the database based on the analysis results.

[0379] What it does: Based on the additional information and the results of the sentiment analysis engine, the server retrieves relevant information from an internal database, which contains plant-specific growing guidelines and problem-solving solutions. For example, it uses an SQL query to search for the appropriate growing guidelines.

[0380] Input: Additional information provided by the user and the results of the sentiment analysis engine.

[0381] Output: Relevant information retrieved from the internal database.

[0382] Step 7:

[0383] The server generates and transmits the development advice to the user.

[0384] Specific operation: The server combines information obtained from the database, analysis results, and additional information provided by the user to generate optimal growing advice. The generated advice includes specific examples as prompts. For example, "It is recommended that this plant be protected from direct sunlight and watered once a week. There is no need to worry. If you follow this advice, it will recover its health."

[0385] Input: Information retrieved from the database, analysis results, and additional information.

[0386] Output: Development advice notified to the user.

[0387] Through this process, users receive detailed advice on the health of their plants and can take specific actions.

[0388] (Application example 2)

[0389] 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."

[0390] Current plant cultivation support systems can analyze the type and health of plants, but they cannot provide flexible advice based on the user's emotions. Furthermore, there is a lack of systems for food delivery that provide advice on the nutritional value and health aspects of food. This creates a need for a comprehensive system to support plant cultivation and healthy eating.

[0391] 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 a user to take and send an image of a plant or food, means for executing an image recognition model to analyze the image received by the server, and means for analyzing the user's emotions using an emotion engine and adjusting the content and tone of advice. This enables the user to quickly and accurately diagnose the health condition of the plant or food and provide cultivation or food advice that takes the user's emotions into consideration.

[0392] A "user" is someone who uses the system to take images of plants or food and provide information about them.

[0393] "Plants" are living things such as green plants and flowers that are cultivated by the user.

[0394] "Food" refers to food such as dishes or ingredients that the user photographs.

[0395] "Means for taking and transmitting images" refers to a function that allows a user to take an image of a plant or food using a device such as a smartphone and transmit that image to a server.

[0396] The "server" is a computer system that receives and analyzes images, references a database, and generates optimal advice.

[0397] An "image recognition model" is an analytical method that uses machine learning algorithms to identify the type and health status of plants or food.

[0398] "Means for determining status" refers to the function of determining the current health status of a plant or food based on the analysis results of an image recognition model.

[0399] "Means for requesting additional information" refers to a function that allows the server to request missing information from the user based on the analysis results.

[0400] "Means for providing additional information" refers to a function that allows users to provide information such as sunlight exposure, watering frequency, and ingredients used in response to inquiries from the server.

[0401] "Means for referencing a database" refers to the function by which the server searches an internal database based on the additional information provided and obtains relevant growing guidelines and nutritional information.

[0402] "Means for generating and transmitting raising or food advice" refers to a function that generates optimal raising or food advice based on the information and analysis results acquired by the server and transmits it to the user.

[0403] An "emotion engine" is software that uses natural language processing technology to recognize and analyze a user's emotional state.

[0404] "Means for analyzing emotions and adjusting the content and tone of advice" refers to a function that provides the user with advice of appropriate content and tone based on the user's emotions analyzed by the emotion engine.

[0405] MODE FOR CARRYING OUT THE INVENTION

[0406] To put the present invention into practice, we will explain the specific configuration and method of a system that allows users to take and send images of plants or food. This system is built by combining a user's terminal, a server, a database, and an emotion engine.

[0407] System Configuration

[0408] 1. User Device:

[0409] Using a smartphone or tablet, users take pictures of plants or food and send them to a server via an application.

[0410] 2. Server:

[0411] The server analyzes the received image, queries the user for additional information, and generates optimal nutrition or dietary advice based on the acquired information by referencing a database. It also runs an emotion engine to analyze the user's emotions and adjust the content and tone of the advice.

[0412] 3. Database:

[0413] Databases such as MySQL and MongoDB are used to store growing guidelines, nutritional information, and problem solutions for each plant and food.

[0414] 4. Emotion Engine:

[0415] It uses NLP (Natural Language Processing) APIs to analyze user sentiment and tailor advice accordingly.

[0416] 5. Image Recognition Model:

[0417] TensorFlow and PyTorch are used to run machine learning models to analyze images of plants or food.

[0418] Program processing explanation

[0419] The server receives the image sent by the user and inputs it into an image recognition model to identify the type of plant or food and its health condition. The server then queries the user for any additional information needed based on the analysis results. The user provides the server with information such as sunlight exposure, watering frequency, and ingredients used. The server then uses an emotion engine to analyze the user's emotions and recognize their emotional state.

[0420] The server then uses this information to retrieve relevant information from a database, which includes growing guidelines, nutritional information, and solutions for each plant or food. The server then integrates the retrieved data, analysis results, and the user's emotional state to generate optimal growing or food advice. This advice is then sent to the user.

[0421] Examples of concrete examples and prompts

[0422] Example 1: When the leaves of a houseplant turn brown

[0423] 1. A user takes a photo of a houseplant whose leaves are turning brown and sends it to the server through the application.

[0424] 2. The server receives the photo and inputs it into an AI image recognition model.

[0425] 3. The image recognition model produces the analysis result that "the leaves are brown."

[0426] 4. The server sends a query to the user: "I've checked the condition of the leaves. When was the last time you watered them?"

[0427] 5. The user responds, "3 days ago."

[0428] 6. The emotion engine analyzes the user's message and recognizes that the user is "worried."

[0429] 7. The server consults the database to find the appropriate watering frequency.

[0430] 8. The server generates advice such as "It is recommended that you keep this plant out of direct sunlight and water it once a week. Also, there is no need to worry; if you follow this advice, it will recover its health" and sends it to the user.

[0431] 9. Users take this advice and apply it in practice.

[0432] Example 2: If you are concerned about the nutritional value of a dish

[0433] 1. A user takes a photo of a healthy salad and sends it with the comment, "I want to continue eating healthy."

[0434] 2. The server receives the photo, determines it is a "salad," and retrieves nutritional information for the main ingredients used (e.g., lettuce, tomato, cucumber) from the database.

[0435] 3. The emotion engine recognizes the user's emotional state of "motivation."

[0436] 4. The server integrates the database information with the emotional state, generates advice for the user, such as "This salad is very healthy, especially rich in vitamin C. Keep it up!", and sends it to the user.

[0437] Prompt Sentence Examples

[0438] "Please analyze the food in this image to get the ingredient information."

[0439] "Identify the emotion a user feels when they say 'I'm very happy.'"

[0440] "Generate personalized health advice based on analytics results and user sentiment."

[0441] Through these specific examples, users can quickly and accurately diagnose the health of plants or food and receive emotionally sensitive advice.

[0442] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0443] Step 1:

[0444] A user takes an image of a plant or food item and sends the image to a server through the application.

[0445] Input: An image of a plant or food

[0446] Output: Image data sent to the server

[0447] Specific operation: Take a picture using the camera on the user device and press the send button in the application

[0448] Step 2:

[0449] The server inputs the images received from the user into an image recognition model for analysis.

[0450] Input: Received image data

[0451] Output: Image recognition results (identification of plant or food type and health status)

[0452] Specific operation: The server inputs image data into an AI image recognition model (e.g., TensorFlow or PyTorch) and obtains the analysis results.

[0453] Step 3:

[0454] The server queries the user for missing information based on the results of image recognition.

[0455] Input: Image recognition results (type of plant or food and health status)

[0456] Output: A message asking for more information

[0457] Specific operation: Based on the analysis results, the server generates a message to send additional information (e.g., sunlight, watering frequency, ingredients used) and sends it to the user's device.

[0458] Step 4:

[0459] The user provides additional information in response to a query from the server.

[0460] Input: Query message from the server

[0461] Output: Additional information provided

[0462] What happens: The user answers questions through the application and sends the information to the server.

[0463] Step 5:

[0464] The server uses an emotion engine to analyze the user's emotions.

[0465] Input: User's message or voice data

[0466] Output: Sentiment analysis results (e.g., worry, satisfaction, anxiety, etc.)

[0467] Specific operation: The server inputs the user's message and voice data into an emotion engine (e.g., NLP API) to identify the emotional state.

[0468] Step 6:

[0469] Using the additional information acquired by the server and the results of emotion analysis, the server references the database to acquire related information.

[0470] Input: Additional information and sentiment analysis results

[0471] Output: Growing guidelines or nutritional information

[0472] What happens: The server searches an internal database (e.g., MySQL or MongoDB) to retrieve relevant growing guidelines and nutritional information.

[0473] Step 7:

[0474] The server integrates the acquired data, analysis results, and emotional state to generate optimal development or food advice.

[0475] Input: Nutritional guidelines or nutritional information, additional information, emotional state

[0476] Output: personalized advice

[0477] What it does: The server runs an algorithm that integrates the data and generates personalized nutrition or dietary advice.

[0478] Step 8:

[0479] The server sends the generated advice to the user.

[0480] Input: personalized advice

[0481] Output: Notification message to the user's terminal

[0482] What happens: The server generates a message containing the advice and sends it to the user's application.

[0483] In this way, users can quickly and accurately diagnose the health of their plants or food products and receive emotionally sensitive advice.

[0484] 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.

[0485] 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.

[0486] 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.

[0487] [Second embodiment]

[0488] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0489] 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.

[0490] 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).

[0491] 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.

[0492] 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.

[0493] 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).

[0494] 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.

[0495] 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.

[0496] 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.

[0497] 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.

[0498] 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.

[0499] 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."

[0500] The present invention relates to a system that combines image analysis of plants with the collection of additional information to provide users with optimal plant cultivation advice. This system is composed of a user, a server, and a terminal. Below, the program processing of this system is explained in natural language, and a detailed description of the mode for carrying out the invention is given with specific examples.

[0501] System Overview

[0502] In this system, users take pictures of plants and send them to a server via an application. The server inputs the received images into an AI image recognition model to identify the plant's species and its health condition. The server then queries the user for any additional information needed based on the analysis results. By integrating the additional information provided by the user with information from a database referenced by the server, the server generates optimal cultivation advice and sends it to the user.

[0503] Program processing explanation

[0504] 1. The user takes and sends a photo of the plant

[0505] Users use a smartphone or tablet to take a photo of the plant's current condition, and the image is sent to the server via the application.

[0506] 2. The server receives and analyzes the image

[0507] The server receives the images sent by the user, which are then fed into an AI image recognition model that uses machine learning algorithms to identify the plant's type and health status.

[0508] 3. The server queries for additional information based on the analysis results

[0509] Based on the analysis results of the image recognition model, the server queries the user for additional information needed to gain a detailed understanding of the current state of the plant.

[0510] 4. User provides additional information

[0511] In response to a query from the server, the user provides additional information such as exposure to sunlight, frequency of watering, recent weather conditions, etc. This information is sent to the server.

[0512] 5. The server references the database

[0513] The server uses the additional information provided to retrieve relevant information from a database, which includes plant-specific growing guidelines and solutions to problems.

[0514] 6. The server generates and sends the training advice

[0515] The server combines the information retrieved from the database, the additional information provided, and the analysis results to generate optimal breeding advice, which is then sent to the user.

[0516] Specific examples

[0517] Example 1: When the leaves of a houseplant turn brown

[0518] 1. A user takes a photo of a houseplant whose leaves are turning brown and sends it to the server through the application.

[0519] 2. The server receives the photo and inputs it into an AI image recognition model.

[0520] 3. The image recognition model produces the analysis result that "the leaves are brown."

[0521] 4. The server sends a query to the user: "I've checked the condition of the leaves. When was the last time you watered them?"

[0522] 5. The user responds, "3 days ago."

[0523] 6. The server uses the user's answer to look up the appropriate watering frequency from the database.

[0524] 7. The server generates advice that says, "It is recommended that this plant be kept out of direct sunlight and watered once a week," and sends it to the user.

[0525] 8. Users take this advice and apply it in practice.

[0526] Example 2: When vegetable disease is suspected

[0527] 1. A user takes a photo of vegetables in their garden that have unnatural spots and sends it to the server through the application.

[0528] 2. The server receives the photo and inputs it into an AI image recognition model.

[0529] 3. The image recognition model produces the analysis result that "there are spots on the leaf."

[0530] 4. The server asks the user, "I noticed spots on the leaves. Please tell me about the sunlight and recent weather."

[0531] 5. The user responds, "It's sunny and it's been raining a lot lately."

[0532] 6. Based on the user's answers, the server references information from the database about diseases that are more likely to occur during rainy seasons.

[0533] 7. The server generates advice such as, "Mold disease is more likely to occur during rainy seasons. It is effective to improve ventilation and use fungicides as needed," and sends it to the user.

[0534] 8. The user takes the advice and applies it.

[0535] This system quickly and accurately diagnoses the health of plants, providing support to gardening enthusiasts to grow healthy plants.

[0536] The processing flow will be explained below.

[0537] Step 1:

[0538] Users take a photo of the plant and upload and send it to the chatbot app using their smartphone or tablet.

[0539] Step 2:

[0540] The server receives plant photos sent by users, converts them into a specific format, and prepares them for image analysis.

[0541] Step 3:

[0542] The server inputs the received images into an AI image recognition model, which identifies the plant's type and health status (e.g., changes in leaf color, signs of disease, etc.).

[0543] Step 4:

[0544] The server analyzes the output of the AI ​​image recognition model to determine the plant's condition, which involves formalizing the analysis results and comparing them with a database stored on the server.

[0545] Step 5:

[0546] Based on the analysis, the server generates a message asking the user for additional information, such as "How much sunlight does this plant get?"

[0547] Step 6:

[0548] The server generates a message and sends it to the user, which notifies the user's chatbot app and prompts for more information.

[0549] Step 7:

[0550] The user provides additional information in response to a question posed by the server, for example, "It's sunny and it's been raining a lot lately."

[0551] Step 8:

[0552] The server receives additional information from the user, which is stored in a database within the server and converted into the appropriate format.

[0553] Step 9:

[0554] The server references its internal database based on the additional information, searches for appropriate training advice and problem solutions, and extracts the most appropriate information.

[0555] Step 10:

[0556] The server integrates the information obtained from the database, the analysis results, and additional information provided by the user to generate optimal training advice.

[0557] Step 11:

[0558] The server sends the generated training advice to the user, who is then notified in their chatbot app and the advice is displayed.

[0559] Step 12:

[0560] The user receives advice from the server and puts into practice specific cultivation methods, such as moving the plant to avoid direct sunlight.

[0561] Example 1

[0562] 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."

[0563] In conventional plant cultivation, it is difficult for users to accurately grasp the health condition of plants and quickly take appropriate measures. In addition, since ordinary users do not have specialized knowledge of plants, it is difficult to accurately diagnose the condition of plants and find the optimal cultivation method.

[0564] 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.

[0565] In this invention, the server includes means for a user to acquire and transmit images of plants using a camera, means for the server to store the received images, means for running an AI image recognition model to analyze the stored images, means for the server to identify the state of the plant based on the image recognition results, means for the server to query the user for additional information based on the identification results, means for the user to input and transmit the additional information, means for the server to refer to a database based on the provided additional information, and means for the server to synthesize the information in the database, the additional information, and the analysis results to generate optimal instructions and communicate them to the user. This allows the user to easily diagnose the health of their plants and receive appropriate cultivation advice.

[0566] A "user" is an individual or organization that uses the system and is responsible for acquiring images of plants and transmitting them to the server.

[0567] A "photography device" is an electronic device, such as a smartphone or tablet, that captures images of plants and transmits those images to the system.

[0568] "Video" refers to images or videos of plants captured by a user using a camera.

[0569] "Server" is a central computer system that receives, stores, and analyzes user-submitted video.

[0570] An "AI image recognition model" is an artificial intelligence program that uses machine learning algorithms to identify plant species and health conditions.

[0571] A "database" is a collection of information that systematically stores information, including cultivation guidelines and solutions for each plant, and that can be referenced by a server.

[0572] "Identification" is the process by which an AI image recognition model analyzes video footage, identifies the type of plant and its health condition, and generates a judgment result.

[0573] "Additional information" is detailed information related to plant cultivation that the user provides in response to a query from the server.

[0574] "Growth advice" is optimal instructions for keeping plants healthy, generated by the server by integrating information from the database, additional information, and analysis results.

[0575] The present invention is a system that combines image analysis of plants with the collection of additional information to provide users with optimal plant cultivation advice. This system is composed of users, a server, and terminals.

[0576] Users first capture images of plants using a camera such as a smartphone or tablet, and then send the images to the server via a dedicated application. The camera can be a standard smartphone or tablet equipped with a high-resolution camera.

[0577] The server temporarily stores the received video and runs an AI image recognition model using TensorFlow via a Python script. This identifies the type of plant and its health condition from the video. This image recognition model is trained based on machine learning algorithms, enabling highly accurate analysis.

[0578] Next, the server queries the user for additional information based on the image recognition results, such as "How often have you watered your plants recently?" or "How sunny is the area?", and sends the questions to the user via the application.

[0579] The user enters detailed information in response to these questions and submits it back to the server, which then retrieves the additional information provided by the user.

[0580] The server then consults a MySQL database to retrieve plant-specific cultivation guidelines and solutions. By combining the retrieved information, additional information, and the results of image recognition, the server generates optimal cultivation advice and sends it to the user via the application.

[0581] This system is unique in that it allows users to easily diagnose the health of their plants and receive appropriate growing advice.

[0582] Specific examples

[0583] Example 1: When the leaves of a houseplant turn brown

[0584] 1. A user takes a photo of a houseplant whose leaves are turning brown and sends it to the server through the application.

