System

Abstract

A system is provided.SOLUTION: A system comprising: means for collecting production information from abundant farmers; means for storing the collected production information in a database; means for preprocessing the stored production information and inputting the preprocessed production information to a AI model; means for performing analysis using the AI model; means for generating an optimal plan for fruit production based on a result of the analysis; means for distributing the generated optimal plan to users; means for collecting feedback from the users; and means for storing the collected feedback in the database and causing the AI model to relearn.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] In modern society, the number of people involved in agriculture is decreasing due to the declining birthrate, aging population, and urbanization. As a result, it is becoming difficult to pass on the fruit production know-how cultivated by our predecessors. This problem makes it difficult to produce delicious fruit stably. Therefore, there is a need for a system that can effectively provide the know-how of our predecessors to successors and new entrants in agriculture. [Means for solving the problem]

[0005] To solve this problem, the present invention provides a fruit production suggestion system that includes the following means: means for collecting production information from experienced farmers, means for saving the collected production information in a database, means for preprocessing the saved production information and inputting it into an AI model, means for performing analysis using the AI ​​model, means for generating an optimal fruit production plan based on the analysis results, means for distributing the generated optimal plan to users, means for collecting feedback from users, and means for saving the collected feedback in a database and retraining the AI ​​model, thereby making it possible to provide know-how for consistently producing high-quality fruit.

[0006] An "experienced farmer" is someone who has been involved in agriculture for many years and has advanced knowledge and skills in crop production.

[0007] "Production information" refers to data on cultivation methods for specific crops, timing of fertilization, pest control measures, harvest time, etc.

[0008] A "database" is an electronic system that structures and stores collected production information for later rapid access.

[0009] "Preprocessing" refers to processes such as data cleaning, normalization, and missing value completion to prepare collected production information in a form suitable for analysis and input into AI models.

[0010] An "AI model" is a program that uses machine learning algorithms to learn patterns and rules from large amounts of data and make predictions and judgments based on new data.

[0011] "Analysis" is the process of deriving effective methods and optimal conditions for fruit production based on the data input into the AI ​​model.

[0012] An "optimal plan" is a method or schedule generated based on the analysis results for producing fruit most effectively in a specific region or under specific conditions.

[0013] "Users" are farmers and newcomers who receive information about fruit production through the system.

[0014] "Feedback" refers to reports and data from users about the results of implementing the proposed optimal plan and any additional information gained in the process.

[0015] "Retraining" is the process of updating an existing AI model using newly collected feedback data to enable it to make more accurate predictions and recommendations. [Brief explanation of the drawings]

[0016] [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

[0017] 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.

[0018] First, the terms used in the following description will be explained.

[0019] 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).

[0020] 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.

[0021] 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.

[0022] 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.

[0023] 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."

[0024] [First embodiment]

[0025] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0026] 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.

[0027] 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).

[0028] 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.

[0029] 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.

[0030] 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.

[0031] 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.

[0032] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0033] 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.

[0034] 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.

[0035] 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.

[0036] 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."

[0037] The present invention provides a system that collects production information from experienced farmers and proposes an optimal fruit production plan based on that information. The program processing of this system will be specifically described below.

[0038] Data collection

[0039] server

[0040] The server first collects production information from farmers, including soil type, climate conditions, fertilization timing, pruning methods, and pest and disease control measures. This information can be received through online forms or APIs. For example, the server obtains data from an apple farmer that includes the fertilization schedule and details of the fertilizers used.

[0041] Data storage

[0042] server

[0043] The server stores the collected production information in a database, which uses a high-performance storage system to structure and store the various crops and their associated production information, allowing for quick and easy access later.

[0044] Data preprocessing and analysis

[0045] server

[0046] The stored data is preprocessed before being input into the AI ​​model. Preprocessing includes data normalization, missing value completion, and outlier detection and removal. The preprocessed data is then analyzed by the AI ​​model to learn optimal fruit production methods. For example, in apple production, the model learns the relationship between climatic conditions and yield, and determines the optimal fertilization schedule and pruning method.

[0047] Generating and delivering optimal plans

[0048] server

[0049] Based on the analysis results, the server generates an optimal plan for specific fruit production, including recommended cultivation techniques, fertilization timing, and pest control measures. The generated plan is then sent from the server to the user's device.

[0050] Terminal

[0051] The user's terminal receives and displays the optimal plan sent from the server. The user then carries out fruit production based on this plan. For example, a new apple farmer may start growing apples while referring to the received plan.

[0052] Gathering feedback and relearning

[0053] User

[0054] The user provides the server with feedback on the results of implementing the proposed optimal plan and the information obtained during the process, including the yield, quality, and any problems encountered.

[0055] server

[0056] The server collects user feedback and stores it in a database. Furthermore, the collected feedback data is used to retrain the AI ​​model, improving the accuracy of its suggestions. For example, new pest control measures are learned based on feedback from apple farmers.

[0057] By operating this system, farmers can always obtain the latest know-how, enabling them to produce delicious fruit consistently. This cycle of continuous feedback and relearning keeps improving the quality of suggestions, allowing farmers to work on fruit production with peace of mind.

[0058] The processing flow will be explained below.

[0059] Program processing steps

[0060] Step 1:

[0061] The server collects production information from farmers, such as soil type, climate conditions, fertilization timing, pruning methods, and pest and disease control measures, via online forms and APIs.

[0062] Step 2:

[0063] The server stores the collected production information in a database, which is used to structure and organize the collected information, allowing it to be efficiently retrieved for subsequent processing.

[0064] Step 3:

[0065] The server preprocesses the production information stored in the database. This preprocessing includes normalizing the data, filling in missing values, and detecting and removing outliers. This prepares the data to improve the accuracy of analysis.

[0066] Step 4:

[0067] The server then inputs the preprocessed data into an AI model, which then analyzes the data. The AI ​​model then uses machine learning algorithms to learn patterns and rules from the data, such as the optimal fertilization schedule for a given climate.

[0068] Step 5:

[0069] Based on the analysis results of the AI ​​model, the server generates a specific optimal plan for fruit production, including recommended cultivation methods, fertilization timing, and pest control measures.

[0070] Step 6:

[0071] The server then delivers the generated optimal plan to the user's device. By providing an optimal plan tailored to each user's conditions, the user can receive individually customized advice.

[0072] Step 7:

[0073] The terminal receives the optimal plan delivered from the server and displays it to the user. The user then carries out fruit production based on the displayed plan. For example, a farmer who is starting fruit production for the first time can start cultivation according to the delivered plan.

[0074] Step 8:

[0075] The user provides feedback to the server via their terminal about the results and information gained during the process of implementing the proposed optimal plan, including information on harvest volume, quality, and any problems encountered.

[0076] Step 9:

[0077] The server collects user feedback and stores it in a database. The feedback data is used in the next re-learning step.

[0078] Step 10:

[0079] The server uses the collected feedback data to retrain the AI ​​model, improving the model's prediction accuracy and proposal content, and increasing the quality of the optimal plan provided from the next time onwards.

[0080] Through this series of processing steps, the fruit generation suggestion system can provide farmers with high-quality and reliable information, thereby improving the efficiency of fruit production.

[0081] Example 1

[0082] 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."

[0083] Conventional fruit production systems have the problem of being unable to provide optimal production plans based on local conditions and the experience of individual farmers. Furthermore, they lack the re-learning functionality to effectively utilize collected production information and adapt to the constantly evolving agricultural environment. These issues make it difficult to achieve efficient and stable fruit production.

[0084] 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.

[0085] In this invention, the server includes a means for collecting production information from experienced farmers, a means for storing the collected production information in a database, and a means for preprocessing the stored production information and inputting it into an AI technology model. This enables the generation of an optimal fruit production plan based on the collected information. The server further includes a means for analysis using the AI ​​technology model and a means for generating an optimal agricultural production plan based on the analysis results. This enables the provision of an optimal production plan based on the latest technology. The server also includes a means for collecting feedback from users, storing the collected feedback in a database, and retraining the AI ​​technology model. This enables continuous system improvement based on the collected feedback data.

[0086] "Agricultural worker" means a person who is engaged in agriculture and has knowledge and experience related to fruit production.

[0087] "Production information" refers to various data related to fruit production, such as soil type, climatic conditions, timing of fertilization, pruning methods, and measures against pests and diseases.

[0088] A "database" is an information system that systematically stores collected production information and feedback, allowing it to be searched, managed, and used.

[0089] "Preprocessing" refers to processing such as normalizing data, filling in missing values, and removing outliers before inputting collected production information into an AI technology model.

[0090] An "AI technology model" is an algorithm and calculation system that uses artificial intelligence technology to analyze data and generate optimal production plans and forecasts.

[0091] "Analysis" refers to analyzing pre-processed data using an AI technology model and extracting optimal production plans, including recommended cultivation methods, fertilization timing, and pest and disease control measures.

[0092] A "production plan" is a document that includes specific methods and procedures recommended for achieving efficient and stable fruit production.

[0093] "User" refers to a farmer who uses the system to receive a fruit production plan.

[0094] "Feedback" refers to returning the results of the production plan and data obtained during the process to the system, and includes information on harvest volume, quality, and any problems that arise.

[0095] "Relearning" refers to the retraining of AI technology models using collected feedback data, a process aimed at improving analytical accuracy and continuous improvement of the system.

[0096] MODE FOR CARRYING OUT THE INVENTION

[0097] The present invention relates to a system that collects production information from experienced farmers and proposes an optimal fruit production plan based on that information. A specific embodiment for implementing this system will be described below.

[0098] Data collection

[0099] The server first collects production information from farmers. This information includes soil type, climate conditions, fertilization timing, pruning methods, and pest and disease prevention measures. The information can be collected via an online form using a web page or mobile application, or via an API endpoint. For example, an apple farmer can enter information such as "soil type: clay" and "climatic conditions: average temperature 15°C" into an online form and submit it.

[0100] Data storage

[0101] The server stores production information received through online forms and APIs in a database. Relational databases such as MySQL and PostgreSQL are suitable for this purpose. The received data is validated according to a specified format and then saved in the database.

[0102] Data preprocessing and analysis

[0103] The stored data is preprocessed by the server and input into an AI technology model. Preprocessing involves normalizing the data, filling in missing values, and removing outliers using Python scripts and the Pandas library. The preprocessed data is then analyzed by an AI technology model built using TensorFlow or PyTorch. This analysis allows the system to learn optimal fertilization timing and pruning methods based on weather conditions and production data.

[0104] Generating and delivering optimal plans

[0105] The server generates a specific optimal plan for fruit production based on the analysis results of the AI ​​technology model. This plan includes details such as recommended cultivation methods, fertilization timing, and pest control measures. The generated plan is converted into a format such as PDF or JSON and sent to the terminal. The terminal receives the optimal plan sent from the server and displays it to the user. For example, a new apple farmer may start growing apples by referring to the plan sent from the server.

[0106] Gathering feedback and relearning

[0107] The user puts the proposed optimal plan into practice and provides the results and information on the process as feedback to the server. For example, information on the yield after fertilization or the occurrence of pests and diseases is provided as feedback. The server stores the collected feedback in a database and preprocesses it again. The preprocessed feedback data is used to retrain the AI ​​technology model, improving the accuracy of the next proposal. This continuous cycle of feedback and re-learning ensures that the latest know-how is always reflected in the system.

[0108] Examples of concrete examples and prompts

[0109] For example, the following data is collected from apple farmers in Nagano Prefecture:

[0110] Soil type: clay

[0111] Climate: Average temperature 15°C, annual precipitation 900mm

[0112] Fertilization timing: April and August

[0113] Fertilizer used: Nitrogen fertilizer 100kg / ha

[0114] Pruning method: Prune branches in half in February

[0115] Pest control: Pesticide spraying in June

[0116] Based on this data, the AI ​​technology model generates an optimal fruit production plan and suggests the following plan for new farmers:

[0117] Fertilization timing: Changed to March and July

[0118] Fertilizer used: Nitrogen fertilizer 120 kg / ha

[0119] Pruning method: Light pruning in March

[0120] Pest control: Pesticide spraying in May and July

[0121] Prompt Sentence Examples

[0122] "Please suggest the optimal fertilization schedule and pruning method based on data from apple farmers in Nagano Prefecture. The collected data includes soil type, climatic conditions, fertilization timing and fertilizer use, pruning methods, and pest and disease control measures."

[0123] By operating this system, farmers can always access the latest know-how and produce delicious fruit consistently. The continuous feedback and relearning cycle keeps improving the quality of the suggestions, so farmers can work on fruit production with peace of mind.

[0124] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0125] Step 1:

[0126] The server collects production information from farmers through online forms and APIs.

[0127] Input: Production information provided by farmers (e.g., soil type, climatic conditions, fertilization timing, pruning methods, pest and disease control measures)

[0128] Data processing: Organize the information entered in the online form in JSON format.

[0129] Output: Production information in formatted JSON format

[0130] Specifically, the system works by providing a form on a web page or mobile app where apple farmers can enter data such as "soil type: clay" and "climatic conditions: average temperature 15 degrees" and then submit it.

[0131] Step 2:

[0132] The server stores the received production information in a database.

[0133] Input: Production information in formatted JSON

[0134] Data processing: Generates SQL insert statements to save data to a specified table in the database.

[0135] Output: Production information stored in a database

[0136] Specifically, data is inserted into tables such as "soil information" and "climate information" using MySQL or PostgreSQL.

[0137] Step 3:

[0138] The server pre-processes the stored production information.

[0139] Input: Production information extracted from the database

[0140] Data processing: Using Python scripts and the Pandas library, we normalize the data, impute missing values, and remove outliers.

[0141] Output: A preprocessed, clean dataset

[0142] Specifically, the extracted data is loaded into a Pandas data frame, missing values ​​are filled with the average value, and outlying values ​​are removed.

[0143] Step 4:

[0144] The server inputs the preprocessed data into an AI technology model for analysis.

[0145] Input: Preprocessed clean dataset

[0146] Data calculation: Data is input into a trained AI technology model using TensorFlow or PyTorch to predict the optimal production plan.

[0147] Output: Optimal production plan (e.g., fertilization timing, pruning method, pest control)

[0148] Specifically, the preprocessed data is input into a TensorFlow model, and a recommended plan such as "Fertilization timing: March and July" and "Pruning method: Light pruning in March" is output.

[0149] Step 5:

[0150] The server generates a production plan based on the analysis results and distributes it to the terminal.

[0151] Input: Analysis results from AI technology model

[0152] Data processing: Convert the analysis results into a format that is easy for users to understand (such as PDF or JSON).

[0153] Output: A file of the generated production plan

[0154] Specifically, the generated plan is converted into a PDF file and sent to the user's device by email.

[0155] Step 6:

[0156] The terminal receives and displays the optimum plan distributed from the server.

[0157] Input: Production plan file sent from the server

[0158] Data processing: Converts data into a format suitable for display in a PDF viewer or app.

[0159] Output: Displayed production plan

[0160] Specifically, a new apple farmer opens the PDF plan he or she received and checks information such as "fertilize in March and July" and "spray pesticides in May and July."

[0161] Step 7:

[0162] The user puts the proposed optimal plan into practice and provides feedback on the results.

[0163] Input: Results of implementing the production plan (e.g., yield, quality, information on pests and diseases that have occurred)

[0164] Data processing: Enter feedback information through online forms or apps.

[0165] Output: Formatted feedback data

[0166] Specifically, the user enters information such as "harvest yield after fertilization: 800 kg" and "pests and diseases encountered: aphids" into an online form and submits it.

[0167] Step 8:

[0168] The server stores the feedback information in a database and uses it for re-learning.

[0169] Input: Formatted feedback data

[0170] Data processing: Save the data in a feedback table in the database and perform preprocessing again. Impute missing values ​​and remove outliers.

[0171] Output: Preprocessed feedback data

[0172] Specifically, the feedback data is stored in a database, and a clean dataset is prepared again using Python and Pandas.

[0173] Step 9:

[0174] The server uses the pre-processed feedback data to retrain the AI ​​technology model.

[0175] Input: Preprocessed feedback data

[0176] Data calculation: Feedback data is input into the AI ​​technology model, and the model parameters are readjusted to perform re-learning.

[0177] Output: AI technology model with improved accuracy

[0178] Specifically, the feedback data is re-input into the TensorFlow model, allowing it to learn and generate a new optimal plan.

[0179] (Application example 1)

[0180] 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."

[0181] Generally, farmers produce fruit based on their experience and knowledge, but their methods are largely dependent on the skills and knowledge of each individual farmer and are not standardized. This often results in inconsistent yields and quality, which in turn reduces the efficiency of agricultural production and potentially leads to unstable profits. Finding appropriate measures to quickly respond to changes in environmental conditions and climate is particularly challenging, and another contributing factor is the lack of automation in the production process. A system that can resolve these issues and improve the efficiency and quality of fruit production is needed.

[0182] 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.

[0183] In this invention, the server includes: means for collecting production information from experienced farmers; means for saving the collected production information in a database; means for preprocessing the saved production information and inputting it into an AI model; means for analyzing using the AI ​​model; means for generating an optimal plan for fruit production based on the analysis results; means for applying the generated optimal plan to production equipment; means for managing fertilization and pruning performed by the production equipment according to a schedule; means for the production equipment to automatically perform fertilization, pruning, and pest control; means for distributing the generated optimal plan to users; means for collecting feedback from users; and means for saving the collected feedback in a database and retraining the AI ​​model. This enables standardization and optimization of agricultural production, uniform harvest yields and quality, and labor-saving and cost reduction through automation.

[0184] "Agricultural workers" refers to people who work professionally in agriculture and have the skills and knowledge to produce crops such as fruits and vegetables.

[0185] "Production information" refers to various types of information that farmers use when producing fruits and crops, including soil type, climatic conditions, timing of fertilization, pruning methods, and pest and disease control measures.

[0186] A "database" is a high-performance storage system that stores collected production information and feedback information in a structured manner so that it can be accessed quickly and easily later.

[0187] "Preprocessing" refers to the processing carried out before collected production information is input into the AI ​​model, and specifically includes data normalization, filling in missing values, and detecting and removing outliers.

[0188] An "AI model" is a model that uses artificial intelligence technologies such as machine learning and deep learning, and is used to analyze production information and generate optimal fruit production plans.

[0189] The "analysis results" are data and information obtained through analytical processing using an AI model, and are used to derive optimal fruit production plans.

[0190] The "optimal plan" is an execution plan for fruit production generated based on the analysis results of the AI ​​model, and includes recommended cultivation methods, fertilization timing, and pest and disease prevention measures.

[0191] "Production equipment" refers to mechanical devices used to automate various tasks in fruit production, specifically robots and machines that perform fertilization, pruning, and pest control.

[0192] "Feedback" refers to the results of the user's implementation of the proposed optimal plan and the information obtained in the process, including harvest volume, quality, and any problems that arise.

[0193] "Retraining" is the process of retraining an AI model using collected feedback information to improve the accuracy of its suggestions.

[0194] As an embodiment of the present invention, a specific description will be given of how the elements of the server, terminal, and user work together.

[0195] 1. Data Collection

[0196] The server first collects production information from farmers, including soil type, weather conditions, fertilization timing, pruning methods, pest control measures, etc. Data can be collected via an online form or API.

[0197] 2. Data storage

[0198] The server stores the collected production information in a database, which uses a high-performance storage system for efficient management of structured data, allowing this data to be accessed quickly and easily later.

[0199] 3. Data Preprocessing

[0200] The server preprocesses the stored data, which includes normalizing the data, imputing missing values, and removing outliers. The preprocessed data is then input into machine learning and deep learning AI models.

[0201] 4. Analysis using AI models

[0202] The server inputs the preprocessed data into an AI model for analysis. The AI ​​model is built using machine learning frameworks such as TensorFlow and Keras. The analysis results generate an optimal fruit production plan.

[0203] 5. Generating and Applying the Optimal Plan

[0204] The server generates a specific production plan based on the analysis results. This plan includes recommended cultivation techniques, fertilization timing, and pest control measures. The server then applies this optimal plan to production equipment. Production equipment is automated machinery such as robots that perform fertilization, pruning, and pest control.

[0205] 6. Plan Management and Execution

[0206] The production equipment manages and executes fertilization and pruning according to a schedule based on the optimal plan received from the server, significantly reducing the amount of manual management work.

[0207] 7. Delivery of the Plan

[0208] The server then delivers the generated optimal plan to the user's device, and the user performs the task while referring to the plan displayed on the smart glasses or robot.

[0209] 8. Gathering Feedback

[0210] Users provide feedback to the server on the results of their practice and information gained during the process, including yield, quality, and any problems encountered.

[0211] 9. Relearn

[0212] The server stores the collected feedback data in a database and retrains the AI ​​model, which continually improves the accuracy of its suggestions.

[0213] Specific examples

[0214] For example, an AI model analyzes data collected from apple farmers and generates an optimal fertilization schedule. This plan is then executed by production equipment, and information on yield and quality is sent back to the server as feedback. The AI ​​model re-learns based on the collected feedback data, and a new optimal plan is generated.

[0215] Prompt Sentence Examples

[0216] "Task: Analyze data collected from farmers and generate an optimal fruit production plan. Data collected includes soil type, weather conditions, fertilization timing, pruning methods, and pest and disease control."

[0217] In this way, this invention will enable the standardization and optimization of agricultural production processes, leading to labor savings through automation and improved yields and quality.

[0218] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0219] Step 1:

[0220] Data collection

[0221] The server collects production information from farmers using online forms and APIs, including information on soil type, climate conditions, fertilization timing, pruning methods, and pest and disease control. The input is various production information provided by farmers, and the output is structured data of this information. The server converts this information into an appropriate format and stores it in a database.

[0222] Step 2:

[0223] Data storage

[0224] The server stores the production information collected in step 1 in a database. The input is structured production information data, and the output is production information data stored in a database. A database management system (e.g., PostgreSQL) is used to store data quickly and efficiently.

