System

Abstract

A system is provided.SOLUTION: A system including means for uploading a photograph of a plant taken by a user, means for transmitting the uploaded photograph data to a server, means for passing the photograph data received by the server to an image recognition engine and identifying a type of disease or pest of the plant, means for generating a specific countermeasure against the disease or pest of the plant based on an identification result, means for providing a recommendation and a purchase link of a necessary product in addition to the countermeasure, and means for transmitting and displaying a result to a user terminal.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] When individual gardening enthusiasts grow plants at home, proper management of the health of their plants requires specialized knowledge, which is often difficult for beginners. In particular, it is difficult to quickly and accurately identify plant diseases and pests and take appropriate countermeasures. Furthermore, procuring the products necessary to solve the problems is also time-consuming. The present invention aims to solve these problems and provide a system that allows users to easily and quickly manage the health of their plants. [Means for solving the problem]

[0005] The present invention provides a system that includes a means for users to upload photos of plants they have taken, a means for transmitting the uploaded photo data to a server, a means for the server to pass the received photo data to an image recognition engine and identify the type of plant disease or pest, a means for generating specific countermeasures for the plant disease or pest based on the identification results, a means for providing necessary product recommendations and purchase links in addition to the countermeasures, and a means for transmitting and displaying the results to a user's terminal. The system also includes a means for the image recognition engine to detect abnormalities in the photo and extract features, and a means for an AI model to analyze the features and identify the type of disease or pest. This allows users to properly manage the health of their plants and quickly procure the necessary products, even without specialized knowledge.

[0006] "Users" are individual gardening enthusiasts who use the system to upload photos of their plants and receive disease and pest identification and treatment suggestions.

[0007] A "terminal" is a device that a user uses to access the system, such as a smartphone or a computer.

[0008] The "server" is the central device of the system that receives photo data sent by users and analyzes it using an image recognition engine and AI model.

[0009] "Photo data" refers to plant image information that a user takes using a device and uploads.

[0010] An "image recognition engine" is software or an algorithm that detects abnormalities in the photo data received by the server and identifies plant diseases and pests.

[0011] An "AI model" is an artificial intelligence model that analyzes features extracted by an image recognition engine and identifies types of plant diseases and pests.

[0012] "Features" are information extracted from an image and are attribute data used to identify plant diseases and pests.

[0013] "Identification results" are conclusions about the type of plant disease or pest obtained using an image recognition engine and AI model.

[0014] "Countermeasures" are specific methods of care or treatment for diseases or pests that are generated based on the identification results.

[0015] "Recommended products" are related products such as nutrients and insecticides that are suggested by the server based on the identification results and countermeasures.

[0016] "Purchase Link" means direct access to an online shopping site provided to enable users to easily purchase the recommended products. [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 is a system in which users upload photos of plants, and the server analyzes the photo data using an image recognition engine to identify plant diseases and pests and provide appropriate countermeasures. Specific embodiments for implementing the present invention are described below.

[0039] 1. Upload and send photos

[0040] Users take photos of their plants' leaves, stems, and flowers using a device such as a smartphone or PC, and upload the photos to the system using the system's application or web interface. At this time, the device receives the user's photo data.

[0041] 2. Receiving and analyzing photo data by the server

[0042] After the device receives the photo data, it sends it to the server. The server temporarily stores the received photo data in storage and then performs preprocessing on the image (e.g., image resizing, noise removal, color correction, etc.).

[0043] The server then passes the preprocessed image data to an image recognition engine, which detects abnormal areas in the photo and extracts features, which are important information for identifying plant diseases and pests.

[0044] 3. Identifying diseases and pests

[0045] The server then uses the AI ​​model to analyze the features provided by the image recognition engine and identify the type of plant disease or pest. Based on the identified disease or pest type (e.g., black spot or aphids), a detailed diagnosis is generated.

[0046] 4. Proposal of countermeasures

[0047] Based on the results of the diagnosis, the server will suggest specific measures to take against diseases and pests, such as removing the infected area or using a specific fungicide in the case of black spot.

[0048] 5. Recommend related products and generate purchase links

[0049] Furthermore, based on the diagnosis results and countermeasures, the server searches the database for relevant products such as nutrients, fungicides, and insecticides that are needed and recommends them to the user. The recommended products include a purchase link to an online shopping platform such as Yahoo Shopping.

[0050] 6. Sending and displaying results

[0051] The server generates a response that combines the diagnosis results, countermeasures, recommended products, and a purchase link, and sends it to the device. The device receives this data and displays it in a format that is easy for the user to understand. The display content includes a detailed explanation, such as "Your roses are suffering from black spot disease. The following measures are required to treat this disease," as well as images of the recommended products and purchase links.

[0052] Specific examples

[0053] For example, suppose a user finds black spots on the leaves of a rose and uploads a photo of the leaves. The device sends the photo to a server, which analyzes it using an image recognition engine and AI model and identifies it as black spot disease. The diagnosis result is displayed as follows: "The black spots found on the rose leaves are black spot disease. It is recommended that you remove the infected areas and use a specific fungicide." In addition, the app recommends a fungicide suitable for the solution and provides a purchase link, allowing the user to immediately purchase the necessary product.

[0054] In this way, users can effectively manage plant health and quickly source the products they need, even without specialized knowledge.

[0055] The processing flow will be explained below.

[0056] Step 1:

[0057] The user takes a photo of the plant with their device.

[0058] Step 2:

[0059] A user uploads a photograph of a plant to the system through the system's application or web interface.

[0060] Step 3:

[0061] The device sends the photo data uploaded by the user to the server.

[0062] The transmitted data includes the photo file and metadata such as the user ID.

[0063] Step 4:

[0064] The server stores the received photo data in storage.

[0065] Step 5:

[0066] The server performs image pre-processing (e.g., image resizing, noise removal, color correction, etc.).

[0067] Step 6:

[0068] The server passes the preprocessed images to an image recognition engine.

[0069] Step 7:

[0070] The image recognition engine detects abnormal areas in the photo and extracts features.

[0071] Step 8:

[0072] The AI ​​model analyzes the features and identifies the type of disease or pest.

[0073] During this process, specific identification results such as "black spot disease" or "aphids" are obtained.

[0074] Step 9:

[0075] The server generates a diagnosis result based on the output of the AI ​​model.

[0076] The diagnosis results include information such as the name of the identified disease or pest, a description of the symptoms, and the degree of progression.

[0077] Step 10:

[0078] The server generates appropriate countermeasures based on the identified diseases and pests.

[0079] For example, specific measures include "in the case of black spot disease, remove the infected area and use a specific fungicide."

[0080] Step 11:

[0081] Based on the diagnosis results and countermeasures, the server searches a database for relevant products such as necessary nutrients, fungicides, and insecticides and recommends them.

[0082] Step 12:

[0083] The server generates a purchase link to Yahoo! Shopping or the like along with information about the recommended product.

[0084] Step 13:

[0085] The server generates a response including the diagnosis result, countermeasures, recommended products, and a purchase link, and transmits it to the terminal.

[0086] Step 14:

[0087] The device analyzes the data received from the server and displays it in an easy-to-understand manner for the user.

[0088] The display clearly lists the diagnostic results, countermeasures, recommended products, and links to purchase them.

[0089] Step 15:

[0090] The user checks the displayed diagnostic results and countermeasures, and if necessary, clicks on the purchase link for the recommended product to proceed with the purchase process on Yahoo! Shopping.

[0091] These are the detailed steps of the program's processing, which allows users to quickly identify plant problems and take appropriate measures.

[0092] Example 1

[0093] 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."

[0094] Traditionally, diagnosing plant diseases and pests required specialized knowledge, making it difficult for average users. Furthermore, actually receiving a diagnosis required a visit from an expert or bringing the plant to a facility, which was costly and time-consuming. Furthermore, the process of finding specific countermeasures and necessary products after a diagnosis was time-consuming. There is a need for a system that addresses these issues and allows average users to easily manage the health of their plants.

[0095] 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.

[0096] In this invention, the server includes means for uploading images of plants taken by users, means for transmitting the uploaded image data to the server, means for passing the image data received by the server to an image recognition system and identifying the type of plant disease or pest, means for generating specific countermeasures for the plant disease or pest based on the identification results, means for providing recommendations and purchase links for necessary products in addition to the countermeasures, and means for transmitting and displaying the results to a user terminal. This enables users, even without specialized knowledge, to quickly and easily diagnose plant diseases and pests and obtain appropriate countermeasures and necessary products.

[0097] A "user" is an entity that uses the system to upload images of plants and receive diagnostic results and countermeasures.

[0098] "Terminal" refers to an electronic device used by a user, such as a smartphone or computer, for taking and uploading images and displaying the results.

[0099] "Image data" refers to data that digitally represents an image of a plant photographed by a user.

[0100] A "server" is a central computing device that stores received image data and performs analysis using an image recognition system and artificial intelligence models.

[0101] An "image recognition system" is software that detects abnormal parts from received image data and extracts characteristic information.

[0102] "Feature information" is information about specific parts or patterns in an image that are important for identifying diseases or pests, extracted by the image recognition system.

[0103] An "artificial intelligence model" is a trained algorithm that analyzes feature information provided by an image recognition system and identifies the type of disease or pest.

[0104] "Identification results" are information about the type of plant disease or pest obtained as a result of analysis by the artificial intelligence model.

[0105] "Countermeasures" are specific treatment methods or measures against plant diseases or pests that are generated based on the identification results.

[0106] "Recommended products" are products that are required to implement countermeasures and are recommended to users.

[0107] "Purchase Link" means the URL for purchasing the Recommended Product on an online shopping platform.

[0108] "Results" refers collectively to information including identification results, countermeasures, recommended products, and purchase links that are provided to users.

[0109] The present invention is a system in which users upload images of plants they have taken, and the server analyzes the image data using an image recognition system and artificial intelligence model to identify plant diseases and types of pests and provide appropriate countermeasures.

[0110] First, the user takes an image of the plant using a device such as a smartphone or PC. It is preferable to take an image that clearly captures any abnormalities, such as leaves, stems, or flowers. Next, the user selects and uploads the image using the system's application or web interface. The device receives the image data and sends it to the server.

[0111] The server receives image data sent from the user's device and temporarily stores it in storage. The server then performs preprocessing on the stored image data. This preprocessing includes image resizing, noise removal, color correction, etc. This preprocessing improves the accuracy of analysis by the image recognition system.

[0112] The server then passes the preprocessed image data to an image recognition system, which uses deep learning and computer vision techniques to detect abnormalities in the image and extract feature information, which is key to identifying plant diseases and pests.

[0113] The extracted feature information is returned to the server, which then inputs it into an AI model. The AI ​​model is pre-trained and capable of identifying the type of plant disease or pest. The AI ​​model analyzes the feature information and identifies the specific disease or pest. For example, black spot or aphids may be detected.

[0114] Based on the identification results, the server generates specific countermeasures for the disease or pest. For example, in the case of black spot disease, this includes how to remove the infected area and how to use a specific fungicide. Based on the countermeasures, the server also searches a database for related products, such as nutrients, fungicides, and insecticides, and recommends them to the user. The recommended products include a purchase link to an online shopping platform.

[0115] Finally, the server generates response data that combines the diagnosis results, countermeasures, recommended products, and a purchase link, and sends it to the device. The device then displays the received response data to the user. The display includes the diagnosis results, specific countermeasures, images of recommended products, and purchase links, allowing the user to quickly and effectively manage the health of their plants based on this information.

[0116] For example, suppose a user finds black spots on a rose leaf and uploads an image of the leaf. The user's device sends the image to a server, which analyzes it using an image recognition system and an artificial intelligence model and identifies it as black spot disease. The diagnosis result is displayed as follows: "The black spots found on the rose leaf are black spot disease. It is recommended that you remove the infected area and use a specific fungicide." The app also recommends the best fungicide for the treatment and provides a link to purchase it. In this way, users can effectively manage the health of their plants and quickly obtain the necessary products without any specialized knowledge.

[0117] An example of a prompt sentence to input to the generative AI model is as follows:

[0118] "I uploaded a picture of some black spots on the leaves of my plant. Can you please tell me what these black spots are and how to deal with them?"

[0119] In this way, the present invention supports the user's plant health management by identifying diseases and pests based on images of plants taken by the user and suggesting appropriate countermeasures and related products.

[0120] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0121] Step 1:

[0122] The user takes a picture of the plant using a device such as a smartphone or PC. The captured image is saved on the device as a digital image file. The input is the image taken by the user with the device's camera, and this image is saved on the device as the output.

[0123] Step 2:

[0124] A user opens the system's application or web interface, selects a captured image, and presses a button to upload it. The input is the image file selected by the user, and the selected image is included in the upload request as the output.

[0125] Step 3:

[0126] The device receives the image data uploaded by the user. It creates a request to send the image data to the server along with the user authentication information, and sends it to the server as an HTTP POST request. The input is the image data selected by the user and the authentication information, and the output is an HTTP request containing these.

[0127] Step 4:

[0128] The server receives a request for image data sent from the terminal and extracts the image data. The server saves this image data in storage. The input is the HTTP request sent from the terminal, and the extracted image data is saved in storage as intermediate output.

[0129] Step 5:

[0130] The server performs image preprocessing such as resizing, noise removal, and color correction on the stored image data. The input is the stored raw image file, and the processed image after these preprocessing steps is the output. Preprocessing at this step improves the accuracy of the subsequent image recognition.

[0131] Step 6:

[0132] The server passes the preprocessed image data to an image recognition system, which detects abnormalities and extracts feature information. The preprocessed image data is input, and the location and feature information of abnormalities are obtained as output through the image recognition system.

[0133] Step 7:

[0134] The server inputs the feature information provided by the image recognition system into an artificial intelligence model. The AI ​​model analyzes the feature information and identifies the type of plant disease or pest. The input is feature information, and the output is specific information about the disease or pest as a result of the identification.

[0135] Step 8:

[0136] The server generates specific countermeasures based on the identification results, including detailed treatment methods and countermeasures for the identified diseases and pests. The input is the identification results, and the generated countermeasures are the output.

[0137] Step 9:

[0138] The server searches a database of related products based on the countermeasure and finds recommended products such as needed nutrients, fungicides, insecticides, etc. The input is the countermeasure information, and the output is related product information from the database.

[0139] Step 10:

[0140] The server compiles information about the recommended products and generates a purchase link to an online shopping platform. The input is the information about the recommended products, and the generated purchase link is the output.

[0141] Step 11:

[0142] The server generates response data that combines the diagnosis results, countermeasures, recommended products, and purchase links, and sends it to the user's device. The input is the diagnosis results, countermeasures, recommended products, and purchase links that have been generated so far, and the response data that includes these is the output.

[0143] Step 12:

[0144] The device then displays the received response data to the user. The displayed content includes the diagnosis results, specific countermeasures, images of recommended products, and links to purchase them, all in a format that is easy for the user to understand. The input is the response data from the server, and the display content that the user can see is the output.

[0145] Through these processing steps, users can quickly and effectively diagnose plant diseases and pests without specialized knowledge, and obtain appropriate countermeasures and necessary products.

[0146] (Application example 1)

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

[0148] In modern agriculture and horticulture, there is a need for early detection and rapid response to plant diseases and pests. Especially in large-scale cultivation environments, there are limitations to manual monitoring and response. There is also a need for systems that can accurately identify the type of disease or pest and quickly provide appropriate countermeasures. Furthermore, it is also important to be able to easily obtain the products needed for these countermeasures.

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

[0150] In this invention, the server includes a means for uploading photos of plants taken by a user or a robot to the server and implementing appropriate countermeasures based on the analysis results, a means for recommending products related to countermeasures for identified diseases and pests, and a means for notifying an administrator of the diagnosis results and recommended products. This enables early detection of diseases and pests and prompt response, automates monitoring and management of the cultivation environment, and realizes efficient agricultural and horticultural activities.

[0151] 1. "User" refers to the individual or artifact that takes photos of plants and uploads them to the system.

[0152] 2. "Plant photos" refers to image data of plant leaves, stems, flowers, etc.

[0153] 3. "Means for uploading" refers to technology that has the functionality to transfer plant photos to a system or server.

[0154] 4. "Server" refers to a computer system that receives plant photo data and performs image recognition and analysis.

[0155] 5. "Image recognition engine" refers to algorithms and software that analyze photographic data, detect abnormalities, and extract features.

[0156] 6. "Methods for identifying types of plant diseases and pests" refers to technologies that use image recognition engines and AI models to analyze the health of plants and identify diseases and pests.

[0157] 7. "Means for generating specific countermeasures" refers to a function that suggests specific countermeasures for plant diseases and pests based on the identification results.

[0158] 8. "Means for recommending necessary products and providing links to purchase them" refers to a system that has the function of searching for products related to the solution and providing links to purchase them.

[0159] 9. "Means for transmitting and displaying results on user devices" refers to the technology for transferring and displaying analysis results and countermeasures on the device used by the user.

[0160] 10. "Means for a robot to take photos, upload the photos to a server, and take appropriate countermeasures based on the analysis results" refers to technology in which a robot placed in a factory or other environment takes photos of plants, sends them to a server, and takes appropriate countermeasures based on the diagnostic results.

[0161] 11. "Means for recommending products related to countermeasures for identified diseases or pests" refers to a system that has the functionality to search for and recommend products necessary for appropriate treatment or countermeasures based on the diagnosis of a disease or pest.

[0162] 12. "Means for notifying the Administrator of the diagnosis results and recommended products" refers to technology for notifying the Administrator of details of diagnosed diseases or pests and information on recommended products.

[0163] The present invention relates to a system for identifying plant diseases and pests using photos of plants taken by a user and providing appropriate countermeasures. Specific embodiments for carrying out the present invention will be described below.

[0164] First, a user or a robot in the factory takes a photo of the plant. The user takes a photo of the plant using a smartphone or computer and uploads the photo to the system. Meanwhile, the robot takes a photo of the plant in the factory using its built-in camera.

[0165] Next, the captured photos are uploaded and sent to a server. The server passes the received photo data to an image recognition engine. This image recognition engine analyzes the photos, detects abnormalities such as plant diseases and pests, and extracts feature values. The image recognition engines used include libraries such as TensorFlow and Keras.

[0166] The extracted features are then analyzed by an AI model, which uses the features obtained from the image recognition engine to identify the type of disease or pest. For this identification, a pre-trained generative AI model is used. The model used includes a deep learning model (e.g., a convolutional neural network).

[0167] Based on the identification results, the server generates appropriate countermeasures. For example, for a specific disease, it suggests methods for removing the infected area or the use of specific medications. It also searches a database of products related to the recommended countermeasures and lists the corresponding products. This includes necessary nutrients, fungicides, and insecticides, and provides links to purchase these products.

[0168] The server then generates a response that compiles the diagnosis results, proposed countermeasures, and recommended products, and notifies the user or factory manager via a smartphone or computer application, or by email.

[0169] As a concrete example, suppose strange spots appear on the leaves of tomatoes being grown in a factory. A robot takes a photo of the spot and sends it to the server. The server analyzes the photo using an image recognition engine and an AI model and identifies it as spot disease. The diagnosis results are displayed as spot disease, and countermeasures include removing the infected area and using a specific fungicide. Furthermore, a link to purchase the recommended fungicide is provided, allowing managers to take prompt action.

[0170] Example prompt sentence:

[0171] Below are some examples of prompts to input to the generative AI model.

[0172] "Please identify the plant disease or pest seen in this image. Please suggest the necessary treatment and related products suitable for this disease."

[0173] Input image: path_to_plant_image.jpg

[0174] In this way, the present invention provides a system that effectively supports plant health management.

[0175] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0176] Step 1:

[0177] The user or the robot takes a photo of the plant. The user uses a smartphone, and the robot uses its built-in camera. The input is the plant photo, which becomes the input data for the system. The output is the captured photo data.

[0178] Step 2:

[0179] The device uploads the photograph of the plant to the server. The input is the photographed photo data, which becomes the data to be sent to the server. The output is the completion of sending the photo data to the server.

[0180] Step 3:

[0181] The server passes the received photo data to the image recognition engine, which performs preprocessing such as image resizing, noise removal, and color correction. The input is photo data, which becomes the data to be preprocessed. The output is preprocessed image data.

[0182] Step 4:

[0183] The server passes the preprocessed image data to an image recognition engine, which extracts features to identify plant diseases and pest types. The preprocessed image data is input, which becomes the input data for feature extraction. The extracted features are output.

[0184] Step 5:

[0185] The server inputs the extracted features into an AI model to identify the type of disease or pest. The extracted features serve as input data for the AI ​​model, and the identification result is generated as output.

[0186] Step 6:

[0187] The server generates specific countermeasures for plant diseases and pests based on the identification results. The input is the identification results, which serve as input data for countermeasure generation. The output is the specific countermeasures.

[0188] Step 7:

[0189] The server generates the necessary product recommendations and purchase links based on the identification results and countermeasures. The identification results and countermeasures are input, which become the input data for generating recommended products. The recommended products and purchase links are generated as output.

[0190] Step 8:

[0191] The server sends the diagnosis results, countermeasures, recommended products, and purchase links to the user's or administrator's terminal for display. The inputs are the diagnosis results, countermeasures, recommended products, and purchase links, which serve as notification data for the user or administrator. The output is the display result that is displayed on the terminal.

[0192] In this way, the system of the present invention can effectively support plant health management.

[0193] 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.

[0194] The present invention combines an emotion engine with a system that analyzes plant photos uploaded by users, identifies plant diseases and pests, and recommends specific countermeasures and necessary products based on the results. Specific embodiments for implementing the present invention are described below.

[0195] 1. Upload and send photos

[0196] Users take photos of plants using their own devices and upload them to the system's application or web interface, at which point the device receives the user's photo data.

[0197] 2. Receiving and analyzing photo data by the server

[0198] After the device receives the photo data, it sends it to the server. The server stores the received photo data in storage. It then performs preprocessing on the image (e.g., image resizing, noise removal, color correction, etc.) and passes the preprocessed image data to the image recognition engine.

[0199] 3. Identifying diseases and pests

[0200] The server's image recognition engine detects abnormalities in the photo and extracts features. At the same time, an AI model analyzes the features and identifies the type of plant disease or pest. Based on the identified disease or type of pest (e.g., black spot or aphids), a detailed diagnosis is generated.

[0201] 4. Proposal of countermeasures

[0202] Based on the results of the diagnosis, the server will suggest specific measures to deal with the disease or pest, such as how to remove the infected area or use a specific fungicide in the case of black spot.

