system

Abstract

To provide a system that effectively supports pesticide-free cultivation. [Solution] A system including: means for collecting data on pesticide-free cultivation; means for having a generative artificial intelligence learn know-how on pesticide-free cultivation based on the data on pesticide-free cultivation; means for saving and updating a model as a result of the learning; means for collecting crop condition data using a sensing device; means for analyzing the crop condition data and generating a diagnostic result; means for providing advice on pesticide-free cultivation based on the diagnostic result; means for transmitting the advice and diagnostic result and communicating with farmers; and means for receiving feedback from farmers and reflecting it in the model.

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] Pesticide-free cultivation is a method that is kind to the environment and consumer health, but it requires the right know-how, timing, and measures, making it difficult for traditional farmers. Specialist knowledge is required, particularly in the use of organic fertilizers and pest prevention measures, and a system that can provide this information quickly and accurately is needed. There is also a need for a system that can monitor the condition of crops in real time and provide appropriate advice and reminders based on that information. [Means for solving the problem]

[0005] The present invention provides the information and timing necessary for pesticide-free cultivation through a system including: means for collecting data on pesticide-free cultivation; means for training a generative artificial intelligence (AI) to learn know-how about pesticide-free cultivation based on the data on pesticide-free cultivation; means for saving and updating a model resulting from the learning; means for collecting crop condition data using a sensing device; means for analyzing the crop condition data and generating a diagnosis; means for providing advice on pesticide-free cultivation based on the diagnosis; means for transmitting the advice and diagnosis and communicating with farmers; and means for receiving feedback from farmers and reflecting it in the model. The system further includes means for generating optimal answers to farmers' questions using generative AI and transmitting them to the farmers, and means for monitoring crop condition data in real time using a sensing device, generating reminders and additional advice based on the monitoring data, and transmitting them to the farmers, thereby effectively supporting pesticide-free cultivation.

[0006] "Pesticide-free cultivation" is a method of growing crops without using chemical pesticides.

[0007] "Data collection means" refers to a method, device, or system for collecting specific information.

[0008] "Generative artificial intelligence" refers to algorithms or systems that learn information from large amounts of data and generate intelligent answers for specific tasks.

[0009] "Know-how" means practical knowledge and skills in a particular field.

[0010] A "model" refers to a computational or predictive framework built on specific data and algorithms.

[0011] "Preservation" means storing data or information safely and making it available for reuse as needed.

[0012] "Update" means replacing existing data or information with new content or parameters.

[0013] A "sensing device" refers to a device that detects the surrounding environment or the state of an object and acquires that data.

[0014] "Analysis" is the process of extracting information from collected data and making evaluations and diagnoses.

[0015] "Diagnosis results" refer to the conclusions and evaluation results obtained through analysis.

[0016] "Advice providing means" refers to a method or device that recommends appropriate actions or measures based on the diagnostic results obtained.

[0017] "Communication means" refers to methods and devices for sending and receiving information.

[0018] "Feedback" refers to opinions and result information returned by users of the system.

[0019] "Reminder" refers to a function that notifies you of the time and content of a specific action or measure.

[0020] "Monitoring" means continuously observing a particular condition or environment and collecting data. [Brief explanation of the drawings]

[0021] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 11] FIG. 3 is a sequence diagram showing a processing flow of the data processing system according to the first embodiment. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0022] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

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

[0024] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), and an APU (Accelerated Processing Unit).

[0025] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

[0026] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0027] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0028] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0029] [First embodiment]

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

[0031] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0032] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0033] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0034] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0035] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0036] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

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

[0038] 2, in the data processing device 12, a specific process is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0039] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0040] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with the specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0041] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0042] The system of the present invention includes a method and an apparatus for effectively supporting pesticide-free cultivation. A specific embodiment will be described below, focusing on a server, a terminal, and a user (agricultural worker).

[0043] Data collection and learning

[0044] server

[0045] The server collects a large amount of data related to pesticide-free farming from the internet and existing databases, including types of organic fertilizer and their application methods, pest and disease ecology, and climate data.

[0046] The server cleanses the collected data, removing noise and missing data. It then normalizes the data and trains it using generative AI. Specifically, the data is formatted in a way that makes it easy for the AI ​​model to understand, and it learns the know-how of pesticide-free farming.

[0047] The model generated as a result of learning is stored on the server and updated as necessary.

[0048] Crop condition diagnosis

[0049] Terminal

[0050] Sensing devices (e.g., e-kakashi) connected to the terminal periodically collect data such as soil quality, temperature, humidity, and light intensity.

[0051] The collected data is transmitted from the terminal to a server.

[0052] server

[0053] The server receives the data sent from the device and analyzes it using generative artificial intelligence. The purpose of the analysis is to diagnose the current condition of the crops and derive the necessary countermeasures.

[0054] Based on the analysis results, appropriate advice and reminders are generated. For example, if the soil pH level is outside the appropriate range, advice on the timing and amount of organic fertilizer to be used is generated.

[0055] Communication with farmers

[0056] server

[0057] The server sends the generated advice and diagnostic results to the terminal.

[0058] It also accepts feedback and questions from farmers and generates optimal answers, which are then sent to the device.

[0059] Terminal

[0060] The terminal notifies the farmer of advice and diagnostic results sent from the server, for example by providing appropriate information via an alert or display panel.

[0061] Farmers can also use their devices to input questions to the generative AI, which are then sent to the server.

[0062] User (farmer)

[0063] Farmers can then use the advice they receive through the device to carry out their farming work, such as applying appropriate organic fertilizers or taking measures to prevent specific pests and diseases.

[0064] The results of the advice and any feedback felt are entered into the device and sent to the server.

[0065] Cultivation management

[0066] Terminal

[0067] The terminal continuously monitors the condition of the crops through a sensing device, and the collected data is sent to a server in real time.

[0068] server

[0069] The server analyzes changes in the cultivation environment based on the received data and generates necessary reminders and additional advice, such as "Low temperatures are predicted this week, so please take measures to prevent frost."

[0070] Any generated reminders or additional advice will also be sent to the farmer via the device.

[0071] Specific examples

[0072] Examples of organic fertilizer use

[0073] 1. The device uses e-kakashi to measure the soil's pH level, humidity, and temperature, and sends the data to the server.

[0074] 2. The server analyzes the received data using generative artificial intelligence and generates advice on the appropriate timing and amount of organic fertilizer to use based on the condition of the soil.

[0075] 3. The server sends the generated advice to the terminal and notifies the farmer.

[0076] 4. The user (farmer) applies organic fertilizer based on the advice and observes the results.

[0077] 5. The terminal measures the observation results again using the sensing device and sends the data to the server.

[0078] 6. The server analyzes the new data and generates additional advice if necessary, and notifies the farmer via the terminal.

[0079] Examples of pest prevention

[0080] 1. The server trains the generative AI to learn about the ecology of pests and diseases and preventive measures.

[0081] 2. The device uses e-kakashi to collect data on the crops and their surrounding environment and transmits it to the server.

[0082] 3. The server analyzes the received data using generative artificial intelligence and generates advice on risk assessments of pest and disease outbreaks and preventive measures.

[0083] 4. The server sends the generated advice to the terminal and notifies the farmer.

[0084] 5. The user (farmer) implements preventive measures based on the advice and observes the results.

[0085] 6. The device measures the observations and sends them to the server.

[0086] 7. The server continuously analyzes the data, generates new advice, and notifies the farmer via his / her terminal.

[0087] As described above, this system enables farmers to accurately grasp the know-how and timing required for pesticide-free cultivation and then put it into practice.

[0088] The processing flow will be explained below.

[0089] Examples of organic fertilizer use

[0090] Step 1:

[0091] The device uses e-kakashi to measure the soil's pH level, humidity, and temperature, and then sends the data to the server.

[0092] Step 2:

[0093] The server refers to the contents of the database based on the data received and preprocesses the data, specifically removing outliers and normalizing the data.

[0094] Step 3:

[0095] The server uses generative artificial intelligence to analyze the pre-processed data and generate information on the current state of the crops and the appropriate use of organic fertilizer.

[0096] Step 4:

[0097] Based on the analysis results, the server generates advice including the appropriate timing and amount of organic fertilizer to use and sends that advice to the terminal.

[0098] Step 5:

[0099] The terminal notifies the farmer of the advice sent from the server, for example by displaying the information via an alert or a display panel.

[0100] Step 6:

[0101] The user (farmer) applies organic fertilizer based on the advice, observes the results, and enters the observation results into the terminal.

[0102] Step 7:

[0103] The device collects the observations and sends the data to a server.

[0104] Step 8:

[0105] The server analyzes the observation data and suggests new advice or adjustments as needed, for example determining whether soil conditions have improved and suggesting further preventative measures or additional fertilization.

[0106] Examples of pest prevention

[0107] Step 1:

[0108] The server trains the generative AI with data on pests and diseases, including their ecology, preventative measures, and their relationship with climate.

[0109] Step 2:

[0110] The terminal uses e-kakashi to collect data on the condition of the crops and the surrounding environment (temperature, humidity, air temperature, etc.) and send it to the server.

[0111] Step 3:

[0112] The server preprocesses the received data, removing outliers and normalizing the data.

[0113] Step 4:

[0114] The server analyzes the preprocessed data using generative artificial intelligence to generate risk assessments and preventative measures for pest and disease outbreaks.

[0115] Step 5:

[0116] The server generates advice including preventive measures based on the risk assessment and transmits the advice to the terminal.

[0117] Step 6:

[0118] The terminal notifies the farmer of the advice sent from the server, for example by providing information using a display panel or alerts.

[0119] Step 7:

[0120] The user (farmer) implements preventive measures based on the advice received, for example, installing moth nets or spraying natural pesticides.

[0121] Step 8:

[0122] The device monitors the results again through e-kakashi and sends the data to the server.

[0123] Step 9:

[0124] The server analyzes the monitoring data and evaluates the effectiveness of preventive measures, generating additional measures and reminders as needed and sending notifications via the device.

[0125] Through the above processing steps, the present invention effectively supports pesticide-free cultivation, enabling farmers to accurately grasp and implement the necessary know-how and timing.

[0126] Example 1

[0127] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0128] Practicing pesticide-free cultivation in the agricultural field is extremely delicate and complex. To successfully cultivate crops without pesticides, it is necessary to use organic fertilizer at the appropriate time, prevent pests and diseases, and constantly monitor the condition of the crops. However, acquiring the knowledge and skills necessary to achieve this requires a great deal of effort and time. For this reason, there is a need for a support system to help farmers cultivate crops without pesticides effectively.

[0129] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0130] In this invention, the server includes a means for collecting data on pesticide-free cultivation, a means for training the artificial intelligence to learn know-how on pesticide-free cultivation based on the data on pesticide-free cultivation, and a means for saving and updating the model as a result of the learning, thereby making it possible to provide optimal advice and diagnostic results on pesticide-free cultivation.

[0131] "Data on pesticide-free cultivation" refers to information related to the knowledge and techniques required to carry out pesticide-free cultivation, including types of organic fertilizers and how to use them, the ecology of pests and diseases, and climate data.

[0132] "Generative AI" refers to AI that uses technologies such as machine learning and deep learning to analyze data and automatically generate and learn knowledge for specific purposes.

[0133] "Sensing device" refers to a measuring device used to measure parameters of the crop environment, such as soil quality, temperature, humidity, and light intensity.

[0134] "Plant condition data" refers to data that includes information about crops and their surrounding environment, such as soil quality, temperature, humidity, and light intensity.

[0135] "Diagnosis results" refers to information about the health of agricultural crops and necessary measures obtained by analyzing collected plant condition data.

[0136] "Advice" refers to specific instructions and suggestions for farmers to successfully cultivate crops without pesticides, based on the diagnostic results generated.

[0137] "Users" refers to agricultural workers and those involved in agriculture who practice pesticide-free cultivation.

[0138] "Feedback" refers to information provided by the user regarding the evaluation of the system's advice and diagnostic results and the execution results.

[0139] "Model" refers to a computational model that incorporates know-how for pesticide-free cultivation using generative artificial intelligence that learns from collected data.

[0140] "Real-time monitoring" refers to continuously observing plant condition data using sensing devices and immediately processing the results.

[0141] A "reminder" is information that notifies a user of the timing and precautions to take when taking a specific action.

[0142] "Additional advice" refers to new instructions or suggestions generated based on real-time monitoring data.

[0143] The system of this invention includes a method and an apparatus for collecting data, analyzing it, and providing advice to support pesticide-free cultivation. A specific embodiment will be described, focusing on a server, a terminal, and a user (agricultural worker).

[0144] Data collection and learning

[0145] server

[0146] The server collects data related to pesticide-free farming from the Internet and existing databases. This data includes types of organic fertilizers, application methods, pest and disease ecology, and climate data. As a specific example, the Open Weather Map API can be used to collect weather data.

[0147] The collected data is cleansed to remove noise and missing data, then normalized and trained using a generative artificial intelligence (AI) model (using, for example, Tensorflow or PyTorch) to learn the know-how of pesticide-free farming.

[0148] The resulting AI model is stored on a server and regularly updated. This model is used to provide knowledge and optimal strategies for pesticide-free farming.

[0149] Crop condition diagnosis

[0150] Terminal

[0151] Sensing devices (e.g., e-kakashi) connected to the terminal periodically collect data on soil quality, temperature, humidity, light intensity, etc. This allows for a detailed understanding of the conditions of crops and their environment.

[0152] The collected data is sent to a server via Wi-Fi or mobile communications.

[0153] server

[0154] The server uses generative artificial intelligence to analyze the data it receives, specifically data on soil pH levels, temperature, and humidity, to diagnose the current condition of the crops.

[0155] Based on the analysis results, advice on pesticide-free cultivation is generated. For example, if the soil pH level is outside the appropriate range, advice is provided on the appropriate timing and amount of organic fertilizer to be used.

[0156] Communication with farmers

[0157] server

[0158] The server sends the generated advice and diagnostic results to the device, possibly in the form of push notification or email.

[0159] It also accepts feedback and questions from farmers and generates optimal answers based on that information. For example, it uses generative artificial intelligence to create optimal answers to users' questions.

[0160] Terminal

[0161] The terminal notifies the user of advice and diagnostic results sent from the server, allowing the user to receive appropriate information on pesticide-free farming in a timely manner.

[0162] Additionally, users can use their terminals to input questions into the system, which are then sent to the server.

[0163] User (farmer)

[0164] Farmers can then carry out agricultural work based on the advice they receive through the device, such as applying appropriate organic fertilizer or taking measures to prevent specific pests and diseases.

[0165] By inputting the results of the execution and feedback into the device and sending it to the server, the system continues to learn and provides more accurate advice.

[0166] Cultivation management

[0167] Terminal

[0168] The terminal continuously monitors the condition of the crops through a sensing device, and the collected data is sent to a server in real time.

[0169] server

[0170] The server analyzes changes in the cultivation environment based on the received data and generates necessary reminders and additional advice, such as "Low temperatures are predicted this week, so please take measures to prevent frost."

[0171] Specific examples

[0172] Examples of organic fertilizer use

[0173] 1. Using a sensing device (e-kakashi) connected to a terminal, the pH level, humidity, and temperature of the soil are measured and the data is sent to the server.

[0174] 2. The server analyzes the received data using generative artificial intelligence and generates advice on the appropriate timing and amount of organic fertilizer to use based on the condition of the soil.

[0175] 3. The server sends the generated advice to the terminal and notifies the farmer.

[0176] 4. The user (farmer) applies organic fertilizer based on the advice received through the terminal and observes the results.

[0177] 5. The terminal measures the observation results again using the sensing device and sends the data to the server.

[0178] 6. The server analyzes the new data and generates additional advice if necessary, and notifies the farmer via the terminal.

[0179] Examples of pest prevention

[0180] 1. The server trains the generative AI to learn about the ecology of pests and diseases and preventive measures.

[0181] 2. The terminal uses a sensing device (e-kakashi) to collect data on the crops and their surrounding environment and transmits it to the server.

[0182] 3. The server analyzes the received data using generative artificial intelligence and generates advice on risk assessments of pest and disease outbreaks and preventive measures.

[0183] 4. The server sends the generated advice to the terminal and notifies the farmer.

[0184] 5. The user (farmer) implements preventive measures based on the advice and observes the results.

[0185] 6. The device measures the observations and sends them to the server.

[0186] 7. The server continuously analyzes the data, generates new advice, and notifies the farmer via his / her terminal.

[0187] Prompt Sentence Examples

[0188] 1. What is the appropriate time and amount to use organic fertilizer?

[0189] 2. What measures are necessary to prevent pests and diseases?

[0190] As described above, the system of the present invention effectively supports farmers in accurately grasping the knowledge and timing necessary for pesticide-free cultivation and putting it into practice.

[0191] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0192] Step 1:

[0193] Data collection

[0194] The server collects data on organic farming from sources including the internet and existing databases, including types of organic fertilizers and their application methods, pest and disease ecology, and climate data.

[0195] Input: Raw data from the internet and existing databases.

[0196] Output: Data related to pesticide-free cultivation before cleansing.

[0197] What it does: The server collects data using APIs and web scraping and stores it in a local database.

[0198] Step 2:

[0199] Data Cleansing

[0200] The server cleanses the collected data, removing noise and missing data, thereby improving the quality of the data.

[0201] Input: Raw data collected.

[0202] Output: Clean, cleansed data.

[0203] What it does: The server runs algorithms to detect outliers and impute missing values, for example filtering out abnormal pH values, temperatures, etc.

[0204] Step 3:

[0205] Data normalization

[0206] The server normalizes the cleansed data and puts it into a format that is easy for the generative AI model to understand.

[0207] Input: Cleansed data.

[0208] Output: Normalized data.

[0209] Specific operation: The server performs data scaling and normalization to convert numeric data into a certain range.

[0210] Step 4:

[0211] Model learning

[0212] The server uses the normalized data to train a generative AI model (using TensorFlow or PyTorch).

[0213] Input: Normalized data.

[0214] Output: The trained model.

[0215] Specific operation: The server applies a machine learning algorithm to teach the model know-how regarding pesticide-free cultivation.

[0216] Step 5:

[0217] Save Model

[0218] The server stores the trained model and updates it as needed.

[0219] Input: A trained model.

[0220] Output: The saved model.

[0221] Specific operation: The server saves the trained model in a database and sets a schedule for periodic retraining.

[0222] Step 6:

[0223] Sensing

[0224] A sensing device (e.g., e-kakashi) connected to the terminal periodically collects data such as soil quality, temperature, humidity, and light intensity.

[0225] Input: Environmental data (temperature, humidity, light level, etc.).

[0226] Output: Collected environmental data.

[0227] Specific operation: The device periodically reads data from the sensors and temporarily stores it in local storage.

[0228] Step 7:

[0229] Data transmission

[0230] The device sends the collected data to a server via Wi-Fi or mobile communications.

[0231] Input: Collected environmental data.

[0232] Output: The data sent to the server.

[0233] Specific operation: The terminal transmits data to the server via the network in real time or in batch processing.

[0234] Step 8:

[0235] Data reception

[0236] The server receives the data sent from the terminal.

[0237] Input: Data sent from the terminal.

[0238] Output: The received data.

[0239] Specific operation: The server immediately stores the received data in a database and prepares it for analysis.

[0240] Step 9:

[0241] Data analysis

[0242] The server analyzes the received data using a generative AI model to diagnose the current condition of the crops.

[0243] Input: Received data, trained model.

[0244] Output: Diagnostic results.

[0245] Specific operation: The server inputs data into the generative AI model and analyzes the health of the crops and necessary measures.

[0246] Step 10:

[0247] Advice Generation

[0248] Based on the analysis results, the server generates advice and reminders on pesticide-free farming.

[0249] Input: Diagnostic results.

[0250] Output: Advice and reminders.

[0251] Specific actions: The server automatically generates a sentence that suggests appropriate measures and instructions for action.

[0252] Step 11:

[0253] Send Advice

[0254] The server transmits the generated advice to the terminal.

[0255] Input: Advice and reminders.

[0256] Output: Advice sent to the terminal.

[0257] Specific behavior: The server sends the advice using a messaging protocol.

[0258] Step 12:

[0259] Receive feedback

[0260] The server accepts feedback and questions from users via the terminal.

[0261] Input: User feedback and questions.

[0262] Output: Feedback and questions received.

[0263] Specific operation: The device sends questions and feedback entered by the user to the server.

[0264] Step 13:

[0265] Optimal response generation

[0266] The server uses a generative AI model to generate optimal responses to the feedback and questions it receives.

[0267] Input: Feedback, questions, trained models.

[0268] Output: Best response.

[0269] Specific operation: The server inputs feedback and questions into the generative AI model to generate optimal answers and improvements.

[0270] Step 14:

[0271] Response Send

[0272] The server generates a response and sends it to the terminal.

[0273] Input: Best response.

[0274] Output: The response sent to the terminal.

[0275] Specific operation: The server sends a response to the terminal via a messaging protocol.

[0276] Step 15:

[0277] monitoring

[0278] The terminal monitors the condition of the plants in real time through sensing devices.

[0279] Input: Real-time data from sensing devices.

[0280] Output: Monitored data.

[0281] Specific operation: The terminal continuously collects data and transmits it to the server in real time.

[0282] Step 16:

[0283] Additional advice generation

[0284] The server analyzes the received monitoring data and generates additional advice and reminders as needed.

[0285] Input: Real-time monitoring data.

[0286] Output: Additional advice and reminders.

[0287] Specific operation: The server has the generative AI model further analyze the data and generate additional feedback.

[0288] Step 17:

[0289] Send additional advice

[0290] The server sends the generated additional advice to the terminal.

[0291] Input: Additional advice or reminders.

[0292] Output: Additional advice sent to the terminal.

[0293] Specific behavior: The server sends additional advice via the messaging protocol.

[0294] Through these steps, the system supports farmers in effectively implementing pesticide-free cultivation.

[0295] (Application example 1)

[0296] 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."

[0297] In pesticide-free farming, it is extremely important to acquire the know-how for proper farming practices and carry them out efficiently and effectively. However, traditional methods are prone to time lags in data collection and delayed feedback, making it difficult to obtain real-time advice. Furthermore, in the food delivery industry, there is no established method for safely and quickly delivering pesticide-free produce. Highly accurate data collection and analysis, as well as real-time information provision, are essential to resolving these issues.

[0298] 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.

[0299] In this invention, the server includes a means for collecting data on pesticide-free farming, a means for training generative AI to learn pesticide-free farming know-how, and a means for saving and updating the model resulting from the learning. This allows farmers to receive pesticide-free farming advice in real time and perform appropriate farm work. This invention also includes a means for collecting data on food delivery and a means for providing delivery routes and specific instructions. This allows for the safe and prompt delivery of pesticide-free agricultural products. Furthermore, since information is provided in real time via a head-mounted display, delivery personnel can always act based on the latest information.

[0300] "Pesticide-free cultivation" is an agricultural method that uses natural methods to prevent pests and diseases when growing crops without using chemical pesticides, and is gentle on the environment and the human body.

[0301] "Generative AI" is an AI system that analyzes large amounts of data, automatically learns patterns, and generates predictions and optimal advice.

[0302] "Know-how" is a general term for the specific techniques, knowledge, and experience required for pesticide-free cultivation.

[0303] A "model" is a mathematical or statistical representation that serves as the basis for data analysis and prediction, generated as a result of training generative artificial intelligence.

[0304] A "sensing device" is a device for measuring and collecting environmental data such as temperature, humidity, and light intensity.

[0305] "Diagnosis results" are information about the condition of crops and necessary measures generated after analyzing collected data.

[0306] "Advice" refers to specific instructions or recommendations for farmers that are generated based on the diagnostic results.

[0307] "Communication means" refers to the technical means for transmitting and receiving data between the server and the farmer's terminal.

[0308] "Feedback" refers to the results of implementing advice, as well as opinions and questions, sent by farmers to the server.

[0309] "Delivery" refers to the process of delivering pesticide-free agricultural products to consumers.

[0310] A "head-mounted display" is a display device worn on the head to display information within the field of view.

[0311] "Real-time information provision" refers to providing the analysis results of sensing devices and servers to users immediately and without delay.

[0312] This invention provides a system that realizes efficient pesticide-free cultivation and safe food delivery. This system consists of a server, terminals (including sensing devices), and users (farmers and delivery personnel).

[0313] 1. Program processing overview

[0314] server

[0315] The server collects data on pesticide-free farming and uses it to train the generative AI on the know-how of pesticide-free farming. This data includes the types of organic fertilizers and their use, the ecology of pests and diseases, and climate data. The server cleanses the collected data, removing noise and missing data. The data is then normalized and trained by the generative AI. The model generated as a result of the learning is stored on the server and updated as necessary.