[0225] Step 3:

[0226] Data Preprocessing

[0227] The server performs preprocessing on the stored production information before inputting it into the AI ​​model. Specifically, it normalizes the data, fills in missing values, and detects and removes outliers. The input is the production information data stored in the database, and the output is the preprocessed data. This preprocessing is performed using the Python Pandas library.

[0228] Step 4:

[0229] Analysis using AI models

[0230] The server inputs the preprocessed data into an AI model for analysis. Specifically, it uses machine learning and deep learning algorithms to generate an optimal fruit production plan. The input is the preprocessed data, and the output is the analysis results from the AI ​​model. Machine learning frameworks such as TensorFlow and Keras are used.

[0231] Step 5:

[0232] Generating an optimal plan

[0233] Based on the analysis results of the AI ​​model, the server generates an optimal fruit production plan for the production equipment (factory robots) to execute. The input is the analysis results, and the output is an optimal plan that includes specific fertilization timing, pruning methods, pest control measures, etc.

[0234] Step 6:

[0235] Applying and Managing Plans

[0236] The production equipment receives the generated optimal plan and manages fertilization and pruning according to the schedule. This includes setting the timing for fertilization and pruning and performing the actual work. The input is the optimal plan, and the output is the execution schedule and the specific fertilization and pruning operations.

[0237] Step 7:

[0238] Execution and automation

[0239] The production equipment automatically carries out fertilization, pruning, and pest control based on an optimal plan. The input is the execution schedule, and the output is the results of fertilization and pruning.

[0240] Step 8:

[0241] Plan Delivery

[0242] The server delivers the generated optimal plan to the user's device. The user performs the task while referring to the plan displayed on the smart glasses or robot. The input is the optimal plan, and the output is the plan displayed on the user's device.

[0243] Step 9:

[0244] Feedback collection

[0245] The user provides the server with the results of implementing the proposed optimal plan and information obtained during the process, including harvest volume, quality, and any problems that occurred. The input is the implementation results and information obtained during the process, and the output is feedback data.

[0246] Step 10:

[0247] Relearn

[0248] The server stores the collected feedback data in a database and retrains the AI ​​model, which continuously improves the accuracy of the suggestions. The input is the feedback data, and the output is the retrained AI model.

[0249] 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.

[0250] This invention improves the user experience by combining a system that collects production information from experienced farmers and proposes optimal fruit production plans based on that information with an emotion engine that recognizes the user's emotions. The program processing of this system is explained in detail below.

[0251] Data collection and storage

[0252] server

[0253] The server first collects production information from farmers. This information includes soil type, climate conditions, fertilization timing, pruning methods, and pest and disease prevention measures. This information can be received through online forms or APIs. For example, data is obtained from an apple farmer that includes fertilization schedules and details of the fertilizers used. The server then stores the collected production information in a database.

[0254] Data preprocessing and analysis

[0255] server

[0256] The stored data is preprocessed before being input into the AI ​​model. Preprocessing includes data normalization, missing value completion, and outlier detection and removal. The preprocessed data is then analyzed by the AI ​​model to learn optimal fruit production methods. For example, in apple production, the model learns the relationship between climatic conditions and yield, and determines the optimal fertilization schedule and pruning method.

[0257] Generating and delivering optimal plans

[0258] server

[0259] Based on the analysis results, the server generates an optimal plan for specific fruit production, including recommended cultivation techniques, fertilization timing, and pest control measures. The generated plan is then sent from the server to the user's device.

[0260] Terminal

[0261] The user's terminal receives and displays the optimal plan sent from the server. The user then carries out fruit production based on this plan. For example, a new apple farmer may start growing apples while referring to the received plan.

[0262] Gathering feedback and relearning

[0263] User

[0264] The user provides the server with feedback on the results of implementing the proposed optimal plan and the information obtained during the process, including the yield, quality, and any problems encountered.

[0265] server

[0266] The server collects user feedback and stores it in a database. Furthermore, the collected feedback data is used to retrain the AI ​​model, improving the accuracy of its suggestions. For example, new pest control measures are learned based on feedback from apple farmers.

[0267] Introducing the Emotion Engine

[0268] Server and Device

[0269] The server is equipped with an emotion engine that recognizes the user's emotions. The emotion engine analyzes the user's emotional state when entering feedback and uses that information to further refine the optimal plan. For example, if the user is facing a difficult situation, the engine can provide more detailed support information.

[0270] Terminal

[0271] The device uses an emotion engine to monitor the user's emotions in real time during interactions, and if the user feels stressed, it will provide encouraging messages or additional support to keep the user motivated.

[0272] Specific examples

[0273] For example, let's say an apple farmer starts cultivating based on a proposed plan, but is having trouble with pests and diseases. When the user provides feedback about this, the emotion engine recognizes the user's anxiety and immediately provides specific countermeasures and contact information for experts. This allows the user to take measures with peace of mind.

[0274] This system allows farmers to receive the latest know-how as well as emotional support when needed, enabling them to produce high-quality fruit consistently. The introduction of the emotion engine allows users to use the service with peace of mind, which is expected to lead to more effective production.

[0275] The processing flow will be explained below.

[0276] Program processing steps

[0277] Step 1:

[0278] The server collects production information from farmers through online forms and APIs, such as soil type, climate conditions, fertilization timing, pruning methods, pest control measures, etc. For example, it collects fertilization schedules and details of the fertilizers used from apple farmers.

[0279] Step 2:

[0280] The server stores the collected production information in a database, which structures and organizes the collected information so that it can be accessed quickly and efficiently for subsequent processing.

[0281] Step 3:

[0282] The server performs preprocessing of the production information stored in the database. Preprocessing includes data normalization, missing value completion, and outlier detection and removal. For example, missing values ​​are completed with the average value, and outliers are detected and removed.

[0283] Step 4:

[0284] The server inputs the preprocessed data into an AI model for analysis. The AI ​​model uses machine learning algorithms to learn patterns and rules from the data. For example, it can learn the optimal fertilization schedule for apple production.

[0285] Step 5:

[0286] Based on the results of the AI ​​model's analysis, the server generates a specific optimal plan for fruit production, including recommended cultivation methods, fertilization timing, and pest control measures.

[0287] Step 6:

[0288] The server then delivers the generated optimal plan to the user's device. By providing an optimal plan tailored to each user's conditions, the user can receive individually customized advice.

[0289] Step 7:

[0290] The terminal receives the optimal plan delivered from the server and displays it to the user. The user then carries out fruit production based on the displayed plan. For example, a new apple farmer starts cultivating fruit according to the delivered plan.

[0291] Step 8:

[0292] The device uses an emotion engine to monitor the user's emotions in real time, and if the user is feeling stressed, it will provide encouraging messages or additional support.

[0293] Step 9:

[0294] The user provides feedback to the server via their device about the results of implementing the proposed optimal plan and the emotions they felt during the process, including the yield, quality, problems encountered, and emotional state.

[0295] Step 10:

[0296] The server collects and stores feedback from users in a database, including the user's emotional state as analyzed by the emotion engine.

[0297] Step 11:

[0298] The server uses the collected feedback data and emotional information to retrain the AI ​​model, improving the accuracy of recommendations and the user experience, and enhancing the quality of the optimal plan provided from the next time onwards.

[0299] Through this series of processing steps, the fruit generation suggestion system can provide farmers with high-quality and reliable information, improving the efficiency of fruit production and the user experience. The introduction of the emotion engine creates an environment where users can use the service with peace of mind, and more effective production can be expected.

[0300] Example 2

[0301] 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."

[0302] Conventional agricultural production systems often propose incomplete production plans based solely on the experience and knowledge of farmers, and have the problem of not providing adequate proposals that are optimized for specific conditions or regions. Furthermore, because support does not take into account the emotional state of users, there is also the issue of being unable to respond appropriately when faced with difficult situations.

[0303] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for collecting production information from experienced farmers, means for saving the collected production information in a database, means for preprocessing the saved production information and inputting it into an analysis device, means for performing analysis using the analysis device, means for generating an optimal crop production plan based on the analysis results, means for distributing the generated optimal plan to users, means for collecting feedback from users, means for saving the collected feedback in a database and retraining the analysis device, means for analyzing emotional states, means for improving the optimal plan based on emotional states, and means for monitoring the user's emotions in real time during crop production. This makes it possible to provide a production plan optimized for specific conditions and regions and to provide appropriate support according to the user's emotions.

[0304] An "agricultural worker" is a person with specialized knowledge and experience in crop production and management.

[0305] "Production information" refers to data related to crop production, including soil type, climatic conditions, timing of fertilization, pruning methods, and measures against pests and diseases.

[0306] A "database" is a system for efficiently storing, managing, and searching large amounts of data.

[0307] "Preprocessing" is the process of preparing data for analysis, and includes normalizing data, imputing missing values, and detecting and removing outliers.

[0308] An "analysis device" is a device that uses stored data to perform complex calculations and processing to derive optimal solutions, and generally refers to an AI model or machine learning model.

[0309] "Analysis" is the process of deriving specific results or patterns from input data.

[0310] A "crop production plan" is a detailed description of the crop production methods that are best suited to specific conditions and regions.

[0311] "User" refers to farmers and related persons who use this system to produce crops.

[0312] "Feedback" refers to the act of a user returning the results of using the system and the data obtained to the system.

[0313] "Emotional state" refers to the mental state or emotion that a user displays when entering feedback or while working.

[0314] The "emotion engine" is a system that analyzes the user's emotional state from their input data and behavior, and provides an appropriate response.

[0315] "Real-time monitoring" is the process of instantly monitoring the user's behavior and status on the spot and quickly providing analytical results.

[0316] This invention is a system that proposes optimal crop production plans based on production information from experienced farmers, and further improves the user experience by combining it with an emotion engine that recognizes the user's emotions. The program processing of this system is explained below.

[0317] Data collection and storage

[0318] server

[0319] The server first collects production information from farmers. This information includes soil type, climate conditions, fertilization timing, pruning methods, and pest and disease control measures. This information can be received through an online form or API. For example, data including fertilization schedules and details of the fertilizers used is obtained from an apple farmer. The collected production information is stored in a database. Databases used include MySQL and PostgreSQL.

[0320] Data preprocessing and analysis

[0321] server

[0322] The stored data is input into an AI model after undergoing preprocessing. Preprocessing includes data normalization, missing value completion, and outlier detection and removal. Data processing libraries such as NumPy and Pandas are used for preprocessing. The preprocessed data is then analyzed by an AI model using machine learning frameworks such as TensorFlow and PyTorch. For example, in apple production, the relationship between weather conditions and yield can be learned to determine the optimal fertilization schedule and pruning method.

[0323] Generating and delivering optimal plans

[0324] server

[0325] Based on the analysis results, the server generates an optimal plan for specific crop production, including recommended cultivation techniques, fertilization timing, and pest control measures. The generated plan is then sent from the server to the user's device.

[0326] Gathering feedback and relearning

[0327] User

[0328] The user provides the server with feedback on the results of implementing the proposed optimal plan and information obtained during the process, including the yield, quality, and any problems encountered.

[0329] server

[0330] The server collects user feedback and stores it in a database. Furthermore, the collected feedback data is used to retrain the AI ​​model, improving the accuracy of its suggestions. For example, new pest control measures are learned based on feedback from apple farmers.

[0331] Introducing the Emotion Engine

[0332] Server and Device

[0333] The server is equipped with an emotion engine that recognizes the user's emotions. The emotion engine analyzes the user's emotional state when entering feedback and uses that information to further refine the optimal plan. For example, if the user is facing a difficult situation, the engine can provide more detailed support information.

[0334] Terminal

[0335] The device uses an emotion engine to monitor the user's emotions in real time during interactions, and if the user feels stressed, it will provide encouraging messages or additional support to keep the user motivated.

[0336] Specific examples

[0337] For example, let's say an apple farmer starts cultivating based on a proposed plan, but is having trouble with pests and diseases. When the user provides feedback about this, the emotion engine recognizes the user's anxiety and immediately provides specific countermeasures and contact information for experts. This allows the user to take measures with peace of mind.

[0338] Prompt Sentence Examples

[0339] "I applied fertilizer in March and July, but I'm having trouble with insect damage. What can I do?"

[0340] This system allows farmers to receive the latest know-how as well as emotional support when needed, enabling them to produce high-quality crops consistently. The introduction of the emotion engine allows users to use the service with peace of mind, which is expected to lead to more effective production.

[0341] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0342] Step 1: Data collection

[0343] server

[0344] The server provides an online form to farmers. The form contains input fields such as soil type, climate conditions, fertilization timing, pruning methods, and pest and disease prevention measures. The server receives the form data sent by the farmer and also processes API requests to obtain production information from outside. The input data includes fertilization schedules and details of the fertilizers used, which the server saves in a database. Specifically, the apple farmer enters information such as "clay soil" and "fertilization schedule for March and July" into the online form and submits it.

[0345] Input: Production information obtained via online forms or API requests.

[0346] Output: Production information stored in a database.

[0347] Step 2: Preprocessing

[0348] server

[0349] The server retrieves the stored production information from the database and performs preprocessing. Preprocessing includes data normalization, missing value completion, and outlier detection and removal. NumPy and Pandas are used to normalize the data and generate standardized data. Specifically, the server converts the fertilization timing (March and July) into a standardized numerical format and completes missing values ​​in the climate data with the average of past data.

[0350] Input: Production information retrieved from the database.

[0351] Output: The preprocessed dataset.

[0352] Step 3: Model analysis

[0353] server

[0354] The server inputs the preprocessed data into an AI model. The model used is trained using TensorFlow and PyTorch. The AI ​​model analyzes the optimal production method based on the input data. Specifically, it learns the relationship between weather conditions and yield, and derives the optimal fertilization schedule and pruning method.

[0355] Input: Preprocessed data.

[0356] Output: Analysis of optimal crop production methods.

[0357] Step 4: Generate and distribute optimal plans

[0358] server

[0359] Based on the analysis results, the server generates a specific crop production plan. This plan includes recommended cultivation methods, fertilization timing, and pest control measures. The generated plan is delivered to the user's device in JSON format. As a specific operation, the server generates a recommended plan to "apply ammonium nitrate fertilizer in March and July."

[0360] Input: Analysis results of the AI ​​model.

[0361] Output: The generated optimal plan.

[0362] Terminal

[0363] The terminal receives the optimal plan sent from the server and displays it on the application. The user produces crops based on this plan. Specifically, a new apple farmer begins cultivation based on the received plan.

[0364] Input: The optimal plan delivered by the server.

[0365] Output: The plan displayed on the terminal.

[0366] Step 5: Gather feedback and retrain

[0367] User

[0368] Users provide feedback to the server on the results of their work and the information they have gained during the process, including the yield, quality, and any problems they may have encountered. For example, an apple farmer might input, "After applying fertilizer in March, insect damage occurred."

[0369] Input: User feedback.

[0370] Output: Data sent to the server.

[0371] server

[0372] The server stores the feedback in a database and retrains the AI ​​model, which improves the accuracy of its suggestions. Specifically, it retrains the TensorFlow model using the new data.

[0373] Input: Feedback data from users.

[0374] Output: The updated AI model.

[0375] Step 6: Implementing the Emotion Engine

[0376] Server and Device

[0377] The server uses an emotion engine to analyze the user's emotions when entering feedback. If the user is facing a difficult situation, the emotion engine will provide specific solutions and specialist consultation options. The device will monitor the user's emotions in real time and provide encouraging messages if the user is feeling stressed. For example, if the user enters "I'm very worried" in the feedback, the emotion engine will analyze this, determine it as "anxiety," and provide additional support.

[0378] Input: User feedback, emotion data.

[0379] Output: Supportive information and messages based on emotional state.

[0380] (Application example 2)

[0381] 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."

[0382] Modern factories are required to improve production efficiency and reduce employee stress, but optimizing production schedules and managing machine maintenance remain challenges. Providing an efficient work environment that takes into account employee emotions is also important, but existing systems do not adequately address this issue.

[0383] 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.

[0384] In this invention, the server includes means for collecting production information from experienced farmers, means for saving the collected production information in a database, means for preprocessing the saved production information and inputting it into an AI model, means for analyzing using the AI ​​model, means for generating an optimal plan for fruit production based on the analysis results, means for distributing the generated optimal plan to users, means for collecting feedback from users, means for saving the collected feedback in a database and retraining the AI ​​model, and means for recognizing the emotional state of users and improving the optimal plan based on the analysis results. This makes it possible to optimize production schedules and provide an efficient work environment that takes employee emotions into consideration.

[0385] "Agricultural workers" refers to people who are engaged in agricultural work, especially those who have specialized knowledge and experience and work on producing crops.

[0386] "Production information" refers to detailed data on crop production, such as soil type, climatic conditions, fertilization timing, pruning methods, and pest and disease control measures.

[0387] A "database" refers to a system that can efficiently store, manage, and access large amounts of data.

[0388] "Preprocessing" refers to processes such as normalizing data, filling in missing values, and detecting and removing outliers, which are carried out to make the input data to an AI model analyzable.

[0389] An "AI model" refers to a system that uses artificial intelligence algorithms and machine learning techniques to analyze data, learn patterns, and make predictions and decisions.

[0390] "Analysis" refers to the process of extracting specific information and insights from collected data.

[0391] An "optimal plan" is a plan that proposes the most suitable methods and schedules for agricultural production based on the analysis results of an AI model.

[0392] "Delivery" refers to the process of transmitting the generated optimal plan to the user's terminal and making it available for use.

[0393] "Feedback" refers to information provided by users based on their practical results and experiences.

[0394] "Retraining" refers to the process of using collected feedback to retrain an AI model, improving its accuracy and the precision of its recommendations.

[0395] "Emotional state" refers to a user's psychological state or feeling, which is identified through text analysis and an emotion engine.

[0396] "Improvement" refers to the process of making changes or additions to existing plans or systems to make them more effective and improve their accuracy and usability.

[0397] A "system" is a set of multiple interrelated components and processes that function to achieve a specific purpose.

[0398] The present invention relates to a smart factory management application for optimizing factory management. The program processing of this system will be specifically described below.

[0399] Data collection and storage

[0400] The server collects production information from production equipment and facilities within the factory. This production information includes various sensor data, machine operating status, maintenance schedules, etc. The collected information is saved in the server's database in real time.

[0401] Data preprocessing and analysis

[0402] The server preprocesses the collected production information. This preprocessing includes data normalization, missing value completion, and outlier detection and removal. The preprocessed data is then input into an AI model. An example of the AI ​​model used here is RandomForestRegressor. This model analyzes the production information and generates an optimal production schedule and efficiency improvement plan.

[0403] Generating and delivering optimal plans

[0404] The server generates an optimal production plan based on the analysis results of the AI ​​model. This plan includes machine operation schedules, maintenance timing, efficient resource allocation, etc. The generated optimal plan is then distributed from the server to the user's device.

[0405] The user's device receives the optimal plan and presents it to the factory's monitoring system and manager. The user then carries out production activities based on this plan.

[0406] Gathering feedback and relearning

[0407] The user implements the proposed optimal plan and provides the results and information obtained during the process as feedback to the server, including production efficiency, problems, and areas for improvement.

[0408] The server stores the collected feedback in a database and retrains the AI ​​model to improve the accuracy of future suggestions. Retraining involves tuning the AI ​​model using the feedback data.

[0409] Introducing the Emotion Engine

[0410] The server is equipped with an emotion engine that recognizes the user's emotional state. The emotion engine uses text and voice analysis to determine the user's emotions. Once the emotional state is recognized, the server uses that information to further refine the optimal plan. This refinement can provide encouraging messages or additional support information if the user is facing a difficult situation.

[0411] Specific examples

[0412] For example, if a factory experiences frequent equipment breakdowns and employees are feeling stressed, the information is sent to the server through user feedback. The emotion engine recognizes the employee's stress level from this feedback and immediately provides suggestions for improvement and encouraging messages.

[0413] Example prompt sentence:

[0414] Generate plans to optimize maintenance frequency on production lines and reduce equipment breakdowns, plus add support messages when employees' stress levels are high.

[0415] In this way, the system of the present invention makes it possible to optimize production schedules and provide an efficient working environment that takes into account the emotions of employees.

[0416] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0417] Step 1:

[0418] The server collects production information from production equipment and facilities within the factory. This includes data obtained from sensors, machine operation status, maintenance schedules, etc. Input data is sent to the server in real time via API or sensor devices. The output is the collected production information stored in a database.

[0419] Step 2:

[0420] The server preprocesses the collected production information. The input is data obtained from the production information database. Data normalization, missing value imputation, and outlier detection and removal are performed. For example, missing values ​​are imputed using pandas and SimpleImputer, and data is normalized using StandardScaler. The output is the preprocessed data.

[0421] Step 3:

[0422] The server inputs the preprocessed data into an AI model for analysis. The input is the preprocessed data, and the output is the analysis results. The AI ​​model used is, for example, RandomForestRegressor, and analyzes the data to generate production schedules and efficiency plans.

[0423] Step 4:

[0424] The server generates an optimal production plan based on the analysis results. The input is the analysis results from the AI ​​model. The output is the generated optimal production plan, which includes machine operation schedules, maintenance timing, and efficient resource allocation.

[0425] Step 5:

[0426] The server distributes the generated optimal plan to the user's terminal. The input is the generated optimal production plan. The output is the distributed production plan, which the user uses to carry out production activities. The terminal displays the received production plan on the factory's monitoring system and to the manager.

[0427] Step 6:

[0428] The user implements the proposed optimal plan. The input is the delivered optimal plan. The results of the implementation and information obtained during the process are provided as feedback. The output is the collected feedback information.

[0429] Step 7:

[0430] The server stores the collected feedback information in a database and retrains the AI ​​model. The input is the feedback information. Retraining uses the feedback to tune the AI ​​model and improve the accuracy of its suggestions. The output is the retrained AI model.