[0203] 5. Recommend related products and generate purchase links

[0204] Based on the diagnosis and countermeasures, the server then searches a database for relevant products, such as suitable nutrients, fungicides, and insecticides, and recommends them to the user, including a link to an online shopping platform for purchase.

[0205] 6. Emotion Recognition by Emotion Engine

[0206] A new feature being added is the emotion engine, which recognizes the user's emotions. The emotion engine identifies the user's emotional state by analyzing facial expressions, voice, and behavioral patterns while the user is using the system. This emotion data is collected through sensors such as cameras and microphones.

[0207] 7. Emotion-based response optimization

[0208] The server uses the emotion data from the emotion engine to provide the optimal response based on the user's emotions. For example, if the user is feeling down, it will provide a more encouraging message.

[0209] 8. Tailoring product recommendations based on emotions

[0210] Using data from the emotion engine, the server adjusts the display order and content of recommended products. For example, if the user is in a hurry, it can prioritize products with immediate effects.

[0211] 9. Sending and displaying results

[0212] The server sends the diagnosis results, countermeasures, emotion recognition results, recommended products, and a purchase link all together to the device. The device receives this data and displays it in an easy-to-understand manner for the user. For example, along with the diagnosis results, the device may display an explanation such as "Your plant is suffering from black spot disease. To treat this disease, the following measures are required," as well as an encouraging message based on the user's emotion, an image of the recommended product, and a purchase link.

[0213] Specific examples

[0214] For example, suppose a user finds black spots on a rose leaf and uploads a photo of the leaf. The device sends the photo to a server, which uses an image recognition engine and an AI model to identify it as black spot disease. The diagnosis results are displayed as follows: "The black spots found on the rose leaf are black spot disease. It is recommended that you remove the infected area and use a specific fungicide." In addition, the emotion engine recognizes from the user's facial expression that they appear worried, and prioritizes displaying encouraging messages such as "Don't worry, recovery is expected if you take early action" and links to purchase fast-acting fungicides.

[0215] In this way, users can effectively manage the health of their plants without any specialized knowledge, quickly obtain the necessary products, and receive appropriate emotional support.

[0216] The processing flow will be explained below.

[0217] Step 1:

[0218] The user takes a photo of the plant with their device.

[0219] Step 2:

[0220] A user uploads a photograph of a plant to the system through the system's application or web interface.

[0221] Step 3:

[0222] The device sends the photo data uploaded by the user to the server.

[0223] The transmitted data includes the photo file and metadata such as the user ID.

[0224] Step 4:

[0225] The server stores the received photo data in storage.

[0226] Step 5:

[0227] The server performs image pre-processing (e.g., image resizing, noise removal, color correction, etc.).

[0228] Step 6:

[0229] The server passes the preprocessed images to an image recognition engine.

[0230] Step 7:

[0231] The image recognition engine detects abnormal areas in the photo and extracts features.

[0232] Step 8:

[0233] The AI ​​model analyzes the features and identifies the type of disease or pest.

[0234] During this process, specific identification results such as "black spot disease" or "aphids" are obtained.

[0235] Step 9:

[0236] The server generates a diagnosis result based on the output of the AI ​​model.

[0237] The diagnosis results include information such as the name of the identified disease or pest, a description of the symptoms, and the degree of progression.

[0238] Step 10:

[0239] The server generates appropriate countermeasures based on the identified diseases and pests.

[0240] For example, specific measures include "in the case of black spot disease, remove the infected area and use a specific fungicide."

[0241] Step 11:

[0242] Based on the diagnosis results and countermeasures, the server searches a database for relevant products such as necessary nutrients, fungicides, and insecticides and recommends them.

[0243] Step 12:

[0244] The server generates a purchase link to an online shopping platform along with information about the recommended products.

[0245] Step 13:

[0246] The server generates a response that combines the diagnosis results, countermeasures, recommended products, and a purchase link, and transmits it to the terminal.

[0247] Step 14:

[0248] The device analyzes the data received from the server and displays it in an easy-to-understand manner for the user.

[0249] The display clearly lists the diagnostic results, countermeasures, recommended products, and links to purchase them.

[0250] Step 15:

[0251] The user checks the displayed diagnostic results and countermeasures.

[0252] Step 16:

[0253] The user clicks on the purchase link for the recommended product and proceeds with the online shopping purchase process.

[0254] Step 17:

[0255] The emotion engine analyzes the user's facial expressions, voice, and behavioral patterns to recognize their emotions.

[0256] Emotional data is collected through sensors such as cameras and microphones.

[0257] Step 18:

[0258] The server provides the optimal response according to the user's emotions based on the emotion data from the emotion engine.

[0259] For example, if the user is feeling down, include an encouraging message.

[0260] Step 19:

[0261] The server uses data from the emotion engine to adjust the content and order of recommended products.

[0262] For example, if a user is in a hurry, products with immediate effects will be displayed first.

[0263] Step 20:

[0264] The device receives the adjusted results based on the emotion data from the server and displays them again to the user.

[0265] For example, along with an encouraging message, product information that is displayed with priority and has a high immediate effect is displayed.

[0266] These are the specific processing steps of the system that combines the emotion engine. This flow not only enables users to quickly identify plant problems and take appropriate measures, but also allows them to receive appropriate emotional support.

[0267] Example 2

[0268] 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."

[0269] Conventional plant disease and pest diagnosis systems are limited to identifying diseases and pests, and are insufficient in proposing specific countermeasures or related products. Furthermore, they lack support that takes into account the user's emotions, and there is a need for improved usability. This often leads to anxiety and stress in users regarding plant health management.

[0270] 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.

[0271] In this invention, the server includes means for uploading photos of plants taken by users, means for transmitting the uploaded photo data to the server, means for storing and preprocessing the photo data received by the server, means for passing the preprocessed photo data to an image recognition engine and identifying the type of plant disease or pest, means for generating specific countermeasures for the plant disease or pest based on the identification results, means for recommending necessary products and providing purchase links in addition to the countermeasures, means for recognizing the user's emotions and adjusting the display content of the countermeasures and recommended products based on the emotions, and means for transmitting the results to the user terminal and displaying them. This enables users to effectively manage the health of their plants, quickly procure necessary products, and receive appropriate emotional support.

[0272] "User" refers to an individual who uses the system to take and upload photos of plants.

[0273] "Device" refers to the electronic device a user uses to take photos and upload data, including smartphones and tablets.

[0274] "Server" refers to the computer system that receives, stores, processes, and analyzes photo data sent by users.

[0275] "Photo data" refers to image files taken by a user on a device and sent to a server.

[0276] "Preprocessing" refers to image improvement processes such as resizing, noise removal, and color correction that are performed on the photo data received by the server.

[0277] "Image recognition engine" refers to software or algorithms used to detect abnormalities and extract features from preprocessed photographic data.

[0278] "Features" refer to measurable information extracted from photos by an image recognition engine to identify diseases and pests.

[0279] An "AI model" refers to an algorithm that uses machine learning technology to analyze features and identify types of plant diseases and pests.

[0280] "Identification results" refers to diagnostic information regarding the type of disease or pest identified by the AI ​​model.

[0281] "Countermeasures" refer to specific treatment methods for plant diseases and pests based on the identification results.

[0282] "Product Recommendations" refers to suggestions of relevant products that can be used to treat or protect plants, based on the response measures.

[0283] "Buy Link" means a URL or button that provides direct access to an online shopping site for the recommended product.

[0284] "Emotion engine" refers to software or algorithms for recognizing a user's emotional state.

[0285] "Emotional Data" means information regarding a User's current emotional state as determined by the Emotion Engine.

[0286] The present invention combines an emotion engine with a system that analyzes plant photos uploaded by users, identifies plant diseases and pests, and recommends specific countermeasures and necessary products based on the results. Specific embodiments for implementing the present invention are described below.

[0287] Taking and uploading photos

[0288] Users take photos of plants using their own devices. They then upload the photos through the system's application or web interface. The device then receives the user's photo data. Specifically, users take photos with their smartphone or camera and tap the "upload" button in the app.

[0289] Receiving and sending photo data

[0290] The device receives the photo data uploaded by the user and sends the data to the server. The device's network module transfers the data to the server using an HTTP request.

[0291] Photo data storage and preprocessing

[0292] The server stores the received photo data in storage. It then performs image preprocessing, which includes image resizing, noise removal, color correction, etc. Specifically, the server performs preprocessing using an image processing library (e.g., OpenCV).

[0293] Analysis by image recognition engine

[0294] The server passes the preprocessed image data to an image recognition engine, which detects abnormalities and extracts features. Specifically, a machine learning model (e.g., TensorFlow or PyTorch model) is used.

[0295] Identifying diseases and pests with AI models

[0296] The server inputs the feature values ​​sent from the image recognition engine into the AI ​​model to identify the type of plant disease or pest. Specifically, the AI ​​model analyzes the data using a neural network and outputs the results.

[0297] Generating diagnostic results

[0298] The server generates detailed diagnostic results based on the identified disease or pest type, using templates to create text information to display to the user as the diagnostic results.

[0299] Proposal of countermeasures

[0300] Based on the diagnosis results, the server proposes specific countermeasures for diseases and pests. For example, in the case of black spot disease, it suggests "how to remove the infected area" and "how to use a specific fungicide." Specific operations involve retrieving appropriate information from a database of countermeasure information that has been set up in advance.

[0301] Related product recommendations

[0302] The server recommends relevant nutrients, fungicides, and insecticides based on the diagnosis and countermeasures, searching for product information from a database of products suitable for the countermeasures, and generating a purchase link to an online shopping platform.

[0303] Emotion recognition by emotion engine

[0304] The device uses an emotion engine to recognize the user's emotions. Specifically, it analyzes sensor information collected through the camera and microphone to identify the user's emotional state from their facial expressions and tone of voice.

[0305] Sending emotional data

[0306] The device sends the recognized emotion data to the server. The device transfers the emotional state data to the server using an HTTP request.

[0307] Emotion-based response optimization

[0308] The server provides the optimal response based on the user's emotions based on the emotion data from the emotion engine. For example, if the user is feeling down, it will add an encouraging message. Specifically, it selects and edits a template message based on the emotion data.

[0309] Emotion-based product recommendation adjustment

[0310] The server uses emotional data to adjust the display order and order of recommended products. For example, if the user is in a hurry, it will prioritize products with immediate effects. Specifically, it rearranges the display order of products based on emotional data.

[0311] Sending and displaying results

[0312] The server compiles the diagnosis results, countermeasures, emotion recognition results, recommended products, and purchase links and sends them to the device. The device then receives this data and displays it in an easy-to-understand manner for the user. Specifically, it uses UI components to display the results in an application or web interface.

[0313] Specific examples

[0314] For example, suppose a user notices black spots on a rose leaf and uploads a photo of the leaf. The device sends the photo to the server, which uses an image recognition engine and AI model to identify it as black spot disease. The diagnosis results are displayed as follows: "The black spots on the rose leaf are black spot disease. It is recommended that you remove the infected area and use a specific fungicide." Additionally, the emotion engine recognizes the user's concern from their facial expression and prioritizes displaying encouraging messages such as "Don't worry, recovery is expected with early intervention" and links to purchase fast-acting fungicides. This allows users to effectively manage plant health without specialized knowledge, quickly procure the necessary products, and receive appropriate emotional support.

[0315] Prompt Sentence Examples

[0316] "Analyze a photo of black spots on rose leaves, detail the type of disease and how to treat it. Also, acknowledge the user's concern and include a message of encouragement."

[0317] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0318] Step 1:

[0319] The user takes a photo of a plant on their device and uploads the photo to the application or web interface. The input is the photo data of the plant taken by the user. Specifically, the user takes a photo with their smartphone or camera and taps the "upload" button in the application. The output is the photo data saved on the device.

[0320] Step 2:

[0321] The device receives photo data uploaded by the user. The input is the photo data uploaded by the user. Specifically, the uploaded photos are saved in a temporary folder in the device's application. The output is the saved photo data.

[0322] Step 3:

[0323] The device sends the received photo data to the server. The input is the photo data saved in the temporary folder. The device's network module transfers the data to the server using an HTTP request. The output is the photo data sent to the server.

[0324] Step 4:

[0325] The server saves the received photo data in storage. The input is the photo data sent from the device. An example of software used is a cloud storage service such as AWS S3. The output is the photo data saved in storage.

[0326] Step 5:

[0327] The server performs preprocessing on the stored photo data. The input is the photo data stored in storage. Preprocessing includes image resizing, noise removal, color correction, etc. Specifically, the server performs preprocessing using an image processing library (e.g., OpenCV). The output is the preprocessed image data.

[0328] Step 6:

[0329] The server passes the preprocessed image data to the image recognition engine. The input is the preprocessed image data. The image recognition engine detects abnormal parts in the image and extracts features. Specifically, a machine learning model (e.g., TensorFlow or PyTorch model) is used. The output is the extracted features.

[0330] Step 7:

[0331] The server inputs the features sent from the image recognition engine into the AI ​​model to identify the type of plant disease or pest. The input is the extracted features. The AI ​​model analyzes the data using a neural network and outputs the results. The output is the type of disease or pest identified.

[0332] Step 8:

[0333] The server generates detailed diagnostic results based on the identified disease or pest type. The input is the identification result from the AI ​​model. Specifically, a template is used to create text information to display to the user as the diagnostic result. The output is text data of the diagnostic result.

[0334] Step 9:

[0335] Based on the diagnosis results, the server proposes specific countermeasures against diseases and pests. The input is the text data of the diagnosis results. For example, in the case of black spot disease, it will suggest "how to remove the infected area" and "how to use a specific fungicide." The specific operation involves retrieving appropriate information from a database of pre-set countermeasure information. The output is text data of specific countermeasures.

[0336] Step 10:

[0337] The server recommends relevant nutrients, fungicides, and insecticides based on the diagnosis results and countermeasures. The input is text data of the specific countermeasures. Specifically, it searches for product information from a database of products suitable for the countermeasures and generates a purchase link to an online shopping platform. The output is data on the recommended products and the purchase link.

[0338] Step 11:

[0339] The device uses an emotion engine to recognize the user's emotions. The input is sensor information collected through the camera and microphone. The emotion engine identifies the user's emotional state from their facial expressions and tone of voice. Specifically, it uses an emotion analysis algorithm. The output is the user's emotional data.

[0340] Step 12:

[0341] The device sends the recognized emotion data to the server. The input is the identified user emotion data. The device transfers the emotional state data to the server using an HTTP request. The output is the emotion data sent to the server.

[0342] Step 13:

[0343] The server provides the optimal response based on the user's emotions, based on the emotion data from the emotion engine. The input is the emotion data sent to the server. For example, if the user is feeling down, an encouraging message is added. The specific operation is to select and edit a template message based on the emotion data. The output is text data of the optimal response based on the emotion.

[0344] Step 14:

[0345] The server uses the emotional data to adjust the display content and order of recommended products. The input is the emotional data sent to the server. For example, if the user is in a hurry, products with immediate effects are displayed first. Specifically, the display order of products is rearranged based on the emotional data. The output is recommended product data that has been adjusted based on the emotion.

[0346] Step 15:

[0347] The server compiles the diagnosis results, countermeasures, emotion recognition results, recommended products, and purchase links and sends them to the terminal. The input is the adjusted recommended product data and various text data. Specifically, it compiles this data in HTML or JSON format and sends it to the terminal as an HTTP response. The output is the display data sent to the terminal.

[0348] Step 16:

[0349] The device receives the data sent from the server and displays it in a user-friendly way. The input is the display data sent from the server. Specific operations include using UI components to display the results in an application or web interface. The output is the diagnosis results, countermeasures, emotion recognition results, recommended products, and purchase links displayed to the user.

[0350] (Application example 2)

[0351] 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."

[0352] In modern plant cultivation and gardening, when plants are attacked by disease or pests, it is necessary to take prompt and appropriate measures. However, it is difficult for ordinary users to accurately identify plant diseases and pests and take appropriate measures. Furthermore, if users feel discouraged or impatient, it may affect their ability to resolve the problem if appropriate support is not provided. A system that can solve these issues is needed.

[0353] 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 uploading photos of plants taken by the user, means for transmitting the uploaded photo data to the server, means for passing the photo data received by the server to an image recognition engine and identifying the type of plant disease or pest, means for generating specific countermeasures for the plant disease or pest based on the identification results, means for providing necessary product recommendations and purchase links in addition to the countermeasures, means for transmitting the results to the user terminal and displaying them, means for collecting emotional data from the user's facial expressions and voice, means for analyzing the emotional data to identify the user's emotional state, and means for adjusting the display content of the countermeasures and recommended products based on the emotional state. This enables the user to quickly and accurately identify plant diseases and pests and take appropriate countermeasures, while also receiving appropriate emotional support.

[0354] A "user" is someone who takes photos of their plants and uses the system to diagnose diseases and pests, receive suggested treatments, and receive emotional support.

[0355] "Photo data" refers to image information of plants taken by users, and is data that is sent to the server and analyzed.

[0356] The "server" is a computer system that receives uploaded photo data, analyzes it using an image recognition engine, and generates diagnostic results, countermeasures, and information based on emotion analysis, which it then provides to users.

[0357] An "image recognition engine" is software or algorithm that analyzes received photo data and identifies types of plant diseases and pests.

[0358] "Countermeasures" refer to specific methods of dealing with plant diseases and pests that are proposed based on the diagnostic results.

[0359] "Recommendation" refers to presenting products suitable for the user based on diagnostic results and sentiment analysis.

[0360] "Purchase Link" means a web link that enables a User to purchase a Recommended Product online.

[0361] "User Device" means a smartphone, tablet, or other electronic device used by a User.

[0362] "Facial expression" refers to the movement and position of the user's face, and is used as data for emotion analysis.

[0363] "Voice" refers to the words and voices spoken by the user and is used as data for emotion analysis.

[0364] "Emotional data" refers to data that indicates the emotional state identified by analyzing a user's facial expressions and voice.

[0365] "Emotional state" refers to the user's current emotions, as determined as a result of emotion analysis.

[0366] The present invention combines an emotion engine with a system that analyzes photos of plants taken by users, identifies plant diseases and pests, and recommends specific countermeasures and necessary products based on the results. Specific embodiments of the present invention are described in detail below.

[0367] 1. Upload and send photos

[0368] Users can take photos of plants using their smart devices and upload them via the app or web interface, which then sends the photos to the server.

[0369] 2. Photo data is received and analyzed by the server

[0370] The server stores the photo data received from the device in storage, then performs image preprocessing (e.g., resizing, noise removal, color correction, etc.), and inputs the preprocessed image data into the image recognition engine.

[0371] 3. Disease and pest identification

[0372] The image recognition engine detects abnormalities in the photo and extracts features. The AI ​​model then analyzes the features to identify the type of plant disease or pest, such as black spot or aphids.

[0373] 4. Proposal of countermeasures

[0374] Based on the identification results, the server generates specific countermeasures for plant diseases and pests, such as removing the infected area and applying a specific fungicide in the case of black spot.

[0375] 5. Recommend related products and generate purchase links

[0376] Based on the diagnosis and countermeasures, the server then searches its database for relevant products, such as suitable nutrients, fungicides, and insecticides, and recommends them to the user, including a link to an online shopping platform for purchase.

[0377] 6. Emotion recognition using emotion engine

[0378] The emotion engine analyzes the user's facial expressions, voice, and behavioral patterns to identify their emotional state. Emotional data is collected through sensors such as cameras and microphones.

[0379] 7. Emotion-based response optimization

[0380] The server uses the emotion data from the emotion engine to provide the optimal response based on the user's emotions. For example, if the user is feeling down, it will provide a more encouraging message.

[0381] 8. Tailoring product recommendations based on emotions

[0382] The server uses emotional data to adjust the content and order of recommended products. For example, if the user is in a hurry, products with immediate effects will be displayed first.

[0383] 9. Sending and displaying results

[0384] The server compiles the diagnosis results, countermeasures, emotion recognition results, recommended products, and purchase links and sends them to the user's device. The user's device receives this data and displays it in an easy-to-understand manner. Specifically, along with the diagnosis results, the data includes an explanation such as "Your plant is suffering from black spot disease. The following measures are necessary to treat this disease," an encouraging message based on emotion, an image of the recommended product, and a purchase link.

[0385] Specific examples

[0386] Suppose a user finds black spots on a rose leaf and uploads a photo of the leaf. The device sends the photo to a server, which uses an image recognition engine and an AI model to identify it as black spot disease. The diagnosis results are displayed as follows: "The black spots found on the rose leaf are black spot disease. It is recommended that you remove the infected area and use a specific fungicide." In addition, the emotion engine recognizes from the user's facial expression that he or she looks worried, and prioritizes displaying encouraging messages such as "Don't worry, early intervention is likely to lead to recovery" and links to purchase fast-acting fungicides.

[0387] Example prompt for a generative AI model:

[0388] "I noticed black spots on the leaves of my roses. Explain to the concerned user how to treat black spot and what fungicide to buy. Include a message of encouragement."

[0389] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0390] Step 1:

[0391] The user takes a photo of a plant using a smart device. The input is the plant photo data, and the output is the photo stored on the device. This photo data is the basis for subsequent processing.

[0392] Step 2:

[0393] The user uploads plant photo data to the server through the application or web interface. The input is the photo data taken by the user, and the output is the photo data sent to the server. Specifically, the user presses the "upload" button in the application to send the photo data.

[0394] Step 3:

[0395] The server stores the received photo data in storage and performs image preprocessing. The input is the photo data sent to the server, and the output is the preprocessed image data. Specific operations include resizing, noise removal, and color correction.

[0396] Step 4:

[0397] The server passes the preprocessed image data to an image recognition engine to identify the type of plant disease or pest. The input is the preprocessed image data, and the output is data with extracted features. The image recognition engine detects abnormal areas and extracts features.

[0398] Step 5:

[0399] The AI ​​model analyzes the extracted features to identify the type of plant disease or pest. The input is the data from which the features have been extracted, and the output is information that identifies the type of disease or pest. Specifically, the AI ​​model identifies black spot disease, aphids, etc.

[0400] Step 6:

[0401] Based on the identification results, the server generates specific countermeasures for plant diseases and pests. The input is information that identifies the type of disease or pest, and the output is a list of specific countermeasures. For example, in the case of black spot disease, it is recommended to remove the infected area and use a specific fungicide.