[0316] Terminal

[0317] Sensing devices connected to the terminal (e.g., soil sensors and temperature / humidity sensors) periodically collect data on soil quality, temperature, humidity, light intensity, etc. The collected data is sent from the terminal to a server. The server receives the data sent from the terminal and analyzes it using generative artificial intelligence. Based on the analysis results, advice and reminders regarding pesticide-free cultivation are generated. For example, if the soil's pH level is outside the appropriate range, advice on the appropriate timing and amount of organic fertilizer to be used is generated.

[0318] User (farmer)

[0319] Farmers perform farm work based on the advice they receive through the device. For example, they may apply appropriate organic fertilizer or take measures to prevent specific pests and diseases. The results of implementing the advice and feedback they feel are entered into the device and sent to a server. Furthermore, the device monitors the condition of the crops through a sensing device and continuously sends data to the server in real time.

[0320] 2. Food delivery support

[0321] The system also has a support function to help food delivery workers deliver pesticide-free produce safely and effectively. The server collects data on food deliveries and provides optimal delivery routes and handling methods. Delivery workers can receive advice in real time using a head-mounted display.

[0322] Hardware and Software Use Cases

[0323] Hardware: Head-mounted display (e.g., Microsoft® HoloLens®), soil sensor, temperature and humidity sensor

[0324] Software: Python, Server API (e.g. "https: / / agriculture-data-source.com / api / getData")

[0325] 3. Adding concrete examples

[0326] Specific work examples

[0327] 1. The server collects data on pesticide-free farming through the API.

[0328] 2. Based on the collected data, generative AI learns the know-how of pesticide-free cultivation.

[0329] 3. The model generated as a result of learning is saved on the server.

[0330] 4. Farmers use sensing devices to measure soil quality, temperature, humidity, light intensity, etc., and send the data from their terminals to a server.

[0331] 5. The server performs the analysis and generates appropriate advice.

[0332] 6. Delivery personnel will wear head-mounted displays and be provided with real-time information on appropriate delivery routes and handling methods.

[0333] Prompt Sentence Examples

[0334] "The temperature is low today, so please take precautions against the cold."

[0335] "Your soil pH is dropping. Add organic fertilizer."

[0336] By using the above method, this invention enables pesticide-free cultivation and its delivery to be carried out efficiently and effectively.

[0337] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0338] Step 1:

[0339] Data collection

[0340] The server collects data on pesticide-free farming. Specifically, it obtains information on the types and use of organic fertilizers, the ecology of pests and diseases, and climate data from the Internet and existing databases. The input is a list of data to be collected, and the output is a file of the collected data.

[0341] Step 2:

[0342] Data Cleansing and Normalization

[0343] The server cleanses the collected data, removing noise and missing data. Then, it normalizes the data and formats it in a way that makes it easier for generative AI to learn. The input is the collected data file, and the output is the cleansed, normalized data.

[0344] Step 3:

[0345] Learning with generative artificial intelligence

[0346] The server uses the normalized data to train the generative AI to learn the know-how of pesticide-free cultivation. Specifically, the normalized data is input into the AI ​​model and learning is repeated. The input is the normalized data, and the output is the trained model.

[0347] Step 4:

[0348] Saving a trained model

[0349] The server saves the generated trained model and updates it as necessary. The input is the trained model, and the output is the saved model data. Specifically, the model is stored in a database within the server.

[0350] Step 5:

[0351] Data collection using sensing devices

[0352] Sensing devices (e.g., soil sensors, temperature and humidity sensors) connected to the terminal periodically collect data on soil quality, temperature, humidity, light intensity, etc. The input is the environmental data collected by the sensor, and the output is the measurement data sent to the terminal.

[0353] Step 6:

[0354] Sending data to the server

[0355] The terminal transmits the collected data to the server in real time. The input is the measurement data, and the output is the data transmitted to the server.

[0356] Step 7:

[0357] Data analysis and generation of diagnostic results

[0358] The server receives the data sent from the terminal and analyzes it using generative artificial intelligence. Specifically, it uses a data analysis algorithm to diagnose the condition of the crops and generate the results. The input is the sent data and the output is the diagnosis result.

[0359] Step 8:

[0360] Generating Advice

[0361] The server generates advice on pesticide-free farming based on the diagnostic results. For example, if the soil pH is outside the appropriate range, it will suggest the appropriate timing and amount of organic fertilizer to use. The input is the diagnostic results, and the output is advice.

[0362] Step 9:

[0363] Advice and notification of diagnostic results

[0364] The server sends the generated advice and diagnosis results to the terminal and notifies the farmer. The input is advice and diagnosis results, and the output is notification data sent to the terminal.

[0365] Step 10:

[0366] Gathering and implementing feedback

[0367] Farmers perform farm work based on the advice received through their devices, and input the results and feedback into the device and send it to the server. The server receives this feedback and reflects it in the model. The input is the feedback data, and the output is updated model data.

[0368] Step 11:

[0369] Providing delivery routes and specific instructions

[0370] The server collects data about food delivery and provides optimal delivery routes and handling methods. The input is delivery data, and the output is instructions and route data.

[0371] Step 12:

[0372] Real-time information provision

[0373] The delivery person wears a head-mounted display and receives advice and route information in real time from the server. The input is instructions and route data, and the output is information displayed on the head-mounted display.

[0374] 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.

[0375] The system of this invention includes a method and device for effectively supporting pesticide-free farming, and in particular, combines an emotion engine that recognizes the user's emotions and adjusts the content and timing of advice based on those emotions. A specific embodiment will be described below, focusing on a server, a terminal, and a user (agricultural worker).

[0376] Data collection and learning

[0377] server

[0378] The server collects a large amount of data related to pesticide-free farming from the internet and existing databases, including types of organic fertilizer and their application methods, pest and disease ecology, and climate data.

[0379] The server cleanses the collected data, removing noise and missing data. It then normalizes the data and trains it using generative AI. Specifically, the data is formatted in a way that makes it easy for the AI ​​model to understand, and it learns the know-how of pesticide-free farming.

[0380] The model generated as a result of learning is stored on the server and updated as necessary.

[0381] Crop condition diagnosis

[0382] Terminal

[0383] Sensing devices (e.g., e-kakashi) connected to the terminal periodically collect data such as soil quality, temperature, humidity, and light intensity.

[0384] The collected data is transmitted from the terminal to a server.

[0385] server

[0386] The server receives the data sent from the device and analyzes it using generative artificial intelligence. The purpose of the analysis is to diagnose the current condition of the crops and derive the necessary countermeasures.

[0387] Based on the analysis results, appropriate advice and reminders are generated. For example, if the soil pH level is outside the appropriate range, advice on the timing and amount of organic fertilizer to be used is generated.

[0388] Communication with farmers

[0389] server

[0390] The server sends the generated advice and diagnostic results to the terminal.

[0391] It also accepts feedback and questions from farmers and generates optimal answers, which are then sent to the device.

[0392] Terminal

[0393] The terminal notifies the farmer of advice and diagnostic results sent from the server, for example by providing appropriate information via an alert or display panel.

[0394] Farmers can also use their devices to input questions to the generative AI, which are then sent to the server.

[0395] User (farmer)

[0396] Farmers can then use the advice they receive through the device to carry out their farming work, such as applying appropriate organic fertilizers or taking measures to prevent specific pests and diseases.

[0397] The results of the advice and any feedback felt are entered into the device and sent to the server.

[0398] Cultivation management

[0399] Terminal

[0400] The terminal continuously monitors the condition of the crops through a sensing device, and the collected data is sent to a server in real time.

[0401] server

[0402] The server analyzes changes in the cultivation environment based on the received data and generates necessary reminders and additional advice, such as "Low temperatures are predicted this week, so please take measures to prevent frost."

[0403] Any generated reminders or additional advice will also be sent to the farmer via the device.

[0404] Combining Emotion Engines

[0405] Terminal

[0406] When the device communicates with the farmer, it uses an emotion engine to analyze the tone of voice and text content. For example, if the farmer is emotional, the emotion engine will recognize that emotion.

[0407] server

[0408] The emotion information obtained from the emotion engine is used to adjust the content and timing of the advice provided by the generative AI. For example, a farmer feeling stressed might be given simple, actionable advice along with an encouraging message.

[0409] It also fine-tunes reminders and advice based on emotions and delivers them in a format that farmers find most acceptable.

[0410] User (farmer)

[0411] Farmers implement the advice provided and enter their results and feelings into the device, which also sends emotional feedback to the server.

[0412] Specific examples

[0413] Examples of organic fertilizer use

[0414] 1. The device uses e-kakashi to measure the soil's pH level, humidity, and temperature, and sends the data to the server.

[0415] 2. The server analyzes the received data using generative artificial intelligence and generates advice on the appropriate timing and amount of organic fertilizer to use based on the condition of the soil.

[0416] 3. The server sends the generated advice to the terminal and notifies the farmer.

[0417] 4. The device uses an emotion engine to analyze the farmer's emotions, and if they are feeling stressed or anxious, it will provide advice with an encouraging message.

[0418] 5. The user (farmer) applies organic fertilizer based on the advice and observes the results. The user inputs the observation results and their feelings into the terminal and sends them to the server.

[0419] 6. The server analyzes the observation data and sentiment information and suggests new advice or adjustments as needed, for example determining whether soil conditions have improved and suggesting further preventative measures or additional fertilization.

[0420] Examples of pest prevention

[0421] 1. The server trains the generative AI to learn about the ecology of pests and diseases and preventative measures. The data includes the ecology of pests and diseases, preventative measures, and their relationship with climate.

[0422] 2. The device uses e-kakashi to collect data on the condition of the crops and the surrounding environment (temperature, humidity, air temperature, etc.) and send it to the server.

[0423] 3. The server analyzes the received data using generative artificial intelligence and generates a risk assessment of pest and disease outbreaks and preventive measures.

[0424] 4. The server generates advice including preventive measures based on the risk assessment and sends the advice to the terminal.

[0425] 5. The device analyzes the farmer's emotions using an emotion engine and tailors advice based on their emotions. For example, it provides detailed instructions on specific procedures to farmers who are feeling anxious.

[0426] 6. The user (farmer) implements preventive measures based on the advice received, for example, installing moth nets or spraying natural pesticides.

[0427] 7. The device monitors the results again through e-kakashi and sends the data to the server.

[0428] 8. The server analyzes the monitoring data and emotional information to evaluate the effectiveness of preventive measures, and generates additional measures and reminders as needed, and notifies users via their devices.

[0429] Through the above processing steps, this invention effectively supports pesticide-free cultivation, enabling farmers to accurately grasp the necessary know-how and timing and put it into practice. By combining it with an emotion engine, it is possible to provide support that matches the psychological state of farmers, improving work efficiency and satisfaction.

[0430] The processing flow will be explained below.

[0431] Examples of organic fertilizer use

[0432] Step 1:

[0433] The device uses e-kakashi to measure the soil's pH level, humidity, and temperature, and then sends the data to the server.

[0434] Step 2:

[0435] The server refers to the contents of the database based on the data received and preprocesses the data, specifically removing outliers and normalizing the data.

[0436] Step 3:

[0437] The server uses generative artificial intelligence to analyze the pre-processed data and generate information on the current state of the crops and the appropriate use of organic fertilizer.

[0438] Step 4:

[0439] Based on the analysis results, the server generates advice including the appropriate timing and amount of organic fertilizer to use and sends that advice to the terminal.

[0440] Step 5:

[0441] The terminal notifies the farmer of the advice sent from the server, for example by displaying the information via an alert or a display panel.

[0442] Step 6:

[0443] The device uses an emotion engine to analyze the farmer's emotions, and if they are feeling stressed or anxious, it will provide advice along with an encouraging message.

[0444] Step 7:

[0445] The user (farmer) applies organic fertilizer based on the advice, observes the results, and inputs their observations and their feelings into the device.

[0446] Step 8:

[0447] The device collects observations and emotional information and sends the data to a server.

[0448] Step 9:

[0449] The server analyzes the observation data and sentiment information and suggests new advice or adjustments as needed, for example determining whether soil conditions have improved and suggesting further preventative measures or additional fertilization.

[0450] Examples of pest prevention

[0451] Step 1:

[0452] The server trains the generative AI with data on pests and diseases, including their ecology, preventative measures, and their relationship with climate.

[0453] Step 2:

[0454] The terminal uses e-kakashi to collect data on the condition of the crops and the surrounding environment (temperature, humidity, air temperature, etc.) and send it to the server.

[0455] Step 3:

[0456] The server preprocesses the received data, removing outliers and normalizing the data.

[0457] Step 4:

[0458] The server analyzes the preprocessed data using generative artificial intelligence to generate risk assessments and preventative measures for pest and disease outbreaks.

[0459] Step 5:

[0460] The server generates advice including preventive measures based on the risk assessment and transmits the advice to the terminal.

[0461] Step 6:

[0462] The terminal notifies the farmer of the advice sent from the server, for example by providing information using a display panel or alerts.

[0463] Step 7:

[0464] The device uses an emotion engine to analyze the farmer's emotions and tailor advice based on their feelings, for example providing detailed instructions on specific procedures to farmers who are feeling anxious.

[0465] Step 8:

[0466] The user (farmer) implements preventive measures based on the advice received, for example, installing moth nets or spraying natural pesticides.

[0467] Step 9:

[0468] The device monitors the results again through e-kakashi and sends the data to the server.

[0469] Step 10:

[0470] The server analyzes the monitoring data and emotional information to evaluate the effectiveness of preventive measures, and generates additional measures and reminders as needed, which are then sent via the device.

[0471] These processing steps effectively support pesticide-free cultivation, allowing farmers to accurately grasp the necessary know-how and timing, and then carry it out.By combining it with an emotion engine, it is possible to provide support that matches the psychological state of farmers, improving work efficiency and satisfaction.

[0472] Example 2

[0473] 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."

[0474] In modern agriculture, pesticide-free cultivation is becoming increasingly important from the perspectives of health and environmental protection, but its implementation requires advanced expertise and technology. Furthermore, because the emotions and psychological state of farmers also affect work efficiency and satisfaction, support that takes emotions into consideration is also necessary. Conventional systems have difficulty addressing these complex challenges, particularly in terms of real-time condition monitoring and adjusting advice based on emotions.

[0475] 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.

[0476] In this invention, the server includes: means for collecting data on pesticide-free farming; means for training a generative artificial intelligence (AI) to learn know-how about pesticide-free farming; means for saving and updating the model as the learning result; means for collecting crop condition data using a sensing device; means for analyzing the crop condition data and generating diagnostic results; means for providing advice on pesticide-free farming based on the diagnostic results; means for transmitting the advice and diagnostic results and communicating with the farmer; means for receiving feedback from the farmer and reflecting it in the model; means for analyzing the farmer's emotions; and means for adjusting the content and timing of advice based on the analyzed emotional information. This allows farmers to acquire know-how about pesticide-free farming in real time and perform farm work efficiently and effectively. Furthermore, emotionally sensitive support can improve work efficiency and satisfaction.

[0477] "Pesticide-free cultivation" is an agricultural method in which crops are grown without the use of pesticides, and is important from the perspectives of health and environmental protection.

[0478] "Data collection means" refers to devices or mechanisms that obtain necessary data from sensors, databases, the Internet, etc.

[0479] "Generative AI" is an AI system that learns from collected data and generates solutions and advice for specific problems.

[0480] A "learning result model" is a collection of solutions and know-how for specific problems that is obtained as a result of learning by generative artificial intelligence.

[0481] A "sensing device" is a device used to measure and record the condition of soil and the environment, collecting data such as temperature, humidity, and light intensity.

[0482] "Crop condition data" refers to information about the cultivation environment and growth of crops, such as soil conditions, weather conditions, and crop growth status.

[0483] "Analysis means" refers to a method or device for analyzing collected data and deriving useful information or knowledge.

[0484] "Diagnosis results" are conclusions about the current state and future predictions drawn based on collected and analyzed data.

[0485] "Advice delivery methods" are systems or mechanisms that provide specific guidelines and recommendations based on diagnostic results.

[0486] "Communication means" refers to a system for two-way exchange of data and information, and often refers specifically to connections with agricultural workers.

[0487] "Feedback receiving means" is a mechanism for receiving reactions and results from users.

[0488] "Emotion analysis means" refers to a method or device for analyzing a user's emotions and psychological state, and infers emotions from the tone of voice and the content of text.

[0489] "Advice adjustment means" refers to a system or method that changes the content and timing of advice provided based on the results of sentiment analysis.

[0490] The system of this invention includes a method and device for effectively supporting pesticide-free cultivation, and in particular, combines an emotion engine that recognizes the user's emotions and adjusts the content and timing of advice based on those emotions. Specific embodiments focusing on a server, a terminal, and a user (agricultural worker) are described below.

[0491] Data collection and learning

[0492] server

[0493] The server collects a large amount of data related to pesticide-free farming from the internet and existing databases, including types of organic fertilizer and their application methods, pest and disease ecology, and climate data.

[0494] The server cleanses the collected data, removing noise and missing data, then normalizes it and trains the generative AI model. Specifically, the data is formatted in a way that makes it easy for the AI ​​model to understand, and it learns the know-how of pesticide-free farming.

[0495] The model generated as a result of learning is stored on the server and updated as necessary.

[0496] Crop condition diagnosis

[0497] Terminal

[0498] Sensing devices (e.g., ec sensing devices) connected to the terminal periodically collect data such as soil quality, temperature, humidity, and light intensity.

[0499] The collected data is transmitted from the terminal to a server.

[0500] server

[0501] The server receives the data sent from the device and analyzes it using a generative AI model. The purpose of the analysis is to diagnose the current condition of the crops and derive the necessary countermeasures.

[0502] Based on the analysis results, appropriate advice and reminders are generated. For example, if the soil pH level is outside the appropriate range, advice on the timing and amount of organic fertilizer to be used is generated.

[0503] Communication with farmers

[0504] server

[0505] The server sends the generated advice and diagnostic results to the terminal.

[0506] It also accepts feedback and questions from farmers and generates optimal answers, which are then sent to the device.

[0507] Terminal

[0508] The terminal notifies the farmer of advice and diagnostic results sent from the server, for example by providing appropriate information via an alert or display panel.

[0509] Farmers can also use their devices to input questions to the generative AI model, which are also sent to the server.

[0510] User (farmer)

[0511] Farmers can then carry out farm work based on the advice they receive through the device, such as applying appropriate organic fertilizer and taking measures to prevent pests and diseases.

[0512] The results of the advice and any feedback felt are entered into the device and sent to the server.

[0513] Cultivation management

[0514] Terminal

[0515] The terminal continuously monitors the condition of the crops through a sensing device, and the collected data is sent to a server in real time.

[0516] server

[0517] The server analyzes changes in the cultivation environment based on the received data and generates necessary reminders and additional advice, such as "Low temperatures are predicted this week, so please take measures to prevent frost."

[0518] Any generated reminders or additional advice will also be sent to the farmer via the device.

[0519] Combining Emotion Engines

[0520] Terminal

[0521] When the device communicates with the farmer, it uses an emotion engine to analyze the tone of voice and text content. For example, if the farmer is emotional, the emotion engine will recognize that emotion.

[0522] server

[0523] The emotion information obtained from the emotion engine is used to tailor the content and timing of the advice provided by the generative AI model. For example, a farmer experiencing stress might be given a simple, actionable piece of advice along with an encouraging message.

[0524] It also fine-tunes reminders and advice based on emotions and delivers them in a format that farmers find easy to accept.

[0525] User (farmer)

[0526] Farmers implement the advice provided and enter the results and emotions they felt into the device, which also sends emotional feedback to the server.

[0527] Specific examples

[0528] Examples of organic fertilizer use

[0529] 1. The device uses a sensing device to measure the soil's pH level, humidity, and temperature, and then sends the data to the server.

[0530] 2. The server analyzes the received data using a generative AI model and generates advice on the appropriate timing and amount of organic fertilizer to use based on the condition of the soil.

[0531] 3. The server sends the generated advice to the terminal and notifies the farmer.

[0532] 4. The device uses an emotion engine to analyze the farmer's emotions, and if they are feeling stressed or anxious, it will provide advice with an encouraging message.

[0533] 5. The user (farmer) applies organic fertilizer based on the advice and observes the results. The user inputs the observation results and their feelings into the device and sends them to the server.

[0534] 6. The server analyzes the observation data and sentiment information and suggests new advice or adjustments as needed, for example determining whether soil conditions have improved and suggesting further preventative measures or additional fertilization.

[0535] Examples of pest prevention

[0536] 1. The server trains the generative AI to learn about the ecology of pests and diseases and preventative measures. The data includes the ecology of pests and diseases, preventative measures, and their relationship with climate.

[0537] 2. The terminal uses a sensing device to collect data on the condition of the crops and the surrounding environment (temperature, humidity, air temperature, etc.) and transmits it to the server.

[0538] 3. The server analyzes the received data using a generative AI model to generate a risk assessment of pest and disease outbreaks and generate preventive measures.

[0539] 4. The server generates advice including preventive measures based on the risk assessment and sends the advice to the terminal.

[0540] 5. The device analyzes the farmer's emotions using an emotion engine and tailors advice based on their emotions. For example, it provides detailed instructions on specific procedures to farmers who are feeling anxious.

[0541] 6. The user (farmer) implements preventive measures based on the advice received, for example, installing moth nets or spraying natural pesticides.

[0542] 7. The terminal monitors the implementation results again through the sensing device and sends the data to the server.

[0543] 8. The server analyzes the monitoring data and emotional information to evaluate the effectiveness of preventive measures, and generates additional measures and reminders as needed, and notifies users via their devices.

[0544] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0545] Step 1:

[0546] Data collection

[0547] The server collects data on pesticide-free farming from the internet and existing databases, including the type of organic fertilizer, how it is used, the ecology of pests and diseases, and weather data.

[0548] Input: Internet databases and meteorological data related to pesticide-free farming.

[0549] Output: Collected data before cleansing.

[0550] Specific behavior: Extract data via API and store it in a local database.

[0551] Step 2:

[0552] Data Cleansing and Learning

[0553] The server cleanses the collected data, removing noise and missing data, then normalizes the data and trains the generative AI model.

[0554] Input: Collected data before cleansing.

[0555] Output: Cleansed and normalized training data and a trained model.

[0556] What it does: It uses database queries and data analysis tools to remove unnecessary data and feed it to machine learning algorithms.

[0557] Step 3:

[0558] Collecting data on crop conditions

[0559] The terminal uses a sensing device to periodically collect data such as soil quality, temperature, humidity, and light intensity and transmits it to a server.

[0560] Input: Real-time data from soil and environmental sensors.

[0561] Output: Collected crop condition data.

[0562] Specific operation: Data is acquired from the sensing device, stored on the terminal, and then sent to the server.

[0563] Step 4:

[0564] Analysis of crop conditions

[0565] The server analyzes the crop condition data sent from the device using a generative AI model, generates diagnostic results, and derives necessary countermeasures.

[0566] Input: Crop status data sent from the terminal.

[0567] Output: Diagnostic results and remedial action.

[0568] What it does: It uses data analysis algorithms to extract meaningful features from the data and make predictions based on the model.

[0569] Step 5:

[0570] Advice Generation and Notifications

[0571] The server generates appropriate advice and reminders based on the analysis results and sends them to the device.

[0572] Input: Diagnostic results and remedial action.

[0573] Output: Advice and reminders.

[0574] Specific operation: Advice is created using a generative AI model and the data is sent to the device.

[0575] Step 6:

[0576] Giving and receiving feedback from farmers

[0577] The terminal notifies the farmer of advice and diagnostic results from the server, who then performs farm work based on the advice and enters feedback into the terminal.

[0578] Input: Advice and diagnostic results from the server.

[0579] Output: Farmer feedback.

[0580] Specific behavior: Uses the notification system to display advice and records user input.

[0581] Step 7:

[0582] Sentiment analysis and advice adjustment

[0583] The device uses an emotion engine to analyze the farmer's emotions and transmits the results to a server, which then adjusts the content and timing of advice based on the emotional information.

[0584] Input: Farmer sentiment data.

[0585] Output: Adjusted advice.

[0586] What it does: It uses speech and text analysis tools to determine emotional state, sends that information to a server, and generates and resends tailored advice.

[0587] Step 8:

[0588] Continuous monitoring and updates

[0589] The terminal continuously monitors the condition of the crops through a sensing device and transmits the data in real time to the server, which analyzes the received data and generates necessary reminders and additional advice.