[0431] Step 8:

[0432] The server analyzes the emotion from the feedback using an emotion engine that recognizes the user's emotional state. The input is the feedback text or voice data. The emotion engine performs text analysis to determine the user's emotion. The output is the recognized emotional state.

[0433] Step 9:

[0434] The server refines the optimal plan based on the recognized emotional state. The input is the emotional state recognized by the emotion engine and the existing optimal plan. For example, if the user is feeling stressed, it provides an encouraging message or additional support information. The output is the refined optimal plan.

[0435] Through the above processing steps, this system optimizes production schedules and provides an efficient working environment that takes into account the emotions of employees.

[0436] 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.

[0437] 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.

[0438] 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.

[0439] [Second embodiment]

[0440] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0441] 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.

[0442] 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).

[0443] 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.

[0444] 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.

[0445] 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).

[0446] 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.

[0447] 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.

[0448] 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.

[0449] 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.

[0450] 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.

[0451] 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."

[0452] The present invention provides a system that collects production information from experienced farmers and proposes an optimal fruit production plan based on that information. The program processing of this system will be specifically described below.

[0453] Data collection

[0454] server

[0455] The server first collects production information from farmers, including soil type, climate conditions, fertilization timing, pruning methods, and pest and disease control measures. This information can be received through online forms or APIs. For example, the server obtains data from an apple farmer that includes the fertilization schedule and details of the fertilizers used.

[0456] Data storage

[0457] server

[0458] The server stores the collected production information in a database, which uses a high-performance storage system to structure and store the various crops and their associated production information, allowing for quick and easy access later.

[0459] Data preprocessing and analysis

[0460] server

[0461] The stored data is preprocessed before being input into the AI ​​model. Preprocessing includes data normalization, missing value completion, and outlier detection and removal. The preprocessed data is then analyzed by the AI ​​model to learn optimal fruit production methods. For example, in apple production, the model learns the relationship between climatic conditions and yield, and determines the optimal fertilization schedule and pruning method.

[0462] Generating and delivering optimal plans

[0463] server

[0464] Based on the analysis results, the server generates an optimal plan for specific fruit production, including recommended cultivation techniques, fertilization timing, and pest control measures. The generated plan is then sent from the server to the user's device.

[0465] Terminal

[0466] The user's terminal receives and displays the optimal plan sent from the server. The user then carries out fruit production based on this plan. For example, a new apple farmer may start growing apples while referring to the received plan.

[0467] Gathering feedback and relearning

[0468] User

[0469] The user provides the server with feedback on the results of implementing the proposed optimal plan and the information obtained during the process, including the yield, quality, and any problems encountered.

[0470] server

[0471] The server collects user feedback and stores it in a database. Furthermore, the collected feedback data is used to retrain the AI ​​model, improving the accuracy of its suggestions. For example, new pest control measures are learned based on feedback from apple farmers.

[0472] By operating this system, farmers can always obtain the latest know-how, enabling them to produce delicious fruit consistently. This cycle of continuous feedback and relearning keeps improving the quality of the suggestions, allowing farmers to work on fruit production with peace of mind.

[0473] The processing flow will be explained below.

[0474] Program processing steps

[0475] Step 1:

[0476] The server collects production information from farmers, such as soil type, weather conditions, fertilization timing, pruning methods, and pest and disease control measures, via online forms and APIs.

[0477] Step 2:

[0478] The server stores the collected production information in a database, which is used to structure and organize the collected information, allowing it to be efficiently retrieved for subsequent processing.

[0479] Step 3:

[0480] The server preprocesses the production information stored in the database. This preprocessing includes normalizing the data, filling in missing values, and detecting and removing outliers. This prepares the data to improve the accuracy of analysis.

[0481] Step 4:

[0482] The server then inputs the preprocessed data into an AI model, which then analyzes the data. The AI ​​model then uses machine learning algorithms to learn patterns and rules from the data, such as the optimal fertilization schedule for a given climate.

[0483] Step 5:

[0484] Based on the analysis results of the AI ​​model, the server generates a specific optimal plan for fruit production, including recommended cultivation methods, fertilization timing, and pest control measures.

[0485] Step 6:

[0486] The server then delivers the generated optimal plan to the user's device. By providing an optimal plan tailored to each user's conditions, the user can receive individually customized advice.

[0487] Step 7:

[0488] The terminal receives the optimal plan delivered from the server and displays it to the user. The user then carries out fruit production based on the displayed plan. For example, a farmer who is starting fruit production for the first time may start cultivation according to the delivered plan.

[0489] Step 8:

[0490] The user provides feedback to the server via their terminal about the results and information gained during the process of implementing the proposed optimal plan, including information on harvest volume, quality, and any problems encountered.

[0491] Step 9:

[0492] The server collects user feedback and stores it in a database. The feedback data is used in the next re-learning step.

[0493] Step 10:

[0494] The server uses the collected feedback data to retrain the AI ​​model, improving the model's prediction accuracy and proposal content, and increasing the quality of the optimal plan provided from the next time onwards.

[0495] Through this series of processing steps, the fruit generation suggestion system can provide farmers with high-quality and reliable information, thereby improving the efficiency of fruit production.

[0496] Example 1

[0497] 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."

[0498] Conventional fruit production systems have the problem of being unable to provide optimal production plans based on local conditions and the experience of individual farmers. Furthermore, they lack the re-learning functionality to effectively utilize collected production information and adapt to the constantly evolving agricultural environment. These issues make it difficult to achieve efficient and stable fruit production.

[0499] 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.

[0500] In this invention, the server includes a means for collecting production information from experienced farmers, a means for storing the collected production information in a database, and a means for preprocessing the stored production information and inputting it into an AI technology model. This enables the generation of an optimal fruit production plan based on the collected information. The server further includes a means for analysis using the AI ​​technology model and a means for generating an optimal agricultural production plan based on the analysis results. This enables the provision of an optimal production plan based on the latest technology. The server also includes a means for collecting feedback from users, storing the collected feedback in a database, and retraining the AI ​​technology model. This enables continuous system improvement based on the collected feedback data.

[0501] "Agricultural worker" means a person who is engaged in agriculture and has knowledge and experience related to fruit production.

[0502] "Production information" refers to various data related to fruit production, such as soil type, climatic conditions, timing of fertilization, pruning methods, and measures against pests and diseases.

[0503] A "database" is an information system that systematically stores collected production information and feedback, allowing it to be searched, managed, and used.

[0504] "Preprocessing" refers to processing such as normalizing data, filling in missing values, and removing outliers before inputting collected production information into an AI technology model.

[0505] An "AI technology model" is an algorithm and calculation system that uses artificial intelligence technology to analyze data and generate optimal production plans and forecasts.

[0506] "Analysis" refers to analyzing pre-processed data using an AI technology model and extracting optimal production plans, including recommended cultivation methods, fertilization timing, and pest and disease control measures.

[0507] A "production plan" is a document that includes specific methods and procedures recommended for achieving efficient and stable fruit production.

[0508] "User" refers to a farmer who uses the system to receive a fruit production plan.

[0509] "Feedback" refers to returning the results of the production plan and data obtained during the process to the system, and includes information on harvest volume, quality, and any problems that arise.

[0510] "Relearning" refers to the retraining of AI technology models using collected feedback data, a process aimed at improving analytical accuracy and continuous improvement of the system.

[0511] MODE FOR CARRYING OUT THE INVENTION

[0512] The present invention relates to a system that collects production information from experienced farmers and proposes an optimal fruit production plan based on that information. A specific embodiment for implementing this system will be described below.

[0513] Data collection

[0514] The server first collects production information from farmers. This information includes soil type, climate conditions, fertilization timing, pruning methods, and pest and disease prevention measures. The information can be collected via an online form using a web page or mobile application, or via an API endpoint. For example, an apple farmer can enter information such as "soil type: clay" and "climatic conditions: average temperature 15°C" into an online form and submit it.

[0515] Data storage

[0516] The server stores production information received through online forms and APIs in a database. Relational databases such as MySQL and PostgreSQL are suitable for this purpose. The received data is validated according to a specified format and then saved in the database.

[0517] Data preprocessing and analysis

[0518] The stored data is preprocessed by the server and input into an AI technology model. Preprocessing involves normalizing the data, filling in missing values, and removing outliers using Python scripts and the Pandas library. The preprocessed data is then analyzed by an AI technology model built using TensorFlow or PyTorch. This analysis allows the system to learn optimal fertilization timing and pruning methods based on weather conditions and production data.

[0519] Generating and delivering optimal plans

[0520] The server generates a specific optimal plan for fruit production based on the analysis results of the AI ​​technology model. This plan includes details such as recommended cultivation methods, fertilization timing, and pest control measures. The generated plan is converted into a format such as PDF or JSON and sent to the terminal. The terminal receives the optimal plan sent from the server and displays it to the user. For example, a new apple farmer may start growing apples by referring to the plan sent from the server.

[0521] Gathering feedback and relearning

[0522] The user puts the proposed optimal plan into practice and provides the results and information on the process as feedback to the server. For example, information on the yield after fertilization or the occurrence of pests and diseases is provided as feedback. The server stores the collected feedback in a database and preprocesses it again. The preprocessed feedback data is used to retrain the AI ​​technology model, improving the accuracy of the next proposal. This continuous cycle of feedback and re-learning ensures that the latest know-how is always reflected in the system.

[0523] Examples of specific examples and prompts

[0524] For example, the following data is collected from apple farmers in Nagano Prefecture:

[0525] Soil type: clay

[0526] Climate: Average temperature 15°C, annual precipitation 900mm

[0527] Fertilization timing: April and August

[0528] Fertilizer used: Nitrogen fertilizer 100kg / ha

[0529] Pruning method: Prune branches in half in February

[0530] Pest control: Pesticide spraying in June

[0531] Based on this data, the AI ​​technology model generates an optimal fruit production plan and suggests the following plan for new farmers:

[0532] Fertilization timing: Changed to March and July

[0533] Fertilizer used: Nitrogen fertilizer 120 kg / ha

[0534] Pruning method: Light pruning in March

[0535] Pest control: Pesticide spraying in May and July

[0536] Prompt Sentence Examples

[0537] "Please suggest the optimal fertilization schedule and pruning method based on data from apple farmers in Nagano Prefecture. The collected data includes soil type, climatic conditions, fertilization timing and fertilizer use, pruning methods, and pest and disease control measures."

[0538] By operating this system, farmers can always access the latest know-how and produce delicious fruit consistently. The continuous feedback and relearning cycle keeps improving the quality of the suggestions, so farmers can work on fruit production with peace of mind.

[0539] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0540] Step 1:

[0541] The server collects production information from farmers through online forms and APIs.

[0542] Input: Production information provided by farmers (e.g., soil type, climatic conditions, fertilization timing, pruning methods, pest and disease control measures)

[0543] Data processing: Organize the information entered in the online form in JSON format.

[0544] Output: Production information in formatted JSON format

[0545] Specifically, the system works by providing a form on a web page or mobile app where apple farmers can enter data such as "soil type: clay" and "climatic conditions: average temperature 15 degrees" and then submit it.

[0546] Step 2:

[0547] The server stores the received production information in a database.

[0548] Input: Production information in formatted JSON

[0549] Data processing: Generates SQL insert statements to save data to a specified table in the database.

[0550] Output: Production information stored in a database

[0551] Specifically, data is inserted into tables such as "soil information" and "climate information" using MySQL or PostgreSQL.

[0552] Step 3:

[0553] The server pre-processes the stored production information.

[0554] Input: Production information extracted from the database

[0555] Data processing: Using Python scripts and the Pandas library, we normalize the data, impute missing values, and remove outliers.

[0556] Output: A preprocessed, clean dataset

[0557] Specifically, the extracted data is loaded into a Pandas data frame, missing values ​​are filled with the average value, and outlying values ​​are removed.

[0558] Step 4:

[0559] The server inputs the preprocessed data into an AI technology model for analysis.

[0560] Input: Preprocessed clean dataset

[0561] Data calculation: Data is input into a trained AI technology model using TensorFlow or PyTorch to predict the optimal production plan.

[0562] Output: Optimal production plan (e.g., fertilization timing, pruning method, pest control)

[0563] Specifically, the preprocessed data is input into a TensorFlow model, and a recommended plan such as "Fertilization timing: March and July" and "Pruning method: Light pruning in March" is output.

[0564] Step 5:

[0565] The server generates a production plan based on the analysis results and distributes it to the terminal.

[0566] Input: Analysis results from AI technology model

[0567] Data processing: Convert the analysis results into a format that is easy for users to understand (such as PDF or JSON).

[0568] Output: A file of the generated production plan

[0569] Specifically, the generated plan is converted into a PDF file and sent to the user's device by email.

[0570] Step 6:

[0571] The terminal receives and displays the optimum plan distributed from the server.

[0572] Input: Production plan file sent from the server

[0573] Data processing: Converts data into a format suitable for display in a PDF viewer or app.

[0574] Output: Displayed production plan

[0575] Specifically, a new apple farmer opens the PDF plan he or she received and checks information such as "fertilize in March and July" and "spray pesticides in May and July."

[0576] Step 7:

[0577] The user puts the proposed optimal plan into practice and provides feedback on the results.

[0578] Input: Results of implementing the production plan (e.g., yield, quality, information on pests and diseases that have occurred)

[0579] Data processing: Enter feedback information through online forms or apps.

[0580] Output: Formatted feedback data

[0581] Specifically, the user enters information such as "harvest yield after fertilization: 800 kg" and "pests and diseases encountered: aphids" into an online form and submits it.

[0582] Step 8:

[0583] The server stores the feedback information in a database and uses it for re-learning.

[0584] Input: Formatted feedback data

[0585] Data processing: Save the data in a feedback table in the database and perform preprocessing again. Impute missing values ​​and remove outliers.

[0586] Output: Preprocessed feedback data

[0587] Specifically, the feedback data is stored in a database, and a clean dataset is prepared again using Python and Pandas.

[0588] Step 9:

[0589] The server uses the pre-processed feedback data to retrain the AI ​​technology model.

[0590] Input: Preprocessed feedback data

[0591] Data calculation: Feedback data is input into the AI ​​technology model, and the model parameters are readjusted to perform re-learning.

[0592] Output: AI technology model with improved accuracy

[0593] Specifically, the feedback data is re-input into the TensorFlow model, allowing it to learn and generate a new optimal plan.

[0594] (Application example 1)

[0595] 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."

[0596] Generally, farmers produce fruit based on their experience and knowledge, but their methods are largely dependent on the skills and knowledge of each individual farmer and are not standardized. This often results in inconsistent yields and quality, which in turn reduces the efficiency of agricultural production and potentially leads to unstable profits. Finding appropriate measures to quickly respond to changes in environmental conditions and climate is particularly challenging, and another contributing factor is the lack of automation in the production process. A system that can resolve these issues and improve the efficiency and quality of fruit production is needed.

[0597] 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.

[0598] In this invention, the server includes: means for collecting production information from experienced farmers; means for saving the collected production information in a database; means for preprocessing the saved production information and inputting it into an AI model; means for analyzing using the AI ​​model; means for generating an optimal plan for fruit production based on the analysis results; means for applying the generated optimal plan to production equipment; means for managing fertilization and pruning performed by the production equipment according to a schedule; means for the production equipment to automatically perform fertilization, pruning, and pest control; means for distributing the generated optimal plan to users; means for collecting feedback from users; and means for saving the collected feedback in a database and retraining the AI ​​model. This enables standardization and optimization of agricultural production, uniform harvest yields and quality, and labor-saving and cost reduction through automation.

[0599] "Agricultural workers" refers to people who work professionally in agriculture and have the skills and knowledge to produce crops such as fruits and vegetables.

[0600] "Production information" refers to various types of information that farmers use when producing fruits and crops, including soil type, climatic conditions, timing of fertilization, pruning methods, and pest and disease control measures.

[0601] A "database" is a high-performance storage system that stores collected production information and feedback information in a structured manner so that it can be accessed quickly and easily later.

[0602] "Preprocessing" refers to the processing carried out before collected production information is input into the AI ​​model, and specifically includes data normalization, missing value completion, and outlier detection and removal.

[0603] An "AI model" is a model that uses artificial intelligence technologies such as machine learning and deep learning, and is used to analyze production information and generate optimal fruit production plans.

[0604] The "analysis results" are data and information obtained through analytical processing using an AI model, and are used to derive optimal fruit production plans.

[0605] The "optimal plan" is an execution plan for fruit production generated based on the analysis results of the AI ​​model, and includes recommended cultivation methods, fertilization timing, and pest and disease prevention measures.

[0606] "Production equipment" refers to mechanical devices used to automate various tasks in fruit production, specifically robots and machines that perform fertilization, pruning, and pest control.

[0607] "Feedback" refers to the results of the user's implementation of the proposed optimal plan and the information obtained in the process, including harvest volume, quality, and any problems that arise.

[0608] "Retraining" is the process of retraining an AI model using collected feedback information to improve the accuracy of its suggestions.

[0609] As an embodiment of the present invention, a specific description will be given of how the elements of the server, terminal, and user work together.

[0610] 1. Data Collection

[0611] The server first collects production information from farmers, including soil type, weather conditions, fertilization timing, pruning methods, pest control measures, etc. Data can be collected via an online form or API.

[0612] 2. Data storage

[0613] The server stores the collected production information in a database, which uses a high-performance storage system for efficient management of structured data, allowing this data to be accessed quickly and easily later.

[0614] 3. Data Preprocessing

[0615] The server preprocesses the stored data, which includes normalizing the data, imputing missing values, and removing outliers. The preprocessed data is then input into machine learning and deep learning AI models.

[0616] 4. Analysis using AI models

[0617] The server inputs the preprocessed data into an AI model for analysis. The AI ​​model is built using machine learning frameworks such as TensorFlow and Keras. The analysis results generate an optimal fruit production plan.

[0618] 5. Generating and Applying the Optimal Plan

[0619] The server generates a specific production plan based on the analysis results. This plan includes recommended cultivation techniques, fertilization timing, and pest control measures. The server then applies this optimal plan to production equipment. Production equipment is automated machinery such as robots that perform fertilization, pruning, and pest control.

[0620] 6. Plan Management and Execution

[0621] The production equipment manages and executes fertilization and pruning according to a schedule based on the optimal plan received from the server, significantly reducing the amount of manual management work required.

[0622] 7. Delivery of the Plan

[0623] The server then delivers the generated optimal plan to the user's device, and the user performs the task while referring to the plan displayed on the smart glasses or robot.

[0624] 8. Gathering Feedback

[0625] Users provide feedback to the server on the results of their practice and information gained during the process, including yield, quality, and any problems encountered.

[0626] 9. Relearn

[0627] The server stores the collected feedback data in a database and retrains the AI ​​model, allowing the accuracy of the suggestions to continue to improve.

[0628] Specific examples

[0629] For example, an AI model analyzes data collected from apple farmers and generates an optimal fertilization schedule. This plan is then executed by production equipment, and information on yield and quality is sent back to the server as feedback. The AI ​​model re-learns based on the collected feedback data, and a new optimal plan is generated.

[0630] Prompt Sentence Examples

[0631] "Task: Analyze data collected from farmers and generate an optimal fruit production plan. Data collected includes soil type, weather conditions, fertilization timing, pruning methods, and pest and disease control."

[0632] In this way, this invention will enable the standardization and optimization of agricultural production processes, leading to labor savings through automation and improved yields and quality.

[0633] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0634] Step 1:

[0635] Data collection

[0636] The server collects production information from farmers using online forms and APIs, including information on soil type, climate conditions, fertilization timing, pruning methods, and pest and disease control. The input is various production information provided by farmers, and the output is structured data of this information. The server converts this information into an appropriate format and stores it in a database.

[0637] Step 2:

[0638] Data storage

[0639] The server stores the production information collected in step 1 in a database. The input is structured production information data, and the output is production information data stored in a database. A database management system (e.g., PostgreSQL) is used to store data quickly and efficiently.

[0640] Step 3:

[0641] Data Preprocessing

[0642] The server performs preprocessing on the stored production information before inputting it into the AI ​​model. Specifically, it normalizes the data, fills in missing values, and detects and removes outliers. The input is the production information data stored in the database, and the output is the preprocessed data. This preprocessing is performed using the Python Pandas library.

[0643] Step 4:

[0644] Analysis using AI models

[0645] The server inputs the preprocessed data into an AI model for analysis. Specifically, it uses machine learning and deep learning algorithms to generate an optimal fruit production plan. The input is the preprocessed data, and the output is the analysis results from the AI ​​model. Machine learning frameworks such as TensorFlow and Keras are used.

[0646] Step 5:

[0647] Generating an optimal plan

[0648] Based on the analysis results of the AI ​​model, the server generates an optimal fruit production plan for the production equipment (factory robots) to execute. The input is the analysis results, and the output is an optimal plan that includes specific fertilization timing, pruning methods, pest control measures, etc.

[0649] Step 6:

[0650] Applying and Managing Plans

[0651] The production equipment receives the generated optimal plan and manages fertilization and pruning according to the schedule. This includes setting the timing for fertilization and pruning and performing the actual work. The input is the optimal plan, and the output is the execution schedule and the specific fertilization and pruning actions.

[0652] Step 7:

[0653] Execution and automation

[0654] The production equipment automatically carries out fertilization, pruning, and pest control based on an optimal plan. The input is the execution schedule, and the output is the results of fertilization and pruning.

[0655] Step 8:

[0656] Plan Delivery

[0657] The server delivers the generated optimal plan to the user's device. The user performs the task while referring to the plan displayed on the smart glasses or robot. The input is the optimal plan, and the output is the plan displayed on the user's device.

[0658] Step 9:

[0659] Feedback collection

[0660] The user provides the server with the results of implementing the proposed optimal plan and information obtained during the process, including harvest volume, quality, and any problems that occurred. The input is the implementation results and information obtained during the process, and the output is feedback data.