[0585] 2. The server receives the photo and inputs it into an AI image recognition model using TensorFlow.

[0586] 3. The image recognition model produces the analysis result that "the leaves are brown."

[0587] 4. The server sends a query to the user: "I've checked the condition of the leaves. When was the last time you watered them?"

[0588] 5. The user responds, "3 days ago."

[0589] 6. The server looks up the appropriate watering frequency from the MySQL database based on the user's answer.

[0590] 7. The server generates advice such as "It is recommended that this plant be kept out of direct sunlight and watered once a week" and sends it to the user.

[0591] 8. Users take this advice and apply it in practice.

[0592] Example 2: When vegetable disease is suspected

[0593] 1. A user takes a photo of vegetables in their garden that have unnatural spots and sends it to the server through the application.

[0594] 2. The server receives the photo and inputs it into an AI image recognition model using TensorFlow.

[0595] 3. The image recognition model produces the analysis result that "there are spots on the leaf."

[0596] 4. The server asks the user, "I noticed spots on the leaves. Please tell me about the sunlight and recent weather."

[0597] 5. The user responds, "It's sunny and it's been raining a lot lately."

[0598] 6. Based on the user's response, the server retrieves information from a MySQL database about diseases that are more likely to occur during rainy seasons.

[0599] 7. The server generates advice such as "Mold disease is more likely to occur during rainy seasons. It is effective to improve ventilation and use fungicides as needed," and sends it to the user.

[0600] 8. The user takes the advice and applies it.

[0601] Prompt Sentence Examples

[0602] Prompt 1:

[0603] If your houseplant's leaves are turning brown, take a photo of the plant and send the image to an AI model to analyze its health and provide additional information and advice based on its health.

[0604] Prompt Statement 2:

[0605] If you notice spots on your vegetable leaves, take a photo and send the image to the AI ​​model, along with additional information like sunlight and weather conditions, to generate appropriate growing advice.

[0606] In this way, the system quickly and accurately diagnoses the health of plants, providing support to gardening enthusiasts in growing healthy plants.

[0607] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0608] Step 1:

[0609] Users take and send images of plants

[0610] The user captures a video of the plant using a smartphone or tablet. The user opens the dedicated application, selects the image they have taken, and presses the send button. At this time, the input data is the image file of the photographed plant, which is then sent to the server. Specifically, the user uses the camera function in the application to take a picture of the plant and upload it to the server.

[0611] Step 2:

[0612] The server receives and saves the image.

[0613] The server receives the image sent by the user and temporarily stores it. The received image is saved in a dedicated directory and assigned a unique ID. The input data is the image file sent by the user, and this image file is saved in the server's storage. Specifically, the server receives the image file, saves it in storage, and records the file path.

[0614] Step 3:

[0615] The server performs image analysis

[0616] The server inputs the received images into an AI image recognition model. This model uses TensorFlow via a Python script to identify the plant's type and health status based on machine learning algorithms. The input for this step is the path to the saved image file, and the output is the image analysis results in JSON format. Specifically, the server passes the path to the saved image file to the AI ​​image recognition model, which then parses and saves the results in JSON format.

[0617] Step 4:

[0618] The server queries the user for additional information

[0619] Based on the results of image recognition, the server queries the user for more detailed information. The server generates questions such as "How often have you watered your plants recently?" or "How sunny is the area?" and sends them to the user through the application. The input to this step is the image analysis result data, and the output is a query message to be sent to the user. Specifically, the server determines the required information and sends the question to the user through the application.

[0620] Step 5:

[0621] User provides additional information

[0622] The user enters detailed information in response to the received question into the application and sends it to the server. The input data is additional information that the user entered into the application, and this is sent back to the server. A specific example of this is when the user enters information such as "I watered the plants three days ago" and sends it to the server.

[0623] Step 6:

[0624] The server references the database

[0625] The server references the database based on the additional information to obtain cultivation guidelines and problem-solving solutions for each plant. The database used is MySQL, and the required information is obtained using SQL queries. The input data is the user's additional information and the results of image analysis, and the output is the cultivation guidelines and problem-solving solutions obtained from the database. Specifically, the server creates an SQL query based on the user's information and obtains the relevant information from the database.

[0626] Step 7:

[0627] The server generates and sends training advice

[0628] The server integrates the information obtained from the database, the user's additional information, and the image analysis results to generate optimal breeding advice. This advice is then sent to the user through the application. The input data is the user's additional information, the database information, and the image analysis results, and the output is the breeding advice to be sent to the user. Specifically, the server generates advice and sends it to the user.

[0629] Step 8:

[0630] User receives advice and implements it

[0631] The user checks the advice received in the application and follows the instructions. The input data is the cultivation advice sent from the server, and the user performs the action based on this. Specifically, the user reads the advice and actually carries out the instructions, such as changing the location of the plant.

[0632] Through the above processing steps, the system allows users to easily diagnose the health of their plants and receive appropriate growing advice.

[0633] (Application example 1)

[0634] 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."

[0635] Gardening stores and home improvement centers face the problem of taking time to determine the type and health of plants, making it difficult to provide appropriate growing advice immediately, which can lead to lower customer satisfaction and affect the store's credibility.

[0636] 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.

[0637] In this invention, the server includes: a means for a user to take and send an image of a plant; a means for executing an image recognition model to analyze the image received by the server; a means for the server to determine the type and health of the plant based on the image recognition results; a means for the server to query the user for additional information based on the determination results; a means for the user to provide the additional information; a means for the server to refer to a database based on the provided additional information; a means for the server to generate optimal cultivation advice and send it to the user; and a means for a gardening store to allow store staff or visitors to take and send photos of plants and for the server to provide the plant diagnosis results and cultivation advice. This makes it possible for the gardening store to instantly diagnose the health of plants and provide appropriate cultivation advice.

[0638] A "user" is an individual or store staff member who accesses the system to diagnose the health of plants and obtain growing advice.

[0639] A "plant image" is a digital photograph taken by a user and sent to the system to represent the state of the plant.

[0640] The "transmission means" is a communication means by which the user transmits plant images and additional information to the server.

[0641] The "server" is a central computer system that performs plant image analysis, collects additional information, and generates cultivation advice.

[0642] An "image recognition model" is an artificial intelligence model for identifying plant species and health status based on machine learning algorithms.

[0643] The "analysis means" is a means for inputting the plant image received by the server into an image recognition model and analyzing it.

[0644] The "determination means" is a function of the server that determines the type and health condition of a plant based on the results of the image recognition model.

[0645] The "query means" is a function of the server that queries the user for additional information based on the determination result.

[0646] "Additional information" is information provided by the user to understand the current state of the plant in detail, and includes sunlight exposure, watering frequency, weather conditions, etc.

[0647] The "reference means" is a function that allows the server to obtain related information from a database based on the additional information provided.

[0648] The "database" is a collection of information that stores cultivation guidelines and solutions to problems for each plant.

[0649] The "development advice generating means" is a means by which the server integrates the information in the database with the additional information to generate optimal development advice.

[0650] A "gardening store" is a physical store that sells plants and related products, and is a place where users can use the plant diagnostic application.

[0651] "Store staff or visitors" refers to customers or store staff who use the plant diagnostic system at a gardening store.

[0652] System configuration

[0653] This invention is a system that provides plant cultivation advice by combining plant image analysis and additional information collection. This system receives plant images taken and sent by users, analyzes them using an AI image recognition model, and identifies the plant's species and health condition. It then queries the user for any additional information needed, and generates and provides optimal cultivation advice.

[0654] Hardware and software used

[0655] Server: The server is built using a web framework such as Flask or Django. This server plays a central role in receiving images sent by users, analyzing them, querying necessary information, and generating and providing training advice.

[0656] Terminal (smartphone, tablet, etc.): A terminal where the user takes pictures of plants and sends them to the server. It can be implemented as an Android or iOS application.

[0657] Generative AI models: These are machine learning models built using deep learning frameworks such as TensorFlow and PyTorch, and are used for image recognition to identify plant species and health.

[0658] Database: Use a database system such as MySQL or MongoDB to store growing guidelines and problem solutions for each plant.

[0659] Process Overview

[0660] The user takes an image of the plant and sends it to the server via the application. The received image is analyzed by an image recognition model run by the server. Based on the analysis results, the plant's type and health condition are determined, and the user is then queried for additional information based on that information. The additional information provided by the user is compared with a database, and optimal growing advice is generated. The generated advice is notified to the user, who can use it to grow the plant.

[0661] Specific examples

[0662] Example 1: When the leaves of a houseplant turn brown

[0663] 1. A user takes a photo of a houseplant whose leaves are turning brown and sends it to the server through the application.

[0664] 2. The server receives the photo and analyzes the image using a generative AI model.

[0665] 3. The image recognition model produces the analysis result that "the leaves are brown."

[0666] 4. The server sends the query to the user: "I've checked the condition of the leaves. When was the last time you watered them?"

[0667] 5. The user responds, "3 days ago."

[0668] 6. Based on the user's answer, the server looks up the appropriate watering frequency from the database.

[0669] 7. The server generates advice that says, "It is recommended that this plant be kept out of direct sunlight and watered once a week," and sends it to the user.

[0670] 8. Users take this advice and apply it in practice.

[0671] Example 2: When vegetable disease is suspected

[0672] 1. A user takes a photo of vegetables in their garden that have unnatural spots and sends it to the server through the application.

[0673] 2. The server receives the photo and analyzes the image using a generative AI model.

[0674] 3. The image recognition model produces the analysis result that "there are spots on the leaf."

[0675] 4. The server asks the user, "I noticed spots on the leaves. Please tell me about the sunlight and recent weather."

[0676] 5. The user responds, "It's sunny and it's been raining a lot lately."

[0677] 6. Based on the user's answers, the server references information from the database about diseases that are more likely to occur during rainy seasons.

[0678] 7. The server generates advice such as, "Mold disease is more likely to occur during rainy seasons. It is effective to improve ventilation and use fungicides as needed," and sends it to the user.

[0679] 8. The user takes the advice and applies it.

[0680] Prompt Sentence Examples

[0681] "My tomato leaves are turning yellow. When was the last time I watered them?"

[0682] "My rose leaves are turning brown. What's the weather like these days?"

[0683] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0684] Step 1:

[0685] The user takes a picture of a plant and sends it to the server through the application. The input is the image data of the plant taken by the user, and this data is sent to the server. The output is the image data that arrives at the server.

[0686] Step 2:

[0687] The server takes in the received image data and analyzes the image using a generative AI model. The input is the image data received by the server, and the output is the analysis results of the generative AI model, which include information on the plant's type and health condition. Specifically, the image is preprocessed and converted into an appropriate format before being input into the AI ​​model.

[0688] Step 3:

[0689] The server determines the type and health of the plant based on the analysis results of the generated AI model. The input is the analysis result from step 2, and the output is information about the determined plant type and its health condition. Specific operations include decoding the analysis results and converting them into meaningful information.

[0690] Step 4:

[0691] Based on the judgment result, the server queries the user for additional information. The input is the type and health condition of the plant judged in step 3, and the output is the question to be sent to the user. Specifically, the server generates an appropriate prompt sentence according to the plant's condition and sends it to the user's device.

[0692] Step 5:

[0693] The user provides the necessary additional information in response to a query from the server. The input is the question presented to the user, and the output is the additional information the user provides to the server. Specifically, text and options are entered through the terminal application and sent to the server.

[0694] Step 6:

[0695] The server references the database based on the additional information provided by the user. The input is the additional information obtained in step 5, and the output is related information retrieved from the database. Specifically, the server performs a database search using the additional information as a key to obtain the relevant training guidelines and problem solutions.

[0696] Step 7:

[0697] The server integrates the database information with the additional information to generate optimal training advice. The input is the database information obtained in step 6 and the additional information provided by the user, and the output is the generated training advice. Specifically, the information obtained from the database is combined with the user's input and an algorithm is used to generate optimal advice.

[0698] Step 8:

[0699] The server sends the generated training advice to the user. The input is the training advice generated in step 7, and the output is the advice content sent to the user's terminal. Specific operations include converting it into a message format and sending it to the user's terminal.

[0700] 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.

[0701] The present invention relates to a system that combines plant image analysis, additional information collection, and an emotion engine that recognizes the user's emotions to provide optimal plant cultivation advice to the user. This system is composed of a user, a server, a terminal, and an emotion engine. Below, the program processing of this system is explained in natural language, and a detailed description of the embodiment of the invention is given with specific examples.

[0702] System Overview

[0703] In this system, users take pictures of plants and send them to a server via an application. The server inputs the received images into an AI image recognition model to identify the plant's species and its health condition. The server then queries the user for any additional information needed based on the analysis results, and uses an emotion engine to recognize the user's emotions. By integrating the additional information provided by the user, the emotion engine's analysis results, and information from a database referenced by the server, the server generates optimal cultivation advice and sends it to the user.

[0704] Program processing explanation

[0705] 1. The user takes and sends a photo of the plant

[0706] Users use a smartphone or tablet to take a photo of the plant's current condition, and the image is sent to the server via the application.

[0707] 2. The server receives and analyzes the image

[0708] The server receives the images sent by the user, which are then fed into an AI image recognition model that uses machine learning algorithms to identify the plant's type and health status.

[0709] 3. The server queries for additional information based on the analysis results

[0710] Based on the analysis results of the image recognition model, the server queries the user for additional information needed to gain a detailed understanding of the current state of the plant.

[0711] 4. User provides additional information

[0712] In response to a query from the server, the user provides additional information such as exposure to sunlight, frequency of watering, recent weather conditions, etc. This information is sent to the server.

[0713] 5. The server analyzes the user's emotions

[0714] The emotion engine installed on the server analyzes messages and voice data sent by users and recognizes their emotional state. For example, if a user sends a comment such as "My plants haven't been doing well lately, and I'm worried," the emotion is recognized as "worried."

[0715] 6. The server references the database

[0716] Based on the additional information provided and the results of the emotion engine's analysis, the server retrieves relevant information by referencing an internal database, which includes plant-specific cultivation guidelines and solutions to problems.

[0717] 7. The server generates and sends the training advice

[0718] The server combines the information retrieved from the database, the analysis results, and additional information provided by the user to generate optimal parenting advice. Based on the analysis results of the emotion engine, the content and tone of the advice may be adjusted to include softer language or encouraging messages. This advice is then sent to the user, who then notifies the user's chatbot app.

[0719] Specific examples

[0720] Example 1: When the leaves of a houseplant turn brown

[0721] 1. A user takes a photo of a houseplant whose leaves are turning brown and sends it to the server through the application.

[0722] 2. The server receives the photo and inputs it into an AI image recognition model.

[0723] 3. The image recognition model produces the analysis result that "the leaves are brown."

[0724] 4. The server sends a query to the user: "I've checked the condition of the leaves. When was the last time you watered them?"

[0725] 5. The user responds, "3 days ago."

[0726] 6. The emotion engine analyzes the user's message and recognizes that the user is "worried."

[0727] 7. The server consults the database to find the appropriate watering frequency.

[0728] 8. The server generates advice such as "It is recommended that you keep this plant out of direct sunlight and water it once a week. Also, there is no need to worry; if you follow this advice, it will recover its health" and sends it to the user.

[0729] 9. Users take this advice and apply it in practice.

[0730] Example 2: When vegetable disease is suspected

[0731] 1. A user takes a photo of vegetables in their garden that have unnatural spots and sends it to the server through the application.

[0732] 2. The server receives the photo and inputs it into an AI image recognition model.

[0733] 3. The image recognition model produces the analysis result that "there are spots on the leaf."

[0734] 4. The server asks the user, "I noticed spots on the leaves. Please tell me about the sunlight and recent weather."

[0735] 5. The user responds, "It's sunny and it's been raining a lot lately."

[0736] 6. The emotion engine analyzes the user's message and recognizes that the user is feeling "anxiety."

[0737] 7. The server references the database and retrieves information about diseases that are more likely to occur during rainy seasons.

[0738] 8. The server generates advice such as, "Mold disease is more likely to occur during rainy seasons. It is effective to improve ventilation and use fungicides as needed. Don't worry, the problem will be solved if you take action early." and sends it to the user.

[0739] 9. The user takes the advice and applies it.

[0740] In this way, the system quickly and accurately diagnoses the health of plants and provides support to gardeners to grow healthy plants while taking into account the user's emotions.

[0741] The processing flow will be explained below.

[0742] Step 1:

[0743] Users take photos of plants with their smartphones or tablets and use the chatbot app to send the photos to the server.

[0744] Step 2:

[0745] The server receives plant photos submitted by users and formats them in a way that makes them ready for image analysis.

[0746] Step 3:

[0747] The server inputs the received photos into an AI image recognition model, which uses machine learning algorithms to identify the plant's type and health status (e.g., changes in leaf color or signs of disease).

[0748] Step 4:

[0749] The server analyzes the output of the AI ​​image recognition model to determine the plant's current condition, and the analyzed data is compared with the server's internal database.

[0750] Step 5:

[0751] Based on the analysis results, the server generates a message to ask the user for additional information, such as "How much sunlight does the plant get?"

[0752] Step 6:

[0753] The server generates a message and sends it to the user, which notifies the user's chatbot app and prompts for more information.

[0754] Step 7:

[0755] The user responds to queries from the server and provides additional information such as exposure to sunlight, watering frequency, recent weather conditions, etc. This information is sent to the server through the application.

[0756] Step 8:

[0757] The server receives the additional information sent by the user, converts it into a specific format, and stores it in an internal database.

[0758] Step 9:

[0759] An emotion engine implemented on the server analyzes text messages and voice data sent by the user and recognizes the user's emotional state (e.g., anxiety, worry, joy).