[0402] Step 7:

[0403] Based on the diagnosis results and solutions, the server searches the database for relevant products and recommends them to the user. The input is a list of specific solutions, and the output is a list of recommended products and a purchase link. Specifically, a link to an online shopping platform is provided.

[0404] Step 8:

[0405] The server collects the user's facial expressions and voice using a camera and microphone to obtain emotion data. The input is the user's facial expressions and voice, and the output is data that identifies the user's emotional state. The collected emotion data is passed to the emotion engine.

[0406] Step 9:

[0407] The emotion engine analyzes the emotion data and identifies the user's emotional state. The input is the user's facial expression and voice data, and the output is the user's emotional state. Specifically, the emotion engine identifies the emotional state as "worry" or "anxiety," etc.

[0408] Step 10:

[0409] The server adjusts the displayed content of solutions and recommended products based on the user's emotional state. The input is the user's emotional state and the information generated in the previous step, and the output is optimized solutions and product lists. For example, if the user is worried, an encouraging message is provided.

[0410] Step 11:

[0411] The server compiles the diagnosis results, countermeasures, emotion recognition results, recommended products, and purchase links and sends them to the user's device. The input is the optimized countermeasures and product list, and the output is the information displayed on the user's device. Specifically, the diagnosis results, countermeasures, recommended products, and encouraging messages are displayed on the user's device.

[0412] Step 12:

[0413] The user's device displays the data received from the server in an easy-to-understand manner. The input is the data sent from the server, and the output is the diagnostic results and countermeasure information displayed to the user. Based on the displayed information, the user can take countermeasures against plant diseases and pests and purchase related products.

[0414] 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.

[0415] 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.

[0416] 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.

[0417] [Second embodiment]

[0418] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0419] 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.

[0420] 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).

[0421] 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.

[0422] 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.

[0423] 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).

[0424] 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.

[0425] 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.

[0426] 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.

[0427] 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.

[0428] 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.

[0429] 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."

[0430] The present invention is a system in which users upload photos of plants, and the server analyzes the photo data using an image recognition engine to identify plant diseases and pests and provide appropriate countermeasures. Specific embodiments for implementing the present invention are described below.

[0431] 1. Upload and send photos

[0432] Users take photos of their plants' leaves, stems, and flowers using a device such as a smartphone or PC, and upload the photos to the system using the system's application or web interface. At this time, the device receives the user's photo data.

[0433] 2. Receiving and analyzing photo data by the server

[0434] After the device receives the photo data, it sends it to the server. The server temporarily stores the received photo data in storage and then performs preprocessing on the image (e.g., image resizing, noise removal, color correction, etc.).

[0435] The server then passes the preprocessed image data to an image recognition engine, which detects abnormal areas in the photo and extracts features, which are important information for identifying plant diseases and pests.

[0436] 3. Identifying diseases and pests

[0437] The server then uses the AI ​​model to analyze the features provided by the image recognition engine and identify the type of plant disease or pest. Based on the identified disease or pest type (e.g., black spot or aphids), a detailed diagnosis is generated.

[0438] 4. Proposal of countermeasures

[0439] Based on the results of the diagnosis, the server will suggest specific measures to take against diseases and pests, such as removing the infected area or using a specific fungicide in the case of black spot.

[0440] 5. Recommend related products and generate purchase links

[0441] Furthermore, based on the diagnosis results and countermeasures, the server searches the database for relevant products such as nutrients, fungicides, and insecticides that are needed and recommends them to the user. The recommended products include a purchase link to an online shopping platform such as Yahoo Shopping.

[0442] 6. Sending and displaying results

[0443] The server generates a response that combines the diagnosis results, countermeasures, recommended products, and a purchase link, and sends it to the device. The device receives this data and displays it in a format that is easy for the user to understand. The display content includes a detailed explanation, such as "Your roses are suffering from black spot disease. The following measures are required to treat this disease," as well as images of the recommended products and purchase links.

[0444] Specific examples

[0445] For example, suppose a user finds black spots on the leaves of a rose and uploads a photo of the leaves. The device sends the photo to a server, which analyzes it using an image recognition engine and AI model and identifies it as black spot disease. The diagnosis result is displayed as follows: "The black spots found on the rose leaves are black spot disease. It is recommended that you remove the infected areas and use a specific fungicide." In addition, the app recommends a fungicide suitable for the solution and provides a purchase link, allowing the user to immediately purchase the necessary product.

[0446] In this way, users can effectively manage plant health and quickly source the products they need, even without specialized knowledge.

[0447] The processing flow will be explained below.

[0448] Step 1:

[0449] The user takes a photo of the plant with their device.

[0450] Step 2:

[0451] A user uploads a photograph of a plant to the system through the system's application or web interface.

[0452] Step 3:

[0453] The device sends the photo data uploaded by the user to the server.

[0454] The transmitted data includes the photo file and metadata such as the user ID.

[0455] Step 4:

[0456] The server stores the received photo data in storage.

[0457] Step 5:

[0458] The server performs image pre-processing (e.g., image resizing, noise removal, color correction, etc.).

[0459] Step 6:

[0460] The server passes the preprocessed images to an image recognition engine.

[0461] Step 7:

[0462] The image recognition engine detects abnormal areas in the photo and extracts features.

[0463] Step 8:

[0464] The AI ​​model analyzes the features and identifies the type of disease or pest.

[0465] During this process, specific identification results such as "black spot disease" or "aphids" are obtained.

[0466] Step 9:

[0467] The server generates a diagnosis result based on the output of the AI ​​model.

[0468] The diagnosis results include information such as the name of the identified disease or pest, a description of the symptoms, and the degree of progression.

[0469] Step 10:

[0470] The server generates appropriate countermeasures based on the identified diseases and pests.

[0471] For example, specific measures include "in the case of black spot disease, remove the infected area and use a specific fungicide."

[0472] Step 11:

[0473] Based on the diagnosis results and countermeasures, the server searches a database for relevant products such as necessary nutrients, fungicides, and insecticides and recommends them.

[0474] Step 12:

[0475] The server generates a purchase link to Yahoo! Shopping or the like along with information about the recommended product.

[0476] Step 13:

[0477] The server generates a response including the diagnosis result, countermeasures, recommended products, and a purchase link, and transmits it to the terminal.

[0478] Step 14:

[0479] The device analyzes the data received from the server and displays it in an easy-to-understand manner for the user.

[0480] The display clearly lists the diagnostic results, countermeasures, recommended products, and links to purchase them.

[0481] Step 15:

[0482] The user checks the displayed diagnostic results and countermeasures, and if necessary, clicks on the purchase link for the recommended product to proceed with the purchase process on Yahoo! Shopping.

[0483] These are the detailed steps of the program's processing, which allows users to quickly identify plant problems and take appropriate measures.

[0484] Example 1

[0485] 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."

[0486] Traditionally, diagnosing plant diseases and pests required specialized knowledge, making it difficult for average users. Furthermore, actually receiving a diagnosis required a visit from an expert or bringing the plant to a facility, which was costly and time-consuming. Furthermore, the process of finding specific countermeasures and necessary products after a diagnosis was time-consuming. There is a need for a system that addresses these issues and allows average users to easily manage the health of their plants.

[0487] 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.

[0488] In this invention, the server includes means for uploading images of plants taken by users, means for transmitting the uploaded image data to the server, means for passing the image data received by the server to an image recognition system and identifying the type of plant disease or pest, means for generating specific countermeasures for the plant disease or pest based on the identification results, means for providing recommendations and purchase links for necessary products in addition to the countermeasures, and means for transmitting and displaying the results to a user terminal. This enables users, even without specialized knowledge, to quickly and easily diagnose plant diseases and pests and obtain appropriate countermeasures and necessary products.

[0489] A "user" is an entity that uses the system to upload images of plants and receive diagnostic results and countermeasures.

[0490] "Terminal" refers to an electronic device used by a user, such as a smartphone or computer, for taking and uploading images and displaying the results.

[0491] "Image data" refers to data that digitally represents an image of a plant photographed by a user.

[0492] A "server" is a central computing device that stores received image data and performs analysis using an image recognition system and artificial intelligence models.

[0493] An "image recognition system" is software that detects abnormal parts from received image data and extracts characteristic information.

[0494] "Feature information" is information about specific parts or patterns in an image that are important for identifying diseases or pests, extracted by the image recognition system.

[0495] An "artificial intelligence model" is a trained algorithm that analyzes feature information provided by an image recognition system and identifies the type of disease or pest.

[0496] "Identification results" are information about the type of plant disease or pest obtained as a result of analysis by the artificial intelligence model.

[0497] "Countermeasures" are specific treatment methods or measures against plant diseases or pests that are generated based on the identification results.

[0498] "Recommended products" are products that are required to implement countermeasures and are recommended to users.

[0499] "Purchase Link" means the URL for purchasing the Recommended Product on an online shopping platform.

[0500] "Results" refers collectively to information including identification results, countermeasures, recommended products, and purchase links that are provided to users.

[0501] The present invention is a system in which users upload images of plants they have taken, and the server analyzes the image data using an image recognition system and artificial intelligence model to identify plant diseases and types of pests and provide appropriate countermeasures.

[0502] First, the user takes an image of the plant using a device such as a smartphone or PC. It is preferable to take an image that clearly captures any abnormalities, such as leaves, stems, or flowers. Next, the user selects and uploads the image using the system's application or web interface. The device receives the image data and sends it to the server.

[0503] The server receives image data sent from the user's device and temporarily stores it in storage. The server then performs preprocessing on the stored image data. This preprocessing includes image resizing, noise removal, color correction, etc. This preprocessing improves the accuracy of analysis by the image recognition system.

[0504] The server then passes the preprocessed image data to an image recognition system, which uses deep learning and computer vision techniques to detect abnormalities in the image and extract feature information, which is key to identifying plant diseases and pests.

[0505] The extracted feature information is returned to the server, which then inputs it into an AI model. The AI ​​model is pre-trained and capable of identifying the type of plant disease or pest. The AI ​​model analyzes the feature information and identifies the specific disease or pest. For example, black spot or aphids may be detected.

[0506] Based on the identification results, the server generates specific countermeasures for the disease or pest. For example, in the case of black spot disease, this includes how to remove the infected area and how to use a specific fungicide. Based on the countermeasures, the server also searches a database for related products, such as nutrients, fungicides, and insecticides, and recommends them to the user. The recommended products include a purchase link to an online shopping platform.

[0507] Finally, the server generates response data that combines the diagnosis results, countermeasures, recommended products, and a purchase link, and sends it to the device. The device then displays the received response data to the user. The display includes the diagnosis results, specific countermeasures, images of recommended products, and purchase links, allowing the user to quickly and effectively manage the health of their plants based on this information.

[0508] For example, suppose a user finds black spots on a rose leaf and uploads an image of the leaf. The user's device sends the image to a server, which analyzes it using an image recognition system and an artificial intelligence model and identifies it as black spot disease. The diagnosis result is displayed as follows: "The black spots found on the rose leaf are black spot disease. It is recommended that you remove the infected area and use a specific fungicide." The app also recommends the best fungicide for the treatment and provides a link to purchase it. In this way, users can effectively manage the health of their plants and quickly obtain the necessary products without any specialized knowledge.

[0509] An example of a prompt sentence to input to the generative AI model is as follows:

[0510] "I uploaded a picture of some black spots on the leaves of my plant. Can you please tell me what these black spots are and how to deal with them?"

[0511] In this way, the present invention supports the user's plant health management by identifying diseases and pests based on images of plants taken by the user and suggesting appropriate countermeasures and related products.

[0512] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0513] Step 1:

[0514] The user takes a picture of the plant using a device such as a smartphone or PC. The captured image is saved on the device as a digital image file. The input is the image taken by the user with the device's camera, and this image is saved on the device as the output.

[0515] Step 2:

[0516] A user opens the system's application or web interface, selects a captured image, and presses a button to upload it. The input is the image file selected by the user, and the selected image is included in the upload request as the output.

[0517] Step 3:

[0518] The device receives the image data uploaded by the user. It creates a request to send the image data to the server along with the user authentication information, and sends it to the server as an HTTP POST request. The input is the image data selected by the user and the authentication information, and the output is an HTTP request containing these.

[0519] Step 4:

[0520] The server receives a request for image data sent from the terminal and extracts the image data. The server saves this image data in storage. The input is the HTTP request sent from the terminal, and the extracted image data is saved in storage as intermediate output.

[0521] Step 5:

[0522] The server performs image preprocessing such as resizing, noise removal, and color correction on the stored image data. The input is the stored raw image file, and the processed image after these preprocessing steps is the output. Preprocessing at this step improves the accuracy of the subsequent image recognition.

[0523] Step 6:

[0524] The server passes the preprocessed image data to an image recognition system, which detects abnormalities and extracts feature information. The preprocessed image data is input, and the location and feature information of abnormalities are obtained as output through the image recognition system.

[0525] Step 7:

[0526] The server inputs the feature information provided by the image recognition system into an artificial intelligence model. The AI ​​model analyzes the feature information and identifies the type of plant disease or pest. The input is feature information, and the output is specific information about the disease or pest as a result of the identification.

[0527] Step 8:

[0528] The server generates specific countermeasures based on the identification results, including detailed treatment methods and countermeasures for the identified diseases and pests. The input is the identification results, and the generated countermeasures are the output.

[0529] Step 9:

[0530] The server searches a database of related products based on the countermeasure and finds recommended products such as needed nutrients, fungicides, insecticides, etc. The input is the countermeasure information, and the output is related product information from the database.

[0531] Step 10:

[0532] The server compiles information about the recommended products and generates a purchase link to an online shopping platform. The input is the information about the recommended products, and the generated purchase link is the output.

[0533] Step 11:

[0534] The server generates response data that combines the diagnosis results, countermeasures, recommended products, and purchase links, and sends it to the user's device. The input is the diagnosis results, countermeasures, recommended products, and purchase links that have been generated so far, and the response data that includes these is the output.

[0535] Step 12:

[0536] The device then displays the received response data to the user. The displayed content includes the diagnosis results, specific countermeasures, images of recommended products, and links to purchase them, all in a format that is easy for the user to understand. The input is the response data from the server, and the display content that the user can see is the output.

[0537] Through these processing steps, users can quickly and effectively diagnose plant diseases and pests without specialized knowledge, and obtain appropriate countermeasures and necessary products.

[0538] (Application example 1)

[0539] 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."

[0540] In modern agriculture and horticulture, there is a need for early detection and rapid response to plant diseases and pests. Especially in large-scale cultivation environments, there are limitations to manual monitoring and response. There is also a need for systems that can accurately identify the type of disease or pest and quickly provide appropriate countermeasures. Furthermore, it is also important to be able to easily obtain the products needed for these countermeasures.

[0541] 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.

[0542] In this invention, the server includes a means for uploading photos of plants taken by a user or a robot to the server and implementing appropriate countermeasures based on the analysis results, a means for recommending products related to countermeasures for identified diseases and pests, and a means for notifying an administrator of the diagnosis results and recommended products. This enables early detection of diseases and pests and prompt response, automates monitoring and management of the cultivation environment, and realizes efficient agricultural and horticultural activities.

[0543] 1. "User" refers to the individual or artifact that takes photos of plants and uploads them to the system.

[0544] 2. "Plant photos" refers to image data of plant leaves, stems, flowers, etc.

[0545] 3. "Means for uploading" refers to technology that has the functionality to transfer plant photos to a system or server.

[0546] 4. "Server" refers to a computer system that receives plant photo data and performs image recognition and analysis.

[0547] 5. "Image recognition engine" refers to algorithms and software that analyze photographic data, detect abnormalities, and extract features.

[0548] 6. "Methods for identifying types of plant diseases and pests" refers to technologies that use image recognition engines and AI models to analyze the health of plants and identify diseases and pests.

[0549] 7. "Means for generating specific countermeasures" refers to a function that suggests specific countermeasures for plant diseases and pests based on the identification results.

[0550] 8. "Means for recommending necessary products and providing links to purchase them" refers to a system that has the function of searching for products related to the solution and providing links to purchase them.

[0551] 9. "Means for transmitting and displaying results on user devices" refers to the technology for transferring and displaying analysis results and countermeasures on the device used by the user.

[0552] 10. "Means for a robot to take photos, upload the photos to a server, and take appropriate countermeasures based on the analysis results" refers to technology in which a robot placed in a factory or other environment takes photos of plants, sends them to a server, and takes appropriate countermeasures based on the diagnostic results.

[0553] 11. "Means for recommending products related to countermeasures for identified diseases or pests" refers to a system that has the functionality to search for and recommend products necessary for appropriate treatment or countermeasures based on the diagnosis of a disease or pest.

[0554] 12. "Means for notifying the Administrator of the diagnosis results and recommended products" refers to technology for notifying the Administrator of details of diagnosed diseases or pests and information on recommended products.

[0555] The present invention relates to a system for identifying plant diseases and pests using photos of plants taken by a user and providing appropriate countermeasures. Specific embodiments for carrying out the present invention will be described below.

[0556] First, a user or a robot in the factory takes a photo of the plant. The user takes a photo of the plant using a smartphone or computer and uploads the photo to the system. Meanwhile, the robot takes a photo of the plant in the factory using its built-in camera.

[0557] Next, the captured photos are uploaded and sent to a server. The server passes the received photo data to an image recognition engine. This image recognition engine analyzes the photos, detects abnormalities such as plant diseases and pests, and extracts feature values. The image recognition engines used include libraries such as TensorFlow and Keras.

[0558] The extracted features are then analyzed by an AI model, which uses the features obtained from the image recognition engine to identify the type of disease or pest. For this identification, a pre-trained generative AI model is used. The model used includes a deep learning model (e.g., a convolutional neural network).

[0559] Based on the identification results, the server generates appropriate countermeasures. For example, for a specific disease, it suggests methods for removing the infected area or the use of specific medications. It also searches a database of products related to the recommended countermeasures and lists the corresponding products. This includes necessary nutrients, fungicides, and insecticides, and provides links to purchase these products.

[0560] The server then generates a response that compiles the diagnosis results, proposed countermeasures, and recommended products, and notifies the user or factory manager via a smartphone or computer application, or by email.

[0561] As a concrete example, suppose strange spots appear on the leaves of tomatoes being grown in a factory. A robot takes a photo of the spot and sends it to the server. The server analyzes the photo using an image recognition engine and an AI model and identifies it as spot disease. The diagnosis results are displayed as spot disease, and countermeasures include removing the infected area and using a specific fungicide. Furthermore, a link to purchase the recommended fungicide is provided, allowing managers to take prompt action.

[0562] Example prompt sentence:

[0563] Below are some examples of prompts to input to the generative AI model.

[0564] "Please identify the plant disease or pest seen in this image. Please suggest the necessary treatment and related products suitable for this disease."

[0565] Input image: path_to_plant_image.jpg

[0566] In this way, the present invention provides a system that effectively supports plant health management.

[0567] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0568] Step 1:

[0569] The user or the robot takes a photo of the plant. The user uses a smartphone, and the robot uses its built-in camera. The input is the plant photo, which becomes the input data for the system. The output is the captured photo data.

[0570] Step 2:

[0571] The device uploads the photograph of the plant to the server. The input is the photographed photo data, which becomes the data to be sent to the server. The output is the completion of sending the photo data to the server.

[0572] Step 3:

[0573] The server passes the received photo data to the image recognition engine, which performs preprocessing such as image resizing, noise removal, and color correction. The input is photo data, which becomes the data to be preprocessed. The output is preprocessed image data.

[0574] Step 4:

[0575] The server passes the preprocessed image data to an image recognition engine, which extracts features to identify plant diseases and pest types. The preprocessed image data is input, which becomes the input data for feature extraction. The extracted features are output.

[0576] Step 5:

[0577] The server inputs the extracted features into an AI model to identify the type of disease or pest. The extracted features serve as input data for the AI ​​model, and the identification result is generated as output.

[0578] Step 6:

[0579] The server generates specific countermeasures for plant diseases and pests based on the identification results. The input is the identification results, which serve as input data for countermeasure generation. The output is the specific countermeasures.

[0580] Step 7:

[0581] The server generates the necessary product recommendations and purchase links based on the identification results and countermeasures. The identification results and countermeasures are input, which become the input data for generating recommended products. The recommended products and purchase links are generated as output.

[0582] Step 8:

[0583] The server sends the diagnosis results, countermeasures, recommended products, and purchase links to the user's or administrator's terminal for display. The inputs are the diagnosis results, countermeasures, recommended products, and purchase links, which serve as notification data for the user or administrator. The output is the display result that is displayed on the terminal.

[0584] In this way, the system of the present invention can effectively support plant health management.

[0585] 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.

[0586] The present invention combines an emotion engine with a system that analyzes plant photos uploaded by users, identifies plant diseases and pests, and recommends specific countermeasures and necessary products based on the results. Specific embodiments for implementing the present invention are described below.

[0587] 1. Upload and send photos

[0588] Users take photos of plants using their own devices and upload them to the system's application or web interface, at which point the device receives the user's photo data.

[0589] 2. Receiving and analyzing photo data by the server

[0590] After the device receives the photo data, it sends it to the server. The server stores the received photo data in storage. It then performs preprocessing on the image (e.g., image resizing, noise removal, color correction, etc.) and passes the preprocessed image data to the image recognition engine.

[0591] 3. Identifying diseases and pests

[0592] The server's image recognition engine detects abnormalities in the photo and extracts features. At the same time, an AI model analyzes the features and identifies the type of plant disease or pest. Based on the identified disease or type of pest (e.g., black spot or aphids), a detailed diagnosis is generated.

[0593] 4. Proposal of countermeasures

[0594] Based on the results of the diagnosis, the server will suggest specific measures to deal with the disease or pest, such as how to remove the infected area or use a specific fungicide in the case of black spot.

[0595] 5. Recommend related products and generate purchase links

[0596] Based on the diagnosis and countermeasures, the server then searches a database for relevant products, such as suitable nutrients, fungicides, and insecticides, and recommends them to the user, including a link to an online shopping platform for purchase.

[0597] 6. Emotion Recognition by Emotion Engine

[0598] A new feature being added is the emotion engine, which recognizes the user's emotions. The emotion engine identifies the user's emotional state by analyzing facial expressions, voice, and behavioral patterns while the user is using the system. This emotion data is collected through sensors such as cameras and microphones.

[0599] 7. Emotion-based response optimization

[0600] The server uses the emotion data from the emotion engine to provide the optimal response based on the user's emotions. For example, if the user is feeling down, it will provide a more encouraging message.