[0661] Step 10:

[0662] Relearn

[0663] The server stores the collected feedback data in a database and retrains the AI ​​model, which continuously improves the accuracy of the suggestions. The input is the feedback data, and the output is the retrained AI model.

[0664] 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.

[0665] This invention improves the user experience by combining a system that collects production information from experienced farmers and proposes optimal fruit production plans based on that information with an emotion engine that recognizes the user's emotions. The program processing of this system is explained in detail below.

[0666] Data collection and storage

[0667] server

[0668] The server first collects production information from farmers. This information includes soil type, climate conditions, fertilization timing, pruning methods, and pest and disease prevention measures. This information can be received through online forms or APIs. For example, data is obtained from an apple farmer that includes fertilization schedules and details of the fertilizers used. The server then stores the collected production information in a database.

[0669] Data preprocessing and analysis

[0670] server

[0671] The stored data is preprocessed before being input into the AI ​​model. Preprocessing includes data normalization, missing value completion, and outlier detection and removal. The preprocessed data is then analyzed by the AI ​​model to learn optimal fruit production methods. For example, in apple production, the model learns the relationship between climatic conditions and yield, and determines the optimal fertilization schedule and pruning method.

[0672] Generating and delivering optimal plans

[0673] server

[0674] Based on the analysis results, the server generates an optimal plan for specific fruit production, including recommended cultivation techniques, fertilization timing, and pest control measures. The generated plan is then sent from the server to the user's device.

[0675] Terminal

[0676] The user's terminal receives and displays the optimal plan sent from the server. The user then carries out fruit production based on this plan. For example, a new apple farmer may start growing apples while referring to the received plan.

[0677] Gathering feedback and relearning

[0678] User

[0679] The user provides the server with feedback on the results of implementing the proposed optimal plan and the information obtained during the process, including the yield, quality, and any problems encountered.

[0680] server

[0681] The server collects user feedback and stores it in a database. Furthermore, the collected feedback data is used to retrain the AI ​​model, improving the accuracy of its suggestions. For example, new pest control measures are learned based on feedback from apple farmers.

[0682] Introducing the Emotion Engine

[0683] Server and Device

[0684] The server is equipped with an emotion engine that recognizes the user's emotions. The emotion engine analyzes the user's emotional state when entering feedback and uses that information to further refine the optimal plan. For example, if the user is facing a difficult situation, the engine can provide more detailed support information.

[0685] Terminal

[0686] The device uses an emotion engine to monitor the user's emotions in real time during interactions, and if the user feels stressed, it will provide encouraging messages or additional support to keep the user motivated.

[0687] Specific examples

[0688] For example, let's say an apple farmer starts cultivating based on a proposed plan, but is having trouble with pests and diseases. When the user provides feedback about this, the emotion engine recognizes the user's anxiety and immediately provides specific countermeasures and contact information for experts. This allows the user to take measures with peace of mind.

[0689] This system allows farmers to receive the latest know-how as well as emotional support when needed, enabling them to produce high-quality fruit consistently. The introduction of the emotion engine allows users to use the service with peace of mind, which is expected to lead to more effective production.

[0690] The processing flow will be explained below.

[0691] Program processing steps

[0692] Step 1:

[0693] The server collects production information from farmers through online forms and APIs, such as soil type, climate conditions, fertilization timing, pruning methods, pest control measures, etc. For example, it collects fertilization schedules and details of the fertilizers used from apple farmers.

[0694] Step 2:

[0695] The server stores the collected production information in a database, which structures and organizes the collected information so that it can be accessed quickly and efficiently for subsequent processing.

[0696] Step 3:

[0697] The server performs preprocessing of the production information stored in the database. Preprocessing includes data normalization, missing value completion, and outlier detection and removal. For example, missing values ​​are completed with the average value, and outliers are detected and removed.

[0698] Step 4:

[0699] The server inputs the preprocessed data into an AI model for analysis. The AI ​​model uses machine learning algorithms to learn patterns and rules from the data. For example, it can learn the optimal fertilization schedule for apple production.

[0700] Step 5:

[0701] Based on the results of the AI ​​model's analysis, the server generates a specific optimal plan for fruit production, including recommended cultivation methods, fertilization timing, and pest control measures.

[0702] Step 6:

[0703] The server then delivers the generated optimal plan to the user's device. By providing an optimal plan tailored to each user's conditions, the user can receive individually customized advice.

[0704] Step 7:

[0705] The terminal receives the optimal plan delivered from the server and displays it to the user. The user then carries out fruit production based on the displayed plan. For example, a new apple farmer starts cultivating fruit according to the delivered plan.

[0706] Step 8:

[0707] The device uses an emotion engine to monitor the user's emotions in real time, and if the user is feeling stressed, it will provide encouraging messages or additional support.

[0708] Step 9:

[0709] The user provides feedback to the server via their device about the results of implementing the proposed optimal plan and the emotions they felt during the process, including the yield, quality, problems encountered, and emotional state.

[0710] Step 10:

[0711] The server collects and stores feedback from users in a database, including the user's emotional state as analyzed by the emotion engine.

[0712] Step 11:

[0713] The server uses the collected feedback data and emotional information to retrain the AI ​​model, improving the accuracy of recommendations and the user experience, and enhancing the quality of the optimal plan provided from the next time onwards.

[0714] Through this series of processing steps, the fruit generation suggestion system can provide farmers with high-quality and reliable information, improving the efficiency of fruit production and the user experience. The introduction of the emotion engine creates an environment where users can use the service with peace of mind, and more effective production can be expected.

[0715] Example 2

[0716] 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."

[0717] Conventional agricultural production systems often propose incomplete production plans based solely on the experience and knowledge of farmers, and have the problem of not providing adequate proposals that are optimized for specific conditions or regions. Furthermore, because support does not take into account the emotional state of users, there is also the issue of being unable to respond appropriately when faced with difficult situations.

[0718] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for collecting production information from experienced farmers, means for saving the collected production information in a database, means for preprocessing the saved production information and inputting it into an analysis device, means for performing analysis using the analysis device, means for generating an optimal crop production plan based on the analysis results, means for distributing the generated optimal plan to users, means for collecting feedback from users, means for saving the collected feedback in a database and retraining the analysis device, means for analyzing emotional states, means for improving the optimal plan based on emotional states, and means for monitoring the user's emotions in real time during crop production. This makes it possible to provide a production plan optimized for specific conditions and regions and to provide appropriate support according to the user's emotions.

[0719] An "agricultural worker" is a person with specialized knowledge and experience in crop production and management.

[0720] "Production information" refers to data related to crop production, including soil type, climatic conditions, timing of fertilization, pruning methods, and measures against pests and diseases.

[0721] A "database" is a system for efficiently storing, managing, and searching large amounts of data.

[0722] "Preprocessing" is the process of preparing data for analysis, and includes normalizing data, imputing missing values, and detecting and removing outliers.

[0723] An "analysis device" is a device that uses stored data to perform complex calculations and processing to derive optimal solutions, and generally refers to an AI model or machine learning model.

[0724] "Analysis" is the process of deriving specific results or patterns from input data.

[0725] A "crop production plan" is a detailed description of the crop production methods that are best suited to specific conditions and regions.

[0726] "User" refers to farmers and related persons who use this system to produce crops.

[0727] "Feedback" refers to the act of a user returning the results of using the system and the data obtained to the system.

[0728] "Emotional state" refers to the mental state or emotion that a user displays when entering feedback or while working.

[0729] The "emotion engine" is a system that analyzes the user's emotional state from their input data and behavior, and provides an appropriate response.

[0730] "Real-time monitoring" is the process of instantly monitoring the user's behavior and status on the spot and quickly providing analytical results.

[0731] This invention is a system that proposes optimal crop production plans based on production information from experienced farmers, and further improves the user experience by combining it with an emotion engine that recognizes the user's emotions. The program processing of this system is explained below.

[0732] Data collection and storage

[0733] server

[0734] The server first collects production information from farmers. This information includes soil type, climate conditions, fertilization timing, pruning methods, and pest and disease control measures. This information can be received through an online form or API. For example, data including fertilization schedules and details of the fertilizers used is obtained from an apple farmer. The collected production information is stored in a database. Databases used include MySQL and PostgreSQL.

[0735] Data preprocessing and analysis

[0736] server

[0737] The stored data is input into an AI model after undergoing preprocessing. Preprocessing includes data normalization, missing value completion, and outlier detection and removal. Data processing libraries such as NumPy and Pandas are used for preprocessing. The preprocessed data is then analyzed by an AI model using machine learning frameworks such as TensorFlow and PyTorch. For example, in apple production, the relationship between weather conditions and yield can be learned to determine the optimal fertilization schedule and pruning method.

[0738] Generating and delivering optimal plans

[0739] server

[0740] Based on the analysis results, the server generates an optimal plan for specific crop production, including recommended cultivation techniques, fertilization timing, and pest control measures. The generated plan is then sent from the server to the user's device.

[0741] Gathering feedback and relearning

[0742] User

[0743] The user provides the server with feedback on the results of implementing the proposed optimal plan and information obtained during the process, including the yield, quality, and any problems encountered.

[0744] server

[0745] The server collects user feedback and stores it in a database. Furthermore, the collected feedback data is used to retrain the AI ​​model, improving the accuracy of its suggestions. For example, new pest control measures are learned based on feedback from apple farmers.

[0746] Introducing the Emotion Engine

[0747] Server and Device

[0748] The server is equipped with an emotion engine that recognizes the user's emotions. The emotion engine analyzes the user's emotional state when entering feedback and uses that information to further refine the optimal plan. For example, if the user is facing a difficult situation, the engine can provide more detailed support information.

[0749] Terminal

[0750] The device uses an emotion engine to monitor the user's emotions in real time during interactions, and if the user feels stressed, it will provide encouraging messages or additional support to keep the user motivated.

[0751] Specific examples

[0752] For example, let's say an apple farmer starts cultivating based on a proposed plan, but is having trouble with pests and diseases. When the user provides feedback about this, the emotion engine recognizes the user's anxiety and immediately provides specific countermeasures and contact information for experts. This allows the user to take measures with peace of mind.

[0753] Prompt Sentence Examples

[0754] "I applied fertilizer in March and July, but I'm having trouble with insect damage. What can I do?"

[0755] This system allows farmers to receive the latest know-how as well as emotional support when needed, enabling them to produce high-quality crops consistently. The introduction of the emotion engine allows users to use the service with peace of mind, which is expected to lead to more effective production.

[0756] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0757] Step 1: Data collection

[0758] server

[0759] The server provides an online form to farmers. The form contains input fields such as soil type, climate conditions, fertilization timing, pruning methods, and pest and disease prevention measures. The server receives the form data sent by the farmer and also processes API requests to obtain production information from outside. The input data includes fertilization schedules and details of the fertilizers used, which the server saves in a database. Specifically, the apple farmer enters information such as "clay soil" and "fertilization schedule for March and July" into the online form and submits it.

[0760] Input: Production information obtained via online forms or API requests.

[0761] Output: Production information stored in a database.

[0762] Step 2: Preprocessing

[0763] server

[0764] The server retrieves the stored production information from the database and performs preprocessing. Preprocessing includes data normalization, missing value completion, and outlier detection and removal. NumPy and Pandas are used to normalize the data and generate standardized data. Specifically, the server converts the fertilization timing (March and July) into a standardized numerical format and completes missing values ​​in the climate data with the average of past data.

[0765] Input: Production information retrieved from the database.

[0766] Output: The preprocessed dataset.

[0767] Step 3: Model analysis

[0768] server

[0769] The server inputs the preprocessed data into an AI model. The model used is trained using TensorFlow and PyTorch. The AI ​​model analyzes the optimal production method based on the input data. Specifically, it learns the relationship between weather conditions and yield, and derives the optimal fertilization schedule and pruning method.

[0770] Input: Preprocessed data.

[0771] Output: Analysis of optimal crop production methods.

[0772] Step 4: Generate and distribute optimal plans

[0773] server

[0774] Based on the analysis results, the server generates a specific crop production plan. This plan includes recommended cultivation methods, fertilization timing, and pest control measures. The generated plan is delivered to the user's device in JSON format. As a specific operation, the server generates a recommended plan to "apply ammonium nitrate fertilizer in March and July."

[0775] Input: Analysis results of the AI ​​model.

[0776] Output: The generated optimal plan.

[0777] Terminal

[0778] The terminal receives the optimal plan sent from the server and displays it on the application. The user produces crops based on this plan. Specifically, a new apple farmer begins cultivation based on the received plan.

[0779] Input: The optimal plan delivered by the server.

[0780] Output: The plan displayed on the terminal.

[0781] Step 5: Gather feedback and retrain

[0782] User

[0783] Users provide feedback to the server on the results of their work and the information they have gained during the process, including the yield, quality, and any problems they may have encountered. For example, an apple farmer might input, "After applying fertilizer in March, insect damage occurred."

[0784] Input: User feedback.

[0785] Output: Data sent to the server.

[0786] server

[0787] The server stores the feedback in a database and retrains the AI ​​model, which improves the accuracy of its suggestions. Specifically, it retrains the TensorFlow model using the new data.

[0788] Input: Feedback data from users.

[0789] Output: The updated AI model.

[0790] Step 6: Implementing the Emotion Engine

[0791] Server and Device

[0792] The server uses an emotion engine to analyze the user's emotions when entering feedback. If the user is facing a difficult situation, the emotion engine will provide specific solutions and specialist consultation options. The device will monitor the user's emotions in real time and provide encouraging messages if the user is feeling stressed. For example, if the user enters "I'm very worried" in the feedback, the emotion engine will analyze this, determine it as "anxiety," and provide additional support.

[0793] Input: User feedback, emotion data.

[0794] Output: Supportive information and messages based on emotional state.

[0795] (Application example 2)

[0796] 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."

[0797] Modern factories are required to improve production efficiency and reduce employee stress, but optimizing production schedules and managing machine maintenance remain challenges. Providing an efficient work environment that takes into account employee emotions is also important, but existing systems do not adequately address this issue.

[0798] 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.

[0799] In this invention, the server includes means for collecting production information from experienced farmers, means for saving the collected production information in a database, means for preprocessing the saved production information and inputting it into an AI model, means for analyzing using the AI ​​model, means for generating an optimal plan for fruit production based on the analysis results, means for distributing the generated optimal plan to users, means for collecting feedback from users, means for saving the collected feedback in a database and retraining the AI ​​model, and means for recognizing the emotional state of users and improving the optimal plan based on the analysis results. This makes it possible to optimize production schedules and provide an efficient work environment that takes employee emotions into consideration.

[0800] "Agricultural workers" refers to people who are engaged in agricultural work, especially those who have specialized knowledge and experience and work on producing crops.

[0801] "Production information" refers to detailed data on crop production, such as soil type, climatic conditions, fertilization timing, pruning methods, and pest and disease control measures.

[0802] A "database" refers to a system that can efficiently store, manage, and access large amounts of data.

[0803] "Preprocessing" refers to processes such as normalizing data, filling in missing values, and detecting and removing outliers, which are carried out to make the input data to an AI model analyzable.

[0804] An "AI model" refers to a system that uses artificial intelligence algorithms and machine learning techniques to analyze data, learn patterns, and make predictions and decisions.

[0805] "Analysis" refers to the process of extracting specific information and insights from collected data.

[0806] An "optimal plan" is a plan that proposes the most suitable methods and schedules for agricultural production based on the analysis results of an AI model.

[0807] "Delivery" refers to the process of transmitting the generated optimal plan to the user's terminal and making it available for use.

[0808] "Feedback" refers to information provided by users based on their practical results and experiences.

[0809] "Retraining" refers to the process of using collected feedback to retrain an AI model, improving its accuracy and the precision of its recommendations.

[0810] "Emotional state" refers to a user's psychological state or feeling, which is identified through text analysis and an emotion engine.

[0811] "Improvement" refers to the process of making changes or additions to existing plans or systems to make them more effective and improve their accuracy and usability.

[0812] A "system" is a set of multiple interrelated components and processes that function to achieve a specific purpose.

[0813] The present invention relates to a smart factory management application for optimizing factory management. The program processing of this system will be specifically described below.

[0814] Data collection and storage

[0815] The server collects production information from production equipment and facilities within the factory. This production information includes various sensor data, machine operating status, maintenance schedules, etc. The collected information is saved in the server's database in real time.

[0816] Data preprocessing and analysis

[0817] The server preprocesses the collected production information. This preprocessing includes data normalization, missing value completion, and outlier detection and removal. The preprocessed data is then input into an AI model. An example of the AI ​​model used here is RandomForestRegressor. This model analyzes the production information and generates an optimal production schedule and efficiency improvement plan.

[0818] Generating and delivering optimal plans

[0819] The server generates an optimal production plan based on the analysis results of the AI ​​model. This plan includes machine operation schedules, maintenance timing, efficient resource allocation, etc. The generated optimal plan is then distributed from the server to the user's device.

[0820] The user's device receives the optimal plan and presents it to the factory's monitoring system and manager. The user then carries out production activities based on this plan.

[0821] Gathering feedback and relearning

[0822] The user implements the proposed optimal plan and provides the results and information obtained during the process as feedback to the server, including production efficiency, problems, and areas for improvement.

[0823] The server stores the collected feedback in a database and retrains the AI ​​model to improve the accuracy of future suggestions. Retraining involves tuning the AI ​​model using the feedback data.

[0824] Introducing the Emotion Engine

[0825] The server is equipped with an emotion engine that recognizes the user's emotional state. The emotion engine uses text and voice analysis to determine the user's emotions. Once the emotional state is recognized, the server uses that information to further refine the optimal plan. This refinement can provide encouraging messages or additional support information if the user is facing a difficult situation.

[0826] Specific examples

[0827] For example, if a factory experiences frequent equipment breakdowns and employees are feeling stressed, the information is sent to the server through user feedback. The emotion engine recognizes the employee's stress level from this feedback and immediately provides suggestions for improvement and encouraging messages.

[0828] Example prompt sentence:

[0829] Generate plans to optimize maintenance frequency on production lines and reduce equipment breakdowns, plus add support messages when employees' stress levels are high.

[0830] In this way, the system of the present invention makes it possible to optimize production schedules and provide an efficient working environment that takes into account the emotions of employees.

[0831] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0832] Step 1:

[0833] The server collects production information from production equipment and facilities within the factory. This includes data obtained from sensors, machine operation status, maintenance schedules, etc. Input data is sent to the server in real time via API or sensor devices. The output is the collected production information stored in a database.

[0834] Step 2:

[0835] The server preprocesses the collected production information. The input is data obtained from the production information database. Data normalization, missing value imputation, and outlier detection and removal are performed. For example, missing values ​​are imputed using pandas and SimpleImputer, and data is normalized using StandardScaler. The output is the preprocessed data.

[0836] Step 3:

[0837] The server inputs the preprocessed data into an AI model for analysis. The input is the preprocessed data, and the output is the analysis results. The AI ​​model used is, for example, RandomForestRegressor, and analyzes the data to generate production schedules and efficiency plans.

[0838] Step 4:

[0839] The server generates an optimal production plan based on the analysis results. The input is the analysis results from the AI ​​model. The output is the generated optimal production plan, which includes machine operation schedules, maintenance timing, and efficient resource allocation.

[0840] Step 5:

[0841] The server distributes the generated optimal plan to the user's terminal. The input is the generated optimal production plan. The output is the distributed production plan, which the user uses to carry out production activities. The terminal displays the received production plan on the factory's monitoring system and to the manager.

[0842] Step 6:

[0843] The user implements the proposed optimal plan. The input is the delivered optimal plan. The results of the implementation and information obtained during the process are provided as feedback. The output is the collected feedback information.

[0844] Step 7:

[0845] The server stores the collected feedback information in a database and retrains the AI ​​model. The input is the feedback information. Retraining uses the feedback to tune the AI ​​model and improve the accuracy of its suggestions. The output is the retrained AI model.

[0846] Step 8:

[0847] The server analyzes the emotion from the feedback using an emotion engine that recognizes the user's emotional state. The input is the feedback text or voice data. The emotion engine performs text analysis to determine the user's emotion. The output is the recognized emotional state.

[0848] Step 9:

[0849] The server refines the optimal plan based on the recognized emotional state. The input is the emotional state recognized by the emotion engine and the existing optimal plan. For example, if the user is feeling stressed, it provides an encouraging message or additional support information. The output is the refined optimal plan.

[0850] Through the above processing steps, this system optimizes production schedules and provides an efficient working environment that takes into account the emotions of employees.

[0851] 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.

[0852] 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.

[0853] 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.

[0854] [Third embodiment]

[0855] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0856] 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.

[0857] 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).

[0858] 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.

[0859] 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.

[0860] 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).

[0861] 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.

[0862] 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.

[0863] 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.

[0864] 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.

[0865] 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.

[0866] 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."

[0867] The present invention provides a system that collects production information from experienced farmers and proposes an optimal fruit production plan based on that information. The program processing of this system will be specifically described below.

[0868] Data collection

[0869] server

[0870] The server first collects production information from farmers, including soil type, climate conditions, fertilization timing, pruning methods, and pest and disease control measures. This information can be received through online forms or APIs. For example, the server obtains data from an apple farmer that includes the fertilization schedule and details of the fertilizers used.

[0871] Data storage

[0872] server

[0873] The server stores the collected production information in a database, which uses a high-performance storage system to structure and store the various crops and their associated production information, allowing for quick and easy access later.

[0874] Data preprocessing and analysis

[0875] server

[0876] The stored data is preprocessed before being input into the AI ​​model. Preprocessing includes data normalization, missing value completion, and outlier detection and removal. The preprocessed data is then analyzed by the AI ​​model to learn optimal fruit production methods. For example, in apple production, the model learns the relationship between climatic conditions and yield, and determines the optimal fertilization schedule and pruning method.

[0877] Generating and delivering optimal plans

[0878] server

[0879] Based on the analysis results, the server generates an optimal plan for specific fruit production, including recommended cultivation techniques, fertilization timing, and pest control measures. The generated plan is then sent from the server to the user's device.

