system

Abstract

We provide the system. [Solution] A processing means for analyzing market demand and weather conditions for agricultural products using a generative model, and for generating a cultivation plan for agricultural products. A method for receiving investment information from users, comparing it with information on abandoned farmland, and selecting the most suitable farmland, A means of applying a cultivation plan to selected farmland, calculating profits, and distributing those profits to users, A system that includes this.

Description

Technical Field

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

Background Art

[0002] Patent Document 1 discloses a method for controlling a persona chatbot, which is performed by at least one processor, including the steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to the 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

Summary of the Invention

Problems to be Solved by the Invention

[0004] Due to population decline and depopulation, the number of abandoned cultivated lands that are left unused is increasing. There is a need to build a new platform that reutilizes this unused agricultural land and links agriculture with personal investment. In existing systems, it is not possible to sufficiently predict the demand for agricultural products and analyze weather conditions, making it difficult to manage agricultural land efficiently and distribute profits. Furthermore, there is a problem that support for investment judgment and farmland selection is insufficient for those who have no experience in agriculture.

Means for Solving the Problems

[0005] This invention provides a system that uses a generative model to analyze market demand and weather conditions for agricultural products and provides users with an optimal cultivation plan. Specifically, firstly, it uses a generative model to analyze market and weather data and generate demand forecasts and cultivation plans for agricultural products. Secondly, based on the user's investment information, it selects the most suitable farmland from abandoned farmland and applies an appropriate cultivation plan. Thirdly, it calculates the revenue from agricultural product sales after harvest and distributes the revenue according to the user, thereby solving these problems. Furthermore, it provides a learning platform based on the generative model for those with no prior agricultural experience and offers educational support through agricultural experience.

[0006] A "generative model" is a machine learning algorithm used for data analysis and prediction, and specifically refers to a mathematical model used to learn new data patterns and generate effective predictions.

[0007] "Market demand" is an indicator that shows the trend in demand for a particular agricultural product, indicating how much quantity consumers and distributors are seeking in a given market.

[0008] "Weather conditions" refer to the combination of climatic factors such as temperature, precipitation, and sunshine hours that affect cultivation, and are environmental elements that play an important role in the growth of agricultural crops.

[0009] A "cultivation plan" refers to a detailed plan for carrying out a series of agricultural tasks, such as sowing seeds, fertilizing, irrigating, and harvesting crops, at the optimal timing and in the most appropriate manner.

[0010] "Abandoned farmland" refers to agricultural land that was originally used for agricultural production but is now not being cultivated and is left neglected.

[0011] A "user" refers to an individual or organization that makes agricultural investments using this system and is the entity that makes investment decisions on a project-by-project basis.

[0012] "Profit sharing" refers to the act of fairly distributing the profits obtained from the sale of agricultural products to stakeholders according to their investment amount and contribution.

[0013] A "learning platform" refers to an online environment for educational support provided to people with no prior experience or beginners in agriculture, enabling them to acquire knowledge and skills. [Brief explanation of the drawing]

[0014] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Figure 11] This is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] This is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13]It is a sequence diagram showing the processing flow of the data processing system in Embodiment 2 when the emotion engine is combined. [Figure 14] It is a sequence diagram showing the processing flow of the data processing system in Application Example 2 when the emotion engine is combined.

Mode for Carrying Out the Invention

[0015] Hereinafter, an example of an embodiment of the system according to the technology of the present disclosure will be described with reference to the accompanying drawings.

[0016] First, the terms used in the following description will be explained.

[0017] In the following embodiments, a numbered processor (hereinafter simply referred to as "processor") may be one arithmetic unit or a combination of multiple arithmetic units. Also, the processor may be one type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), and the like.

[0018] In the following embodiments, a numbered RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0019] In the following embodiments, a numbered storage is one or more non-volatile storage devices that store various programs and various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes, and the like.

[0020] In the following embodiments, the signed communication interface (I / F) is an interface that includes a communication processor and an antenna, etc. The communication interface manages communication between multiple computers. Examples of communication standards applicable to the communication interface include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0021] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." That is, "A and / or B" means that it may be A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or."

[0022] [First Embodiment]

[0023] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0024] As shown in Figure 1, the 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.

[0025] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0026] The smart device 14 comprises a computer 36, a reception device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The reception device 38, output device 40, and camera 42 are also connected to the bus 52.

[0027] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and 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.

[0028] 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 perceptible to the user 20 (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0029] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

[0030] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0031] As shown in Figure 2, in the data processing device 12, a specific processing 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" related to the technology of this 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 according to the specific processing program 56 executed on the RAM 30.

[0032] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0033] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with a 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0034] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0035] This invention provides a system that enables effective management and investment in agriculture using generative models. Embodiments of this system are described in detail below.

[0036] User registration and profile settings:

[0037] Users create a profile by entering information about their interests, investment capabilities, and agricultural experience through a dedicated application. The terminal receives this information, performs the necessary data validation, and then sends it to the server. The server stores this data in a database and uses it for subsequent analysis and recommendations.

[0038] Market and weather data collection:

[0039] The server collects market and weather data from external data providers via APIs. Market data includes price trends and consumption patterns for agricultural products, while weather data includes future temperatures, precipitation, and sunshine duration. The server analyzes this data, which is then used by generative models for later predictions.

[0040] Gathering information on abandoned farmland:

[0041] The server collects information about abandoned farmland from public databases and municipal records. This includes information such as land size, soil quality, and proximity to water sources. The server uses this information to create a list of available farmland.

[0042] Demand forecasting and crop recommendations:

[0043] The server uses a generative model to analyze collected market and weather data and forecast demand for agricultural projects. This generates specific suggestions on which crops should be cultivated. Based on the user's profile information, a list of the most suitable crops is generated and presented to the user.

[0044] Farmland selection and investment decision-making:

[0045] The user makes investment decisions based on the presented list of crops. Based on the selected crops, the server selects the most suitable abandoned farmland and provides that information to the user. The user then chooses a specific plot of land and decides to invest in it.

[0046] Agricultural planning and management:

[0047] The server utilizes generative models to create a cultivation plan tailored to the selected farmland and crops. This plan includes sowing dates, irrigation schedules, and fertilization plans. Detailed steps are provided to the user via a terminal to support the execution of the plan.

[0048] Profit sharing:

[0049] The harvested crops are sold at the optimal price based on market analysis. The server calculates the sales and distributes the profits according to the user's investment amount. Information regarding profit distribution is notified to the user via their terminal.

[0050] This system enables users to make appropriate investment decisions and achieve effective agricultural management. This promotes the utilization of unused, abandoned farmland and generates sustainable agricultural revenue.

[0051] The following describes the processing flow.

[0052] Step 1:

[0053] The user opens the application and registers. The user enters details such as their name, contact information, investment amount, and agricultural experience. The terminal receives the entered information, validates the data, and then sends it to the server. The server stores the received information in a database and creates a user profile.

[0054] Step 2:

[0055] The server continuously collects information on price trends and demand patterns in the agricultural market using APIs from external data providers. Simultaneously, weather data includes predicted future temperatures, precipitation, and sunshine duration. This data is stored in a database and prepared for use in generative models.

[0056] Step 3:

[0057] The server collects information on abandoned farmland from local government and public databases. This information includes the location, size, soil quality, and proximity to water sources. The server organizes this data and builds datasets to identify usable farmland.

[0058] Step 4:

[0059] The server uses collected market and weather data to run a generative model and predict future demand for agricultural products. The generated demand forecast shows the market opportunity for specific crops. Based on this information, the server creates a list of crops best suited to the user's profile and sends it to the terminal.

[0060] Step 5:

[0061] The terminal displays investment candidates based on a list of crops and demand forecast data received from the server. The user reviews the list and selects which project to invest in. Once the user makes a decision, that information is sent from the terminal to the server.

[0062] Step 6:

[0063] Based on the user's selection, the server executes a process to select the most suitable abandoned farmland. It filters the data of available land, selects the land best suited for crop cultivation, and proposes it to the user. Once the user reviews the proposal and selects the land, the server records the information and supports the contract procedures.

[0064] Step 7:

[0065] The server creates an optimal farming plan for the selected farmland. This plan includes details such as crop planting, fertilization, irrigation schedules, and harvest plans. The server sends this plan to the terminal, providing the user with a detailed implementation guide.

[0066] Step 8:

[0067] As harvest time approaches, the server re-analyzes market data to determine the optimal timing and channels for sales. The harvested crops are then shipped to market based on the generated sales strategy.

[0068] Step 9:

[0069] The server calculates the total sales revenue of agricultural products and distributes the profits based on the user's investment amount. Details of the profit distribution are notified to the user via their terminal, and the user receives their share of the profits.

[0070] This will enable the system to efficiently utilize abandoned farmland and support the maximization of profits in agricultural projects.

[0071] (Example 1)

[0072] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0073] Conventional agricultural management systems make it time-consuming to forecast individual market demand and select appropriate farmland, and it is difficult to create highly profitable cultivation plans. This has resulted in challenges such as the ineffective utilization of abandoned farmland and insufficient profit distribution to users. To solve these problems, there is a need to provide a system that efficiently analyzes market data and weather information to support optimal crop cultivation and profit management.

[0074] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0075] In this invention, the server includes a computation means for analyzing market demand and weather conditions for agricultural products using a generative model and generating a crop cultivation plan; a means for receiving investment information from users and matching it with information on abandoned farmland to select the optimal farmland; and an information processing means for applying the cultivation plan using the generative model to the selected farmland and supporting the execution of the plan. This enables the efficient proposal of highly profitable agricultural projects, promotes the utilization of abandoned farmland, and allows for profit sharing with users.

[0076] A "generative model" is a model that uses machine learning algorithms to analyze information collected from diverse data sources and generate specific predictions or suggestions.

[0077] "Market demand" refers to information that indicates consumers' willingness to purchase and purchasing trends for specific agricultural products.

[0078] "Weather conditions" refer to information that indicates meteorological factors such as temperature, precipitation, and sunshine duration in a specific region.

[0079] A "cultivation plan" is a detailed action plan for growing a specific crop, including sowing dates, irrigation schedules, and fertilization plans.

[0080] A "user" refers to someone who uses the system, inputs investment information, and receives proposals and management for agricultural projects.

[0081] "Abandoned farmland" refers to agricultural land that was previously cultivated but is no longer in use.

[0082] "Revenue calculation" is the process of calculating the income generated as a result of a specific agricultural project and distributing it to the stakeholders.

[0083] The system implementing this invention mainly includes a server, a terminal, and a user interface. Each process is as follows:

[0084] Data processing by the server

[0085] The server has means of collecting market and weather data from external data providers via APIs. This allows it to obtain information on the latest market trends and weather conditions. The collected data is analyzed using a generative AI model to develop demand forecasts for agricultural products and optimal cultivation plans. The server stores these generated results and provides them to users as needed.

[0086] User and device interface

[0087] Users access the system using a dedicated application and input information about their interests, investment capabilities, and agricultural experience. This information is received at the terminal, validated, and then sent to the server. The server uses this information to generate a user profile, which is then used to suggest future agricultural projects.

[0088] Specific example

[0089] If a user has an investment limit of 1 million yen and is interested in wheat cultivation, they register this information in the system. This information is sent to the server, and based on the generated AI model, if wheat cultivation is predicted to be highly profitable, the server presents the user with an appropriate cultivation plan and the most suitable farmland.

[0090] Example of a prompt

[0091] "My available investment is 1 million yen, and I'm interested in growing wheat, but I'm a beginner. Please propose a suitable farming plan based on these conditions."

[0092] This allows users to receive specific farming plans based on certain conditions, enabling them to make rational investment decisions and select farmland. The system promotes the utilization of unused, abandoned farmland and makes it possible to generate sustainable agricultural revenues.

[0093] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0094] Step 1: User registration and data entry

[0095] Users input information about their interests, investment capabilities, and agricultural experience using a dedicated application. The terminal receives this information and performs data validation. Specifically, it checks if the entered investment amount is a numerical value and verifies that agricultural experience is entered in a selection format. The output of this step is sent to the server as validated user information.

[0096] Step 2: Data Collection

[0097] The server collects market and weather data using APIs from external data providers. Inputs include up-to-date agricultural product price information, consumer trends, and weather forecast data. The server receives this data and stores it in a database. This information is used as input for a generative AI model. The output is raw data ready for analysis.

[0098] Step 3: Analysis using generative models

[0099] The server inputs user profiles, collected market data, and weather data into a generative AI model. The generative model analyzes these inputs to forecast demand for agricultural products. Specifically, it uses machine learning algorithms to predict future demand trends from historical data. The output is a list of agricultural products recommended to the user.

[0100] Step 4: Farmland Selection

[0101] The server selects suitable farmland from a database of abandoned land based on the crops chosen by the user. This process considers factors such as land location, soil quality, and proximity to water sources. The input is the user's selected crop information, and the output is a list of suitable farmland.

[0102] Step 5: Cultivation plan and implementation support

[0103] The server utilizes a generation AI model to create a cultivation plan suitable for the selected crops. Specifically, it includes details such as sowing time, irrigation schedule, and fertilization plan. The cultivation plan is provided to the user via a terminal, along with instructions on how to implement the plan. The input is data on the selected farmland and crops, and the output is a specific cultivation plan.

[0104] Step 6: Profit Calculation and Distribution

[0105] The server sells harvested crops at the optimal price based on market data. The calculation uses harvest yield, selling price, and cost structure as inputs to determine sales and profits. The output is revenue information distributed to users, which is notified to users via their terminals.

[0106] (Application Example 1)

[0107] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0108] A challenge in modern urban areas is that abandoned farmland is left unattended and not utilized for sustainable agricultural activities. Furthermore, urban residents have limited opportunities to participate in agricultural projects, making effective cultivation management difficult. This invention aims to provide a system that supports urban residents and enables the efficient use and monetization of underutilized land.