[0590] Input: Continuous real-time data from sensing equipment.

[0591] Output: Reminders and additional advice.

[0592] Specific operation: Collect and transmit data using a real-time data collection system, and generate new advice and reminders based on the analysis results.

[0593] (Application example 2)

[0594] 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."

[0595] In pesticide-free cultivation, farmers need a lot of effort and knowledge to obtain appropriate advice. Furthermore, the timing and content of information provided about cultivation is uniform, making it difficult to respond to the emotions and psychological state of farmers. This prevents farmers from obtaining the necessary information at the right time, which can result in reduced cultivation efficiency and increased stress.

[0596] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0597] In this invention, the server includes means for collecting data on pesticide-free farming and having the generative AI learn know-how about pesticide-free farming, means for saving and updating the model resulting from the learning, means for recognizing the emotional state of the farmer, and means for adjusting the content and timing of advice based on the emotional state, thereby enabling the farmer to receive the most appropriate advice and information at the appropriate time according to his or her emotional state.

[0598] "Pesticide-free cultivation" is a method of cultivating crops using natural materials and techniques without using chemical pesticides.

[0599] "Data collection means" refers to devices and systems for collecting data on pesticide-free cultivation and crop condition data.

[0600] "Generative AI" refers to AI that has the ability to learn specific knowledge and skills based on large amounts of data, and as a result generate useful information and advice.

[0601] "Know-how" refers to the practical knowledge and skills required for a specific purpose.

[0602] A "sensing device" is a device for collecting environmental data such as temperature, humidity, and soil quality.

[0603] "Diagnosis results" are information on the condition of crops and appropriate countermeasures obtained as a result of analyzing collected data.

[0604] "Advice providing means" refers to a device or system that provides specific instructions and advice to farmers based on the generated diagnostic results and know-how.

[0605] "Communication means" means a device or system for transmitting advice and diagnostic results to farmers and receiving feedback from farmers.

[0606] An "emotional state" refers to the feelings or psychological state that a person is in.

[0607] "Feedback receiving means" refers to a device or system for receiving opinions and feedback from farmers.

[0608] A "model updating means" is a device or system that improves or modifies an existing artificial intelligence model based on collected data and feedback.

[0609] A "timing adjustment means" is a device or system that takes into account the emotional state of the farmer and determines the optimal timing for providing advice.

[0610] The system of this invention includes a method and device for effectively supporting pesticide-free cultivation, and in particular, it combines an emotion engine that recognizes the emotions of farmers and adjusts the content and timing of advice based on those emotions. Specific embodiments focusing on a server, a terminal, and a user (agricultural worker) are described below.

[0611] Data collection and learning

[0612] server

[0613] The server collects large amounts of data related to pesticide-free farming from the internet and existing databases. This includes the types and use of organic fertilizers, the ecology of pests and diseases, and climate data. The server then cleanses the collected data, removing noise and missing data. It then normalizes the data and trains it using generative AI. Specifically, the data is formatted in a way that is easy for the AI ​​model to understand, and it is trained to learn the know-how of pesticide-free farming. The model generated as a result of the training is stored on the server and updated as necessary.

[0614] Crop condition diagnosis

[0615] Terminal

[0616] The sensing device connected to the terminal periodically collects data on soil quality, temperature, humidity, light intensity, etc. The collected data is then sent from the terminal to a server.

[0617] server

[0618] The server receives the data sent from the device and analyzes it using generative artificial intelligence. The purpose of the analysis is to diagnose the current condition of the crops and determine the necessary countermeasures. Based on the analysis results, appropriate advice and reminders are generated. For example, if the soil pH level is outside the appropriate range, advice is generated on the appropriate timing and amount of organic fertilizer to be used.

[0619] Communication with farmers

[0620] server

[0621] The server sends the generated advice and diagnostic results to the device. It also accepts feedback and questions from farmers and generates optimal answers to those questions. These answers are also sent to the device.

[0622] Terminal

[0623] The terminal notifies the farmer of advice and diagnostic results sent from the server. For example, appropriate information is provided via alerts or a display panel. Farmers can also use the terminal to input questions to the generative AI, which is also sent to the server.

[0624] User (farmer)

[0625] Farmers perform farm work based on the advice they receive through their devices. For example, they may apply appropriate organic fertilizer or take measures to prevent specific pests and diseases. The results of implementing the advice and any feedback they feel are entered into the device and sent to the server.

[0626] Cultivation management

[0627] Terminal

[0628] The terminal continuously monitors the condition of the crops through a sensing device, and the collected data is sent to a server in real time.

[0629] server

[0630] The server analyzes changes in the cultivation environment based on the received data and generates necessary reminders and additional advice. For example, it could say, "Low temperatures are predicted this week, so please take measures to prevent frost." The generated reminders and additional advice are also notified to farmers via their terminals.

[0631] Combining Emotion Engines

[0632] Terminal

[0633] When the device communicates with the farmer, it uses an emotion engine to analyze the tone of voice and text content. For example, if the farmer is emotional, the emotion engine will recognize that emotion.

[0634] server

[0635] The content and timing of advice provided by the generative AI is adjusted based on the emotional information obtained from the emotion engine. For example, a farmer feeling stressed can be provided with simple, actionable advice along with an encouraging message. The system also fine-tunes the content of reminders and advice based on emotions, providing them in a format that is easy for farmers to accept.

[0636] User (farmer)

[0637] Farmers implement the advice provided and enter their results and feelings into the device, which also sends emotional feedback to the server.

[0638] Example: Use of organic fertilizer

[0639] 1. The device uses a sensing device to measure the soil's pH level, humidity, and temperature, and then sends the data to the server.

[0640] 2. The server analyzes the received data using generative artificial intelligence and generates advice on the appropriate timing and amount of organic fertilizer to use based on the condition of the soil.

[0641] 3. The server sends the generated advice to the terminal and notifies the farmer.

[0642] 4. The device uses an emotion engine to analyze the farmer's emotions, and if they are feeling stressed or anxious, it will provide advice with an encouraging message.

[0643] 5. The user (farmer) applies organic fertilizer based on the advice and observes the results. The user inputs the observation results and their feelings into the terminal and sends them to the server.

[0644] 6. The server analyzes the observation data and sentiment information and suggests new advice or adjustments as needed, for example determining whether soil conditions have improved and suggesting further preventative measures or additional fertilization.

[0645] Example: Prevention of pests and diseases

[0646] 1. The server trains the generative AI to learn about the ecology of pests and diseases and preventative measures. The data includes the ecology of pests and diseases, preventative measures, and their relationship with climate.

[0647] 2. The terminal uses a sensing device to collect data on the condition of the crops and the surrounding environment (temperature, humidity, air temperature, etc.) and transmits it to the server.

[0648] 3. The server analyzes the received data using generative artificial intelligence and generates a risk assessment of pest and disease outbreaks and preventive measures.

[0649] 4. The server generates advice including preventive measures based on the risk assessment and sends the advice to the terminal.

[0650] 5. The device analyzes the farmer's emotions using an emotion engine and tailors advice based on their emotions. For example, it provides detailed instructions on specific procedures to farmers who are feeling anxious.

[0651] 6. The user (farmer) implements preventive measures based on the advice received, for example, installing moth nets or spraying natural pesticides.

[0652] 7. The terminal monitors the implementation results again through the sensing device and sends the data to the server.

[0653] 8. The server analyzes the monitoring data and emotional information to evaluate the effectiveness of preventive measures, and generates additional measures and reminders as needed, and notifies users via their devices.

[0654] Examples of prompts:

[0655] "User types in question: 'What fertilizer should I use for the current weather?'

[0656] Prompt for generative AI model: "User emotional state: Neutral. Input question: What fertilizer should I use based on the current weather?"

[0657] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0658] Step 1:

[0659] The server collects data on pesticide-free farming. The data is collected from the internet and existing databases, and mainly covers the types and usage of organic fertilizers, the ecology of pests and diseases, and climate data. The input is data from the source, and the output is cleansed data. The data is cleansed and noise and missing data are removed.

[0660] Step 2:

[0661] The server normalizes the cleansed data and trains it using generative AI. In this process, the data is converted into a format suitable for the AI ​​model, and the AI ​​is trained on the know-how of pesticide-free farming. The input is the cleansed data, and the output is a trained AI model.

[0662] Step 3:

[0663] The trained model is stored on the server and updated as needed. The server manages model versions and always maintains the latest cultivation know-how. The input is the trained AI model, and the output is the stored model.

[0664] Step 4:

[0665] A sensing device connected to the terminal periodically collects data on soil quality, temperature, humidity, light intensity, etc. The input is real-time data from the sensing device, and the output is data sent to the server.

[0666] Step 5:

[0667] The server receives the data sent from the device and analyzes it using generative artificial intelligence. The purpose of the analysis is to diagnose the current condition of the crops and derive the necessary countermeasures. The input is the condition data from the device, and the output is advice as the diagnosis result.

[0668] Step 6:

[0669] The server sends the generated advice and diagnostic results to the terminal. The server also responds to feedback and questions from the user as needed. The input is the diagnostic results and advice, and the output is the information sent to the terminal.

[0670] Step 7:

[0671] The terminal notifies the farmer of advice and diagnostic results sent from the server. Specifically, appropriate information is provided through alerts and display panels. The input is advice and diagnostic results, and the output is notifications to the farmer.

[0672] Step 8:

[0673] Farmers use terminals to input questions to the generative AI. The questions are sent from the terminals to the server. The input is the farmer's question, and the output is the question sent to the server.

[0674] Step 9:

[0675] The server recognizes the farmer's emotional state. It uses an emotion engine to analyze the tone of voice and text content. The input is the farmer's voice or text data, and the output is the analyzed emotional state.

[0676] Step 10:

[0677] The server adjusts the content and timing of advice based on the emotional state. If the user is feeling stressed, the server provides advice along with an encouraging message. The input is the analyzed emotional state, and the output is the adjusted advice.

[0678] Step 11:

[0679] Farmers perform farm work based on the advice provided. They input their results and feelings into a terminal and send them to a server. The input is the farmer's feedback, and the output is the feedback sent to the server.

[0680] Step 12:

[0681] The server analyzes the observation data and sentiment information and proposes new advice or adjustments as needed. The input is the farmer's feedback and observation data, and the output is new advice.

[0682] Examples of prompts:

[0683] "User types in question: 'What fertilizer should I use for the current weather?'

[0684] Prompt for generative AI model: "User emotional state: Neutral. Input question: What fertilizer should I use based on the current weather?"

[0685] 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.

[0686] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0687] 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.

[0688] [Second embodiment]

[0689] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0690] 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.

[0691] 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).

[0692] 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.

[0693] 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.

[0694] 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).

[0695] 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.

[0696] 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.

[0697] 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.

[0698] 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.

[0699] 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.

[0700] 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."

[0701] The system of the present invention includes a method and an apparatus for effectively supporting pesticide-free cultivation. A specific embodiment will be described below, focusing on a server, a terminal, and a user (agricultural worker).

[0702] Data collection and learning

[0703] server

[0704] The server collects a large amount of data related to pesticide-free farming from the internet and existing databases, including types of organic fertilizer and their application methods, pest and disease ecology, and climate data.

[0705] The server cleanses the collected data, removing noise and missing data. It then normalizes the data and trains it using generative AI. Specifically, the data is formatted in a way that makes it easy for the AI ​​model to understand, and it learns the know-how of pesticide-free farming.

[0706] The model generated as a result of learning is stored on the server and updated as necessary.

[0707] Crop condition diagnosis

[0708] Terminal

[0709] Sensing devices (e.g., e-kakashi) connected to the terminal periodically collect data such as soil quality, temperature, humidity, and light intensity.

[0710] The collected data is transmitted from the terminal to a server.

[0711] server

[0712] The server receives the data sent from the device and analyzes it using generative artificial intelligence. The purpose of the analysis is to diagnose the current condition of the crops and derive the necessary countermeasures.

[0713] Based on the analysis results, appropriate advice and reminders are generated. For example, if the soil pH level is outside the appropriate range, advice on the timing and amount of organic fertilizer to be used is generated.

[0714] Communication with farmers

[0715] server

[0716] The server sends the generated advice and diagnostic results to the terminal.

[0717] It also accepts feedback and questions from farmers and generates optimal answers, which are then sent to the device.

[0718] Terminal

[0719] The terminal notifies the farmer of advice and diagnostic results sent from the server, for example by providing appropriate information via an alert or display panel.

[0720] Farmers can also use their devices to input questions to the generative AI, which are then sent to the server.

[0721] User (farmer)

[0722] Farmers can then use the advice they receive through the device to carry out their farming work, such as applying appropriate organic fertilizers or taking measures to prevent specific pests and diseases.

[0723] The results of the advice and any feedback felt are entered into the device and sent to the server.

[0724] Cultivation management

[0725] Terminal

[0726] The terminal continuously monitors the condition of the crops through a sensing device, and the collected data is sent to a server in real time.

[0727] server

[0728] The server analyzes changes in the cultivation environment based on the received data and generates necessary reminders and additional advice, such as "Low temperatures are predicted this week, so please take measures to prevent frost."

[0729] Any generated reminders or additional advice will also be sent to the farmer via the device.

[0730] Specific examples

[0731] Examples of organic fertilizer use

[0732] 1. The device uses e-kakashi to measure the soil's pH level, humidity, and temperature, and sends the data to the server.

[0733] 2. The server analyzes the received data using generative artificial intelligence and generates advice on the appropriate timing and amount of organic fertilizer to use based on the condition of the soil.

[0734] 3. The server sends the generated advice to the terminal and notifies the farmer.

[0735] 4. The user (farmer) applies organic fertilizer based on the advice and observes the results.

[0736] 5. The terminal measures the observation results again using the sensing device and sends the data to the server.

[0737] 6. The server analyzes the new data and generates additional advice if necessary, and notifies the farmer via the terminal.

[0738] Examples of pest prevention

[0739] 1. The server trains the generative AI to learn about the ecology of pests and diseases and preventive measures.

[0740] 2. The device uses e-kakashi to collect data on the crops and their surrounding environment and transmits it to the server.

[0741] 3. The server analyzes the received data using generative artificial intelligence and generates advice on risk assessments of pest and disease outbreaks and preventive measures.

[0742] 4. The server sends the generated advice to the terminal and notifies the farmer.

[0743] 5. The user (farmer) implements preventive measures based on the advice and observes the results.

[0744] 6. The device measures the observations and sends them to the server.

[0745] 7. The server continuously analyzes the data, generates new advice, and notifies the farmer via his / her terminal.

[0746] As described above, this system enables farmers to accurately grasp the know-how and timing required for pesticide-free cultivation and then put it into practice.

[0747] The processing flow will be explained below.

[0748] Examples of organic fertilizer use

[0749] Step 1:

[0750] The device uses e-kakashi to measure the soil's pH level, humidity, and temperature, and then sends the data to the server.

[0751] Step 2:

[0752] The server refers to the contents of the database based on the data received and preprocesses the data, specifically removing outliers and normalizing the data.

[0753] Step 3:

[0754] The server uses generative artificial intelligence to analyze the pre-processed data and generate information on the current state of the crops and the appropriate use of organic fertilizer.

[0755] Step 4:

[0756] Based on the analysis results, the server generates advice including the appropriate timing and amount of organic fertilizer to use and sends that advice to the terminal.

[0757] Step 5:

[0758] The terminal notifies the farmer of the advice sent from the server, for example by displaying the information via an alert or a display panel.

[0759] Step 6:

[0760] The user (farmer) applies organic fertilizer based on the advice, observes the results, and enters the observation results into the terminal.

[0761] Step 7:

[0762] The device collects the observations and sends the data to a server.

[0763] Step 8:

[0764] The server analyzes the observation data and suggests new advice or adjustments as needed, for example determining whether soil conditions have improved and suggesting further preventative measures or additional fertilization.

[0765] Examples of pest prevention

[0766] Step 1:

[0767] The server trains the generative AI with data on pests and diseases, including their ecology, preventative measures, and their relationship with climate.

[0768] Step 2:

[0769] The terminal uses e-kakashi to collect data on the condition of the crops and the surrounding environment (temperature, humidity, air temperature, etc.) and send it to the server.

[0770] Step 3:

[0771] The server preprocesses the received data, removing outliers and normalizing the data.

[0772] Step 4:

[0773] The server analyzes the preprocessed data using generative artificial intelligence to generate risk assessments and preventative measures for pest and disease outbreaks.

[0774] Step 5:

[0775] The server generates advice including preventive measures based on the risk assessment and transmits the advice to the terminal.

[0776] Step 6:

[0777] The terminal notifies the farmer of the advice sent from the server, for example by providing information using a display panel or alerts.

[0778] Step 7:

[0779] The user (farmer) implements preventive measures based on the advice received, for example, installing moth nets or spraying natural pesticides.

[0780] Step 8:

[0781] The device monitors the results again through e-kakashi and sends the data to the server.

[0782] Step 9:

[0783] The server analyzes the monitoring data and evaluates the effectiveness of preventive measures, generating additional measures and reminders as needed and sending notifications via the device.

[0784] Through the above processing steps, the present invention effectively supports pesticide-free cultivation, enabling farmers to accurately grasp and implement the necessary know-how and timing.

[0785] Example 1

[0786] 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."

[0787] Practicing pesticide-free cultivation in the agricultural field is extremely delicate and complex. To successfully cultivate crops without pesticides, it is necessary to use organic fertilizer at the appropriate time, prevent pests and diseases, and constantly monitor the condition of the crops. However, acquiring the knowledge and skills necessary to achieve this requires a great deal of effort and time. For this reason, there is a need for a support system to help farmers cultivate crops without pesticides effectively.

[0788] 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.

[0789] In this invention, the server includes a means for collecting data on pesticide-free cultivation, a means for training the artificial intelligence to learn know-how on pesticide-free cultivation based on the data on pesticide-free cultivation, and a means for saving and updating the model as a result of the learning, thereby making it possible to provide optimal advice and diagnostic results on pesticide-free cultivation.

[0790] "Data on pesticide-free cultivation" refers to information related to the knowledge and techniques required to carry out pesticide-free cultivation, including types of organic fertilizers and how to use them, the ecology of pests and diseases, and climate data.

[0791] "Generative AI" refers to AI that uses technologies such as machine learning and deep learning to analyze data and automatically generate and learn knowledge for specific purposes.

[0792] "Sensing device" refers to a measuring device used to measure parameters of the crop environment, such as soil quality, temperature, humidity, and light intensity.

[0793] "Plant condition data" refers to data that includes information about crops and their surrounding environment, such as soil quality, temperature, humidity, and light intensity.

[0794] "Diagnosis results" refers to information about the health of agricultural crops and necessary measures obtained by analyzing collected plant condition data.

[0795] "Advice" refers to specific instructions and suggestions for farmers to successfully cultivate crops without pesticides, based on the diagnostic results generated.

[0796] "Users" refers to agricultural workers and those involved in agriculture who practice pesticide-free cultivation.

[0797] "Feedback" refers to information provided by the user regarding the evaluation of the system's advice and diagnostic results and the execution results.

[0798] "Model" refers to a computational model that incorporates know-how for pesticide-free cultivation using generative artificial intelligence that learns from collected data.

[0799] "Real-time monitoring" refers to continuously observing plant condition data using sensing devices and immediately processing the results.

[0800] A "reminder" is information that notifies a user of the timing and precautions to take when taking a specific action.

[0801] "Additional advice" refers to new instructions or suggestions generated based on real-time monitoring data.

[0802] The system of this invention includes a method and an apparatus for collecting data, analyzing it, and providing advice to support pesticide-free cultivation. A specific embodiment will be described, focusing on a server, a terminal, and a user (agricultural worker).

[0803] Data collection and learning

[0804] server

[0805] The server collects data related to pesticide-free farming from the Internet and existing databases. This data includes types of organic fertilizers, application methods, pest and disease ecology, and climate data. As a specific example, the Open Weather Map API can be used to collect weather data.

[0806] The collected data is cleansed to remove noise and missing data, then normalized and trained using a generative artificial intelligence (AI) model (using TensorFlow or PyTorch, for example) to learn the know-how of pesticide-free farming.

[0807] The resulting AI model is stored on a server and regularly updated. This model is used to provide knowledge and optimal strategies for pesticide-free farming.

[0808] Crop condition diagnosis

[0809] Terminal

[0810] Sensing devices (e.g., e-kakashi) connected to the terminal periodically collect data on soil quality, temperature, humidity, light intensity, etc. This allows for a detailed understanding of the conditions of crops and their environment.

[0811] The collected data is sent to a server via Wi-Fi or mobile communications.

[0812] server

[0813] The server uses generative artificial intelligence to analyze the data it receives, specifically data on soil pH levels, temperature, and humidity, to diagnose the current condition of the crops.

[0814] Based on the analysis results, advice on pesticide-free cultivation is generated. For example, if the soil pH level is outside the appropriate range, advice is provided on the appropriate timing and amount of organic fertilizer to be used.

[0815] Communication with farmers

[0816] server

[0817] The server sends the generated advice and diagnostic results to the device, possibly in the form of push notification or email.

[0818] It also accepts feedback and questions from farmers and generates optimal answers based on that information. For example, it uses generative artificial intelligence to create optimal answers to users' questions.

[0819] Terminal

[0820] The terminal notifies the user of advice and diagnostic results sent from the server, allowing the user to receive appropriate information on pesticide-free farming in a timely manner.

[0821] Additionally, users can use their terminals to input questions into the system, which are then sent to the server.

[0822] User (farmer)

[0823] Farmers can then carry out agricultural work based on the advice they receive through the device, such as applying appropriate organic fertilizer or taking measures to prevent specific pests and diseases.

[0824] By inputting the results of the execution and feedback into the device and sending it to the server, the system continues to learn and provides more accurate advice.

[0825] Cultivation management

[0826] Terminal

[0827] The terminal continuously monitors the condition of the crops through a sensing device, and the collected data is sent to a server in real time.

[0828] server

[0829] The server analyzes changes in the cultivation environment based on the received data and generates necessary reminders and additional advice, such as "Low temperatures are predicted this week, so please take measures to prevent frost."

[0830] Specific examples

[0831] Examples of organic fertilizer use

[0832] 1. Using a sensing device (e-kakashi) connected to a terminal, the pH level, humidity, and temperature of the soil are measured and the data is sent to the server.

[0833] 2. The server analyzes the received data using generative artificial intelligence and generates advice on the appropriate timing and amount of organic fertilizer to use based on the condition of the soil.

[0834] 3. The server sends the generated advice to the terminal and notifies the farmer.

[0835] 4. The user (farmer) applies organic fertilizer based on the advice received through the terminal and observes the results.

[0836] 5. The terminal measures the observation results again using the sensing device and sends the data to the server.

[0837] 6. The server analyzes the new data and generates additional advice if necessary, and notifies the farmer via the terminal.

[0838] Examples of pest prevention

[0839] 1. The server trains the generative AI to learn about the ecology of pests and diseases and preventive measures.

[0840] 2. The terminal uses a sensing device (e-kakashi) to collect data on the crops and their surrounding environment and transmits it to the server.

[0841] 3. The server analyzes the received data using generative artificial intelligence and generates advice on risk assessments of pest and disease outbreaks and preventive measures.

[0842] 4. The server sends the generated advice to the terminal and notifies the farmer.

[0843] 5. The user (farmer) implements preventive measures based on the advice and observes the results.

[0844] 6. The device measures the observations and sends them to the server.

[0845] 7. The server continuously analyzes the data, generates new advice, and notifies the farmer via his / her terminal.

[0846] Prompt Sentence Examples

[0847] 1. What is the appropriate time and amount to use organic fertilizer?

[0848] 2. What measures are necessary to prevent pests and diseases?

[0849] As described above, the system of the present invention effectively supports farmers in accurately grasping the knowledge and timing necessary for pesticide-free cultivation and putting it into practice.

[0850] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0851] Step 1:

[0852] Data collection

[0853] The server collects data on organic farming from sources including the internet and existing databases, including types of organic fertilizers and their application methods, pest and disease ecology, and climate data.

[0854] Input: Raw data from the internet and existing databases.

[0855] Output: Data related to pesticide-free cultivation before cleansing.

[0856] What it does: The server collects data using APIs and web scraping and stores it in a local database.

[0857] Step 2:

[0858] Data Cleansing

[0859] The server cleanses the collected data, removing noise and missing data, thereby improving the quality of the data.

[0860] Input: Raw data collected.

[0861] Output: Clean, cleansed data.