[0760] Step 10:

[0761] The server refers to an internal database based on the additional information and the analysis results of the emotion engine to search for appropriate development guidelines and solutions to problems.

[0762] Step 11:

[0763] The server combines information obtained from the database, the results of image analysis, additional information provided by the user, and the results of the emotion engine analysis to generate optimal training advice. The content and tone of the advice are also adjusted based on the results of the emotion engine.

[0764] Step 12:

[0765] The server sends the generated training advice to the user, who is then notified in their chatbot app and given specific advice.

[0766] Step 13:

[0767] The user receives advice from the server and puts the specific cultivation methods suggested into practice, such as changing the location of the plant to avoid direct sunlight or reviewing the frequency of watering.

[0768] Example 2

[0769] 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."

[0770] Conventional plant growing systems have incomplete processes for accurately identifying the condition of plants and providing appropriate growing advice to users. In particular, they lack consideration for identifying the plant's health and the user's emotional state, making it difficult to provide satisfying growing support. Furthermore, there are problems with the systems' ineffective management of additional information provided by users and the ineffective personalization of advice based on emotional analysis. The purpose of this invention is to solve these problems and provide optimal growing advice to users.

[0771] 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.

[0772] In this invention, the server includes a means for a user to take and send an image of a plant, a means for analyzing the image by executing a generative AI model, and a means for identifying the plant's type and health condition based on the results of the image recognition model. This allows the plant's condition to be accurately identified and the user to be asked for detailed additional information based on the analysis results. Furthermore, the server includes a means for analyzing the user's emotions using a sentiment analysis engine and a means for referencing a database based on the provided additional information and sentiment analysis information, making it possible to provide personalized, optimal plant-growing advice to the user. Furthermore, by including a means for generating prompt sentences that provide specific examples when generating plant-growing advice, the server can provide the user with more specific advice and is useful for troubleshooting. This enhances overall support for plant cultivation and is expected to improve user satisfaction.

[0773] "User" refers to an individual who uses the system to take images of plants and transmit the information.

[0774] A "server" refers to a device that analyzes received image data, references a database, and generates and transmits optimal training advice.

[0775] "Generative AI model" refers to a model that uses machine learning algorithms to analyze image data and identify plant species and health conditions.

[0776] "Image recognition model" refers to an algorithm or software that analyzes received image data to identify the type of plant and its health condition.

[0777] "Additional information" refers to information such as sunlight exposure, watering frequency, and recent weather conditions provided by the user to further analyze the health of the plant.

[0778] "Emotion analysis engine" refers to an engine that analyzes text data and voice data provided by a user to recognize the user's emotional state.

[0779] The "database" refers to a collection of information that stores plant-specific growing guidelines, problem-solving solutions, and other related information.

[0780] "Growth advice" refers to instructions and advice on the correct way to grow plants that are generated by the server based on the database and analysis results and provided to the user.

[0781] A "prompt sentence" refers to an advice sentence containing specific examples generated by a generative AI model.

[0782] The present invention relates to a system that combines plant image analysis, additional information collection, and an emotion engine that recognizes the user's emotions to provide optimal plant cultivation advice to the user. This system is composed of a user, a server, a terminal, and an emotion engine.

[0783] System Overview

[0784] The user takes a photo of a plant and sends it to the server via the application. The server inputs the received image into a generative AI model to identify the plant's species and its health condition. The server then queries the user for any additional information needed based on the analysis results and recognizes the user's emotions using an emotion engine. Finally, the server combines the additional information provided by the user, the analysis results of the emotion engine, and information from a database referenced by the server to generate optimal planting advice and send it to the user.

[0785] Hardware and software used

[0786] User device: A smartphone or tablet is used to take pictures of plants and send them to the server via the application.

[0787] Server: A computer system with powerful processing power where the generative AI model and sentiment analysis engine run.

[0788] Generative AI models: Image recognition software based on machine learning algorithms (e.g., TensorFlow, PyTorch).

[0789] Sentiment analysis engine: Software that analyzes a user's emotional state from text or voice (e.g., OpenAI GPT-3, IBM Watson).

[0790] Database: Information storage for plant growing guidelines and problem solutions.

[0791] Specific examples

[0792] Example 1: When the leaves of a houseplant turn brown

[0793] 1. A user takes a photo of a houseplant whose leaves are turning brown and sends it to the server through the application.

[0794] 2. The server receives the photo and inputs it into a generative AI model (using TensorFlow, for example).

[0795] 3. The generative AI model produces the analysis result that "the leaves are turning brown."

[0796] 4. The server sends a query to the user: "I've checked the condition of the leaves. When was the last time you watered them?"

[0797] 5. The user responds, "3 days ago."

[0798] 6. The sentiment analysis engine analyzes the user's message ("I'm worried because my plants haven't been doing well lately") and recognizes that the user is "worried."

[0799] 7. The server consults the database to find the appropriate watering frequency.

[0800] 8. The server generates advice to the user: "It is recommended that you keep this plant out of direct sunlight and water it once a week. There is no need to worry; if you follow this advice, it will recover."

[0801] 9. Users take this advice and apply it in practice.

[0802] Example 2: When vegetable disease is suspected

[0803] 1. A user takes a photo of vegetables in their garden that have unnatural spots and sends it to the server through the application.

[0804] 2. The server receives the photos and inputs them into a generative AI model (using, for example, PyTorch).

[0805] 3. The generative AI model produces the analysis result that "the leaf has spots."

[0806] 4. The server asks the user, "I noticed spots on the leaves. Please tell me about the sunlight and recent weather."

[0807] 5. The user responds, "It's sunny and it's been raining a lot lately."

[0808] 6. The sentiment analysis engine analyzes the user's message ("It's been raining a lot lately, and I'm worried that my vegetables might get sick") and recognizes that the user is feeling "anxious."

[0809] 7. The server references the database and retrieves information about diseases that are more likely to occur during rainy seasons.

[0810] 8. The server generates advice such as, "Mold disease is more likely to occur during rainy seasons. It is effective to improve ventilation and use fungicides as needed. Don't worry, the problem will be solved if you take action early." and sends it to the user.

[0811] 9. The user takes the advice and applies it.

[0812] By taking these steps into consideration, the system can provide highly accurate training advice by comprehensively considering the information provided by the user and their emotional state.

[0813] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0814] Step 1:

[0815] The user takes a picture of the plant and sends it.

[0816] Specific operation: The user takes a photo of a plant using a smartphone or tablet, and the image is sent to the server via the application.

[0817] Input: Plant image data.

[0818] Output: Image data sent to the server.

[0819] Step 2:

[0820] The server receives the images and analyzes them using a generative AI model.

[0821] How it works: The server inputs the received image data into a generative AI model such as TensorFlow or PyTorch, which processes the data to identify the plant species and its health status.

[0822] Input: Received plant image data.

[0823] Output: Analysis of plant type and health.

[0824] Step 3:

[0825] The server queries the user for additional information based on the results of image recognition.

[0826] How it works: Based on the results of the generative AI model's analysis, the server generates additional information to understand the plant's current condition in more detail. This additional information is sent to the user as a text message. For example, it may ask, "I've checked the condition of the leaves. When was the last time you watered them?"

[0827] Input: Analysis results of the image recognition model.

[0828] Output: A message asking the user for more information.

[0829] Step 4:

[0830] The user provides additional information.

[0831] Specific operation: In response to queries from the server, the user inputs information such as sunlight exposure, watering frequency, and recent weather conditions, and sends it to the server via the application.

[0832] Input: A query message from the server as a trigger.

[0833] Output: Additional information sent to the server.

[0834] Step 5:

[0835] The server receives the additional information provided by the user and analyzes the user's emotions using a sentiment analysis engine.

[0836] Specific operation: The server inputs the text and voice included in the additional information into an emotion analysis engine (e.g., OpenAI GPT-3 or IBM Watson) to analyze the user's emotional state. For example, if a user sends a message saying, "My plants haven't been doing well lately, and I'm worried," this message will be recognized as expressing "worry."

[0837] Input: Additional information provided by the user.

[0838] Output: Analysis results about the user's emotional state.

[0839] Step 6:

[0840] The server references the database based on the analysis results.

[0841] What it does: Based on the additional information and the results of the sentiment analysis engine, the server retrieves relevant information from an internal database, which contains plant-specific growing guidelines and problem-solving solutions. For example, it uses an SQL query to search for the appropriate growing guidelines.

[0842] Input: Additional information provided by the user and the results of the sentiment analysis engine.

[0843] Output: Relevant information retrieved from the internal database.

[0844] Step 7:

[0845] The server generates and transmits the development advice to the user.

[0846] Specific operation: The server combines information obtained from the database, analysis results, and additional information provided by the user to generate optimal growing advice. The generated advice includes specific examples as prompts. For example, "It is recommended that this plant be protected from direct sunlight and watered once a week. There is no need to worry. If you follow this advice, it will recover its health."

[0847] Input: Information retrieved from the database, analysis results, and additional information.

[0848] Output: Development advice notified to the user.

[0849] Through this process, users receive detailed advice on the health of their plants and can take specific actions.

[0850] (Application example 2)

[0851] 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."

[0852] Current plant cultivation support systems can analyze the type and health of plants, but they cannot provide flexible advice based on the user's emotions. Furthermore, there is a lack of systems for food delivery that provide advice on the nutritional value and health aspects of food. This creates a need for a comprehensive system to support plant cultivation and healthy eating.

[0853] 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 a user to take and send an image of a plant or food, means for executing an image recognition model to analyze the image received by the server, and means for analyzing the user's emotions using an emotion engine and adjusting the content and tone of advice. This enables the user to quickly and accurately diagnose the health condition of the plant or food and provide cultivation or food advice that takes the user's emotions into consideration.

[0854] A "user" is someone who uses the system to take images of plants or food and provide information about them.

[0855] "Plants" are living things such as green plants and flowers that are cultivated by the user.

[0856] "Food" refers to food such as dishes or ingredients that the user photographs.

[0857] "Means for taking and transmitting images" refers to a function that allows a user to take an image of a plant or food using a device such as a smartphone and transmit that image to a server.

[0858] The "server" is a computer system that receives and analyzes images, references a database, and generates optimal advice.

[0859] An "image recognition model" is an analytical method that uses machine learning algorithms to identify the type and health status of plants or food.

[0860] "Means for determining status" refers to the function of determining the current health status of a plant or food based on the analysis results of an image recognition model.

[0861] "Means for requesting additional information" refers to a function that allows the server to request missing information from the user based on the analysis results.

[0862] "Means for providing additional information" refers to a function that allows users to provide information such as sunlight exposure, watering frequency, and ingredients used in response to inquiries from the server.

[0863] "Means for referencing a database" refers to the function by which the server searches an internal database based on the additional information provided and obtains relevant growing guidelines and nutritional information.

[0864] "Means for generating and transmitting raising or food advice" refers to a function that generates optimal raising or food advice based on the information and analysis results acquired by the server and transmits it to the user.

[0865] An "emotion engine" is software that uses natural language processing technology to recognize and analyze a user's emotional state.

[0866] "Means for analyzing emotions and adjusting the content and tone of advice" refers to a function that provides the user with advice of appropriate content and tone based on the user's emotions analyzed by the emotion engine.

[0867] MODE FOR CARRYING OUT THE INVENTION

[0868] To put the present invention into practice, we will explain the specific configuration and method of a system that allows users to take and send images of plants or food. This system is built by combining a user's terminal, a server, a database, and an emotion engine.

[0869] System Configuration

[0870] 1. User Device:

[0871] Using a smartphone or tablet, users take pictures of plants or food and send them to a server via an application.

[0872] 2. Server:

[0873] The server analyzes the received image, queries the user for additional information, and generates optimal nutrition or dietary advice based on the acquired information by referencing a database. It also runs an emotion engine to analyze the user's emotions and adjust the content and tone of the advice.

[0874] 3. Database:

[0875] Databases such as MySQL and MongoDB are used to store growing guidelines, nutritional information, and problem solutions for each plant and food.

[0876] 4. Emotion Engine:

[0877] It uses NLP (Natural Language Processing) APIs to analyze user sentiment and tailor advice accordingly.

[0878] 5. Image Recognition Model:

[0879] TensorFlow and PyTorch are used to run machine learning models to analyze images of plants or food.

[0880] Program processing explanation

[0881] The server receives the image sent by the user and inputs it into an image recognition model to identify the type of plant or food and its health condition. The server then queries the user for any additional information needed based on the analysis results. The user provides the server with information such as sunlight exposure, watering frequency, and ingredients used. The server then uses an emotion engine to analyze the user's emotions and recognize their emotional state.

[0882] The server then uses this information to retrieve relevant information from a database, which includes growing guidelines, nutritional information, and solutions for each plant or food. The server then integrates the retrieved data, analysis results, and the user's emotional state to generate optimal growing or food advice. This advice is then sent to the user.

[0883] Examples of concrete examples and prompts

[0884] Example 1: When the leaves of a houseplant turn brown

[0885] 1. A user takes a photo of a houseplant whose leaves are turning brown and sends it to the server through the application.

[0886] 2. The server receives the photo and inputs it into an AI image recognition model.

[0887] 3. The image recognition model produces the analysis result that "the leaves are brown."

[0888] 4. The server sends a query to the user: "I've checked the condition of the leaves. When was the last time you watered them?"

[0889] 5. The user responds, "3 days ago."

[0890] 6. The emotion engine analyzes the user's message and recognizes that the user is "worried."

[0891] 7. The server consults the database to find the appropriate watering frequency.

[0892] 8. The server generates advice such as "It is recommended that you keep this plant out of direct sunlight and water it once a week. Also, there is no need to worry; if you follow this advice, it will recover its health" and sends it to the user.

[0893] 9. Users take this advice and apply it in practice.

[0894] Example 2: If you are concerned about the nutritional value of a dish

[0895] 1. A user takes a photo of a healthy salad and sends it with the comment, "I want to continue eating healthy."

[0896] 2. The server receives the photo, determines it is a "salad," and retrieves nutritional information for the main ingredients used (e.g., lettuce, tomato, cucumber) from the database.

[0897] 3. The emotion engine recognizes the user's emotional state of "motivation."

[0898] 4. The server integrates the database information with the emotional state, generates advice for the user, such as "This salad is very healthy, especially rich in vitamin C. Keep it up!", and sends it to the user.

[0899] Prompt Sentence Examples

[0900] "Please analyze the food in this image to get the ingredient information."

[0901] "Identify the emotion a user feels when they say 'I'm very happy.'"

[0902] "Generate personalized health advice based on analytics results and user sentiment."

[0903] Through these specific examples, users can quickly and accurately diagnose the health of plants or food and receive emotionally sensitive advice.

[0904] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0905] Step 1:

[0906] A user takes an image of a plant or food item and sends the image to a server through the application.

[0907] Input: An image of a plant or food

[0908] Output: Image data sent to the server

[0909] Specific operation: Take a picture using the camera on the user device and press the send button in the application

[0910] Step 2:

[0911] The server inputs the images received from the user into an image recognition model for analysis.

[0912] Input: Received image data

[0913] Output: Image recognition results (identification of plant or food type and health status)

[0914] Specific operation: The server inputs image data into an AI image recognition model (e.g., TensorFlow or PyTorch) and obtains the analysis results.

[0915] Step 3:

[0916] The server queries the user for missing information based on the results of image recognition.

[0917] Input: Image recognition results (type of plant or food and health status)

[0918] Output: A message asking for more information

[0919] Specific operation: Based on the analysis results, the server generates a message to send additional information (e.g., sunlight, watering frequency, ingredients used) and sends it to the user's device.

[0920] Step 4:

[0921] The user provides additional information in response to a query from the server.

[0922] Input: Query message from the server

[0923] Output: Additional information provided

[0924] What happens: The user answers questions through the application and sends the information to the server.

[0925] Step 5:

[0926] The server uses an emotion engine to analyze the user's emotions.

[0927] Input: User's message or voice data

[0928] Output: Sentiment analysis results (e.g., worry, satisfaction, anxiety, etc.)

[0929] Specific operation: The server inputs the user's message and voice data into an emotion engine (e.g., NLP API) to identify the emotional state.

[0930] Step 6:

[0931] Using the additional information acquired by the server and the results of emotion analysis, the server references the database to acquire related information.

[0932] Input: Additional information and sentiment analysis results

[0933] Output: Growing guidelines or nutritional information

[0934] What happens: The server searches an internal database (e.g., MySQL or MongoDB) to retrieve relevant growing guidelines and nutritional information.

[0935] Step 7:

[0936] The server integrates the acquired data, analysis results, and emotional state to generate optimal development or food advice.

[0937] Input: Nutritional guidelines or nutritional information, additional information, emotional state

[0938] Output: personalized advice

[0939] What it does: The server runs an algorithm that integrates the data and generates personalized nutrition or dietary advice.

[0940] Step 8:

[0941] The server sends the generated advice to the user.

[0942] Input: personalized advice

[0943] Output: Notification message to the user's terminal

[0944] What happens: The server generates a message containing the advice and sends it to the user's application.

[0945] In this way, users can quickly and accurately diagnose the health of their plants or food products and receive emotionally sensitive advice.

[0946] 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.

[0947] 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.

[0948] 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.

[0949] [Third embodiment]

[0950] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0951] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0952] 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).

[0953] 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.

[0954] 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.

[0955] 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).

[0956] 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.

[0957] 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.

[0958] 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.

[0959] 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.

[0960] 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.

[0961] 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."

[0962] The present invention relates to a system that combines image analysis of plants with the collection of additional information to provide users with optimal plant cultivation advice. This system is composed of a user, a server, and a terminal. Below, the program processing of this system is explained in natural language, and a detailed description of the mode for carrying out the invention is given with specific examples.