[0109] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0110] This invention includes a server that includes processing means for analyzing market demand and weather conditions for agricultural products using a generative model and generating a crop cultivation plan; means for receiving investment information from users and selecting optimal farmland by comparing it with information on abandoned farmland; means for applying the cultivation plan to the selected farmland, calculating profits, and distributing profits to users; and support means for urban residents to participate in agricultural projects through smart devices and manage the efficient use of abandoned farmland. This enables urban residents to easily participate in sustainable agricultural projects and to utilize unused land for effective agricultural management and profit generation.

[0111] A "generative model" is an algorithm that automatically generates new data and predictions based on a vast amount of existing data.

[0112] "Market demand" refers to the total quantity of goods that consumers in a particular market wish to purchase during a given period.

[0113] "Meteorological conditions" refer to atmospheric conditions such as weather, temperature, and precipitation in a specific region or period.

[0114] "Agricultural products" refer to plants and food produced through agriculture.

[0115] A "cultivation plan" is a detailed set of instructions for determining the timing and methods for efficiently growing a specific crop.

[0116] "Investment information" refers to financially relevant data and information necessary for decision-making that a user possesses about an investment target.

[0117] "Abandoned farmland" refers to land that was once used as agricultural land but is no longer in use.

[0118] "Urban residents" is a term that refers to citizens who live in urban areas.

[0119] "Smart devices" are a general term for electronic devices that have internet connectivity and allow users to obtain and manipulate information.

[0120] "Efficient use" means making the most of limited resources and time to achieve one's goals.

[0121] "Profit calculation" is the process of calculating the profits that can be obtained from a particular business or investment activity.

[0122] "Support measures" refer to methods and techniques that provide support to ensure that a particular task can be performed smoothly.

[0123] This invention provides a system that enables urban residents to invest in and participate in agricultural projects by utilizing generative models. The server first creates a profile based on investment information obtained from the user, which is entered via a dedicated smart device. Next, it analyzes market and weather data collected from multiple external data providers to predict market demand for agricultural products. This process utilizes a generative AI model equipped with machine learning algorithms. This allows for the selection of the most suitable crops for the user and the generation of a cultivation plan.

[0124] The terminal presents the generated cultivation plan to the user and selects the most suitable farmland by comparing it with information on abandoned farmland. At this stage, the user can select a specific plot of land and make an investment decision. After selection, the server applies the cultivation plan, calculates the profits, and distributes the profits to the user. This entire process functions as a means of realizing sustainable agriculture within a smart city.

[0125] As a concrete example, let's say person A, who lives in an urban area, accesses an application using their smartphone. Through the app, they register their investment capabilities and interests and participate in a tomato cultivation project on unused land in the suburbs. The app provides them with weather data and market trends, indicating that the land is suitable for tomato cultivation. They then participate in the project, and ultimately, the profits are distributed according to their investment.

[0126] A concrete example of a prompt for a generative model might be, "What is the best time and management method for growing tomatoes in an urban area?" This prompt prompts the system to provide a cultivation plan suitable for the given environment.

[0127] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0128] Step 1:

[0129] The server receives investment information transmitted from users via smart devices. This includes inputting the user's interests, investment capabilities, and agricultural experience. This data is stored in a database and used to generate profiles.

[0130] Step 2:

[0131] The server collects market and weather data from external data providers via APIs. This process obtains data on agricultural product price trends, consumption patterns, and weather conditions. Based on the collected data, a generative AI model makes market demand forecasts.

[0132] Step 3:

[0133] The generative AI model analyzes market and weather data to generate a list of optimal crops based on the user's profile. When prompted with "Please suggest crops suitable for cultivation under specific market and weather conditions," the analysis results will output a suggested list.

[0134] Step 4:

[0135] The terminal presents the user with a list of generated crops and prompts them to make a selection. The user chooses the crops they wish to cultivate from the presented list and makes an investment decision. At this time, based on the specifications of the selected crops, the system presents the most suitable abandoned farmland from the server.

[0136] Step 5:

[0137] The server generates a cultivation plan based on the user's selections. This plan specifically designs the sowing period, irrigation schedule, and fertilization plan. This plan is then provided to the user's terminal to assist with its implementation.

[0138] Step 6:

[0139] Users carry out agricultural activities based on the cultivation plan displayed on their terminal. Progress at each step is fed back to the server via the terminal, and the plan is adjusted as needed.

[0140] Step 7:

[0141] After harvesting, the server sells the crops at the optimal price based on market analysis. Profit calculations are performed, and the profits are distributed according to the user's investment. This result is then notified to the user's device.

[0142] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0143] This invention aims to build a system that provides a personalized experience tailored to the user's emotions by incorporating an emotion engine into an agricultural investment platform. The embodiments of this system are described in detail below.

[0144] User registration and profile settings:

[0145] Users access the application through their device and register. They fill in profile information, including their emotional state, and register their investment capabilities and interests with the system. The device sends this information to the server. The server stores the received information in a database and creates individual user profiles.

[0146] Collection and analysis of market and weather data:

[0147] The server uses APIs from external data providers to collect data on agricultural market trends and weather conditions. This data is stored in a database and analyzed by a generative model. Based on the collected data, the generative model predicts market demand and prepares agricultural cultivation suggestions for the user.

[0148] How the emotion engine works:

[0149] The emotion engine analyzes information and operation history entered from the user's device to infer the user's emotional state. Based on this inference, the server adjusts the interface and content to present information in a way that is most acceptable to the user.

[0150] Suggestions and choices for the user:

[0151] The server incorporates emotional data analyzed by the emotion engine to propose a customized list of crops and a cultivation plan to the user. The user receives these proposals through their terminal and decides on their investment. Throughout this process, the emotion engine monitors the user's responses in real time and adjusts the proposals as needed.

[0152] Investment decision support:

[0153] The emotion engine fine-tunes the feedback method to make the user more receptive to the cultivation plan they have chosen. For example, if a user is feeling anxious, it helps to increase their sense of security by providing detailed information about the risks and benefits of the investment.

[0154] Revenue sharing and learning platform:

[0155] When revenue is generated, the server calculates the revenue and distributes it to the user. The distribution results are notified to the user via their device. In addition, the emotion engine updates learning content based on the user's interests and emotional state, supporting continuous education about agriculture.

[0156] For example, if a user is feeling anxious about their first agricultural investment, the emotion engine can recognize that emotion and add reassuring supplementary information to make suggestions. This allows users to make investment decisions with greater confidence and provides an agricultural experience tailored to their individual needs.

[0157] The following describes the processing flow.

[0158] Step 1:

[0159] Users access the application through their device and register. They enter information such as their name, contact details, investment intentions, and emotional tendencies. The device sends this information to the server, which stores it in a database and generates a user profile.

[0160] Step 2:

[0161] The server periodically collects market and weather data through APIs from external data providers. Market data includes price trends and demand forecasts for agricultural products, while weather data includes temperature, precipitation, and sunshine duration. The server analyzes this data using generative models and makes demand forecasts based on these analyses.

[0162] Step 3:

[0163] The server activates an emotion engine and analyzes the user's emotional state based on past operation logs obtained from the user's terminal and directly entered emotional information. The analysis results are reflected in the user's profile and used to make future suggestions.

[0164] Step 4:

[0165] The server creates a list of crops and an investment plan based on the collected data and analysis results. This list includes the optimal crops reflecting the current market conditions and is structured to present information in a way that suits the user's emotional state. The server then sends this information to the terminal.

[0166] Step 5:

[0167] The terminal displays a list of crops and investment plans sent from the server to the user. Based on the analysis results of the emotion engine, the order of the displayed content and the level of detail in the explanations are adjusted. The user reviews this, selects projects that interest them, and decides to invest.

[0168] Step 6:

[0169] The server receives the user's selection and identifies the most suitable abandoned farmland. The selection is based on crop characteristics, land conditions, and the user's investment strategy. Detailed information about the proposed farmland is sent to the terminal for the user to review.

[0170] Step 7:

[0171] The server creates an optimal cultivation plan for the selected farmland based on a generative model. This plan includes sowing, fertilization, and irrigation schedules, enabling real-time agricultural management. The server sends the plan to the terminal, prompting the user to execute it.

[0172] Step 8:

[0173] As harvest time approaches, the server re-evaluates market and weather data to determine the optimal sales strategy. The emotion engine takes into account the user's current emotional state and presents information in a way that minimizes stress.

[0174] Step 9:

[0175] The server compiles sales results, calculates revenue, and distributes it to users based on prior investment information. The terminal notifies users of the distribution results and supports the process of depositing the revenue into their accounts. The emotion engine monitors user satisfaction and provides feedback.

[0176] This will enable the creation of a personalized agricultural investment platform tailored to each individual user.

[0177] (Example 2)

[0178] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0179] In modern agricultural investment, there is a need for systems that enable users to effectively utilize diverse market and weather data and make investment decisions based on their individual emotional states. However, properly analyzing this data and providing users with the most relevant information is not easy. In particular, providing a personalized experience that takes user emotions into account is not yet fully realized with current technology.

[0180] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0181] This invention includes a server that uses a generative model to analyze market demand and weather conditions for agricultural products and generates a crop cultivation plan; a server that receives investment information from users and matches it with information on abandoned farmland to select the optimal farmland; and a server that uses an emotion engine to analyze the user's emotional state and adjust the user interface and content accordingly. This enables the user to receive personalized investment suggestions based on their emotions and make investment decisions with confidence.

[0182] A "generative model" is a technique that uses machine learning algorithms to analyze market data and weather data obtained from multiple data sources and generate outputs that are aligned with a specific purpose.

[0183] An "emotion engine" is a technology that analyzes a user's operation history and input information to infer the user's emotional state and then individually adjusts information content and user interfaces based on that.

[0184] "Investment information" refers to individual data that users provide when making agricultural investments, such as the amount of funds and the investment targets.

[0185] "Abandoned farmland" refers to agricultural land that was once cultivated but is no longer in use, and it serves as a source of information for selecting land suitable for new cultivation activities.

[0186] A "customized crop list" is a list of recommended crops generated by the emotion engine and individually created based on the user's emotions and interests.

[0187] This invention provides a system that enables users to make efficient and emotion-based agricultural investments. Specifically, it combines a generative AI model and an emotion engine to provide users with personalized cultivation plans and investment suggestions.

[0188] The server automatically collects data on agricultural market trends and weather conditions using APIs from external data providers. This data is analyzed using a generative AI model to help generate market demand forecasts and crop cultivation plans. The generative AI model learns from information gathered from various data sources and provides optimal output.

[0189] Users input information about their emotional state and investment capabilities through their devices and send it to the server. The emotion engine analyzes the input from the device and the user's operation history to infer the user's emotional state. Based on this inference, the server adjusts the information content and user interface to facilitate effective communication.

[0190] Furthermore, the system has a function to select farmland suitable for the user by integrating information on abandoned farmland. A generated cultivation plan is applied to the selected farmland, and profit calculations are performed based on that plan. If profits are generated, they are then distributed to the user.

[0191] For example, if a user making their first agricultural investment feels anxious, the emotion engine effectively captures this emotion. The server then provides detailed information about the investment's risks and benefits to reassure the user, supporting them in making a confident decision. In this way, flexible investment suggestions tailored to the user's emotions become possible.

[0192] An example of a prompt to input into the generating AI model is: "Based on the latest agricultural market data, please propose a cultivation plan for the next season. Also, please consider crops the user has shown interest in in the past and provide additional information that the emotion engine should add to alleviate the user's concerns."

[0193] Therefore, this invention can provide an emotion-based, personalized agricultural investment experience.

[0194] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0195] Step 1:

[0196] Users access the application and register through their devices. Input information includes data on the user's emotional state, investment capacity, and interests. This input information is organized by the device and sent to the server. The server receives the data and stores it in a database to create a user profile. This profile forms the basis for future personalized recommendations.

[0197] Step 2:

[0198] The server collects market and weather data using APIs from external data providers. This input data includes information on current market trends and weather conditions. The server stores this data in a database and performs analysis using a generative AI model. Specifically, it generates market demand forecasts and crop cultivation plans based on the data. The output provides forecast information and data necessary for recommendations.

[0199] Step 3:

[0200] The emotion engine receives operation history and emotion information entered from the user's device and analyzes the user's emotional state. This analysis infers the user's emotional state. Based on this inference, the server processes the data to adjust the user interface and the information presented. For example, the order in which information is presented, the colors used, and the font size may be changed.

[0201] Step 4:

[0202] The server incorporates information analyzed by the emotion engine to generate a personalized list of crops and a cultivation plan for each user. Emotional data and predictive information from the generative AI model are used as input. As output, suggestions are created for the user and sent to them via their device.

[0203] Step 5:

[0204] The user receives suggestions from their device and makes an investment choice. The emotion engine monitors the user's reactions in real time as they make their choice, adjusting the suggestions and presentation methods as needed. The output records the final decision based on the user's selection.

[0205] Step 6:

[0206] The server calculates profits based on the selected cultivation plan. It uses projected profits and risk assessments as input data to calculate detailed investment results. The resulting profit information is distributed to the user and notified via their device. Furthermore, the emotion engine updates learning content based on the user's emotional state, supporting continuous education for future investments.

[0207] (Application Example 2)

[0208] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as a "server" and the smart device 14 as a "terminal".

[0209] Modern agricultural investment systems require the provision of personalized investment experiences that take into account the individual emotional states of investors. However, conventional systems struggle to provide dynamic suggestions that consider investors' emotions, limiting improvements in the user experience. Therefore, more effective support is needed to enable investors to make investment decisions with confidence.