[0862] What it does: The server runs algorithms to detect outliers and impute missing values, for example filtering out abnormal pH values, temperatures, etc.

[0863] Step 3:

[0864] Data normalization

[0865] The server normalizes the cleansed data and puts it into a format that is easy for the generative AI model to understand.

[0866] Input: Cleansed data.

[0867] Output: Normalized data.

[0868] Specific operation: The server performs data scaling and normalization to convert numeric data into a certain range.

[0869] Step 4:

[0870] Model learning

[0871] The server uses the normalized data to train a generative AI model (using TensorFlow or PyTorch).

[0872] Input: Normalized data.

[0873] Output: The trained model.

[0874] Specific operation: The server applies a machine learning algorithm to teach the model know-how regarding pesticide-free cultivation.

[0875] Step 5:

[0876] Save Model

[0877] The server stores the trained model and updates it as needed.

[0878] Input: A trained model.

[0879] Output: The saved model.

[0880] Specific operation: The server saves the trained model in a database and sets a schedule for periodic retraining.

[0881] Step 6:

[0882] Sensing

[0883] A sensing device (e.g., e-kakashi) connected to the terminal periodically collects data such as soil quality, temperature, humidity, and light intensity.

[0884] Input: Environmental data (temperature, humidity, light level, etc.).

[0885] Output: Collected environmental data.

[0886] Specific operation: The device periodically reads data from the sensors and temporarily stores it in local storage.

[0887] Step 7:

[0888] Data transmission

[0889] The device sends the collected data to a server via Wi-Fi or mobile communications.

[0890] Input: Collected environmental data.

[0891] Output: The data sent to the server.

[0892] Specific operation: The terminal transmits data to the server via the network in real time or in batch processing.

[0893] Step 8:

[0894] Data reception

[0895] The server receives the data sent from the terminal.

[0896] Input: Data sent from the terminal.

[0897] Output: The received data.

[0898] Specific operation: The server immediately stores the received data in a database and prepares it for analysis.

[0899] Step 9:

[0900] Data analysis

[0901] The server analyzes the received data using a generative AI model to diagnose the current condition of the crops.

[0902] Input: Received data, trained model.

[0903] Output: Diagnostic results.

[0904] Specific operation: The server inputs data into the generative AI model and analyzes the health of the crops and necessary measures.

[0905] Step 10:

[0906] Advice Generation

[0907] Based on the analysis results, the server generates advice and reminders on pesticide-free farming.

[0908] Input: Diagnostic results.

[0909] Output: Advice and reminders.

[0910] Specific actions: The server automatically generates a sentence that suggests appropriate measures and instructions for action.

[0911] Step 11:

[0912] Send Advice

[0913] The server transmits the generated advice to the terminal.

[0914] Input: Advice and reminders.

[0915] Output: Advice sent to the terminal.

[0916] Specific behavior: The server sends the advice using a messaging protocol.

[0917] Step 12:

[0918] Receive feedback

[0919] The server accepts feedback and questions from users via the terminal.

[0920] Input: User feedback and questions.

[0921] Output: Feedback and questions received.

[0922] Specific operation: The device sends questions and feedback entered by the user to the server.

[0923] Step 13:

[0924] Optimal response generation

[0925] The server uses a generative AI model to generate optimal responses to the feedback and questions it receives.

[0926] Input: Feedback, questions, trained models.

[0927] Output: Best response.

[0928] Specific operation: The server inputs feedback and questions into the generative AI model to generate optimal answers and improvements.

[0929] Step 14:

[0930] Response Send

[0931] The server generates a response and sends it to the terminal.

[0932] Input: Best response.

[0933] Output: The response sent to the terminal.

[0934] Specific operation: The server sends a response to the terminal via a messaging protocol.

[0935] Step 15:

[0936] monitoring

[0937] The terminal monitors the condition of the plants in real time through sensing devices.

[0938] Input: Real-time data from sensing devices.

[0939] Output: Monitored data.

[0940] Specific operation: The terminal continuously collects data and transmits it to the server in real time.

[0941] Step 16:

[0942] Additional advice generation

[0943] The server analyzes the received monitoring data and generates additional advice and reminders as needed.

[0944] Input: Real-time monitoring data.

[0945] Output: Additional advice and reminders.

[0946] Specific operation: The server has the generative AI model further analyze the data and generate additional feedback.

[0947] Step 17:

[0948] Send additional advice

[0949] The server sends the generated additional advice to the terminal.

[0950] Input: Additional advice or reminders.

[0951] Output: Additional advice sent to the terminal.

[0952] Specific behavior: The server sends additional advice via the messaging protocol.

[0953] Through these steps, the system supports farmers in effectively implementing pesticide-free cultivation.

[0954] (Application example 1)

[0955] 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."

[0956] In pesticide-free farming, it is extremely important to acquire the know-how for proper farming practices and carry them out efficiently and effectively. However, traditional methods are prone to time lags in data collection and delayed feedback, making it difficult to obtain real-time advice. Furthermore, in the food delivery industry, there is no established method for safely and quickly delivering pesticide-free produce. Highly accurate data collection and analysis, as well as real-time information provision, are essential to resolving these issues.

[0957] 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.

[0958] In this invention, the server includes a means for collecting data on pesticide-free farming, a means for training generative AI to learn pesticide-free farming know-how, and a means for saving and updating the model resulting from the learning. This allows farmers to receive pesticide-free farming advice in real time and perform appropriate farm work. This invention also includes a means for collecting data on food delivery and a means for providing delivery routes and specific instructions. This allows for the safe and prompt delivery of pesticide-free agricultural products. Furthermore, since information is provided in real time via a head-mounted display, delivery personnel can always act based on the latest information.

[0959] "Pesticide-free cultivation" is an agricultural method that uses natural methods to prevent pests and diseases when growing crops without using chemical pesticides, and is gentle on the environment and the human body.

[0960] "Generative AI" is an AI system that analyzes large amounts of data, automatically learns patterns, and generates predictions and optimal advice.

[0961] "Know-how" is a general term for the specific techniques, knowledge, and experience required for pesticide-free cultivation.

[0962] A "model" is a mathematical or statistical representation that serves as the basis for data analysis and prediction, generated as a result of training generative artificial intelligence.

[0963] A "sensing device" is a device for measuring and collecting environmental data such as temperature, humidity, and light intensity.

[0964] "Diagnosis results" are information about the condition of crops and necessary measures generated after analyzing collected data.

[0965] "Advice" refers to specific instructions or recommendations for farmers that are generated based on the diagnostic results.

[0966] "Communication means" refers to the technical means for transmitting and receiving data between the server and the farmer's terminal.

[0967] "Feedback" refers to the results of implementing advice, as well as opinions and questions, sent by farmers to the server.

[0968] "Delivery" refers to the process of delivering pesticide-free agricultural products to consumers.

[0969] A "head-mounted display" is a display device worn on the head to display information within the field of view.

[0970] "Real-time information provision" refers to providing the analysis results of sensing devices and servers to users immediately and without delay.

[0971] This invention provides a system that realizes efficient pesticide-free cultivation and safe food delivery. This system consists of a server, terminals (including sensing devices), and users (farmers and delivery personnel).

[0972] 1. Program processing overview

[0973] server

[0974] The server collects data on pesticide-free farming and uses it to train the generative AI on the know-how of pesticide-free farming. This data includes the types of organic fertilizers and their use, the ecology of pests and diseases, and climate data. The server cleanses the collected data, removing noise and missing data. The data is then normalized and trained by the generative AI. The model generated as a result of the learning is stored on the server and updated as necessary.

[0975] Terminal

[0976] Sensing devices connected to the terminal (e.g., soil sensors and temperature / humidity sensors) periodically collect data on soil quality, temperature, humidity, light intensity, etc. The collected data is sent from the terminal to a server. The server receives the data sent from the terminal and analyzes it using generative artificial intelligence. Based on the analysis results, advice and reminders regarding pesticide-free cultivation are generated. For example, if the soil's pH level is outside the appropriate range, advice on the appropriate timing and amount of organic fertilizer to be used is generated.

[0977] User (farmer)

[0978] Farmers perform farm work based on the advice they receive through the device. For example, they may apply appropriate organic fertilizer or take measures to prevent specific pests and diseases. The results of implementing the advice and feedback they feel are entered into the device and sent to a server. Furthermore, the device monitors the condition of the crops through a sensing device and continuously sends data to the server in real time.

[0979] 2. Food delivery support

[0980] The system also has a support function to help food delivery workers deliver pesticide-free produce safely and effectively. The server collects data on food deliveries and provides optimal delivery routes and handling methods. Delivery workers can receive advice in real time using a head-mounted display.

[0981] Hardware and Software Use Cases

[0982] Hardware: Head-mounted display (e.g. Microsoft HoloLens), soil sensor, temperature and humidity sensor

[0983] Software: Python, Server API (e.g. "https: / / agriculture-data-source.com / api / getData")

[0984] 3. Adding concrete examples

[0985] Specific work examples

[0986] 1. The server collects data on pesticide-free farming through the API.

[0987] 2. Based on the collected data, generative AI learns the know-how of pesticide-free cultivation.

[0988] 3. The model generated as a result of learning is saved on the server.

[0989] 4. Farmers use sensing devices to measure soil quality, temperature, humidity, light intensity, etc., and send the data from their terminals to a server.

[0990] 5. The server performs the analysis and generates appropriate advice.

[0991] 6. Delivery personnel will wear head-mounted displays and be provided with real-time information on appropriate delivery routes and handling methods.

[0992] Prompt Sentence Examples

[0993] "The temperature is low today, so please take precautions against the cold."

[0994] "Your soil pH is dropping. Add organic fertilizer."

[0995] By using the above method, this invention enables pesticide-free cultivation and its delivery to be carried out efficiently and effectively.

[0996] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0997] Step 1:

[0998] Data collection

[0999] The server collects data on pesticide-free farming. Specifically, it obtains information on the types and use of organic fertilizers, the ecology of pests and diseases, and climate data from the Internet and existing databases. The input is a list of data to be collected, and the output is a file of the collected data.

[1000] Step 2:

[1001] Data Cleansing and Normalization

[1002] The server cleanses the collected data, removing noise and missing data. Then, it normalizes the data and formats it in a way that makes it easier for generative AI to learn. The input is the collected data file, and the output is the cleansed, normalized data.

[1003] Step 3:

[1004] Learning with generative artificial intelligence

[1005] The server uses the normalized data to train the generative AI to learn the know-how of pesticide-free cultivation. Specifically, the normalized data is input into the AI ​​model and learning is repeated. The input is the normalized data, and the output is the trained model.

[1006] Step 4:

[1007] Saving a trained model

[1008] The server saves the generated trained model and updates it as necessary. The input is the trained model, and the output is the saved model data. Specifically, the model is stored in a database within the server.

[1009] Step 5:

[1010] Data collection using sensing devices

[1011] Sensing devices (e.g., soil sensors, temperature and humidity sensors) connected to the terminal periodically collect data on soil quality, temperature, humidity, light intensity, etc. The input is the environmental data collected by the sensor, and the output is the measurement data sent to the terminal.

[1012] Step 6:

[1013] Sending data to the server

[1014] The terminal transmits the collected data to the server in real time. The input is the measurement data, and the output is the data transmitted to the server.

[1015] Step 7:

[1016] Data analysis and generation of diagnostic results

[1017] The server receives the data sent from the terminal and analyzes it using generative artificial intelligence. Specifically, it uses a data analysis algorithm to diagnose the condition of the crops and generate the results. The input is the sent data and the output is the diagnosis result.

[1018] Step 8:

[1019] Generating Advice

[1020] The server generates advice on pesticide-free farming based on the diagnostic results. For example, if the soil pH is outside the appropriate range, it will suggest the appropriate timing and amount of organic fertilizer to use. The input is the diagnostic results, and the output is advice.

[1021] Step 9:

[1022] Advice and notification of diagnostic results

[1023] The server sends the generated advice and diagnosis results to the terminal and notifies the farmer. The input is advice and diagnosis results, and the output is notification data sent to the terminal.

[1024] Step 10:

[1025] Gathering and implementing feedback

[1026] Farmers perform farm work based on the advice received through their devices, and input the results and feedback into the device and send it to the server. The server receives this feedback and reflects it in the model. The input is the feedback data, and the output is updated model data.

[1027] Step 11:

[1028] Providing delivery routes and specific instructions

[1029] The server collects data about food delivery and provides optimal delivery routes and handling methods. The input is delivery data, and the output is instructions and route data.

[1030] Step 12:

[1031] Real-time information provision

[1032] The delivery person wears a head-mounted display and receives advice and route information in real time from the server. The input is instructions and route data, and the output is information displayed on the head-mounted display.

[1033] 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.

[1034] The system of this invention includes a method and device for effectively supporting pesticide-free farming, and in particular, combines an emotion engine that recognizes the user's emotions and adjusts the content and timing of advice based on those emotions. A specific embodiment will be described below, focusing on a server, a terminal, and a user (agricultural worker).

[1035] Data collection and learning

[1036] server

[1037] The server collects a large amount of data related to pesticide-free farming from the internet and existing databases, including types of organic fertilizer and their application methods, pest and disease ecology, and climate data.

[1038] The server cleanses the collected data, removing noise and missing data. It then normalizes the data and trains it using generative AI. Specifically, the data is formatted in a way that makes it easy for the AI ​​model to understand, and it learns the know-how of pesticide-free farming.

[1039] The model generated as a result of learning is stored on the server and updated as necessary.

[1040] Crop condition diagnosis

[1041] Terminal

[1042] Sensing devices (e.g., e-kakashi) connected to the terminal periodically collect data such as soil quality, temperature, humidity, and light intensity.

[1043] The collected data is transmitted from the terminal to a server.

[1044] server

[1045] The server receives the data sent from the device and analyzes it using generative artificial intelligence. The purpose of the analysis is to diagnose the current condition of the crops and derive the necessary countermeasures.

[1046] Based on the analysis results, appropriate advice and reminders are generated. For example, if the soil pH level is outside the appropriate range, advice on the timing and amount of organic fertilizer to be used is generated.

[1047] Communication with farmers

[1048] server

[1049] The server sends the generated advice and diagnostic results to the terminal.

[1050] It also accepts feedback and questions from farmers and generates optimal answers, which are then sent to the device.

[1051] Terminal

[1052] The terminal notifies the farmer of advice and diagnostic results sent from the server, for example by providing appropriate information via an alert or display panel.

[1053] Farmers can also use their devices to input questions to the generative AI, which are then sent to the server.

[1054] User (farmer)

[1055] Farmers can then use the advice they receive through the device to carry out their farming work, such as applying appropriate organic fertilizers or taking measures to prevent specific pests and diseases.

[1056] The results of the advice and any feedback felt are entered into the device and sent to the server.

[1057] Cultivation management

[1058] Terminal

[1059] The terminal continuously monitors the condition of the crops through a sensing device, and the collected data is sent to a server in real time.

[1060] server

[1061] The server analyzes changes in the cultivation environment based on the received data and generates necessary reminders and additional advice, such as "Low temperatures are predicted this week, so please take measures to prevent frost."

[1062] Any generated reminders or additional advice will also be sent to the farmer via the device.

[1063] Combining Emotion Engines

[1064] Terminal

[1065] When the device communicates with the farmer, it uses an emotion engine to analyze the tone of voice and text content. For example, if the farmer is emotional, the emotion engine will recognize that emotion.

[1066] server

[1067] The emotion information obtained from the emotion engine is used to adjust the content and timing of the advice provided by the generative AI. For example, a farmer feeling stressed might be given simple, actionable advice along with an encouraging message.

[1068] It also fine-tunes reminders and advice based on emotions and delivers them in a format that farmers find most acceptable.

[1069] User (farmer)

[1070] Farmers implement the advice provided and enter their results and feelings into the device, which also sends emotional feedback to the server.

[1071] Specific examples

[1072] Examples of organic fertilizer use

[1073] 1. The device uses e-kakashi to measure the soil's pH level, humidity, and temperature, and sends the data to the server.

[1074] 2. The server analyzes the received data using generative artificial intelligence and generates advice on the appropriate timing and amount of organic fertilizer to use based on the condition of the soil.

[1075] 3. The server sends the generated advice to the terminal and notifies the farmer.

[1076] 4. The device uses an emotion engine to analyze the farmer's emotions, and if they are feeling stressed or anxious, it will provide advice with an encouraging message.

[1077] 5. The user (farmer) applies organic fertilizer based on the advice and observes the results. The user inputs the observation results and their feelings into the terminal and sends them to the server.

[1078] 6. The server analyzes the observation data and sentiment information and suggests new advice or adjustments as needed, for example determining whether soil conditions have improved and suggesting further preventative measures or additional fertilization.

[1079] Examples of pest prevention

[1080] 1. The server trains the generative AI to learn about the ecology of pests and diseases and preventative measures. The data includes the ecology of pests and diseases, preventative measures, and their relationship with climate.

[1081] 2. The device uses e-kakashi to collect data on the condition of the crops and the surrounding environment (temperature, humidity, air temperature, etc.) and send it to the server.

[1082] 3. The server analyzes the received data using generative artificial intelligence and generates a risk assessment of pest and disease outbreaks and preventive measures.

[1083] 4. The server generates advice including preventive measures based on the risk assessment and sends the advice to the terminal.

[1084] 5. The device analyzes the farmer's emotions using an emotion engine and tailors advice based on their emotions. For example, it provides detailed instructions on specific procedures to farmers who are feeling anxious.

[1085] 6. The user (farmer) implements preventive measures based on the advice received, for example, installing moth nets or spraying natural pesticides.

[1086] 7. The device monitors the results again through e-kakashi and sends the data to the server.

[1087] 8. The server analyzes the monitoring data and emotional information to evaluate the effectiveness of preventive measures, and generates additional measures and reminders as needed, and notifies users via their devices.

[1088] Through the above processing steps, this invention effectively supports pesticide-free cultivation, enabling farmers to accurately grasp the necessary know-how and timing and put it into practice. By combining it with an emotion engine, it is possible to provide support that matches the psychological state of farmers, improving work efficiency and satisfaction.

[1089] The processing flow will be explained below.

[1090] Examples of organic fertilizer use

[1091] Step 1:

[1092] The device uses e-kakashi to measure the soil's pH level, humidity, and temperature, and then sends the data to the server.

[1093] Step 2:

[1094] The server refers to the contents of the database based on the data received and preprocesses the data, specifically removing outliers and normalizing the data.

[1095] Step 3:

[1096] The server uses generative artificial intelligence to analyze the pre-processed data and generate information on the current state of the crops and the appropriate use of organic fertilizer.

[1097] Step 4:

[1098] Based on the analysis results, the server generates advice including the appropriate timing and amount of organic fertilizer to use and sends that advice to the terminal.

[1099] Step 5:

[1100] The terminal notifies the farmer of the advice sent from the server, for example by displaying the information via an alert or a display panel.

[1101] Step 6:

[1102] The device uses an emotion engine to analyze the farmer's emotions, and if they are feeling stressed or anxious, it will provide advice along with an encouraging message.

[1103] Step 7:

[1104] The user (farmer) applies organic fertilizer based on the advice, observes the results, and inputs their observations and their feelings into the device.

[1105] Step 8:

[1106] The device collects observations and emotional information and sends the data to a server.

[1107] Step 9:

[1108] The server analyzes the observation data and sentiment information and suggests new advice or adjustments as needed, for example determining whether soil conditions have improved and suggesting further preventative measures or additional fertilization.

[1109] Examples of pest prevention

[1110] Step 1:

[1111] The server trains the generative AI with data on pests and diseases, including their ecology, preventative measures, and their relationship with climate.

[1112] Step 2:

[1113] The terminal uses e-kakashi to collect data on the condition of the crops and the surrounding environment (temperature, humidity, air temperature, etc.) and send it to the server.

[1114] Step 3:

[1115] The server preprocesses the received data, removing outliers and normalizing the data.

[1116] Step 4:

[1117] The server analyzes the preprocessed data using generative artificial intelligence to generate risk assessments and preventative measures for pest and disease outbreaks.

[1118] Step 5:

[1119] The server generates advice including preventive measures based on the risk assessment and transmits the advice to the terminal.

[1120] Step 6:

[1121] The terminal notifies the farmer of the advice sent from the server, for example by providing information using a display panel or alerts.

[1122] Step 7:

[1123] The device uses an emotion engine to analyze the farmer's emotions and tailor advice based on their feelings, for example providing detailed instructions on specific procedures to farmers who are feeling anxious.

[1124] Step 8:

[1125] The user (farmer) implements preventive measures based on the advice received, for example, installing moth nets or spraying natural pesticides.

[1126] Step 9:

[1127] The device monitors the results again through e-kakashi and sends the data to the server.

[1128] Step 10:

[1129] The server analyzes the monitoring data and emotional information to evaluate the effectiveness of preventive measures, and generates additional measures and reminders as needed, which are then sent via the device.

[1130] These processing steps effectively support pesticide-free cultivation, allowing farmers to accurately grasp the necessary know-how and timing, and then carry it out.By combining it with an emotion engine, it is possible to provide support that matches the psychological state of farmers, improving work efficiency and satisfaction.

[1131] Example 2

[1132] 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."

[1133] In modern agriculture, pesticide-free cultivation is becoming increasingly important from the perspectives of health and environmental protection, but its implementation requires advanced expertise and technology. Furthermore, because the emotions and psychological state of farmers also affect work efficiency and satisfaction, support that takes emotions into consideration is also necessary. Conventional systems have difficulty addressing these complex challenges, particularly in terms of real-time condition monitoring and adjusting advice based on emotions.

[1134] 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.

[1135] In this invention, the server includes: means for collecting data on pesticide-free farming; means for training a generative artificial intelligence (AI) to learn know-how about pesticide-free farming; means for saving and updating the model as the learning result; means for collecting crop condition data using a sensing device; means for analyzing the crop condition data and generating diagnostic results; means for providing advice on pesticide-free farming based on the diagnostic results; means for transmitting the advice and diagnostic results and communicating with the farmer; means for receiving feedback from the farmer and reflecting it in the model; means for analyzing the farmer's emotions; and means for adjusting the content and timing of advice based on the analyzed emotional information. This allows farmers to acquire know-how about pesticide-free farming in real time and perform farm work efficiently and effectively. Furthermore, emotionally sensitive support can improve work efficiency and satisfaction.

[1136] "Pesticide-free cultivation" is an agricultural method in which crops are grown without the use of pesticides, and is important from the perspectives of health and environmental protection.

[1137] "Data collection means" refers to devices or mechanisms that obtain necessary data from sensors, databases, the Internet, etc.

[1138] "Generative AI" is an AI system that learns from collected data and generates solutions and advice for specific problems.

[1139] A "learning result model" is a collection of solutions and know-how for specific problems that is obtained as a result of learning by generative artificial intelligence.

[1140] A "sensing device" is a device used to measure and record the condition of soil and the environment, collecting data such as temperature, humidity, and light intensity.

[1141] "Crop condition data" refers to information about the cultivation environment and growth of crops, such as soil conditions, weather conditions, and crop growth status.

[1142] "Analysis means" refers to a method or device for analyzing collected data and deriving useful information or knowledge.

[1143] "Diagnosis results" are conclusions about the current state and future predictions drawn based on collected and analyzed data.

[1144] "Advice delivery methods" are systems or mechanisms that provide specific guidelines and recommendations based on diagnostic results.

[1145] "Communication means" refers to a system for two-way exchange of data and information, and often refers specifically to connections with agricultural workers.

[1146] "Feedback receiving means" is a mechanism for receiving reactions and results from users.

[1147] "Emotion analysis means" refers to a method or device for analyzing a user's emotions and psychological state, and infers emotions from the tone of voice and the content of text.

[1148] "Advice adjustment means" refers to a system or method that changes the content and timing of advice provided based on the results of sentiment analysis.

[1149] The system of this invention includes a method and device for effectively supporting pesticide-free cultivation, and in particular, combines an emotion engine that recognizes the user's emotions and adjusts the content and timing of advice based on those emotions. Specific embodiments focusing on a server, a terminal, and a user (agricultural worker) are described below.

[1150] Data collection and learning

[1151] server

[1152] The server collects a large amount of data related to pesticide-free farming from the internet and existing databases, including types of organic fertilizer and their application methods, pest and disease ecology, and climate data.

[1153] The server cleanses the collected data, removing noise and missing data, then normalizes it and trains the generative AI model. Specifically, the data is formatted in a way that makes it easy for the AI ​​model to understand, and it learns the know-how of pesticide-free farming.

[1154] The model generated as a result of learning is stored on the server and updated as necessary.