[0963] System Overview

[0964] In this system, users take pictures of plants and send them to a server via an application. The server inputs the received images into an AI image recognition model to identify the plant's species and its health condition. The server then queries the user for any additional information needed based on the analysis results. By integrating the additional information provided by the user with information from a database referenced by the server, the server generates optimal cultivation advice and sends it to the user.

[0965] Program processing explanation

[0966] 1. The user takes and sends a photo of the plant

[0967] Users use a smartphone or tablet to take a photo of the plant's current condition, and the image is sent to the server via the application.

[0968] 2. The server receives and analyzes the image

[0969] The server receives the images sent by the user, which are then fed into an AI image recognition model that uses machine learning algorithms to identify the plant's type and health status.

[0970] 3. The server queries for additional information based on the analysis results

[0971] Based on the analysis results of the image recognition model, the server queries the user for additional information needed to gain a detailed understanding of the current state of the plant.

[0972] 4. User provides additional information

[0973] In response to a query from the server, the user provides additional information such as exposure to sunlight, frequency of watering, recent weather conditions, etc. This information is sent to the server.

[0974] 5. The server references the database

[0975] The server uses the additional information provided to retrieve relevant information from a database, which includes plant-specific growing guidelines and solutions to problems.

[0976] 6. The server generates and sends the training advice

[0977] The server combines the information retrieved from the database, the additional information provided, and the analysis results to generate optimal breeding advice, which is then sent to the user.

[0978] Specific examples

[0979] Example 1: When the leaves of a houseplant turn brown

[0980] 1. A user takes a photo of a houseplant whose leaves are turning brown and sends it to the server through the application.

[0981] 2. The server receives the photo and inputs it into an AI image recognition model.

[0982] 3. The image recognition model produces the analysis result that "the leaves are brown."

[0983] 4. The server sends a query to the user: "I've checked the condition of the leaves. When was the last time you watered them?"

[0984] 5. The user responds, "3 days ago."

[0985] 6. The server uses the user's answer to look up the appropriate watering frequency from the database.

[0986] 7. The server generates advice that says, "It is recommended that this plant be kept out of direct sunlight and watered once a week," and sends it to the user.

[0987] 8. Users take this advice and apply it in practice.

[0988] Example 2: When vegetable disease is suspected

[0989] 1. A user takes a photo of vegetables in their garden that have unnatural spots and sends it to the server through the application.

[0990] 2. The server receives the photo and inputs it into an AI image recognition model.

[0991] 3. The image recognition model produces the analysis result that "there are spots on the leaf."

[0992] 4. The server asks the user, "I noticed spots on the leaves. Please tell me about the sunlight and recent weather."

[0993] 5. The user responds, "It's sunny and it's been raining a lot lately."

[0994] 6. Based on the user's answers, the server references information from the database about diseases that are more likely to occur during rainy seasons.

[0995] 7. The server generates advice such as, "Mold disease is more likely to occur during rainy seasons. It is effective to improve ventilation and use fungicides as needed," and sends it to the user.

[0996] 8. The user takes the advice and applies it.

[0997] This system quickly and accurately diagnoses the health of plants, providing support to gardening enthusiasts to grow healthy plants.

[0998] The processing flow will be explained below.

[0999] Step 1:

[1000] Users take a photo of the plant and upload and send it to the chatbot app using their smartphone or tablet.

[1001] Step 2:

[1002] The server receives plant photos sent by users, converts them into a specific format, and prepares them for image analysis.

[1003] Step 3:

[1004] The server inputs the received images into an AI image recognition model, which identifies the plant's type and health status (e.g., changes in leaf color, signs of disease, etc.).

[1005] Step 4:

[1006] The server analyzes the output of the AI ​​image recognition model to determine the plant's condition, which involves formalizing the analysis results and comparing them with a database stored on the server.

[1007] Step 5:

[1008] Based on the analysis, the server generates a message asking the user for additional information, such as "How much sunlight does this plant get?"

[1009] Step 6:

[1010] The server generates a message and sends it to the user, which notifies the user's chatbot app and prompts for more information.

[1011] Step 7:

[1012] The user provides additional information in response to a question posed by the server, for example, "It's sunny and it's been raining a lot lately."

[1013] Step 8:

[1014] The server receives additional information from the user, which is stored in a database within the server and converted into the appropriate format.

[1015] Step 9:

[1016] The server references its internal database based on the additional information, searches for appropriate training advice and problem solutions, and extracts the most appropriate information.

[1017] Step 10:

[1018] The server integrates the information obtained from the database, the analysis results, and additional information provided by the user to generate optimal training advice.

[1019] Step 11:

[1020] The server sends the generated training advice to the user, who is then notified in their chatbot app and the advice is displayed.

[1021] Step 12:

[1022] The user receives advice from the server and puts into practice specific cultivation methods, such as moving the plant to avoid direct sunlight.

[1023] Example 1

[1024] 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."

[1025] In conventional plant cultivation, it is difficult for users to accurately grasp the health condition of plants and quickly take appropriate measures. In addition, since ordinary users do not have specialized knowledge of plants, it is difficult to accurately diagnose the condition of plants and find the optimal cultivation method.

[1026] 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.

[1027] In this invention, the server includes means for a user to acquire and transmit images of plants using a camera, means for the server to store the received images, means for running an AI image recognition model to analyze the stored images, means for the server to identify the state of the plant based on the image recognition results, means for the server to query the user for additional information based on the identification results, means for the user to input and transmit the additional information, means for the server to refer to a database based on the provided additional information, and means for the server to synthesize the information in the database, the additional information, and the analysis results to generate optimal instructions and communicate them to the user. This allows the user to easily diagnose the health of their plants and receive appropriate cultivation advice.

[1028] A "user" is an individual or organization that uses the system and is responsible for acquiring images of plants and transmitting them to the server.

[1029] A "photography device" is an electronic device, such as a smartphone or tablet, that captures images of plants and transmits those images to the system.

[1030] "Video" refers to images or videos of plants captured by a user using a camera.

[1031] "Server" is a central computer system that receives, stores, and analyzes user-submitted video.

[1032] An "AI image recognition model" is an artificial intelligence program that uses machine learning algorithms to identify plant species and health conditions.

[1033] A "database" is a collection of information that systematically stores information, including cultivation guidelines and solutions for each plant, and that can be referenced by a server.

[1034] "Identification" is the process by which an AI image recognition model analyzes video footage, identifies the type of plant and its health condition, and generates a judgment result.

[1035] "Additional information" is detailed information related to plant cultivation that the user provides in response to a query from the server.

[1036] "Growth advice" is optimal instructions for keeping plants healthy, generated by the server by integrating information from the database, additional information, and analysis results.

[1037] The present invention is a system that combines image analysis of plants with the collection of additional information to provide users with optimal plant cultivation advice. This system is composed of users, a server, and terminals.

[1038] Users first capture images of plants using a camera such as a smartphone or tablet, and then send the images to the server via a dedicated application. The camera can be a standard smartphone or tablet equipped with a high-resolution camera.

[1039] The server temporarily stores the received video and runs an AI image recognition model using TensorFlow via a Python script. This identifies the type of plant and its health condition from the video. This image recognition model is trained based on machine learning algorithms, enabling highly accurate analysis.

[1040] Next, the server queries the user for additional information based on the image recognition results, such as "How often have you watered your plants recently?" or "How sunny is the area?", and sends the questions to the user via the application.

[1041] The user enters detailed information in response to these questions and submits it back to the server, which then retrieves the additional information provided by the user.

[1042] The server then consults a MySQL database to retrieve plant-specific cultivation guidelines and solutions. By combining the retrieved information, additional information, and the results of image recognition, the server generates optimal cultivation advice and sends it to the user via the application.

[1043] This system is unique in that it allows users to easily diagnose the health of their plants and receive appropriate growing advice.

[1044] Specific examples

[1045] Example 1: When the leaves of a houseplant turn brown

[1046] 1. A user takes a photo of a houseplant whose leaves are turning brown and sends it to the server through the application.

[1047] 2. The server receives the photo and inputs it into an AI image recognition model using TensorFlow.

[1048] 3. The image recognition model produces the analysis result that "the leaves are brown."

[1049] 4. The server sends a query to the user: "I've checked the condition of the leaves. When was the last time you watered them?"

[1050] 5. The user responds, "3 days ago."

[1051] 6. The server looks up the appropriate watering frequency from the MySQL database based on the user's answer.

[1052] 7. The server generates advice such as "It is recommended that this plant be kept out of direct sunlight and watered once a week" and sends it to the user.

[1053] 8. Users take this advice and apply it in practice.

[1054] Example 2: When vegetable disease is suspected

[1055] 1. A user takes a photo of vegetables in their garden that have unnatural spots and sends it to the server through the application.

[1056] 2. The server receives the photo and inputs it into an AI image recognition model using TensorFlow.

[1057] 3. The image recognition model produces the analysis result that "there are spots on the leaf."

[1058] 4. The server asks the user, "I noticed spots on the leaves. Please tell me about the sunlight and recent weather."

[1059] 5. The user responds, "It's sunny and it's been raining a lot lately."

[1060] 6. Based on the user's response, the server retrieves information from a MySQL database about diseases that are more likely to occur during rainy seasons.

[1061] 7. The server generates advice such as "Mold disease is more likely to occur during rainy seasons. It is effective to improve ventilation and use fungicides as needed," and sends it to the user.

[1062] 8. The user takes the advice and applies it.

[1063] Prompt Sentence Examples

[1064] Prompt 1:

[1065] If your houseplant's leaves are turning brown, take a photo of the plant and send the image to an AI model to analyze its health and provide additional information and advice based on its health.

[1066] Prompt Statement 2:

[1067] If you notice spots on your vegetable leaves, take a photo and send the image to the AI ​​model, along with additional information like sunlight and weather conditions, to generate appropriate growing advice.

[1068] In this way, the system quickly and accurately diagnoses the health of plants, providing support to gardening enthusiasts in growing healthy plants.

[1069] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1070] Step 1:

[1071] Users take and send images of plants

[1072] The user captures a video of the plant using a smartphone or tablet. The user opens the dedicated application, selects the image they have taken, and presses the send button. At this time, the input data is the image file of the photographed plant, which is then sent to the server. Specifically, the user uses the camera function in the application to take a picture of the plant and upload it to the server.

[1073] Step 2:

[1074] The server receives and saves the image.

[1075] The server receives the image sent by the user and temporarily stores it. The received image is saved in a dedicated directory and assigned a unique ID. The input data is the image file sent by the user, and this image file is saved in the server's storage. Specifically, the server receives the image file, saves it in storage, and records the file path.

[1076] Step 3:

[1077] The server performs image analysis

[1078] The server inputs the received images into an AI image recognition model. This model uses TensorFlow via a Python script to identify the plant's type and health status based on machine learning algorithms. The input for this step is the path to the saved image file, and the output is the image analysis results in JSON format. Specifically, the server passes the path to the saved image file to the AI ​​image recognition model, which then parses and saves the results in JSON format.

[1079] Step 4:

[1080] The server queries the user for additional information

[1081] Based on the results of image recognition, the server queries the user for more detailed information. The server generates questions such as "How often have you watered your plants recently?" or "How sunny is the area?" and sends them to the user through the application. The input to this step is the image analysis result data, and the output is a query message to be sent to the user. Specifically, the server determines the required information and sends the question to the user through the application.

[1082] Step 5:

[1083] User provides additional information

[1084] The user enters detailed information in response to the received question into the application and sends it to the server. The input data is additional information that the user entered into the application, and this is sent back to the server. A specific example of this is when the user enters information such as "I watered the plants three days ago" and sends it to the server.

[1085] Step 6:

[1086] The server references the database

[1087] The server references the database based on the additional information to obtain cultivation guidelines and problem-solving solutions for each plant. The database used is MySQL, and the required information is obtained using SQL queries. The input data is the user's additional information and the results of image analysis, and the output is the cultivation guidelines and problem-solving solutions obtained from the database. Specifically, the server creates an SQL query based on the user's information and obtains the relevant information from the database.

[1088] Step 7:

[1089] The server generates and sends training advice

[1090] The server integrates the information obtained from the database, the user's additional information, and the image analysis results to generate optimal breeding advice. This advice is then sent to the user through the application. The input data is the user's additional information, the database information, and the image analysis results, and the output is the breeding advice to be sent to the user. Specifically, the server generates advice and sends it to the user.

[1091] Step 8:

[1092] User receives advice and implements it

[1093] The user checks the advice received in the application and follows the instructions. The input data is the cultivation advice sent from the server, and the user performs the action based on this. Specifically, the user reads the advice and actually carries out the instructions, such as changing the location of the plant.

[1094] Through the above processing steps, the system allows users to easily diagnose the health of their plants and receive appropriate growing advice.

[1095] (Application example 1)

[1096] 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."

[1097] Gardening stores and home improvement centers face the problem of taking time to determine the type and health of plants, making it difficult to provide appropriate growing advice immediately, which can lead to lower customer satisfaction and affect the store's credibility.

[1098] 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.

[1099] In this invention, the server includes: a means for a user to take and send an image of a plant; a means for executing an image recognition model to analyze the image received by the server; a means for the server to determine the type and health of the plant based on the image recognition results; a means for the server to query the user for additional information based on the determination results; a means for the user to provide the additional information; a means for the server to refer to a database based on the provided additional information; a means for the server to generate optimal cultivation advice and send it to the user; and a means for a gardening store to allow store staff or visitors to take and send photos of plants and for the server to provide the plant diagnosis results and cultivation advice. This makes it possible for the gardening store to instantly diagnose the health of plants and provide appropriate cultivation advice.

[1100] A "user" is an individual or store staff member who accesses the system to diagnose the health of plants and obtain growing advice.

[1101] A "plant image" is a digital photograph taken by a user and sent to the system to represent the state of the plant.

[1102] The "transmission means" is a communication means by which the user transmits plant images and additional information to the server.

[1103] The "server" is a central computer system that performs plant image analysis, collects additional information, and generates cultivation advice.

[1104] An "image recognition model" is an artificial intelligence model for identifying plant species and health status based on machine learning algorithms.

[1105] The "analysis means" is a means for inputting the plant image received by the server into an image recognition model and analyzing it.

[1106] The "determination means" is a function of the server that determines the type and health condition of a plant based on the results of the image recognition model.

[1107] The "query means" is a function of the server that queries the user for additional information based on the determination result.

[1108] "Additional information" is information provided by the user to understand the current state of the plant in detail, and includes sunlight exposure, watering frequency, weather conditions, etc.

[1109] The "reference means" is a function that allows the server to obtain related information from a database based on the additional information provided.

[1110] The "database" is a collection of information that stores cultivation guidelines and solutions to problems for each plant.

[1111] The "development advice generating means" is a means by which the server integrates the information in the database with the additional information to generate optimal development advice.

[1112] A "gardening store" is a physical store that sells plants and related products, and is a place where users can use the plant diagnostic application.

[1113] "Store staff or visitors" refers to customers or store staff who use the plant diagnostic system at a gardening store.

[1114] System configuration

[1115] This invention is a system that provides plant cultivation advice by combining plant image analysis and additional information collection. This system receives plant images taken and sent by users, analyzes them using an AI image recognition model, and identifies the plant's species and health condition. It then queries the user for any additional information needed, and generates and provides optimal cultivation advice.

[1116] Hardware and software used

[1117] Server: The server is built using a web framework such as Flask or Django. This server plays a central role in receiving images sent by users, analyzing them, querying necessary information, and generating and providing training advice.

[1118] Terminal (smartphone, tablet, etc.): A terminal where the user takes pictures of plants and sends them to the server. It can be implemented as an Android or iOS application.

[1119] Generative AI models: These are machine learning models built using deep learning frameworks such as TensorFlow and PyTorch, and are used for image recognition to identify plant species and health.

[1120] Database: Use a database system such as MySQL or MongoDB to store growing guidelines and problem solutions for each plant.

[1121] Process Overview

[1122] The user takes an image of the plant and sends it to the server via the application. The received image is analyzed by an image recognition model run by the server. Based on the analysis results, the plant's type and health condition are determined, and the user is then queried for additional information based on that information. The additional information provided by the user is compared with a database, and optimal growing advice is generated. The generated advice is notified to the user, who can use it to grow the plant.

[1123] Specific examples

[1124] Example 1: When the leaves of a houseplant turn brown

[1125] 1. A user takes a photo of a houseplant whose leaves are turning brown and sends it to the server through the application.

[1126] 2. The server receives the photo and analyzes the image using a generative AI model.

[1127] 3. The image recognition model produces the analysis result that "the leaves are brown."

[1128] 4. The server sends the query to the user: "I've checked the condition of the leaves. When was the last time you watered them?"

[1129] 5. The user responds, "3 days ago."

[1130] 6. Based on the user's answer, the server looks up the appropriate watering frequency from the database.

[1131] 7. The server generates advice that says, "It is recommended that this plant be kept out of direct sunlight and watered once a week," and sends it to the user.

[1132] 8. Users take this advice and apply it in practice.

[1133] Example 2: When vegetable disease is suspected

[1134] 1. A user takes a photo of vegetables in their garden that have unnatural spots and sends it to the server through the application.

[1135] 2. The server receives the photo and analyzes the image using a generative AI model.

[1136] 3. The image recognition model produces the analysis result that "there are spots on the leaf."

[1137] 4. The server asks the user, "I noticed spots on the leaves. Please tell me about the sunlight and recent weather."

[1138] 5. The user responds, "It's sunny and it's been raining a lot lately."

[1139] 6. Based on the user's answers, the server references information from the database about diseases that are more likely to occur during rainy seasons.