[0210] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0211] This invention includes a server that uses a generative model to analyze market demand and weather conditions for agricultural products and generates a crop cultivation plan; a server that receives investment information from users and matches it with information on abandoned farmland to select the optimal farmland; and a server that analyzes the user's emotional state, personalizes crop choices based on that, provides real-time emotional feedback, and supports investment decision-making. This enables individualized responses tailored to the user's emotions, making it possible to support safer and more efficient investment decision-making.

[0212] A "generative model" is a system that uses various algorithms and data to create or analyze new information.

[0213] "Market demand" is an indicator that shows the degree of consumer and industry willingness to purchase a particular agricultural product.

[0214] "Weather conditions" refer to atmospheric conditions such as temperature, precipitation, wind speed, and humidity, and are factors that have a significant impact on agricultural production.

[0215] A "cultivation plan" is a detailed plan that specifies which crops to cultivate and how to cultivate them on a particular plot of land.

[0216] "Investment information" refers to information that shows how much money a user will invest and how they will invest it in the agricultural sector.

[0217] "Abandoned farmland" refers to agricultural land that was previously cultivated but has been abandoned for some reason and is no longer in use.

[0218] Personalization is the act of adjusting and optimizing suggestions and services based on an individual's characteristics and preferences.

[0219] "Profit calculation" is the process of quantifying and calculating the profits and losses obtained from a particular investment activity.

[0220] An "emotional state" refers to a set of psychological and physiological responses that an individual experiences at a particular moment.

[0221] "Investment decision support" refers to support activities that provide information and feedback to help users make better investment choices.

[0222] As an embodiment for carrying out this invention, the configuration and operation of a system using an electronic computer will be described.

[0223] First, the server uses a generative model to collect market and weather data from multiple data sources and uses this data to predict market demand for agricultural products. Typically, APIs from external data providers are used to collect market data. The collected data is stored in a database and analyzed by machine learning algorithms. The results of this analysis are then used to generate cultivation plans for the user.

[0224] Users access the system from devices such as smartphones and input their investment information. The data entered on the device is sent to a server and cross-referenced with information on abandoned farmland. This allows for the selection of the most suitable farmland and the creation of a cultivation plan tailored to the user.

[0225] Furthermore, the device uses its built-in camera to analyze the user's emotional state in real time. This emotional analysis utilizes facial recognition and voice analysis technologies to capture the user's feelings. Based on the emotional state, the service content and presentation methods are personalized, providing the user with a selection of agricultural products that are suitable for them.

[0226] If a user agrees with the proposal, they can quickly invest funds using an electronic payment API. The profits resulting from the investment are calculated through a profit calculation process and distributed to the user.

[0227] For example, if the emotion engine analyzes that a user is in a relaxed mood on holiday, it will suggest a low-risk, small-scale investment plan and provide basic educational content about agriculture (for example, a video introducing the crop growing process).

[0228] Examples of prompts for a generative AI model include:

[0229] "Based on an analysis of the user's current emotional state, which is relaxed, please suggest a recommended low-risk agricultural investment plan."

[0230] These are some examples.

[0231] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0232] Step 1:

[0233] The server uses APIs from external data providers to collect market and weather data. The input is data retrieved from the API, and the output is a well-organized dataset. Before being stored in the database, the data undergoes preprocessing, including format conversion and imputation of missing values.

[0234] Step 2:

[0235] The server uses a generative model to analyze collected market and weather data. The input is a pre-processed dataset, and the output is forecast information about future market demand. Machine learning algorithms are used for the analysis, including multivariate and time series analysis.

[0236] Step 3:

[0237] The user enters their investment information from the terminal. This information includes the user's investment amount, risk tolerance, and types of crops they are interested in, and the output is user profile information. The terminal sends the entered information to the server and updates the profile.

[0238] Step 4:

[0239] The server selects the most suitable farmland based on the user profile. Inputs are user profiles and data on abandoned farmland, while output is information on the selected farmland. This process utilizes a Geographic Information System (GIS) for map analysis.

[0240] Step 5:

[0241] The device uses its built-in camera to analyze the user's emotional state. The input is real-time image data, and the output is an estimated emotional state (e.g., relaxed, excited, anxious). It utilizes an emotion analysis library to analyze emotions from facial expressions and voice.

[0242] Step 6:

[0243] The server proposes a personalized cultivation plan based on estimated emotional states and user profiles. Inputs are emotional states, user profiles, and predicted market demand; output is the proposed agricultural investment plan. A generative AI model is used to develop appropriate crop selections and investment plans.

[0244] Step 7:

[0245] The user reviews the proposal and decides whether to invest. The input is the proposed investment plan, and the output is the instruction to execute the investment. The user reviews it on their terminal and prepares to make the payment.

[0246] Step 8:

[0247] The server uses an electronic payment API to execute user investments and complete transactions. Input is the user's payment information, and output is a transaction completion notification. A secure communication protocol is used for the payment process.

[0248] Step 9:

[0249] The server calculates profits and distributes them to users. Inputs are investment results and market data, and output is a notification of profit results to users. A profit distribution algorithm is used to ensure fair distribution.

[0250] Step 10:

[0251] The device updates and provides learning content to the user based on their emotional state. The input is the updated emotional state and learning history, and the output is new educational content. An educational plan is then executed using a generative AI model.

[0252] 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 user input for the result of the specific processing. The control unit 46A transmits the audio data indicating 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.

[0253] Data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0254] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart device 14.

[0255] [Second Embodiment]

[0256] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0257] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0258] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0259] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0260] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0261] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0262] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0263] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0264] The specific processing program 56 is an example of a "program" relating to the technology of this 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.

[0265] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0266] In the smart glasses 214, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0267] Next, the identification processing performed by the identification processing unit 290 of the data processing device 12 will be described. 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".

[0268] This invention provides a system that enables effective management and investment in agriculture using generative models. Embodiments of this system are described in detail below.

[0269] User registration and profile settings:

[0270] Users create a profile by entering information about their interests, investment capabilities, and agricultural experience through a dedicated application. The terminal receives this information, performs the necessary data validation, and then sends it to the server. The server stores this data in a database and uses it for subsequent analysis and recommendations.

[0271] Market and weather data collection:

[0272] The server collects market and weather data from external data providers via APIs. Market data includes price trends and consumption patterns for agricultural products, while weather data includes future temperatures, precipitation, and sunshine duration. The server analyzes this data, which is then used by generative models for later predictions.

[0273] Gathering information on abandoned farmland:

[0274] The server collects information about abandoned farmland from public databases and municipal records. This includes information such as land size, soil quality, and proximity to water sources. The server uses this information to create a list of available farmland.

[0275] Demand forecasting and crop recommendations:

[0276] The server uses a generative model to analyze collected market and weather data and forecast demand for agricultural projects. This generates specific suggestions on which crops should be cultivated. Based on the user's profile information, a list of the most suitable crops is generated and presented to the user.

[0277] Farmland selection and investment decision-making:

[0278] The user makes investment decisions based on the presented list of crops. Based on the selected crops, the server selects the most suitable abandoned farmland and provides that information to the user. The user then chooses a specific plot of land and decides to invest in it.

[0279] Agricultural planning and management:

[0280] The server utilizes generative models to create a cultivation plan tailored to the selected farmland and crops. This plan includes sowing dates, irrigation schedules, and fertilization plans. Detailed steps are provided to the user via a terminal to support the execution of the plan.

[0281] Profit distribution:

[0282] The harvested crops are sold at the optimal price based on market analysis. The server calculates the sales revenue and performs the process of distributing the profit according to the user's investment amount. Information regarding profit distribution is notified to the user through the terminal.

[0283] With this system, users can make appropriate investment decisions and achieve effective agricultural management. As a result, the utilization of unused fallow farmland is promoted, and sustainable agricultural profits are generated.

[0284] The following describes the process flow.

[0285] Step 1:

[0286] The user opens the application and performs new registration. The user enters details such as name, contact information, investable amount, and agricultural experience. The terminal receives the input information, validates the data, and then sends it to the server. The server saves the received information in the database and creates a user profile.

[0287] Step 2:

[0288] The server continuously collects information on price trends and demand patterns in the agricultural product market by using the API of an external data provider. At the same time, the weather data includes future predicted temperature, precipitation, sunshine hours, etc. These data are stored in the database and prepared for use in the generation model.

[0289] Step 3:

[0290] The server collects information on fallow farmland from local governments or public databases. This information includes the location, area, soil quality, proximity to water sources, etc. of the land. The server organizes these data and constructs a dataset for identifying available agricultural land.

[0291] Step 4:

[0292] The server uses collected market and weather data to run a generative model and predict future demand for agricultural products. The generated demand forecast shows the market opportunity for specific crops. Based on this information, the server creates a list of crops best suited to the user's profile and sends it to the terminal.

[0293] Step 5:

[0294] The terminal displays investment candidates based on a list of crops and demand forecast data received from the server. The user reviews the list and selects which project to invest in. Once the user makes a decision, that information is sent from the terminal to the server.

[0295] Step 6:

[0296] Based on the user's selection, the server executes a process to select the most suitable abandoned farmland. It filters the data of available land, selects the land best suited for crop cultivation, and proposes it to the user. Once the user reviews the proposal and selects the land, the server records the information and supports the contract procedures.

[0297] Step 7:

[0298] The server creates an optimal farming plan for the selected farmland. This plan includes details such as crop planting, fertilization, irrigation schedules, and harvest plans. The server sends this plan to the terminal, providing the user with a detailed implementation guide.

[0299] Step 8:

[0300] As harvest time approaches, the server re-analyzes market data to determine the optimal timing and channels for sales. The harvested crops are then shipped to market based on the generated sales strategy.

[0301] Step 9:

[0302] The server calculates the total sales of agricultural products and distributes the profits based on the user's investment amount. The details of the profit distribution are notified to the user through the terminal, and the user receives their own profits.

[0303] In this way, the system can efficiently utilize fallow farmland and support maximizing profits in agricultural projects.

[0304] (Example 1)

[0305] Next, Example 1 will be described. In the following description, the data processing device 12 is referred to as the "server", and the smart glasses 214 are referred to as the "terminal".

[0306] In a conventional agricultural management system, it is time-consuming to predict individual market demands and select appropriate farmland, and it is also difficult to create a highly profitable cultivation plan. For this reason, there are problems such as the inability to effectively utilize fallow farmland and insufficient profit distribution to users. To solve these problems, it is necessary to provide a system that efficiently analyzes market data and weather information and supports optimal cultivation and profit management of agricultural crops.

[0307] The specific processing by the specific processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0308] In this invention, the server includes calculation means for analyzing the market demand and weather conditions of agricultural products using a generation model and generating a cultivation plan for agricultural crops, means for receiving investment information from users, collating it with information on fallow farmland, and selecting optimal farmland, and information processing means for applying the cultivation plan using the generation model to the selected farmland and supporting plan execution. In this way, it is possible to efficiently propose highly profitable agricultural projects, promote the utilization of fallow farmland, and distribute profits to users.

[0309] A "generative model" is a model that uses machine learning algorithms to analyze information collected from diverse data sources and generate specific predictions or suggestions.

[0310] "Market demand" refers to information that indicates consumers' willingness to purchase and purchasing trends for specific agricultural products.

[0311] "Weather conditions" refer to information that indicates meteorological factors such as temperature, precipitation, and sunshine duration in a specific region.

[0312] A "cultivation plan" is a detailed action plan for growing a specific crop, including sowing dates, irrigation schedules, and fertilization plans.

[0313] A "user" refers to someone who uses the system, inputs investment information, and receives proposals and management for agricultural projects.

[0314] "Abandoned farmland" refers to agricultural land that was previously cultivated but is no longer in use.

[0315] "Revenue calculation" is the process of calculating the income generated as a result of a specific agricultural project and distributing it to the stakeholders.

[0316] The system implementing this invention mainly includes a server, a terminal, and a user interface. Each process is as follows:

[0317] Data processing by the server

[0318] The server has means of collecting market and weather data from external data providers via APIs. This allows it to obtain information on the latest market trends and weather conditions. The collected data is analyzed using a generative AI model to develop demand forecasts for agricultural products and optimal cultivation plans. The server stores these generated results and provides them to users as needed.

[0319] User and device interface

[0320] Users access the system using a dedicated application and input information about their interests, investment capabilities, and agricultural experience. This information is received at the terminal, validated, and then sent to the server. The server uses this information to generate a user profile, which is then used to suggest future agricultural projects.

[0321] Specific example

[0322] If a user has an investment limit of 1 million yen and is interested in wheat cultivation, they register this information in the system. This information is sent to the server, and based on the generated AI model, if wheat cultivation is predicted to be highly profitable, the server presents the user with an appropriate cultivation plan and the most suitable farmland.

[0323] Example of a prompt

[0324] "My available investment is 1 million yen, and I'm interested in growing wheat, but I'm a beginner. Please propose a suitable farming plan based on these conditions."

[0325] This allows users to receive specific farming plans based on certain conditions, enabling them to make rational investment decisions and select farmland. The system promotes the utilization of unused, abandoned farmland and makes it possible to generate sustainable agricultural revenues.

[0326] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0327] Step 1: User registration and data entry

[0328] Users input information about their interests, investment capabilities, and agricultural experience using a dedicated application. The terminal receives this information and performs data validation. Specifically, it checks if the entered investment amount is a numerical value and verifies that agricultural experience is entered in a selection format. The output of this step is sent to the server as validated user information.

[0329] Step 2: Data Collection

[0330] The server collects market and weather data using APIs from external data providers. Inputs include up-to-date agricultural product price information, consumer trends, and weather forecast data. The server receives this data and stores it in a database. This information is used as input for a generative AI model. The output is raw data ready for analysis.

[0331] Step 3: Analysis using generative models

[0332] The server inputs user profiles, collected market data, and weather data into a generative AI model. The generative model analyzes these inputs to forecast demand for agricultural products. Specifically, it uses machine learning algorithms to predict future demand trends from historical data. The output is a list of agricultural products recommended to the user.