[0601] 8. Tailoring product recommendations based on emotions

[0602] Using data from the emotion engine, the server adjusts the display order and content of recommended products. For example, if the user is in a hurry, it can prioritize products with immediate effects.

[0603] 9. Sending and displaying results

[0604] The server sends the diagnosis results, countermeasures, emotion recognition results, recommended products, and a purchase link all together to the device. The device receives this data and displays it in an easy-to-understand manner for the user. For example, along with the diagnosis results, the device may display an explanation such as "Your plant is suffering from black spot disease. To treat this disease, the following measures are required," as well as an encouraging message based on the user's emotion, an image of the recommended product, and a purchase link.

[0605] Specific examples

[0606] For example, suppose a user finds black spots on a rose leaf and uploads a photo of the leaf. The device sends the photo to a server, which uses an image recognition engine and an AI model to identify it as black spot disease. The diagnosis results are displayed as follows: "The black spots found on the rose leaf are black spot disease. It is recommended that you remove the infected area and use a specific fungicide." In addition, the emotion engine recognizes from the user's facial expression that they appear worried, and prioritizes displaying encouraging messages such as "Don't worry, recovery is expected if you take early action" and links to purchase fast-acting fungicides.

[0607] In this way, users can effectively manage the health of their plants without any specialized knowledge, quickly obtain the necessary products, and receive appropriate emotional support.

[0608] The processing flow will be explained below.

[0609] Step 1:

[0610] The user takes a photo of the plant with their device.

[0611] Step 2:

[0612] A user uploads a photograph of a plant to the system through the system's application or web interface.

[0613] Step 3:

[0614] The device sends the photo data uploaded by the user to the server.

[0615] The transmitted data includes the photo file and metadata such as the user ID.

[0616] Step 4:

[0617] The server stores the received photo data in storage.

[0618] Step 5:

[0619] The server performs image pre-processing (e.g., image resizing, noise removal, color correction, etc.).

[0620] Step 6:

[0621] The server passes the preprocessed images to an image recognition engine.

[0622] Step 7:

[0623] The image recognition engine detects abnormal areas in the photo and extracts features.

[0624] Step 8:

[0625] The AI ​​model analyzes the features and identifies the type of disease or pest.

[0626] During this process, specific identification results such as "black spot disease" or "aphids" are obtained.

[0627] Step 9:

[0628] The server generates a diagnosis result based on the output of the AI ​​model.

[0629] The diagnosis results include information such as the name of the identified disease or pest, a description of the symptoms, and the degree of progression.

[0630] Step 10:

[0631] The server generates appropriate countermeasures based on the identified diseases and pests.

[0632] For example, specific measures include "in the case of black spot disease, remove the infected area and use a specific fungicide."

[0633] Step 11:

[0634] Based on the diagnosis results and countermeasures, the server searches a database for relevant products such as necessary nutrients, fungicides, and insecticides and recommends them.

[0635] Step 12:

[0636] The server generates a purchase link to an online shopping platform along with information about the recommended products.

[0637] Step 13:

[0638] The server generates a response that combines the diagnosis results, countermeasures, recommended products, and a purchase link, and transmits it to the terminal.

[0639] Step 14:

[0640] The device analyzes the data received from the server and displays it in an easy-to-understand manner for the user.

[0641] The display clearly lists the diagnostic results, countermeasures, recommended products, and links to purchase them.

[0642] Step 15:

[0643] The user checks the displayed diagnostic results and countermeasures.

[0644] Step 16:

[0645] The user clicks on the purchase link for the recommended product and proceeds with the online shopping purchase process.

[0646] Step 17:

[0647] The emotion engine analyzes the user's facial expressions, voice, and behavioral patterns to recognize their emotions.

[0648] Emotional data is collected through sensors such as cameras and microphones.

[0649] Step 18:

[0650] The server provides the optimal response according to the user's emotions based on the emotion data from the emotion engine.

[0651] For example, if the user is feeling down, include an encouraging message.

[0652] Step 19:

[0653] The server uses data from the emotion engine to adjust the content and order of recommended products.

[0654] For example, if a user is in a hurry, products with immediate effects will be displayed first.

[0655] Step 20:

[0656] The device receives the adjusted results based on the emotion data from the server and displays them again to the user.

[0657] For example, along with an encouraging message, product information that is displayed with priority and has a high immediate effect is displayed.

[0658] These are the specific processing steps of the system that combines the emotion engine. This flow not only enables users to quickly identify plant problems and take appropriate measures, but also allows them to receive appropriate emotional support.

[0659] Example 2

[0660] 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."

[0661] Conventional plant disease and pest diagnosis systems are limited to identifying diseases and pests, and are insufficient in proposing specific countermeasures or related products. Furthermore, they lack support that takes into account the user's emotions, and there is a need for improved usability. This often leads to anxiety and stress in users regarding plant health management.

[0662] 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.

[0663] In this invention, the server includes means for uploading photos of plants taken by users, means for transmitting the uploaded photo data to the server, means for storing and preprocessing the photo data received by the server, means for passing the preprocessed photo data to an image recognition engine and identifying the type of plant disease or pest, means for generating specific countermeasures for the plant disease or pest based on the identification results, means for recommending necessary products and providing purchase links in addition to the countermeasures, means for recognizing the user's emotions and adjusting the display content of the countermeasures and recommended products based on the emotions, and means for transmitting the results to the user terminal and displaying them. This enables users to effectively manage the health of their plants, quickly procure necessary products, and receive appropriate emotional support.

[0664] "User" refers to an individual who uses the system to take and upload photos of plants.

[0665] "Device" refers to the electronic device a user uses to take photos and upload data, including smartphones and tablets.

[0666] "Server" refers to the computer system that receives, stores, processes, and analyzes photo data sent by users.

[0667] "Photo data" refers to image files taken by a user on a device and sent to a server.

[0668] "Preprocessing" refers to image improvement processes such as resizing, noise removal, and color correction that are performed on the photo data received by the server.

[0669] "Image recognition engine" refers to software or algorithms used to detect abnormalities and extract features from preprocessed photographic data.

[0670] "Features" refer to measurable information extracted from photos by an image recognition engine to identify diseases and pests.

[0671] An "AI model" refers to an algorithm that uses machine learning technology to analyze features and identify types of plant diseases and pests.

[0672] "Identification results" refers to diagnostic information regarding the type of disease or pest identified by the AI ​​model.

[0673] "Countermeasures" refer to specific treatment methods for plant diseases and pests based on the identification results.

[0674] "Product Recommendations" refers to suggestions of relevant products that can be used to treat or protect plants, based on the response measures.

[0675] "Buy Link" means a URL or button that provides direct access to an online shopping site for the recommended product.

[0676] "Emotion engine" refers to software or algorithms for recognizing a user's emotional state.

[0677] "Emotional Data" means information regarding a User's current emotional state as determined by the Emotion Engine.

[0678] The present invention combines an emotion engine with a system that analyzes plant photos uploaded by users, identifies plant diseases and pests, and recommends specific countermeasures and necessary products based on the results. Specific embodiments for implementing the present invention are described below.

[0679] Taking and uploading photos

[0680] Users take photos of plants using their own devices. They then upload the photos through the system's application or web interface. The device then receives the user's photo data. Specifically, users take photos with their smartphone or camera and tap the "upload" button in the app.

[0681] Receiving and sending photo data

[0682] The device receives the photo data uploaded by the user and sends the data to the server. The device's network module transfers the data to the server using an HTTP request.

[0683] Photo data storage and preprocessing

[0684] The server stores the received photo data in storage. It then performs image preprocessing, which includes image resizing, noise removal, color correction, etc. Specifically, the server performs preprocessing using an image processing library (e.g., OpenCV).

[0685] Analysis by image recognition engine

[0686] The server passes the preprocessed image data to an image recognition engine, which detects abnormalities and extracts features. Specifically, a machine learning model (e.g., TensorFlow or PyTorch model) is used.

[0687] Identifying diseases and pests with AI models

[0688] The server inputs the feature values ​​sent from the image recognition engine into the AI ​​model to identify the type of plant disease or pest. Specifically, the AI ​​model analyzes the data using a neural network and outputs the results.

[0689] Generating diagnostic results

[0690] The server generates detailed diagnostic results based on the identified disease or pest type, using templates to create text information to display to the user as the diagnostic results.

[0691] Proposal of countermeasures

[0692] Based on the diagnosis results, the server proposes specific countermeasures for diseases and pests. For example, in the case of black spot disease, it suggests "how to remove the infected area" and "how to use a specific fungicide." Specific operations involve retrieving appropriate information from a database of countermeasure information that has been set up in advance.

[0693] Related product recommendations

[0694] The server recommends relevant nutrients, fungicides, and insecticides based on the diagnosis and countermeasures, searching for product information from a database of products suitable for the countermeasures, and generating a purchase link to an online shopping platform.

[0695] Emotion recognition by emotion engine

[0696] The device uses an emotion engine to recognize the user's emotions. Specifically, it analyzes sensor information collected through the camera and microphone to identify the user's emotional state from their facial expressions and tone of voice.

[0697] Sending emotional data

[0698] The device sends the recognized emotion data to the server. The device transfers the emotional state data to the server using an HTTP request.

[0699] Emotion-based response optimization

[0700] The server provides the optimal response based on the user's emotions based on the emotion data from the emotion engine. For example, if the user is feeling down, it will add an encouraging message. Specifically, it selects and edits a template message based on the emotion data.

[0701] Emotion-based product recommendation adjustment

[0702] The server uses emotional data to adjust the display order and order of recommended products. For example, if the user is in a hurry, it will prioritize products with immediate effects. Specifically, it rearranges the display order of products based on emotional data.

[0703] Sending and displaying results

[0704] The server compiles the diagnosis results, countermeasures, emotion recognition results, recommended products, and purchase links and sends them to the device. The device then receives this data and displays it in an easy-to-understand manner for the user. Specifically, it uses UI components to display the results in an application or web interface.

[0705] Specific examples

[0706] For example, suppose a user notices black spots on a rose leaf and uploads a photo of the leaf. The device sends the photo to the server, which uses an image recognition engine and AI model to identify it as black spot disease. The diagnosis results are displayed as follows: "The black spots on the rose leaf are black spot disease. It is recommended that you remove the infected area and use a specific fungicide." Additionally, the emotion engine recognizes the user's concern from their facial expression and prioritizes displaying encouraging messages such as "Don't worry, recovery is expected with early intervention" and links to purchase fast-acting fungicides. This allows users to effectively manage plant health without specialized knowledge, quickly procure the necessary products, and receive appropriate emotional support.

[0707] Prompt Sentence Examples

[0708] "Analyze a photo of black spots on rose leaves, detail the type of disease and how to treat it. Also, acknowledge the user's concern and include a message of encouragement."

[0709] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0710] Step 1:

[0711] The user takes a photo of a plant on their device and uploads the photo to the application or web interface. The input is the photo data of the plant taken by the user. Specifically, the user takes a photo with their smartphone or camera and taps the "upload" button in the application. The output is the photo data saved on the device.

[0712] Step 2:

[0713] The device receives photo data uploaded by the user. The input is the photo data uploaded by the user. Specifically, the uploaded photos are saved in a temporary folder in the device's application. The output is the saved photo data.

[0714] Step 3:

[0715] The device sends the received photo data to the server. The input is the photo data saved in the temporary folder. The device's network module transfers the data to the server using an HTTP request. The output is the photo data sent to the server.

[0716] Step 4:

[0717] The server saves the received photo data in storage. The input is the photo data sent from the device. An example of software used is a cloud storage service such as AWS S3. The output is the photo data saved in storage.

[0718] Step 5:

[0719] The server performs preprocessing on the stored photo data. The input is the photo data stored in storage. Preprocessing includes image resizing, noise removal, color correction, etc. Specifically, the server performs preprocessing using an image processing library (e.g., OpenCV). The output is the preprocessed image data.

[0720] Step 6:

[0721] The server passes the preprocessed image data to the image recognition engine. The input is the preprocessed image data. The image recognition engine detects abnormal parts in the image and extracts features. Specifically, a machine learning model (e.g., TensorFlow or PyTorch model) is used. The output is the extracted features.

[0722] Step 7:

[0723] The server inputs the features sent from the image recognition engine into the AI ​​model to identify the type of plant disease or pest. The input is the extracted features. The AI ​​model analyzes the data using a neural network and outputs the results. The output is the type of disease or pest identified.

[0724] Step 8:

[0725] The server generates detailed diagnostic results based on the identified disease or pest type. The input is the identification result from the AI ​​model. Specifically, a template is used to create text information to display to the user as the diagnostic result. The output is text data of the diagnostic result.

[0726] Step 9:

[0727] Based on the diagnosis results, the server proposes specific countermeasures against diseases and pests. The input is the text data of the diagnosis results. For example, in the case of black spot disease, it will suggest "how to remove the infected area" and "how to use a specific fungicide." The specific operation involves retrieving appropriate information from a database of pre-set countermeasure information. The output is text data of specific countermeasures.

[0728] Step 10:

[0729] The server recommends relevant nutrients, fungicides, and insecticides based on the diagnosis results and countermeasures. The input is text data of the specific countermeasures. Specifically, it searches for product information from a database of products suitable for the countermeasures and generates a purchase link to an online shopping platform. The output is data on the recommended products and the purchase link.

[0730] Step 11:

[0731] The device uses an emotion engine to recognize the user's emotions. The input is sensor information collected through the camera and microphone. The emotion engine identifies the user's emotional state from their facial expressions and tone of voice. Specifically, it uses an emotion analysis algorithm. The output is the user's emotional data.

[0732] Step 12:

[0733] The device sends the recognized emotion data to the server. The input is the identified user emotion data. The device transfers the emotional state data to the server using an HTTP request. The output is the emotion data sent to the server.

[0734] Step 13:

[0735] The server provides the optimal response based on the user's emotions, based on the emotion data from the emotion engine. The input is the emotion data sent to the server. For example, if the user is feeling down, an encouraging message is added. The specific operation is to select and edit a template message based on the emotion data. The output is text data of the optimal response based on the emotion.

[0736] Step 14:

[0737] The server uses the emotional data to adjust the display content and order of recommended products. The input is the emotional data sent to the server. For example, if the user is in a hurry, products with immediate effects are displayed first. Specifically, the display order of products is rearranged based on the emotional data. The output is recommended product data that has been adjusted based on the emotion.

[0738] Step 15:

[0739] The server compiles the diagnosis results, countermeasures, emotion recognition results, recommended products, and purchase links and sends them to the terminal. The input is the adjusted recommended product data and various text data. Specifically, it compiles this data in HTML or JSON format and sends it to the terminal as an HTTP response. The output is the display data sent to the terminal.

[0740] Step 16:

[0741] The device receives the data sent from the server and displays it in a user-friendly way. The input is the display data sent from the server. Specific operations include using UI components to display the results in an application or web interface. The output is the diagnosis results, countermeasures, emotion recognition results, recommended products, and purchase links displayed to the user.

[0742] (Application example 2)

[0743] 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."

[0744] In modern plant cultivation and gardening, when plants are attacked by disease or pests, it is necessary to take prompt and appropriate measures. However, it is difficult for ordinary users to accurately identify plant diseases and pests and take appropriate measures. Furthermore, if users feel discouraged or impatient, it may affect their ability to resolve the problem if appropriate support is not provided. A system that can solve these issues is needed.

[0745] 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 uploading photos of plants taken by the user, means for transmitting the uploaded photo data to the server, means for passing the photo data received by the server to an image recognition engine and identifying the type of plant disease or pest, means for generating specific countermeasures for the plant disease or pest based on the identification results, means for providing necessary product recommendations and purchase links in addition to the countermeasures, means for transmitting the results to the user terminal and displaying them, means for collecting emotional data from the user's facial expressions and voice, means for analyzing the emotional data to identify the user's emotional state, and means for adjusting the display content of the countermeasures and recommended products based on the emotional state. This enables the user to quickly and accurately identify plant diseases and pests and take appropriate countermeasures, while also receiving appropriate emotional support.

[0746] A "user" is someone who takes photos of their plants and uses the system to diagnose diseases and pests, receive suggested treatments, and receive emotional support.

[0747] "Photo data" refers to image information of plants taken by users, and is data that is sent to the server and analyzed.

[0748] The "server" is a computer system that receives uploaded photo data, analyzes it using an image recognition engine, and generates diagnostic results, countermeasures, and information based on emotion analysis, which it then provides to users.

[0749] An "image recognition engine" is software or algorithm that analyzes received photo data and identifies types of plant diseases and pests.

[0750] "Countermeasures" refer to specific methods of dealing with plant diseases and pests that are proposed based on the diagnostic results.

[0751] "Recommendation" refers to presenting products suitable for the user based on diagnostic results and sentiment analysis.

[0752] "Purchase Link" means a web link that enables a User to purchase a Recommended Product online.

[0753] "User Device" means a smartphone, tablet, or other electronic device used by a User.

[0754] "Facial expression" refers to the movement and position of the user's face, and is used as data for emotion analysis.

[0755] "Voice" refers to the words and voices spoken by the user and is used as data for emotion analysis.

[0756] "Emotional data" refers to data that indicates the emotional state identified by analyzing a user's facial expressions and voice.

[0757] "Emotional state" refers to the user's current emotions, as determined as a result of emotion analysis.

[0758] The present invention combines an emotion engine with a system that analyzes photos of plants taken by users, identifies plant diseases and pests, and recommends specific countermeasures and necessary products based on the results. Specific embodiments of the present invention are described in detail below.

[0759] 1. Upload and send photos

[0760] Users can take photos of plants using their smart devices and upload them via the app or web interface, which then sends the photos to the server.

[0761] 2. Photo data is received and analyzed by the server

[0762] The server stores the photo data received from the device in storage, then performs image preprocessing (e.g., resizing, noise removal, color correction, etc.), and inputs the preprocessed image data into the image recognition engine.

[0763] 3. Disease and pest identification

[0764] The image recognition engine detects abnormalities in the photo and extracts features. The AI ​​model then analyzes the features to identify the type of plant disease or pest, such as black spot or aphids.

[0765] 4. Proposal of countermeasures

[0766] Based on the identification results, the server generates specific countermeasures for plant diseases and pests, such as removing the infected area and applying a specific fungicide in the case of black spot.

[0767] 5. Recommend related products and generate purchase links

[0768] Based on the diagnosis and countermeasures, the server then searches its database for relevant products, such as suitable nutrients, fungicides, and insecticides, and recommends them to the user, including a link to an online shopping platform for purchase.

[0769] 6. Emotion recognition using emotion engine

[0770] The emotion engine analyzes the user's facial expressions, voice, and behavioral patterns to identify their emotional state. Emotional data is collected through sensors such as cameras and microphones.

[0771] 7. Emotion-based response optimization

[0772] The server uses the emotion data from the emotion engine to provide the optimal response based on the user's emotions. For example, if the user is feeling down, it will provide a more encouraging message.

[0773] 8. Tailoring product recommendations based on emotions

[0774] The server uses emotional data to adjust the content and order of recommended products. For example, if the user is in a hurry, products with immediate effects will be displayed first.

[0775] 9. Sending and displaying results

[0776] The server compiles the diagnosis results, countermeasures, emotion recognition results, recommended products, and purchase links and sends them to the user's device. The user's device receives this data and displays it in an easy-to-understand manner. Specifically, along with the diagnosis results, the data includes an explanation such as "Your plant is suffering from black spot disease. The following measures are necessary to treat this disease," an encouraging message based on emotion, an image of the recommended product, and a purchase link.

[0777] Specific examples

[0778] Suppose a user finds black spots on a rose leaf and uploads a photo of the leaf. The device sends the photo to a server, which uses an image recognition engine and an AI model to identify it as black spot disease. The diagnosis results are displayed as follows: "The black spots found on the rose leaf are black spot disease. It is recommended that you remove the infected area and use a specific fungicide." In addition, the emotion engine recognizes from the user's facial expression that he or she looks worried, and prioritizes displaying encouraging messages such as "Don't worry, early intervention is likely to lead to recovery" and links to purchase fast-acting fungicides.

[0779] Example prompt for a generative AI model:

[0780] "I noticed black spots on the leaves of my roses. Explain to the concerned user how to treat black spot and what fungicide to buy. Include a message of encouragement."

[0781] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0782] Step 1:

[0783] The user takes a photo of a plant using a smart device. The input is the plant photo data, and the output is the photo stored on the device. This photo data is the basis for subsequent processing.

[0784] Step 2:

[0785] The user uploads plant photo data to the server through the application or web interface. The input is the photo data taken by the user, and the output is the photo data sent to the server. Specifically, the user presses the "upload" button in the application to send the photo data.

[0786] Step 3:

[0787] The server stores the received photo data in storage and performs image preprocessing. The input is the photo data sent to the server, and the output is the preprocessed image data. Specific operations include resizing, noise removal, and color correction.

[0788] Step 4:

[0789] The server passes the preprocessed image data to an image recognition engine to identify the type of plant disease or pest. The input is the preprocessed image data, and the output is data with extracted features. The image recognition engine detects abnormal areas and extracts features.

[0790] Step 5:

[0791] The AI ​​model analyzes the extracted features to identify the type of plant disease or pest. The input is the data from which the features have been extracted, and the output is information that identifies the type of disease or pest. Specifically, the AI ​​model identifies black spot disease, aphids, etc.

[0792] Step 6:

[0793] Based on the identification results, the server generates specific countermeasures for plant diseases and pests. The input is information that identifies the type of disease or pest, and the output is a list of specific countermeasures. For example, in the case of black spot disease, it is recommended to remove the infected area and use a specific fungicide.

[0794] Step 7:

[0795] Based on the diagnosis results and solutions, the server searches the database for relevant products and recommends them to the user. The input is a list of specific solutions, and the output is a list of recommended products and a purchase link. Specifically, a link to an online shopping platform is provided.

[0796] Step 8:

[0797] The server collects the user's facial expressions and voice using a camera and microphone to obtain emotion data. The input is the user's facial expressions and voice, and the output is data that identifies the user's emotional state. The collected emotion data is passed to the emotion engine.

[0798] Step 9:

[0799] The emotion engine analyzes the emotion data and identifies the user's emotional state. The input is the user's facial expression and voice data, and the output is the user's emotional state. Specifically, the emotion engine identifies the emotional state as "worry" or "anxiety," etc.