[1140] 7. The server generates advice such as, "Mold disease is more likely to occur during rainy seasons. It is effective to improve ventilation and use fungicides as needed," and sends it to the user.

[1141] 8. The user takes the advice and applies it.

[1142] Prompt Sentence Examples

[1143] "My tomato leaves are turning yellow. When was the last time I watered them?"

[1144] "My rose leaves are turning brown. What's the weather like these days?"

[1145] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1146] Step 1:

[1147] The user takes a picture of a plant and sends it to the server through the application. The input is the image data of the plant taken by the user, and this data is sent to the server. The output is the image data that arrives at the server.

[1148] Step 2:

[1149] The server takes in the received image data and analyzes the image using a generative AI model. The input is the image data received by the server, and the output is the analysis results of the generative AI model, which include information on the plant's type and health condition. Specifically, the image is preprocessed and converted into an appropriate format before being input into the AI ​​model.

[1150] Step 3:

[1151] The server determines the type and health of the plant based on the analysis results of the generated AI model. The input is the analysis result from step 2, and the output is information about the determined plant type and its health condition. Specific operations include decoding the analysis results and converting them into meaningful information.

[1152] Step 4:

[1153] Based on the judgment result, the server queries the user for additional information. The input is the type and health condition of the plant judged in step 3, and the output is the question to be sent to the user. Specifically, the server generates an appropriate prompt sentence according to the plant's condition and sends it to the user's device.

[1154] Step 5:

[1155] The user provides the necessary additional information in response to a query from the server. The input is the question presented to the user, and the output is the additional information the user provides to the server. Specifically, text and options are entered through the terminal application and sent to the server.

[1156] Step 6:

[1157] The server references the database based on the additional information provided by the user. The input is the additional information obtained in step 5, and the output is related information retrieved from the database. Specifically, the server performs a database search using the additional information as a key to obtain the relevant training guidelines and problem solutions.

[1158] Step 7:

[1159] The server integrates the database information with the additional information to generate optimal training advice. The input is the database information obtained in step 6 and the additional information provided by the user, and the output is the generated training advice. Specifically, the information obtained from the database is combined with the user's input and an algorithm is used to generate optimal advice.

[1160] Step 8:

[1161] The server sends the generated training advice to the user. The input is the training advice generated in step 7, and the output is the advice content sent to the user's terminal. Specific operations include converting it into a message format and sending it to the user's terminal.

[1162] 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.

[1163] The present invention relates to a system that combines plant image analysis, additional information collection, and an emotion engine that recognizes the user's emotions to provide optimal plant cultivation advice to the user. This system is composed of a user, a server, a terminal, and an emotion engine. Below, the program processing of this system is explained in natural language, and a detailed description of the embodiment of the invention is given with specific examples.

[1164] System Overview

[1165] In this system, users take pictures of plants and send them to a server via an application. The server inputs the received images into an AI image recognition model to identify the plant's species and its health condition. The server then queries the user for any additional information needed based on the analysis results, and uses an emotion engine to recognize the user's emotions. By integrating the additional information provided by the user, the emotion engine's analysis results, and information from a database referenced by the server, the server generates optimal cultivation advice and sends it to the user.

[1166] Program processing explanation

[1167] 1. The user takes and sends a photo of the plant

[1168] Users use a smartphone or tablet to take a photo of the plant's current condition, and the image is sent to the server via the application.

[1169] 2. The server receives and analyzes the image

[1170] The server receives the images sent by the user, which are then fed into an AI image recognition model that uses machine learning algorithms to identify the plant's type and health status.

[1171] 3. The server queries for additional information based on the analysis results

[1172] Based on the analysis results of the image recognition model, the server queries the user for additional information needed to gain a detailed understanding of the current state of the plant.

[1173] 4. User provides additional information

[1174] In response to a query from the server, the user provides additional information such as exposure to sunlight, frequency of watering, recent weather conditions, etc. This information is sent to the server.

[1175] 5. The server analyzes the user's emotions

[1176] The emotion engine installed on the server analyzes messages and voice data sent by users and recognizes their emotional state. For example, if a user sends a comment such as "My plants haven't been doing well lately, and I'm worried," the emotion is recognized as "worried."

[1177] 6. The server references the database

[1178] Based on the additional information provided and the results of the emotion engine's analysis, the server retrieves relevant information by referencing an internal database, which includes plant-specific cultivation guidelines and solutions to problems.

[1179] 7. The server generates and sends the training advice

[1180] The server combines the information retrieved from the database, the analysis results, and additional information provided by the user to generate optimal parenting advice. Based on the analysis results of the emotion engine, the content and tone of the advice may be adjusted to include softer language or encouraging messages. This advice is then sent to the user, who then notifies the user's chatbot app.

[1181] Specific examples

[1182] Example 1: When the leaves of a houseplant turn brown

[1183] 1. A user takes a photo of a houseplant whose leaves are turning brown and sends it to the server through the application.

[1184] 2. The server receives the photo and inputs it into an AI image recognition model.

[1185] 3. The image recognition model produces the analysis result that "the leaves are brown."

[1186] 4. The server sends a query to the user: "I've checked the condition of the leaves. When was the last time you watered them?"

[1187] 5. The user responds, "3 days ago."

[1188] 6. The emotion engine analyzes the user's message and recognizes that the user is "worried."

[1189] 7. The server consults the database to find the appropriate watering frequency.

[1190] 8. The server generates advice such as "It is recommended that you keep this plant out of direct sunlight and water it once a week. Also, there is no need to worry; if you follow this advice, it will recover its health" and sends it to the user.

[1191] 9. Users take this advice and apply it in practice.

[1192] Example 2: When vegetable disease is suspected

[1193] 1. A user takes a photo of vegetables in their garden that have unnatural spots and sends it to the server through the application.

[1194] 2. The server receives the photo and inputs it into an AI image recognition model.

[1195] 3. The image recognition model produces the analysis result that "there are spots on the leaf."

[1196] 4. The server asks the user, "I noticed spots on the leaves. Please tell me about the sunlight and recent weather."

[1197] 5. The user responds, "It's sunny and it's been raining a lot lately."

[1198] 6. The emotion engine analyzes the user's message and recognizes that the user is feeling "anxiety."

[1199] 7. The server references the database and retrieves information about diseases that are more likely to occur during rainy seasons.

[1200] 8. The server generates advice such as, "Mold disease is more likely to occur during rainy seasons. It is effective to improve ventilation and use fungicides as needed. Don't worry, the problem will be solved if you take action early." and sends it to the user.

[1201] 9. The user takes the advice and applies it.

[1202] In this way, the system quickly and accurately diagnoses the health of plants and provides support to gardeners to grow healthy plants while taking into account the user's emotions.

[1203] The processing flow will be explained below.

[1204] Step 1:

[1205] Users take photos of plants with their smartphones or tablets and use the chatbot app to send the photos to the server.

[1206] Step 2:

[1207] The server receives plant photos submitted by users and formats them in a way that makes them ready for image analysis.

[1208] Step 3:

[1209] The server inputs the received photos into an AI image recognition model, which uses machine learning algorithms to identify the plant's type and health status (e.g., changes in leaf color or signs of disease).

[1210] Step 4:

[1211] The server analyzes the output of the AI ​​image recognition model to determine the plant's current condition, and the analyzed data is compared with the server's internal database.

[1212] Step 5:

[1213] Based on the analysis results, the server generates a message to ask the user for additional information, such as "How much sunlight does the plant get?"

[1214] Step 6:

[1215] The server generates a message and sends it to the user, which notifies the user's chatbot app and prompts for more information.

[1216] Step 7:

[1217] The user responds to queries from the server and provides additional information such as exposure to sunlight, watering frequency, recent weather conditions, etc. This information is sent to the server through the application.

[1218] Step 8:

[1219] The server receives the additional information sent by the user, converts it into a specific format, and stores it in an internal database.

[1220] Step 9:

[1221] An emotion engine implemented on the server analyzes text messages and voice data sent by the user and recognizes the user's emotional state (e.g., anxiety, worry, joy).

[1222] Step 10:

[1223] The server refers to an internal database based on the additional information and the analysis results of the emotion engine to search for appropriate development guidelines and solutions to problems.

[1224] Step 11:

[1225] The server combines information obtained from the database, the results of image analysis, additional information provided by the user, and the results of the emotion engine analysis to generate optimal training advice. The content and tone of the advice are also adjusted based on the results of the emotion engine.

[1226] Step 12:

[1227] The server sends the generated training advice to the user, who is then notified in their chatbot app and given specific advice.

[1228] Step 13:

[1229] The user receives advice from the server and puts the specific cultivation methods suggested into practice, such as changing the location of the plant to avoid direct sunlight or reviewing the frequency of watering.

[1230] Example 2

[1231] 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."

[1232] Conventional plant growing systems have incomplete processes for accurately identifying the condition of plants and providing appropriate growing advice to users. In particular, they lack consideration for identifying the plant's health and the user's emotional state, making it difficult to provide satisfying growing support. Furthermore, there are problems with the systems' ineffective management of additional information provided by users and the ineffective personalization of advice based on emotional analysis. The purpose of this invention is to solve these problems and provide optimal growing advice to users.

[1233] 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.

[1234] In this invention, the server includes a means for a user to take and send an image of a plant, a means for analyzing the image by executing a generative AI model, and a means for identifying the plant's type and health condition based on the results of the image recognition model. This allows the plant's condition to be accurately identified and the user to be asked for detailed additional information based on the analysis results. Furthermore, the server includes a means for analyzing the user's emotions using a sentiment analysis engine and a means for referencing a database based on the provided additional information and sentiment analysis information, making it possible to provide personalized, optimal plant-growing advice to the user. Furthermore, by including a means for generating prompt sentences that provide specific examples when generating plant-growing advice, the server can provide the user with more specific advice and is useful for troubleshooting. This enhances overall support for plant cultivation and is expected to improve user satisfaction.

[1235] "User" refers to an individual who uses the system to take images of plants and transmit the information.

[1236] A "server" refers to a device that analyzes received image data, references a database, and generates and transmits optimal training advice.

[1237] "Generative AI model" refers to a model that uses machine learning algorithms to analyze image data and identify plant species and health conditions.

[1238] "Image recognition model" refers to an algorithm or software that analyzes received image data to identify the type of plant and its health condition.

[1239] "Additional information" refers to information such as sunlight exposure, watering frequency, and recent weather conditions provided by the user to further analyze the health of the plant.

[1240] "Emotion analysis engine" refers to an engine that analyzes text data and voice data provided by a user to recognize the user's emotional state.

[1241] The "database" refers to a collection of information that stores plant-specific growing guidelines, problem-solving solutions, and other related information.

[1242] "Growth advice" refers to instructions and advice on the correct way to grow plants that are generated by the server based on the database and analysis results and provided to the user.

[1243] A "prompt sentence" refers to an advice sentence containing specific examples generated by a generative AI model.

[1244] The present invention relates to a system that combines plant image analysis, additional information collection, and an emotion engine that recognizes the user's emotions to provide optimal plant cultivation advice to the user. This system is composed of a user, a server, a terminal, and an emotion engine.

[1245] System Overview

[1246] The user takes a photo of a plant and sends it to the server via the application. The server inputs the received image into a generative AI model to identify the plant's species and its health condition. The server then queries the user for any additional information needed based on the analysis results and recognizes the user's emotions using an emotion engine. Finally, the server combines the additional information provided by the user, the analysis results of the emotion engine, and information from a database referenced by the server to generate optimal planting advice and send it to the user.

[1247] Hardware and software used

[1248] User device: A smartphone or tablet is used to take pictures of plants and send them to the server via the application.

[1249] Server: A computer system with powerful processing power where the generative AI model and sentiment analysis engine run.

[1250] Generative AI models: Image recognition software based on machine learning algorithms (e.g., TensorFlow, PyTorch).

[1251] Sentiment analysis engine: Software that analyzes a user's emotional state from text or voice (e.g., OpenAI GPT-3, IBM Watson).

[1252] Database: Information storage for plant growing guidelines and problem solutions.

[1253] Specific examples

[1254] Example 1: When the leaves of a houseplant turn brown

[1255] 1. A user takes a photo of a houseplant whose leaves are turning brown and sends it to the server through the application.

[1256] 2. The server receives the photo and inputs it into a generative AI model (using TensorFlow, for example).

[1257] 3. The generative AI model produces the analysis result that "the leaves are turning brown."

[1258] 4. The server sends a query to the user: "I've checked the condition of the leaves. When was the last time you watered them?"

[1259] 5. The user responds, "3 days ago."

[1260] 6. The sentiment analysis engine analyzes the user's message ("I'm worried because my plants haven't been doing well lately") and recognizes that the user is "worried."

[1261] 7. The server consults the database to find the appropriate watering frequency.

[1262] 8. The server generates advice to the user: "It is recommended that you keep this plant out of direct sunlight and water it once a week. There is no need to worry; if you follow this advice, it will recover."

[1263] 9. Users take this advice and apply it in practice.

[1264] Example 2: When vegetable disease is suspected

[1265] 1. A user takes a photo of vegetables in their garden that have unnatural spots and sends it to the server through the application.

[1266] 2. The server receives the photos and inputs them into a generative AI model (using, for example, PyTorch).

[1267] 3. The generative AI model produces the analysis result that "the leaf has spots."

[1268] 4. The server asks the user, "I noticed spots on the leaves. Please tell me about the sunlight and recent weather."

[1269] 5. The user responds, "It's sunny and it's been raining a lot lately."

[1270] 6. The sentiment analysis engine analyzes the user's message ("It's been raining a lot lately, and I'm worried that my vegetables might get sick") and recognizes that the user is feeling "anxious."

[1271] 7. The server references the database and retrieves information about diseases that are more likely to occur during rainy seasons.

[1272] 8. The server generates advice such as, "Mold disease is more likely to occur during rainy seasons. It is effective to improve ventilation and use fungicides as needed. Don't worry, the problem will be solved if you take action early." and sends it to the user.

[1273] 9. The user takes the advice and applies it.

[1274] By taking these steps into consideration, the system can provide highly accurate training advice by comprehensively considering the information provided by the user and their emotional state.

[1275] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1276] Step 1:

[1277] The user takes a picture of the plant and sends it.

[1278] Specific operation: The user takes a photo of a plant using a smartphone or tablet, and the image is sent to the server via the application.

[1279] Input: Plant image data.

[1280] Output: Image data sent to the server.

[1281] Step 2:

[1282] The server receives the images and analyzes them using a generative AI model.

[1283] How it works: The server inputs the received image data into a generative AI model such as TensorFlow or PyTorch, which processes the data to identify the plant species and its health status.

[1284] Input: Received plant image data.

[1285] Output: Analysis of plant type and health.

[1286] Step 3:

[1287] The server queries the user for additional information based on the results of image recognition.

[1288] How it works: Based on the results of the generative AI model's analysis, the server generates additional information to understand the plant's current condition in more detail. This additional information is sent to the user as a text message. For example, it may ask, "I've checked the condition of the leaves. When was the last time you watered them?"

[1289] Input: Analysis results of the image recognition model.

[1290] Output: A message asking the user for more information.

[1291] Step 4:

[1292] The user provides additional information.

[1293] Specific operation: In response to queries from the server, the user inputs information such as sunlight exposure, watering frequency, and recent weather conditions, and sends it to the server via the application.

[1294] Input: A query message from the server as a trigger.

[1295] Output: Additional information sent to the server.

[1296] Step 5:

[1297] The server receives the additional information provided by the user and analyzes the user's emotions using a sentiment analysis engine.

[1298] Specific operation: The server inputs the text and voice included in the additional information into an emotion analysis engine (e.g., OpenAI GPT-3 or IBM Watson) to analyze the user's emotional state. For example, if a user sends a message saying, "My plants haven't been doing well lately, and I'm worried," this message will be recognized as expressing "worry."

[1299] Input: Additional information provided by the user.

[1300] Output: Analysis results about the user's emotional state.

[1301] Step 6:

[1302] The server references the database based on the analysis results.

[1303] What it does: Based on the additional information and the results of the sentiment analysis engine, the server retrieves relevant information from an internal database, which contains plant-specific growing guidelines and problem-solving solutions. For example, it uses an SQL query to search for the appropriate growing guidelines.

[1304] Input: Additional information provided by the user and the results of the sentiment analysis engine.

[1305] Output: Relevant information retrieved from the internal database.

[1306] Step 7:

[1307] The server generates and transmits the development advice to the user.

[1308] Specific operation: The server combines information obtained from the database, analysis results, and additional information provided by the user to generate optimal growing advice. The generated advice includes specific examples as prompts. For example, "It is recommended that this plant be protected from direct sunlight and watered once a week. There is no need to worry. If you follow this advice, it will recover its health."

[1309] Input: Information retrieved from the database, analysis results, and additional information.

[1310] Output: Development advice notified to the user.

[1311] Through this process, users receive detailed advice on the health of their plants and can take specific actions.

[1312] (Application example 2)

[1313] 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."

[1314] Current plant cultivation support systems can analyze the type and health of plants, but they cannot provide flexible advice based on the user's emotions. Furthermore, there is a lack of systems for food delivery that provide advice on the nutritional value and health aspects of food. This creates a need for a comprehensive system to support plant cultivation and healthy eating.

[1315] 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 a user to take and send an image of a plant or food, means for executing an image recognition model to analyze the image received by the server, and means for analyzing the user's emotions using an emotion engine and adjusting the content and tone of advice. This enables the user to quickly and accurately diagnose the health condition of the plant or food and provide cultivation or food advice that takes the user's emotions into consideration.