[0880] Terminal

[0881] The user's terminal receives and displays the optimal plan sent from the server. The user then carries out fruit production based on this plan. For example, a new apple farmer may start growing apples while referring to the received plan.

[0882] Gathering feedback and relearning

[0883] User

[0884] The user provides the server with feedback on the results of implementing the proposed optimal plan and the information obtained during the process, including the yield, quality, and any problems encountered.

[0885] server

[0886] The server collects user feedback and stores it in a database. Furthermore, the collected feedback data is used to retrain the AI ​​model, improving the accuracy of its suggestions. For example, new pest control measures are learned based on feedback from apple farmers.

[0887] By operating this system, farmers can always obtain the latest know-how, enabling them to produce delicious fruit consistently. This cycle of continuous feedback and relearning keeps improving the quality of the suggestions, allowing farmers to work on fruit production with peace of mind.

[0888] The processing flow will be explained below.

[0889] Program processing steps

[0890] Step 1:

[0891] The server collects production information from farmers, such as soil type, weather conditions, fertilization timing, pruning methods, and pest and disease control measures, via online forms and APIs.

[0892] Step 2:

[0893] The server stores the collected production information in a database, which is used to structure and organize the collected information, allowing it to be efficiently retrieved for subsequent processing.

[0894] Step 3:

[0895] The server preprocesses the production information stored in the database. This preprocessing includes normalizing the data, filling in missing values, and detecting and removing outliers. This prepares the data to improve the accuracy of analysis.

[0896] Step 4:

[0897] The server then inputs the preprocessed data into an AI model, which then analyzes the data. The AI ​​model then uses machine learning algorithms to learn patterns and rules from the data, such as the optimal fertilization schedule for a given climate.

[0898] Step 5:

[0899] Based on the analysis results of the AI ​​model, the server generates a specific optimal plan for fruit production, including recommended cultivation methods, fertilization timing, and pest control measures.

[0900] Step 6:

[0901] The server then delivers the generated optimal plan to the user's device. By providing an optimal plan tailored to each user's conditions, the user can receive individually customized advice.

[0902] Step 7:

[0903] The terminal receives the optimal plan delivered from the server and displays it to the user. The user then carries out fruit production based on the displayed plan. For example, a farmer who is starting fruit production for the first time may start cultivation according to the delivered plan.

[0904] Step 8:

[0905] The user provides feedback to the server via their terminal about the results and information gained during the process of implementing the proposed optimal plan, including information on harvest volume, quality, and any problems encountered.

[0906] Step 9:

[0907] The server collects user feedback and stores it in a database. The feedback data is used in the next re-learning step.

[0908] Step 10:

[0909] The server uses the collected feedback data to retrain the AI ​​model, improving the model's prediction accuracy and proposal content, and increasing the quality of the optimal plan provided from the next time onwards.

[0910] Through this series of processing steps, the fruit generation suggestion system can provide farmers with high-quality and reliable information, thereby improving the efficiency of fruit production.

[0911] Example 1

[0912] 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."

[0913] Conventional fruit production systems have the problem of being unable to provide optimal production plans based on local conditions and the experience of individual farmers. Furthermore, they lack the re-learning functionality to effectively utilize collected production information and adapt to the constantly evolving agricultural environment. These issues make it difficult to achieve efficient and stable fruit production.

[0914] 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.

[0915] In this invention, the server includes a means for collecting production information from experienced farmers, a means for storing the collected production information in a database, and a means for preprocessing the stored production information and inputting it into an AI technology model. This enables the generation of an optimal fruit production plan based on the collected information. The server further includes a means for analysis using the AI ​​technology model and a means for generating an optimal agricultural production plan based on the analysis results. This enables the provision of an optimal production plan based on the latest technology. The server also includes a means for collecting feedback from users, storing the collected feedback in a database, and retraining the AI ​​technology model. This enables continuous system improvement based on the collected feedback data.

[0916] "Agricultural worker" means a person who is engaged in agriculture and has knowledge and experience related to fruit production.

[0917] "Production information" refers to various data related to fruit production, such as soil type, climatic conditions, timing of fertilization, pruning methods, and measures against pests and diseases.

[0918] A "database" is an information system that systematically stores collected production information and feedback, allowing it to be searched, managed, and used.

[0919] "Preprocessing" refers to processing such as normalizing data, filling in missing values, and removing outliers before inputting collected production information into an AI technology model.

[0920] An "AI technology model" is an algorithm and calculation system that uses artificial intelligence technology to analyze data and generate optimal production plans and forecasts.

[0921] "Analysis" refers to analyzing pre-processed data using an AI technology model and extracting optimal production plans, including recommended cultivation methods, fertilization timing, and pest and disease control measures.

[0922] A "production plan" is a document that includes specific methods and procedures recommended for achieving efficient and stable fruit production.

[0923] "User" refers to a farmer who uses the system to receive a fruit production plan.

[0924] "Feedback" refers to returning the results of the production plan and data obtained during the process to the system, and includes information on harvest volume, quality, and any problems that arise.

[0925] "Relearning" refers to the retraining of AI technology models using collected feedback data, a process aimed at improving analytical accuracy and continuous improvement of the system.

[0926] MODE FOR CARRYING OUT THE INVENTION

[0927] The present invention relates to a system that collects production information from experienced farmers and proposes an optimal fruit production plan based on that information. A specific embodiment for implementing this system will be described below.

[0928] Data collection

[0929] The server first collects production information from farmers. This information includes soil type, climate conditions, fertilization timing, pruning methods, and pest and disease prevention measures. The information can be collected via an online form using a web page or mobile application, or via an API endpoint. For example, an apple farmer can enter information such as "soil type: clay" and "climatic conditions: average temperature 15°C" into an online form and submit it.

[0930] Data storage

[0931] The server stores production information received through online forms and APIs in a database. Relational databases such as MySQL and PostgreSQL are suitable for this purpose. The received data is validated according to a specified format and then saved in the database.

[0932] Data preprocessing and analysis

[0933] The stored data is preprocessed by the server and input into an AI technology model. Preprocessing involves normalizing the data, filling in missing values, and removing outliers using Python scripts and the Pandas library. The preprocessed data is then analyzed by an AI technology model built using TensorFlow or PyTorch. This analysis allows the system to learn optimal fertilization timing and pruning methods based on weather conditions and production data.

[0934] Generating and delivering optimal plans

[0935] The server generates a specific optimal plan for fruit production based on the analysis results of the AI ​​technology model. This plan includes details such as recommended cultivation methods, fertilization timing, and pest control measures. The generated plan is converted into a format such as PDF or JSON and sent to the terminal. The terminal receives the optimal plan sent from the server and displays it to the user. For example, a new apple farmer may start growing apples by referring to the plan sent from the server.

[0936] Gathering feedback and relearning

[0937] The user puts the proposed optimal plan into practice and provides the results and information on the process as feedback to the server. For example, information on the yield after fertilization or the occurrence of pests and diseases is provided as feedback. The server stores the collected feedback in a database and preprocesses it again. The preprocessed feedback data is used to retrain the AI ​​technology model, improving the accuracy of the next proposal. This continuous cycle of feedback and re-learning ensures that the latest know-how is always reflected in the system.

[0938] Examples of specific examples and prompts

[0939] For example, the following data is collected from apple farmers in Nagano Prefecture:

[0940] Soil type: clay

[0941] Climate: Average temperature 15°C, annual precipitation 900mm

[0942] Fertilization timing: April and August

[0943] Fertilizer used: Nitrogen fertilizer 100kg / ha

[0944] Pruning method: Prune branches in half in February

[0945] Pest control: Pesticide spraying in June

[0946] Based on this data, the AI ​​technology model generates an optimal fruit production plan and suggests the following plan for new farmers:

[0947] Fertilization timing: Changed to March and July

[0948] Fertilizer used: Nitrogen fertilizer 120 kg / ha

[0949] Pruning method: Light pruning in March

[0950] Pest control: Pesticide spraying in May and July

[0951] Prompt Sentence Examples

[0952] "Please suggest the optimal fertilization schedule and pruning method based on data from apple farmers in Nagano Prefecture. The collected data includes soil type, climatic conditions, fertilization timing and fertilizer use, pruning methods, and pest and disease control measures."

[0953] By operating this system, farmers can always access the latest know-how and produce delicious fruit consistently. The continuous feedback and relearning cycle keeps improving the quality of the suggestions, so farmers can work on fruit production with peace of mind.

[0954] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0955] Step 1:

[0956] The server collects production information from farmers through online forms and APIs.

[0957] Input: Production information provided by farmers (e.g., soil type, climatic conditions, fertilization timing, pruning methods, pest and disease control measures)

[0958] Data processing: Organize the information entered in the online form in JSON format.

[0959] Output: Production information in formatted JSON format

[0960] Specifically, the system works by providing a form on a web page or mobile app where apple farmers can enter data such as "soil type: clay" and "climatic conditions: average temperature 15 degrees" and then submit it.

[0961] Step 2:

[0962] The server stores the received production information in a database.

[0963] Input: Production information in formatted JSON

[0964] Data processing: Generates SQL insert statements to save data to a specified table in the database.

[0965] Output: Production information stored in a database

[0966] Specifically, data is inserted into tables such as "soil information" and "climate information" using MySQL or PostgreSQL.

[0967] Step 3:

[0968] The server pre-processes the stored production information.

[0969] Input: Production information extracted from the database

[0970] Data processing: Using Python scripts and the Pandas library, we normalize the data, impute missing values, and remove outliers.

[0971] Output: A preprocessed, clean dataset

[0972] Specifically, the extracted data is loaded into a Pandas data frame, missing values ​​are filled with the average value, and outlying values ​​are removed.

[0973] Step 4:

[0974] The server inputs the preprocessed data into an AI technology model for analysis.

[0975] Input: Preprocessed clean dataset

[0976] Data calculation: Data is input into a trained AI technology model using TensorFlow or PyTorch to predict the optimal production plan.

[0977] Output: Optimal production plan (e.g., fertilization timing, pruning method, pest control)

[0978] Specifically, the preprocessed data is input into a TensorFlow model, and a recommended plan such as "Fertilization timing: March and July" and "Pruning method: Light pruning in March" is output.

[0979] Step 5:

[0980] The server generates a production plan based on the analysis results and distributes it to the terminal.

[0981] Input: Analysis results from AI technology model

[0982] Data processing: Convert the analysis results into a format that is easy for users to understand (such as PDF or JSON).

[0983] Output: A file of the generated production plan

[0984] Specifically, the generated plan is converted into a PDF file and sent to the user's device by email.

[0985] Step 6:

[0986] The terminal receives and displays the optimum plan distributed from the server.

[0987] Input: Production plan file sent from the server

[0988] Data processing: Converts data into a format suitable for display in a PDF viewer or app.

[0989] Output: Displayed production plan

[0990] Specifically, a new apple farmer opens the PDF plan he or she received and checks information such as "fertilize in March and July" and "spray pesticides in May and July."

[0991] Step 7:

[0992] The user puts the proposed optimal plan into practice and provides feedback on the results.

[0993] Input: Results of implementing the production plan (e.g., yield, quality, information on pests and diseases that have occurred)

[0994] Data processing: Enter feedback information through online forms or apps.

[0995] Output: Formatted feedback data

[0996] Specifically, the user enters information such as "harvest yield after fertilization: 800 kg" and "pests and diseases encountered: aphids" into an online form and submits it.

[0997] Step 8:

[0998] The server stores the feedback information in a database and uses it for re-learning.

[0999] Input: Formatted feedback data

[1000] Data processing: Save the data in a feedback table in the database and perform preprocessing again. Impute missing values ​​and remove outliers.

[1001] Output: Preprocessed feedback data

[1002] Specifically, the feedback data is stored in a database, and a clean dataset is prepared again using Python and Pandas.

[1003] Step 9:

[1004] The server uses the pre-processed feedback data to retrain the AI ​​technology model.

[1005] Input: Preprocessed feedback data

[1006] Data calculation: Feedback data is input into the AI ​​technology model, and the model parameters are readjusted to perform re-learning.

[1007] Output: AI technology model with improved accuracy

[1008] Specifically, the feedback data is re-input into the TensorFlow model, allowing it to learn and generate a new optimal plan.

[1009] (Application example 1)

[1010] 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."

[1011] Generally, farmers produce fruit based on their experience and knowledge, but their methods are largely dependent on the skills and knowledge of each individual farmer and are not standardized. This often results in inconsistent yields and quality, which in turn reduces the efficiency of agricultural production and potentially leads to unstable profits. Finding appropriate measures to quickly respond to changes in environmental conditions and climate is particularly challenging, and another contributing factor is the lack of automation in the production process. A system that can resolve these issues and improve the efficiency and quality of fruit production is needed.

[1012] 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.

[1013] In this invention, the server includes: means for collecting production information from experienced farmers; means for saving the collected production information in a database; means for preprocessing the saved production information and inputting it into an AI model; means for analyzing using the AI ​​model; means for generating an optimal plan for fruit production based on the analysis results; means for applying the generated optimal plan to production equipment; means for managing fertilization and pruning performed by the production equipment according to a schedule; means for the production equipment to automatically perform fertilization, pruning, and pest control; means for distributing the generated optimal plan to users; means for collecting feedback from users; and means for saving the collected feedback in a database and retraining the AI ​​model. This enables standardization and optimization of agricultural production, uniform harvest yields and quality, and labor-saving and cost reduction through automation.

[1014] "Agricultural workers" refers to people who work professionally in agriculture and have the skills and knowledge to produce crops such as fruits and vegetables.

[1015] "Production information" refers to various types of information that farmers use when producing fruits and crops, including soil type, climatic conditions, timing of fertilization, pruning methods, and pest and disease control measures.

[1016] A "database" is a high-performance storage system that stores collected production information and feedback information in a structured manner so that it can be accessed quickly and easily later.

[1017] "Preprocessing" refers to the processing carried out before collected production information is input into the AI ​​model, and specifically includes data normalization, missing value completion, and outlier detection and removal.

[1018] An "AI model" is a model that uses artificial intelligence technologies such as machine learning and deep learning, and is used to analyze production information and generate optimal fruit production plans.

[1019] The "analysis results" are data and information obtained through analytical processing using an AI model, and are used to derive optimal fruit production plans.

[1020] The "optimal plan" is an execution plan for fruit production generated based on the analysis results of the AI ​​model, and includes recommended cultivation methods, fertilization timing, and pest and disease prevention measures.

[1021] "Production equipment" refers to mechanical devices used to automate various tasks in fruit production, specifically robots and machines that perform fertilization, pruning, and pest control.

[1022] "Feedback" refers to the results of the user's implementation of the proposed optimal plan and the information obtained in the process, including harvest volume, quality, and any problems that arise.

[1023] "Retraining" is the process of retraining an AI model using collected feedback information to improve the accuracy of its suggestions.

[1024] As an embodiment of the present invention, a specific description will be given of how the elements of the server, terminal, and user work together.

[1025] 1. Data Collection

[1026] The server first collects production information from farmers, including soil type, weather conditions, fertilization timing, pruning methods, pest control measures, etc. Data can be collected via an online form or API.

[1027] 2. Data storage

[1028] The server stores the collected production information in a database, which uses a high-performance storage system for efficient management of structured data, allowing this data to be accessed quickly and easily later.

[1029] 3. Data Preprocessing

[1030] The server preprocesses the stored data, which includes normalizing the data, imputing missing values, and removing outliers. The preprocessed data is then input into machine learning and deep learning AI models.

[1031] 4. Analysis using AI models

[1032] The server inputs the preprocessed data into an AI model for analysis. The AI ​​model is built using machine learning frameworks such as TensorFlow and Keras. The analysis results generate an optimal fruit production plan.

[1033] 5. Generating and Applying the Optimal Plan

[1034] The server generates a specific production plan based on the analysis results. This plan includes recommended cultivation techniques, fertilization timing, and pest control measures. The server then applies this optimal plan to production equipment. Production equipment is automated machinery such as robots that perform fertilization, pruning, and pest control.

[1035] 6. Plan Management and Execution

[1036] The production equipment manages and executes fertilization and pruning according to a schedule based on the optimal plan received from the server, significantly reducing the amount of manual management work required.

[1037] 7. Delivery of the Plan

[1038] The server then delivers the generated optimal plan to the user's device, and the user performs the task while referring to the plan displayed on the smart glasses or robot.

[1039] 8. Gathering Feedback

[1040] Users provide feedback to the server on the results of their practice and information gained during the process, including yield, quality, and any problems encountered.

[1041] 9. Relearn

[1042] The server stores the collected feedback data in a database and retrains the AI ​​model, allowing the accuracy of the suggestions to continue to improve.

[1043] Specific examples

[1044] For example, an AI model analyzes data collected from apple farmers and generates an optimal fertilization schedule. This plan is then executed by production equipment, and information on yield and quality is sent back to the server as feedback. The AI ​​model re-learns based on the collected feedback data, and a new optimal plan is generated.

[1045] Prompt Sentence Examples

[1046] "Task: Analyze data collected from farmers and generate an optimal fruit production plan. Data collected includes soil type, weather conditions, fertilization timing, pruning methods, and pest and disease control."

[1047] In this way, this invention will enable the standardization and optimization of agricultural production processes, leading to labor savings through automation and improved yields and quality.

[1048] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1049] Step 1:

[1050] Data collection

[1051] The server collects production information from farmers using online forms and APIs, including information on soil type, climate conditions, fertilization timing, pruning methods, and pest and disease control. The input is various production information provided by farmers, and the output is structured data of this information. The server converts this information into an appropriate format and stores it in a database.

[1052] Step 2:

[1053] Data storage

[1054] The server stores the production information collected in step 1 in a database. The input is structured production information data, and the output is production information data stored in a database. A database management system (e.g., PostgreSQL) is used to store data quickly and efficiently.

[1055] Step 3:

[1056] Data Preprocessing

[1057] The server performs preprocessing on the stored production information before inputting it into the AI ​​model. Specifically, it normalizes the data, fills in missing values, and detects and removes outliers. The input is the production information data stored in the database, and the output is the preprocessed data. This preprocessing is performed using the Python Pandas library.

[1058] Step 4:

[1059] Analysis using AI models

[1060] The server inputs the preprocessed data into an AI model for analysis. Specifically, it uses machine learning and deep learning algorithms to generate an optimal fruit production plan. The input is the preprocessed data, and the output is the analysis results from the AI ​​model. Machine learning frameworks such as TensorFlow and Keras are used.

[1061] Step 5:

[1062] Generating an optimal plan

[1063] Based on the analysis results of the AI ​​model, the server generates an optimal fruit production plan for the production equipment (factory robots) to execute. The input is the analysis results, and the output is an optimal plan that includes specific fertilization timing, pruning methods, pest control measures, etc.

[1064] Step 6:

[1065] Applying and Managing Plans

[1066] The production equipment receives the generated optimal plan and manages fertilization and pruning according to the schedule. This includes setting the timing for fertilization and pruning and performing the actual work. The input is the optimal plan, and the output is the execution schedule and the specific fertilization and pruning actions.

[1067] Step 7:

[1068] Execution and automation

[1069] The production equipment automatically carries out fertilization, pruning, and pest control based on an optimal plan. The input is the execution schedule, and the output is the results of fertilization and pruning.

[1070] Step 8:

[1071] Plan Delivery

[1072] The server delivers the generated optimal plan to the user's device. The user performs the task while referring to the plan displayed on the smart glasses or robot. The input is the optimal plan, and the output is the plan displayed on the user's device.

[1073] Step 9:

[1074] Feedback collection

[1075] The user provides the server with the results of implementing the proposed optimal plan and information obtained during the process, including harvest volume, quality, and any problems that occurred. The input is the implementation results and information obtained during the process, and the output is feedback data.

[1076] Step 10:

[1077] Relearn

[1078] The server stores the collected feedback data in a database and retrains the AI ​​model, which continuously improves the accuracy of the suggestions. The input is the feedback data, and the output is the retrained AI model.

[1079] 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.

[1080] This invention improves the user experience by combining a system that collects production information from experienced farmers and proposes optimal fruit production plans based on that information with an emotion engine that recognizes the user's emotions. The program processing of this system is explained in detail below.

[1081] Data collection and storage

[1082] server

[1083] The server first collects production information from farmers. This information includes soil type, climate conditions, fertilization timing, pruning methods, and pest and disease prevention measures. This information can be received through online forms or APIs. For example, data is obtained from an apple farmer that includes fertilization schedules and details of the fertilizers used. The server then stores the collected production information in a database.

[1084] Data preprocessing and analysis

[1085] server

[1086] The stored data is preprocessed before being input into the AI ​​model. Preprocessing includes data normalization, missing value completion, and outlier detection and removal. The preprocessed data is then analyzed by the AI ​​model to learn optimal fruit production methods. For example, in apple production, the model learns the relationship between climatic conditions and yield, and determines the optimal fertilization schedule and pruning method.

[1087] Generating and delivering optimal plans

[1088] server

[1089] Based on the analysis results, the server generates an optimal plan for specific fruit production, including recommended cultivation techniques, fertilization timing, and pest control measures. The generated plan is then sent from the server to the user's device.

[1090] Terminal

[1091] The user's terminal receives and displays the optimal plan sent from the server. The user then carries out fruit production based on this plan. For example, a new apple farmer may start growing apples while referring to the received plan.

[1092] Gathering feedback and relearning

[1093] User

[1094] The user provides the server with feedback on the results of implementing the proposed optimal plan and the information obtained during the process, including the yield, quality, and any problems encountered.

[1095] server

[1096] The server collects user feedback and stores it in a database. Furthermore, the collected feedback data is used to retrain the AI ​​model, improving the accuracy of its suggestions. For example, new pest control measures are learned based on feedback from apple farmers.