[0800] Step 10:

[0801] The server adjusts the displayed content of solutions and recommended products based on the user's emotional state. The input is the user's emotional state and the information generated in the previous step, and the output is optimized solutions and product lists. For example, if the user is worried, an encouraging message is provided.

[0802] Step 11:

[0803] The server compiles the diagnosis results, countermeasures, emotion recognition results, recommended products, and purchase links and sends them to the user's device. The input is the optimized countermeasures and product list, and the output is the information displayed on the user's device. Specifically, the diagnosis results, countermeasures, recommended products, and encouraging messages are displayed on the user's device.

[0804] Step 12:

[0805] The user's device displays the data received from the server in an easy-to-understand manner. The input is the data sent from the server, and the output is the diagnostic results and countermeasure information displayed to the user. Based on the displayed information, the user can take countermeasures against plant diseases and pests and purchase related products.

[0806] 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.

[0807] 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.

[0808] 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.

[0809] [Third embodiment]

[0810] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0811] 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.

[0812] 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).

[0813] 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.

[0814] 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.

[0815] 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).

[0816] 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.

[0817] 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.

[0818] 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.

[0819] 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.

[0820] 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.

[0821] 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."

[0822] The present invention is a system in which users upload photos of plants, and the server analyzes the photo data using an image recognition engine to identify plant diseases and pests and provide appropriate countermeasures. Specific embodiments for implementing the present invention are described below.

[0823] 1. Upload and send photos

[0824] Users take photos of their plants' leaves, stems, and flowers using a device such as a smartphone or PC, and upload the photos to the system using the system's application or web interface. At this time, the device receives the user's photo data.

[0825] 2. Receiving and analyzing photo data by the server

[0826] After the device receives the photo data, it sends it to the server. The server temporarily stores the received photo data in storage and then performs preprocessing on the image (e.g., image resizing, noise removal, color correction, etc.).

[0827] The server then passes the preprocessed image data to an image recognition engine, which detects abnormal areas in the photo and extracts features, which are important information for identifying plant diseases and pests.

[0828] 3. Identifying diseases and pests

[0829] The server then uses the AI ​​model to analyze the features provided by the image recognition engine and identify the type of plant disease or pest. Based on the identified disease or pest type (e.g., black spot or aphids), a detailed diagnosis is generated.

[0830] 4. Proposal of countermeasures

[0831] Based on the results of the diagnosis, the server will suggest specific measures to take against diseases and pests, such as removing the infected area or using a specific fungicide in the case of black spot.

[0832] 5. Recommend related products and generate purchase links

[0833] Furthermore, based on the diagnosis results and countermeasures, the server searches the database for relevant products such as nutrients, fungicides, and insecticides that are needed and recommends them to the user. The recommended products include a purchase link to an online shopping platform such as Yahoo Shopping.

[0834] 6. Sending and displaying results

[0835] The server generates a response that combines the diagnosis results, countermeasures, recommended products, and a purchase link, and sends it to the device. The device receives this data and displays it in a format that is easy for the user to understand. The display content includes a detailed explanation, such as "Your roses are suffering from black spot disease. The following measures are required to treat this disease," as well as images of the recommended products and purchase links.

[0836] Specific examples

[0837] For example, suppose a user finds black spots on the leaves of a rose and uploads a photo of the leaves. The device sends the photo to a server, which analyzes it using an image recognition engine and AI model and identifies it as black spot disease. The diagnosis result is displayed as follows: "The black spots found on the rose leaves are black spot disease. It is recommended that you remove the infected areas and use a specific fungicide." In addition, the app recommends a fungicide suitable for the solution and provides a purchase link, allowing the user to immediately purchase the necessary product.

[0838] In this way, users can effectively manage plant health and quickly source the products they need, even without specialized knowledge.

[0839] The processing flow will be explained below.

[0840] Step 1:

[0841] The user takes a photo of the plant with their device.

[0842] Step 2:

[0843] A user uploads a photograph of a plant to the system through the system's application or web interface.

[0844] Step 3:

[0845] The device sends the photo data uploaded by the user to the server.

[0846] The transmitted data includes the photo file and metadata such as the user ID.

[0847] Step 4:

[0848] The server stores the received photo data in storage.

[0849] Step 5:

[0850] The server performs image pre-processing (e.g., image resizing, noise removal, color correction, etc.).

[0851] Step 6:

[0852] The server passes the preprocessed images to an image recognition engine.

[0853] Step 7:

[0854] The image recognition engine detects abnormal areas in the photo and extracts features.

[0855] Step 8:

[0856] The AI ​​model analyzes the features and identifies the type of disease or pest.

[0857] During this process, specific identification results such as "black spot disease" or "aphids" are obtained.

[0858] Step 9:

[0859] The server generates a diagnosis result based on the output of the AI ​​model.

[0860] The diagnosis results include information such as the name of the identified disease or pest, a description of the symptoms, and the degree of progression.

[0861] Step 10:

[0862] The server generates appropriate countermeasures based on the identified diseases and pests.

[0863] For example, specific measures include "in the case of black spot disease, remove the infected area and use a specific fungicide."

[0864] Step 11:

[0865] Based on the diagnosis results and countermeasures, the server searches a database for relevant products such as necessary nutrients, fungicides, and insecticides and recommends them.

[0866] Step 12:

[0867] The server generates a purchase link to Yahoo! Shopping or the like along with information about the recommended product.

[0868] Step 13:

[0869] The server generates a response including the diagnosis result, countermeasures, recommended products, and a purchase link, and transmits it to the terminal.

[0870] Step 14:

[0871] The device analyzes the data received from the server and displays it in an easy-to-understand manner for the user.

[0872] The display clearly lists the diagnostic results, countermeasures, recommended products, and links to purchase them.

[0873] Step 15:

[0874] The user checks the displayed diagnostic results and countermeasures, and if necessary, clicks on the purchase link for the recommended product to proceed with the purchase process on Yahoo! Shopping.

[0875] These are the detailed steps of the program's processing, which allows users to quickly identify plant problems and take appropriate measures.

[0876] Example 1

[0877] 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."

[0878] Traditionally, diagnosing plant diseases and pests required specialized knowledge, making it difficult for average users. Furthermore, actually receiving a diagnosis required a visit from an expert or bringing the plant to a facility, which was costly and time-consuming. Furthermore, the process of finding specific countermeasures and necessary products after a diagnosis was time-consuming. There is a need for a system that addresses these issues and allows average users to easily manage the health of their plants.

[0879] 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.

[0880] In this invention, the server includes means for uploading images of plants taken by users, means for transmitting the uploaded image data to the server, means for passing the image data received by the server to an image recognition system and identifying the type of plant disease or pest, means for generating specific countermeasures for the plant disease or pest based on the identification results, means for providing recommendations and purchase links for necessary products in addition to the countermeasures, and means for transmitting and displaying the results to a user terminal. This enables users, even without specialized knowledge, to quickly and easily diagnose plant diseases and pests and obtain appropriate countermeasures and necessary products.

[0881] A "user" is an entity that uses the system to upload images of plants and receive diagnostic results and countermeasures.

[0882] "Terminal" refers to an electronic device used by a user, such as a smartphone or computer, for taking and uploading images and displaying the results.

[0883] "Image data" refers to data that digitally represents an image of a plant photographed by a user.

[0884] A "server" is a central computing device that stores received image data and performs analysis using an image recognition system and artificial intelligence models.

[0885] An "image recognition system" is software that detects abnormal parts from received image data and extracts characteristic information.

[0886] "Feature information" is information about specific parts or patterns in an image that are important for identifying diseases or pests, extracted by the image recognition system.

[0887] An "artificial intelligence model" is a trained algorithm that analyzes feature information provided by an image recognition system and identifies the type of disease or pest.

[0888] "Identification results" are information about the type of plant disease or pest obtained as a result of analysis by the artificial intelligence model.

[0889] "Countermeasures" are specific treatment methods or measures against plant diseases or pests that are generated based on the identification results.

[0890] "Recommended products" are products that are required to implement countermeasures and are recommended to users.

[0891] "Purchase Link" means the URL for purchasing the Recommended Product on an online shopping platform.

[0892] "Results" refers collectively to information including identification results, countermeasures, recommended products, and purchase links that are provided to users.

[0893] The present invention is a system in which users upload images of plants they have taken, and the server analyzes the image data using an image recognition system and artificial intelligence model to identify plant diseases and types of pests and provide appropriate countermeasures.

[0894] First, the user takes an image of the plant using a device such as a smartphone or PC. It is preferable to take an image that clearly captures any abnormalities, such as leaves, stems, or flowers. Next, the user selects and uploads the image using the system's application or web interface. The device receives the image data and sends it to the server.

[0895] The server receives image data sent from the user's device and temporarily stores it in storage. The server then performs preprocessing on the stored image data. This preprocessing includes image resizing, noise removal, color correction, etc. This preprocessing improves the accuracy of analysis by the image recognition system.

[0896] The server then passes the preprocessed image data to an image recognition system, which uses deep learning and computer vision techniques to detect abnormalities in the image and extract feature information, which is key to identifying plant diseases and pests.

[0897] The extracted feature information is returned to the server, which then inputs it into an AI model. The AI ​​model is pre-trained and capable of identifying the type of plant disease or pest. The AI ​​model analyzes the feature information and identifies the specific disease or pest. For example, black spot or aphids may be detected.

[0898] Based on the identification results, the server generates specific countermeasures for the disease or pest. For example, in the case of black spot disease, this includes how to remove the infected area and how to use a specific fungicide. Based on the countermeasures, the server also searches a database for related products, such as nutrients, fungicides, and insecticides, and recommends them to the user. The recommended products include a purchase link to an online shopping platform.

[0899] Finally, the server generates response data that combines the diagnosis results, countermeasures, recommended products, and a purchase link, and sends it to the device. The device then displays the received response data to the user. The display includes the diagnosis results, specific countermeasures, images of recommended products, and purchase links, allowing the user to quickly and effectively manage the health of their plants based on this information.

[0900] For example, suppose a user finds black spots on a rose leaf and uploads an image of the leaf. The user's device sends the image to a server, which analyzes it using an image recognition system and an artificial intelligence model and identifies it as black spot disease. The diagnosis result is displayed as follows: "The black spots found on the rose leaf are black spot disease. It is recommended that you remove the infected area and use a specific fungicide." The app also recommends the best fungicide for the treatment and provides a link to purchase it. In this way, users can effectively manage the health of their plants and quickly obtain the necessary products without any specialized knowledge.

[0901] An example of a prompt sentence to input to the generative AI model is as follows:

[0902] "I uploaded a picture of some black spots on the leaves of my plant. Can you please tell me what these black spots are and how to deal with them?"

[0903] In this way, the present invention supports the user's plant health management by identifying diseases and pests based on images of plants taken by the user and suggesting appropriate countermeasures and related products.

[0904] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0905] Step 1:

[0906] The user takes a picture of the plant using a device such as a smartphone or PC. The captured image is saved on the device as a digital image file. The input is the image taken by the user with the device's camera, and this image is saved on the device as the output.

[0907] Step 2:

[0908] A user opens the system's application or web interface, selects a captured image, and presses a button to upload it. The input is the image file selected by the user, and the selected image is included in the upload request as the output.

[0909] Step 3:

[0910] The device receives the image data uploaded by the user. It creates a request to send the image data to the server along with the user authentication information, and sends it to the server as an HTTP POST request. The input is the image data selected by the user and the authentication information, and the output is an HTTP request containing these.

[0911] Step 4:

[0912] The server receives a request for image data sent from the terminal and extracts the image data. The server saves this image data in storage. The input is the HTTP request sent from the terminal, and the extracted image data is saved in storage as intermediate output.

[0913] Step 5:

[0914] The server performs image preprocessing such as resizing, noise removal, and color correction on the stored image data. The input is the stored raw image file, and the processed image after these preprocessing steps is the output. Preprocessing at this step improves the accuracy of the subsequent image recognition.

[0915] Step 6:

[0916] The server passes the preprocessed image data to an image recognition system, which detects abnormalities and extracts feature information. The preprocessed image data is input, and the location and feature information of abnormalities are obtained as output through the image recognition system.

[0917] Step 7:

[0918] The server inputs the feature information provided by the image recognition system into an artificial intelligence model. The AI ​​model analyzes the feature information and identifies the type of plant disease or pest. The input is feature information, and the output is specific information about the disease or pest as a result of the identification.

[0919] Step 8:

[0920] The server generates specific countermeasures based on the identification results, including detailed treatment methods and countermeasures for the identified diseases and pests. The input is the identification results, and the generated countermeasures are the output.

[0921] Step 9:

[0922] The server searches a database of related products based on the countermeasure and finds recommended products such as needed nutrients, fungicides, insecticides, etc. The input is the countermeasure information, and the output is related product information from the database.

[0923] Step 10:

[0924] The server compiles information about the recommended products and generates a purchase link to an online shopping platform. The input is the information about the recommended products, and the generated purchase link is the output.

[0925] Step 11:

[0926] The server generates response data that combines the diagnosis results, countermeasures, recommended products, and purchase links, and sends it to the user's device. The input is the diagnosis results, countermeasures, recommended products, and purchase links that have been generated so far, and the response data that includes these is the output.

[0927] Step 12:

[0928] The device then displays the received response data to the user. The displayed content includes the diagnosis results, specific countermeasures, images of recommended products, and links to purchase them, all in a format that is easy for the user to understand. The input is the response data from the server, and the display content that the user can see is the output.

[0929] Through these processing steps, users can quickly and effectively diagnose plant diseases and pests without specialized knowledge, and obtain appropriate countermeasures and necessary products.

[0930] (Application example 1)

[0931] 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."

[0932] In modern agriculture and horticulture, there is a need for early detection and rapid response to plant diseases and pests. Especially in large-scale cultivation environments, there are limitations to manual monitoring and response. There is also a need for systems that can accurately identify the type of disease or pest and quickly provide appropriate countermeasures. Furthermore, it is also important to be able to easily obtain the products needed for these countermeasures.

[0933] 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.

[0934] In this invention, the server includes a means for uploading photos of plants taken by a user or a robot to the server and implementing appropriate countermeasures based on the analysis results, a means for recommending products related to countermeasures for identified diseases and pests, and a means for notifying an administrator of the diagnosis results and recommended products. This enables early detection of diseases and pests and prompt response, automates monitoring and management of the cultivation environment, and realizes efficient agricultural and horticultural activities.

[0935] 1. "User" refers to the individual or artifact that takes photos of plants and uploads them to the system.

[0936] 2. "Plant photos" refers to image data of plant leaves, stems, flowers, etc.

[0937] 3. "Means for uploading" refers to technology that has the functionality to transfer plant photos to a system or server.

[0938] 4. "Server" refers to a computer system that receives plant photo data and performs image recognition and analysis.

[0939] 5. "Image recognition engine" refers to algorithms and software that analyze photographic data, detect abnormalities, and extract features.

[0940] 6. "Methods for identifying types of plant diseases and pests" refers to technologies that use image recognition engines and AI models to analyze the health of plants and identify diseases and pests.

[0941] 7. "Means for generating specific countermeasures" refers to a function that suggests specific countermeasures for plant diseases and pests based on the identification results.

[0942] 8. "Means for recommending necessary products and providing links to purchase them" refers to a system that has the function of searching for products related to the solution and providing links to purchase them.

[0943] 9. "Means for transmitting and displaying results on user devices" refers to the technology for transferring and displaying analysis results and countermeasures on the device used by the user.

[0944] 10. "Means for a robot to take photos, upload the photos to a server, and take appropriate countermeasures based on the analysis results" refers to technology in which a robot placed in a factory or other environment takes photos of plants, sends them to a server, and takes appropriate countermeasures based on the diagnostic results.

[0945] 11. "Means for recommending products related to countermeasures for identified diseases or pests" refers to a system that has the functionality to search for and recommend products necessary for appropriate treatment or countermeasures based on the diagnosis of a disease or pest.

[0946] 12. "Means for notifying the Administrator of the diagnosis results and recommended products" refers to technology for notifying the Administrator of details of diagnosed diseases or pests and information on recommended products.

[0947] The present invention relates to a system for identifying plant diseases and pests using photos of plants taken by a user and providing appropriate countermeasures. Specific embodiments for carrying out the present invention will be described below.

[0948] First, a user or a robot in the factory takes a photo of the plant. The user takes a photo of the plant using a smartphone or computer and uploads the photo to the system. Meanwhile, the robot takes a photo of the plant in the factory using its built-in camera.

[0949] Next, the captured photos are uploaded and sent to a server. The server passes the received photo data to an image recognition engine. This image recognition engine analyzes the photos, detects abnormalities such as plant diseases and pests, and extracts feature values. The image recognition engines used include libraries such as TensorFlow and Keras.

[0950] The extracted features are then analyzed by an AI model, which uses the features obtained from the image recognition engine to identify the type of disease or pest. For this identification, a pre-trained generative AI model is used. The model used includes a deep learning model (e.g., a convolutional neural network).

[0951] Based on the identification results, the server generates appropriate countermeasures. For example, for a specific disease, it suggests methods for removing the infected area or the use of specific medications. It also searches a database of products related to the recommended countermeasures and lists the corresponding products. This includes necessary nutrients, fungicides, and insecticides, and provides links to purchase these products.

[0952] The server then generates a response that compiles the diagnosis results, proposed countermeasures, and recommended products, and notifies the user or factory manager via a smartphone or computer application, or by email.

[0953] As a concrete example, suppose strange spots appear on the leaves of tomatoes being grown in a factory. A robot takes a photo of the spot and sends it to the server. The server analyzes the photo using an image recognition engine and an AI model and identifies it as spot disease. The diagnosis results are displayed as spot disease, and countermeasures include removing the infected area and using a specific fungicide. Furthermore, a link to purchase the recommended fungicide is provided, allowing managers to take prompt action.

[0954] Example prompt sentence:

[0955] Below are some examples of prompts to input to the generative AI model.

[0956] "Please identify the plant disease or pest seen in this image. Please suggest the necessary treatment and related products suitable for this disease."

[0957] Input image: path_to_plant_image.jpg

[0958] In this way, the present invention provides a system that effectively supports plant health management.

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

[0960] Step 1:

[0961] The user or the robot takes a photo of the plant. The user uses a smartphone, and the robot uses its built-in camera. The input is the plant photo, which becomes the input data for the system. The output is the captured photo data.

[0962] Step 2:

[0963] The device uploads the photograph of the plant to the server. The input is the photographed photo data, which becomes the data to be sent to the server. The output is the completion of sending the photo data to the server.

[0964] Step 3:

[0965] The server passes the received photo data to the image recognition engine, which performs preprocessing such as image resizing, noise removal, and color correction. The input is photo data, which becomes the data to be preprocessed. The output is preprocessed image data.

[0966] Step 4:

[0967] The server passes the preprocessed image data to an image recognition engine, which extracts features to identify plant diseases and pest types. The preprocessed image data is input, which becomes the input data for feature extraction. The extracted features are output.

[0968] Step 5:

[0969] The server inputs the extracted features into an AI model to identify the type of disease or pest. The extracted features serve as input data for the AI ​​model, and the identification result is generated as output.

[0970] Step 6:

[0971] The server generates specific countermeasures for plant diseases and pests based on the identification results. The input is the identification results, which serve as input data for countermeasure generation. The output is the specific countermeasures.

[0972] Step 7:

[0973] The server generates the necessary product recommendations and purchase links based on the identification results and countermeasures. The identification results and countermeasures are input, which become the input data for generating recommended products. The recommended products and purchase links are generated as output.

[0974] Step 8:

[0975] The server sends the diagnosis results, countermeasures, recommended products, and purchase links to the user's or administrator's terminal for display. The inputs are the diagnosis results, countermeasures, recommended products, and purchase links, which serve as notification data for the user or administrator. The output is the display result that is displayed on the terminal.

[0976] In this way, the system of the present invention can effectively support plant health management.

[0977] 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.

[0978] The present invention combines an emotion engine with a system that analyzes plant photos uploaded by users, identifies plant diseases and pests, and recommends specific countermeasures and necessary products based on the results. Specific embodiments for implementing the present invention are described below.

[0979] 1. Upload and send photos

[0980] Users take photos of plants using their own devices and upload them to the system's application or web interface, at which point the device receives the user's photo data.

[0981] 2. Receiving and analyzing photo data by the server

[0982] After the device receives the photo data, it sends it to the server. The server stores the received photo data in storage. It then performs preprocessing on the image (e.g., image resizing, noise removal, color correction, etc.) and passes the preprocessed image data to the image recognition engine.

[0983] 3. Identifying diseases and pests

[0984] The server's image recognition engine detects abnormalities in the photo and extracts features. At the same time, an AI model analyzes the features and identifies the type of plant disease or pest. Based on the identified disease or type of pest (e.g., black spot or aphids), a detailed diagnosis is generated.

[0985] 4. Proposal of countermeasures

[0986] Based on the results of the diagnosis, the server will suggest specific measures to deal with the disease or pest, such as how to remove the infected area or use a specific fungicide in the case of black spot.

[0987] 5. Recommend related products and generate purchase links

[0988] Based on the diagnosis and countermeasures, the server then searches a database for relevant products, such as suitable nutrients, fungicides, and insecticides, and recommends them to the user, including a link to an online shopping platform for purchase.

[0989] 6. Emotion Recognition by Emotion Engine

[0990] A new feature being added is the emotion engine, which recognizes the user's emotions. The emotion engine identifies the user's emotional state by analyzing facial expressions, voice, and behavioral patterns while the user is using the system. This emotion data is collected through sensors such as cameras and microphones.

[0991] 7. Emotion-based response optimization

[0992] The server uses the emotion data from the emotion engine to provide the optimal response based on the user's emotions. For example, if the user is feeling down, it will provide a more encouraging message.

[0993] 8. Tailoring product recommendations based on emotions

[0994] Using data from the emotion engine, the server adjusts the display order and content of recommended products. For example, if the user is in a hurry, it can prioritize products with immediate effects.

[0995] 9. Sending and displaying results

[0996] The server sends the diagnosis results, countermeasures, emotion recognition results, recommended products, and a purchase link all together to the device. The device receives this data and displays it in an easy-to-understand manner for the user. For example, along with the diagnosis results, the device may display an explanation such as "Your plant is suffering from black spot disease. To treat this disease, the following measures are required," as well as an encouraging message based on the user's emotion, an image of the recommended product, and a purchase link.