[1316] A "user" is someone who uses the system to take images of plants or food and provide information about them.

[1317] "Plants" are living things such as green plants and flowers that are cultivated by the user.

[1318] "Food" refers to food such as dishes or ingredients that the user photographs.

[1319] "Means for taking and transmitting images" refers to a function that allows a user to take an image of a plant or food using a device such as a smartphone and transmit that image to a server.

[1320] The "server" is a computer system that receives and analyzes images, references a database, and generates optimal advice.

[1321] An "image recognition model" is an analytical method that uses machine learning algorithms to identify the type and health status of plants or food.

[1322] "Means for determining status" refers to the function of determining the current health status of a plant or food based on the analysis results of an image recognition model.

[1323] "Means for requesting additional information" refers to a function that allows the server to request missing information from the user based on the analysis results.

[1324] "Means for providing additional information" refers to a function that allows users to provide information such as sunlight exposure, watering frequency, and ingredients used in response to inquiries from the server.

[1325] "Means for referencing a database" refers to the function by which the server searches an internal database based on the additional information provided and obtains relevant growing guidelines and nutritional information.

[1326] "Means for generating and transmitting raising or food advice" refers to a function that generates optimal raising or food advice based on the information and analysis results acquired by the server and transmits it to the user.

[1327] An "emotion engine" is software that uses natural language processing technology to recognize and analyze a user's emotional state.

[1328] "Means for analyzing emotions and adjusting the content and tone of advice" refers to a function that provides the user with advice of appropriate content and tone based on the user's emotions analyzed by the emotion engine.

[1329] MODE FOR CARRYING OUT THE INVENTION

[1330] To put the present invention into practice, we will explain the specific configuration and method of a system that allows users to take and send images of plants or food. This system is built by combining a user's terminal, a server, a database, and an emotion engine.

[1331] System Configuration

[1332] 1. User Device:

[1333] Using a smartphone or tablet, users take pictures of plants or food and send them to a server via an application.

[1334] 2. Server:

[1335] The server analyzes the received image, queries the user for additional information, and generates optimal nutrition or dietary advice based on the acquired information by referencing a database. It also runs an emotion engine to analyze the user's emotions and adjust the content and tone of the advice.

[1336] 3. Database:

[1337] Databases such as MySQL and MongoDB are used to store growing guidelines, nutritional information, and problem solutions for each plant and food.

[1338] 4. Emotion Engine:

[1339] It uses NLP (Natural Language Processing) APIs to analyze user sentiment and tailor advice accordingly.

[1340] 5. Image Recognition Model:

[1341] TensorFlow and PyTorch are used to run machine learning models to analyze images of plants or food.

[1342] Program processing explanation

[1343] The server receives the image sent by the user and inputs it into an image recognition model to identify the type of plant or food and its health condition. The server then queries the user for any additional information needed based on the analysis results. The user provides the server with information such as sunlight exposure, watering frequency, and ingredients used. The server then uses an emotion engine to analyze the user's emotions and recognize their emotional state.

[1344] The server then uses this information to retrieve relevant information from a database, which includes growing guidelines, nutritional information, and solutions for each plant or food. The server then integrates the retrieved data, analysis results, and the user's emotional state to generate optimal growing or food advice. This advice is then sent to the user.

[1345] Examples of concrete examples and prompts

[1346] Example 1: When the leaves of a houseplant turn brown

[1347] 1. A user takes a photo of a houseplant whose leaves are turning brown and sends it to the server through the application.

[1348] 2. The server receives the photo and inputs it into an AI image recognition model.

[1349] 3. The image recognition model produces the analysis result that "the leaves are brown."

[1350] 4. The server sends a query to the user: "I've checked the condition of the leaves. When was the last time you watered them?"

[1351] 5. The user responds, "3 days ago."

[1352] 6. The emotion engine analyzes the user's message and recognizes that the user is "worried."

[1353] 7. The server consults the database to find the appropriate watering frequency.

[1354] 8. The server generates advice such as "It is recommended that you keep this plant out of direct sunlight and water it once a week. Also, there is no need to worry; if you follow this advice, it will recover its health" and sends it to the user.

[1355] 9. Users take this advice and apply it in practice.

[1356] Example 2: If you are concerned about the nutritional value of a dish

[1357] 1. A user takes a photo of a healthy salad and sends it with the comment, "I want to continue eating healthy."

[1358] 2. The server receives the photo, determines it is a "salad," and retrieves nutritional information for the main ingredients used (e.g., lettuce, tomato, cucumber) from the database.

[1359] 3. The emotion engine recognizes the user's emotional state of "motivation."

[1360] 4. The server integrates the database information with the emotional state, generates advice for the user, such as "This salad is very healthy, especially rich in vitamin C. Keep it up!", and sends it to the user.

[1361] Prompt Sentence Examples

[1362] "Please analyze the food in this image to get the ingredient information."

[1363] "Identify the emotion a user feels when they say 'I'm very happy.'"

[1364] "Generate personalized health advice based on analytics results and user sentiment."

[1365] Through these specific examples, users can quickly and accurately diagnose the health of plants or food and receive emotionally sensitive advice.

[1366] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1367] Step 1:

[1368] A user takes an image of a plant or food item and sends the image to a server through the application.

[1369] Input: An image of a plant or food

[1370] Output: Image data sent to the server

[1371] Specific operation: Take a picture using the camera on the user device and press the send button in the application

[1372] Step 2:

[1373] The server inputs the images received from the user into an image recognition model for analysis.

[1374] Input: Received image data

[1375] Output: Image recognition results (identification of plant or food type and health status)

[1376] Specific operation: The server inputs image data into an AI image recognition model (e.g., TensorFlow or PyTorch) and obtains the analysis results.

[1377] Step 3:

[1378] The server queries the user for missing information based on the results of image recognition.

[1379] Input: Image recognition results (type of plant or food and health status)

[1380] Output: A message asking for more information

[1381] Specific operation: Based on the analysis results, the server generates a message to send additional information (e.g., sunlight, watering frequency, ingredients used) and sends it to the user's device.

[1382] Step 4:

[1383] The user provides additional information in response to a query from the server.

[1384] Input: Query message from the server

[1385] Output: Additional information provided

[1386] What happens: The user answers questions through the application and sends the information to the server.

[1387] Step 5:

[1388] The server uses an emotion engine to analyze the user's emotions.

[1389] Input: User's message or voice data

[1390] Output: Sentiment analysis results (e.g., worry, satisfaction, anxiety, etc.)

[1391] Specific operation: The server inputs the user's message and voice data into an emotion engine (e.g., NLP API) to identify the emotional state.

[1392] Step 6:

[1393] Using the additional information acquired by the server and the results of emotion analysis, the server references the database to acquire related information.

[1394] Input: Additional information and sentiment analysis results

[1395] Output: Growing guidelines or nutritional information

[1396] What happens: The server searches an internal database (e.g., MySQL or MongoDB) to retrieve relevant growing guidelines and nutritional information.

[1397] Step 7:

[1398] The server integrates the acquired data, analysis results, and emotional state to generate optimal development or food advice.

[1399] Input: Nutritional guidelines or nutritional information, additional information, emotional state

[1400] Output: personalized advice

[1401] What it does: The server runs an algorithm that integrates the data and generates personalized nutrition or dietary advice.

[1402] Step 8:

[1403] The server sends the generated advice to the user.

[1404] Input: personalized advice

[1405] Output: Notification message to the user's terminal

[1406] What happens: The server generates a message containing the advice and sends it to the user's application.

[1407] In this way, users can quickly and accurately diagnose the health of their plants or food products and receive emotionally sensitive advice.

[1408] 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.

[1409] 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.

[1410] 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.

[1411] [Fourth embodiment]

[1412] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1413] 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.

[1414] 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).

[1415] 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.

[1416] 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.

[1417] 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).

[1418] 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.

[1419] 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.

[1420] 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.

[1421] 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.

[1422] 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.

[1423] 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.

[1424] 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."

[1425] The present invention relates to a system that combines image analysis of plants with the collection of additional information to provide users with optimal plant cultivation advice. This system is composed of a user, a server, and a terminal. Below, the program processing of this system is explained in natural language, and a detailed description of the mode for carrying out the invention is given with specific examples.

[1426] System Overview

[1427] In this system, users take pictures of plants and send them to a server via an application. The server inputs the received images into an AI image recognition model to identify the plant's species and its health condition. The server then queries the user for any additional information needed based on the analysis results. By integrating the additional information provided by the user with information from a database referenced by the server, the server generates optimal cultivation advice and sends it to the user.

[1428] Program processing explanation

[1429] 1. The user takes and sends a photo of the plant

[1430] Users use a smartphone or tablet to take a photo of the plant's current condition, and the image is sent to the server via the application.

[1431] 2. The server receives and analyzes the image

[1432] The server receives the images sent by the user, which are then fed into an AI image recognition model that uses machine learning algorithms to identify the plant's type and health status.

[1433] 3. The server queries for additional information based on the analysis results

[1434] Based on the analysis results of the image recognition model, the server queries the user for additional information needed to gain a detailed understanding of the current state of the plant.

[1435] 4. User provides additional information

[1436] In response to a query from the server, the user provides additional information such as exposure to sunlight, frequency of watering, recent weather conditions, etc. This information is sent to the server.

[1437] 5. The server references the database

[1438] The server uses the additional information provided to retrieve relevant information from a database, which includes plant-specific growing guidelines and solutions to problems.

[1439] 6. The server generates and sends the training advice

[1440] The server combines the information retrieved from the database, the additional information provided, and the analysis results to generate optimal breeding advice, which is then sent to the user.

[1441] Specific examples

[1442] Example 1: When the leaves of a houseplant turn brown

[1443] 1. A user takes a photo of a houseplant whose leaves are turning brown and sends it to the server through the application.

[1444] 2. The server receives the photo and inputs it into an AI image recognition model.

[1445] 3. The image recognition model produces the analysis result that "the leaves are brown."

[1446] 4. The server sends a query to the user: "I've checked the condition of the leaves. When was the last time you watered them?"

[1447] 5. The user responds, "3 days ago."

[1448] 6. The server uses the user's answer to look up the appropriate watering frequency from the database.

[1449] 7. The server generates advice that says, "It is recommended that this plant be kept out of direct sunlight and watered once a week," and sends it to the user.

[1450] 8. Users take this advice and apply it in practice.

[1451] Example 2: When vegetable disease is suspected

[1452] 1. A user takes a photo of vegetables in their garden that have unnatural spots and sends it to the server through the application.

[1453] 2. The server receives the photo and inputs it into an AI image recognition model.

[1454] 3. The image recognition model produces the analysis result that "there are spots on the leaf."

[1455] 4. The server asks the user, "I noticed spots on the leaves. Please tell me about the sunlight and recent weather."

[1456] 5. The user responds, "It's sunny and it's been raining a lot lately."

[1457] 6. Based on the user's answers, the server references information from the database about diseases that are more likely to occur during rainy seasons.

[1458] 7. The server generates advice such as, "Mold disease is more likely to occur during rainy seasons. It is effective to improve ventilation and use fungicides as needed," and sends it to the user.

[1459] 8. The user takes the advice and applies it.

[1460] This system quickly and accurately diagnoses the health of plants, providing support to gardening enthusiasts to grow healthy plants.

[1461] The processing flow will be explained below.

[1462] Step 1:

[1463] Users take a photo of the plant and upload and send it to the chatbot app using their smartphone or tablet.

[1464] Step 2:

[1465] The server receives plant photos sent by users, converts them into a specific format, and prepares them for image analysis.

[1466] Step 3:

[1467] The server inputs the received images into an AI image recognition model, which identifies the plant's type and health status (e.g., changes in leaf color, signs of disease, etc.).

[1468] Step 4:

[1469] The server analyzes the output of the AI ​​image recognition model to determine the plant's condition, which involves formalizing the analysis results and comparing them with a database stored on the server.

[1470] Step 5:

[1471] Based on the analysis, the server generates a message asking the user for additional information, such as "How much sunlight does this plant get?"

[1472] Step 6:

[1473] The server generates a message and sends it to the user, which notifies the user's chatbot app and prompts for more information.

[1474] Step 7:

[1475] The user provides additional information in response to a question posed by the server, for example, "It's sunny and it's been raining a lot lately."

[1476] Step 8:

[1477] The server receives additional information from the user, which is stored in a database within the server and converted into the appropriate format.

[1478] Step 9:

[1479] The server references its internal database based on the additional information, searches for appropriate training advice and problem solutions, and extracts the most appropriate information.

[1480] Step 10:

[1481] The server integrates the information obtained from the database, the analysis results, and additional information provided by the user to generate optimal training advice.

[1482] Step 11:

[1483] The server sends the generated training advice to the user, who is then notified in their chatbot app and the advice is displayed.

[1484] Step 12:

[1485] The user receives advice from the server and puts into practice specific cultivation methods, such as moving the plant to avoid direct sunlight.

[1486] Example 1

[1487] 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."

[1488] In conventional plant cultivation, it is difficult for users to accurately grasp the health condition of plants and quickly take appropriate measures. In addition, since ordinary users do not have specialized knowledge of plants, it is difficult to accurately diagnose the condition of plants and find the optimal cultivation method.

[1489] 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.

[1490] In this invention, the server includes means for a user to acquire and transmit images of plants using a camera, means for the server to store the received images, means for running an AI image recognition model to analyze the stored images, means for the server to identify the state of the plant based on the image recognition results, means for the server to query the user for additional information based on the identification results, means for the user to input and transmit the additional information, means for the server to refer to a database based on the provided additional information, and means for the server to synthesize the information in the database, the additional information, and the analysis results to generate optimal instructions and communicate them to the user. This allows the user to easily diagnose the health of their plants and receive appropriate cultivation advice.

[1491] A "user" is an individual or organization that uses the system and is responsible for acquiring images of plants and transmitting them to the server.

[1492] A "photography device" is an electronic device, such as a smartphone or tablet, that captures images of plants and transmits those images to the system.

[1493] "Video" refers to images or videos of plants captured by a user using a camera.

[1494] "Server" is a central computer system that receives, stores, and analyzes user-submitted video.

[1495] An "AI image recognition model" is an artificial intelligence program that uses machine learning algorithms to identify plant species and health conditions.

[1496] A "database" is a collection of information that systematically stores information, including cultivation guidelines and solutions for each plant, and that can be referenced by a server.

[1497] "Identification" is the process by which an AI image recognition model analyzes video footage, identifies the type of plant and its health condition, and generates a judgment result.

[1498] "Additional information" is detailed information related to plant cultivation that the user provides in response to a query from the server.

[1499] "Growth advice" is optimal instructions for keeping plants healthy, generated by the server by integrating information from the database, additional information, and analysis results.

[1500] The present invention is a system that combines image analysis of plants with the collection of additional information to provide users with optimal plant cultivation advice. This system is composed of users, a server, and terminals.

[1501] Users first capture images of plants using a camera such as a smartphone or tablet, and then send the images to the server via a dedicated application. The camera can be a standard smartphone or tablet equipped with a high-resolution camera.

[1502] The server temporarily stores the received video and runs an AI image recognition model using TensorFlow via a Python script. This identifies the type of plant and its health condition from the video. This image recognition model is trained based on machine learning algorithms, enabling highly accurate analysis.

[1503] Next, the server queries the user for additional information based on the image recognition results, such as "How often have you watered your plants recently?" or "How sunny is the area?", and sends the questions to the user via the application.

[1504] The user enters detailed information in response to these questions and submits it back to the server, which then retrieves the additional information provided by the user.

[1505] The server then consults a MySQL database to retrieve plant-specific cultivation guidelines and solutions. By combining the retrieved information, additional information, and the results of image recognition, the server generates optimal cultivation advice and sends it to the user via the application.

[1506] This system is unique in that it allows users to easily diagnose the health of their plants and receive appropriate growing advice.

[1507] Specific examples

[1508] Example 1: When the leaves of a houseplant turn brown

[1509] 1. A user takes a photo of a houseplant whose leaves are turning brown and sends it to the server through the application.

[1510] 2. The server receives the photo and inputs it into an AI image recognition model using TensorFlow.

[1511] 3. The image recognition model produces the analysis result that "the leaves are brown."

[1512] 4. The server sends a query to the user: "I've checked the condition of the leaves. When was the last time you watered them?"

[1513] 5. The user responds, "3 days ago."

[1514] 6. The server looks up the appropriate watering frequency from the MySQL database based on the user's answer.

[1515] 7. The server generates advice such as "It is recommended that this plant be kept out of direct sunlight and watered once a week" and sends it to the user.

[1516] 8. Users take this advice and apply it in practice.

[1517] Example 2: When vegetable disease is suspected

[1518] 1. A user takes a photo of vegetables in their garden that have unnatural spots and sends it to the server through the application.

[1519] 2. The server receives the photo and inputs it into an AI image recognition model using TensorFlow.

[1520] 3. The image recognition model produces the analysis result that "there are spots on the leaf."

[1521] 4. The server asks the user, "I noticed spots on the leaves. Please tell me about the sunlight and recent weather."

[1522] 5. The user responds, "It's sunny and it's been raining a lot lately."

[1523] 6. Based on the user's response, the server retrieves information from a MySQL database about diseases that are more likely to occur during rainy seasons.

[1524] 7. The server generates advice such as "Mold disease is more likely to occur during rainy seasons. It is effective to improve ventilation and use fungicides as needed," and sends it to the user.

[1525] 8. The user takes the advice and applies it.

[1526] Prompt Sentence Examples

[1527] Prompt 1:

[1528] If your houseplant's leaves are turning brown, take a photo of the plant and send the image to an AI model to analyze its health and provide additional information and advice based on its health.