[1155] Crop condition diagnosis

[1156] Terminal

[1157] Sensing devices (e.g., ec sensing devices) connected to the terminal periodically collect data such as soil quality, temperature, humidity, and light intensity.

[1158] The collected data is transmitted from the terminal to a server.

[1159] server

[1160] The server receives the data sent from the device and analyzes it using a generative AI model. The purpose of the analysis is to diagnose the current condition of the crops and derive the necessary countermeasures.

[1161] Based on the analysis results, appropriate advice and reminders are generated. For example, if the soil pH level is outside the appropriate range, advice on the timing and amount of organic fertilizer to be used is generated.

[1162] Communication with farmers

[1163] server

[1164] The server sends the generated advice and diagnostic results to the terminal.

[1165] It also accepts feedback and questions from farmers and generates optimal answers, which are then sent to the device.

[1166] Terminal

[1167] The terminal notifies the farmer of advice and diagnostic results sent from the server, for example by providing appropriate information via an alert or display panel.

[1168] Farmers can also use their devices to input questions to the generative AI model, which are also sent to the server.

[1169] User (farmer)

[1170] Farmers can then carry out farm work based on the advice they receive through the device, such as applying appropriate organic fertilizer and taking measures to prevent pests and diseases.

[1171] The results of the advice and any feedback felt are entered into the device and sent to the server.

[1172] Cultivation management

[1173] Terminal

[1174] The terminal continuously monitors the condition of the crops through a sensing device, and the collected data is sent to a server in real time.

[1175] server

[1176] The server analyzes changes in the cultivation environment based on the received data and generates necessary reminders and additional advice, such as "Low temperatures are predicted this week, so please take measures to prevent frost."

[1177] Any generated reminders or additional advice will also be sent to the farmer via the device.

[1178] Combining Emotion Engines

[1179] Terminal

[1180] When the device communicates with the farmer, it uses an emotion engine to analyze the tone of voice and text content. For example, if the farmer is emotional, the emotion engine will recognize that emotion.

[1181] server

[1182] The emotion information obtained from the emotion engine is used to tailor the content and timing of the advice provided by the generative AI model. For example, a farmer experiencing stress might be given a simple, actionable piece of advice along with an encouraging message.

[1183] It also fine-tunes reminders and advice based on emotions and delivers them in a format that farmers find easy to accept.

[1184] User (farmer)

[1185] Farmers implement the advice provided and enter the results and emotions they felt into the device, which also sends emotional feedback to the server.

[1186] Specific examples

[1187] Examples of organic fertilizer use

[1188] 1. The device uses a sensing device to measure the soil's pH level, humidity, and temperature, and then sends the data to the server.

[1189] 2. The server analyzes the received data using a generative AI model and generates advice on the appropriate timing and amount of organic fertilizer to use based on the condition of the soil.

[1190] 3. The server sends the generated advice to the terminal and notifies the farmer.

[1191] 4. The device uses an emotion engine to analyze the farmer's emotions, and if they are feeling stressed or anxious, it will provide advice with an encouraging message.

[1192] 5. The user (farmer) applies organic fertilizer based on the advice and observes the results. The user inputs the observation results and their feelings into the device and sends them to the server.

[1193] 6. The server analyzes the observation data and sentiment information and suggests new advice or adjustments as needed, for example determining whether soil conditions have improved and suggesting further preventative measures or additional fertilization.

[1194] Examples of pest prevention

[1195] 1. The server trains the generative AI to learn about the ecology of pests and diseases and preventative measures. The data includes the ecology of pests and diseases, preventative measures, and their relationship with climate.

[1196] 2. The terminal uses a sensing device to collect data on the condition of the crops and the surrounding environment (temperature, humidity, air temperature, etc.) and transmits it to the server.

[1197] 3. The server analyzes the received data using a generative AI model to generate a risk assessment of pest and disease outbreaks and generate preventive measures.

[1198] 4. The server generates advice including preventive measures based on the risk assessment and sends the advice to the terminal.

[1199] 5. The device analyzes the farmer's emotions using an emotion engine and tailors advice based on their emotions. For example, it provides detailed instructions on specific procedures to farmers who are feeling anxious.

[1200] 6. The user (farmer) implements preventive measures based on the advice received, for example, installing moth nets or spraying natural pesticides.

[1201] 7. The terminal monitors the implementation results again through the sensing device and sends the data to the server.

[1202] 8. The server analyzes the monitoring data and emotional information to evaluate the effectiveness of preventive measures, and generates additional measures and reminders as needed, and notifies users via their devices.

[1203] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1204] Step 1:

[1205] Data collection

[1206] The server collects data on pesticide-free farming from the internet and existing databases, including the type of organic fertilizer, how it is used, the ecology of pests and diseases, and weather data.

[1207] Input: Internet databases and meteorological data related to pesticide-free farming.

[1208] Output: Collected data before cleansing.

[1209] Specific behavior: Extract data via API and store it in a local database.

[1210] Step 2:

[1211] Data Cleansing and Learning

[1212] The server cleanses the collected data, removing noise and missing data, then normalizes the data and trains the generative AI model.

[1213] Input: Collected data before cleansing.

[1214] Output: Cleansed and normalized training data and a trained model.

[1215] What it does: It uses database queries and data analysis tools to remove unnecessary data and feed it to machine learning algorithms.

[1216] Step 3:

[1217] Collecting data on crop conditions

[1218] The terminal uses a sensing device to periodically collect data such as soil quality, temperature, humidity, and light intensity and transmits it to a server.

[1219] Input: Real-time data from soil and environmental sensors.

[1220] Output: Collected crop condition data.

[1221] Specific operation: Data is acquired from the sensing device, stored on the terminal, and then sent to the server.

[1222] Step 4:

[1223] Analysis of crop conditions

[1224] The server analyzes the crop condition data sent from the device using a generative AI model, generates diagnostic results, and derives necessary countermeasures.

[1225] Input: Crop status data sent from the terminal.

[1226] Output: Diagnostic results and remedial action.

[1227] What it does: It uses data analysis algorithms to extract meaningful features from the data and make predictions based on the model.

[1228] Step 5:

[1229] Advice Generation and Notifications

[1230] The server generates appropriate advice and reminders based on the analysis results and sends them to the device.

[1231] Input: Diagnostic results and remedial action.

[1232] Output: Advice and reminders.

[1233] Specific operation: Advice is created using a generative AI model and the data is sent to the device.

[1234] Step 6:

[1235] Giving and receiving feedback from farmers

[1236] The terminal notifies the farmer of advice and diagnostic results from the server, who then performs farm work based on the advice and enters feedback into the terminal.

[1237] Input: Advice and diagnostic results from the server.

[1238] Output: Farmer feedback.

[1239] Specific behavior: Uses the notification system to display advice and records user input.

[1240] Step 7:

[1241] Sentiment analysis and advice adjustment

[1242] The device uses an emotion engine to analyze the farmer's emotions and transmits the results to a server, which then adjusts the content and timing of advice based on the emotional information.

[1243] Input: Farmer sentiment data.

[1244] Output: Adjusted advice.

[1245] What it does: It uses speech and text analysis tools to determine emotional state, sends that information to a server, and generates and resends tailored advice.

[1246] Step 8:

[1247] Continuous monitoring and updates

[1248] The terminal continuously monitors the condition of the crops through a sensing device and transmits the data in real time to the server, which analyzes the received data and generates necessary reminders and additional advice.

[1249] Input: Continuous real-time data from sensing equipment.

[1250] Output: Reminders and additional advice.

[1251] Specific operation: Collect and transmit data using a real-time data collection system, and generate new advice and reminders based on the analysis results.

[1252] (Application example 2)

[1253] 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."

[1254] In pesticide-free cultivation, farmers need a lot of effort and knowledge to obtain appropriate advice. Furthermore, the timing and content of information provided about cultivation is uniform, making it difficult to respond to the emotions and psychological state of farmers. This prevents farmers from obtaining the necessary information at the right time, which can result in reduced cultivation efficiency and increased stress.

[1255] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1256] In this invention, the server includes means for collecting data on pesticide-free farming and having the generative AI learn know-how about pesticide-free farming, means for saving and updating the model resulting from the learning, means for recognizing the emotional state of the farmer, and means for adjusting the content and timing of advice based on the emotional state, thereby enabling the farmer to receive the most appropriate advice and information at the appropriate time according to his or her emotional state.

[1257] "Pesticide-free cultivation" is a method of cultivating crops using natural materials and techniques without using chemical pesticides.

[1258] "Data collection means" refers to devices and systems for collecting data on pesticide-free cultivation and crop condition data.

[1259] "Generative AI" refers to AI that has the ability to learn specific knowledge and skills based on large amounts of data, and as a result generate useful information and advice.

[1260] "Know-how" refers to the practical knowledge and skills required for a specific purpose.

[1261] A "sensing device" is a device for collecting environmental data such as temperature, humidity, and soil quality.

[1262] "Diagnosis results" are information on the condition of crops and appropriate countermeasures obtained as a result of analyzing collected data.

[1263] "Advice providing means" refers to a device or system that provides specific instructions and advice to farmers based on the generated diagnostic results and know-how.

[1264] "Communication means" means a device or system for transmitting advice and diagnostic results to farmers and receiving feedback from farmers.

[1265] An "emotional state" refers to the feelings or psychological state that a person is in.

[1266] "Feedback receiving means" refers to a device or system for receiving opinions and feedback from farmers.

[1267] A "model updating means" is a device or system that improves or modifies an existing artificial intelligence model based on collected data and feedback.

[1268] A "timing adjustment means" is a device or system that takes into account the emotional state of the farmer and determines the optimal timing for providing advice.

[1269] The system of this invention includes a method and device for effectively supporting pesticide-free cultivation, and in particular, it combines an emotion engine that recognizes the emotions of farmers and adjusts the content and timing of advice based on those emotions. Specific embodiments focusing on a server, a terminal, and a user (agricultural worker) are described below.

[1270] Data collection and learning

[1271] server

[1272] The server collects large amounts of data related to pesticide-free farming from the internet and existing databases. This includes the types and use of organic fertilizers, the ecology of pests and diseases, and climate data. The server then cleanses the collected data, removing noise and missing data. It then normalizes the data and trains it using generative AI. Specifically, the data is formatted in a way that is easy for the AI ​​model to understand, and it is trained to learn the know-how of pesticide-free farming. The model generated as a result of the training is stored on the server and updated as necessary.

[1273] Crop condition diagnosis

[1274] Terminal

[1275] The sensing device connected to the terminal periodically collects data on soil quality, temperature, humidity, light intensity, etc. The collected data is then sent from the terminal to a server.

[1276] server

[1277] The server receives the data sent from the device and analyzes it using generative artificial intelligence. The purpose of the analysis is to diagnose the current condition of the crops and determine the necessary countermeasures. Based on the analysis results, appropriate advice and reminders are generated. For example, if the soil pH level is outside the appropriate range, advice is generated on the appropriate timing and amount of organic fertilizer to be used.

[1278] Communication with farmers

[1279] server

[1280] The server sends the generated advice and diagnostic results to the device. It also accepts feedback and questions from farmers and generates optimal answers to those questions. These answers are also sent to the device.

[1281] Terminal

[1282] The terminal notifies the farmer of advice and diagnostic results sent from the server. For example, appropriate information is provided via alerts or a display panel. Farmers can also use the terminal to input questions to the generative AI, which is also sent to the server.

[1283] User (farmer)

[1284] Farmers perform farm work based on the advice they receive through their devices. For example, they may apply appropriate organic fertilizer or take measures to prevent specific pests and diseases. The results of implementing the advice and any feedback they feel are entered into the device and sent to the server.

[1285] Cultivation management

[1286] Terminal

[1287] The terminal continuously monitors the condition of the crops through a sensing device, and the collected data is sent to a server in real time.

[1288] server

[1289] The server analyzes changes in the cultivation environment based on the received data and generates necessary reminders and additional advice. For example, it could say, "Low temperatures are predicted this week, so please take measures to prevent frost." The generated reminders and additional advice are also notified to farmers via their terminals.

[1290] Combining Emotion Engines

[1291] Terminal

[1292] When the device communicates with the farmer, it uses an emotion engine to analyze the tone of voice and text content. For example, if the farmer is emotional, the emotion engine will recognize that emotion.

[1293] server

[1294] The content and timing of advice provided by the generative AI is adjusted based on the emotional information obtained from the emotion engine. For example, a farmer feeling stressed can be provided with simple, actionable advice along with an encouraging message. The system also fine-tunes the content of reminders and advice based on emotions, providing them in a format that is easy for farmers to accept.

[1295] User (farmer)

[1296] Farmers implement the advice provided and enter their results and feelings into the device, which also sends emotional feedback to the server.

[1297] Example: Use of organic fertilizer

[1298] 1. The device uses a sensing device to measure the soil's pH level, humidity, and temperature, and then sends the data to the server.

[1299] 2. The server analyzes the received data using generative artificial intelligence and generates advice on the appropriate timing and amount of organic fertilizer to use based on the condition of the soil.

[1300] 3. The server sends the generated advice to the terminal and notifies the farmer.

[1301] 4. The device uses an emotion engine to analyze the farmer's emotions, and if they are feeling stressed or anxious, it will provide advice with an encouraging message.

[1302] 5. The user (farmer) applies organic fertilizer based on the advice and observes the results. The user inputs the observation results and their feelings into the terminal and sends them to the server.

[1303] 6. The server analyzes the observation data and sentiment information and suggests new advice or adjustments as needed, for example determining whether soil conditions have improved and suggesting further preventative measures or additional fertilization.

[1304] Example: Prevention of pests and diseases

[1305] 1. The server trains the generative AI to learn about the ecology of pests and diseases and preventative measures. The data includes the ecology of pests and diseases, preventative measures, and their relationship with climate.

[1306] 2. The terminal uses a sensing device to collect data on the condition of the crops and the surrounding environment (temperature, humidity, air temperature, etc.) and transmits it to the server.

[1307] 3. The server analyzes the received data using generative artificial intelligence and generates a risk assessment of pest and disease outbreaks and preventive measures.

[1308] 4. The server generates advice including preventive measures based on the risk assessment and sends the advice to the terminal.

[1309] 5. The device analyzes the farmer's emotions using an emotion engine and tailors advice based on their emotions. For example, it provides detailed instructions on specific procedures to farmers who are feeling anxious.

[1310] 6. The user (farmer) implements preventive measures based on the advice received, for example, installing moth nets or spraying natural pesticides.

[1311] 7. The terminal monitors the implementation results again through the sensing device and sends the data to the server.

[1312] 8. The server analyzes the monitoring data and emotional information to evaluate the effectiveness of preventive measures, and generates additional measures and reminders as needed, and notifies users via their devices.

[1313] Examples of prompts:

[1314] "User types in question: 'What fertilizer should I use for the current weather?'

[1315] Prompt for generative AI model: "User emotional state: Neutral. Input question: What fertilizer should I use based on the current weather?"

[1316] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1317] Step 1:

[1318] The server collects data on pesticide-free farming. The data is collected from the internet and existing databases, and mainly covers the types and usage of organic fertilizers, the ecology of pests and diseases, and climate data. The input is data from the source, and the output is cleansed data. The data is cleansed and noise and missing data are removed.

[1319] Step 2:

[1320] The server normalizes the cleansed data and trains it using generative AI. In this process, the data is converted into a format suitable for the AI ​​model, and the AI ​​is trained on the know-how of pesticide-free farming. The input is the cleansed data, and the output is a trained AI model.

[1321] Step 3:

[1322] The trained model is stored on the server and updated as needed. The server manages model versions and always maintains the latest cultivation know-how. The input is the trained AI model, and the output is the stored model.

[1323] Step 4:

[1324] A sensing device connected to the terminal periodically collects data on soil quality, temperature, humidity, light intensity, etc. The input is real-time data from the sensing device, and the output is data sent to the server.

[1325] Step 5:

[1326] The server receives the data sent from the device and analyzes it using generative artificial intelligence. The purpose of the analysis is to diagnose the current condition of the crops and derive the necessary countermeasures. The input is the condition data from the device, and the output is advice as the diagnosis result.

[1327] Step 6:

[1328] The server sends the generated advice and diagnostic results to the terminal. The server also responds to feedback and questions from the user as needed. The input is the diagnostic results and advice, and the output is the information sent to the terminal.

[1329] Step 7:

[1330] The terminal notifies the farmer of advice and diagnostic results sent from the server. Specifically, appropriate information is provided through alerts and display panels. The input is advice and diagnostic results, and the output is notifications to the farmer.

[1331] Step 8:

[1332] Farmers use terminals to input questions to the generative AI. The questions are sent from the terminals to the server. The input is the farmer's question, and the output is the question sent to the server.

[1333] Step 9:

[1334] The server recognizes the farmer's emotional state. It uses an emotion engine to analyze the tone of voice and text content. The input is the farmer's voice or text data, and the output is the analyzed emotional state.

[1335] Step 10:

[1336] The server adjusts the content and timing of advice based on the emotional state. If the user is feeling stressed, the server provides advice along with an encouraging message. The input is the analyzed emotional state, and the output is the adjusted advice.

[1337] Step 11:

[1338] Farmers perform farm work based on the advice provided. They input their results and feelings into a terminal and send them to a server. The input is the farmer's feedback, and the output is the feedback sent to the server.

[1339] Step 12:

[1340] The server analyzes the observation data and sentiment information and proposes new advice or adjustments as needed. The input is the farmer's feedback and observation data, and the output is new advice.

[1341] Examples of prompts:

[1342] "User types in question: 'What fertilizer should I use for the current weather?'

[1343] Prompt for generative AI model: "User emotional state: Neutral. Input question: What fertilizer should I use based on the current weather?"

[1344] 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.

[1345] 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.

[1346] 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.

[1347] [Third embodiment]

[1348] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[1349] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[1350] 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).

[1351] 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.

[1352] 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.

[1353] 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).

[1354] 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.

[1355] 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.

[1356] 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.

[1357] 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.

[1358] 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.

[1359] 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."

[1360] The system of the present invention includes a method and an apparatus for effectively supporting pesticide-free cultivation. A specific embodiment will be described below, focusing on a server, a terminal, and a user (agricultural worker).

[1361] Data collection and learning

[1362] server

[1363] The server collects a large amount of data related to pesticide-free farming from the internet and existing databases, including types of organic fertilizer and their application methods, pest and disease ecology, and climate data.

[1364] The server cleanses the collected data, removing noise and missing data. It then normalizes the data and trains it using generative AI. Specifically, the data is formatted in a way that makes it easy for the AI ​​model to understand, and it learns the know-how of pesticide-free farming.

[1365] The model generated as a result of learning is stored on the server and updated as necessary.

[1366] Crop condition diagnosis

[1367] Terminal

[1368] Sensing devices (e.g., e-kakashi) connected to the terminal periodically collect data such as soil quality, temperature, humidity, and light intensity.

[1369] The collected data is transmitted from the terminal to a server.

[1370] server

[1371] The server receives the data sent from the device and analyzes it using generative artificial intelligence. The purpose of the analysis is to diagnose the current condition of the crops and derive the necessary countermeasures.

[1372] Based on the analysis results, appropriate advice and reminders are generated. For example, if the soil pH level is outside the appropriate range, advice on the timing and amount of organic fertilizer to be used is generated.

[1373] Communication with farmers

[1374] server

[1375] The server sends the generated advice and diagnostic results to the terminal.

[1376] It also accepts feedback and questions from farmers and generates optimal answers, which are then sent to the device.

[1377] Terminal

[1378] The terminal notifies the farmer of advice and diagnostic results sent from the server, for example by providing appropriate information via an alert or display panel.

[1379] Farmers can also use their devices to input questions to the generative AI, which are then sent to the server.

[1380] User (farmer)

[1381] Farmers can then use the advice they receive through the device to carry out their farming work, such as applying appropriate organic fertilizers or taking measures to prevent specific pests and diseases.

[1382] The results of the advice and any feedback felt are entered into the device and sent to the server.

[1383] Cultivation management

[1384] Terminal

[1385] The terminal continuously monitors the condition of the crops through a sensing device, and the collected data is sent to a server in real time.

[1386] server

[1387] The server analyzes changes in the cultivation environment based on the received data and generates necessary reminders and additional advice, such as "Low temperatures are predicted this week, so please take measures to prevent frost."

[1388] Any generated reminders or additional advice will also be sent to the farmer via the device.

[1389] Specific examples

[1390] Examples of organic fertilizer use

[1391] 1. The device uses e-kakashi to measure the soil's pH level, humidity, and temperature, and sends the data to the server.

[1392] 2. The server analyzes the received data using generative artificial intelligence and generates advice on the appropriate timing and amount of organic fertilizer to use based on the condition of the soil.

[1393] 3. The server sends the generated advice to the terminal and notifies the farmer.

[1394] 4. The user (farmer) applies organic fertilizer based on the advice and observes the results.

[1395] 5. The terminal measures the observation results again using the sensing device and sends the data to the server.

[1396] 6. The server analyzes the new data and generates additional advice if necessary, and notifies the farmer via the terminal.

[1397] Examples of pest prevention

[1398] 1. The server trains the generative AI to learn about the ecology of pests and diseases and preventive measures.

[1399] 2. The device uses e-kakashi to collect data on the crops and their surrounding environment and transmits it to the server.

[1400] 3. The server analyzes the received data using generative artificial intelligence and generates advice on risk assessments of pest and disease outbreaks and preventive measures.

[1401] 4. The server sends the generated advice to the terminal and notifies the farmer.

[1402] 5. The user (farmer) implements preventive measures based on the advice and observes the results.

[1403] 6. The device measures the observations and sends them to the server.

[1404] 7. The server continuously analyzes the data, generates new advice, and notifies the farmer via his / her terminal.

[1405] As described above, this system enables farmers to accurately grasp the know-how and timing required for pesticide-free cultivation and then put it into practice.

[1406] The processing flow will be explained below.

[1407] Examples of organic fertilizer use

[1408] Step 1:

[1409] The device uses e-kakashi to measure the soil's pH level, humidity, and temperature, and then sends the data to the server.

[1410] Step 2:

[1411] The server refers to the contents of the database based on the data received and preprocesses the data, specifically removing outliers and normalizing the data.

[1412] Step 3:

[1413] The server uses generative artificial intelligence to analyze the pre-processed data and generate information on the current state of the crops and the appropriate use of organic fertilizer.

[1414] Step 4:

[1415] Based on the analysis results, the server generates advice including the appropriate timing and amount of organic fertilizer to use and sends that advice to the terminal.

[1416] Step 5:

[1417] The terminal notifies the farmer of the advice sent from the server, for example by displaying the information via an alert or a display panel.

[1418] Step 6:

[1419] The user (farmer) applies organic fertilizer based on the advice, observes the results, and enters the observation results into the terminal.

[1420] Step 7:

[1421] The device collects the observations and sends the data to a server.

[1422] Step 8:

[1423] The server analyzes the observation data and suggests new advice or adjustments as needed, for example determining whether soil conditions have improved and suggesting further preventative measures or additional fertilization.

[1424] Examples of pest prevention

[1425] Step 1:

[1426] The server trains the generative AI with data on pests and diseases, including their ecology, preventative measures, and their relationship with climate.

[1427] Step 2:

[1428] The terminal uses e-kakashi to collect data on the condition of the crops and the surrounding environment (temperature, humidity, air temperature, etc.) and send it to the server.

[1429] Step 3:

[1430] The server preprocesses the received data, removing outliers and normalizing the data.

[1431] Step 4:

[1432] The server analyzes the preprocessed data using generative artificial intelligence to generate risk assessments and preventative measures for pest and disease outbreaks.

[1433] Step 5:

[1434] The server generates advice including preventive measures based on the risk assessment and transmits the advice to the terminal.

[1435] Step 6:

[1436] The terminal notifies the farmer of the advice sent from the server, for example by providing information using a display panel or alerts.

[1437] Step 7:

[1438] The user (farmer) implements preventive measures based on the advice received, for example, installing moth nets or spraying natural pesticides.

[1439] Step 8:

[1440] The device monitors the results again through e-kakashi and sends the data to the server.

[1441] Step 9:

[1442] The server analyzes the monitoring data and evaluates the effectiveness of preventive measures, generating additional measures and reminders as needed and sending notifications via the device.

[1443] Through the above processing steps, the present invention effectively supports pesticide-free cultivation, enabling farmers to accurately grasp and implement the necessary know-how and timing.

[1444] Example 1

[1445] 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."