[0333] Step 4: Farmland Selection

[0334] The server selects suitable farmland from a database of abandoned land based on the crops chosen by the user. This process considers factors such as land location, soil quality, and proximity to water sources. The input is the user's selected crop information, and the output is a list of suitable farmland.

[0335] Step 5: Cultivation plan and implementation support

[0336] The server utilizes a generation AI model to create a cultivation plan suitable for the selected crops. Specifically, it includes details such as sowing time, irrigation schedule, and fertilization plan. The cultivation plan is provided to the user via a terminal, along with instructions on how to implement the plan. The input is data on the selected farmland and crops, and the output is a specific cultivation plan.

[0337] Step 6: Profit Calculation and Distribution

[0338] The server sells harvested crops at the optimal price based on market data. The calculation uses harvest yield, selling price, and cost structure as inputs to determine sales and profits. The output is revenue information distributed to users, which is notified to users via their terminals.

[0339] (Application Example 1)

[0340] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0341] A challenge in modern urban areas is that abandoned farmland is left unattended and not utilized for sustainable agricultural activities. Furthermore, urban residents have limited opportunities to participate in agricultural projects, making effective cultivation management difficult. This invention aims to provide a system that supports urban residents and enables the efficient use and monetization of underutilized land.

[0342] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0343] This invention includes a server that includes processing means for analyzing market demand and weather conditions for agricultural products using a generative model and generating a crop cultivation plan; means for receiving investment information from users and selecting optimal farmland by comparing it with information on abandoned farmland; means for applying the cultivation plan to the selected farmland, calculating profits, and distributing profits to users; and support means for urban residents to participate in agricultural projects through smart devices and manage the efficient use of abandoned farmland. This enables urban residents to easily participate in sustainable agricultural projects and to utilize unused land for effective agricultural management and profit generation.

[0344] A "generative model" is an algorithm that automatically generates new data and predictions based on a vast amount of existing data.

[0345] "Market demand" refers to the total quantity of goods that consumers in a particular market wish to purchase during a given period.

[0346] "Meteorological conditions" refer to atmospheric conditions such as weather, temperature, and precipitation in a specific region or period.

[0347] "Agricultural products" refer to plants and food produced through agriculture.

[0348] A "cultivation plan" is a detailed set of instructions for determining the timing and methods for efficiently growing a specific crop.

[0349] "Investment information" refers to financially relevant data and information necessary for decision-making that a user possesses about an investment target.

[0350] "Abandoned farmland" refers to land that was once used as agricultural land but is no longer in use.

[0351] "Urban residents" is a term that refers to citizens who live in urban areas.

[0352] "Smart devices" are a general term for electronic devices that have internet connectivity and allow users to obtain and manipulate information.

[0353] "Efficient use" means making the most of limited resources and time to achieve one's goals.

[0354] "Profit calculation" is the process of calculating the profits that can be obtained from a particular business or investment activity.

[0355] "Support measures" refer to methods and techniques that provide support to ensure that a particular task can be performed smoothly.

[0356] This invention provides a system that enables urban residents to invest in and participate in agricultural projects by utilizing generative models. The server first creates a profile based on investment information obtained from the user, which is entered via a dedicated smart device. Next, it analyzes market and weather data collected from multiple external data providers to predict market demand for agricultural products. This process utilizes a generative AI model equipped with machine learning algorithms. This allows for the selection of the most suitable crops for the user and the generation of a cultivation plan.

[0357] The terminal presents the generated cultivation plan to the user and selects the most suitable farmland by comparing it with information on abandoned farmland. At this stage, the user can select a specific plot of land and make an investment decision. After selection, the server applies the cultivation plan, calculates the profits, and distributes the profits to the user. This entire process functions as a means of realizing sustainable agriculture within a smart city.

[0358] As a concrete example, let's say person A, who lives in an urban area, accesses an application using their smartphone. Through the app, they register their investment capabilities and interests and participate in a tomato cultivation project on unused land in the suburbs. The app provides them with weather data and market trends, indicating that the land is suitable for tomato cultivation. They then participate in the project, and ultimately, the profits are distributed according to their investment.

[0359] A concrete example of a prompt for a generative model might be, "What is the best time and management method for growing tomatoes in an urban area?" This prompt prompts the system to provide a cultivation plan suitable for the given environment.

[0360] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0361] Step 1:

[0362] The server receives investment information transmitted from users via smart devices. This includes inputting the user's interests, investment capabilities, and agricultural experience. This data is stored in a database and used to generate profiles.

[0363] Step 2:

[0364] The server collects market and weather data from external data providers via APIs. This process obtains data on agricultural product price trends, consumption patterns, and weather conditions. Based on the collected data, a generative AI model makes market demand forecasts.

[0365] Step 3:

[0366] The generative AI model analyzes market and weather data to generate a list of optimal crops based on the user's profile. When prompted with "Please suggest crops suitable for cultivation under specific market and weather conditions," the analysis results will output a suggested list.

[0367] Step 4:

[0368] The terminal presents the user with a list of generated crops and prompts them to make a selection. The user chooses the crops they wish to cultivate from the presented list and makes an investment decision. At this time, based on the specifications of the selected crops, the system presents the most suitable abandoned farmland from the server.

[0369] Step 5:

[0370] The server generates a cultivation plan based on the user's selections. This plan specifically designs the sowing period, irrigation schedule, and fertilization plan. This plan is then provided to the user's terminal to assist with its implementation.

[0371] Step 6:

[0372] Users carry out agricultural activities based on the cultivation plan displayed on their terminal. Progress at each step is fed back to the server via the terminal, and the plan is adjusted as needed.

[0373] Step 7:

[0374] After harvesting, the server sells the crops at the optimal price based on market analysis. Profit calculations are performed, and the profits are distributed according to the user's investment. This result is then notified to the user's device.

[0375] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0376] This invention aims to build a system that provides a personalized experience tailored to the user's emotions by incorporating an emotion engine into an agricultural investment platform. The embodiments of this system are described in detail below.

[0377] User registration and profile settings:

[0378] Users access the application through their device and register. They fill in profile information, including their emotional state, and register their investment capabilities and interests with the system. The device sends this information to the server. The server stores the received information in a database and creates individual user profiles.

[0379] Collection and analysis of market and weather data:

[0380] The server uses APIs from external data providers to collect data on agricultural market trends and weather conditions. This data is stored in a database and analyzed by a generative model. Based on the collected data, the generative model predicts market demand and prepares agricultural cultivation suggestions for the user.

[0381] How the emotion engine works:

[0382] The emotion engine analyzes information and operation history entered from the user's device to infer the user's emotional state. Based on this inference, the server adjusts the interface and content to present information in a way that is most acceptable to the user.

[0383] Suggestions and choices for the user:

[0384] The server incorporates emotional data analyzed by the emotion engine to propose a customized list of crops and a cultivation plan to the user. The user receives these proposals through their terminal and decides on their investment. Throughout this process, the emotion engine monitors the user's responses in real time and adjusts the proposals as needed.

[0385] Investment decision support:

[0386] The emotion engine fine-tunes the feedback method to make the user more receptive to the cultivation plan they have chosen. For example, if a user is feeling anxious, it helps to increase their sense of security by providing detailed information about the risks and benefits of the investment.

[0387] Revenue sharing and learning platform:

[0388] When revenue is generated, the server calculates the revenue and distributes it to the user. The distribution results are notified to the user via their device. In addition, the emotion engine updates learning content based on the user's interests and emotional state, supporting continuous education about agriculture.

[0389] For example, if a user is feeling anxious about their first agricultural investment, the emotion engine can recognize that emotion and add reassuring supplementary information to make suggestions. This allows users to make investment decisions with greater confidence and provides an agricultural experience tailored to their individual needs.

[0390] The following describes the processing flow.

[0391] Step 1:

[0392] Users access the application through their device and register. They enter information such as their name, contact details, investment intentions, and emotional tendencies. The device sends this information to the server, which stores it in a database and generates a user profile.

[0393] Step 2:

[0394] The server periodically collects market and weather data through APIs from external data providers. Market data includes price trends and demand forecasts for agricultural products, while weather data includes temperature, precipitation, and sunshine duration. The server analyzes this data using generative models and makes demand forecasts based on these analyses.

[0395] Step 3:

[0396] The server activates an emotion engine and analyzes the user's emotional state based on past operation logs obtained from the user's terminal and directly entered emotional information. The analysis results are reflected in the user's profile and used to make future suggestions.

[0397] Step 4:

[0398] The server creates a list of crops and an investment plan based on the collected data and analysis results. This list includes the optimal crops reflecting the current market conditions and is structured to present information in a way that suits the user's emotional state. The server then sends this information to the terminal.

[0399] Step 5:

[0400] The terminal displays a list of crops and investment plans sent from the server to the user. Based on the analysis results of the emotion engine, the order of the displayed content and the level of detail in the explanations are adjusted. The user reviews this, selects projects that interest them, and decides to invest.

[0401] Step 6:

[0402] The server receives the user's selection and identifies the most suitable abandoned farmland. The selection is based on crop characteristics, land conditions, and the user's investment strategy. Detailed information about the proposed farmland is sent to the terminal for the user to review.

[0403] Step 7:

[0404] The server creates an optimal cultivation plan for the selected farmland based on a generative model. This plan includes sowing, fertilization, and irrigation schedules, enabling real-time agricultural management. The server sends the plan to the terminal, prompting the user to execute it.

[0405] Step 8:

[0406] As harvest time approaches, the server re-evaluates market and weather data to determine the optimal sales strategy. The emotion engine takes into account the user's current emotional state and presents information in a way that minimizes stress.

[0407] Step 9:

[0408] The server compiles sales results, calculates revenue, and distributes it to users based on prior investment information. The terminal notifies users of the distribution results and supports the process of depositing the revenue into their accounts. The emotion engine monitors user satisfaction and provides feedback.

[0409] This will enable the creation of a personalized agricultural investment platform tailored to each individual user.

[0410] (Example 2)

[0411] Next, we will describe Example 2. 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".

[0412] In modern agricultural investment, there is a need for systems that enable users to effectively utilize diverse market and weather data and make investment decisions based on their individual emotional states. However, properly analyzing this data and providing users with the most relevant information is not easy. In particular, providing a personalized experience that takes user emotions into account is not yet fully realized with current technology.

[0413] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0414] This invention includes a server that uses a generative model to analyze market demand and weather conditions for agricultural products and generates a crop cultivation plan; a server that receives investment information from users and matches it with information on abandoned farmland to select the optimal farmland; and a server that uses an emotion engine to analyze the user's emotional state and adjust the user interface and content accordingly. This enables the user to receive personalized investment suggestions based on their emotions and make investment decisions with confidence.

[0415] A "generative model" is a technique that uses machine learning algorithms to analyze market data and weather data obtained from multiple data sources and generate outputs that are aligned with a specific purpose.

[0416] An "emotion engine" is a technology that analyzes a user's operation history and input information to infer the user's emotional state and then individually adjusts information content and user interfaces based on that.

[0417] "Investment information" refers to individual data that users provide when making agricultural investments, such as the amount of funds and the investment targets.

[0418] "Abandoned farmland" refers to agricultural land that was once cultivated but is no longer in use, and it serves as a source of information for selecting land suitable for new cultivation activities.

[0419] A "customized crop list" is a list of recommended crops generated by the emotion engine and individually created based on the user's emotions and interests.

[0420] This invention provides a system that enables users to make efficient and emotion-based agricultural investments. Specifically, it combines a generative AI model and an emotion engine to provide users with personalized cultivation plans and investment suggestions.

[0421] The server automatically collects data on agricultural market trends and weather conditions using APIs from external data providers. This data is analyzed using a generative AI model to help generate market demand forecasts and crop cultivation plans. The generative AI model learns from information gathered from various data sources and provides optimal output.

[0422] Users input information about their emotional state and investment capabilities through their devices and send it to the server. The emotion engine analyzes the input from the device and the user's operation history to infer the user's emotional state. Based on this inference, the server adjusts the information content and user interface to facilitate effective communication.

[0423] Furthermore, the system has a function to select farmland suitable for the user by integrating information on abandoned farmland. A generated cultivation plan is applied to the selected farmland, and profit calculations are performed based on that plan. If profits are generated, they are then distributed to the user.

[0424] For example, if a user making their first agricultural investment feels anxious, the emotion engine effectively captures this emotion. The server then provides detailed information about the investment's risks and benefits to reassure the user, supporting them in making a confident decision. In this way, flexible investment suggestions tailored to the user's emotions become possible.

[0425] An example of a prompt to input into the generating AI model is: "Based on the latest agricultural market data, please propose a cultivation plan for the next season. Also, please consider crops the user has shown interest in in the past and provide additional information that the emotion engine should add to alleviate the user's concerns."

[0426] Therefore, this invention can provide an emotion-based, personalized agricultural investment experience.

[0427] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0428] Step 1:

[0429] Users access the application and register through their devices. Input information includes data on the user's emotional state, investment capacity, and interests. This input information is organized by the device and sent to the server. The server receives the data and stores it in a database to create a user profile. This profile forms the basis for future personalized recommendations.

[0430] Step 2:

[0431] The server collects market and weather data using APIs from external data providers. This input data includes information on current market trends and weather conditions. The server stores this data in a database and performs analysis using a generative AI model. Specifically, it generates market demand forecasts and crop cultivation plans based on the data. The output provides forecast information and data necessary for recommendations.

[0432] Step 3:

[0433] The emotion engine receives operation history and emotion information entered from the user's device and analyzes the user's emotional state. This analysis infers the user's emotional state. Based on this inference, the server processes the data to adjust the user interface and the information presented. For example, the order in which information is presented, the colors used, and the font size may be changed.

[0434] Step 4:

[0435] The server incorporates information analyzed by the emotion engine to generate a personalized list of crops and a cultivation plan for each user. Emotional data and predictive information from the generative AI model are used as input. As output, suggestions are created for the user and sent to them via their device.