[1097] Introducing the Emotion Engine

[1098] Server and Device

[1099] The server is equipped with an emotion engine that recognizes the user's emotions. The emotion engine analyzes the user's emotional state when entering feedback and uses that information to further refine the optimal plan. For example, if the user is facing a difficult situation, the engine can provide more detailed support information.

[1100] Terminal

[1101] The device uses an emotion engine to monitor the user's emotions in real time during interactions, and if the user feels stressed, it will provide encouraging messages or additional support to keep the user motivated.

[1102] Specific examples

[1103] For example, let's say an apple farmer starts cultivating based on a proposed plan, but is having trouble with pests and diseases. When the user provides feedback about this, the emotion engine recognizes the user's anxiety and immediately provides specific countermeasures and contact information for experts. This allows the user to take measures with peace of mind.

[1104] This system allows farmers to receive the latest know-how as well as emotional support when needed, enabling them to produce high-quality fruit consistently. The introduction of the emotion engine allows users to use the service with peace of mind, which is expected to lead to more effective production.

[1105] The processing flow will be explained below.

[1106] Program processing steps

[1107] Step 1:

[1108] The server collects production information from farmers through online forms and APIs, such as soil type, climate conditions, fertilization timing, pruning methods, pest control measures, etc. For example, it collects fertilization schedules and details of the fertilizers used from apple farmers.

[1109] Step 2:

[1110] The server stores the collected production information in a database, which structures and organizes the collected information so that it can be accessed quickly and efficiently for subsequent processing.

[1111] Step 3:

[1112] The server performs preprocessing of the production information stored in the database. Preprocessing includes data normalization, missing value completion, and outlier detection and removal. For example, missing values ​​are completed with the average value, and outliers are detected and removed.

[1113] Step 4:

[1114] The server inputs the preprocessed data into an AI model for analysis. The AI ​​model uses machine learning algorithms to learn patterns and rules from the data. For example, it can learn the optimal fertilization schedule for apple production.

[1115] Step 5:

[1116] Based on the results of the AI ​​model's analysis, the server generates a specific optimal plan for fruit production, including recommended cultivation methods, fertilization timing, and pest control measures.

[1117] Step 6:

[1118] The server then delivers the generated optimal plan to the user's device. By providing an optimal plan tailored to each user's conditions, the user can receive individually customized advice.

[1119] Step 7:

[1120] The terminal receives the optimal plan delivered from the server and displays it to the user. The user then carries out fruit production based on the displayed plan. For example, a new apple farmer starts cultivating fruit according to the delivered plan.

[1121] Step 8:

[1122] The device uses an emotion engine to monitor the user's emotions in real time, and if the user is feeling stressed, it will provide encouraging messages or additional support.

[1123] Step 9:

[1124] The user provides feedback to the server via their device about the results of implementing the proposed optimal plan and the emotions they felt during the process, including the yield, quality, problems encountered, and emotional state.

[1125] Step 10:

[1126] The server collects and stores feedback from users in a database, including the user's emotional state as analyzed by the emotion engine.

[1127] Step 11:

[1128] The server uses the collected feedback data and emotional information to retrain the AI ​​model, improving the accuracy of recommendations and the user experience, and enhancing the quality of the optimal plan provided from the next time onwards.

[1129] Through this series of processing steps, the fruit generation suggestion system can provide farmers with high-quality and reliable information, improving the efficiency of fruit production and the user experience. The introduction of the emotion engine creates an environment where users can use the service with peace of mind, and more effective production can be expected.

[1130] Example 2

[1131] 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."

[1132] Conventional agricultural production systems often propose incomplete production plans based solely on the experience and knowledge of farmers, and have the problem of not providing adequate proposals that are optimized for specific conditions or regions. Furthermore, because support does not take into account the emotional state of users, there is also the issue of being unable to respond appropriately when faced with difficult situations.

[1133] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for collecting production information from experienced farmers, means for saving the collected production information in a database, means for preprocessing the saved production information and inputting it into an analysis device, means for performing analysis using the analysis device, means for generating an optimal crop production plan based on the analysis results, means for distributing the generated optimal plan to users, means for collecting feedback from users, means for saving the collected feedback in a database and retraining the analysis device, means for analyzing emotional states, means for improving the optimal plan based on emotional states, and means for monitoring the user's emotions in real time during crop production. This makes it possible to provide a production plan optimized for specific conditions and regions and to provide appropriate support according to the user's emotions.

[1134] An "agricultural worker" is a person with specialized knowledge and experience in crop production and management.

[1135] "Production information" refers to data related to crop production, including soil type, climatic conditions, timing of fertilization, pruning methods, and measures against pests and diseases.

[1136] A "database" is a system for efficiently storing, managing, and searching large amounts of data.

[1137] "Preprocessing" is the process of preparing data for analysis, and includes normalizing data, imputing missing values, and detecting and removing outliers.

[1138] An "analysis device" is a device that uses stored data to perform complex calculations and processing to derive optimal solutions, and generally refers to an AI model or machine learning model.

[1139] "Analysis" is the process of deriving specific results or patterns from input data.

[1140] A "crop production plan" is a detailed description of the crop production methods that are best suited to specific conditions and regions.

[1141] "User" refers to farmers and related persons who use this system to produce crops.

[1142] "Feedback" refers to the act of a user returning the results of using the system and the data obtained to the system.

[1143] "Emotional state" refers to the mental state or emotion that a user displays when entering feedback or while working.

[1144] The "emotion engine" is a system that analyzes the user's emotional state from their input data and behavior, and provides an appropriate response.

[1145] "Real-time monitoring" is the process of instantly monitoring the user's behavior and status on the spot and quickly providing analytical results.

[1146] This invention is a system that proposes optimal crop production plans based on production information from experienced farmers, and further improves the user experience by combining it with an emotion engine that recognizes the user's emotions. The program processing of this system is explained below.

[1147] Data collection and storage

[1148] server

[1149] The server first collects production information from farmers. This information includes soil type, climate conditions, fertilization timing, pruning methods, and pest and disease control measures. This information can be received through an online form or API. For example, data including fertilization schedules and details of the fertilizers used is obtained from an apple farmer. The collected production information is stored in a database. Databases used include MySQL and PostgreSQL.

[1150] Data preprocessing and analysis

[1151] server

[1152] The stored data is input into an AI model after undergoing preprocessing. Preprocessing includes data normalization, missing value completion, and outlier detection and removal. Data processing libraries such as NumPy and Pandas are used for preprocessing. The preprocessed data is then analyzed by an AI model using machine learning frameworks such as TensorFlow and PyTorch. For example, in apple production, the relationship between weather conditions and yield can be learned to determine the optimal fertilization schedule and pruning method.

[1153] Generating and delivering optimal plans

[1154] server

[1155] Based on the analysis results, the server generates an optimal plan for specific crop production, including recommended cultivation techniques, fertilization timing, and pest control measures. The generated plan is then sent from the server to the user's device.

[1156] Gathering feedback and relearning

[1157] User

[1158] The user provides the server with feedback on the results of implementing the proposed optimal plan and information obtained during the process, including the yield, quality, and any problems encountered.

[1159] server

[1160] The server collects user feedback and stores it in a database. Furthermore, the collected feedback data is used to retrain the AI ​​model, improving the accuracy of its suggestions. For example, new pest control measures are learned based on feedback from apple farmers.

[1161] Introducing the Emotion Engine

[1162] Server and Device

[1163] The server is equipped with an emotion engine that recognizes the user's emotions. The emotion engine analyzes the user's emotional state when entering feedback and uses that information to further refine the optimal plan. For example, if the user is facing a difficult situation, the engine can provide more detailed support information.

[1164] Terminal

[1165] The device uses an emotion engine to monitor the user's emotions in real time during interactions, and if the user feels stressed, it will provide encouraging messages or additional support to keep the user motivated.

[1166] Specific examples

[1167] For example, let's say an apple farmer starts cultivating based on a proposed plan, but is having trouble with pests and diseases. When the user provides feedback about this, the emotion engine recognizes the user's anxiety and immediately provides specific countermeasures and contact information for experts. This allows the user to take measures with peace of mind.

[1168] Prompt Sentence Examples

[1169] "I applied fertilizer in March and July, but I'm having trouble with insect damage. What can I do?"

[1170] This system allows farmers to receive the latest know-how as well as emotional support when needed, enabling them to produce high-quality crops consistently. The introduction of the emotion engine allows users to use the service with peace of mind, which is expected to lead to more effective production.

[1171] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1172] Step 1: Data collection

[1173] server

[1174] The server provides an online form to farmers. The form contains input fields such as soil type, climate conditions, fertilization timing, pruning methods, and pest and disease prevention measures. The server receives the form data sent by the farmer and also processes API requests to obtain production information from outside. The input data includes fertilization schedules and details of the fertilizers used, which the server saves in a database. Specifically, the apple farmer enters information such as "clay soil" and "fertilization schedule for March and July" into the online form and submits it.

[1175] Input: Production information obtained via online forms or API requests.

[1176] Output: Production information stored in a database.

[1177] Step 2: Preprocessing

[1178] server

[1179] The server retrieves the stored production information from the database and performs preprocessing. Preprocessing includes data normalization, missing value completion, and outlier detection and removal. NumPy and Pandas are used to normalize the data and generate standardized data. Specifically, the server converts the fertilization timing (March and July) into a standardized numerical format and completes missing values ​​in the climate data with the average of past data.

[1180] Input: Production information retrieved from the database.

[1181] Output: The preprocessed dataset.

[1182] Step 3: Model analysis

[1183] server

[1184] The server inputs the preprocessed data into an AI model. The model used is trained using TensorFlow and PyTorch. The AI ​​model analyzes the optimal production method based on the input data. Specifically, it learns the relationship between weather conditions and yield, and derives the optimal fertilization schedule and pruning method.

[1185] Input: Preprocessed data.

[1186] Output: Analysis of optimal crop production methods.

[1187] Step 4: Generate and distribute optimal plans

[1188] server

[1189] Based on the analysis results, the server generates a specific crop production plan. This plan includes recommended cultivation methods, fertilization timing, and pest control measures. The generated plan is delivered to the user's device in JSON format. As a specific operation, the server generates a recommended plan to "apply ammonium nitrate fertilizer in March and July."

[1190] Input: Analysis results of the AI ​​model.

[1191] Output: The generated optimal plan.

[1192] Terminal

[1193] The terminal receives the optimal plan sent from the server and displays it on the application. The user produces crops based on this plan. Specifically, a new apple farmer begins cultivation based on the received plan.

[1194] Input: The optimal plan delivered by the server.

[1195] Output: The plan displayed on the terminal.

[1196] Step 5: Gather feedback and retrain

[1197] User

[1198] Users provide feedback to the server on the results of their work and the information they have gained during the process, including the yield, quality, and any problems they may have encountered. For example, an apple farmer might input, "After applying fertilizer in March, insect damage occurred."

[1199] Input: User feedback.

[1200] Output: Data sent to the server.

[1201] server

[1202] The server stores the feedback in a database and retrains the AI ​​model, which improves the accuracy of its suggestions. Specifically, it retrains the TensorFlow model using the new data.

[1203] Input: Feedback data from users.

[1204] Output: The updated AI model.

[1205] Step 6: Implementing the Emotion Engine

[1206] Server and Device

[1207] The server uses an emotion engine to analyze the user's emotions when entering feedback. If the user is facing a difficult situation, the emotion engine will provide specific solutions and specialist consultation options. The device will monitor the user's emotions in real time and provide encouraging messages if the user is feeling stressed. For example, if the user enters "I'm very worried" in the feedback, the emotion engine will analyze this, determine it as "anxiety," and provide additional support.

[1208] Input: User feedback, emotion data.

[1209] Output: Supportive information and messages based on emotional state.

[1210] (Application example 2)

[1211] 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."

[1212] Modern factories are required to improve production efficiency and reduce employee stress, but optimizing production schedules and managing machine maintenance remain challenges. Providing an efficient work environment that takes into account employee emotions is also important, but existing systems do not adequately address this issue.

[1213] 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.

[1214] In this invention, the server includes means for collecting production information from experienced farmers, means for saving the collected production information in a database, means for preprocessing the saved production information and inputting it into an AI model, means for analyzing using the AI ​​model, means for generating an optimal plan for fruit production based on the analysis results, means for distributing the generated optimal plan to users, means for collecting feedback from users, means for saving the collected feedback in a database and retraining the AI ​​model, and means for recognizing the emotional state of users and improving the optimal plan based on the analysis results. This makes it possible to optimize production schedules and provide an efficient work environment that takes employee emotions into consideration.

[1215] "Agricultural workers" refers to people who are engaged in agricultural work, especially those who have specialized knowledge and experience and work on producing crops.

[1216] "Production information" refers to detailed data on crop production, such as soil type, climatic conditions, fertilization timing, pruning methods, and pest and disease control measures.

[1217] A "database" refers to a system that can efficiently store, manage, and access large amounts of data.

[1218] "Preprocessing" refers to processes such as normalizing data, filling in missing values, and detecting and removing outliers, which are carried out to make the input data to an AI model analyzable.

[1219] An "AI model" refers to a system that uses artificial intelligence algorithms and machine learning techniques to analyze data, learn patterns, and make predictions and decisions.

[1220] "Analysis" refers to the process of extracting specific information and insights from collected data.

[1221] An "optimal plan" is a plan that proposes the most suitable methods and schedules for agricultural production based on the analysis results of an AI model.

[1222] "Delivery" refers to the process of transmitting the generated optimal plan to the user's terminal and making it available for use.

[1223] "Feedback" refers to information provided by users based on their practical results and experiences.

[1224] "Retraining" refers to the process of using collected feedback to retrain an AI model, improving its accuracy and the precision of its recommendations.

[1225] "Emotional state" refers to a user's psychological state or feeling, which is identified through text analysis and an emotion engine.

[1226] "Improvement" refers to the process of making changes or additions to existing plans or systems to make them more effective and improve their accuracy and usability.

[1227] A "system" is a set of multiple interrelated components and processes that function to achieve a specific purpose.

[1228] The present invention relates to a smart factory management application for optimizing factory management. The program processing of this system will be specifically described below.

[1229] Data collection and storage

[1230] The server collects production information from production equipment and facilities within the factory. This production information includes various sensor data, machine operating status, maintenance schedules, etc. The collected information is saved in the server's database in real time.

[1231] Data preprocessing and analysis

[1232] The server preprocesses the collected production information. This preprocessing includes data normalization, missing value completion, and outlier detection and removal. The preprocessed data is then input into an AI model. An example of the AI ​​model used here is RandomForestRegressor. This model analyzes the production information and generates an optimal production schedule and efficiency improvement plan.

[1233] Generating and delivering optimal plans

[1234] The server generates an optimal production plan based on the analysis results of the AI ​​model. This plan includes machine operation schedules, maintenance timing, efficient resource allocation, etc. The generated optimal plan is then distributed from the server to the user's device.

[1235] The user's device receives the optimal plan and presents it to the factory's monitoring system and manager. The user then carries out production activities based on this plan.

[1236] Gathering feedback and relearning

[1237] The user implements the proposed optimal plan and provides the results and information obtained during the process as feedback to the server, including production efficiency, problems, and areas for improvement.

[1238] The server stores the collected feedback in a database and retrains the AI ​​model to improve the accuracy of future suggestions. Retraining involves tuning the AI ​​model using the feedback data.

[1239] Introducing the Emotion Engine

[1240] The server is equipped with an emotion engine that recognizes the user's emotional state. The emotion engine uses text and voice analysis to determine the user's emotions. Once the emotional state is recognized, the server uses that information to further refine the optimal plan. This refinement can provide encouraging messages or additional support information if the user is facing a difficult situation.

[1241] Specific examples

[1242] For example, if equipment breakdowns occur frequently at a factory and employees are feeling stressed, the information is sent to the server through user feedback. The emotion engine recognizes the employee's stress level from this feedback and immediately provides suggestions for improvement and encouraging messages.

[1243] Example prompt sentence:

[1244] Generate plans to optimize maintenance frequency on production lines and reduce equipment breakdowns, plus add support messages if employees' stress levels are high.

[1245] In this way, the system of the present invention makes it possible to optimize production schedules and provide an efficient working environment that takes into account the emotions of employees.

[1246] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1247] Step 1:

[1248] The server collects production information from production equipment and facilities within the factory. This includes data obtained from sensors, machine operation status, maintenance schedules, etc. Input data is sent to the server in real time via API or sensor devices. The output is the collected production information stored in a database.

[1249] Step 2:

[1250] The server preprocesses the collected production information. The input is data obtained from the production information database. Data normalization, missing value imputation, and outlier detection and removal are performed. For example, missing values ​​are imputed using pandas and SimpleImputer, and data is normalized using StandardScaler. The output is the preprocessed data.

[1251] Step 3:

[1252] The server inputs the preprocessed data into an AI model for analysis. The input is the preprocessed data, and the output is the analysis results. The AI ​​model used is, for example, RandomForestRegressor, and analyzes the data to generate production schedules and efficiency plans.

[1253] Step 4:

[1254] The server generates an optimal production plan based on the analysis results. The input is the analysis results from the AI ​​model. The output is the generated optimal production plan, which includes machine operation schedules, maintenance timing, and efficient resource allocation.

[1255] Step 5:

[1256] The server distributes the generated optimal plan to the user's terminal. The input is the generated optimal production plan. The output is the distributed production plan, which the user uses to carry out production activities. The terminal displays the received production plan on the factory's monitoring system and to the manager.

[1257] Step 6:

[1258] The user implements the proposed optimal plan. The input is the delivered optimal plan. The results of the implementation and information obtained during the process are provided as feedback. The output is the collected feedback information.

[1259] Step 7:

[1260] The server stores the collected feedback information in a database and retrains the AI ​​model. The input is the feedback information. Retraining uses the feedback to tune the AI ​​model and improve the accuracy of its suggestions. The output is the retrained AI model.

[1261] Step 8:

[1262] The server analyzes the emotion from the feedback using an emotion engine that recognizes the user's emotional state. The input is the feedback text or voice data. The emotion engine performs text analysis to determine the user's emotion. The output is the recognized emotional state.

[1263] Step 9:

[1264] The server refines the optimal plan based on the recognized emotional state. The input is the emotional state recognized by the emotion engine and the existing optimal plan. For example, if the user is feeling stressed, it provides an encouraging message or additional support information. The output is the refined optimal plan.

[1265] Through the above processing steps, this system optimizes production schedules and provides an efficient working environment that takes into account the emotions of employees.

[1266] 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.

[1267] 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.

[1268] 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.

[1269] [Fourth embodiment]

[1270] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1271] 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.

[1272] 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).

[1273] 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.

[1274] 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.

[1275] 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).

[1276] 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.

[1277] 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.

[1278] 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.

[1279] 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.

[1280] 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.

[1281] 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.

[1282] 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."

[1283] The present invention provides a system that collects production information from experienced farmers and proposes an optimal fruit production plan based on that information. The program processing of this system will be specifically described below.

[1284] Data collection

[1285] server

[1286] The server first collects production information from farmers, including soil type, climate conditions, fertilization timing, pruning methods, and pest and disease control measures. This information can be received through online forms or APIs. For example, the server obtains data from an apple farmer that includes the fertilization schedule and details of the fertilizers used.

[1287] Data storage

[1288] server

[1289] The server stores the collected production information in a database, which uses a high-performance storage system to structure and store the various crops and their associated production information, allowing for quick and easy access later.

[1290] Data preprocessing and analysis

[1291] server

[1292] The stored data is preprocessed before being input into the AI ​​model. Preprocessing includes data normalization, missing value completion, and outlier detection and removal. The preprocessed data is then analyzed by the AI ​​model to learn optimal fruit production methods. For example, in apple production, the model learns the relationship between climatic conditions and yield, and determines the optimal fertilization schedule and pruning method.

[1293] Generating and delivering optimal plans

[1294] server

[1295] Based on the analysis results, the server generates an optimal plan for specific fruit production, including recommended cultivation techniques, fertilization timing, and pest control measures. The generated plan is then sent from the server to the user's device.

[1296] Terminal

[1297] The user's terminal receives and displays the optimal plan sent from the server. The user then carries out fruit production based on this plan. For example, a new apple farmer may start growing apples while referring to the received plan.

[1298] Gathering feedback and relearning

[1299] User

[1300] The user provides the server with feedback on the results of implementing the proposed optimal plan and the information obtained during the process, including the yield, quality, and any problems encountered.

[1301] server

[1302] The server collects user feedback and stores it in a database. Furthermore, the collected feedback data is used to retrain the AI ​​model, improving the accuracy of its suggestions. For example, new pest control measures are learned based on feedback from apple farmers.

[1303] By operating this system, farmers can always obtain the latest know-how, enabling them to produce delicious fruit consistently. This cycle of continuous feedback and relearning keeps improving the quality of the suggestions, allowing farmers to work on fruit production with peace of mind.

[1304] The processing flow will be explained below.

[1305] Program processing steps

[1306] Step 1:

[1307] The server collects production information from farmers, such as soil type, weather conditions, fertilization timing, pruning methods, and pest and disease control measures, via online forms and APIs.

[1308] Step 2:

[1309] The server stores the collected production information in a database, which is used to structure and organize the collected information, allowing it to be efficiently retrieved for subsequent processing.

[1310] Step 3:

[1311] The server preprocesses the production information stored in the database. This preprocessing includes normalizing the data, filling in missing values, and detecting and removing outliers. This prepares the data to improve the accuracy of analysis.

[1312] Step 4:

[1313] The server then inputs the preprocessed data into an AI model, which then analyzes the data. The AI ​​model then uses machine learning algorithms to learn patterns and rules from the data, such as the optimal fertilization schedule for a given climate.

[1314] Step 5:

[1315] Based on the analysis results of the AI ​​model, the server generates a specific optimal plan for fruit production, including recommended cultivation methods, fertilization timing, and pest control measures.

[1316] Step 6:

[1317] The server then delivers the generated optimal plan to the user's device. By providing an optimal plan tailored to each user's conditions, the user can receive individually customized advice.