[1446] Practicing pesticide-free cultivation in the agricultural field is extremely delicate and complex. To successfully cultivate crops without pesticides, it is necessary to use organic fertilizer at the appropriate time, prevent pests and diseases, and constantly monitor the condition of the crops. However, acquiring the knowledge and skills necessary to achieve this requires a great deal of effort and time. For this reason, there is a need for a support system to help farmers cultivate crops without pesticides effectively.

[1447] 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.

[1448] In this invention, the server includes a means for collecting data on pesticide-free cultivation, a means for training the artificial intelligence to learn know-how on pesticide-free cultivation based on the data on pesticide-free cultivation, and a means for saving and updating the model as a result of the learning, thereby making it possible to provide optimal advice and diagnostic results on pesticide-free cultivation.

[1449] "Data on pesticide-free cultivation" refers to information related to the knowledge and techniques required to carry out pesticide-free cultivation, including types of organic fertilizers and how to use them, the ecology of pests and diseases, and climate data.

[1450] "Generative AI" refers to AI that uses technologies such as machine learning and deep learning to analyze data and automatically generate and learn knowledge for specific purposes.

[1451] "Sensing device" refers to a measuring device used to measure parameters of the crop environment, such as soil quality, temperature, humidity, and light intensity.

[1452] "Plant condition data" refers to data that includes information about crops and their surrounding environment, such as soil quality, temperature, humidity, and light intensity.

[1453] "Diagnosis results" refers to information about the health of agricultural crops and necessary measures obtained by analyzing collected plant condition data.

[1454] "Advice" refers to specific instructions and suggestions for farmers to successfully cultivate crops without pesticides, based on the diagnostic results generated.

[1455] "Users" refers to agricultural workers and those involved in agriculture who practice pesticide-free cultivation.

[1456] "Feedback" refers to information provided by the user regarding the evaluation of the system's advice and diagnostic results and the execution results.

[1457] "Model" refers to a computational model that incorporates know-how for pesticide-free cultivation using generative artificial intelligence that learns from collected data.

[1458] "Real-time monitoring" refers to continuously observing plant condition data using sensing devices and immediately processing the results.

[1459] A "reminder" is information that notifies a user of the timing and precautions to take when taking a specific action.

[1460] "Additional advice" refers to new instructions or suggestions generated based on real-time monitoring data.

[1461] The system of this invention includes a method and an apparatus for collecting data, analyzing it, and providing advice to support pesticide-free cultivation. A specific embodiment will be described, focusing on a server, a terminal, and a user (agricultural worker).

[1462] Data collection and learning

[1463] server

[1464] The server collects data related to pesticide-free farming from the Internet and existing databases. This data includes types of organic fertilizers, application methods, pest and disease ecology, and climate data. As a specific example, the Open Weather Map API can be used to collect weather data.

[1465] The collected data is cleansed to remove noise and missing data, then normalized and trained using a generative artificial intelligence (AI) model (using TensorFlow or PyTorch, for example) to learn the know-how of pesticide-free farming.

[1466] The resulting AI model is stored on a server and regularly updated. This model is used to provide knowledge and optimal strategies for pesticide-free farming.

[1467] Crop condition diagnosis

[1468] Terminal

[1469] Sensing devices (e.g., e-kakashi) connected to the terminal periodically collect data on soil quality, temperature, humidity, light intensity, etc. This allows for a detailed understanding of the conditions of crops and their environment.

[1470] The collected data is sent to a server via Wi-Fi or mobile communications.

[1471] server

[1472] The server uses generative artificial intelligence to analyze the data it receives, specifically data on soil pH levels, temperature, and humidity, to diagnose the current condition of the crops.

[1473] Based on the analysis results, advice on pesticide-free cultivation is generated. For example, if the soil pH level is outside the appropriate range, advice is provided on the appropriate timing and amount of organic fertilizer to be used.

[1474] Communication with farmers

[1475] server

[1476] The server sends the generated advice and diagnostic results to the device, possibly in the form of push notification or email.

[1477] It also accepts feedback and questions from farmers and generates optimal answers based on that information. For example, it uses generative artificial intelligence to create optimal answers to users' questions.

[1478] Terminal

[1479] The terminal notifies the user of advice and diagnostic results sent from the server, allowing the user to receive appropriate information on pesticide-free farming in a timely manner.

[1480] Additionally, users can use their terminals to input questions into the system, which are then sent to the server.

[1481] User (farmer)

[1482] Farmers can then carry out agricultural work based on the advice they receive through the device, such as applying appropriate organic fertilizer or taking measures to prevent specific pests and diseases.

[1483] By inputting the results of the execution and feedback into the device and sending it to the server, the system continues to learn and provides more accurate advice.

[1484] Cultivation management

[1485] Terminal

[1486] The terminal continuously monitors the condition of the crops through a sensing device, and the collected data is sent to a server in real time.

[1487] server

[1488] The server analyzes changes in the cultivation environment based on the received data and generates necessary reminders and additional advice, such as "Low temperatures are predicted this week, so please take measures to prevent frost."

[1489] Specific examples

[1490] Examples of organic fertilizer use

[1491] 1. Using a sensing device (e-kakashi) connected to a terminal, the pH level, humidity, and temperature of the soil are measured and the data is sent to the server.

[1492] 2. The server analyzes the received data using generative artificial intelligence and generates advice on the appropriate timing and amount of organic fertilizer to use based on the condition of the soil.

[1493] 3. The server sends the generated advice to the terminal and notifies the farmer.

[1494] 4. The user (farmer) applies organic fertilizer based on the advice received through the terminal and observes the results.

[1495] 5. The terminal measures the observation results again using the sensing device and sends the data to the server.

[1496] 6. The server analyzes the new data and generates additional advice if necessary, and notifies the farmer via the terminal.

[1497] Examples of pest prevention

[1498] 1. The server trains the generative AI to learn about the ecology of pests and diseases and preventive measures.

[1499] 2. The terminal uses a sensing device (e-kakashi) to collect data on the crops and their surrounding environment and transmits it to the server.

[1500] 3. The server analyzes the received data using generative artificial intelligence and generates advice on risk assessments of pest and disease outbreaks and preventive measures.

[1501] 4. The server sends the generated advice to the terminal and notifies the farmer.

[1502] 5. The user (farmer) implements preventive measures based on the advice and observes the results.

[1503] 6. The device measures the observations and sends them to the server.

[1504] 7. The server continuously analyzes the data, generates new advice, and notifies the farmer via his / her terminal.

[1505] Prompt Sentence Examples

[1506] 1. What is the appropriate time and amount to use organic fertilizer?

[1507] 2. What measures are necessary to prevent pests and diseases?

[1508] As described above, the system of the present invention effectively supports farmers in accurately grasping the knowledge and timing necessary for pesticide-free cultivation and putting it into practice.

[1509] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1510] Step 1:

[1511] Data collection

[1512] The server collects data on organic farming from sources including the internet and existing databases, including types of organic fertilizers and their application methods, pest and disease ecology, and climate data.

[1513] Input: Raw data from the internet and existing databases.

[1514] Output: Data related to pesticide-free cultivation before cleansing.

[1515] What it does: The server collects data using APIs and web scraping and stores it in a local database.

[1516] Step 2:

[1517] Data Cleansing

[1518] The server cleanses the collected data, removing noise and missing data, thereby improving the quality of the data.

[1519] Input: Raw data collected.

[1520] Output: Clean, cleansed data.

[1521] What it does: The server runs algorithms to detect outliers and impute missing values, for example filtering out abnormal pH values, temperatures, etc.

[1522] Step 3:

[1523] Data normalization

[1524] The server normalizes the cleansed data and puts it into a format that is easy for the generative AI model to understand.

[1525] Input: Cleansed data.

[1526] Output: Normalized data.

[1527] Specific operation: The server performs data scaling and normalization to convert numeric data into a certain range.

[1528] Step 4:

[1529] Model learning

[1530] The server uses the normalized data to train a generative AI model (using TensorFlow or PyTorch).

[1531] Input: Normalized data.

[1532] Output: The trained model.

[1533] Specific operation: The server applies a machine learning algorithm to teach the model know-how regarding pesticide-free cultivation.

[1534] Step 5:

[1535] Save Model

[1536] The server stores the trained model and updates it as needed.

[1537] Input: A trained model.

[1538] Output: The saved model.

[1539] Specific operation: The server saves the trained model in a database and sets a schedule for periodic retraining.

[1540] Step 6:

[1541] Sensing

[1542] A sensing device (e.g., e-kakashi) connected to the terminal periodically collects data such as soil quality, temperature, humidity, and light intensity.

[1543] Input: Environmental data (temperature, humidity, light level, etc.).

[1544] Output: Collected environmental data.

[1545] Specific operation: The device periodically reads data from the sensors and temporarily stores it in local storage.

[1546] Step 7:

[1547] Data transmission

[1548] The device sends the collected data to a server via Wi-Fi or mobile communications.

[1549] Input: Collected environmental data.

[1550] Output: The data sent to the server.

[1551] Specific operation: The terminal transmits data to the server via the network in real time or in batch processing.

[1552] Step 8:

[1553] Data reception

[1554] The server receives the data sent from the terminal.

[1555] Input: Data sent from the terminal.

[1556] Output: The received data.

[1557] Specific operation: The server immediately stores the received data in a database and prepares it for analysis.

[1558] Step 9:

[1559] Data analysis

[1560] The server analyzes the received data using a generative AI model to diagnose the current condition of the crops.

[1561] Input: Received data, trained model.

[1562] Output: Diagnostic results.

[1563] Specific operation: The server inputs data into the generative AI model and analyzes the health of the crops and necessary measures.

[1564] Step 10:

[1565] Advice Generation

[1566] Based on the analysis results, the server generates advice and reminders on pesticide-free farming.

[1567] Input: Diagnostic results.

[1568] Output: Advice and reminders.

[1569] Specific actions: The server automatically generates a sentence that suggests appropriate measures and instructions for action.

[1570] Step 11:

[1571] Send Advice

[1572] The server transmits the generated advice to the terminal.

[1573] Input: Advice and reminders.

[1574] Output: Advice sent to the terminal.

[1575] Specific behavior: The server sends the advice using a messaging protocol.

[1576] Step 12:

[1577] Receive feedback

[1578] The server accepts feedback and questions from users via the terminal.

[1579] Input: User feedback and questions.

[1580] Output: Feedback and questions received.

[1581] Specific operation: The device sends questions and feedback entered by the user to the server.

[1582] Step 13:

[1583] Optimal response generation

[1584] The server uses a generative AI model to generate optimal responses to the feedback and questions it receives.

[1585] Input: Feedback, questions, trained models.

[1586] Output: Best response.

[1587] Specific operation: The server inputs feedback and questions into the generative AI model to generate optimal answers and improvements.

[1588] Step 14:

[1589] Response Send

[1590] The server generates a response and sends it to the terminal.

[1591] Input: Best response.

[1592] Output: The response sent to the terminal.

[1593] Specific operation: The server sends a response to the terminal via a messaging protocol.

[1594] Step 15:

[1595] monitoring

[1596] The terminal monitors the condition of the plants in real time through sensing devices.

[1597] Input: Real-time data from sensing devices.

[1598] Output: Monitored data.

[1599] Specific operation: The terminal continuously collects data and transmits it to the server in real time.

[1600] Step 16:

[1601] Additional advice generation

[1602] The server analyzes the received monitoring data and generates additional advice and reminders as needed.

[1603] Input: Real-time monitoring data.

[1604] Output: Additional advice and reminders.

[1605] Specific operation: The server has the generative AI model further analyze the data and generate additional feedback.

[1606] Step 17:

[1607] Send additional advice

[1608] The server sends the generated additional advice to the terminal.

[1609] Input: Additional advice or reminders.

[1610] Output: Additional advice sent to the terminal.

[1611] Specific behavior: The server sends additional advice via the messaging protocol.

[1612] Through these steps, the system supports farmers in effectively implementing pesticide-free cultivation.

[1613] (Application example 1)

[1614] 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."

[1615] In pesticide-free farming, it is extremely important to acquire the know-how for proper farming practices and carry them out efficiently and effectively. However, traditional methods are prone to time lags in data collection and delayed feedback, making it difficult to obtain real-time advice. Furthermore, in the food delivery industry, there is no established method for safely and quickly delivering pesticide-free produce. Highly accurate data collection and analysis, as well as real-time information provision, are essential to resolving these issues.

[1616] 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.

[1617] In this invention, the server includes a means for collecting data on pesticide-free farming, a means for training generative AI to learn pesticide-free farming know-how, and a means for saving and updating the model resulting from the learning. This allows farmers to receive pesticide-free farming advice in real time and perform appropriate farm work. This invention also includes a means for collecting data on food delivery and a means for providing delivery routes and specific instructions. This allows for the safe and prompt delivery of pesticide-free agricultural products. Furthermore, since information is provided in real time via a head-mounted display, delivery personnel can always act based on the latest information.

[1618] "Pesticide-free cultivation" is an agricultural method that uses natural methods to prevent pests and diseases when growing crops without using chemical pesticides, and is gentle on the environment and the human body.

[1619] "Generative AI" is an AI system that analyzes large amounts of data, automatically learns patterns, and generates predictions and optimal advice.

[1620] "Know-how" is a general term for the specific techniques, knowledge, and experience required for pesticide-free cultivation.

[1621] A "model" is a mathematical or statistical representation that serves as the basis for data analysis and prediction, generated as a result of training generative artificial intelligence.

[1622] A "sensing device" is a device for measuring and collecting environmental data such as temperature, humidity, and light intensity.

[1623] "Diagnosis results" are information about the condition of crops and necessary measures generated after analyzing collected data.

[1624] "Advice" refers to specific instructions or recommendations for farmers that are generated based on the diagnostic results.

[1625] "Communication means" refers to the technical means for transmitting and receiving data between the server and the farmer's terminal.

[1626] "Feedback" refers to the results of implementing advice, as well as opinions and questions, sent by farmers to the server.

[1627] "Delivery" refers to the process of delivering pesticide-free agricultural products to consumers.

[1628] A "head-mounted display" is a display device worn on the head to display information within the field of view.

[1629] "Real-time information provision" refers to providing the analysis results of sensing devices and servers to users immediately and without delay.

[1630] This invention provides a system that realizes efficient pesticide-free cultivation and safe food delivery. This system consists of a server, terminals (including sensing devices), and users (farmers and delivery personnel).

[1631] 1. Program processing overview

[1632] server

[1633] The server collects data on pesticide-free farming and uses it to train the generative AI on the know-how of pesticide-free farming. This data includes the types of organic fertilizers and their use, the ecology of pests and diseases, and climate data. The server cleanses the collected data, removing noise and missing data. The data is then normalized and trained by the generative AI. The model generated as a result of the learning is stored on the server and updated as necessary.

[1634] Terminal

[1635] Sensing devices connected to the terminal (e.g., soil sensors and temperature / humidity sensors) periodically collect data on soil quality, temperature, humidity, light intensity, etc. The collected data is sent from the terminal to a server. The server receives the data sent from the terminal and analyzes it using generative artificial intelligence. Based on the analysis results, advice and reminders regarding pesticide-free cultivation are generated. For example, if the soil's pH level is outside the appropriate range, advice on the appropriate timing and amount of organic fertilizer to be used is generated.

[1636] User (farmer)

[1637] Farmers perform farm work based on the advice they receive through the device. For example, they may apply appropriate organic fertilizer or take measures to prevent specific pests and diseases. The results of implementing the advice and feedback they feel are entered into the device and sent to a server. Furthermore, the device monitors the condition of the crops through a sensing device and continuously sends data to the server in real time.

[1638] 2. Food delivery support

[1639] The system also has a support function to help food delivery workers deliver pesticide-free produce safely and effectively. The server collects data on food deliveries and provides optimal delivery routes and handling methods. Delivery workers can receive advice in real time using a head-mounted display.

[1640] Hardware and Software Use Cases

[1641] Hardware: Head-mounted display (e.g. Microsoft HoloLens), soil sensor, temperature and humidity sensor

[1642] Software: Python, Server API (e.g. "https: / / agriculture-data-source.com / api / getData")

[1643] 3. Adding concrete examples

[1644] Specific work examples

[1645] 1. The server collects data on pesticide-free farming through the API.

[1646] 2. Based on the collected data, generative AI learns the know-how of pesticide-free cultivation.

[1647] 3. The model generated as a result of learning is saved on the server.

[1648] 4. Farmers use sensing devices to measure soil quality, temperature, humidity, light intensity, etc., and send the data from their terminals to a server.

[1649] 5. The server performs the analysis and generates appropriate advice.

[1650] 6. Delivery personnel will wear head-mounted displays and be provided with real-time information on appropriate delivery routes and handling methods.

[1651] Prompt Sentence Examples

[1652] "The temperature is low today, so please take precautions against the cold."

[1653] "Your soil pH is dropping. Add organic fertilizer."

[1654] By using the above method, this invention enables pesticide-free cultivation and its delivery to be carried out efficiently and effectively.

[1655] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1656] Step 1:

[1657] Data collection

[1658] The server collects data on pesticide-free farming. Specifically, it obtains information on the types and use of organic fertilizers, the ecology of pests and diseases, and climate data from the Internet and existing databases. The input is a list of data to be collected, and the output is a file of the collected data.

[1659] Step 2:

[1660] Data Cleansing and Normalization

[1661] The server cleanses the collected data, removing noise and missing data. Then, it normalizes the data and formats it in a way that makes it easier for generative AI to learn. The input is the collected data file, and the output is the cleansed, normalized data.

[1662] Step 3:

[1663] Learning with generative artificial intelligence

[1664] The server uses the normalized data to train the generative AI to learn the know-how of pesticide-free cultivation. Specifically, the normalized data is input into the AI ​​model and learning is repeated. The input is the normalized data, and the output is the trained model.

[1665] Step 4:

[1666] Saving a trained model

[1667] The server saves the generated trained model and updates it as necessary. The input is the trained model, and the output is the saved model data. Specifically, the model is stored in a database within the server.

[1668] Step 5:

[1669] Data collection using sensing devices

[1670] Sensing devices (e.g., soil sensors, temperature and humidity sensors) connected to the terminal periodically collect data on soil quality, temperature, humidity, light intensity, etc. The input is the environmental data collected by the sensor, and the output is the measurement data sent to the terminal.

[1671] Step 6:

[1672] Sending data to the server

[1673] The terminal transmits the collected data to the server in real time. The input is the measurement data, and the output is the data transmitted to the server.

[1674] Step 7:

[1675] Data analysis and generation of diagnostic results

[1676] The server receives the data sent from the terminal and analyzes it using generative artificial intelligence. Specifically, it uses a data analysis algorithm to diagnose the condition of the crops and generate the results. The input is the sent data and the output is the diagnosis result.

[1677] Step 8:

[1678] Generating Advice

[1679] The server generates advice on pesticide-free farming based on the diagnostic results. For example, if the soil pH is outside the appropriate range, it will suggest the appropriate timing and amount of organic fertilizer to use. The input is the diagnostic results, and the output is advice.

[1680] Step 9:

[1681] Advice and notification of diagnostic results

[1682] The server sends the generated advice and diagnosis results to the terminal and notifies the farmer. The input is advice and diagnosis results, and the output is notification data sent to the terminal.

[1683] Step 10:

[1684] Gathering and implementing feedback

[1685] Farmers perform farm work based on the advice received through their devices, and input the results and feedback into the device and send it to the server. The server receives this feedback and reflects it in the model. The input is the feedback data, and the output is updated model data.

[1686] Step 11:

[1687] Providing delivery routes and specific instructions

[1688] The server collects data about food delivery and provides optimal delivery routes and handling methods. The input is delivery data, and the output is instructions and route data.

[1689] Step 12:

[1690] Real-time information provision

[1691] The delivery person wears a head-mounted display and receives advice and route information in real time from the server. The input is instructions and route data, and the output is information displayed on the head-mounted display.

[1692] 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.

[1693] The system of this invention includes a method and device for effectively supporting pesticide-free farming, and in particular, combines an emotion engine that recognizes the user's emotions and adjusts the content and timing of advice based on those emotions. A specific embodiment will be described below, focusing on a server, a terminal, and a user (agricultural worker).

[1694] Data collection and learning

[1695] server

[1696] The server collects a large amount of data related to pesticide-free farming from the internet and existing databases, including types of organic fertilizer and their application methods, pest and disease ecology, and climate data.

[1697] The server cleanses the collected data, removing noise and missing data. It then normalizes the data and trains it using generative AI. Specifically, the data is formatted in a way that makes it easy for the AI ​​model to understand, and it learns the know-how of pesticide-free farming.

[1698] The model generated as a result of learning is stored on the server and updated as necessary.

[1699] Crop condition diagnosis

[1700] Terminal

[1701] Sensing devices (e.g., e-kakashi) connected to the terminal periodically collect data such as soil quality, temperature, humidity, and light intensity.

[1702] The collected data is transmitted from the terminal to a server.

[1703] server

[1704] The server receives the data sent from the device and analyzes it using generative artificial intelligence. The purpose of the analysis is to diagnose the current condition of the crops and derive the necessary countermeasures.

[1705] Based on the analysis results, appropriate advice and reminders are generated. For example, if the soil pH level is outside the appropriate range, advice on the timing and amount of organic fertilizer to be used is generated.

[1706] Communication with farmers

[1707] server

[1708] The server sends the generated advice and diagnostic results to the terminal.

[1709] It also accepts feedback and questions from farmers and generates optimal answers, which are then sent to the device.

[1710] Terminal

[1711] The terminal notifies the farmer of advice and diagnostic results sent from the server, for example by providing appropriate information via an alert or display panel.

[1712] Farmers can also use their devices to input questions to the generative AI, which are then sent to the server.

[1713] User (farmer)

[1714] Farmers can then use the advice they receive through the device to carry out their farming work, such as applying appropriate organic fertilizers or taking measures to prevent specific pests and diseases.

[1715] The results of the advice and any feedback felt are entered into the device and sent to the server.

[1716] Cultivation management

[1717] Terminal

[1718] The terminal continuously monitors the condition of the crops through a sensing device, and the collected data is sent to a server in real time.

[1719] server

[1720] The server analyzes changes in the cultivation environment based on the received data and generates necessary reminders and additional advice, such as "Low temperatures are predicted this week, so please take measures to prevent frost."

[1721] Any generated reminders or additional advice will also be sent to the farmer via the device.

[1722] Combining Emotion Engines

[1723] Terminal

[1724] When the device communicates with the farmer, it uses an emotion engine to analyze the tone of voice and text content. For example, if the farmer is emotional, the emotion engine will recognize that emotion.

[1725] server

[1726] The emotion information obtained from the emotion engine is used to adjust the content and timing of the advice provided by the generative AI. For example, a farmer feeling stressed might be given simple, actionable advice along with an encouraging message.

[1727] It also fine-tunes reminders and advice based on emotions and delivers them in a format that farmers find most acceptable.

[1728] User (farmer)

[1729] Farmers implement the advice provided and enter their results and feelings into the device, which also sends emotional feedback to the server.

[1730] Specific examples

[1731] Examples of organic fertilizer use

[1732] 1. The device uses e-kakashi to measure the soil's pH level, humidity, and temperature, and sends the data to the server.

[1733] 2. The server analyzes the received data using generative artificial intelligence and generates advice on the appropriate timing and amount of organic fertilizer to use based on the condition of the soil.

[1734] 3. The server sends the generated advice to the terminal and notifies the farmer.

[1735] 4. The device uses an emotion engine to analyze the farmer's emotions, and if they are feeling stressed or anxious, it will provide advice with an encouraging message.

[1736] 5. The user (farmer) applies organic fertilizer based on the advice and observes the results. The user inputs the observation results and their feelings into the terminal and sends them to the server.

[1737] 6. The server analyzes the observation data and sentiment information and suggests new advice or adjustments as needed, for example determining whether soil conditions have improved and suggesting further preventative measures or additional fertilization.

[1738] Examples of pest prevention

[1739] 1. The server trains the generative AI to learn about the ecology of pests and diseases and preventative measures. The data includes the ecology of pests and diseases, preventative measures, and their relationship with climate.

[1740] 2. The device uses e-kakashi to collect data on the condition of the crops and the surrounding environment (temperature, humidity, air temperature, etc.) and send it to the server.

[1741] 3. The server analyzes the received data using generative artificial intelligence and generates a risk assessment of pest and disease outbreaks and preventive measures.

[1742] 4. The server generates advice including preventive measures based on the risk assessment and sends the advice to the terminal.

[1743] 5. The device analyzes the farmer's emotions using an emotion engine and tailors advice based on their emotions. For example, it provides detailed instructions on specific procedures to farmers who are feeling anxious.