[0436] Step 5:

[0437] The user receives suggestions from their device and makes an investment choice. The emotion engine monitors the user's reactions in real time as they make their choice, adjusting the suggestions and presentation methods as needed. The output records the final decision based on the user's selection.

[0438] Step 6:

[0439] The server calculates profits based on the selected cultivation plan. It uses projected profits and risk assessments as input data to calculate detailed investment results. The resulting profit information is distributed to the user and notified via their device. Furthermore, the emotion engine updates learning content based on the user's emotional state, supporting continuous education for future investments.

[0440] (Application Example 2)

[0441] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0442] Modern agricultural investment systems require the provision of personalized investment experiences that take into account the individual emotional states of investors. However, conventional systems struggle to provide dynamic suggestions that consider investors' emotions, limiting improvements in the user experience. Therefore, more effective support is needed to enable investors to make investment decisions with confidence.

[0443] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0444] This invention includes a server that uses a generative model to analyze market demand and weather conditions for agricultural products and generates a crop cultivation plan; a server that receives investment information from users and matches it with information on abandoned farmland to select the optimal farmland; and a server that analyzes the user's emotional state, personalizes crop choices based on that, provides real-time emotional feedback, and supports investment decision-making. This enables individualized responses tailored to the user's emotions, making it possible to support safer and more efficient investment decision-making.

[0445] A "generative model" is a system that uses various algorithms and data to create or analyze new information.

[0446] "Market demand" is an indicator that shows the degree of consumer and industry willingness to purchase a particular agricultural product.

[0447] "Weather conditions" refer to atmospheric conditions such as temperature, precipitation, wind speed, and humidity, and are factors that have a significant impact on agricultural production.

[0448] A "cultivation plan" is a detailed plan that specifies which crops to cultivate and how to cultivate them on a particular plot of land.

[0449] "Investment information" refers to information that shows how much money a user will invest and how they will invest it in the agricultural sector.

[0450] "Abandoned farmland" refers to agricultural land that was previously cultivated but has been abandoned for some reason and is no longer in use.

[0451] Personalization is the act of adjusting and optimizing suggestions and services based on an individual's characteristics and preferences.

[0452] "Profit calculation" is the process of quantifying and calculating the profits and losses obtained from a particular investment activity.

[0453] An "emotional state" refers to a set of psychological and physiological responses that an individual experiences at a particular moment.

[0454] "Investment decision support" refers to support activities that provide information and feedback to help users make better investment choices.

[0455] As an embodiment for carrying out this invention, the configuration and operation of a system using an electronic computer will be described.

[0456] First, the server uses a generative model to collect market and weather data from multiple data sources and uses this data to predict market demand for agricultural products. Typically, APIs from external data providers are used to collect market data. The collected data is stored in a database and analyzed by machine learning algorithms. The results of this analysis are then used to generate cultivation plans for the user.

[0457] Users access the system from devices such as smartphones and input their investment information. The data entered on the device is sent to a server and cross-referenced with information on abandoned farmland. This allows for the selection of the most suitable farmland and the creation of a cultivation plan tailored to the user.

[0458] Furthermore, the device uses its built-in camera to analyze the user's emotional state in real time. This emotional analysis utilizes facial recognition and voice analysis technologies to capture the user's feelings. Based on the emotional state, the service content and presentation methods are personalized, providing the user with a selection of agricultural products that are suitable for them.

[0459] If a user agrees with the proposal, they can quickly invest funds using an electronic payment API. The profits resulting from the investment are calculated through a profit calculation process and distributed to the user.

[0460] For example, if the emotion engine analyzes that a user is in a relaxed mood on holiday, it will suggest a low-risk, small-scale investment plan and provide basic educational content about agriculture (for example, a video introducing the crop growing process).

[0461] Examples of prompts for a generative AI model include:

[0462] "Based on an analysis of the user's current emotional state, which is relaxed, please suggest a recommended low-risk agricultural investment plan."

[0463] These are some examples.

[0464] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0465] Step 1:

[0466] The server uses APIs from external data providers to collect market and weather data. The input is data retrieved from the API, and the output is a well-organized dataset. Before being stored in the database, the data undergoes preprocessing, including format conversion and imputation of missing values.

[0467] Step 2:

[0468] The server uses a generative model to analyze collected market and weather data. The input is a pre-processed dataset, and the output is forecast information about future market demand. Machine learning algorithms are used for the analysis, including multivariate and time series analysis.

[0469] Step 3:

[0470] The user enters their investment information from the terminal. This information includes the user's investment amount, risk tolerance, and preferred crop types, while the output is user profile information. The terminal sends the entered information to the server and updates the profile.

[0471] Step 4:

[0472] The server selects the most suitable farmland based on the user profile. Inputs are user profiles and data on abandoned farmland, while output is information on the selected farmland. This process utilizes a Geographic Information System (GIS) for map analysis.

[0473] Step 5:

[0474] The device uses its built-in camera to analyze the user's emotional state. The input is real-time image data, and the output is an estimated emotional state (e.g., relaxed, excited, anxious). It utilizes an emotion analysis library to analyze emotions from facial expressions and voice.

[0475] Step 6:

[0476] The server proposes a personalized cultivation plan based on estimated emotional states and user profiles. Inputs are emotional states, user profiles, and predicted market demand; output is the proposed agricultural investment plan. A generative AI model is used to develop appropriate crop selections and investment plans.

[0477] Step 7:

[0478] The user reviews the proposal and decides whether to invest. The input is the proposed investment plan, and the output is the instruction to execute the investment. The user reviews it on their terminal and prepares to make the payment.

[0479] Step 8:

[0480] The server uses an electronic payment API to execute user investments and complete transactions. Input is the user's payment information, and output is a transaction completion notification. A secure communication protocol is used for the payment process.

[0481] Step 9:

[0482] The server calculates profits and distributes them to users. Inputs are investment results and market data, and output is a notification of profit results to users. A profit distribution algorithm is used to ensure fair distribution.

[0483] Step 10:

[0484] The device updates and provides learning content to the user based on their emotional state. The input is the updated emotional state and learning history, and the output is new educational content. An educational plan is then executed using a generative AI model.

[0485] 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 user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0486] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0487] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart glasses 214.

[0488] [Third Embodiment]

[0489] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0490] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0491] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0492] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0493] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0494] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0495] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0496] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0497] The specific processing program 56 is an example of a "program" relating to the technology of this 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.

[0498] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0499] In the headset terminal 314, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0500] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the headset terminal 314 will be referred to as the "terminal".

[0501] This invention provides a system that enables effective management and investment in agriculture using generative models. Embodiments of this system are described in detail below.

[0502] User registration and profile settings:

[0503] Users create a profile by entering information about their interests, investment capabilities, and agricultural experience through a dedicated application. The terminal receives this information, performs the necessary data validation, and then sends it to the server. The server stores this data in a database and uses it for subsequent analysis and recommendations.

[0504] Market and weather data collection:

[0505] The server collects market and weather data from external data providers via APIs. Market data includes price trends and consumption patterns for agricultural products, while weather data includes future temperatures, precipitation, and sunshine duration. The server analyzes this data, which is then used by generative models for later predictions.

[0506] Gathering information on abandoned farmland:

[0507] The server collects information about abandoned farmland from public databases and municipal records. This includes information such as land size, soil quality, and proximity to water sources. The server uses this information to create a list of available farmland.

[0508] Demand forecasting and crop recommendations:

[0509] The server uses a generative model to analyze collected market and weather data and forecast demand for agricultural projects. This generates specific suggestions on which crops should be cultivated. Based on the user's profile information, a list of the most suitable crops is generated and presented to the user.

[0510] Farmland selection and investment decision-making:

[0511] The user makes investment decisions based on the presented list of crops. Based on the selected crops, the server selects the most suitable abandoned farmland and provides that information to the user. The user then chooses a specific plot of land and decides to invest in it.

[0512] Agricultural planning and management:

[0513] The server utilizes generative models to create a cultivation plan tailored to the selected farmland and crops. This plan includes sowing dates, irrigation schedules, and fertilization plans. Detailed steps are provided to the user via a terminal to support the execution of the plan.

[0514] Profit sharing:

[0515] The harvested crops are sold at the optimal price based on market analysis. The server calculates the sales and distributes the profits according to the user's investment amount. Information regarding profit distribution is notified to the user via their terminal.

[0516] This system enables users to make appropriate investment decisions and achieve effective agricultural management. This promotes the utilization of unused, abandoned farmland and generates sustainable agricultural revenue.

[0517] The following describes the processing flow.

[0518] Step 1:

[0519] The user opens the application and registers. The user enters details such as their name, contact information, investment amount, and agricultural experience. The terminal receives the entered information, validates the data, and then sends it to the server. The server stores the received information in a database and creates a user profile.

[0520] Step 2:

[0521] The server continuously collects information on price trends and demand patterns in the agricultural market using APIs from external data providers. Simultaneously, weather data includes predicted future temperatures, precipitation, and sunshine duration. This data is stored in a database and prepared for use in generative models.

[0522] Step 3:

[0523] The server collects information on abandoned farmland from local government and public databases. This information includes the location, size, soil quality, and proximity to water sources. The server organizes this data and builds datasets to identify usable farmland.

[0524] Step 4:

[0525] The server uses collected market and weather data to run a generative model and predict future demand for agricultural products. The generated demand forecast shows the market opportunity for specific crops. Based on this information, the server creates a list of crops best suited to the user's profile and sends it to the terminal.

[0526] Step 5:

[0527] The terminal displays investment candidates based on a list of crops and demand forecast data received from the server. The user reviews the list and selects which project to invest in. Once the user makes a decision, that information is sent from the terminal to the server.

[0528] Step 6:

[0529] Based on the user's selection, the server executes a process to select the most suitable abandoned farmland. It filters the data of available land, selects the land best suited for crop cultivation, and proposes it to the user. Once the user reviews the proposal and selects the land, the server records the information and supports the contract procedures.

[0530] Step 7:

[0531] The server creates an optimal farming plan for the selected farmland. This plan includes details such as crop planting, fertilization, irrigation schedules, and harvest plans. The server sends this plan to the terminal, providing the user with a detailed implementation guide.

[0532] Step 8:

[0533] As harvest time approaches, the server re-analyzes market data to determine the optimal timing and channels for sales. The harvested crops are then shipped to market based on the generated sales strategy.

[0534] Step 9:

[0535] The server calculates the total sales revenue of agricultural products and distributes the profits based on the user's investment amount. Details of the profit distribution are notified to the user via their terminal, and the user receives their share of the profits.

[0536] This will enable the system to efficiently utilize abandoned farmland and support the maximization of profits in agricultural projects.

[0537] (Example 1)

[0538] Next, we will describe Example 1. 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."

[0539] Conventional agricultural management systems make it time-consuming to forecast individual market demand and select appropriate farmland, and it is difficult to create highly profitable cultivation plans. This has resulted in challenges such as the ineffective utilization of abandoned farmland and insufficient profit distribution to users. To solve these problems, there is a need to provide a system that efficiently analyzes market data and weather information to support optimal crop cultivation and profit management.

[0540] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0541] In this invention, the server includes a computation means for analyzing market demand and weather conditions for agricultural products using a generative model and generating a crop cultivation plan; a means for receiving investment information from users and matching it with information on abandoned farmland to select the optimal farmland; and an information processing means for applying the cultivation plan using the generative model to the selected farmland and supporting the execution of the plan. This enables the efficient proposal of highly profitable agricultural projects, promotes the utilization of abandoned farmland, and allows for profit sharing with users.

[0542] A "generative model" is a model that uses machine learning algorithms to analyze information collected from diverse data sources and generate specific predictions or suggestions.

[0543] "Market demand" refers to information that indicates consumers' willingness to purchase and purchasing trends for specific agricultural products.

[0544] "Weather conditions" refer to information that indicates meteorological factors such as temperature, precipitation, and sunshine duration in a specific region.

[0545] A "cultivation plan" is a detailed action plan for growing a specific crop, including sowing dates, irrigation schedules, and fertilization plans.

[0546] A "user" refers to someone who uses the system, inputs investment information, and receives proposals and management for agricultural projects.

[0547] "Abandoned farmland" refers to agricultural land that was previously cultivated but is no longer in use.

[0548] "Revenue calculation" is the process of calculating the income generated as a result of a specific agricultural project and distributing it to the stakeholders.

[0549] The system implementing this invention mainly includes a server, a terminal, and a user interface. Each process is as follows:

[0550] Data processing by the server

[0551] The server has means of collecting market and weather data from external data providers via APIs. This allows it to obtain information on the latest market trends and weather conditions. The collected data is analyzed using a generative AI model to develop demand forecasts for agricultural products and optimal cultivation plans. The server stores these generated results and provides them to users as needed.

[0552] User and device interface

[0553] Users access the system using a dedicated application and input information about their interests, investment capabilities, and agricultural experience. This information is received at the terminal, validated, and then sent to the server. The server uses this information to generate a user profile, which is then used to suggest future agricultural projects.

[0554] Specific example

[0555] If a user has an investment limit of 1 million yen and is interested in wheat cultivation, they register this information in the system. This information is sent to the server, and based on the generated AI model, if wheat cultivation is predicted to be highly profitable, the server presents the user with an appropriate cultivation plan and the most suitable farmland.

[0556] Example of a prompt

[0557] "My available investment is 1 million yen, and I'm interested in growing wheat, but I'm a beginner. Please propose a suitable farming plan based on these conditions."

[0558] This allows users to receive specific farming plans based on certain conditions, enabling them to make rational investment decisions and select farmland. The system promotes the utilization of unused, abandoned farmland and makes it possible to generate sustainable agricultural revenues.