[1318] Step 7:

[1319] The terminal receives the optimal plan delivered from the server and displays it to the user. The user then carries out fruit production based on the displayed plan. For example, a farmer who is starting fruit production for the first time may start cultivation according to the delivered plan.

[1320] Step 8:

[1321] The user provides feedback to the server via their terminal about the results and information gained during the process of implementing the proposed optimal plan, including information on harvest volume, quality, and any problems encountered.

[1322] Step 9:

[1323] The server collects user feedback and stores it in a database. The feedback data is used in the next re-learning step.

[1324] Step 10:

[1325] The server uses the collected feedback data to retrain the AI ​​model, improving the model's prediction accuracy and proposal content, and increasing the quality of the optimal plan provided from the next time onwards.

[1326] Through this series of processing steps, the fruit generation suggestion system can provide farmers with high-quality and reliable information, thereby improving the efficiency of fruit production.

[1327] Example 1

[1328] 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."

[1329] Conventional fruit production systems have the problem of being unable to provide optimal production plans based on local conditions and the experience of individual farmers. Furthermore, they lack the re-learning functionality to effectively utilize collected production information and adapt to the constantly evolving agricultural environment. These issues make it difficult to achieve efficient and stable fruit production.

[1330] 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.

[1331] In this invention, the server includes a means for collecting production information from experienced farmers, a means for storing the collected production information in a database, and a means for preprocessing the stored production information and inputting it into an AI technology model. This enables the generation of an optimal fruit production plan based on the collected information. The server further includes a means for analysis using the AI ​​technology model and a means for generating an optimal agricultural production plan based on the analysis results. This enables the provision of an optimal production plan based on the latest technology. The server also includes a means for collecting feedback from users, storing the collected feedback in a database, and retraining the AI ​​technology model. This enables continuous system improvement based on the collected feedback data.

[1332] "Agricultural worker" means a person who is engaged in agriculture and has knowledge and experience related to fruit production.

[1333] "Production information" refers to various data related to fruit production, such as soil type, climatic conditions, timing of fertilization, pruning methods, and measures against pests and diseases.

[1334] A "database" is an information system that systematically stores collected production information and feedback, allowing it to be searched, managed, and used.

[1335] "Preprocessing" refers to processing such as normalizing data, filling in missing values, and removing outliers before inputting collected production information into an AI technology model.

[1336] An "AI technology model" is an algorithm and calculation system that uses artificial intelligence technology to analyze data and generate optimal production plans and forecasts.

[1337] "Analysis" refers to analyzing pre-processed data using an AI technology model and extracting optimal production plans, including recommended cultivation methods, fertilization timing, and pest and disease control measures.

[1338] A "production plan" is a document that includes specific methods and procedures recommended for achieving efficient and stable fruit production.

[1339] "User" refers to a farmer who uses the system to receive a fruit production plan.

[1340] "Feedback" refers to returning the results of the production plan and data obtained during the process to the system, and includes information on harvest volume, quality, and any problems that arise.

[1341] "Relearning" refers to the retraining of AI technology models using collected feedback data, a process aimed at improving analytical accuracy and continuous improvement of the system.

[1342] MODE FOR CARRYING OUT THE INVENTION

[1343] The present invention relates to a system that collects production information from experienced farmers and proposes an optimal fruit production plan based on that information. A specific embodiment for implementing this system will be described below.

[1344] Data collection

[1345] The server first collects production information from farmers. This information includes soil type, climate conditions, fertilization timing, pruning methods, and pest and disease prevention measures. The information can be collected via an online form using a web page or mobile application, or via an API endpoint. For example, an apple farmer can enter information such as "soil type: clay" and "climatic conditions: average temperature 15°C" into an online form and submit it.

[1346] Data storage

[1347] The server stores production information received through online forms and APIs in a database. Relational databases such as MySQL and PostgreSQL are suitable for this purpose. The received data is validated according to a specified format and then saved in the database.

[1348] Data preprocessing and analysis

[1349] The stored data is preprocessed by the server and input into an AI technology model. Preprocessing involves normalizing the data, filling in missing values, and removing outliers using Python scripts and the Pandas library. The preprocessed data is then analyzed by an AI technology model built using TensorFlow or PyTorch. This analysis allows the system to learn optimal fertilization timing and pruning methods based on weather conditions and production data.

[1350] Generating and delivering optimal plans

[1351] The server generates a specific optimal plan for fruit production based on the analysis results of the AI ​​technology model. This plan includes details such as recommended cultivation methods, fertilization timing, and pest control measures. The generated plan is converted into a format such as PDF or JSON and sent to the terminal. The terminal receives the optimal plan sent from the server and displays it to the user. For example, a new apple farmer may start growing apples by referring to the plan sent from the server.

[1352] Gathering feedback and relearning

[1353] The user puts the proposed optimal plan into practice and provides the results and information on the process as feedback to the server. For example, information on the yield after fertilization or the occurrence of pests and diseases is provided as feedback. The server stores the collected feedback in a database and preprocesses it again. The preprocessed feedback data is used to retrain the AI ​​technology model, improving the accuracy of the next proposal. This continuous cycle of feedback and re-learning ensures that the latest know-how is always reflected in the system.

[1354] Examples of specific examples and prompts

[1355] For example, the following data is collected from apple farmers in Nagano Prefecture:

[1356] Soil type: clay

[1357] Climate: Average temperature 15°C, annual precipitation 900mm

[1358] Fertilization timing: April and August

[1359] Fertilizer used: Nitrogen fertilizer 100kg / ha

[1360] Pruning method: Prune branches in half in February

[1361] Pest control: Pesticide spraying in June

[1362] Based on this data, the AI ​​technology model generates an optimal fruit production plan and suggests the following plan for new farmers:

[1363] Fertilization timing: Changed to March and July

[1364] Fertilizer used: Nitrogen fertilizer 120 kg / ha

[1365] Pruning method: Light pruning in March

[1366] Pest control: Pesticide spraying in May and July

[1367] Prompt Sentence Examples

[1368] "Please suggest the optimal fertilization schedule and pruning method based on data from apple farmers in Nagano Prefecture. The collected data includes soil type, climatic conditions, fertilization timing and fertilizer use, pruning methods, and pest and disease control measures."

[1369] By operating this system, farmers can always access the latest know-how and produce delicious fruit consistently. The continuous feedback and relearning cycle keeps improving the quality of the suggestions, so farmers can work on fruit production with peace of mind.

[1370] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1371] Step 1:

[1372] The server collects production information from farmers through online forms and APIs.

[1373] Input: Production information provided by farmers (e.g., soil type, climatic conditions, fertilization timing, pruning methods, pest and disease control measures)

[1374] Data processing: Organize the information entered in the online form in JSON format.

[1375] Output: Production information in formatted JSON format

[1376] Specifically, the system works by providing a form on a web page or mobile app where apple farmers can enter data such as "soil type: clay" and "climatic conditions: average temperature 15 degrees" and then submit it.

[1377] Step 2:

[1378] The server stores the received production information in a database.

[1379] Input: Production information in formatted JSON

[1380] Data processing: Generates SQL insert statements to save data to a specified table in the database.

[1381] Output: Production information stored in a database

[1382] Specifically, data is inserted into tables such as "soil information" and "climate information" using MySQL or PostgreSQL.

[1383] Step 3:

[1384] The server pre-processes the stored production information.

[1385] Input: Production information extracted from the database

[1386] Data processing: Using Python scripts and the Pandas library, we normalize the data, impute missing values, and remove outliers.

[1387] Output: A preprocessed, clean dataset

[1388] Specifically, the extracted data is loaded into a Pandas data frame, missing values ​​are filled with the average value, and outlying values ​​are removed.

[1389] Step 4:

[1390] The server inputs the preprocessed data into an AI technology model for analysis.

[1391] Input: Preprocessed clean dataset

[1392] Data calculation: Data is input into a trained AI technology model using TensorFlow or PyTorch to predict the optimal production plan.

[1393] Output: Optimal production plan (e.g., fertilization timing, pruning method, pest control)

[1394] Specifically, the preprocessed data is input into a TensorFlow model, and a recommended plan such as "Fertilization timing: March and July" and "Pruning method: Light pruning in March" is output.

[1395] Step 5:

[1396] The server generates a production plan based on the analysis results and distributes it to the terminal.

[1397] Input: Analysis results from AI technology model

[1398] Data processing: Convert the analysis results into a format that is easy for users to understand (such as PDF or JSON).

[1399] Output: A file of the generated production plan

[1400] Specifically, the generated plan is converted into a PDF file and sent to the user's device by email.

[1401] Step 6:

[1402] The terminal receives and displays the optimum plan distributed from the server.

[1403] Input: Production plan file sent from the server

[1404] Data processing: Converts data into a format suitable for display in a PDF viewer or app.

[1405] Output: Displayed production plan

[1406] Specifically, a new apple farmer opens the PDF plan he or she received and checks information such as "fertilize in March and July" and "spray pesticides in May and July."

[1407] Step 7:

[1408] The user puts the proposed optimal plan into practice and provides feedback on the results.

[1409] Input: Results of implementing the production plan (e.g., yield, quality, information on pests and diseases that have occurred)

[1410] Data processing: Enter feedback information through online forms or apps.

[1411] Output: Formatted feedback data

[1412] Specifically, the user enters information such as "harvest yield after fertilization: 800 kg" and "pests and diseases encountered: aphids" into an online form and submits it.

[1413] Step 8:

[1414] The server stores the feedback information in a database and uses it for re-learning.

[1415] Input: Formatted feedback data

[1416] Data processing: Save the data in a feedback table in the database and perform preprocessing again. Impute missing values ​​and remove outliers.

[1417] Output: Preprocessed feedback data

[1418] Specifically, the feedback data is stored in a database, and a clean dataset is prepared again using Python and Pandas.

[1419] Step 9:

[1420] The server uses the pre-processed feedback data to retrain the AI ​​technology model.

[1421] Input: Preprocessed feedback data

[1422] Data calculation: Feedback data is input into the AI ​​technology model, and the model parameters are readjusted to perform re-learning.

[1423] Output: AI technology model with improved accuracy

[1424] Specifically, the feedback data is re-input into the TensorFlow model, allowing it to learn and generate a new optimal plan.

[1425] (Application example 1)

[1426] 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."

[1427] Generally, farmers produce fruit based on their experience and knowledge, but their methods are largely dependent on the skills and knowledge of each individual farmer and are not standardized. This often results in inconsistent yields and quality, which in turn reduces the efficiency of agricultural production and potentially leads to unstable profits. Finding appropriate measures to quickly respond to changes in environmental conditions and climate is particularly challenging, and another contributing factor is the lack of automation in the production process. A system that can resolve these issues and improve the efficiency and quality of fruit production is needed.

[1428] 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.

[1429] In this invention, the server includes: means for collecting production information from experienced farmers; means for saving the collected production information in a database; means for preprocessing the saved production information and inputting it into an AI model; means for analyzing using the AI ​​model; means for generating an optimal plan for fruit production based on the analysis results; means for applying the generated optimal plan to production equipment; means for managing fertilization and pruning performed by the production equipment according to a schedule; means for the production equipment to automatically perform fertilization, pruning, and pest control; means for distributing the generated optimal plan to users; means for collecting feedback from users; and means for saving the collected feedback in a database and retraining the AI ​​model. This enables standardization and optimization of agricultural production, uniform harvest yields and quality, and labor-saving and cost reduction through automation.

[1430] "Agricultural workers" refers to people who work professionally in agriculture and have the skills and knowledge to produce crops such as fruits and vegetables.

[1431] "Production information" refers to various types of information that farmers use when producing fruits and crops, including soil type, climatic conditions, timing of fertilization, pruning methods, and pest and disease control measures.

[1432] A "database" is a high-performance storage system that stores collected production information and feedback information in a structured manner so that it can be accessed quickly and easily later.

[1433] "Preprocessing" refers to the processing carried out before collected production information is input into the AI ​​model, and specifically includes data normalization, missing value completion, and outlier detection and removal.

[1434] An "AI model" is a model that uses artificial intelligence technologies such as machine learning and deep learning, and is used to analyze production information and generate optimal fruit production plans.

[1435] The "analysis results" are data and information obtained through analytical processing using an AI model, and are used to derive optimal fruit production plans.

[1436] The "optimal plan" is an execution plan for fruit production generated based on the analysis results of the AI ​​model, and includes recommended cultivation methods, fertilization timing, and pest and disease prevention measures.

[1437] "Production equipment" refers to mechanical devices used to automate various tasks in fruit production, specifically robots and machines that perform fertilization, pruning, and pest control.

[1438] "Feedback" refers to the results of the user's implementation of the proposed optimal plan and the information obtained in the process, including harvest volume, quality, and any problems that arise.

[1439] "Retraining" is the process of retraining an AI model using collected feedback information to improve the accuracy of its suggestions.

[1440] As an embodiment of the present invention, a specific description will be given of how the elements of the server, terminal, and user work together.

[1441] 1. Data Collection

[1442] The server first collects production information from farmers, including soil type, weather conditions, fertilization timing, pruning methods, pest control measures, etc. Data can be collected via an online form or API.

[1443] 2. Data storage

[1444] The server stores the collected production information in a database, which uses a high-performance storage system for efficient management of structured data, allowing this data to be accessed quickly and easily later.

[1445] 3. Data Preprocessing

[1446] The server preprocesses the stored data, which includes normalizing the data, imputing missing values, and removing outliers. The preprocessed data is then input into machine learning and deep learning AI models.

[1447] 4. Analysis using AI models

[1448] The server inputs the preprocessed data into an AI model for analysis. The AI ​​model is built using machine learning frameworks such as TensorFlow and Keras. The analysis results generate an optimal fruit production plan.

[1449] 5. Generating and Applying the Optimal Plan

[1450] The server generates a specific production plan based on the analysis results. This plan includes recommended cultivation techniques, fertilization timing, and pest control measures. The server then applies this optimal plan to production equipment. Production equipment is automated machinery such as robots that perform fertilization, pruning, and pest control.

[1451] 6. Plan Management and Execution

[1452] The production equipment manages and executes fertilization and pruning according to a schedule based on the optimal plan received from the server, significantly reducing the amount of manual management work required.

[1453] 7. Delivery of the Plan

[1454] The server then delivers the generated optimal plan to the user's device, and the user performs the task while referring to the plan displayed on the smart glasses or robot.

[1455] 8. Gathering Feedback

[1456] Users provide feedback to the server on the results of their practice and information gained during the process, including yield, quality, and any problems encountered.

[1457] 9. Relearn

[1458] The server stores the collected feedback data in a database and retrains the AI ​​model, allowing the accuracy of the suggestions to continue to improve.

[1459] Specific examples

[1460] For example, an AI model analyzes data collected from apple farmers and generates an optimal fertilization schedule. This plan is then executed by production equipment, and information on yield and quality is sent back to the server as feedback. The AI ​​model re-learns based on the collected feedback data, and a new optimal plan is generated.

[1461] Prompt Sentence Examples

[1462] "Task: Analyze data collected from farmers and generate an optimal fruit production plan. Data collected includes soil type, weather conditions, fertilization timing, pruning methods, and pest and disease control."

[1463] In this way, this invention will enable the standardization and optimization of agricultural production processes, leading to labor savings through automation and improved yields and quality.

[1464] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1465] Step 1:

[1466] Data collection

[1467] The server collects production information from farmers using online forms and APIs, including information on soil type, climate conditions, fertilization timing, pruning methods, and pest and disease control. The input is various production information provided by farmers, and the output is structured data of this information. The server converts this information into an appropriate format and stores it in a database.

[1468] Step 2:

[1469] Data storage

[1470] The server stores the production information collected in step 1 in a database. The input is structured production information data, and the output is production information data stored in a database. A database management system (e.g., PostgreSQL) is used to store data quickly and efficiently.

[1471] Step 3:

[1472] Data Preprocessing

[1473] The server performs preprocessing on the stored production information before inputting it into the AI ​​model. Specifically, it normalizes the data, fills in missing values, and detects and removes outliers. The input is the production information data stored in the database, and the output is the preprocessed data. This preprocessing is performed using the Python Pandas library.

[1474] Step 4:

[1475] Analysis using AI models

[1476] The server inputs the preprocessed data into an AI model for analysis. Specifically, it uses machine learning and deep learning algorithms to generate an optimal fruit production plan. The input is the preprocessed data, and the output is the analysis results from the AI ​​model. Machine learning frameworks such as TensorFlow and Keras are used.

[1477] Step 5:

[1478] Generating an optimal plan

[1479] Based on the analysis results of the AI ​​model, the server generates an optimal fruit production plan for the production equipment (factory robots) to execute. The input is the analysis results, and the output is an optimal plan that includes specific fertilization timing, pruning methods, pest control measures, etc.

[1480] Step 6:

[1481] Applying and Managing Plans

[1482] The production equipment receives the generated optimal plan and manages fertilization and pruning according to the schedule. This includes setting the timing for fertilization and pruning and performing the actual work. The input is the optimal plan, and the output is the execution schedule and the specific fertilization and pruning actions.

[1483] Step 7:

[1484] Execution and automation

[1485] The production equipment automatically carries out fertilization, pruning, and pest control based on an optimal plan. The input is the execution schedule, and the output is the results of fertilization and pruning.

[1486] Step 8:

[1487] Plan Delivery

[1488] The server delivers the generated optimal plan to the user's device. The user performs the task while referring to the plan displayed on the smart glasses or robot. The input is the optimal plan, and the output is the plan displayed on the user's device.

[1489] Step 9:

[1490] Feedback collection

[1491] The user provides the server with the results of implementing the proposed optimal plan and information obtained during the process, including harvest volume, quality, and any problems that occurred. The input is the implementation results and information obtained during the process, and the output is feedback data.

[1492] Step 10:

[1493] Relearn

[1494] The server stores the collected feedback data in a database and retrains the AI ​​model, which continuously improves the accuracy of the suggestions. The input is the feedback data, and the output is the retrained AI model.

[1495] 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.

[1496] This invention improves the user experience by combining a system that collects production information from experienced farmers and proposes optimal fruit production plans based on that information with an emotion engine that recognizes the user's emotions. The program processing of this system is explained in detail below.

[1497] Data collection and storage

[1498] server

[1499] The server first collects production information from farmers. This information includes soil type, climate conditions, fertilization timing, pruning methods, and pest and disease prevention measures. This information can be received through online forms or APIs. For example, data is obtained from an apple farmer that includes fertilization schedules and details of the fertilizers used. The server then stores the collected production information in a database.

[1500] Data preprocessing and analysis

[1501] server

[1502] The stored data is preprocessed before being input into the AI ​​model. Preprocessing includes data normalization, missing value completion, and outlier detection and removal. The preprocessed data is then analyzed by the AI ​​model to learn optimal fruit production methods. For example, in apple production, the model learns the relationship between climatic conditions and yield, and determines the optimal fertilization schedule and pruning method.

[1503] Generating and delivering optimal plans

[1504] server

[1505] Based on the analysis results, the server generates an optimal plan for specific fruit production, including recommended cultivation techniques, fertilization timing, and pest control measures. The generated plan is then sent from the server to the user's device.

[1506] Terminal

[1507] The user's terminal receives and displays the optimal plan sent from the server. The user then carries out fruit production based on this plan. For example, a new apple farmer may start growing apples while referring to the received plan.

[1508] Gathering feedback and relearning

[1509] User

[1510] The user provides the server with feedback on the results of implementing the proposed optimal plan and the information obtained during the process, including the yield, quality, and any problems encountered.

[1511] server

[1512] The server collects user feedback and stores it in a database. Furthermore, the collected feedback data is used to retrain the AI ​​model, improving the accuracy of its suggestions. For example, new pest control measures are learned based on feedback from apple farmers.

[1513] Introducing the Emotion Engine

[1514] Server and Device

[1515] The server is equipped with an emotion engine that recognizes the user's emotions. The emotion engine analyzes the user's emotional state when entering feedback and uses that information to further refine the optimal plan. For example, if the user is facing a difficult situation, the engine can provide more detailed support information.

[1516] Terminal

[1517] The device uses an emotion engine to monitor the user's emotions in real time during interactions, and if the user feels stressed, it will provide encouraging messages or additional support to keep the user motivated.

[1518] Specific examples

[1519] For example, let's say an apple farmer starts cultivating based on a proposed plan, but is having trouble with pests and diseases. When the user provides feedback about this, the emotion engine recognizes the user's anxiety and immediately provides specific countermeasures and contact information for experts. This allows the user to take measures with peace of mind.

[1520] This system allows farmers to receive the latest know-how as well as emotional support when needed, enabling them to produce high-quality fruit consistently. The introduction of the emotion engine allows users to use the service with peace of mind, which is expected to lead to more effective production.

[1521] The processing flow will be explained below.

[1522] Program processing steps

[1523] Step 1:

[1524] The server collects production information from farmers through online forms and APIs, such as soil type, climate conditions, fertilization timing, pruning methods, pest control measures, etc. For example, it collects fertilization schedules and details of the fertilizers used from apple farmers.

[1525] Step 2:

[1526] The server stores the collected production information in a database, which structures and organizes the collected information so that it can be accessed quickly and efficiently for subsequent processing.

[1527] Step 3:

[1528] The server performs preprocessing of the production information stored in the database. Preprocessing includes data normalization, missing value completion, and outlier detection and removal. For example, missing values ​​are completed with the average value, and outliers are detected and removed.

[1529] Step 4:

[1530] The server inputs the preprocessed data into an AI model for analysis. The AI ​​model uses machine learning algorithms to learn patterns and rules from the data. For example, it can learn the optimal fertilization schedule for apple production.

[1531] Step 5:

[1532] Based on the results of the AI ​​model's analysis, the server generates a specific optimal plan for fruit production, including recommended cultivation methods, fertilization timing, and pest control measures.