[1529] Prompt Statement 2:

[1530] If you notice spots on your vegetable leaves, take a photo and send the image to the AI ​​model, along with additional information like sunlight and weather conditions, to generate appropriate growing advice.

[1531] In this way, the system quickly and accurately diagnoses the health of plants, providing support to gardening enthusiasts in growing healthy plants.

[1532] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1533] Step 1:

[1534] Users take and send images of plants

[1535] The user captures a video of the plant using a smartphone or tablet. The user opens the dedicated application, selects the image they have taken, and presses the send button. At this time, the input data is the image file of the photographed plant, which is then sent to the server. Specifically, the user uses the camera function in the application to take a picture of the plant and upload it to the server.

[1536] Step 2:

[1537] The server receives and saves the image.

[1538] The server receives the image sent by the user and temporarily stores it. The received image is saved in a dedicated directory and assigned a unique ID. The input data is the image file sent by the user, and this image file is saved in the server's storage. Specifically, the server receives the image file, saves it in storage, and records the file path.

[1539] Step 3:

[1540] The server performs image analysis

[1541] The server inputs the received images into an AI image recognition model. This model uses TensorFlow via a Python script to identify the plant's type and health status based on machine learning algorithms. The input for this step is the path to the saved image file, and the output is the image analysis results in JSON format. Specifically, the server passes the path to the saved image file to the AI ​​image recognition model, which then parses and saves the results in JSON format.

[1542] Step 4:

[1543] The server queries the user for additional information

[1544] Based on the results of image recognition, the server queries the user for more detailed information. The server generates questions such as "How often have you watered your plants recently?" or "How sunny is the area?" and sends them to the user through the application. The input to this step is the image analysis result data, and the output is a query message to be sent to the user. Specifically, the server determines the required information and sends the question to the user through the application.

[1545] Step 5:

[1546] User provides additional information

[1547] The user enters detailed information in response to the received question into the application and sends it to the server. The input data is additional information that the user entered into the application, and this is sent back to the server. A specific example of this is when the user enters information such as "I watered the plants three days ago" and sends it to the server.

[1548] Step 6:

[1549] The server references the database

[1550] The server references the database based on the additional information to obtain cultivation guidelines and problem-solving solutions for each plant. The database used is MySQL, and the required information is obtained using SQL queries. The input data is the user's additional information and the results of image analysis, and the output is the cultivation guidelines and problem-solving solutions obtained from the database. Specifically, the server creates an SQL query based on the user's information and obtains the relevant information from the database.

[1551] Step 7:

[1552] The server generates and sends training advice

[1553] The server integrates the information obtained from the database, the user's additional information, and the image analysis results to generate optimal breeding advice. This advice is then sent to the user through the application. The input data is the user's additional information, the database information, and the image analysis results, and the output is the breeding advice to be sent to the user. Specifically, the server generates advice and sends it to the user.

[1554] Step 8:

[1555] User receives advice and implements it

[1556] The user checks the advice received in the application and follows the instructions. The input data is the cultivation advice sent from the server, and the user performs the action based on this. Specifically, the user reads the advice and actually carries out the instructions, such as changing the location of the plant.

[1557] Through the above processing steps, the system allows users to easily diagnose the health of their plants and receive appropriate growing advice.

[1558] (Application example 1)

[1559] 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."

[1560] Gardening stores and home improvement centers face the problem of taking time to determine the type and health of plants, making it difficult to provide appropriate growing advice immediately, which can lead to lower customer satisfaction and affect the store's credibility.

[1561] 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.

[1562] In this invention, the server includes: a means for a user to take and send an image of a plant; a means for executing an image recognition model to analyze the image received by the server; a means for the server to determine the type and health of the plant based on the image recognition results; a means for the server to query the user for additional information based on the determination results; a means for the user to provide the additional information; a means for the server to refer to a database based on the provided additional information; a means for the server to generate optimal cultivation advice and send it to the user; and a means for a gardening store to allow store staff or visitors to take and send photos of plants and for the server to provide the plant diagnosis results and cultivation advice. This makes it possible for the gardening store to instantly diagnose the health of plants and provide appropriate cultivation advice.

[1563] A "user" is an individual or store staff member who accesses the system to diagnose the health of plants and obtain growing advice.

[1564] A "plant image" is a digital photograph taken by a user and sent to the system to represent the state of the plant.

[1565] The "transmission means" is a communication means by which the user transmits plant images and additional information to the server.

[1566] The "server" is a central computer system that performs plant image analysis, collects additional information, and generates cultivation advice.

[1567] An "image recognition model" is an artificial intelligence model for identifying plant species and health status based on machine learning algorithms.

[1568] The "analysis means" is a means for inputting the plant image received by the server into an image recognition model and analyzing it.

[1569] The "determination means" is a function of the server that determines the type and health condition of a plant based on the results of the image recognition model.

[1570] The "query means" is a function of the server that queries the user for additional information based on the determination result.

[1571] "Additional information" is information provided by the user to understand the current state of the plant in detail, and includes sunlight exposure, watering frequency, weather conditions, etc.

[1572] The "reference means" is a function that allows the server to obtain related information from a database based on the additional information provided.

[1573] The "database" is a collection of information that stores cultivation guidelines and solutions to problems for each plant.

[1574] The "development advice generating means" is a means by which the server integrates the information in the database with the additional information to generate optimal development advice.

[1575] A "gardening store" is a physical store that sells plants and related products, and is a place where users can use the plant diagnostic application.

[1576] "Store staff or visitors" refers to customers or store staff who use the plant diagnostic system at a gardening store.

[1577] System configuration

[1578] This invention is a system that provides plant cultivation advice by combining plant image analysis and additional information collection. This system receives plant images taken and sent by users, analyzes them using an AI image recognition model, and identifies the plant's species and health condition. It then queries the user for any additional information needed, and generates and provides optimal cultivation advice.

[1579] Hardware and software used

[1580] Server: The server is built using a web framework such as Flask or Django. This server plays a central role in receiving images sent by users, analyzing them, querying necessary information, and generating and providing training advice.

[1581] Terminal (smartphone, tablet, etc.): A terminal where the user takes pictures of plants and sends them to the server. It can be implemented as an Android or iOS application.

[1582] Generative AI models: These are machine learning models built using deep learning frameworks such as TensorFlow and PyTorch, and are used for image recognition to identify plant species and health.

[1583] Database: Use a database system such as MySQL or MongoDB to store growing guidelines and problem solutions for each plant.

[1584] Process Overview

[1585] The user takes an image of the plant and sends it to the server via the application. The received image is analyzed by an image recognition model run by the server. Based on the analysis results, the plant's type and health condition are determined, and the user is then queried for additional information based on that information. The additional information provided by the user is compared with a database, and optimal growing advice is generated. The generated advice is notified to the user, who can use it to grow the plant.

[1586] Specific examples

[1587] Example 1: When the leaves of a houseplant turn brown

[1588] 1. A user takes a photo of a houseplant whose leaves are turning brown and sends it to the server through the application.

[1589] 2. The server receives the photo and analyzes the image using a generative AI model.

[1590] 3. The image recognition model produces the analysis result that "the leaves are brown."

[1591] 4. The server sends the query to the user: "I've checked the condition of the leaves. When was the last time you watered them?"

[1592] 5. The user responds, "3 days ago."

[1593] 6. Based on the user's answer, the server looks up the appropriate watering frequency from the database.

[1594] 7. The server generates advice that says, "It is recommended that this plant be kept out of direct sunlight and watered once a week," and sends it to the user.

[1595] 8. Users take this advice and apply it in practice.

[1596] Example 2: When vegetable disease is suspected

[1597] 1. A user takes a photo of vegetables in their garden that have unnatural spots and sends it to the server through the application.

[1598] 2. The server receives the photo and analyzes the image using a generative AI model.

[1599] 3. The image recognition model produces the analysis result that "there are spots on the leaf."

[1600] 4. The server asks the user, "I noticed spots on the leaves. Please tell me about the sunlight and recent weather."

[1601] 5. The user responds, "It's sunny and it's been raining a lot lately."

[1602] 6. Based on the user's answers, the server references information from the database about diseases that are more likely to occur during rainy seasons.

[1603] 7. The server generates advice such as, "Mold disease is more likely to occur during rainy seasons. It is effective to improve ventilation and use fungicides as needed," and sends it to the user.

[1604] 8. The user takes the advice and applies it.

[1605] Prompt Sentence Examples

[1606] "My tomato leaves are turning yellow. When was the last time I watered them?"

[1607] "My rose leaves are turning brown. What's the weather like these days?"

[1608] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1609] Step 1:

[1610] The user takes a picture of a plant and sends it to the server through the application. The input is the image data of the plant taken by the user, and this data is sent to the server. The output is the image data that arrives at the server.

[1611] Step 2:

[1612] The server takes in the received image data and analyzes the image using a generative AI model. The input is the image data received by the server, and the output is the analysis results of the generative AI model, which include information on the plant's type and health condition. Specifically, the image is preprocessed and converted into an appropriate format before being input into the AI ​​model.

[1613] Step 3:

[1614] The server determines the type and health of the plant based on the analysis results of the generated AI model. The input is the analysis result from step 2, and the output is information about the determined plant type and its health condition. Specific operations include decoding the analysis results and converting them into meaningful information.

[1615] Step 4:

[1616] Based on the judgment result, the server queries the user for additional information. The input is the type and health condition of the plant judged in step 3, and the output is the question to be sent to the user. Specifically, the server generates an appropriate prompt sentence according to the plant's condition and sends it to the user's device.

[1617] Step 5:

[1618] The user provides the necessary additional information in response to a query from the server. The input is the question presented to the user, and the output is the additional information the user provides to the server. Specifically, text and options are entered through the terminal application and sent to the server.

[1619] Step 6:

[1620] The server references the database based on the additional information provided by the user. The input is the additional information obtained in step 5, and the output is related information retrieved from the database. Specifically, the server performs a database search using the additional information as a key to obtain the relevant training guidelines and problem solutions.

[1621] Step 7:

[1622] The server integrates the database information with the additional information to generate optimal training advice. The input is the database information obtained in step 6 and the additional information provided by the user, and the output is the generated training advice. Specifically, the information obtained from the database is combined with the user's input and an algorithm is used to generate optimal advice.

[1623] Step 8:

[1624] The server sends the generated training advice to the user. The input is the training advice generated in step 7, and the output is the advice content sent to the user's terminal. Specific operations include converting it into a message format and sending it to the user's terminal.

[1625] 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.

[1626] The present invention relates to a system that combines plant image analysis, additional information collection, and an emotion engine that recognizes the user's emotions to provide optimal plant cultivation advice to the user. This system is composed of a user, a server, a terminal, and an emotion engine. Below, the program processing of this system is explained in natural language, and a detailed description of the embodiment of the invention is given with specific examples.

[1627] System Overview

[1628] In this system, users take pictures of plants and send them to a server via an application. The server inputs the received images into an AI image recognition model to identify the plant's species and its health condition. The server then queries the user for any additional information needed based on the analysis results, and uses an emotion engine to recognize the user's emotions. By integrating the additional information provided by the user, the emotion engine's analysis results, and information from a database referenced by the server, the server generates optimal cultivation advice and sends it to the user.

[1629] Program processing explanation

[1630] 1. The user takes and sends a photo of the plant

[1631] Users use a smartphone or tablet to take a photo of the plant's current condition, and the image is sent to the server via the application.

[1632] 2. The server receives and analyzes the image

[1633] The server receives the images sent by the user, which are then fed into an AI image recognition model that uses machine learning algorithms to identify the plant's type and health status.

[1634] 3. The server queries for additional information based on the analysis results

[1635] Based on the analysis results of the image recognition model, the server queries the user for additional information needed to gain a detailed understanding of the current state of the plant.

[1636] 4. User provides additional information

[1637] In response to a query from the server, the user provides additional information such as exposure to sunlight, frequency of watering, recent weather conditions, etc. This information is sent to the server.

[1638] 5. The server analyzes the user's emotions

[1639] The emotion engine installed on the server analyzes messages and voice data sent by users and recognizes their emotional state. For example, if a user sends a comment such as "My plants haven't been doing well lately, and I'm worried," the emotion is recognized as "worried."

[1640] 6. The server references the database

[1641] Based on the additional information provided and the results of the emotion engine's analysis, the server retrieves relevant information by referencing an internal database, which includes plant-specific cultivation guidelines and solutions to problems.

[1642] 7. The server generates and sends the training advice

[1643] The server combines the information retrieved from the database, the analysis results, and additional information provided by the user to generate optimal parenting advice. Based on the analysis results of the emotion engine, the content and tone of the advice may be adjusted to include softer language or encouraging messages. This advice is then sent to the user, who then notifies the user's chatbot app.

[1644] Specific examples

[1645] Example 1: When the leaves of a houseplant turn brown

[1646] 1. A user takes a photo of a houseplant whose leaves are turning brown and sends it to the server through the application.

[1647] 2. The server receives the photo and inputs it into an AI image recognition model.

[1648] 3. The image recognition model produces the analysis result that "the leaves are brown."

[1649] 4. The server sends a query to the user: "I've checked the condition of the leaves. When was the last time you watered them?"

[1650] 5. The user responds, "3 days ago."

[1651] 6. The emotion engine analyzes the user's message and recognizes that the user is "worried."

[1652] 7. The server consults the database to find the appropriate watering frequency.

[1653] 8. The server generates advice such as "It is recommended that you keep this plant out of direct sunlight and water it once a week. Also, there is no need to worry; if you follow this advice, it will recover its health" and sends it to the user.

[1654] 9. Users take this advice and apply it in practice.

[1655] Example 2: When vegetable disease is suspected

[1656] 1. A user takes a photo of vegetables in their garden that have unnatural spots and sends it to the server through the application.

[1657] 2. The server receives the photo and inputs it into an AI image recognition model.

[1658] 3. The image recognition model produces the analysis result that "there are spots on the leaf."

[1659] 4. The server asks the user, "I noticed spots on the leaves. Please tell me about the sunlight and recent weather."

[1660] 5. The user responds, "It's sunny and it's been raining a lot lately."

[1661] 6. The emotion engine analyzes the user's message and recognizes that the user is feeling "anxiety."

[1662] 7. The server references the database and retrieves information about diseases that are more likely to occur during rainy seasons.

[1663] 8. The server generates advice such as, "Mold disease is more likely to occur during rainy seasons. It is effective to improve ventilation and use fungicides as needed. Don't worry, the problem will be solved if you take action early." and sends it to the user.

[1664] 9. The user takes the advice and applies it.

[1665] In this way, the system quickly and accurately diagnoses the health of plants and provides support to gardeners to grow healthy plants while taking into account the user's emotions.

[1666] The processing flow will be explained below.

[1667] Step 1:

[1668] Users take photos of plants with their smartphones or tablets and use the chatbot app to send the photos to the server.

[1669] Step 2:

[1670] The server receives plant photos submitted by users and formats them in a way that makes them ready for image analysis.

[1671] Step 3:

[1672] The server inputs the received photos into an AI image recognition model, which uses machine learning algorithms to identify the plant's type and health status (e.g., changes in leaf color or signs of disease).

[1673] Step 4:

[1674] The server analyzes the output of the AI ​​image recognition model to determine the plant's current condition, and the analyzed data is compared with the server's internal database.

[1675] Step 5:

[1676] Based on the analysis results, the server generates a message to ask the user for additional information, such as "How much sunlight does the plant get?"

[1677] Step 6:

[1678] The server generates a message and sends it to the user, which notifies the user's chatbot app and prompts for more information.

[1679] Step 7:

[1680] The user responds to queries from the server and provides additional information such as exposure to sunlight, watering frequency, recent weather conditions, etc. This information is sent to the server through the application.

[1681] Step 8:

[1682] The server receives the additional information sent by the user, converts it into a specific format, and stores it in an internal database.

[1683] Step 9:

[1684] An emotion engine implemented on the server analyzes text messages and voice data sent by the user and recognizes the user's emotional state (e.g., anxiety, worry, joy).

[1685] Step 10:

[1686] The server refers to an internal database based on the additional information and the analysis results of the emotion engine to search for appropriate development guidelines and solutions to problems.

[1687] Step 11:

[1688] The server combines information obtained from the database, the results of image analysis, additional information provided by the user, and the results of the emotion engine analysis to generate optimal training advice. The content and tone of the advice are also adjusted based on the results of the emotion engine.

[1689] Step 12:

[1690] The server sends the generated training advice to the user, who is then notified in their chatbot app and given specific advice.

[1691] Step 13:

[1692] The user receives advice from the server and puts the specific cultivation methods suggested into practice, such as changing the location of the plant to avoid direct sunlight or reviewing the frequency of watering.

[1693] Example 2

[1694] 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."

[1695] Conventional plant growing systems have incomplete processes for accurately identifying the condition of plants and providing appropriate growing advice to users. In particular, they lack consideration for identifying the plant's health and the user's emotional state, making it difficult to provide satisfying growing support. Furthermore, there are problems with the systems' ineffective management of additional information provided by users and the ineffective personalization of advice based on emotional analysis. The purpose of this invention is to solve these problems and provide optimal growing advice to users.

[1696] 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.

[1697] In this invention, the server includes a means for a user to take and send an image of a plant, a means for analyzing the image by executing a generative AI model, and a means for identifying the plant's type and health condition based on the results of the image recognition model. This allows the plant's condition to be accurately identified and the user to be asked for detailed additional information based on the analysis results. Furthermore, the server includes a means for analyzing the user's emotions using a sentiment analysis engine and a means for referencing a database based on the provided additional information and sentiment analysis information, making it possible to provide personalized, optimal plant-growing advice to the user. Furthermore, by including a means for generating prompt sentences that provide specific examples when generating plant-growing advice, the server can provide the user with more specific advice and is useful for troubleshooting. This enhances overall support for plant cultivation and is expected to improve user satisfaction.