[0997] Specific examples

[0998] For example, suppose a user finds black spots on a rose leaf and uploads a photo of the leaf. The device sends the photo to a server, which uses an image recognition engine and an AI model to identify it as black spot disease. The diagnosis results are displayed as follows: "The black spots found on the rose leaf are black spot disease. It is recommended that you remove the infected area and use a specific fungicide." In addition, the emotion engine recognizes from the user's facial expression that they appear worried, and prioritizes displaying encouraging messages such as "Don't worry, recovery is expected if you take early action" and links to purchase fast-acting fungicides.

[0999] In this way, users can effectively manage the health of their plants without any specialized knowledge, quickly obtain the necessary products, and receive appropriate emotional support.

[1000] The processing flow will be explained below.

[1001] Step 1:

[1002] The user takes a photo of the plant with their device.

[1003] Step 2:

[1004] A user uploads a photograph of a plant to the system through the system's application or web interface.

[1005] Step 3:

[1006] The device sends the photo data uploaded by the user to the server.

[1007] The transmitted data includes the photo file and metadata such as the user ID.

[1008] Step 4:

[1009] The server stores the received photo data in storage.

[1010] Step 5:

[1011] The server performs image pre-processing (e.g., image resizing, noise removal, color correction, etc.).

[1012] Step 6:

[1013] The server passes the preprocessed images to an image recognition engine.

[1014] Step 7:

[1015] The image recognition engine detects abnormal areas in the photo and extracts features.

[1016] Step 8:

[1017] The AI ​​model analyzes the features and identifies the type of disease or pest.

[1018] During this process, specific identification results such as "black spot disease" or "aphids" are obtained.

[1019] Step 9:

[1020] The server generates a diagnosis result based on the output of the AI ​​model.

[1021] The diagnosis results include information such as the name of the identified disease or pest, a description of the symptoms, and the degree of progression.

[1022] Step 10:

[1023] The server generates appropriate countermeasures based on the identified diseases and pests.

[1024] For example, specific measures include "in the case of black spot disease, remove the infected area and use a specific fungicide."

[1025] Step 11:

[1026] Based on the diagnosis results and countermeasures, the server searches a database for relevant products such as necessary nutrients, fungicides, and insecticides and recommends them.

[1027] Step 12:

[1028] The server generates a purchase link to an online shopping platform along with information about the recommended products.

[1029] Step 13:

[1030] The server generates a response that combines the diagnosis results, countermeasures, recommended products, and a purchase link, and transmits it to the terminal.

[1031] Step 14:

[1032] The device analyzes the data received from the server and displays it in an easy-to-understand manner for the user.

[1033] The display clearly lists the diagnostic results, countermeasures, recommended products, and links to purchase them.

[1034] Step 15:

[1035] The user checks the displayed diagnostic results and countermeasures.

[1036] Step 16:

[1037] The user clicks on the purchase link for the recommended product and proceeds with the online shopping purchase process.

[1038] Step 17:

[1039] The emotion engine analyzes the user's facial expressions, voice, and behavioral patterns to recognize their emotions.

[1040] Emotional data is collected through sensors such as cameras and microphones.

[1041] Step 18:

[1042] The server provides the optimal response according to the user's emotions based on the emotion data from the emotion engine.

[1043] For example, if the user is feeling down, include an encouraging message.

[1044] Step 19:

[1045] The server uses data from the emotion engine to adjust the content and order of recommended products.

[1046] For example, if a user is in a hurry, products with immediate effects will be displayed first.

[1047] Step 20:

[1048] The device receives the adjusted results based on the emotion data from the server and displays them again to the user.

[1049] For example, along with an encouraging message, product information that is displayed with priority and has a high immediate effect is displayed.

[1050] These are the specific processing steps of the system that combines the emotion engine. This flow not only enables users to quickly identify plant problems and take appropriate measures, but also allows them to receive appropriate emotional support.

[1051] Example 2

[1052] 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."

[1053] Conventional plant disease and pest diagnosis systems are limited to identifying diseases and pests, and are insufficient in proposing specific countermeasures or related products. Furthermore, they lack support that takes into account the user's emotions, and there is a need for improved usability. This often leads to anxiety and stress in users regarding plant health management.

[1054] 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.

[1055] In this invention, the server includes means for uploading photos of plants taken by users, means for transmitting the uploaded photo data to the server, means for storing and preprocessing the photo data received by the server, means for passing the preprocessed photo data to an image recognition engine and identifying the type of plant disease or pest, means for generating specific countermeasures for the plant disease or pest based on the identification results, means for recommending necessary products and providing purchase links in addition to the countermeasures, means for recognizing the user's emotions and adjusting the display content of the countermeasures and recommended products based on the emotions, and means for transmitting the results to the user terminal and displaying them. This enables users to effectively manage the health of their plants, quickly procure necessary products, and receive appropriate emotional support.

[1056] "User" refers to an individual who uses the system to take and upload photos of plants.

[1057] "Device" refers to the electronic device a user uses to take photos and upload data, including smartphones and tablets.

[1058] "Server" refers to the computer system that receives, stores, processes, and analyzes photo data sent by users.

[1059] "Photo data" refers to image files taken by a user on a device and sent to a server.

[1060] "Preprocessing" refers to image improvement processes such as resizing, noise removal, and color correction that are performed on the photo data received by the server.

[1061] "Image recognition engine" refers to software or algorithms used to detect abnormalities and extract features from preprocessed photographic data.

[1062] "Features" refer to measurable information extracted from photos by an image recognition engine to identify diseases and pests.

[1063] An "AI model" refers to an algorithm that uses machine learning technology to analyze features and identify types of plant diseases and pests.

[1064] "Identification results" refers to diagnostic information regarding the type of disease or pest identified by the AI ​​model.

[1065] "Countermeasures" refer to specific treatment methods for plant diseases and pests based on the identification results.

[1066] "Product Recommendations" refers to suggestions of relevant products that can be used to treat or protect plants, based on the response measures.

[1067] "Buy Link" means a URL or button that provides direct access to an online shopping site for the recommended product.

[1068] "Emotion engine" refers to software or algorithms for recognizing a user's emotional state.

[1069] "Emotional Data" means information regarding a User's current emotional state as determined by the Emotion Engine.

[1070] The present invention combines an emotion engine with a system that analyzes plant photos uploaded by users, identifies plant diseases and pests, and recommends specific countermeasures and necessary products based on the results. Specific embodiments for implementing the present invention are described below.

[1071] Taking and uploading photos

[1072] Users take photos of plants using their own devices. They then upload the photos through the system's application or web interface. The device then receives the user's photo data. Specifically, users take photos with their smartphone or camera and tap the "upload" button in the app.

[1073] Receiving and sending photo data

[1074] The device receives the photo data uploaded by the user and sends the data to the server. The device's network module transfers the data to the server using an HTTP request.

[1075] Photo data storage and preprocessing

[1076] The server stores the received photo data in storage. It then performs image preprocessing, which includes image resizing, noise removal, color correction, etc. Specifically, the server performs preprocessing using an image processing library (e.g., OpenCV).

[1077] Analysis by image recognition engine

[1078] The server passes the preprocessed image data to an image recognition engine, which detects abnormalities and extracts features. Specifically, a machine learning model (e.g., TensorFlow or PyTorch model) is used.

[1079] Identifying diseases and pests with AI models

[1080] The server inputs the feature values ​​sent from the image recognition engine into the AI ​​model to identify the type of plant disease or pest. Specifically, the AI ​​model analyzes the data using a neural network and outputs the results.

[1081] Generating diagnostic results

[1082] The server generates detailed diagnostic results based on the identified disease or pest type, using templates to create text information to display to the user as the diagnostic results.

[1083] Proposal of countermeasures

[1084] Based on the diagnosis results, the server proposes specific countermeasures for diseases and pests. For example, in the case of black spot disease, it suggests "how to remove the infected area" and "how to use a specific fungicide." Specific operations involve retrieving appropriate information from a database of countermeasure information that has been set up in advance.

[1085] Related product recommendations

[1086] The server recommends relevant nutrients, fungicides, and insecticides based on the diagnosis and countermeasures, searching for product information from a database of products suitable for the countermeasures, and generating a purchase link to an online shopping platform.

[1087] Emotion recognition by emotion engine

[1088] The device uses an emotion engine to recognize the user's emotions. Specifically, it analyzes sensor information collected through the camera and microphone to identify the user's emotional state from their facial expressions and tone of voice.

[1089] Sending emotional data

[1090] The device sends the recognized emotion data to the server. The device transfers the emotional state data to the server using an HTTP request.

[1091] Emotion-based response optimization

[1092] The server provides the optimal response based on the user's emotions based on the emotion data from the emotion engine. For example, if the user is feeling down, it will add an encouraging message. Specifically, it selects and edits a template message based on the emotion data.

[1093] Emotion-based product recommendation adjustment

[1094] The server uses emotional data to adjust the display order and order of recommended products. For example, if the user is in a hurry, it will prioritize products with immediate effects. Specifically, it rearranges the display order of products based on emotional data.

[1095] Sending and displaying results

[1096] The server compiles the diagnosis results, countermeasures, emotion recognition results, recommended products, and purchase links and sends them to the device. The device then receives this data and displays it in an easy-to-understand manner for the user. Specifically, it uses UI components to display the results in an application or web interface.

[1097] Specific examples

[1098] For example, suppose a user notices black spots on a rose leaf and uploads a photo of the leaf. The device sends the photo to the server, which uses an image recognition engine and AI model to identify it as black spot disease. The diagnosis results are displayed as follows: "The black spots on the rose leaf are black spot disease. It is recommended that you remove the infected area and use a specific fungicide." Additionally, the emotion engine recognizes the user's concern from their facial expression and prioritizes displaying encouraging messages such as "Don't worry, recovery is expected with early intervention" and links to purchase fast-acting fungicides. This allows users to effectively manage plant health without specialized knowledge, quickly procure the necessary products, and receive appropriate emotional support.

[1099] Prompt Sentence Examples

[1100] "Analyze a photo of black spots on rose leaves, detail the type of disease and how to treat it. Also, acknowledge the user's concern and include a message of encouragement."

[1101] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1102] Step 1:

[1103] The user takes a photo of a plant on their device and uploads the photo to the application or web interface. The input is the photo data of the plant taken by the user. Specifically, the user takes a photo with their smartphone or camera and taps the "upload" button in the application. The output is the photo data saved on the device.

[1104] Step 2:

[1105] The device receives photo data uploaded by the user. The input is the photo data uploaded by the user. Specifically, the uploaded photos are saved in a temporary folder in the device's application. The output is the saved photo data.

[1106] Step 3:

[1107] The device sends the received photo data to the server. The input is the photo data saved in the temporary folder. The device's network module transfers the data to the server using an HTTP request. The output is the photo data sent to the server.

[1108] Step 4:

[1109] The server saves the received photo data in storage. The input is the photo data sent from the device. An example of software used is a cloud storage service such as AWS S3. The output is the photo data saved in storage.

[1110] Step 5:

[1111] The server performs preprocessing on the stored photo data. The input is the photo data stored in storage. Preprocessing includes image resizing, noise removal, color correction, etc. Specifically, the server performs preprocessing using an image processing library (e.g., OpenCV). The output is the preprocessed image data.

[1112] Step 6:

[1113] The server passes the preprocessed image data to the image recognition engine. The input is the preprocessed image data. The image recognition engine detects abnormal parts in the image and extracts features. Specifically, a machine learning model (e.g., TensorFlow or PyTorch model) is used. The output is the extracted features.

[1114] Step 7:

[1115] The server inputs the features sent from the image recognition engine into the AI ​​model to identify the type of plant disease or pest. The input is the extracted features. The AI ​​model analyzes the data using a neural network and outputs the results. The output is the type of disease or pest identified.

[1116] Step 8:

[1117] The server generates detailed diagnostic results based on the identified disease or pest type. The input is the identification result from the AI ​​model. Specifically, a template is used to create text information to display to the user as the diagnostic result. The output is text data of the diagnostic result.

[1118] Step 9:

[1119] Based on the diagnosis results, the server proposes specific countermeasures against diseases and pests. The input is the text data of the diagnosis results. For example, in the case of black spot disease, it will suggest "how to remove the infected area" and "how to use a specific fungicide." The specific operation involves retrieving appropriate information from a database of pre-set countermeasure information. The output is text data of specific countermeasures.

[1120] Step 10:

[1121] The server recommends relevant nutrients, fungicides, and insecticides based on the diagnosis results and countermeasures. The input is text data of the specific countermeasures. Specifically, it searches for product information from a database of products suitable for the countermeasures and generates a purchase link to an online shopping platform. The output is data on the recommended products and the purchase link.

[1122] Step 11:

[1123] The device uses an emotion engine to recognize the user's emotions. The input is sensor information collected through the camera and microphone. The emotion engine identifies the user's emotional state from their facial expressions and tone of voice. Specifically, it uses an emotion analysis algorithm. The output is the user's emotional data.

[1124] Step 12:

[1125] The device sends the recognized emotion data to the server. The input is the identified user emotion data. The device transfers the emotional state data to the server using an HTTP request. The output is the emotion data sent to the server.

[1126] Step 13:

[1127] The server provides the optimal response based on the user's emotions, based on the emotion data from the emotion engine. The input is the emotion data sent to the server. For example, if the user is feeling down, an encouraging message is added. The specific operation is to select and edit a template message based on the emotion data. The output is text data of the optimal response based on the emotion.

[1128] Step 14:

[1129] The server uses the emotional data to adjust the display content and order of recommended products. The input is the emotional data sent to the server. For example, if the user is in a hurry, products with immediate effects are displayed first. Specifically, the display order of products is rearranged based on the emotional data. The output is recommended product data that has been adjusted based on the emotion.

[1130] Step 15:

[1131] The server compiles the diagnosis results, countermeasures, emotion recognition results, recommended products, and purchase links and sends them to the terminal. The input is the adjusted recommended product data and various text data. Specifically, it compiles this data in HTML or JSON format and sends it to the terminal as an HTTP response. The output is the display data sent to the terminal.

[1132] Step 16:

[1133] The device receives the data sent from the server and displays it in a user-friendly way. The input is the display data sent from the server. Specific operations include using UI components to display the results in an application or web interface. The output is the diagnosis results, countermeasures, emotion recognition results, recommended products, and purchase links displayed to the user.

[1134] (Application example 2)

[1135] 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."

[1136] In modern plant cultivation and gardening, when plants are attacked by disease or pests, it is necessary to take prompt and appropriate measures. However, it is difficult for ordinary users to accurately identify plant diseases and pests and take appropriate measures. Furthermore, if users feel discouraged or impatient, it may affect their ability to resolve the problem if appropriate support is not provided. A system that can solve these issues is needed.

[1137] 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 uploading photos of plants taken by the user, means for transmitting the uploaded photo data to the server, means for passing the photo data received by the server to an image recognition engine and identifying the type of plant disease or pest, means for generating specific countermeasures for the plant disease or pest based on the identification results, means for providing necessary product recommendations and purchase links in addition to the countermeasures, means for transmitting the results to the user terminal and displaying them, means for collecting emotional data from the user's facial expressions and voice, means for analyzing the emotional data to identify the user's emotional state, and means for adjusting the display content of the countermeasures and recommended products based on the emotional state. This enables the user to quickly and accurately identify plant diseases and pests and take appropriate countermeasures, while also receiving appropriate emotional support.

[1138] A "user" is someone who takes photos of their plants and uses the system to diagnose diseases and pests, receive suggested treatments, and receive emotional support.

[1139] "Photo data" refers to image information of plants taken by users, and is data that is sent to the server and analyzed.

[1140] The "server" is a computer system that receives uploaded photo data, analyzes it using an image recognition engine, and generates diagnostic results, countermeasures, and information based on emotion analysis, which it then provides to users.

[1141] An "image recognition engine" is software or algorithm that analyzes received photo data and identifies types of plant diseases and pests.

[1142] "Countermeasures" refer to specific methods of dealing with plant diseases and pests that are proposed based on the diagnostic results.

[1143] "Recommendation" refers to presenting products suitable for the user based on diagnostic results and sentiment analysis.

[1144] "Purchase Link" means a web link that enables a User to purchase a Recommended Product online.

[1145] "User Device" means a smartphone, tablet, or other electronic device used by a User.

[1146] "Facial expression" refers to the movement and position of the user's face, and is used as data for emotion analysis.

[1147] "Voice" refers to the words and voices spoken by the user and is used as data for emotion analysis.

[1148] "Emotional data" refers to data that indicates the emotional state identified by analyzing a user's facial expressions and voice.

[1149] "Emotional state" refers to the user's current emotions, as determined as a result of emotion analysis.

[1150] The present invention combines an emotion engine with a system that analyzes photos of plants taken by users, identifies plant diseases and pests, and recommends specific countermeasures and necessary products based on the results. Specific embodiments of the present invention are described in detail below.

[1151] 1. Upload and send photos

[1152] Users can take photos of plants using their smart devices and upload them via the app or web interface, which then sends the photos to the server.

[1153] 2. Photo data is received and analyzed by the server

[1154] The server stores the photo data received from the device in storage, then performs image preprocessing (e.g., resizing, noise removal, color correction, etc.), and inputs the preprocessed image data into the image recognition engine.

[1155] 3. Disease and pest identification

[1156] The image recognition engine detects abnormalities in the photo and extracts features. The AI ​​model then analyzes the features to identify the type of plant disease or pest, such as black spot or aphids.

[1157] 4. Proposal of countermeasures

[1158] Based on the identification results, the server generates specific countermeasures for plant diseases and pests, such as removing the infected area and applying a specific fungicide in the case of black spot.

[1159] 5. Recommend related products and generate purchase links

[1160] Based on the diagnosis and countermeasures, the server then searches its database for relevant products, such as suitable nutrients, fungicides, and insecticides, and recommends them to the user, including a link to an online shopping platform for purchase.

[1161] 6. Emotion recognition using emotion engine

[1162] The emotion engine analyzes the user's facial expressions, voice, and behavioral patterns to identify their emotional state. Emotional data is collected through sensors such as cameras and microphones.

[1163] 7. Emotion-based response optimization

[1164] The server uses the emotion data from the emotion engine to provide the optimal response based on the user's emotions. For example, if the user is feeling down, it will provide a more encouraging message.

[1165] 8. Tailoring product recommendations based on emotions

[1166] The server uses emotional data to adjust the content and order of recommended products. For example, if the user is in a hurry, products with immediate effects will be displayed first.

[1167] 9. Sending and displaying results

[1168] The server compiles the diagnosis results, countermeasures, emotion recognition results, recommended products, and purchase links and sends them to the user's device. The user's device receives this data and displays it in an easy-to-understand manner. Specifically, along with the diagnosis results, the data includes an explanation such as "Your plant is suffering from black spot disease. The following measures are necessary to treat this disease," an encouraging message based on emotion, an image of the recommended product, and a purchase link.

[1169] Specific examples

[1170] Suppose a user finds black spots on a rose leaf and uploads a photo of the leaf. The device sends the photo to a server, which uses an image recognition engine and an AI model to identify it as black spot disease. The diagnosis results are displayed as follows: "The black spots found on the rose leaf are black spot disease. It is recommended that you remove the infected area and use a specific fungicide." In addition, the emotion engine recognizes from the user's facial expression that he or she looks worried, and prioritizes displaying encouraging messages such as "Don't worry, early intervention is likely to lead to recovery" and links to purchase fast-acting fungicides.

[1171] Example prompt for a generative AI model:

[1172] "I noticed black spots on the leaves of my roses. Explain to the concerned user how to treat black spot and what fungicide to buy. Include a message of encouragement."

[1173] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1174] Step 1:

[1175] The user takes a photo of a plant using a smart device. The input is the plant photo data, and the output is the photo stored on the device. This photo data is the basis for subsequent processing.

[1176] Step 2:

[1177] The user uploads plant photo data to the server through the application or web interface. The input is the photo data taken by the user, and the output is the photo data sent to the server. Specifically, the user presses the "upload" button in the application to send the photo data.

[1178] Step 3:

[1179] The server stores the received photo data in storage and performs image preprocessing. The input is the photo data sent to the server, and the output is the preprocessed image data. Specific operations include resizing, noise removal, and color correction.

[1180] Step 4:

[1181] The server passes the preprocessed image data to an image recognition engine to identify the type of plant disease or pest. The input is the preprocessed image data, and the output is data with extracted features. The image recognition engine detects abnormal areas and extracts features.

[1182] Step 5:

[1183] The AI ​​model analyzes the extracted features to identify the type of plant disease or pest. The input is the data from which the features have been extracted, and the output is information that identifies the type of disease or pest. Specifically, the AI ​​model identifies black spot disease, aphids, etc.

[1184] Step 6:

[1185] Based on the identification results, the server generates specific countermeasures for plant diseases and pests. The input is information that identifies the type of disease or pest, and the output is a list of specific countermeasures. For example, in the case of black spot disease, it is recommended to remove the infected area and use a specific fungicide.

[1186] Step 7:

[1187] Based on the diagnosis results and solutions, the server searches the database for relevant products and recommends them to the user. The input is a list of specific solutions, and the output is a list of recommended products and a purchase link. Specifically, a link to an online shopping platform is provided.

[1188] Step 8:

[1189] The server collects the user's facial expressions and voice using a camera and microphone to obtain emotion data. The input is the user's facial expressions and voice, and the output is data that identifies the user's emotional state. The collected emotion data is passed to the emotion engine.

[1190] Step 9:

[1191] The emotion engine analyzes the emotion data and identifies the user's emotional state. The input is the user's facial expression and voice data, and the output is the user's emotional state. Specifically, the emotion engine identifies the emotional state as "worry" or "anxiety," etc.

[1192] Step 10:

[1193] The server adjusts the displayed content of solutions and recommended products based on the user's emotional state. The input is the user's emotional state and the information generated in the previous step, and the output is optimized solutions and product lists. For example, if the user is worried, an encouraging message is provided.

[1194] Step 11:

[1195] The server compiles the diagnosis results, countermeasures, emotion recognition results, recommended products, and purchase links and sends them to the user's device. The input is the optimized countermeasures and product list, and the output is the information displayed on the user's device. Specifically, the diagnosis results, countermeasures, recommended products, and encouraging messages are displayed on the user's device.

[1196] Step 12:

[1197] The user's device displays the data received from the server in an easy-to-understand manner. The input is the data sent from the server, and the output is the diagnostic results and countermeasure information displayed to the user. Based on the displayed information, the user can take countermeasures against plant diseases and pests and purchase related products.