[0559] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0560] Step 1: User registration and data entry

[0561] Users input information about their interests, investment capabilities, and agricultural experience using a dedicated application. The terminal receives this information and performs data validation. Specifically, it checks if the entered investment amount is a numerical value and verifies that agricultural experience is entered in a selection format. The output of this step is sent to the server as validated user information.

[0562] Step 2: Data Collection

[0563] The server collects market and weather data using APIs from external data providers. Inputs include up-to-date agricultural product price information, consumer trends, and weather forecast data. The server receives this data and stores it in a database. This information is used as input for a generative AI model. The output is raw data ready for analysis.

[0564] Step 3: Analysis using generative models

[0565] The server inputs user profiles, collected market data, and weather data into a generative AI model. The generative model analyzes these inputs to forecast demand for agricultural products. Specifically, it uses machine learning algorithms to predict future demand trends from historical data. The output is a list of agricultural products recommended to the user.

[0566] Step 4: Farmland Selection

[0567] The server selects suitable farmland from a database of abandoned land based on the crops chosen by the user. This process considers factors such as land location, soil quality, and proximity to water sources. The input is the user's selected crop information, and the output is a list of suitable farmland.

[0568] Step 5: Cultivation plan and implementation support

[0569] The server utilizes a generation AI model to create a cultivation plan suitable for the selected crops. Specifically, it includes details such as sowing time, irrigation schedule, and fertilization plan. The cultivation plan is provided to the user via a terminal, along with instructions on how to implement the plan. The input is data on the selected farmland and crops, and the output is a specific cultivation plan.

[0570] Step 6: Profit Calculation and Distribution

[0571] The server sells harvested crops at the optimal price based on market data. The calculation uses harvest yield, selling price, and cost structure as inputs to determine sales and profits. The output is revenue information distributed to users, which is notified to users via their terminals.

[0572] (Application Example 1)

[0573] Next, we will explain Application Example 1. In the following explanation, 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."

[0574] A challenge in modern urban areas is that abandoned farmland is left unattended and not utilized for sustainable agricultural activities. Furthermore, urban residents have limited opportunities to participate in agricultural projects, making effective cultivation management difficult. This invention aims to provide a system that supports urban residents and enables the efficient use and monetization of underutilized land.

[0575] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0576] This invention includes a server that includes processing means for analyzing market demand and weather conditions for agricultural products using a generative model and generating a crop cultivation plan; means for receiving investment information from users and selecting optimal farmland by comparing it with information on abandoned farmland; means for applying the cultivation plan to the selected farmland, calculating profits, and distributing profits to users; and support means for urban residents to participate in agricultural projects through smart devices and manage the efficient use of abandoned farmland. This enables urban residents to easily participate in sustainable agricultural projects and to utilize unused land for effective agricultural management and profit generation.

[0577] A "generative model" is an algorithm that automatically generates new data and predictions based on a vast amount of existing data.

[0578] "Market demand" refers to the total quantity of goods that consumers in a particular market wish to purchase during a given period.

[0579] "Meteorological conditions" refer to atmospheric conditions such as weather, temperature, and precipitation in a specific region or period.

[0580] "Agricultural products" refer to plants and food produced through agriculture.

[0581] A "cultivation plan" is a detailed set of instructions for determining the timing and methods for efficiently growing a specific crop.

[0582] "Investment information" refers to financially relevant data and information necessary for decision-making that a user possesses about an investment target.

[0583] "Abandoned farmland" refers to land that was once used as agricultural land but is no longer in use.

[0584] "Urban residents" is a term that refers to citizens who live in urban areas.

[0585] "Smart devices" are a general term for electronic devices that have internet connectivity and allow users to obtain and manipulate information.

[0586] "Efficient use" means making the most of limited resources and time to achieve one's goals.

[0587] "Profit calculation" is the process of calculating the profits that can be obtained from a particular business or investment activity.

[0588] "Support measures" refer to methods and techniques that provide support to ensure that a particular task can be performed smoothly.

[0589] This invention provides a system that enables urban residents to invest in and participate in agricultural projects by utilizing generative models. The server first creates a profile based on investment information obtained from the user, which is entered via a dedicated smart device. Next, it analyzes market and weather data collected from multiple external data providers to predict market demand for agricultural products. This process utilizes a generative AI model equipped with machine learning algorithms. This allows for the selection of the most suitable crops for the user and the generation of a cultivation plan.

[0590] The terminal presents the generated cultivation plan to the user and selects the most suitable farmland by comparing it with information on abandoned farmland. At this stage, the user can select a specific plot of land and make an investment decision. After selection, the server applies the cultivation plan, calculates the profits, and distributes the profits to the user. This entire process functions as a means of realizing sustainable agriculture within a smart city.

[0591] As a concrete example, let's say person A, who lives in an urban area, accesses an application using their smartphone. Through the app, they register their investment capabilities and interests and participate in a tomato cultivation project on unused land in the suburbs. The app provides them with weather data and market trends, indicating that the land is suitable for tomato cultivation. They then participate in the project, and ultimately, the profits are distributed according to their investment.

[0592] A concrete example of a prompt for a generative model might be, "What is the best time and management method for growing tomatoes in an urban area?" This prompt prompts the system to provide a cultivation plan suitable for the given environment.

[0593] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0594] Step 1:

[0595] The server receives investment information transmitted from users via smart devices. This includes inputting the user's interests, investment capabilities, and agricultural experience. This data is stored in a database and used to generate profiles.

[0596] Step 2:

[0597] The server collects market and weather data from external data providers via APIs. This process obtains data on agricultural product price trends, consumption patterns, and weather conditions. Based on the collected data, a generative AI model performs market demand forecasting.

[0598] Step 3:

[0599] The generative AI model analyzes market and weather data to generate a list of optimal crops based on the user's profile. When prompted with "Please suggest crops suitable for cultivation under specific market and weather conditions," the analysis results will output a suggested list.

[0600] Step 4:

[0601] The terminal presents the user with a list of generated crops and prompts them to make a selection. The user chooses the crops they wish to cultivate from the presented list and makes an investment decision. At this time, based on the specifications of the selected crops, the system presents the most suitable abandoned farmland from the server.

[0602] Step 5:

[0603] The server generates a cultivation plan based on the user's selections. This plan specifically designs the sowing period, irrigation schedule, and fertilization plan. This plan is then provided to the user's terminal to assist with its implementation.

[0604] Step 6:

[0605] Users carry out agricultural activities based on the cultivation plan displayed on their terminal. Progress at each step is fed back to the server via the terminal, and the plan is adjusted as needed.

[0606] Step 7:

[0607] After harvesting, the server sells the crops at the optimal price based on market analysis. Profit calculations are performed, and the profits are distributed according to the user's investment. This result is then notified to the user's device.

[0608] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0609] This invention aims to build a system that provides a personalized experience tailored to the user's emotions by incorporating an emotion engine into an agricultural investment platform. The embodiments of this system are described in detail below.

[0610] User registration and profile settings:

[0611] Users access the application through their device and register. They fill in profile information, including their emotional state, and register their investment capabilities and interests with the system. The device sends this information to the server. The server stores the received information in a database and creates individual user profiles.

[0612] Collection and analysis of market and weather data:

[0613] The server uses APIs from external data providers to collect data on agricultural market trends and weather conditions. This data is stored in a database and analyzed by a generative model. Based on the collected data, the generative model predicts market demand and prepares agricultural cultivation suggestions for the user.

[0614] How the emotion engine works:

[0615] The emotion engine analyzes information and operation history entered from the user's device to infer the user's emotional state. Based on this inference, the server adjusts the interface and content to present information in a way that is most acceptable to the user.

[0616] Suggestions and choices for the user:

[0617] The server incorporates emotional data analyzed by the emotion engine to propose a customized list of crops and a cultivation plan to the user. The user receives these proposals through their terminal and decides on their investment. Throughout this process, the emotion engine monitors the user's responses in real time and adjusts the proposals as needed.

[0618] Investment decision support:

[0619] The emotion engine fine-tunes the feedback method to make the user more receptive to the cultivation plan they have chosen. For example, if a user is feeling anxious, it helps to increase their sense of security by providing detailed information about the risks and benefits of the investment.

[0620] Revenue sharing and learning platform:

[0621] When revenue is generated, the server calculates the revenue and distributes it to the user. The distribution results are notified to the user via their device. In addition, the emotion engine updates learning content based on the user's interests and emotional state, supporting continuous education about agriculture.

[0622] For example, if a user is feeling anxious about their first agricultural investment, the emotion engine can recognize that emotion and add reassuring supplementary information to make suggestions. This allows users to make investment decisions with greater confidence and provides an agricultural experience tailored to their individual needs.

[0623] The following describes the processing flow.

[0624] Step 1:

[0625] Users access the application through their device and register. They enter information such as their name, contact details, investment intentions, and emotional tendencies. The device sends this information to the server, which stores it in a database and generates a user profile.

[0626] Step 2:

[0627] The server periodically collects market and weather data through APIs from external data providers. Market data includes price trends and demand forecasts for agricultural products, while weather data includes temperature, precipitation, and sunshine duration. The server analyzes this data using generative models and makes demand forecasts based on these analyses.

[0628] Step 3:

[0629] The server activates an emotion engine and analyzes the user's emotional state based on past operation logs obtained from the user's terminal and directly entered emotional information. The analysis results are reflected in the user's profile and used to make future suggestions.

[0630] Step 4:

[0631] The server creates a list of crops and an investment plan based on the collected data and analysis results. This list includes the optimal crops reflecting the current market conditions and is structured to present information in a way that suits the user's emotional state. The server then sends this information to the terminal.

[0632] Step 5:

[0633] The terminal displays a list of crops and investment plans sent from the server to the user. Based on the analysis results of the emotion engine, the order of the displayed content and the level of detail in the explanations are adjusted. The user reviews this, selects projects that interest them, and decides to invest.

[0634] Step 6:

[0635] The server receives the user's selection and identifies the most suitable abandoned farmland. The selection is based on crop characteristics, land conditions, and the user's investment strategy. Detailed information about the proposed farmland is sent to the terminal for the user to review.

[0636] Step 7:

[0637] The server creates an optimal cultivation plan for the selected farmland based on a generative model. This plan includes sowing, fertilization, and irrigation schedules, enabling real-time agricultural management. The server sends the plan to the terminal, prompting the user to execute it.

[0638] Step 8:

[0639] As harvest time approaches, the server re-evaluates market and weather data to determine the optimal sales strategy. The emotion engine takes into account the user's current emotional state and presents information in a way that minimizes stress.

[0640] Step 9:

[0641] The server compiles sales results, calculates revenue, and distributes it to users based on prior investment information. The terminal notifies users of the distribution results and supports the process of depositing the revenue into their accounts. The emotion engine monitors user satisfaction and provides feedback.

[0642] This will enable the creation of a personalized agricultural investment platform tailored to each individual user.

[0643] (Example 2)

[0644] Next, we will describe Example 2. 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."

[0645] In modern agricultural investment, there is a need for systems that enable users to effectively utilize diverse market and weather data and make investment decisions based on their individual emotional states. However, properly analyzing this data and providing users with the most relevant information is not easy. In particular, providing a personalized experience that takes user emotions into account is not yet fully realized with current technology.

[0646] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0647] This invention includes a server that uses a generative model to analyze market demand and weather conditions for agricultural products and generates a crop cultivation plan; a server that receives investment information from users and matches it with information on abandoned farmland to select the optimal farmland; and a server that uses an emotion engine to analyze the user's emotional state and adjust the user interface and content accordingly. This enables the user to receive personalized investment suggestions based on their emotions and make investment decisions with confidence.

[0648] A "generative model" is a technique that uses machine learning algorithms to analyze market data and weather data obtained from multiple data sources and generate outputs that are aligned with a specific purpose.

[0649] An "emotion engine" is a technology that analyzes a user's operation history and input information to infer the user's emotional state and then individually adjusts information content and user interfaces based on that.

[0650] "Investment information" refers to individual data that users provide when making agricultural investments, such as the amount of funds and the investment targets.

[0651] "Abandoned farmland" refers to agricultural land that was once cultivated but is no longer in use, and it serves as a source of information for selecting land suitable for new cultivation activities.

[0652] A "customized crop list" is a list of recommended crops generated by the emotion engine and individually created based on the user's emotions and interests.

[0653] This invention provides a system that enables users to make efficient and emotion-based agricultural investments. Specifically, it combines a generative AI model and an emotion engine to provide users with personalized cultivation plans and investment suggestions.

[0654] The server automatically collects data on agricultural market trends and weather conditions using APIs from external data providers. This data is analyzed using a generative AI model to help generate market demand forecasts and crop cultivation plans. The generative AI model learns from information gathered from various data sources and provides optimal output.

[0655] Users input information about their emotional state and investment capabilities through their devices and send it to the server. The emotion engine analyzes the input from the device and the user's operation history to infer the user's emotional state. Based on this inference, the server adjusts the information content and user interface to facilitate effective communication.

[0656] Furthermore, the system has a function to select farmland suitable for the user by integrating information on abandoned farmland. A generated cultivation plan is applied to the selected farmland, and profit calculations are performed based on that plan. If profits are generated, they are then distributed to the user.

[0657] For example, if a user making their first agricultural investment feels anxious, the emotion engine effectively captures this emotion. The server then provides detailed information about the investment's risks and benefits to reassure the user, supporting them in making a confident decision. In this way, flexible investment suggestions tailored to the user's emotions become possible.

[0658] An example of a prompt to input into the generating AI model is: "Based on the latest agricultural market data, please propose a cultivation plan for the next season. Also, please consider crops the user has shown interest in in the past and provide additional information that the emotion engine should add to alleviate the user's concerns."

[0659] Therefore, this invention can provide an emotion-based, personalized agricultural investment experience.