[1698] "User" refers to an individual who uses the system to take images of plants and transmit the information.

[1699] A "server" refers to a device that analyzes received image data, references a database, and generates and transmits optimal training advice.

[1700] "Generative AI model" refers to a model that uses machine learning algorithms to analyze image data and identify plant species and health conditions.

[1701] "Image recognition model" refers to an algorithm or software that analyzes received image data to identify the type of plant and its health condition.

[1702] "Additional information" refers to information such as sunlight exposure, watering frequency, and recent weather conditions provided by the user to further analyze the health of the plant.

[1703] "Emotion analysis engine" refers to an engine that analyzes text data and voice data provided by a user to recognize the user's emotional state.

[1704] The "database" refers to a collection of information that stores plant-specific growing guidelines, problem-solving solutions, and other related information.

[1705] "Growth advice" refers to instructions and advice on the correct way to grow plants that are generated by the server based on the database and analysis results and provided to the user.

[1706] A "prompt sentence" refers to an advice sentence containing specific examples generated by a generative AI model.

[1707] The present invention relates to a system that combines plant image analysis, additional information collection, and an emotion engine that recognizes the user's emotions to provide optimal plant cultivation advice to the user. This system is composed of a user, a server, a terminal, and an emotion engine.

[1708] System Overview

[1709] The user takes a photo of a plant and sends it to the server via the application. The server inputs the received image into a generative AI model to identify the plant's species and its health condition. The server then queries the user for any additional information needed based on the analysis results and recognizes the user's emotions using an emotion engine. Finally, the server combines the additional information provided by the user, the analysis results of the emotion engine, and information from a database referenced by the server to generate optimal planting advice and send it to the user.

[1710] Hardware and software used

[1711] User device: A smartphone or tablet is used to take pictures of plants and send them to the server via the application.

[1712] Server: A computer system with powerful processing power where the generative AI model and sentiment analysis engine run.

[1713] Generative AI models: Image recognition software based on machine learning algorithms (e.g., TensorFlow, PyTorch).

[1714] Sentiment analysis engine: Software that analyzes a user's emotional state from text or voice (e.g., OpenAI GPT-3, IBM Watson).

[1715] Database: Information storage for plant growing guidelines and problem solutions.

[1716] Specific examples

[1717] Example 1: When the leaves of a houseplant turn brown

[1718] 1. A user takes a photo of a houseplant whose leaves are turning brown and sends it to the server through the application.

[1719] 2. The server receives the photo and inputs it into a generative AI model (using TensorFlow, for example).

[1720] 3. The generative AI model produces the analysis result that "the leaves are turning brown."

[1721] 4. The server sends a query to the user: "I've checked the condition of the leaves. When was the last time you watered them?"

[1722] 5. The user responds, "3 days ago."

[1723] 6. The sentiment analysis engine analyzes the user's message ("I'm worried because my plants haven't been doing well lately") and recognizes that the user is "worried."

[1724] 7. The server consults the database to find the appropriate watering frequency.

[1725] 8. The server generates advice to the user: "It is recommended that you keep this plant out of direct sunlight and water it once a week. There is no need to worry; if you follow this advice, it will recover."

[1726] 9. Users take this advice and apply it in practice.

[1727] Example 2: When vegetable disease is suspected

[1728] 1. A user takes a photo of vegetables in their garden that have unnatural spots and sends it to the server through the application.

[1729] 2. The server receives the photos and inputs them into a generative AI model (using, for example, PyTorch).

[1730] 3. The generative AI model produces the analysis result that "the leaf has spots."

[1731] 4. The server asks the user, "I noticed spots on the leaves. Please tell me about the sunlight and recent weather."

[1732] 5. The user responds, "It's sunny and it's been raining a lot lately."

[1733] 6. The sentiment analysis engine analyzes the user's message ("It's been raining a lot lately, and I'm worried that my vegetables might get sick") and recognizes that the user is feeling "anxious."

[1734] 7. The server references the database and retrieves information about diseases that are more likely to occur during rainy seasons.

[1735] 8. The server generates advice such as, "Mold disease is more likely to occur during rainy seasons. It is effective to improve ventilation and use fungicides as needed. Don't worry, the problem will be solved if you take action early." and sends it to the user.

[1736] 9. The user takes the advice and applies it.

[1737] By taking these steps into consideration, the system can provide highly accurate training advice by comprehensively considering the information provided by the user and their emotional state.

[1738] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1739] Step 1:

[1740] The user takes a picture of the plant and sends it.

[1741] Specific operation: The user takes a photo of a plant using a smartphone or tablet, and the image is sent to the server via the application.

[1742] Input: Plant image data.

[1743] Output: Image data sent to the server.

[1744] Step 2:

[1745] The server receives the images and analyzes them using a generative AI model.

[1746] How it works: The server inputs the received image data into a generative AI model such as TensorFlow or PyTorch, which processes the data to identify the plant species and its health status.

[1747] Input: Received plant image data.

[1748] Output: Analysis of plant type and health.

[1749] Step 3:

[1750] The server queries the user for additional information based on the results of image recognition.

[1751] How it works: Based on the results of the generative AI model's analysis, the server generates additional information to understand the plant's current condition in more detail. This additional information is sent to the user as a text message. For example, it may ask, "I've checked the condition of the leaves. When was the last time you watered them?"

[1752] Input: Analysis results of the image recognition model.

[1753] Output: A message asking the user for more information.

[1754] Step 4:

[1755] The user provides additional information.

[1756] Specific operation: In response to queries from the server, the user inputs information such as sunlight exposure, watering frequency, and recent weather conditions, and sends it to the server via the application.

[1757] Input: A query message from the server as a trigger.

[1758] Output: Additional information sent to the server.

[1759] Step 5:

[1760] The server receives the additional information provided by the user and analyzes the user's emotions using a sentiment analysis engine.

[1761] Specific operation: The server inputs the text and voice included in the additional information into an emotion analysis engine (e.g., OpenAI GPT-3 or IBM Watson) to analyze the user's emotional state. For example, if a user sends a message saying, "My plants haven't been doing well lately, and I'm worried," this message will be recognized as expressing "worry."

[1762] Input: Additional information provided by the user.

[1763] Output: Analysis results about the user's emotional state.

[1764] Step 6:

[1765] The server references the database based on the analysis results.

[1766] What it does: Based on the additional information and the results of the sentiment analysis engine, the server retrieves relevant information from an internal database, which contains plant-specific growing guidelines and problem-solving solutions. For example, it uses an SQL query to search for the appropriate growing guidelines.

[1767] Input: Additional information provided by the user and the results of the sentiment analysis engine.

[1768] Output: Relevant information retrieved from the internal database.

[1769] Step 7:

[1770] The server generates and transmits the development advice to the user.

[1771] Specific operation: The server combines information obtained from the database, analysis results, and additional information provided by the user to generate optimal growing advice. The generated advice includes specific examples as prompts. For example, "It is recommended that this plant be protected from direct sunlight and watered once a week. There is no need to worry. If you follow this advice, it will recover its health."

[1772] Input: Information retrieved from the database, analysis results, and additional information.

[1773] Output: Development advice notified to the user.

[1774] Through this process, users receive detailed advice on the health of their plants and can take specific actions.

[1775] (Application example 2)

[1776] 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."

[1777] Current plant cultivation support systems can analyze the type and health of plants, but they cannot provide flexible advice based on the user's emotions. Furthermore, there is a lack of systems for food delivery that provide advice on the nutritional value and health aspects of food. This creates a need for a comprehensive system to support plant cultivation and healthy eating.

[1778] 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 a user to take and send an image of a plant or food, means for executing an image recognition model to analyze the image received by the server, and means for analyzing the user's emotions using an emotion engine and adjusting the content and tone of advice. This enables the user to quickly and accurately diagnose the health condition of the plant or food and provide cultivation or food advice that takes the user's emotions into consideration.

[1779] A "user" is someone who uses the system to take images of plants or food and provide information about them.

[1780] "Plants" are living things such as green plants and flowers that are cultivated by the user.

[1781] "Food" refers to food such as dishes or ingredients that the user photographs.

[1782] "Means for taking and transmitting images" refers to a function that allows a user to take an image of a plant or food using a device such as a smartphone and transmit that image to a server.

[1783] The "server" is a computer system that receives and analyzes images, references a database, and generates optimal advice.

[1784] An "image recognition model" is an analytical method that uses machine learning algorithms to identify the type and health status of plants or food.

[1785] "Means for determining status" refers to the function of determining the current health status of a plant or food based on the analysis results of an image recognition model.

[1786] "Means for requesting additional information" refers to a function that allows the server to request missing information from the user based on the analysis results.

[1787] "Means for providing additional information" refers to a function that allows users to provide information such as sunlight exposure, watering frequency, and ingredients used in response to inquiries from the server.

[1788] "Means for referencing a database" refers to the function by which the server searches an internal database based on the additional information provided and obtains relevant growing guidelines and nutritional information.

[1789] "Means for generating and transmitting raising or food advice" refers to a function that generates optimal raising or food advice based on the information and analysis results acquired by the server and transmits it to the user.

[1790] An "emotion engine" is software that uses natural language processing technology to recognize and analyze a user's emotional state.

[1791] "Means for analyzing emotions and adjusting the content and tone of advice" refers to a function that provides the user with advice of appropriate content and tone based on the user's emotions analyzed by the emotion engine.

[1792] MODE FOR CARRYING OUT THE INVENTION

[1793] To put the present invention into practice, we will explain the specific configuration and method of a system that allows users to take and send images of plants or food. This system is built by combining a user's terminal, a server, a database, and an emotion engine.

[1794] System Configuration

[1795] 1. User Device:

[1796] Using a smartphone or tablet, users take pictures of plants or food and send them to a server via an application.

[1797] 2. Server:

[1798] The server analyzes the received image, queries the user for additional information, and generates optimal nutrition or dietary advice based on the acquired information by referencing a database. It also runs an emotion engine to analyze the user's emotions and adjust the content and tone of the advice.

[1799] 3. Database:

[1800] Databases such as MySQL and MongoDB are used to store growing guidelines, nutritional information, and problem solutions for each plant and food.

[1801] 4. Emotion Engine:

[1802] It uses NLP (Natural Language Processing) APIs to analyze user sentiment and tailor advice accordingly.

[1803] 5. Image Recognition Model:

[1804] TensorFlow and PyTorch are used to run machine learning models to analyze images of plants or food.

[1805] Program processing explanation

[1806] The server receives the image sent by the user and inputs it into an image recognition model to identify the type of plant or food and its health condition. The server then queries the user for any additional information needed based on the analysis results. The user provides the server with information such as sunlight exposure, watering frequency, and ingredients used. The server then uses an emotion engine to analyze the user's emotions and recognize their emotional state.

[1807] The server then uses this information to retrieve relevant information from a database, which includes growing guidelines, nutritional information, and solutions for each plant or food. The server then integrates the retrieved data, analysis results, and the user's emotional state to generate optimal growing or food advice. This advice is then sent to the user.

[1808] Examples of concrete examples and prompts

[1809] Example 1: When the leaves of a houseplant turn brown

[1810] 1. A user takes a photo of a houseplant whose leaves are turning brown and sends it to the server through the application.

[1811] 2. The server receives the photo and inputs it into an AI image recognition model.

[1812] 3. The image recognition model produces the analysis result that "the leaves are brown."

[1813] 4. The server sends a query to the user: "I've checked the condition of the leaves. When was the last time you watered them?"

[1814] 5. The user responds, "3 days ago."

[1815] 6. The emotion engine analyzes the user's message and recognizes that the user is "worried."

[1816] 7. The server consults the database to find the appropriate watering frequency.

[1817] 8. The server generates advice such as "It is recommended that you keep this plant out of direct sunlight and water it once a week. Also, there is no need to worry; if you follow this advice, it will recover its health" and sends it to the user.

[1818] 9. Users take this advice and apply it in practice.

[1819] Example 2: If you are concerned about the nutritional value of a dish

[1820] 1. A user takes a photo of a healthy salad and sends it with the comment, "I want to continue eating healthy."

[1821] 2. The server receives the photo, determines it is a "salad," and retrieves nutritional information for the main ingredients used (e.g., lettuce, tomato, cucumber) from the database.

[1822] 3. The emotion engine recognizes the user's emotional state of "motivation."

[1823] 4. The server integrates the database information with the emotional state, generates advice for the user, such as "This salad is very healthy, especially rich in vitamin C. Keep it up!", and sends it to the user.

[1824] Prompt Sentence Examples

[1825] "Please analyze the food in this image to get the ingredient information."

[1826] "Identify the emotion a user feels when they say 'I'm very happy.'"

[1827] "Generate personalized health advice based on analytics results and user sentiment."

[1828] Through these specific examples, users can quickly and accurately diagnose the health of plants or food and receive emotionally sensitive advice.

[1829] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1830] Step 1:

[1831] A user takes an image of a plant or food item and sends the image to a server through the application.

[1832] Input: An image of a plant or food

[1833] Output: Image data sent to the server

[1834] Specific operation: Take a picture using the camera on the user device and press the send button in the application

[1835] Step 2:

[1836] The server inputs the images received from the user into an image recognition model for analysis.

[1837] Input: Received image data

[1838] Output: Image recognition results (identification of plant or food type and health status)

[1839] Specific operation: The server inputs image data into an AI image recognition model (e.g., TensorFlow or PyTorch) and obtains the analysis results.

[1840] Step 3:

[1841] The server queries the user for missing information based on the results of image recognition.

[1842] Input: Image recognition results (type of plant or food and health status)

[1843] Output: A message asking for more information

[1844] Specific operation: Based on the analysis results, the server generates a message to send additional information (e.g., sunlight, watering frequency, ingredients used) and sends it to the user's device.

[1845] Step 4:

[1846] The user provides additional information in response to a query from the server.

[1847] Input: Query message from the server

[1848] Output: Additional information provided

[1849] What happens: The user answers questions through the application and sends the information to the server.

[1850] Step 5:

[1851] The server uses an emotion engine to analyze the user's emotions.

[1852] Input: User's message or voice data

[1853] Output: Sentiment analysis results (e.g., worry, satisfaction, anxiety, etc.)

[1854] Specific operation: The server inputs the user's message and voice data into an emotion engine (e.g., NLP API) to identify the emotional state.

[1855] Step 6:

[1856] Using the additional information acquired by the server and the results of emotion analysis, the server references the database to acquire related information.

[1857] Input: Additional information and sentiment analysis results

[1858] Output: Growing guidelines or nutritional information

[1859] What happens: The server searches an internal database (e.g., MySQL or MongoDB) to retrieve relevant growing guidelines and nutritional information.

[1860] Step 7:

[1861] The server integrates the acquired data, analysis results, and emotional state to generate optimal development or food advice.

[1862] Input: Nutritional guidelines or nutritional information, additional information, emotional state

[1863] Output: personalized advice

[1864] What it does: The server runs an algorithm that integrates the data and generates personalized nutrition or dietary advice.

[1865] Step 8:

[1866] The server sends the generated advice to the user.

[1867] Input: personalized advice

[1868] Output: Notification message to the user's terminal

[1869] What happens: The server generates a message containing the advice and sends it to the user's application.

[1870] In this way, users can quickly and accurately diagnose the health of their plants or food products and receive emotionally sensitive advice.

[1871] 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.

[1872] 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.

[1873] 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.

[1874] 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.

[1875] 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.

[1876] 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.

[1877] 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).

[1878] 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.

[1879] 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."

[1880] 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.

[1881] 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).

[1882] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[1883] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[1884] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[1885] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[1886] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[1887] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific processing may be a single processor.

[1888] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[1889] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[1890] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[1891] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[1892] The following is further disclosed regarding the above embodiment.

[1893] (Claim 1)

[1894] A means for a user to take and send an image of a plant;

[1895] means for implementing an image recognition model to analyze the images received by the server;

[1896] A means for the server to determine the state of the plant based on the result of the image recognition;

[1897] A means for the server to inquire about additional information from the user based on the determination result;

[1898] a means for the user to provide additional information;

[1899] a means for the server to perform a database lookup based on the additional information provided;

[1900] A means for the server to generate optimal breeding advice and transmit it to the user;

[1901] A system including:

[1902] (Claim 2)

[1903] 10. The system of claim 1, further comprising means for identifying the type and health of a plant based on a machine learning algorithm.

[1904] (Claim 3)

[1905] The system according to claim 1, further comprising means for storing in the database growing guidelines and solutions to problems for each plant.

[1906] "Example 1"

[1907] (Claim 1)

[1908] A means for a user to acquire and transmit an image of a plant using an imaging device;

[1909] A means for storing the video received by the server;

[1910] A means to run an AI image recognition model to analyze the video stored on the server;

[1911] A means for the server to identify the state of the plant based on the result of the...

Claims

1. A means for a user to take and send an image of a plant; means for implementing an image recognition model to analyze the images received by the server; A means for the server to determine the state of the plant based on the result of the image recognition; A means for the server to inquire about additional information from the user based on the determination result; a means for the user to provide additional information; a means for the server to perform a database lookup based on the additional information provided; A means for the server to generate optimal breeding advice and transmit it to the user; A system including:

2. 10. The system of claim 1, further comprising means for identifying the type and health of a plant based on a machine learning algorithm for the image recognition model.

3. The system according to claim 1, further comprising means for storing in the database growing guidelines and solutions to problems for each plant.

Images