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

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

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

[1201] [Fourth embodiment]

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

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

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

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

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

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

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

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

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

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

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

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

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

[1215] The present invention is a system in which users upload photos of plants, and the server analyzes the photo data using an image recognition engine to identify plant diseases and pests and provide appropriate countermeasures. Specific embodiments for implementing the present invention are described below.

[1216] 1. Upload and send photos

[1217] Users take photos of their plants' leaves, stems, and flowers using a device such as a smartphone or PC, and upload the photos to the system using the system's application or web interface. At this time, the device receives the user's photo data.

[1218] 2. Receiving and analyzing photo data by the server

[1219] After the device receives the photo data, it sends it to the server. The server temporarily stores the received photo data in storage and then performs preprocessing on the image (e.g., image resizing, noise removal, color correction, etc.).

[1220] The server then passes the preprocessed image data to an image recognition engine, which detects abnormal areas in the photo and extracts features, which are important information for identifying plant diseases and pests.

[1221] 3. Identifying diseases and pests

[1222] The server then uses the AI ​​model to analyze the features provided by the image recognition engine and identify the type of plant disease or pest. Based on the identified disease or pest type (e.g., black spot or aphids), a detailed diagnosis is generated.

[1223] 4. Proposal of countermeasures

[1224] Based on the results of the diagnosis, the server will suggest specific measures to take against diseases and pests, such as removing the infected area or using a specific fungicide in the case of black spot.

[1225] 5. Recommend related products and generate purchase links

[1226] Furthermore, based on the diagnosis results and countermeasures, the server searches the database for relevant products such as nutrients, fungicides, and insecticides that are needed and recommends them to the user. The recommended products include a purchase link to an online shopping platform such as Yahoo Shopping.

[1227] 6. Sending and displaying results

[1228] The server generates a response that combines the diagnosis results, countermeasures, recommended products, and a purchase link, and sends it to the device. The device receives this data and displays it in a format that is easy for the user to understand. The display content includes a detailed explanation, such as "Your roses are suffering from black spot disease. The following measures are required to treat this disease," as well as images of the recommended products and purchase links.

[1229] Specific examples

[1230] For example, suppose a user finds black spots on the leaves of a rose and uploads a photo of the leaves. The device sends the photo to a server, which analyzes it using an image recognition engine and AI model and identifies it as black spot disease. The diagnosis result is displayed as follows: "The black spots found on the rose leaves are black spot disease. It is recommended that you remove the infected areas and use a specific fungicide." In addition, the app recommends a fungicide suitable for the solution and provides a purchase link, allowing the user to immediately purchase the necessary product.

[1231] In this way, users can effectively manage plant health and quickly source the products they need, even without specialized knowledge.

[1232] The processing flow will be explained below.

[1233] Step 1:

[1234] The user takes a photo of the plant with their device.

[1235] Step 2:

[1236] A user uploads a photograph of a plant to the system through the system's application or web interface.

[1237] Step 3:

[1238] The device sends the photo data uploaded by the user to the server.

[1239] The transmitted data includes the photo file and metadata such as the user ID.

[1240] Step 4:

[1241] The server stores the received photo data in storage.

[1242] Step 5:

[1243] The server performs image pre-processing (e.g., image resizing, noise removal, color correction, etc.).

[1244] Step 6:

[1245] The server passes the preprocessed images to an image recognition engine.

[1246] Step 7:

[1247] The image recognition engine detects abnormal areas in the photo and extracts features.

[1248] Step 8:

[1249] The AI ​​model analyzes the features and identifies the type of disease or pest.

[1250] During this process, specific identification results such as "black spot disease" or "aphids" are obtained.

[1251] Step 9:

[1252] The server generates a diagnosis result based on the output of the AI ​​model.

[1253] The diagnosis results include information such as the name of the identified disease or pest, a description of the symptoms, and the degree of progression.

[1254] Step 10:

[1255] The server generates appropriate countermeasures based on the identified diseases and pests.

[1256] For example, specific measures include "in the case of black spot disease, remove the infected area and use a specific fungicide."

[1257] Step 11:

[1258] Based on the diagnosis results and countermeasures, the server searches a database for relevant products such as necessary nutrients, fungicides, and insecticides and recommends them.

[1259] Step 12:

[1260] The server generates a purchase link to Yahoo! Shopping or the like along with information about the recommended product.

[1261] Step 13:

[1262] The server generates a response including the diagnosis result, countermeasures, recommended products, and a purchase link, and transmits it to the terminal.

[1263] Step 14:

[1264] The device analyzes the data received from the server and displays it in an easy-to-understand manner for the user.

[1265] The display clearly lists the diagnostic results, countermeasures, recommended products, and links to purchase them.

[1266] Step 15:

[1267] The user checks the displayed diagnostic results and countermeasures, and if necessary, clicks on the purchase link for the recommended product to proceed with the purchase process on Yahoo! Shopping.

[1268] These are the detailed steps of the program's processing, which allows users to quickly identify plant problems and take appropriate measures.

[1269] Example 1

[1270] 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."

[1271] Traditionally, diagnosing plant diseases and pests required specialized knowledge, making it difficult for average users. Furthermore, actually receiving a diagnosis required a visit from an expert or bringing the plant to a facility, which was costly and time-consuming. Furthermore, the process of finding specific countermeasures and necessary products after a diagnosis was time-consuming. There is a need for a system that addresses these issues and allows average users to easily manage the health of their plants.

[1272] 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.

[1273] In this invention, the server includes means for uploading images of plants taken by users, means for transmitting the uploaded image data to the server, means for passing the image data received by the server to an image recognition system and identifying the type of plant disease or pest, means for generating specific countermeasures for the plant disease or pest based on the identification results, means for providing recommendations and purchase links for necessary products in addition to the countermeasures, and means for transmitting and displaying the results to a user terminal. This enables users, even without specialized knowledge, to quickly and easily diagnose plant diseases and pests and obtain appropriate countermeasures and necessary products.

[1274] A "user" is an entity that uses the system to upload images of plants and receive diagnostic results and countermeasures.

[1275] "Terminal" refers to an electronic device used by a user, such as a smartphone or computer, for taking and uploading images and displaying the results.

[1276] "Image data" refers to data that digitally represents an image of a plant photographed by a user.

[1277] A "server" is a central computing device that stores received image data and performs analysis using an image recognition system and artificial intelligence models.

[1278] An "image recognition system" is software that detects abnormal parts from received image data and extracts characteristic information.

[1279] "Feature information" is information about specific parts or patterns in an image that are important for identifying diseases or pests, extracted by the image recognition system.

[1280] An "artificial intelligence model" is a trained algorithm that analyzes feature information provided by an image recognition system and identifies the type of disease or pest.

[1281] "Identification results" are information about the type of plant disease or pest obtained as a result of analysis by the artificial intelligence model.

[1282] "Countermeasures" are specific treatment methods or measures against plant diseases or pests that are generated based on the identification results.

[1283] "Recommended products" are products that are required to implement countermeasures and are recommended to users.

[1284] "Purchase Link" means the URL for purchasing the Recommended Product on an online shopping platform.

[1285] "Results" refers collectively to information including identification results, countermeasures, recommended products, and purchase links that are provided to users.

[1286] The present invention is a system in which users upload images of plants they have taken, and the server analyzes the image data using an image recognition system and artificial intelligence model to identify plant diseases and types of pests and provide appropriate countermeasures.

[1287] First, the user takes an image of the plant using a device such as a smartphone or PC. It is preferable to take an image that clearly captures any abnormalities, such as leaves, stems, or flowers. Next, the user selects and uploads the image using the system's application or web interface. The device receives the image data and sends it to the server.

[1288] The server receives image data sent from the user's device and temporarily stores it in storage. The server then performs preprocessing on the stored image data. This preprocessing includes image resizing, noise removal, color correction, etc. This preprocessing improves the accuracy of analysis by the image recognition system.

[1289] The server then passes the preprocessed image data to an image recognition system, which uses deep learning and computer vision techniques to detect abnormalities in the image and extract feature information, which is key to identifying plant diseases and pests.

[1290] The extracted feature information is returned to the server, which then inputs it into an AI model. The AI ​​model is pre-trained and capable of identifying the type of plant disease or pest. The AI ​​model analyzes the feature information and identifies the specific disease or pest. For example, black spot or aphids may be detected.

[1291] Based on the identification results, the server generates specific countermeasures for the disease or pest. For example, in the case of black spot disease, this includes how to remove the infected area and how to use a specific fungicide. Based on the countermeasures, the server also searches a database for related products, such as nutrients, fungicides, and insecticides, and recommends them to the user. The recommended products include a purchase link to an online shopping platform.

[1292] Finally, the server generates response data that combines the diagnosis results, countermeasures, recommended products, and a purchase link, and sends it to the device. The device then displays the received response data to the user. The display includes the diagnosis results, specific countermeasures, images of recommended products, and purchase links, allowing the user to quickly and effectively manage the health of their plants based on this information.

[1293] For example, suppose a user finds black spots on a rose leaf and uploads an image of the leaf. The user's device sends the image to a server, which analyzes it using an image recognition system and an artificial intelligence model and identifies it as black spot disease. The diagnosis result is displayed as follows: "The black spots found on the rose leaf are black spot disease. It is recommended that you remove the infected area and use a specific fungicide." The app also recommends the best fungicide for the treatment and provides a link to purchase it. In this way, users can effectively manage the health of their plants and quickly obtain the necessary products without any specialized knowledge.

[1294] An example of a prompt sentence to input to the generative AI model is as follows:

[1295] "I uploaded a picture of some black spots on the leaves of my plant. Can you please tell me what these black spots are and how to deal with them?"

[1296] In this way, the present invention supports the user's plant health management by identifying diseases and pests based on images of plants taken by the user and suggesting appropriate countermeasures and related products.

[1297] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1298] Step 1:

[1299] The user takes a picture of the plant using a device such as a smartphone or PC. The captured image is saved on the device as a digital image file. The input is the image taken by the user with the device's camera, and this image is saved on the device as the output.

[1300] Step 2:

[1301] A user opens the system's application or web interface, selects a captured image, and presses a button to upload it. The input is the image file selected by the user, and the selected image is included in the upload request as the output.

[1302] Step 3:

[1303] The device receives the image data uploaded by the user. It creates a request to send the image data to the server along with the user authentication information, and sends it to the server as an HTTP POST request. The input is the image data selected by the user and the authentication information, and the output is an HTTP request containing these.

[1304] Step 4:

[1305] The server receives a request for image data sent from the terminal and extracts the image data. The server saves this image data in storage. The input is the HTTP request sent from the terminal, and the extracted image data is saved in storage as intermediate output.

[1306] Step 5:

[1307] The server performs image preprocessing such as resizing, noise removal, and color correction on the stored image data. The input is the stored raw image file, and the processed image after these preprocessing steps is the output. Preprocessing at this step improves the accuracy of the subsequent image recognition.

[1308] Step 6:

[1309] The server passes the preprocessed image data to an image recognition system, which detects abnormalities and extracts feature information. The preprocessed image data is input, and the location and feature information of abnormalities are obtained as output through the image recognition system.

[1310] Step 7:

[1311] The server inputs the feature information provided by the image recognition system into an artificial intelligence model. The AI ​​model analyzes the feature information and identifies the type of plant disease or pest. The input is feature information, and the output is specific information about the disease or pest as a result of the identification.

[1312] Step 8:

[1313] The server generates specific countermeasures based on the identification results, including detailed treatment methods and countermeasures for the identified diseases and pests. The input is the identification results, and the generated countermeasures are the output.

[1314] Step 9:

[1315] The server searches a database of related products based on the countermeasure and finds recommended products such as needed nutrients, fungicides, insecticides, etc. The input is the countermeasure information, and the output is related product information from the database.

[1316] Step 10:

[1317] The server compiles information about the recommended products and generates a purchase link to an online shopping platform. The input is the information about the recommended products, and the generated purchase link is the output.

[1318] Step 11:

[1319] The server generates response data that combines the diagnosis results, countermeasures, recommended products, and purchase links, and sends it to the user's device. The input is the diagnosis results, countermeasures, recommended products, and purchase links that have been generated so far, and the response data that includes these is the output.

[1320] Step 12:

[1321] The device then displays the received response data to the user. The displayed content includes the diagnosis results, specific countermeasures, images of recommended products, and links to purchase them, all in a format that is easy for the user to understand. The input is the response data from the server, and the display content that the user can see is the output.

[1322] Through these processing steps, users can quickly and effectively diagnose plant diseases and pests without specialized knowledge, and obtain appropriate countermeasures and necessary products.

[1323] (Application example 1)

[1324] 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."

[1325] In modern agriculture and horticulture, there is a need for early detection and rapid response to plant diseases and pests. Especially in large-scale cultivation environments, there are limitations to manual monitoring and response. There is also a need for systems that can accurately identify the type of disease or pest and quickly provide appropriate countermeasures. Furthermore, it is also important to be able to easily obtain the products needed for these countermeasures.

[1326] 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.

[1327] In this invention, the server includes a means for uploading photos of plants taken by a user or a robot to the server and implementing appropriate countermeasures based on the analysis results, a means for recommending products related to countermeasures for identified diseases and pests, and a means for notifying an administrator of the diagnosis results and recommended products. This enables early detection of diseases and pests and prompt response, automates monitoring and management of the cultivation environment, and realizes efficient agricultural and horticultural activities.

[1328] 1. "User" refers to the individual or artifact that takes photos of plants and uploads them to the system.

[1329] 2. "Plant photos" refers to image data of plant leaves, stems, flowers, etc.

[1330] 3. "Means for uploading" refers to technology that has the functionality to transfer plant photos to a system or server.

[1331] 4. "Server" refers to a computer system that receives plant photo data and performs image recognition and analysis.

[1332] 5. "Image recognition engine" refers to algorithms and software that analyze photographic data, detect abnormalities, and extract features.

[1333] 6. "Methods for identifying types of plant diseases and pests" refers to technologies that use image recognition engines and AI models to analyze the health of plants and identify diseases and pests.

[1334] 7. "Means for generating specific countermeasures" refers to a function that suggests specific countermeasures for plant diseases and pests based on the identification results.

[1335] 8. "Means for recommending necessary products and providing links to purchase them" refers to a system that has the function of searching for products related to the solution and providing links to purchase them.

[1336] 9. "Means for transmitting and displaying results on user devices" refers to the technology for transferring and displaying analysis results and countermeasures on the device used by the user.

[1337] 10. "Means for a robot to take photos, upload the photos to a server, and take appropriate countermeasures based on the analysis results" refers to technology in which a robot placed in a factory or other environment takes photos of plants, sends them to a server, and takes appropriate countermeasures based on the diagnostic results.

[1338] 11. "Means for recommending products related to countermeasures for identified diseases or pests" refers to a system that has the functionality to search for and recommend products necessary for appropriate treatment or countermeasures based on the diagnosis of a disease or pest.

[1339] 12. "Means for notifying the Administrator of the diagnosis results and recommended products" refers to technology for notifying the Administrator of details of diagnosed diseases or pests and information on recommended products.

[1340] The present invention relates to a system for identifying plant diseases and pests using photos of plants taken by a user and providing appropriate countermeasures. Specific embodiments for carrying out the present invention will be described below.

[1341] First, a user or a robot in the factory takes a photo of the plant. The user takes a photo of the plant using a smartphone or computer and uploads the photo to the system. Meanwhile, the robot takes a photo of the plant in the factory using its built-in camera.

[1342] Next, the captured photos are uploaded and sent to a server. The server passes the received photo data to an image recognition engine. This image recognition engine analyzes the photos, detects abnormalities such as plant diseases and pests, and extracts feature values. The image recognition engines used include libraries such as TensorFlow and Keras.

[1343] The extracted features are then analyzed by an AI model, which uses the features obtained from the image recognition engine to identify the type of disease or pest. For this identification, a pre-trained generative AI model is used. The model used includes a deep learning model (e.g., a convolutional neural network).

[1344] Based on the identification results, the server generates appropriate countermeasures. For example, for a specific disease, it suggests methods for removing the infected area or the use of specific medications. It also searches a database of products related to the recommended countermeasures and lists the corresponding products. This includes necessary nutrients, fungicides, and insecticides, and provides links to purchase these products.

[1345] The server then generates a response that compiles the diagnosis results, proposed countermeasures, and recommended products, and notifies the user or factory manager via a smartphone or computer application, or by email.

[1346] As a concrete example, suppose strange spots appear on the leaves of tomatoes being grown in a factory. A robot takes a photo of the spot and sends it to the server. The server analyzes the photo using an image recognition engine and an AI model and identifies it as spot disease. The diagnosis results are displayed as spot disease, and countermeasures include removing the infected area and using a specific fungicide. Furthermore, a link to purchase the recommended fungicide is provided, allowing managers to take prompt action.

[1347] Example prompt sentence:

[1348] Below are some examples of prompts to input to the generative AI model.

[1349] "Please identify the plant disease or pest seen in this image. Please suggest the necessary treatment and related products suitable for this disease."

[1350] Input image: path_to_plant_image.jpg

[1351] In this way, the present invention provides a system that effectively supports plant health management.

[1352] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1353] Step 1:

[1354] The user or the robot takes a photo of the plant. The user uses a smartphone, and the robot uses its built-in camera. The input is the plant photo, which becomes the input data for the system. The output is the captured photo data.

[1355] Step 2:

[1356] The device uploads the photograph of the plant to the server. The input is the photographed photo data, which becomes the data to be sent to the server. The output is the completion of sending the photo data to the server.

[1357] Step 3:

[1358] The server passes the received photo data to the image recognition engine, which performs preprocessing such as image resizing, noise removal, and color correction. The input is photo data, which becomes the data to be preprocessed. The output is preprocessed image data.

[1359] Step 4:

[1360] The server passes the preprocessed image data to an image recognition engine, which extracts features to identify plant diseases and pest types. The preprocessed image data is input, which becomes the input data for feature extraction. The extracted features are output.

[1361] Step 5:

[1362] The server inputs the extracted features into an AI model to identify the type of disease or pest. The extracted features serve as input data for the AI ​​model, and the identification result is generated as output.

[1363] Step 6:

[1364] The server generates specific countermeasures for plant diseases and pests based on the identification results. The input is the identification results, which serve as input data for countermeasure generation. The output is the specific countermeasures.

[1365] Step 7:

[1366] The server generates the necessary product recommendations and purchase links based on the identification results and countermeasures. The identification results and countermeasures are input, which become the input data for generating recommended products. The recommended products and purchase links are generated as output.

[1367] Step 8:

[1368] The server sends the diagnosis results, countermeasures, recommended products, and purchase links to the user's or administrator's terminal for display. The inputs are the diagnosis results, countermeasures, recommended products, and purchase links, which serve as notification data for the user or administrator. The output is the display result that is displayed on the terminal.

[1369] In this way, the system of the present invention can effectively support plant health management.

[1370] 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.

[1371] The present invention combines an emotion engine with a system that analyzes plant photos uploaded by users, identifies plant diseases and pests, and recommends specific countermeasures and necessary products based on the results. Specific embodiments for implementing the present invention are described below.

[1372] 1. Upload and send photos

[1373] Users take photos of plants using their own devices and upload them to the system's application or web interface, at which point the device receives the user's photo data.

[1374] 2. Receiving and analyzing photo data by the server

[1375] After the device receives the photo data, it sends it to the server. The server stores the received photo data in storage. It then performs preprocessing on the image (e.g., image resizing, noise removal, color correction, etc.) and passes the preprocessed image data to the image recognition engine.

[1376] 3. Identifying diseases and pests

[1377] The server's image recognition engine detects abnormalities in the photo and extracts features. At the same time, an AI model analyzes the features and identifies the type of plant disease or pest. Based on the identified disease or type of pest (e.g., black spot or aphids), a detailed diagnosis is generated.

[1378] 4. Proposal of countermeasures

[1379] Based on the results of the diagnosis, the server will suggest specific measures to deal with the disease or pest, such as how to remove the infected area or use a specific fungicide in the case of black spot.

[1380] 5. Recommend related products and generate purchase links

[1381] Based on the diagnosis and countermeasures, the server then searches a database for relevant products, such as suitable nutrients, fungicides, and insecticides, and recommends them to the user, including a link to an online shopping platform for purchase.

[1382] 6. Emotion Recognition by Emotion Engine

[1383] A new feature being added is the emotion engine, which recognizes the user's emotions. The emotion engine identifies the user's emotional state by analyzing facial expressions, voice, and behavioral patterns while the user is using the system. This emotion data is collected through sensors such as cameras and microphones.

[1384] 7. Emotion-based response optimization

[1385] The server uses the emotion data from the emotion engine to provide the optimal response based on the user's emotions. For example, if the user is feeling down, it will provide a more encouraging message.

[1386] 8. Tailoring product recommendations based on emotions

[1387] Using data from the emotion engine, the server adjusts the display order and content of recommended products. For example, if the user is in a hurry, it can prioritize products with immediate effects.

[1388] 9. Sending and displaying results

[1389] The server sends the diagnosis results, countermeasures, emotion recognition results, recommended products, and a purchase link all together to the device. The device receives this data and displays it in an easy-to-understand manner for the user. For example, along with the diagnosis results, the device may display an explanation such as "Your plant is suffering from black spot disease. To treat this disease, the following measures are required," as well as an encouraging message based on the user's emotion, an image of the recommended product, and a purchase link.

[1390] Specific examples

[1391] For example, suppose a user finds black spots on a rose leaf and uploads a photo of the leaf. The device sends the photo to a server, which uses an image recognition engine and an AI model to identify it as black spot disease. The diagnosis results are displayed as follows: "The black spots found on the rose leaf are black spot disease. It is recommended that you remove the infected area and use a specific fungicide." In addition, the emotion engine recognizes from the user's facial expression that they appear worried, and prioritizes displaying encouraging messages such as "Don't worry, recovery is expected if you take early action" and links to purchase fast-acting fungicides.

[1392] In this way, users can effectively manage the health of their plants without any specialized knowledge, quickly obtain the necessary products, and receive appropriate emotional support.

[1393] The processing flow will be explained below.

[1394] Step 1:

[1395] The user takes a photo of the plant with their device.

[1396] Step 2:

[1397] A user uploads a photograph of a plant to the system through the system's application or web interface.

[1398] Step 3:

[1399] The device sends the photo data uploaded by the user to the server.

[1400] The transmitted data includes the photo file and metadata such as the user ID.

[1401] Step 4:

[1402] The server stores the received photo data in storage.