[1744] 6. The user (farmer) implements preventive measures based on the advice received, for example, installing moth nets or spraying natural pesticides.

[1745] 7. The device monitors the results again through e-kakashi and sends the data to the server.

[1746] 8. The server analyzes the monitoring data and emotional information to evaluate the effectiveness of preventive measures, and generates additional measures and reminders as needed, and notifies users via their devices.

[1747] Through the above processing steps, this invention effectively supports pesticide-free cultivation, enabling farmers to accurately grasp the necessary know-how and timing and put it into practice. By combining it with an emotion engine, it is possible to provide support that matches the psychological state of farmers, improving work efficiency and satisfaction.

[1748] The processing flow will be explained below.

[1749] Examples of organic fertilizer use

[1750] Step 1:

[1751] The device uses e-kakashi to measure the soil's pH level, humidity, and temperature, and then sends the data to the server.

[1752] Step 2:

[1753] The server refers to the contents of the database based on the data received and preprocesses the data, specifically removing outliers and normalizing the data.

[1754] Step 3:

[1755] The server uses generative artificial intelligence to analyze the pre-processed data and generate information on the current state of the crops and the appropriate use of organic fertilizer.

[1756] Step 4:

[1757] Based on the analysis results, the server generates advice including the appropriate timing and amount of organic fertilizer to use and sends that advice to the terminal.

[1758] Step 5:

[1759] The terminal notifies the farmer of the advice sent from the server, for example by displaying the information via an alert or a display panel.

[1760] Step 6:

[1761] The device uses an emotion engine to analyze the farmer's emotions, and if they are feeling stressed or anxious, it will provide advice along with an encouraging message.

[1762] Step 7:

[1763] The user (farmer) applies organic fertilizer based on the advice, observes the results, and inputs their observations and their feelings into the device.

[1764] Step 8:

[1765] The device collects observations and emotional information and sends the data to a server.

[1766] Step 9:

[1767] The server analyzes the observation data and sentiment information and suggests new advice or adjustments as needed, for example determining whether soil conditions have improved and suggesting further preventative measures or additional fertilization.

[1768] Examples of pest prevention

[1769] Step 1:

[1770] The server trains the generative AI with data on pests and diseases, including their ecology, preventative measures, and their relationship with climate.

[1771] Step 2:

[1772] The terminal uses e-kakashi to collect data on the condition of the crops and the surrounding environment (temperature, humidity, air temperature, etc.) and send it to the server.

[1773] Step 3:

[1774] The server preprocesses the received data, removing outliers and normalizing the data.

[1775] Step 4:

[1776] The server analyzes the preprocessed data using generative artificial intelligence to generate risk assessments and preventative measures for pest and disease outbreaks.

[1777] Step 5:

[1778] The server generates advice including preventive measures based on the risk assessment and transmits the advice to the terminal.

[1779] Step 6:

[1780] The terminal notifies the farmer of the advice sent from the server, for example by providing information using a display panel or alerts.

[1781] Step 7:

[1782] The device uses an emotion engine to analyze the farmer's emotions and tailor advice based on their feelings, for example providing detailed instructions on specific procedures to farmers who are feeling anxious.

[1783] Step 8:

[1784] The user (farmer) implements preventive measures based on the advice received, for example, installing moth nets or spraying natural pesticides.

[1785] Step 9:

[1786] The device monitors the results again through e-kakashi and sends the data to the server.

[1787] Step 10:

[1788] The server analyzes the monitoring data and emotional information to evaluate the effectiveness of preventive measures, and generates additional measures and reminders as needed, which are then sent via the device.

[1789] These processing steps effectively support pesticide-free cultivation, allowing farmers to accurately grasp the necessary know-how and timing, and then carry it out.By combining it with an emotion engine, it is possible to provide support that matches the psychological state of farmers, improving work efficiency and satisfaction.

[1790] Example 2

[1791] 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."

[1792] In modern agriculture, pesticide-free cultivation is becoming increasingly important from the perspectives of health and environmental protection, but its implementation requires advanced expertise and technology. Furthermore, because the emotions and psychological state of farmers also affect work efficiency and satisfaction, support that takes emotions into consideration is also necessary. Conventional systems have difficulty addressing these complex challenges, particularly in terms of real-time condition monitoring and adjusting advice based on emotions.

[1793] 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.

[1794] In this invention, the server includes: means for collecting data on pesticide-free farming; means for training a generative artificial intelligence (AI) to learn know-how about pesticide-free farming; means for saving and updating the model as the learning result; means for collecting crop condition data using a sensing device; means for analyzing the crop condition data and generating diagnostic results; means for providing advice on pesticide-free farming based on the diagnostic results; means for transmitting the advice and diagnostic results and communicating with the farmer; means for receiving feedback from the farmer and reflecting it in the model; means for analyzing the farmer's emotions; and means for adjusting the content and timing of advice based on the analyzed emotional information. This allows farmers to acquire know-how about pesticide-free farming in real time and perform farm work efficiently and effectively. Furthermore, emotionally sensitive support can improve work efficiency and satisfaction.

[1795] "Pesticide-free cultivation" is an agricultural method in which crops are grown without the use of pesticides, and is important from the perspectives of health and environmental protection.

[1796] "Data collection means" refers to devices or mechanisms that obtain necessary data from sensors, databases, the Internet, etc.

[1797] "Generative AI" is an AI system that learns from collected data and generates solutions and advice for specific problems.

[1798] A "learning result model" is a collection of solutions and know-how for specific problems that is obtained as a result of learning by generative artificial intelligence.

[1799] A "sensing device" is a device used to measure and record the condition of soil and the environment, collecting data such as temperature, humidity, and light intensity.

[1800] "Crop condition data" refers to information about the cultivation environment and growth of crops, such as soil conditions, weather conditions, and crop growth status.

[1801] "Analysis means" refers to a method or device for analyzing collected data and deriving useful information or knowledge.

[1802] "Diagnosis results" are conclusions about the current state and future predictions drawn based on collected and analyzed data.

[1803] "Advice delivery methods" are systems or mechanisms that provide specific guidelines and recommendations based on diagnostic results.

[1804] "Communication means" refers to a system for two-way exchange of data and information, and often refers specifically to connections with agricultural workers.

[1805] "Feedback receiving means" is a mechanism for receiving reactions and results from users.

[1806] "Emotion analysis means" refers to a method or device for analyzing a user's emotions and psychological state, and infers emotions from the tone of voice and the content of text.

[1807] "Advice adjustment means" refers to a system or method that changes the content and timing of advice provided based on the results of sentiment analysis.

[1808] The system of this invention includes a method and device for effectively supporting pesticide-free cultivation, and in particular, combines an emotion engine that recognizes the user's emotions and adjusts the content and timing of advice based on those emotions. Specific embodiments focusing on a server, a terminal, and a user (agricultural worker) are described below.

[1809] Data collection and learning

[1810] server

[1811] The server collects a large amount of data related to pesticide-free farming from the internet and existing databases, including types of organic fertilizer and their application methods, pest and disease ecology, and climate data.

[1812] The server cleanses the collected data, removing noise and missing data, then normalizes it and trains the generative AI model. Specifically, the data is formatted in a way that makes it easy for the AI ​​model to understand, and it learns the know-how of pesticide-free farming.

[1813] The model generated as a result of learning is stored on the server and updated as necessary.

[1814] Crop condition diagnosis

[1815] Terminal

[1816] Sensing devices (e.g., ec sensing devices) connected to the terminal periodically collect data such as soil quality, temperature, humidity, and light intensity.

[1817] The collected data is transmitted from the terminal to a server.

[1818] server

[1819] The server receives the data sent from the device and analyzes it using a generative AI model. The purpose of the analysis is to diagnose the current condition of the crops and derive the necessary countermeasures.

[1820] Based on the analysis results, appropriate advice and reminders are generated. For example, if the soil pH level is outside the appropriate range, advice on the timing and amount of organic fertilizer to be used is generated.

[1821] Communication with farmers

[1822] server

[1823] The server sends the generated advice and diagnostic results to the terminal.

[1824] It also accepts feedback and questions from farmers and generates optimal answers, which are then sent to the device.

[1825] Terminal

[1826] The terminal notifies the farmer of advice and diagnostic results sent from the server, for example by providing appropriate information via an alert or display panel.

[1827] Farmers can also use their devices to input questions to the generative AI model, which are also sent to the server.

[1828] User (farmer)

[1829] Farmers can then carry out farm work based on the advice they receive through the device, such as applying appropriate organic fertilizer and taking measures to prevent pests and diseases.

[1830] The results of the advice and any feedback felt are entered into the device and sent to the server.

[1831] Cultivation management

[1832] Terminal

[1833] The terminal continuously monitors the condition of the crops through a sensing device, and the collected data is sent to a server in real time.

[1834] server

[1835] The server analyzes changes in the cultivation environment based on the received data and generates necessary reminders and additional advice, such as "Low temperatures are predicted this week, so please take measures to prevent frost."

[1836] Any generated reminders or additional advice will also be sent to the farmer via the device.

[1837] Combining Emotion Engines

[1838] Terminal

[1839] When the device communicates with the farmer, it uses an emotion engine to analyze the tone of voice and text content. For example, if the farmer is emotional, the emotion engine will recognize that emotion.

[1840] server

[1841] The emotion information obtained from the emotion engine is used to tailor the content and timing of the advice provided by the generative AI model. For example, a farmer experiencing stress might be given a simple, actionable piece of advice along with an encouraging message.

[1842] It also fine-tunes reminders and advice based on emotions and delivers them in a format that farmers find easy to accept.

[1843] User (farmer)

[1844] Farmers implement the advice provided and enter the results and emotions they felt into the device, which also sends emotional feedback to the server.

[1845] Specific examples

[1846] Examples of organic fertilizer use

[1847] 1. The device uses a sensing device to measure the soil's pH level, humidity, and temperature, and then sends the data to the server.

[1848] 2. The server analyzes the received data using a generative AI model and generates advice on the appropriate timing and amount of organic fertilizer to use based on the condition of the soil.

[1849] 3. The server sends the generated advice to the terminal and notifies the farmer.

[1850] 4. The device uses an emotion engine to analyze the farmer's emotions, and if they are feeling stressed or anxious, it will provide advice with an encouraging message.

[1851] 5. The user (farmer) applies organic fertilizer based on the advice and observes the results. The user inputs the observation results and their feelings into the device and sends them to the server.

[1852] 6. The server analyzes the observation data and sentiment information and suggests new advice or adjustments as needed, for example determining whether soil conditions have improved and suggesting further preventative measures or additional fertilization.

[1853] Examples of pest prevention

[1854] 1. The server trains the generative AI to learn about the ecology of pests and diseases and preventative measures. The data includes the ecology of pests and diseases, preventative measures, and their relationship with climate.

[1855] 2. The terminal uses a sensing device to collect data on the condition of the crops and the surrounding environment (temperature, humidity, air temperature, etc.) and transmits it to the server.

[1856] 3. The server analyzes the received data using a generative AI model to generate a risk assessment of pest and disease outbreaks and generate preventive measures.

[1857] 4. The server generates advice including preventive measures based on the risk assessment and sends the advice to the terminal.

[1858] 5. The device analyzes the farmer's emotions using an emotion engine and tailors advice based on their emotions. For example, it provides detailed instructions on specific procedures to farmers who are feeling anxious.

[1859] 6. The user (farmer) implements preventive measures based on the advice received, for example, installing moth nets or spraying natural pesticides.

[1860] 7. The terminal monitors the implementation results again through the sensing device and sends the data to the server.

[1861] 8. The server analyzes the monitoring data and emotional information to evaluate the effectiveness of preventive measures, and generates additional measures and reminders as needed, and notifies users via their devices.

[1862] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1863] Step 1:

[1864] Data collection

[1865] The server collects data on pesticide-free farming from the internet and existing databases, including the type of organic fertilizer, how it is used, the ecology of pests and diseases, and weather data.

[1866] Input: Internet databases and meteorological data related to pesticide-free farming.

[1867] Output: Collected data before cleansing.

[1868] Specific behavior: Extract data via API and store it in a local database.

[1869] Step 2:

[1870] Data Cleansing and Learning

[1871] The server cleanses the collected data, removing noise and missing data, then normalizes the data and trains the generative AI model.

[1872] Input: Collected data before cleansing.

[1873] Output: Cleansed and normalized training data and a trained model.

[1874] What it does: It uses database queries and data analysis tools to remove unnecessary data and feed it to machine learning algorithms.

[1875] Step 3:

[1876] Collecting data on crop conditions

[1877] The terminal uses a sensing device to periodically collect data such as soil quality, temperature, humidity, and light intensity and transmits it to a server.

[1878] Input: Real-time data from soil and environmental sensors.

[1879] Output: Collected crop condition data.

[1880] Specific operation: Data is acquired from the sensing device, stored on the terminal, and then sent to the server.

[1881] Step 4:

[1882] Analysis of crop conditions

[1883] The server analyzes the crop condition data sent from the device using a generative AI model, generates diagnostic results, and derives necessary countermeasures.

[1884] Input: Crop status data sent from the terminal.

[1885] Output: Diagnostic results and remedial action.

[1886] What it does: It uses data analysis algorithms to extract meaningful features from the data and make predictions based on the model.

[1887] Step 5:

[1888] Advice Generation and Notifications

[1889] The server generates appropriate advice and reminders based on the analysis results and sends them to the device.

[1890] Input: Diagnostic results and remedial action.

[1891] Output: Advice and reminders.

[1892] Specific operation: Advice is created using a generative AI model and the data is sent to the device.

[1893] Step 6:

[1894] Giving and receiving feedback from farmers

[1895] The terminal notifies the farmer of advice and diagnostic results from the server, who then performs farm work based on the advice and enters feedback into the terminal.

[1896] Input: Advice and diagnostic results from the server.

[1897] Output: Farmer feedback.

[1898] Specific behavior: Uses the notification system to display advice and records user input.

[1899] Step 7:

[1900] Sentiment analysis and advice adjustment

[1901] The device uses an emotion engine to analyze the farmer's emotions and transmits the results to a server, which then adjusts the content and timing of advice based on the emotional information.

[1902] Input: Farmer sentiment data.

[1903] Output: Adjusted advice.

[1904] What it does: It uses speech and text analysis tools to determine emotional state, sends that information to a server, and generates and resends tailored advice.

[1905] Step 8:

[1906] Continuous monitoring and updates

[1907] The terminal continuously monitors the condition of the crops through a sensing device and transmits the data in real time to the server, which analyzes the received data and generates necessary reminders and additional advice.

[1908] Input: Continuous real-time data from sensing equipment.

[1909] Output: Reminders and additional advice.

[1910] Specific operation: Collect and transmit data using a real-time data collection system, and generate new advice and reminders based on the analysis results.

[1911] (Application example 2)

[1912] 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."

[1913] In pesticide-free cultivation, farmers need a lot of effort and knowledge to obtain appropriate advice. Furthermore, the timing and content of information provided about cultivation is uniform, making it difficult to respond to the emotions and psychological state of farmers. This prevents farmers from obtaining the necessary information at the right time, which can result in reduced cultivation efficiency and increased stress.

[1914] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1915] In this invention, the server includes means for collecting data on pesticide-free farming and having the generative AI learn know-how about pesticide-free farming, means for saving and updating the model resulting from the learning, means for recognizing the emotional state of the farmer, and means for adjusting the content and timing of advice based on the emotional state, thereby enabling the farmer to receive the most appropriate advice and information at the appropriate time according to his or her emotional state.

[1916] "Pesticide-free cultivation" is a method of cultivating crops using natural materials and techniques without using chemical pesticides.

[1917] "Data collection means" refers to devices and systems for collecting data on pesticide-free cultivation and crop condition data.

[1918] "Generative AI" refers to AI that has the ability to learn specific knowledge and skills based on large amounts of data, and as a result generate useful information and advice.

[1919] "Know-how" refers to the practical knowledge and skills required for a specific purpose.

[1920] A "sensing device" is a device for collecting environmental data such as temperature, humidity, and soil quality.

[1921] "Diagnosis results" are information on the condition of crops and appropriate countermeasures obtained as a result of analyzing collected data.

[1922] "Advice providing means" refers to a device or system that provides specific instructions and advice to farmers based on the generated diagnostic results and know-how.

[1923] "Communication means" means a device or system for transmitting advice and diagnostic results to farmers and receiving feedback from farmers.

[1924] An "emotional state" refers to the feelings or psychological state that a person is in.

[1925] "Feedback receiving means" refers to a device or system for receiving opinions and feedback from farmers.

[1926] A "model updating means" is a device or system that improves or modifies an existing artificial intelligence model based on collected data and feedback.

[1927] A "timing adjustment means" is a device or system that takes into account the emotional state of the farmer and determines the optimal timing for providing advice.

[1928] The system of this invention includes a method and device for effectively supporting pesticide-free cultivation, and in particular, it combines an emotion engine that recognizes the emotions of farmers and adjusts the content and timing of advice based on those emotions. Specific embodiments focusing on a server, a terminal, and a user (agricultural worker) are described below.

[1929] Data collection and learning

[1930] server

[1931] The server collects large amounts of data related to pesticide-free farming from the internet and existing databases. This includes the types and use of organic fertilizers, the ecology of pests and diseases, and climate data. The server then cleanses the collected data, removing noise and missing data. It then normalizes the data and trains it using generative AI. Specifically, the data is formatted in a way that is easy for the AI ​​model to understand, and it is trained to learn the know-how of pesticide-free farming. The model generated as a result of the training is stored on the server and updated as necessary.

[1932] Crop condition diagnosis

[1933] Terminal

[1934] The sensing device connected to the terminal periodically collects data on soil quality, temperature, humidity, light intensity, etc. The collected data is then sent from the terminal to a server.

[1935] server

[1936] The server receives the data sent from the device and analyzes it using generative artificial intelligence. The purpose of the analysis is to diagnose the current condition of the crops and determine the necessary countermeasures. Based on the analysis results, appropriate advice and reminders are generated. For example, if the soil pH level is outside the appropriate range, advice is generated on the appropriate timing and amount of organic fertilizer to be used.

[1937] Communication with farmers

[1938] server

[1939] The server sends the generated advice and diagnostic results to the device. It also accepts feedback and questions from farmers and generates optimal answers to those questions. These answers are also sent to the device.

[1940] Terminal

[1941] The terminal notifies the farmer of advice and diagnostic results sent from the server. For example, appropriate information is provided via alerts or a display panel. Farmers can also use the terminal to input questions to the generative AI, which is also sent to the server.

[1942] User (farmer)

[1943] Farmers perform farm work based on the advice they receive through their devices. For example, they may apply appropriate organic fertilizer or take measures to prevent specific pests and diseases. The results of implementing the advice and any feedback they feel are entered into the device and sent to the server.

[1944] Cultivation management

[1945] Terminal

[1946] The terminal continuously monitors the condition of the crops through a sensing device, and the collected data is sent to a server in real time.

[1947] server

[1948] The server analyzes changes in the cultivation environment based on the received data and generates necessary reminders and additional advice. For example, it could say, "Low temperatures are predicted this week, so please take measures to prevent frost." The generated reminders and additional advice are also notified to farmers via their terminals.

[1949] Combining Emotion Engines

[1950] Terminal

[1951] When the device communicates with the farmer, it uses an emotion engine to analyze the tone of voice and text content. For example, if the farmer is emotional, the emotion engine will recognize that emotion.

[1952] server

[1953] The content and timing of advice provided by the generative AI is adjusted based on the emotional information obtained from the emotion engine. For example, a farmer feeling stressed can be provided with simple, actionable advice along with an encouraging message. The system also fine-tunes the content of reminders and advice based on emotions, providing them in a format that is easy for farmers to accept.

[1954] User (farmer)

[1955] Farmers implement the advice provided and enter their results and feelings into the device, which also sends emotional feedback to the server.

[1956] Example: Use of organic fertilizer

[1957] 1. The device uses a sensing device to measure the soil's pH level, humidity, and temperature, and then sends the data to the server.

[1958] 2. The server analyzes the received data using generative artificial intelligence and generates advice on the appropriate timing and amount of organic fertilizer to use based on the condition of the soil.

[1959] 3. The server sends the generated advice to the terminal and notifies the farmer.

[1960] 4. The device uses an emotion engine to analyze the farmer's emotions, and if they are feeling stressed or anxious, it will provide advice with an encouraging message.

[1961] 5. The user (farmer) applies organic fertilizer based on the advice and observes the results. The user inputs the observation results and their feelings into the terminal and sends them to the server.

[1962] 6. The server analyzes the observation data and sentiment information and suggests new advice or adjustments as needed, for example determining whether soil conditions have improved and suggesting further preventative measures or additional fertilization.

[1963] Example: Prevention of pests and diseases

[1964] 1. The server trains the generative AI to learn about the ecology of pests and diseases and preventative measures. The data includes the ecology of pests and diseases, preventative measures, and their relationship with climate.

[1965] 2. The terminal uses a sensing device to collect data on the condition of the crops and the surrounding environment (temperature, humidity, air temperature, etc.) and transmits it to the server.

[1966] 3. The server analyzes the received data using generative artificial intelligence and generates a risk assessment of pest and disease outbreaks and preventive measures.

[1967] 4. The server generates advice including preventive measures based on the risk assessment and sends the advice to the terminal.

[1968] 5. The device analyzes the farmer's emotions using an emotion engine and tailors advice based on their emotions. For example, it provides detailed instructions on specific procedures to farmers who are feeling anxious.

[1969] 6. The user (farmer) implements preventive measures based on the advice received, for example, installing moth nets or spraying natural pesticides.

[1970] 7. The terminal monitors the implementation results again through the sensing device and sends the data to the server.

[1971] 8. The server analyzes the monitoring data and emotional information to evaluate the effectiveness of preventive measures, and generates additional measures and reminders as needed, and notifies users via their devices.

[1972] Examples of prompts:

[1973] "User types in question: 'What fertilizer should I use for the current weather?'

[1974] Prompt for generative AI model: "User emotional state: Neutral. Input question: What fertilizer should I use based on the current weather?"

[1975] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1976] Step 1:

[1977] The server collects data on pesticide-free farming. The data is collected from the internet and existing databases, and mainly covers the types and usage of organic fertilizers, the ecology of pests and diseases, and climate data. The input is data from the source, and the output is cleansed data. The data is cleansed and noise and missing data are removed.

[1978] Step 2:

[1979] The server normalizes the cleansed data and trains it using generative AI. In this process, the data is converted into a format suitable for the AI ​​model, and the AI ​​is trained on the know-how of pesticide-free farming. The input is the cleansed data, and the output is a trained AI model.

[1980] Step 3:

[1981] The trained model is stored on the server and updated as needed. The server manages model versions and always maintains the latest cultivation know-how. The input is the trained AI model, and the output is the stored model.

[1982] Step 4:

[1983] A sensing device connected to the terminal periodically collects data on soil quality, temperature, humidity, light intensity, etc. The input is real-time data from the sensing device, and the output is data sent to the server.

[1984] Step 5:

[1985] The server receives the data sent from the device and analyzes it using generative artificial intelligence. The purpose of the analysis is to diagnose the current condition of the crops and derive the necessary countermeasures. The input is the condition data from the device, and the output is advice as the diagnosis result.

[1986] Step 6:

[1987] The server sends the generated advice and diagnostic results to the terminal. The server also responds to feedback and questions from the user as needed. The input is the diagnostic results and advice, and the output is the information sent to the terminal.

[1988] Step 7:

[1989] The terminal notifies the farmer of advice and diagnostic results sent from the server. Specifically, appropriate information is provided through alerts and display panels. The input is advice and diagnostic results, and the output is notifications to the farmer.

[1990] Step 8:

[1991] Farmers use terminals to input questions to the generative AI. The questions are sent from the terminals to the server. The input is the farmer's question, and the output is the question sent to the server.

[1992] Step 9:

[1993] The server recognizes the farmer's emotional state. It uses an emotion engine to analyze the tone of voice and text content. The input is the farmer's voice or text data, and the output is the analyzed emotional state.

[1994] Step 10:

[1995] The server adjusts the content and timing of advice based on the emotional state. If the user is feeling stressed, the server provides advice along with an encouraging message. The input is the analyzed emotional state, and the output is the adjusted advice.

[1996] Step 11:

[1997] Farmers perform farm work based on the advice provided. They input their results and feelings into a terminal and send them to a server. The input is the farmer's feedback, and the output is the feedback sent to the server.

[1998] Step 12:

[1999] The server analyzes the observation data and sentiment information and proposes new advice or adjustments as needed. The input is the farmer's feedback and observation data, and the output is new advice.