[1533] Step 6:

[1534] The server then delivers the generated optimal plan to the user's device. By providing an optimal plan tailored to each user's conditions, the user can receive individually customized advice.

[1535] Step 7:

[1536] The terminal receives the optimal plan delivered from the server and displays it to the user. The user then carries out fruit production based on the displayed plan. For example, a new apple farmer starts cultivating fruit according to the delivered plan.

[1537] Step 8:

[1538] The device uses an emotion engine to monitor the user's emotions in real time, and if the user is feeling stressed, it will provide encouraging messages or additional support.

[1539] Step 9:

[1540] The user provides feedback to the server via their device about the results of implementing the proposed optimal plan and the emotions they felt during the process, including the yield, quality, problems encountered, and emotional state.

[1541] Step 10:

[1542] The server collects and stores feedback from users in a database, including the user's emotional state as analyzed by the emotion engine.

[1543] Step 11:

[1544] The server uses the collected feedback data and emotional information to retrain the AI ​​model, improving the accuracy of recommendations and the user experience, and enhancing the quality of the optimal plan provided from the next time onwards.

[1545] Through this series of processing steps, the fruit generation suggestion system can provide farmers with high-quality and reliable information, improving the efficiency of fruit production and the user experience. The introduction of the emotion engine creates an environment where users can use the service with peace of mind, and more effective production can be expected.

[1546] Example 2

[1547] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1548] Conventional agricultural production systems often propose incomplete production plans based solely on the experience and knowledge of farmers, and have the problem of not providing adequate proposals that are optimized for specific conditions or regions. Furthermore, because support does not take into account the emotional state of users, there is also the issue of being unable to respond appropriately when faced with difficult situations.

[1549] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for collecting production information from experienced farmers, means for saving the collected production information in a database, means for preprocessing the saved production information and inputting it into an analysis device, means for performing analysis using the analysis device, means for generating an optimal crop production plan based on the analysis results, means for distributing the generated optimal plan to users, means for collecting feedback from users, means for saving the collected feedback in a database and retraining the analysis device, means for analyzing emotional states, means for improving the optimal plan based on emotional states, and means for monitoring the user's emotions in real time during crop production. This makes it possible to provide a production plan optimized for specific conditions and regions and to provide appropriate support according to the user's emotions.

[1550] An "agricultural worker" is a person with specialized knowledge and experience in crop production and management.

[1551] "Production information" refers to data related to crop production, including soil type, climatic conditions, timing of fertilization, pruning methods, and measures against pests and diseases.

[1552] A "database" is a system for efficiently storing, managing, and searching large amounts of data.

[1553] "Preprocessing" is the process of preparing data for analysis, and includes normalizing data, imputing missing values, and detecting and removing outliers.

[1554] An "analysis device" is a device that uses stored data to perform complex calculations and processing to derive optimal solutions, and generally refers to an AI model or machine learning model.

[1555] "Analysis" is the process of deriving specific results or patterns from input data.

[1556] A "crop production plan" is a detailed description of the crop production methods that are best suited to specific conditions and regions.

[1557] "User" refers to farmers and related persons who use this system to produce crops.

[1558] "Feedback" refers to the act of a user returning the results of using the system and the data obtained to the system.

[1559] "Emotional state" refers to the mental state or emotion that a user displays when entering feedback or while working.

[1560] The "emotion engine" is a system that analyzes the user's emotional state from their input data and behavior, and provides an appropriate response.

[1561] "Real-time monitoring" is the process of instantly monitoring the user's behavior and status on the spot and quickly providing analytical results.

[1562] This invention is a system that proposes optimal crop production plans based on production information from experienced farmers, and further improves the user experience by combining it with an emotion engine that recognizes the user's emotions. The program processing of this system is explained below.

[1563] Data collection and storage

[1564] server

[1565] The server first collects production information from farmers. This information includes soil type, climate conditions, fertilization timing, pruning methods, and pest and disease control measures. This information can be received through an online form or API. For example, data including fertilization schedules and details of the fertilizers used is obtained from an apple farmer. The collected production information is stored in a database. Databases used include MySQL and PostgreSQL.

[1566] Data preprocessing and analysis

[1567] server

[1568] The stored data is input into an AI model after undergoing preprocessing. Preprocessing includes data normalization, missing value completion, and outlier detection and removal. Data processing libraries such as NumPy and Pandas are used for preprocessing. The preprocessed data is then analyzed by an AI model using machine learning frameworks such as TensorFlow and PyTorch. For example, in apple production, the relationship between weather conditions and yield can be learned to determine the optimal fertilization schedule and pruning method.

[1569] Generating and delivering optimal plans

[1570] server

[1571] Based on the analysis results, the server generates an optimal plan for specific crop production, including recommended cultivation techniques, fertilization timing, and pest control measures. The generated plan is then sent from the server to the user's device.

[1572] Gathering feedback and relearning

[1573] User

[1574] The user provides the server with feedback on the results of implementing the proposed optimal plan and information obtained during the process, including the yield, quality, and any problems encountered.

[1575] server

[1576] The server collects user feedback and stores it in a database. Furthermore, the collected feedback data is used to retrain the AI ​​model, improving the accuracy of its suggestions. For example, new pest control measures are learned based on feedback from apple farmers.

[1577] Introducing the Emotion Engine

[1578] Server and Device

[1579] The server is equipped with an emotion engine that recognizes the user's emotions. The emotion engine analyzes the user's emotional state when entering feedback and uses that information to further refine the optimal plan. For example, if the user is facing a difficult situation, the engine can provide more detailed support information.

[1580] Terminal

[1581] The device uses an emotion engine to monitor the user's emotions in real time during interactions, and if the user feels stressed, it will provide encouraging messages or additional support to keep the user motivated.

[1582] Specific examples

[1583] For example, let's say an apple farmer starts cultivating based on a proposed plan, but is having trouble with pests and diseases. When the user provides feedback about this, the emotion engine recognizes the user's anxiety and immediately provides specific countermeasures and contact information for experts. This allows the user to take measures with peace of mind.

[1584] Prompt Sentence Examples

[1585] "I applied fertilizer in March and July, but I'm having trouble with insect damage. What can I do?"

[1586] This system allows farmers to receive the latest know-how as well as emotional support when needed, enabling them to produce high-quality crops consistently. The introduction of the emotion engine allows users to use the service with peace of mind, which is expected to lead to more effective production.

[1587] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1588] Step 1: Data collection

[1589] server

[1590] The server provides an online form to farmers. The form contains input fields such as soil type, climate conditions, fertilization timing, pruning methods, and pest and disease prevention measures. The server receives the form data sent by the farmer and also processes API requests to obtain production information from outside. The input data includes fertilization schedules and details of the fertilizers used, which the server saves in a database. Specifically, the apple farmer enters information such as "clay soil" and "fertilization schedule for March and July" into the online form and submits it.

[1591] Input: Production information obtained via online forms or API requests.

[1592] Output: Production information stored in a database.

[1593] Step 2: Preprocessing

[1594] server

[1595] The server retrieves the stored production information from the database and performs preprocessing. Preprocessing includes data normalization, missing value completion, and outlier detection and removal. NumPy and Pandas are used to normalize the data and generate standardized data. Specifically, the server converts the fertilization timing (March and July) into a standardized numerical format and completes missing values ​​in the climate data with the average of past data.

[1596] Input: Production information retrieved from the database.

[1597] Output: The preprocessed dataset.

[1598] Step 3: Model analysis

[1599] server

[1600] The server inputs the preprocessed data into an AI model. The model used is trained using TensorFlow and PyTorch. The AI ​​model analyzes the optimal production method based on the input data. Specifically, it learns the relationship between weather conditions and yield, and derives the optimal fertilization schedule and pruning method.

[1601] Input: Preprocessed data.

[1602] Output: Analysis of optimal crop production methods.

[1603] Step 4: Generate and distribute optimal plans

[1604] server

[1605] Based on the analysis results, the server generates a specific crop production plan. This plan includes recommended cultivation methods, fertilization timing, and pest control measures. The generated plan is delivered to the user's device in JSON format. As a specific operation, the server generates a recommended plan to "apply ammonium nitrate fertilizer in March and July."

[1606] Input: Analysis results of the AI ​​model.

[1607] Output: The generated optimal plan.

[1608] Terminal

[1609] The terminal receives the optimal plan sent from the server and displays it on the application. The user produces crops based on this plan. Specifically, a new apple farmer begins cultivation based on the received plan.

[1610] Input: The optimal plan delivered by the server.

[1611] Output: The plan displayed on the terminal.

[1612] Step 5: Gather feedback and retrain

[1613] User

[1614] Users provide feedback to the server on the results of their work and the information they have gained during the process, including the yield, quality, and any problems they may have encountered. For example, an apple farmer might input, "After applying fertilizer in March, insect damage occurred."

[1615] Input: User feedback.

[1616] Output: Data sent to the server.

[1617] server

[1618] The server stores the feedback in a database and retrains the AI ​​model, which improves the accuracy of its suggestions. Specifically, it retrains the TensorFlow model using the new data.

[1619] Input: Feedback data from users.

[1620] Output: The updated AI model.

[1621] Step 6: Implementing the Emotion Engine

[1622] Server and Device

[1623] The server uses an emotion engine to analyze the user's emotions when entering feedback. If the user is facing a difficult situation, the emotion engine will provide specific solutions and specialist consultation options. The device will monitor the user's emotions in real time and provide encouraging messages if the user is feeling stressed. For example, if the user enters "I'm very worried" in the feedback, the emotion engine will analyze this, determine it as "anxiety," and provide additional support.

[1624] Input: User feedback, emotion data.

[1625] Output: Supportive information and messages based on emotional state.

[1626] (Application example 2)

[1627] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1628] Modern factories are required to improve production efficiency and reduce employee stress, but optimizing production schedules and managing machine maintenance remain challenges. Providing an efficient work environment that takes into account employee emotions is also important, but existing systems do not adequately address this issue.

[1629] 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.

[1630] In this invention, the server includes means for collecting production information from experienced farmers, means for saving the collected production information in a database, means for preprocessing the saved production information and inputting it into an AI model, means for analyzing using the AI ​​model, means for generating an optimal plan for fruit production based on the analysis results, means for distributing the generated optimal plan to users, means for collecting feedback from users, means for saving the collected feedback in a database and retraining the AI ​​model, and means for recognizing the emotional state of users and improving the optimal plan based on the analysis results. This makes it possible to optimize production schedules and provide an efficient work environment that takes employee emotions into consideration.

[1631] "Agricultural workers" refers to people who are engaged in agricultural work, especially those who have specialized knowledge and experience and work on producing crops.

[1632] "Production information" refers to detailed data on crop production, such as soil type, climatic conditions, fertilization timing, pruning methods, and pest and disease control measures.

[1633] A "database" refers to a system that can efficiently store, manage, and access large amounts of data.

[1634] "Preprocessing" refers to processes such as normalizing data, filling in missing values, and detecting and removing outliers, which are carried out to make the input data to an AI model analyzable.

[1635] An "AI model" refers to a system that uses artificial intelligence algorithms and machine learning techniques to analyze data, learn patterns, and make predictions and decisions.

[1636] "Analysis" refers to the process of extracting specific information and insights from collected data.

[1637] An "optimal plan" is a plan that proposes the most suitable methods and schedules for agricultural production based on the analysis results of an AI model.

[1638] "Delivery" refers to the process of transmitting the generated optimal plan to the user's terminal and making it available for use.

[1639] "Feedback" refers to information provided by users based on their practical results and experiences.

[1640] "Retraining" refers to the process of using collected feedback to retrain an AI model, improving its accuracy and the precision of its recommendations.

[1641] "Emotional state" refers to a user's psychological state or feeling, which is identified through text analysis and an emotion engine.

[1642] "Improvement" refers to the process of making changes or additions to existing plans or systems to make them more effective and improve their accuracy and usability.

[1643] A "system" is a set of multiple interrelated components and processes that function to achieve a specific purpose.

[1644] The present invention relates to a smart factory management application for optimizing factory management. The program processing of this system will be specifically described below.

[1645] Data collection and storage

[1646] The server collects production information from production equipment and facilities within the factory. This production information includes various sensor data, machine operating status, maintenance schedules, etc. The collected information is saved in the server's database in real time.

[1647] Data preprocessing and analysis

[1648] The server preprocesses the collected production information. This preprocessing includes data normalization, missing value completion, and outlier detection and removal. The preprocessed data is then input into an AI model. An example of the AI ​​model used here is RandomForestRegressor. This model analyzes the production information and generates an optimal production schedule and efficiency improvement plan.

[1649] Generating and delivering optimal plans

[1650] The server generates an optimal production plan based on the analysis results of the AI ​​model. This plan includes machine operation schedules, maintenance timing, efficient resource allocation, etc. The generated optimal plan is then distributed from the server to the user's device.

[1651] The user's device receives the optimal plan and presents it to the factory's monitoring system and manager. The user then carries out production activities based on this plan.

[1652] Gathering feedback and relearning

[1653] The user implements the proposed optimal plan and provides the results and information obtained during the process as feedback to the server, including production efficiency, problems, and areas for improvement.

[1654] The server stores the collected feedback in a database and retrains the AI ​​model to improve the accuracy of future suggestions. Retraining involves tuning the AI ​​model using the feedback data.

[1655] Introducing the Emotion Engine

[1656] The server is equipped with an emotion engine that recognizes the user's emotional state. The emotion engine uses text and voice analysis to determine the user's emotions. Once the emotional state is recognized, the server uses that information to further refine the optimal plan. This refinement can provide encouraging messages or additional support information if the user is facing a difficult situation.

[1657] Specific examples

[1658] For example, if equipment breakdowns occur frequently at a factory and employees are feeling stressed, the information is sent to the server through user feedback. The emotion engine recognizes the employee's stress level from this feedback and immediately provides suggestions for improvement and encouraging messages.

[1659] Example prompt sentence:

[1660] Generate plans to optimize maintenance frequency on production lines and reduce equipment breakdowns, plus add support messages if employees' stress levels are high.

[1661] In this way, the system of the present invention makes it possible to optimize production schedules and provide an efficient working environment that takes into account the emotions of employees.

[1662] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1663] Step 1:

[1664] The server collects production information from production equipment and facilities within the factory. This includes data obtained from sensors, machine operation status, maintenance schedules, etc. Input data is sent to the server in real time via API or sensor devices. The output is the collected production information stored in a database.

[1665] Step 2:

[1666] The server preprocesses the collected production information. The input is data obtained from the production information database. Data normalization, missing value imputation, and outlier detection and removal are performed. For example, missing values ​​are imputed using pandas and SimpleImputer, and data is normalized using StandardScaler. The output is the preprocessed data.

[1667] Step 3:

[1668] The server inputs the preprocessed data into an AI model for analysis. The input is the preprocessed data, and the output is the analysis results. The AI ​​model used is, for example, RandomForestRegressor, and analyzes the data to generate production schedules and efficiency plans.

[1669] Step 4:

[1670] The server generates an optimal production plan based on the analysis results. The input is the analysis results from the AI ​​model. The output is the generated optimal production plan, which includes machine operation schedules, maintenance timing, and efficient resource allocation.

[1671] Step 5:

[1672] The server distributes the generated optimal plan to the user's terminal. The input is the generated optimal production plan. The output is the distributed production plan, which the user uses to carry out production activities. The terminal displays the received production plan on the factory's monitoring system and to the manager.

[1673] Step 6:

[1674] The user implements the proposed optimal plan. The input is the delivered optimal plan. The results of the implementation and information obtained during the process are provided as feedback. The output is the collected feedback information.

[1675] Step 7:

[1676] The server stores the collected feedback information in a database and retrains the AI ​​model. The input is the feedback information. Retraining uses the feedback to tune the AI ​​model and improve the accuracy of its suggestions. The output is the retrained AI model.

[1677] Step 8:

[1678] The server analyzes the emotion from the feedback using an emotion engine that recognizes the user's emotional state. The input is the feedback text or voice data. The emotion engine performs text analysis to determine the user's emotion. The output is the recognized emotional state.

[1679] Step 9:

[1680] The server refines the optimal plan based on the recognized emotional state. The input is the emotional state recognized by the emotion engine and the existing optimal plan. For example, if the user is feeling stressed, it provides an encouraging message or additional support information. The output is the refined optimal plan.

[1681] Through the above processing steps, this system optimizes production schedules and provides an efficient working environment that takes into account the emotions of employees.

[1682] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[1683] 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.

[1684] 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 robot 414.

[1685] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1686] FIG. 9 is a diagram illustrating an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1687] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[1688] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[1689] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[1690] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[1691] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[1692] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[1693] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[1694] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[1695] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[1696] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[1697] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[1698] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific processing may be a single processor.

[1699] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[1700] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[1701] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[1702] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[1703] The following is further disclosed regarding the above embodiment.

[1704] (Claim 1)

[1705] a means of collecting production information from experienced farmers;

[1706] a means for storing the collected production information in a database;

[1707] A means for preprocessing the stored production information and inputting it into the AI ​​model;

[1708] A means of analysis using AI models,

[1709] means for generating an optimal plan for fruit production based on the analysis results;

[1710] A means for delivering the generated optimal plan to a user;

[1711] a means of collecting user feedback; and

[1712] A means to store the collected feedback in a database and retrain the AI ​​model;

[1713] A system including:

[1714] (Claim 2)

[1715] 2. The system according to claim 1, further comprising means for proposing a production plan suited to a specific region or condition based on information stored in the database.

[1716] (Claim 3)

[1717] 10. The system of claim 1, further comprising means for retraining the AI ​​model based on user feedback.

[1718] "Example 1"

[1719] (Claim 1)

[1720] a means of collecting production information from experienced farmers;

[1721] a means for storing the collected production information in a database;

[1722] A means for preprocessing the stored production information and inputting it into an AI technology model;

[1723] A means of analysis using AI technology models;

[1724] A means for generating an optimal plan for agricultural production based on the analysis results;

[1725] A means for delivering the generated optimal plan to a user;

[1726] a means of collecting user feedback; and

[1727] A means to store the collected feedback in a database and retrain the AI ​​technology model;

[1728] A system including:

[1729] (Claim 2)

[1730] 2. The system according to claim 1, further comprising means for proposing a production plan suited to a specific region or condition based on information stored in the database.

[1731] (Claim 3)

[1732] 10. The system of claim 1, further comprising means for retraining the AI ​​technology model based on user feedback.

[1733] "Application Example 1"

[1734] (Claim 1)

[1735] a means of collecting production information from experienced farmers;

[1736] a means for storing the collected production information in a database;

[1737] A means for preprocessing the stored production information and inputting it into the AI ​​model;

[1738] A means of analysis using AI models,

[1739] means for generating an optimal plan for fruit production based on the analysis results;

[1740] A means for applying the generated optimal plan to the production equipment;

[1741] A means of managing the fertilization and pruning performed by production equipment according to a schedule;

[1742] A means for production equipment to automatically carry out fertilization, pruning, and pest control;

[1743] A means for delivering the generated optimal plan to a user;

[1744] a means of collecting user feedback; and

[1745] A means to store the collected feedback in a database and retrain the AI ​​model;

[1746] A system including:

[1747] (Claim 2)

[1748] 2. The system according to claim 1, further comprising means for proposing a production plan suited to a specific region or condition based on information stored in the database.

[1749] (Claim 3)

[1750] 10. The system of claim 1, further comprising means for retraining the AI ​​model based on user feedback.

[1751] "Example 2: Combining Emotion Engines"

[1752] (Claim 1)

[1753] a means of collecting production information from experienced farmers;

[1754] a means for storing the collected production information in a database;

[1755] A means for preprocessing the stored production information and inputting the preprocessed information into an analysis device;

[1756] means for performing analysis by an analysis device;

[1757] A means for generating an optimal plan for crop production based on the analysis results;

[1758] A means for delivering the generated optimal plan to a user;

[1759] a means of collecting user feedback; and

[1760] a means for storing the collected feedback in a database and retraining the analyzer;

[1761] a means for analyzing an emotional state;

[1762] means for refining the optimal plan based on emotional state;

[1763] a means for monitoring user emotions in real time during crop production;

[1764] A system including:

[1765] (Claim 2)

[1766] 2. The system according to claim 1, further comprising means for proposing a production plan suited to a specific region or condition based on information stored in the database.

[1767] (Claim 3)

[1768] 10. The system of claim 1, further comprising means for retraining the analyzer based on user feedback.

[1769] "Application example 2 when combining emotion engines"

[1770] (Claim 1)

[1771] a means of collecting production information from experienced farmers;

[1772] a means for storing the collected production information in a database;

[1773] A means for preprocessing the stored production information and inputting it into the AI ​​model;

[1774] A means of analysis using AI models,

[1775] means for generating an optimal plan for fruit production based on the analysis results;

[1776] A means for delivering the generated optimal plan to a user;

[1777] a means of collecting user feedback; and

[1778] A means to store the collected feedback in a database and retrain the AI ​​model;

[1779] means for recognizing the user's emotional state and refining the optimal plan based on the analysis results;

[1780] A system including:

[1781] (Claim 2)

[1782] 2. The system according to claim 1, further comprising means for proposing a production plan suited to a specific region or condition based on information stored in the database.

[1783] (Claim 3)

[1784] 10. The system of claim 1, further comprising means for retraining the AI ​​model based on user feedback. [Explanation of symbols]

[1785] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. a means of collecting production information from experienced farmers; a means for storing the collected production information in a database; A means for preprocessing the stored production information and inputting it into the AI ​​model; A means of analysis using AI models, means for generating an optimal plan for fruit production based on the analysis results; A means for delivering the generated optimal plan to a user; a means of collecting user feedback; and A means to store the collected feedback in a database and retrain the AI ​​model; A system including:

2. 2. The system according to claim 1, further comprising means for proposing a production plan corresponding to a specific region or condition based on information stored in the database.

3. 10. The system of claim 1, further comprising means for retraining the AI ​​model based on user feedback.

Images