[1403] Step 5:

[1404] The server performs image pre-processing (e.g., image resizing, noise removal, color correction, etc.).

[1405] Step 6:

[1406] The server passes the preprocessed images to an image recognition engine.

[1407] Step 7:

[1408] The image recognition engine detects abnormal areas in the photo and extracts features.

[1409] Step 8:

[1410] The AI ​​model analyzes the features and identifies the type of disease or pest.

[1411] During this process, specific identification results such as "black spot disease" or "aphids" are obtained.

[1412] Step 9:

[1413] The server generates a diagnosis result based on the output of the AI ​​model.

[1414] The diagnosis results include information such as the name of the identified disease or pest, a description of the symptoms, and the degree of progression.

[1415] Step 10:

[1416] The server generates appropriate countermeasures based on the identified diseases and pests.

[1417] For example, specific measures include "in the case of black spot disease, remove the infected area and use a specific fungicide."

[1418] Step 11:

[1419] Based on the diagnosis results and countermeasures, the server searches a database for relevant products such as necessary nutrients, fungicides, and insecticides and recommends them.

[1420] Step 12:

[1421] The server generates a purchase link to an online shopping platform along with information about the recommended products.

[1422] Step 13:

[1423] The server generates a response that combines the diagnosis results, countermeasures, recommended products, and a purchase link, and transmits it to the terminal.

[1424] Step 14:

[1425] The device analyzes the data received from the server and displays it in an easy-to-understand manner for the user.

[1426] The display clearly lists the diagnostic results, countermeasures, recommended products, and links to purchase them.

[1427] Step 15:

[1428] The user checks the displayed diagnostic results and countermeasures.

[1429] Step 16:

[1430] The user clicks on the purchase link for the recommended product and proceeds with the online shopping purchase process.

[1431] Step 17:

[1432] The emotion engine analyzes the user's facial expressions, voice, and behavioral patterns to recognize their emotions.

[1433] Emotional data is collected through sensors such as cameras and microphones.

[1434] Step 18:

[1435] The server provides the optimal response according to the user's emotions based on the emotion data from the emotion engine.

[1436] For example, if the user is feeling down, include an encouraging message.

[1437] Step 19:

[1438] The server uses data from the emotion engine to adjust the content and order of recommended products.

[1439] For example, if a user is in a hurry, products with immediate effects will be displayed first.

[1440] Step 20:

[1441] The device receives the adjusted results based on the emotion data from the server and displays them again to the user.

[1442] For example, along with an encouraging message, product information that is displayed with priority and has a high immediate effect is displayed.

[1443] These are the specific processing steps of the system that combines the emotion engine. This flow not only enables users to quickly identify plant problems and take appropriate measures, but also allows them to receive appropriate emotional support.

[1444] Example 2

[1445] 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."

[1446] Conventional plant disease and pest diagnosis systems are limited to identifying diseases and pests, and are insufficient in proposing specific countermeasures or related products. Furthermore, they lack support that takes into account the user's emotions, and there is a need for improved usability. This often leads to anxiety and stress in users regarding plant health management.

[1447] 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.

[1448] In this invention, the server includes means for uploading photos of plants taken by users, means for transmitting the uploaded photo data to the server, means for storing and preprocessing the photo data received by the server, means for passing the preprocessed photo data to an image recognition engine and identifying the type of plant disease or pest, means for generating specific countermeasures for the plant disease or pest based on the identification results, means for recommending necessary products and providing purchase links in addition to the countermeasures, means for recognizing the user's emotions and adjusting the display content of the countermeasures and recommended products based on the emotions, and means for transmitting the results to the user terminal and displaying them. This enables users to effectively manage the health of their plants, quickly procure necessary products, and receive appropriate emotional support.

[1449] "User" refers to an individual who uses the system to take and upload photos of plants.

[1450] "Device" refers to the electronic device a user uses to take photos and upload data, including smartphones and tablets.

[1451] "Server" refers to the computer system that receives, stores, processes, and analyzes photo data sent by users.

[1452] "Photo data" refers to image files taken by a user on a device and sent to a server.

[1453] "Preprocessing" refers to image improvement processes such as resizing, noise removal, and color correction that are performed on the photo data received by the server.

[1454] "Image recognition engine" refers to software or algorithms used to detect abnormalities and extract features from preprocessed photographic data.

[1455] "Features" refer to measurable information extracted from photos by an image recognition engine to identify diseases and pests.

[1456] An "AI model" refers to an algorithm that uses machine learning technology to analyze features and identify types of plant diseases and pests.

[1457] "Identification results" refers to diagnostic information regarding the type of disease or pest identified by the AI ​​model.

[1458] "Countermeasures" refer to specific treatment methods for plant diseases and pests based on the identification results.

[1459] "Product Recommendations" refers to suggestions of relevant products that can be used to treat or protect plants, based on the response measures.

[1460] "Buy Link" means a URL or button that provides direct access to an online shopping site for the recommended product.

[1461] "Emotion engine" refers to software or algorithms for recognizing a user's emotional state.

[1462] "Emotional Data" means information regarding a User's current emotional state as determined by the Emotion Engine.

[1463] The present invention combines an emotion engine with a system that analyzes plant photos uploaded by users, identifies plant diseases and pests, and recommends specific countermeasures and necessary products based on the results. Specific embodiments for implementing the present invention are described below.

[1464] Taking and uploading photos

[1465] Users take photos of plants using their own devices. They then upload the photos through the system's application or web interface. The device then receives the user's photo data. Specifically, users take photos with their smartphone or camera and tap the "upload" button in the app.

[1466] Receiving and sending photo data

[1467] The device receives the photo data uploaded by the user and sends the data to the server. The device's network module transfers the data to the server using an HTTP request.

[1468] Photo data storage and preprocessing

[1469] The server stores the received photo data in storage. It then performs image preprocessing, which includes image resizing, noise removal, color correction, etc. Specifically, the server performs preprocessing using an image processing library (e.g., OpenCV).

[1470] Analysis by image recognition engine

[1471] The server passes the preprocessed image data to an image recognition engine, which detects abnormalities and extracts features. Specifically, a machine learning model (e.g., TensorFlow or PyTorch model) is used.

[1472] Identifying diseases and pests with AI models

[1473] The server inputs the feature values ​​sent from the image recognition engine into the AI ​​model to identify the type of plant disease or pest. Specifically, the AI ​​model analyzes the data using a neural network and outputs the results.

[1474] Generating diagnostic results

[1475] The server generates detailed diagnostic results based on the identified disease or pest type, using templates to create text information to display to the user as the diagnostic results.

[1476] Proposal of countermeasures

[1477] Based on the diagnosis results, the server proposes specific countermeasures for diseases and pests. For example, in the case of black spot disease, it suggests "how to remove the infected area" and "how to use a specific fungicide." Specific operations involve retrieving appropriate information from a database of countermeasure information that has been set up in advance.

[1478] Related product recommendations

[1479] The server recommends relevant nutrients, fungicides, and insecticides based on the diagnosis and countermeasures, searching for product information from a database of products suitable for the countermeasures, and generating a purchase link to an online shopping platform.

[1480] Emotion recognition by emotion engine

[1481] The device uses an emotion engine to recognize the user's emotions. Specifically, it analyzes sensor information collected through the camera and microphone to identify the user's emotional state from their facial expressions and tone of voice.

[1482] Sending emotional data

[1483] The device sends the recognized emotion data to the server. The device transfers the emotional state data to the server using an HTTP request.

[1484] Emotion-based response optimization

[1485] The server provides the optimal response based on the user's emotions based on the emotion data from the emotion engine. For example, if the user is feeling down, it will add an encouraging message. Specifically, it selects and edits a template message based on the emotion data.

[1486] Emotion-based product recommendation adjustment

[1487] The server uses emotional data to adjust the display order and order of recommended products. For example, if the user is in a hurry, it will prioritize products with immediate effects. Specifically, it rearranges the display order of products based on emotional data.

[1488] Sending and displaying results

[1489] The server compiles the diagnosis results, countermeasures, emotion recognition results, recommended products, and purchase links and sends them to the device. The device then receives this data and displays it in an easy-to-understand manner for the user. Specifically, it uses UI components to display the results in an application or web interface.

[1490] Specific examples

[1491] For example, suppose a user notices black spots on a rose leaf and uploads a photo of the leaf. The device sends the photo to the server, which uses an image recognition engine and AI model to identify it as black spot disease. The diagnosis results are displayed as follows: "The black spots on the rose leaf are black spot disease. It is recommended that you remove the infected area and use a specific fungicide." Additionally, the emotion engine recognizes the user's concern from their facial expression and prioritizes displaying encouraging messages such as "Don't worry, recovery is expected with early intervention" and links to purchase fast-acting fungicides. This allows users to effectively manage plant health without specialized knowledge, quickly procure the necessary products, and receive appropriate emotional support.

[1492] Prompt Sentence Examples

[1493] "Analyze a photo of black spots on rose leaves, detail the type of disease and how to treat it. Also, acknowledge the user's concern and include a message of encouragement."

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

[1495] Step 1:

[1496] The user takes a photo of a plant on their device and uploads the photo to the application or web interface. The input is the photo data of the plant taken by the user. Specifically, the user takes a photo with their smartphone or camera and taps the "upload" button in the application. The output is the photo data saved on the device.

[1497] Step 2:

[1498] The device receives photo data uploaded by the user. The input is the photo data uploaded by the user. Specifically, the uploaded photos are saved in a temporary folder in the device's application. The output is the saved photo data.

[1499] Step 3:

[1500] The device sends the received photo data to the server. The input is the photo data saved in the temporary folder. The device's network module transfers the data to the server using an HTTP request. The output is the photo data sent to the server.

[1501] Step 4:

[1502] The server saves the received photo data in storage. The input is the photo data sent from the device. An example of software used is a cloud storage service such as AWS S3. The output is the photo data saved in storage.

[1503] Step 5:

[1504] The server performs preprocessing on the stored photo data. The input is the photo data stored in storage. Preprocessing includes image resizing, noise removal, color correction, etc. Specifically, the server performs preprocessing using an image processing library (e.g., OpenCV). The output is the preprocessed image data.

[1505] Step 6:

[1506] The server passes the preprocessed image data to the image recognition engine. The input is the preprocessed image data. The image recognition engine detects abnormal parts in the image and extracts features. Specifically, a machine learning model (e.g., TensorFlow or PyTorch model) is used. The output is the extracted features.

[1507] Step 7:

[1508] The server inputs the features sent from the image recognition engine into the AI ​​model to identify the type of plant disease or pest. The input is the extracted features. The AI ​​model analyzes the data using a neural network and outputs the results. The output is the type of disease or pest identified.

[1509] Step 8:

[1510] The server generates detailed diagnostic results based on the identified disease or pest type. The input is the identification result from the AI ​​model. Specifically, a template is used to create text information to display to the user as the diagnostic result. The output is text data of the diagnostic result.

[1511] Step 9:

[1512] Based on the diagnosis results, the server proposes specific countermeasures against diseases and pests. The input is the text data of the diagnosis results. For example, in the case of black spot disease, it will suggest "how to remove the infected area" and "how to use a specific fungicide." The specific operation involves retrieving appropriate information from a database of pre-set countermeasure information. The output is text data of specific countermeasures.

[1513] Step 10:

[1514] The server recommends relevant nutrients, fungicides, and insecticides based on the diagnosis results and countermeasures. The input is text data of the specific countermeasures. Specifically, it searches for product information from a database of products suitable for the countermeasures and generates a purchase link to an online shopping platform. The output is data on the recommended products and the purchase link.

[1515] Step 11:

[1516] The device uses an emotion engine to recognize the user's emotions. The input is sensor information collected through the camera and microphone. The emotion engine identifies the user's emotional state from their facial expressions and tone of voice. Specifically, it uses an emotion analysis algorithm. The output is the user's emotional data.

[1517] Step 12:

[1518] The device sends the recognized emotion data to the server. The input is the identified user emotion data. The device transfers the emotional state data to the server using an HTTP request. The output is the emotion data sent to the server.

[1519] Step 13:

[1520] The server provides the optimal response based on the user's emotions, based on the emotion data from the emotion engine. The input is the emotion data sent to the server. For example, if the user is feeling down, an encouraging message is added. The specific operation is to select and edit a template message based on the emotion data. The output is text data of the optimal response based on the emotion.

[1521] Step 14:

[1522] The server uses the emotional data to adjust the display content and order of recommended products. The input is the emotional data sent to the server. For example, if the user is in a hurry, products with immediate effects are displayed first. Specifically, the display order of products is rearranged based on the emotional data. The output is recommended product data that has been adjusted based on the emotion.

[1523] Step 15:

[1524] The server compiles the diagnosis results, countermeasures, emotion recognition results, recommended products, and purchase links and sends them to the terminal. The input is the adjusted recommended product data and various text data. Specifically, it compiles this data in HTML or JSON format and sends it to the terminal as an HTTP response. The output is the display data sent to the terminal.

[1525] Step 16:

[1526] The device receives the data sent from the server and displays it in a user-friendly way. The input is the display data sent from the server. Specific operations include using UI components to display the results in an application or web interface. The output is the diagnosis results, countermeasures, emotion recognition results, recommended products, and purchase links displayed to the user.

[1527] (Application example 2)

[1528] 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."

[1529] In modern plant cultivation and gardening, when plants are attacked by disease or pests, it is necessary to take prompt and appropriate measures. However, it is difficult for ordinary users to accurately identify plant diseases and pests and take appropriate measures. Furthermore, if users feel discouraged or impatient, it may affect their ability to resolve the problem if appropriate support is not provided. A system that can solve these issues is needed.

[1530] 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 uploading photos of plants taken by the user, means for transmitting the uploaded photo data to the server, means for passing the photo data received by the server to an image recognition engine and identifying the type of plant disease or pest, means for generating specific countermeasures for the plant disease or pest based on the identification results, means for providing necessary product recommendations and purchase links in addition to the countermeasures, means for transmitting the results to the user terminal and displaying them, means for collecting emotional data from the user's facial expressions and voice, means for analyzing the emotional data to identify the user's emotional state, and means for adjusting the display content of the countermeasures and recommended products based on the emotional state. This enables the user to quickly and accurately identify plant diseases and pests and take appropriate countermeasures, while also receiving appropriate emotional support.

[1531] A "user" is someone who takes photos of their plants and uses the system to diagnose diseases and pests, receive suggested treatments, and receive emotional support.

[1532] "Photo data" refers to image information of plants taken by users, and is data that is sent to the server and analyzed.

[1533] The "server" is a computer system that receives uploaded photo data, analyzes it using an image recognition engine, and generates diagnostic results, countermeasures, and information based on emotion analysis, which it then provides to users.

[1534] An "image recognition engine" is software or algorithm that analyzes received photo data and identifies types of plant diseases and pests.

[1535] "Countermeasures" refer to specific methods of dealing with plant diseases and pests that are proposed based on the diagnostic results.

[1536] "Recommendation" refers to presenting products suitable for the user based on diagnostic results and sentiment analysis.

[1537] "Purchase Link" means a web link that enables a User to purchase a Recommended Product online.

[1538] "User Device" means a smartphone, tablet, or other electronic device used by a User.

[1539] "Facial expression" refers to the movement and position of the user's face, and is used as data for emotion analysis.

[1540] "Voice" refers to the words and voices spoken by the user and is used as data for emotion analysis.

[1541] "Emotional data" refers to data that indicates the emotional state identified by analyzing a user's facial expressions and voice.

[1542] "Emotional state" refers to the user's current emotions, as determined as a result of emotion analysis.

[1543] The present invention combines an emotion engine with a system that analyzes photos of plants taken by users, identifies plant diseases and pests, and recommends specific countermeasures and necessary products based on the results. Specific embodiments of the present invention are described in detail below.

[1544] 1. Upload and send photos

[1545] Users can take photos of plants using their smart devices and upload them via the app or web interface, which then sends the photos to the server.

[1546] 2. Photo data is received and analyzed by the server

[1547] The server stores the photo data received from the device in storage, then performs image preprocessing (e.g., resizing, noise removal, color correction, etc.), and inputs the preprocessed image data into the image recognition engine.

[1548] 3. Disease and pest identification

[1549] The image recognition engine detects abnormalities in the photo and extracts features. The AI ​​model then analyzes the features to identify the type of plant disease or pest, such as black spot or aphids.

[1550] 4. Proposal of countermeasures

[1551] Based on the identification results, the server generates specific countermeasures for plant diseases and pests, such as removing the infected area and applying a specific fungicide in the case of black spot.

[1552] 5. Recommend related products and generate purchase links

[1553] Based on the diagnosis and countermeasures, the server then searches its database for relevant products, such as suitable nutrients, fungicides, and insecticides, and recommends them to the user, including a link to an online shopping platform for purchase.

[1554] 6. Emotion recognition using emotion engine

[1555] The emotion engine analyzes the user's facial expressions, voice, and behavioral patterns to identify their emotional state. Emotional data is collected through sensors such as cameras and microphones.

[1556] 7. Emotion-based response optimization

[1557] The server uses the emotion data from the emotion engine to provide the optimal response based on the user's emotions. For example, if the user is feeling down, it will provide a more encouraging message.

[1558] 8. Tailoring product recommendations based on emotions

[1559] The server uses emotional data to adjust the content and order of recommended products. For example, if the user is in a hurry, products with immediate effects will be displayed first.

[1560] 9. Sending and displaying results

[1561] The server compiles the diagnosis results, countermeasures, emotion recognition results, recommended products, and purchase links and sends them to the user's device. The user's device receives this data and displays it in an easy-to-understand manner. Specifically, along with the diagnosis results, the data includes an explanation such as "Your plant is suffering from black spot disease. The following measures are necessary to treat this disease," an encouraging message based on emotion, an image of the recommended product, and a purchase link.

[1562] Specific examples

[1563] Suppose a user finds black spots on a rose leaf and uploads a photo of the leaf. The device sends the photo to a server, which uses an image recognition engine and an AI model to identify it as black spot disease. The diagnosis results are displayed as follows: "The black spots found on the rose leaf are black spot disease. It is recommended that you remove the infected area and use a specific fungicide." In addition, the emotion engine recognizes from the user's facial expression that he or she looks worried, and prioritizes displaying encouraging messages such as "Don't worry, early intervention is likely to lead to recovery" and links to purchase fast-acting fungicides.

[1564] Example prompt for a generative AI model:

[1565] "I noticed black spots on the leaves of my roses. Explain to the concerned user how to treat black spot and what fungicide to buy. Include a message of encouragement."

[1566] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1567] Step 1:

[1568] The user takes a photo of a plant using a smart device. The input is the plant photo data, and the output is the photo stored on the device. This photo data is the basis for subsequent processing.

[1569] Step 2:

[1570] The user uploads plant photo data to the server through the application or web interface. The input is the photo data taken by the user, and the output is the photo data sent to the server. Specifically, the user presses the "upload" button in the application to send the photo data.

[1571] Step 3:

[1572] The server stores the received photo data in storage and performs image preprocessing. The input is the photo data sent to the server, and the output is the preprocessed image data. Specific operations include resizing, noise removal, and color correction.

[1573] Step 4:

[1574] The server passes the preprocessed image data to an image recognition engine to identify the type of plant disease or pest. The input is the preprocessed image data, and the output is data with extracted features. The image recognition engine detects abnormal areas and extracts features.

[1575] Step 5:

[1576] The AI ​​model analyzes the extracted features to identify the type of plant disease or pest. The input is the data from which the features have been extracted, and the output is information that identifies the type of disease or pest. Specifically, the AI ​​model identifies black spot disease, aphids, etc.

[1577] Step 6:

[1578] Based on the identification results, the server generates specific countermeasures for plant diseases and pests. The input is information that identifies the type of disease or pest, and the output is a list of specific countermeasures. For example, in the case of black spot disease, it is recommended to remove the infected area and use a specific fungicide.

[1579] Step 7:

[1580] Based on the diagnosis results and solutions, the server searches the database for relevant products and recommends them to the user. The input is a list of specific solutions, and the output is a list of recommended products and a purchase link. Specifically, a link to an online shopping platform is provided.

[1581] Step 8:

[1582] The server collects the user's facial expressions and voice using a camera and microphone to obtain emotion data. The input is the user's facial expressions and voice, and the output is data that identifies the user's emotional state. The collected emotion data is passed to the emotion engine.

[1583] Step 9:

[1584] The emotion engine analyzes the emotion data and identifies the user's emotional state. The input is the user's facial expression and voice data, and the output is the user's emotional state. Specifically, the emotion engine identifies the emotional state as "worry" or "anxiety," etc.

[1585] Step 10:

[1586] The server adjusts the displayed content of solutions and recommended products based on the user's emotional state. The input is the user's emotional state and the information generated in the previous step, and the output is optimized solutions and product lists. For example, if the user is worried, an encouraging message is provided.

[1587] Step 11:

[1588] The server compiles the diagnosis results, countermeasures, emotion recognition results, recommended products, and purchase links and sends them to the user's device. The input is the optimized countermeasures and product list, and the output is the information displayed on the user's device. Specifically, the diagnosis results, countermeasures, recommended products, and encouraging messages are displayed on the user's device.

[1589] Step 12:

[1590] The user's device displays the data received from the server in an easy-to-understand manner. The input is the data sent from the server, and the output is the diagnostic results and countermeasure information displayed to the user. Based on the displayed information, the user can take countermeasures against plant diseases and pests and purchase related products.

[1591] 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.

[1592] 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.

[1593] 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.

[1594] 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.

[1595] 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.

[1596] 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.

[1597] 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).

[1598] 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.

[1599] 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."

[1600] 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.

[1601] 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).

[1602] 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.

[1603] 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.

[1604] 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.

[1605] 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.

[1606] 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.

[1607] 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.

[1608] 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.

[1609] 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.

[1610] 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 say...

Claims

1. A means for users to upload photos of plants they have taken; means for transmitting the uploaded photo data to a server; The server passes the received photo data to an image recognition engine to identify the type of plant disease or pest. a means for generating specific countermeasures against plant diseases and pests based on the identification results; A means to provide necessary product recommendations and purchase links in addition to countermeasures, A means to send and display the results on the user's device A system including:

2. The system according to claim 1 , wherein the image recognition engine further comprises means for detecting an abnormal portion in the photograph and extracting a feature amount.

3. The system of claim 1 , wherein the AI ​​model further comprises means for analyzing the features and identifying the type of disease or pest.

Images