[2000] Examples of prompts:

[2001] "User types in question: 'What fertilizer should I use for the current weather?'

[2002] Prompt for generative AI model: "User emotional state: Neutral. Input question: What fertilizer should I use based on the current weather?"

[2003] 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.

[2004] 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.

[2005] 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.

[2006] [Fourth embodiment]

[2007] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[2008] 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.

[2009] 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).

[2010] 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.

[2011] 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.

[2012] 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).

[2013] 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.

[2014] 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.

[2015] 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.

[2016] 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.

[2017] 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.

[2018] 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.

[2019] 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."

[2020] The system of the present invention includes a method and an apparatus for effectively supporting pesticide-free cultivation. A specific embodiment will be described below, focusing on a server, a terminal, and a user (agricultural worker).

[2021] Data collection and learning

[2022] server

[2023] The server collects a large amount of data related to pesticide-free farming from the internet and existing databases, including types of organic fertilizer and their application methods, pest and disease ecology, and climate data.

[2024] The server cleanses the collected data, removing noise and missing data. It then normalizes the data and trains it using generative AI. Specifically, the data is formatted in a way that makes it easy for the AI ​​model to understand, and it learns the know-how of pesticide-free farming.

[2025] The model generated as a result of learning is stored on the server and updated as necessary.

[2026] Crop condition diagnosis

[2027] Terminal

[2028] Sensing devices (e.g., e-kakashi) connected to the terminal periodically collect data such as soil quality, temperature, humidity, and light intensity.

[2029] The collected data is transmitted from the terminal to a server.

[2030] server

[2031] The server receives the data sent from the device and analyzes it using generative artificial intelligence. The purpose of the analysis is to diagnose the current condition of the crops and derive the necessary countermeasures.

[2032] Based on the analysis results, appropriate advice and reminders are generated. For example, if the soil pH level is outside the appropriate range, advice on the timing and amount of organic fertilizer to be used is generated.

[2033] Communication with farmers

[2034] server

[2035] The server sends the generated advice and diagnostic results to the terminal.

[2036] It also accepts feedback and questions from farmers and generates optimal answers, which are then sent to the device.

[2037] Terminal

[2038] The terminal notifies the farmer of advice and diagnostic results sent from the server, for example by providing appropriate information via an alert or display panel.

[2039] Farmers can also use their devices to input questions to the generative AI, which are then sent to the server.

[2040] User (farmer)

[2041] Farmers can then use the advice they receive through the device to carry out their farming work, such as applying appropriate organic fertilizers or taking measures to prevent specific pests and diseases.

[2042] The results of the advice and any feedback felt are entered into the device and sent to the server.

[2043] Cultivation management

[2044] Terminal

[2045] The terminal continuously monitors the condition of the crops through a sensing device, and the collected data is sent to a server in real time.

[2046] server

[2047] The server analyzes changes in the cultivation environment based on the received data and generates necessary reminders and additional advice, such as "Low temperatures are predicted this week, so please take measures to prevent frost."

[2048] Any generated reminders or additional advice will also be sent to the farmer via the device.

[2049] Specific examples

[2050] Examples of organic fertilizer use

[2051] 1. The device uses e-kakashi to measure the soil's pH level, humidity, and temperature, and sends the data to the server.

[2052] 2. The server analyzes the received data using generative artificial intelligence and generates advice on the appropriate timing and amount of organic fertilizer to use based on the condition of the soil.

[2053] 3. The server sends the generated advice to the terminal and notifies the farmer.

[2054] 4. The user (farmer) applies organic fertilizer based on the advice and observes the results.

[2055] 5. The terminal measures the observation results again using the sensing device and sends the data to the server.

[2056] 6. The server analyzes the new data and generates additional advice if necessary, and notifies the farmer via the terminal.

[2057] Examples of pest prevention

[2058] 1. The server trains the generative AI to learn about the ecology of pests and diseases and preventive measures.

[2059] 2. The device uses e-kakashi to collect data on the crops and their surrounding environment and transmits it to the server.

[2060] 3. The server analyzes the received data using generative artificial intelligence and generates advice on risk assessments of pest and disease outbreaks and preventive measures.

[2061] 4. The server sends the generated advice to the terminal and notifies the farmer.

[2062] 5. The user (farmer) implements preventive measures based on the advice and observes the results.

[2063] 6. The device measures the observations and sends them to the server.

[2064] 7. The server continuously analyzes the data, generates new advice, and notifies the farmer via his / her terminal.

[2065] As described above, this system enables farmers to accurately grasp the know-how and timing required for pesticide-free cultivation and then put it into practice.

[2066] The processing flow will be explained below.

[2067] Examples of organic fertilizer use

[2068] Step 1:

[2069] The device uses e-kakashi to measure the soil's pH level, humidity, and temperature, and then sends the data to the server.

[2070] Step 2:

[2071] The server refers to the contents of the database based on the data received and preprocesses the data, specifically removing outliers and normalizing the data.

[2072] Step 3:

[2073] The server uses generative artificial intelligence to analyze the pre-processed data and generate information on the current state of the crops and the appropriate use of organic fertilizer.

[2074] Step 4:

[2075] Based on the analysis results, the server generates advice including the appropriate timing and amount of organic fertilizer to use and sends that advice to the terminal.

[2076] Step 5:

[2077] The terminal notifies the farmer of the advice sent from the server, for example by displaying the information via an alert or a display panel.

[2078] Step 6:

[2079] The user (farmer) applies organic fertilizer based on the advice, observes the results, and enters the observation results into the terminal.

[2080] Step 7:

[2081] The device collects the observations and sends the data to a server.

[2082] Step 8:

[2083] The server analyzes the observation data and suggests new advice or adjustments as needed, for example determining whether soil conditions have improved and suggesting further preventative measures or additional fertilization.

[2084] Examples of pest prevention

[2085] Step 1:

[2086] The server trains the generative AI with data on pests and diseases, including their ecology, preventative measures, and their relationship with climate.

[2087] Step 2:

[2088] The terminal uses e-kakashi to collect data on the condition of the crops and the surrounding environment (temperature, humidity, air temperature, etc.) and send it to the server.

[2089] Step 3:

[2090] The server preprocesses the received data, removing outliers and normalizing the data.

[2091] Step 4:

[2092] The server analyzes the preprocessed data using generative artificial intelligence to generate risk assessments and preventative measures for pest and disease outbreaks.

[2093] Step 5:

[2094] The server generates advice including preventive measures based on the risk assessment and transmits the advice to the terminal.

[2095] Step 6:

[2096] The terminal notifies the farmer of the advice sent from the server, for example by providing information using a display panel or alerts.

[2097] Step 7:

[2098] The user (farmer) implements preventive measures based on the advice received, for example, installing moth nets or spraying natural pesticides.

[2099] Step 8:

[2100] The device monitors the results again through e-kakashi and sends the data to the server.

[2101] Step 9:

[2102] The server analyzes the monitoring data and evaluates the effectiveness of preventive measures, generating additional measures and reminders as needed and sending notifications via the device.

[2103] Through the above processing steps, the present invention effectively supports pesticide-free cultivation, enabling farmers to accurately grasp and implement the necessary know-how and timing.

[2104] Example 1

[2105] 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."

[2106] Practicing pesticide-free cultivation in the agricultural field is extremely delicate and complex. To successfully cultivate crops without pesticides, it is necessary to use organic fertilizer at the appropriate time, prevent pests and diseases, and constantly monitor the condition of the crops. However, acquiring the knowledge and skills necessary to achieve this requires a great deal of effort and time. For this reason, there is a need for a support system to help farmers cultivate crops without pesticides effectively.

[2107] 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.

[2108] In this invention, the server includes a means for collecting data on pesticide-free cultivation, a means for training the artificial intelligence to learn know-how on pesticide-free cultivation based on the data on pesticide-free cultivation, and a means for saving and updating the model as a result of the learning, thereby making it possible to provide optimal advice and diagnostic results on pesticide-free cultivation.

[2109] "Data on pesticide-free cultivation" refers to information related to the knowledge and techniques required to carry out pesticide-free cultivation, including types of organic fertilizers and how to use them, the ecology of pests and diseases, and climate data.

[2110] "Generative AI" refers to AI that uses technologies such as machine learning and deep learning to analyze data and automatically generate and learn knowledge for specific purposes.

[2111] "Sensing device" refers to a measuring device used to measure parameters of the crop environment, such as soil quality, temperature, humidity, and light intensity.

[2112] "Plant condition data" refers to data that includes information about crops and their surrounding environment, such as soil quality, temperature, humidity, and light intensity.

[2113] "Diagnosis results" refers to information about the health of agricultural crops and necessary measures obtained by analyzing collected plant condition data.

[2114] "Advice" refers to specific instructions and suggestions for farmers to successfully cultivate crops without pesticides, based on the diagnostic results generated.

[2115] "Users" refers to agricultural workers and those involved in agriculture who practice pesticide-free cultivation.

[2116] "Feedback" refers to information provided by the user regarding the evaluation of the system's advice and diagnostic results and the execution results.

[2117] "Model" refers to a computational model that incorporates know-how for pesticide-free cultivation using generative artificial intelligence that learns from collected data.

[2118] "Real-time monitoring" refers to continuously observing plant condition data using sensing devices and immediately processing the results.

[2119] A "reminder" is information that notifies a user of the timing and precautions to take when taking a specific action.

[2120] "Additional advice" refers to new instructions or suggestions generated based on real-time monitoring data.

[2121] The system of this invention includes a method and an apparatus for collecting data, analyzing it, and providing advice to support pesticide-free cultivation. A specific embodiment will be described, focusing on a server, a terminal, and a user (agricultural worker).

[2122] Data collection and learning

[2123] server

[2124] The server collects data related to pesticide-free farming from the Internet and existing databases. This data includes types of organic fertilizers, application methods, pest and disease ecology, and climate data. As a specific example, the Open Weather Map API can be used to collect weather data.

[2125] The collected data is cleansed to remove noise and missing data, then normalized and trained using a generative artificial intelligence (AI) model (using TensorFlow or PyTorch, for example) to learn the know-how of pesticide-free farming.

[2126] The resulting AI model is stored on a server and regularly updated. This model is used to provide knowledge and optimal strategies for pesticide-free farming.

[2127] Crop condition diagnosis

[2128] Terminal

[2129] Sensing devices (e.g., e-kakashi) connected to the terminal periodically collect data on soil quality, temperature, humidity, light intensity, etc. This allows for a detailed understanding of the conditions of crops and their environment.

[2130] The collected data is sent to a server via Wi-Fi or mobile communications.

[2131] server

[2132] The server uses generative artificial intelligence to analyze the data it receives, specifically data on soil pH levels, temperature, and humidity, to diagnose the current condition of the crops.

[2133] Based on the analysis results, advice on pesticide-free cultivation is generated. For example, if the soil pH level is outside the appropriate range, advice is provided on the appropriate timing and amount of organic fertilizer to be used.

[2134] Communication with farmers

[2135] server

[2136] The server sends the generated advice and diagnostic results to the device, possibly in the form of push notification or email.

[2137] It also accepts feedback and questions from farmers and generates optimal answers based on that information. For example, it uses generative artificial intelligence to create optimal answers to users' questions.

[2138] Terminal

[2139] The terminal notifies the user of advice and diagnostic results sent from the server, allowing the user to receive appropriate information on pesticide-free farming in a timely manner.

[2140] Additionally, users can use their terminals to input questions into the system, which are then sent to the server.

[2141] User (farmer)

[2142] Farmers can then carry out agricultural work based on the advice they receive through the device, such as applying appropriate organic fertilizer or taking measures to prevent specific pests and diseases.

[2143] By inputting the results of the execution and feedback into the device and sending it to the server, the system continues to learn and provides more accurate advice.

[2144] Cultivation management

[2145] Terminal

[2146] The terminal continuously monitors the condition of the crops through a sensing device, and the collected data is sent to a server in real time.

[2147] server

[2148] The server analyzes changes in the cultivation environment based on the received data and generates necessary reminders and additional advice, such as "Low temperatures are predicted this week, so please take measures to prevent frost."

[2149] Specific examples

[2150] Examples of organic fertilizer use

[2151] 1. Using a sensing device (e-kakashi) connected to a terminal, the pH level, humidity, and temperature of the soil are measured and the data is sent to the server.

[2152] 2. The server analyzes the received data using generative artificial intelligence and generates advice on the appropriate timing and amount of organic fertilizer to use based on the condition of the soil.

[2153] 3. The server sends the generated advice to the terminal and notifies the farmer.

[2154] 4. The user (farmer) applies organic fertilizer based on the advice received through the terminal and observes the results.

[2155] 5. The terminal measures the observation results again using the sensing device and sends the data to the server.

[2156] 6. The server analyzes the new data and generates additional advice if necessary, and notifies the farmer via the terminal.

[2157] Examples of pest prevention

[2158] 1. The server trains the generative AI to learn about the ecology of pests and diseases and preventive measures.

[2159] 2. The terminal uses a sensing device (e-kakashi) to collect data on the crops and their surrounding environment and transmits it to the server.

[2160] 3. The server analyzes the received data using generative artificial intelligence and generates advice on risk assessments of pest and disease outbreaks and preventive measures.

[2161] 4. The server sends the generated advice to the terminal and notifies the farmer.

[2162] 5. The user (farmer) implements preventive measures based on the advice and observes the results.

[2163] 6. The device measures the observations and sends them to the server.

[2164] 7. The server continuously analyzes the data, generates new advice, and notifies the farmer via his / her terminal.

[2165] Prompt Sentence Examples

[2166] 1. What is the appropriate time and amount to use organic fertilizer?

[2167] 2. What measures are necessary to prevent pests and diseases?

[2168] As described above, the system of the present invention effectively supports farmers in accurately grasping the knowledge and timing necessary for pesticide-free cultivation and putting it into practice.

[2169] The flow of the identification process in the first embodiment will be described with reference to FIG.

[2170] Step 1:

[2171] Data collection

[2172] The server collects data on organic farming from sources including the internet and existing databases, including types of organic fertilizers and their application methods, pest and disease ecology, and climate data.

[2173] Input: Raw data from the internet and existing databases.

[2174] Output: Data related to pesticide-free cultivation before cleansing.

[2175] What it does: The server collects data using APIs and web scraping and stores it in a local database.

[2176] Step 2:

[2177] Data Cleansing

[2178] The server cleanses the collected data, removing noise and missing data, thereby improving the quality of the data.

[2179] Input: Raw data collected.

[2180] Output: Clean, cleansed data.

[2181] What it does: The server runs algorithms to detect outliers and impute missing values, for example filtering out abnormal pH values, temperatures, etc.

[2182] Step 3:

[2183] Data normalization

[2184] The server normalizes the cleansed data and puts it into a format that is easy for the generative AI model to understand.

[2185] Input: Cleansed data.

[2186] Output: Normalized data.

[2187] Specific operation: The server performs data scaling and normalization to convert numeric data into a certain range.

[2188] Step 4:

[2189] Model learning

[2190] The server uses the normalized data to train a generative AI model (using TensorFlow or PyTorch).

[2191] Input: Normalized data.

[2192] Output: The trained model.

[2193] Specific operation: The server applies a machine learning algorithm to teach the model know-how regarding pesticide-free cultivation.

[2194] Step 5:

[2195] Save Model

[2196] The server stores the trained model and updates it as needed.

[2197] Input: A trained model.

[2198] Output: The saved model.

[2199] Specific operation: The server saves the trained model in a database and sets a schedule for periodic retraining.

[2200] Step 6:

[2201] Sensing

[2202] A sensing device (e.g., e-kakashi) connected to the terminal periodically collects data such as soil quality, temperature, humidity, and light intensity.

[2203] Input: Environmental data (temperature, humidity, light level, etc.).

[2204] Output: Collected environmental data.

[2205] Specific operation: The device periodically reads data from the sensors and temporarily stores it in local storage.

[2206] Step 7:

[2207] Data transmission

[2208] The device sends the collected data to a server via Wi-Fi or mobile communications.

[2209] Input: Collected environmental data.

[2210] Output: The data sent to the server.

[2211] Specific operation: The terminal transmits data to the server via the network in real time or in batch processing.

[2212] Step 8:

[2213] Data reception

[2214] The server receives the data sent from the terminal.

[2215] Input: Data sent from the terminal.

[2216] Output: The received data.

[2217] Specific operation: The server immediately stores the received data in a database and prepares it for analysis.

[2218] Step 9:

[2219] Data analysis

[2220] The server analyzes the received data using a generative AI model to diagnose the current condition of the crops.

[2221] Input: Received data, trained model.

[2222] Output: Diagnostic results.

[2223] Specific operation: The server inputs data into the generative AI model and analyzes the health of the crops and necessary measures.

[2224] Step 10:

[2225] Advice Generation

[2226] Based on the analysis results, the server generates advice and reminders on pesticide-free farming.

[2227] Input: Diagnostic results.

[2228] Output: Advice and reminders.

[2229] Specific actions: The server automatically generates a sentence that suggests appropriate measures and instructions for action.

[2230] Step 11:

[2231] Send Advice

[2232] The server transmits the generated advice to the terminal.

[2233] Input: Advice and reminders.

[2234] Output: Advice sent to the terminal.

[2235] Specific behavior: The server sends the advice using a messaging protocol.

[2236] Step 12:

[2237] Receive feedback

[2238] The server accepts feedback and questions from users via the terminal.

[2239] Input: User feedback and questions.

[2240] Output: Feedback and questions received.

[2241] Specific operation: The device sends questions and feedback entered by the user to the server.

[2242] Step 13:

[2243] Optimal response generation

[2244] The server uses a generative AI model to generate optimal responses to the feedback and questions it receives.

[2245] Input: Feedback, questions, trained models.

[2246] Output: Best response.

[2247] Specific operation: The server inputs feedback and questions into the generative AI model to generate optimal answers and improvements.

[2248] Step 14:

[2249] Response Send

[2250] The server generates a response and sends it to the terminal.

[2251] Input: Best response.

[2252] Output: The response sent to the terminal.

[2253] Specific operation: The server sends a response to the terminal via a messaging protocol.

[2254] Step 15:

[2255] monitoring

[2256] The terminal monitors the condition of the plants in real time through sensing devices.

[2257] Input: Real-time data from sensing devices.

[2258] Output: Monitored data.

[2259] Specific operation: The terminal continuously collects data and transmits it to the server in real time.

[2260] Step 16:

[2261] Additional advice generation

[2262] The server analyzes the received monitoring data and generates additional advice and reminders as needed.

[2263] Input: Real-time monitoring data.

[2264] Output: Additional advice and reminders.

[2265] Specific operation: The server has the generative AI model further analyze the data and generate additional feedback.

[2266] Step 17:

[2267] Send additional advice

[2268] The server sends the generated additional advice to the terminal.

[2269] Input: Additional advice or reminders.

[2270] Output: Additional advice sent to the terminal.

[2271] Specific behavior: The server sends additional advice via the messaging protocol.

[2272] Through these steps, the system supports farmers in effectively implementing pesticide-free cultivation.

[2273] (Application example 1)

[2274] 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."

[2275] In pesticide-free farming, it is extremely important to acquire the know-how for proper farming practices and carry them out efficiently and effectively. However, traditional methods are prone to time lags in data collection and delayed feedback, making it difficult to obtain real-time advice. Furthermore, in the food delivery industry, there is no established method for safely and quickly delivering pesticide-free produce. Highly accurate data collection and analysis, as well as real-time information provision, are essential to resolving these issues.

[2276] 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.

[2277] In this invention, the server includes a means for collecting data on pesticide-free farming, a means for training generative AI to learn pesticide-free farming know-how, and a means for saving and updating the model resulting from the learning. This allows farmers to receive pesticide-free farming advice in real time and perform appropriate farm work. This invention also includes a means for collecting data on food delivery and a means for providing delivery routes and specific instructions. This allows for the safe and prompt delivery of pesticide-free agricultural products. Furthermore, since information is provided in real time via a head-mounted display, delivery personnel can always act based on the latest information.

[2278] "Pesticide-free cultivation" is an agricultural method that uses natural methods to prevent pests and diseases when growing crops without using chemical pesticides, and is gentle on the environment and the human body.

[2279] "Generative AI" is an AI system that analyzes large amounts of data, automatically learns patterns, and generates predictions and optimal advice.

[2280] "Know-how" is a general term for the specific techniques, knowledge, and experience required for pesticide-free cultivation.

[2281] A "model" is a mathematical or statistical representation that serves as the basis for data analysis and prediction, generated as a result of training generative artificial intelligence.

[2282] A "sensing device" is a device for measuring and collecting environmental data such as temperature, humidity, and light intensity.

[2283] "Diagnosis results" are information about the condition of crops and necessary measures generated after analyzing collected data.

[2284] "Advice" refers to specific instructions or recommendations for farmers that are generated based on the diagnostic results.

[2285] "Communication means" refers to the technical means for transmitting and receiving data between the server and the farmer's terminal.

[2286] "Feedback" refers to the results of implementing advice, as well as opinions and questions, sent by farmers to the server.

[2287] "Delivery" refers to the process of delivering pesticide-free agricultural products to consumers.

[2288] A "head-mounted display" is a display device worn on the head to display information within the field of view.

[2289] "Real-time information provision" refers to providing the analysis results of sensing devices and servers to users immediately and without delay.

[2290] This invention provides a system that realizes efficient pesticide-free cultivation and safe food delivery. This system consists of a server, terminals (including sensing devices), and users (farmers and delivery personnel).

[2291] 1. Program processing overview

[2292] server

[2293] The server collects data on pesticide-free farming and uses it to train the generative AI on the know-how of pesticide-free farming. This data includes the types of organic fertilizers and their use, the ecology of pests and diseases, and climate data. The server cleanses the collected data, removing noise and missing data. The data is then normalized and trained by the generative AI. The model generated as a result of the learning is stored on the server and updated as necessary.

[2294] Terminal

[2295] Sensing devices connected to the terminal (e.g., soil sensors and temperature / humidity sensors) periodically collect data on soil quality, temperature, humidity, light intensity, etc. The collected data is sent from the terminal to a server. The server receives the data sent from the terminal and analyzes it using generative artificial intelligence. Based on the analysis results, advice and reminders regarding pesticide-free cultivation are generated. For example, if the soil's pH level is outside the appropriate range, advice on the appropriate timing and amount of organic fertilizer to be used is generated.

[2296] User (farmer)

[2297] Farmers perform farm work based on the advice they receive through the device. For example, they may apply appropriate organic fertilizer or take measures to prevent specific pests and diseases. The results of implementing the advice and feedback they feel are entered into the device and sent to a server. Furthermore, the device monitors the condition of the crops through a sensing device and continuously sends data to the server in real time.

[2298] 2. Food delivery support

[2299] The system also has a support function to help food delivery workers deliver pesticide-free produce safely and effectively. The server collects data on food deliveries and provides optimal delivery routes and handling methods. Delivery workers can receive advice in real time using a head-mounted display.

[2300] Hardware and Software Use Cases

[2301] Hardware: Head-mounted display (e.g. Microsoft HoloLens), soil sensor, temperature and humidity sensor

[2302] Software: Python, Server API (e.g. "https: / / agriculture-data-source.com / api / getData")

[2303] 3. Adding concrete examples

[2304] Specific work examples

[2305] 1. The server collects data on pesticide-free farming through the API.

[2306] 2. Based on the collected data, generative AI learns the know-how of pesticide-free cultivation.

[2307] 3. The model generated as a result of learning is saved on the server.

[2308] 4. Farmers use sensing devices to measure soil quality, temperature, humidity, light intensity, etc., and send the data from their terminals to a server.

[2309] 5. The server performs the analysis and generates appropriate advice.

[2310] 6. Delivery personnel will wear head-mounted ...

Claims

1. A means of collecting data on pesticide-free cultivation; A means for making a generative artificial intelligence learn know-how about pesticide-free cultivation based on the data on pesticide-free cultivation; A means of saving and updating the resulting model; means for collecting crop condition data using a sensing device; means for analyzing the crop condition data and generating a diagnosis result; A means for providing advice on pesticide-free cultivation based on the diagnosis results; means for transmitting and communicating said advice and diagnostic results to the farmer; means for receiving feedback from farmers and incorporating it into said model; A system including:

2. Using the generative artificial intelligence, optimal answers are generated for questions from agricultural workers, The system of claim 1 further comprising means for transmitting to said farmer.

3. Using the sensing device, monitor crop status data in real time; generating reminders and further advice based on said monitoring data; The system of claim 1 further comprising means for transmitting to said farmer.

Images