[0660] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0661] Step 1:

[0662] Users access the application and register through their devices. Input information includes data on the user's emotional state, investment capacity, and interests. This input information is organized by the device and sent to the server. The server receives the data and stores it in a database to create a user profile. This profile forms the basis for future personalized recommendations.

[0663] Step 2:

[0664] The server collects market and weather data using APIs from external data providers. This input data includes information on current market trends and weather conditions. The server stores this data in a database and performs analysis using a generative AI model. Specifically, it generates market demand forecasts and crop cultivation plans based on the data. The output provides forecast information and data necessary for recommendations.

[0665] Step 3:

[0666] The emotion engine receives operation history and emotion information entered from the user's device and analyzes the user's emotional state. This analysis infers the user's emotional state. Based on this inference, the server processes the data to adjust the user interface and the information presented. For example, the order in which information is presented, the colors used, and the font size may be changed.

[0667] Step 4:

[0668] The server incorporates information analyzed by the emotion engine to generate a personalized list of crops and a cultivation plan for each user. Emotional data and predictive information from the generative AI model are used as input. As output, suggestions are created for the user and sent to them via their device.

[0669] Step 5:

[0670] The user receives suggestions from their device and makes an investment choice. The emotion engine monitors the user's reactions in real time as they make their choice, adjusting the suggestions and presentation methods as needed. The output records the final decision based on the user's selection.

[0671] Step 6:

[0672] The server calculates profits based on the selected cultivation plan. It uses projected profits and risk assessments as input data to calculate detailed investment results. The resulting profit information is distributed to the user and notified via their device. Furthermore, the emotion engine updates learning content based on the user's emotional state, supporting continuous education for future investments.

[0673] (Application Example 2)

[0674] Next, we will explain application example 2. In the following explanation, 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."

[0675] Modern agricultural investment systems require the provision of personalized investment experiences that take into account the individual emotional states of investors. However, conventional systems struggle to provide dynamic suggestions that consider investors' emotions, limiting improvements in the user experience. Therefore, more effective support is needed to enable investors to make investment decisions with confidence.

[0676] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0677] This invention includes a server that uses a generative model to analyze market demand and weather conditions for agricultural products and generates a crop cultivation plan; a server that receives investment information from users and matches it with information on abandoned farmland to select the optimal farmland; and a server that analyzes the user's emotional state, personalizes crop choices based on that, provides real-time emotional feedback, and supports investment decision-making. This enables individualized responses tailored to the user's emotions, making it possible to support safer and more efficient investment decision-making.

[0678] A "generative model" is a system that uses various algorithms and data to create or analyze new information.

[0679] "Market demand" is an indicator that shows the degree of consumer and industry willingness to purchase a particular agricultural product.

[0680] "Weather conditions" refer to atmospheric conditions such as temperature, precipitation, wind speed, and humidity, and are factors that have a significant impact on agricultural production.

[0681] A "cultivation plan" is a detailed plan that specifies which crops to cultivate and how to cultivate them on a particular plot of land.

[0682] "Investment information" refers to information that shows how much money a user will invest and how they will invest it in the agricultural sector.

[0683] "Abandoned farmland" refers to agricultural land that was previously cultivated but has been abandoned for some reason and is no longer in use.

[0684] Personalization is the act of adjusting and optimizing suggestions and services based on an individual's characteristics and preferences.

[0685] "Profit calculation" is the process of quantifying and calculating the profits and losses obtained from a particular investment activity.

[0686] An "emotional state" refers to a set of psychological and physiological responses that an individual experiences at a particular moment.

[0687] "Investment decision support" refers to support activities that provide information and feedback to help users make better investment choices.

[0688] As an embodiment for carrying out this invention, the configuration and operation of a system using an electronic computer will be described.

[0689] First, the server uses a generative model to collect market and weather data from multiple data sources and uses this data to predict market demand for agricultural products. Typically, APIs from external data providers are used to collect market data. The collected data is stored in a database and analyzed by machine learning algorithms. The results of this analysis are then used to generate cultivation plans for the user.

[0690] Users access the system from devices such as smartphones and input their investment information. The data entered on the device is sent to a server and cross-referenced with information on abandoned farmland. This allows for the selection of the most suitable farmland and the creation of a cultivation plan tailored to the user.

[0691] Furthermore, the device uses its built-in camera to analyze the user's emotional state in real time. This emotional analysis utilizes facial recognition and voice analysis technologies to capture the user's feelings. Based on the emotional state, the service content and presentation methods are personalized, providing the user with a selection of agricultural products that are suitable for them.

[0692] If a user agrees with the proposal, they can quickly invest funds using an electronic payment API. The profits resulting from the investment are calculated through a profit calculation process and distributed to the user.

[0693] For example, if the emotion engine analyzes that a user is in a relaxed mood on holiday, it will suggest a low-risk, small-scale investment plan and provide basic educational content about agriculture (for example, a video introducing the crop growing process).

[0694] Examples of prompts for a generative AI model include:

[0695] "Based on an analysis of the user's current emotional state, which is relaxed, please suggest a recommended low-risk agricultural investment plan."

[0696] These are some examples.

[0697] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0698] Step 1:

[0699] The server uses APIs from external data providers to collect market and weather data. The input is data retrieved from the API, and the output is a well-organized dataset. Before being stored in the database, the data undergoes preprocessing, including format conversion and imputation of missing values.

[0700] Step 2:

[0701] The server uses a generative model to analyze collected market and weather data. The input is a pre-processed dataset, and the output is forecast information about future market demand. Machine learning algorithms are used for the analysis, including multivariate and time series analysis.

[0702] Step 3:

[0703] The user enters their investment information from the terminal. This information includes the user's investment amount, risk tolerance, and preferred crop types, while the output is user profile information. The terminal sends the entered information to the server and updates the profile.

[0704] Step 4:

[0705] The server selects the most suitable farmland based on the user profile. Inputs are user profiles and data on abandoned farmland, while output is information on the selected farmland. This process utilizes a Geographic Information System (GIS) for map analysis.

[0706] Step 5:

[0707] The device uses its built-in camera to analyze the user's emotional state. The input is real-time image data, and the output is an estimated emotional state (e.g., relaxed, excited, anxious). It utilizes an emotion analysis library to analyze emotions from facial expressions and voice.

[0708] Step 6:

[0709] The server proposes a personalized cultivation plan based on estimated emotional states and user profiles. Inputs are emotional states, user profiles, and predicted market demand; output is the proposed agricultural investment plan. A generative AI model is used to develop appropriate crop selections and investment plans.

[0710] Step 7:

[0711] The user reviews the proposal and decides whether to invest. The input is the proposed investment plan, and the output is the instruction to execute the investment. The user reviews it on their terminal and prepares to make the payment.

[0712] Step 8:

[0713] The server uses an electronic payment API to execute user investments and complete transactions. Input is the user's payment information, and output is a transaction completion notification. A secure communication protocol is used for the payment process.

[0714] Step 9:

[0715] The server calculates profits and distributes them to users. Inputs are investment results and market data, and output is a notification of profit results to users. A profit distribution algorithm is used to ensure fair distribution.

[0716] Step 10:

[0717] The device updates and provides learning content to the user based on their emotional state. The input is the updated emotional state and learning history, and the output is new educational content. An educational plan is then executed using a generative AI model.

[0718] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0719] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0720] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and specific processing may also be performed by the headset terminal 314.

[0721] [Fourth Embodiment]

[0722] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0723] As shown in Figure 7, the 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.

[0724] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0725] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0726] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0727] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0728] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0729] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive 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 robot 414's emotions can be expressed by controlling these motors. Furthermore, the robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0730] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0731] The specific processing program 56 is an example of a "program" relating to the technology of this 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.

[0732] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0733] In robot 414, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0734] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0735] This invention provides a system that enables effective management and investment in agriculture using generative models. Embodiments of this system are described in detail below.

[0736] User registration and profile settings:

[0737] Users create a profile by entering information about their interests, investment capabilities, and agricultural experience through a dedicated application. The terminal receives this information, performs the necessary data validation, and then sends it to the server. The server stores this data in a database and uses it for subsequent analysis and recommendations.

[0738] Market and weather data collection:

[0739] The server collects market and weather data from external data providers via APIs. Market data includes price trends and consumption patterns for agricultural products, while weather data includes future temperatures, precipitation, and sunshine duration. The server analyzes this data, which is then used by generative models for later predictions.

[0740] Gathering information on abandoned farmland:

[0741] The server collects information about abandoned farmland from public databases and municipal records. This includes information such as land size, soil quality, and proximity to water sources. The server uses this information to create a list of available farmland.

[0742] Demand forecasting and crop recommendations:

[0743] The server uses a generative model to analyze collected market and weather data and forecast demand for agricultural projects. This generates specific suggestions on which crops should be cultivated. Based on the user's profile information, a list of the most suitable crops is generated and presented to the user.

[0744] Farmland selection and investment decision-making:

[0745] The user makes investment decisions based on the presented list of crops. Based on the selected crops, the server selects the most suitable abandoned farmland and provides that information to the user. The user then chooses a specific plot of land and decides to invest in it.

[0746] Agricultural planning and management:

[0747] The server utilizes generative models to create a cultivation plan tailored to the selected farmland and crops. This plan includes sowing dates, irrigation schedules, and fertilization plans. Detailed steps are provided to the user via a terminal to support the execution of the plan.

[0748] Profit sharing:

[0749] The harvested crops are sold at the optimal price based on market analysis. The server calculates the sales and distributes the profits according to the user's investment amount. Information regarding profit distribution is notified to the user via their terminal.

[0750] This system enables users to make appropriate investment decisions and achieve effective agricultural management. This promotes the utilization of unused, abandoned farmland and generates sustainable agricultural revenue.

[0751] The following describes the processing flow.

[0752] Step 1:

[0753] The user opens the application and registers. The user enters details such as their name, contact information, investment amount, and agricultural experience. The terminal receives the entered information, validates the data, and then sends it to the server. The server stores the received information in a database and creates a user profile.

[0754] Step 2:

[0755] The server continuously collects information on price trends and demand patterns in the agricultural market using APIs from external data providers. Simultaneously, weather data includes predicted future temperatures, precipitation, and sunshine duration. This data is stored in a database and prepared for use in generative models.

[0756] Step 3:

[0757] The server collects information on abandoned farmland from local government and public databases. This information includes the location, size, soil quality, and proximity to water sources. The server organizes this data and builds datasets to identify usable farmland.

[0758] Step 4:

[0759] The server uses collected market and weather data to run a generative model and predict future demand for agricultural products. The generated demand forecast shows the market opportunity for specific crops. Based on this information, the server creates a list of crops best suited to the user's profile and sends it to the terminal.

[0760] Step 5:

[0761] The terminal displays investment candidates based on a list of crops and demand forecast data received from the server. The user reviews the list and selects which project to invest in. Once the user makes a decision, that information is sent from the terminal to the server.

[0762] Step 6:

[0763] Based on the user's selection, the server executes a process to select the most suitable abandoned farmland. It filters the data of available land, selects the land best suited for crop cultivation, and proposes it to the user. Once the user reviews the proposal and selects the land, the server records the information and supports the contract procedures.

[0764] Step 7:

[0765] The server creates an optimal farming plan for the selected farmland. This plan includes details such as crop planting, fertilization, irrigation schedules, and harvest plans. The server sends this plan to the terminal, providing the user with a detailed implementation guide.

[0766] Step 8:

[0767] As harvest time approaches, the server re-analyzes market data to determine the optimal timing and channels for sales. The harvested crops are then shipped to market based on the generated sales strategy.

[0768] Step 9:

[0769] The server calculates the total sales revenue of agricultural products and distributes the profits based on the user's investment amount. Details of the profit distribution are notified to the user via their terminal, and the user receives their share of the profits.

[0770] This will enable the system to efficiently utilize abandoned farmland and support the maximization of profits in agricultural projects.

[0771] (Example 1)

[0772] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0773] Conventional agricultural management systems make it time-consuming to forecast individual market demand and select appropriate farmland, and it is difficult to create highly profitable cultivation plans. This has resulted in challenges such as the ineffective utilization of abandoned farmland and insufficient profit distribution to users. To solve these problems, there is a need to provide a system that efficiently analyzes market data and weather information to support optimal crop cultivation and profit management.

[0774] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0775] In this invention, the server includes a computation means for analyzing market demand and weather conditions for agricultural products using a generative model and generating a crop cultivation plan; a means for receiving investment information from users and matching it with information on abandoned farmland to select the optimal farmland; and an information processing means for applying the cultivation plan using the generative model to the selected farmland and supporting the execution of the plan. This enables the efficient proposal of highly profitable agricultural projects, promotes the utilization of abandoned farmland, and allows for profit sharing with users.

[0776] A "generative model" is a model that uses machine learning algorithms to analyze information collected from diverse data sources and generate specific predictions or suggestions.

[0777] "Market demand" refers to information that indicates consumers' willingness to purchase and purchasing trends for specific agricultural products.

[0778] "Weather conditions" refer to information that indicates meteorological factors such as temperature, precipitation, and sunshine duration in a specific region.

[0779] A "cultivation plan" is a detailed action plan for growing a specific crop, including sowing dates, irrigation schedules, and fertilization plans.

[0780] A "user" refers to someone who uses the system, inputs investment information, and receives proposals and management for agricultural projects.

[0781] "Abandoned farmland" refers to agricultural land that was previously cultivated but is no longer in use.

[0782] "Revenue calculation" is the process of calculating the income generated as a result of a specific agricultural project and distributing it to the stakeholders.

[0783] The system implementing this invention mainly includes a server, a terminal, and a user interface. Each process is as follows:

[0784] Data processing by the server

[0785] The server has means of collecting market and weather data from external data providers via APIs. This allows it to obtain information on the latest market trends and weather conditions. The collected data is analyzed using a generative AI model to develop demand forecasts for agricultural products and optimal cultivation plans. The server stores these generated results and provides them to users as needed.

[0786] User and device interface

[0787] Users access the system using a dedicated application and input information about their interests, investment capabilities, and agricultural experience. This information is received at the terminal, validated, and then sent to the server. The server uses this information to generate a user profile, which is then used to suggest future agricultural projects.

[0788] Specific example

[0789] If a user has an investment limit of 1 million yen and is interested in wheat cultivation, they register this information in the system. This information is sent to the server, and based on the generated AI model, if wheat cultivation is predicted to be highly profitable, the server presents the user with an appropriate cultivation plan and the most suitable farmland.

[0790] Example of a prompt

[0791] "My available investment is 1 million yen, and I'm interested in growing wheat, but I'm a beginner. Please propose a suitable farming plan based on these conditions."

[0792] This allows users to receive specific farming plans based on certain conditions, enabling them to make rational investment decisions and select farmland. The system promotes the utilization of unused, abandoned farmland and makes it possible to generate sustainable agricultural revenues.

[0793] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0794] Step 1: User registration and data entry

[0795] Users input information about their interests, investment capabilities, and agricultural experience using a dedicated application. The terminal receives this information and performs data validation. Specifically, it checks if the entered investment amount is a numerical value and verifies that agricultural experience is entered in a selection format. The output of this step is sent to the server as validated user information.

[0796] Step 2: Data Collection

[0797] The server collects market and weather data using APIs from external data providers. Inputs include up-to-date agricultural product price information, consumer trends, and weather forecast data. The server receives this data and stores it in a database. This information is used as input for a generative AI model. The output is raw data ready for analysis.

[0798] Step 3: Analysis using generative models

[0799] The server inputs user profiles, collected market data, and weather data into a generative AI model. The generative model analyzes these inputs to forecast demand for agricultural products. Specifically, it uses machine learning algorithms to predict future demand trends from historical data. The output is a list of agricultural products recommended to the user.

[0800] Step 4: Farmland Selection

[0801] The server selects suitable farmland from a database of abandoned land based on the crops chosen by the user. This process considers factors such as land location, soil quality, and proximity to water sources. The input is the user's selected crop information, and the output is a list of suitable farmland.

[0802] Step 5: Cultivation plan and implementation support

[0803] The server utilizes a generation AI model to create a cultivation plan suitable for the selected crops. Specifically, it includes details such as sowing time, irrigation schedule, and fertilization plan. The cultivation plan is provided to the user via a terminal, along with instructions on how to implement the plan. The input is data on the selected farmland and crops, and the output is a specific cultivation plan.

[0804] Step 6: Profit Calculation and Distribution

[0805] The server sells harvested crops at the optimal price based on market data. The calculation uses harvest yield, selling price, and cost structure as inputs to determine sales and profits. The output is revenue information distributed to users, which is notified to users via their terminals.

[0806] (Application Example 1)

[0807] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0808] A challenge in modern urban areas is that abandoned farmland is left unattended and not utilized for sustainable agricultural activities. Furthermore, urban residents have limited opportunities to participate in agricultural projects, making effective cultivation management difficult. This invention aims to provide a system that supports urban residents and enables the efficient use and monetization of underutilized land.

[0809] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0810] This invention includes a server that includes processing means for analyzing market demand and weather conditions for agricultural products using a generative model and generating a crop cultivation plan; means for receiving investment information from users and selecting optimal farmland by comparing it with information on abandoned farmland; means for applying the cultivation plan to the selected farmland, calculating profits, and distributing profits to users; and support means for urban residents to participate in agricultural projects through smart devices and manage the efficient use of abandoned farmland. This enables urban residents to easily participate in sustainable agricultural projects and to utilize unused land for effective agricultural management and profit generation.

[0811] A "generative model" is an algorithm that automatically generates new data and predictions based on a vast amount of existing data.

[0812] "Market demand" refers to the total quantity of goods that consumers in a particular market wish to purchase during a given period.

[0813] "Meteorological conditions" refer to atmospheric conditions such as weather, temperature, and precipitation in a specific region or period.

[0814] "Agricultural products" refer to plants and food produced through agriculture.

[0815] A "cultivation plan" is a detailed set of instructions for determining the timing and methods for efficiently growing a specific crop.

[0816] "Investment information" refers to financially relevant data and information necessary for decision-making that a user possesses about an investment target.

[0817] "Abandoned farmland" refers to land that was once used as agricultural land but is no longer in use.

[0818] "Urban residents" is a term that refers to citizens who live in urban areas.

[0819] "Smart devices" are a general term for electronic devices that have internet connectivity and allow users to obtain and manipulate information.

[0820] "Efficient use" means making the most of limited resources and time to achieve one's goals.

[0821] "Profit calculation" is the process of calculating the profits that can be obtained from a particular business or investment activity.

[0822] "Support measures" refer to methods and techniques that provide support to ensure that a particular task can be performed smoothly.

[0823] This invention provides a system that enables urban residents to invest in and participate in agricultural projects by utilizing generative models. The server first creates a profile based on investment information obtained from the user, which is entered via a dedicated smart device. Next, it analyzes market and weather data collected from multiple external data providers to predict market demand for agricultural products. This process utilizes a generative AI model equipped with machine learning algorithms. This allows for the selection of the most suitable crops for the user and the generation of a cultivation plan.

[0824] The terminal presents the generated cultivation plan to the user and selects the most suitable farmland by comparing it with information on abandoned farmland. At this stage, the user can select a specific plot of land and make an investment decision. After selection, the server applies the cultivation plan, calculates the profits, and distributes the profits to the user. This entire process functions as a means of realizing sustainable agriculture within a smart city.

[0825] As a concrete example, let's say person A, who lives in an urban area, accesses an application using their smartphone. Through the app, they register their investment capabilities and interests and participate in a tomato cultivation project on unused land in the suburbs. The app provides them with weather data and market trends, indicating that the land is suitable for tomato cultivation. They then participate in the project, and ultimately, the profits are distributed according to their investment.

[0826] A concrete example of a prompt for a generative model might be, "What is the best time and management method for growing tomatoes in an urban area?" This prompt prompts the system to provide a cultivation plan suitable for the given environment.

[0827] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0828] Step 1:

[0829] The server receives investment information transmitted from users via smart devices. This includes inputting the user's interests, investment capabilities, and agricultural experience. This data is stored in a database and used to generate profiles.

[0830] Step 2:

[0831] The server collects market and weather data from external data providers via APIs. This process obtains data on agricultural product price trends, consumption patterns, and weather conditions. Based on the collected data, a generative AI model makes market demand forecasts.

[0832] Step 3:

[0833] The generative AI model analyzes market and weather data to generate a list of optimal crops based on the user's profile. When prompted with "Please suggest crops suitable for cultivation under specific market and weather conditions," the analysis results will output a suggested list.

[0834] Step 4:

[0835] The terminal presents the user with a list of generated crops and prompts them to make a selection. The user chooses the crops they wish to cultivate from the presented list and makes an investment decision. At this time, based on the specifications of the selected crops, the system presents the most suitable abandoned farmland from the server.

[0836] Step 5:

[0837] The server generates a cultivation plan based on the user's selections. This plan specifically designs the sowing period, irrigation schedule, and fertilization plan. This plan is then provided to the user's terminal to assist with its implementation.

[0838] Step 6:

[0839] Users carry out agricultural activities based on the cultivation plan displayed on their terminal. Progress at each step is fed back to the server via the terminal, and the plan is adjusted as needed.

[0840] Step 7:

[0841] After harvesting, the server sells the crops at the optimal price based on market analysis. Profit calculations are performed, and the profits are distributed according to the user's investment. This result is then notified to the user's device.

[0842] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0843] This invention aims to build a system that provides a personalized experience tailored to the user's emotions by incorporating an emotion engine into an agricultural investment platform. The embodiments of this system are described in detail below.

[0844] User registration and profile settings:

[0845] Users access the application through their device and register. They fill in profile information, including their emotional state, and register their investment capabilities and interests with the system. The device sends this information to the server. The server stores the received information in a database and creates individual user profiles.

[0846] Collection and analysis of market and weather data:

[0847] The server uses APIs from external data providers to collect data on agricultural market trends and weather conditions. This data is stored in a database and analyzed by a generative model. Based on the collected data, the generative model predicts market demand and prepares agricultural cultivation suggestions for the user.

[0848] How the emotion engine works:

[0849] The emotion engine analyzes information and operation history entered from the user's device to infer the user's emotional state. Based on this inference, the server adjusts the interface and content to present information in a way that is most acceptable to the user.

[0850] Suggestions and choices for the user:

[0851] The server incorporates emotional data analyzed by the emotion engine to propose a customized list of crops and a cultivation plan to the user. The user receives these proposals through their terminal and decides on their investment. Throughout this process, the emotion engine monitors the user's responses in real time and adjusts the proposals as needed.

[0852] Investment decision support:

[0853] The emotion engine fine-tunes the feedback method to make the user more receptive to the cultivation plan they have chosen. For example, if a user is feeling anxious, it helps to increase their sense of security by providing detailed information about the risks and benefits of the investment.

[0854] Revenue sharing and learning platform:

[0855] When revenue is generated, the server calculates the revenue and distributes it to the user. The distribution results are notified to the user via their device. In addition, the emotion engine updates learning content based on the user's interests and emotional state, supporting continuous education about agriculture.

[0856] For example, if a user is feeling anxious about their first agricultural investment, the emotion engine can recognize that emotion and add reassuring supplementary information to make suggestions. This allows users to make investment decisions with greater confidence and provides an agricultural experience tailored to their individual needs.

[0857] The following describes the processing flow.

[0858] Step 1:

[0859] Users access the application through their device and register. They enter information such as their name, contact details, investment intentions, and emotional tendencies. The device sends this information to the server, which stores it in a database and generates a user profile.

[0860] Step 2:

[0861] The server periodically collects market and weather data through APIs from external data providers. Market data includes price trends and demand forecasts for agricultural products, while weather data includes temperature, precipitation, and sunshine duration. The server analyzes this data using generative models and makes demand forecasts based on these analyses.

[0862] Step 3:

[0863] The server activates an emotion engine and analyzes the user's emotional state based on past operation logs obtained from the user's terminal and directly entered emotional information. The analysis results are reflected in the user's profile and used to make future suggestions.

[0864] Step 4:

[0865] The server creates a list of crops and an investment plan based on the collected data and analysis results. This list includes the optimal crops reflecting the current market conditions and is structured to present information in a way that suits the user's emotional state. The server then sends this information to the terminal.

[0866] Step 5:

[0867] The terminal displays a list of crops and investment plans sent from the server to the user. Based on the analysis results of the emotion engine, the order of the displayed content and the level of detail in the explanations are adjusted. The user reviews this, selects projects that interest them, and decides to invest.

[0868] Step 6:

[0869] The server receives the user's selection and identifies the most suitable abandoned farmland. The selection is based on crop characteristics, land conditions, and the user's investment strategy. Detailed information about the proposed farmland is sent to the terminal for the user to review.

[0870] Step 7:

[0871] The server creates an optimal cultivation plan for the selected farmland based on a generative model. This plan includes sowing, fertilization, and irrigation schedules, enabling real-time agricultural management. The server sends the plan to the terminal, prompting the user to execute it.

[0872] Step 8:

[0873] As harvest time approaches, the server re-evaluates market and weather data to determine the optimal sales strategy. The emotion engine takes into account the user's current emotional state and presents information in a way that minimizes stress.

[0874] Step 9:

[0875] The server compiles sales results, calculates revenue, and distributes it to users based on prior investment information. The terminal notifies users of the distribution results and supports the process of depositing the revenue into their accounts. The emotion engine monitors user satisfaction and provides feedback.

[0876] This will enable the creation of a personalized agricultural investment platform tailored to each individual user.

[0877] (Example 2)

[0878] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0879] In modern agricultural investment, there is a need for systems that enable users to effectively utilize diverse market and weather data and make investment decisions based on their individual emotional states. However, properly analyzing this data and providing users with the most relevant information is not easy. In particular, providing a personalized experience that takes user emotions into account is not yet fully realized with current technology.

[0880] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0881] This invention includes a server that uses a generative model to analyze market demand and weather conditions for agricultural products and generates a crop cultivation plan; a server that receives investment information from users and matches it with information on abandoned farmland to select the optimal farmland; and a server that uses an emotion engine to analyze the user's emotional state and adjust the user interface and content accordingly. This enables the user to receive personalized investment suggestions based on their emotions and make investment decisions with confidence.

[0882] A "generative model" is a technique that uses machine learning algorithms to analyze market data and weather data obtained from multiple data sources and generate outputs that are aligned with a specific purpose.

[0883] An "emotion engine" is a technology that analyzes a user's operation history and input information to infer the user's emotional state and then individually adjusts information content and user interfaces based on that.

[0884] "Investment information" refers to individual data that users provide when making agricultural investments, such as the amount of funds and the investment targets.

[0885] "Abandoned farmland" refers to agricultural land that was once cultivated but is no longer in use, and it serves as a source of information for selecting land suitable for new cultivation activities.

[0886] A "customized crop list" is a list of recommended crops generated by the emotion engine and individually created based on the user's emotions and interests.

[0887] This invention provides a system that enables users to make efficient and emotion-based agricultural investments. Specifically, it combines a generative AI model and an emotion engine to provide users with personalized cultivation plans and investment suggestions.

[0888] The server automatically collects data on agricultural market trends and weather conditions using APIs from external data providers. This data is analyzed using a generative AI model to help generate market demand forecasts and crop cultivation plans. The generative AI model learns from information gathered from various data sources and provides optimal output.

[0889] Users input information about their emotional state and investment capabilities through their devices and send it to the server. The emotion engine analyzes the input from the device and the user's operation history to infer the user's emotional state. Based on this inference, the server adjusts the information content and user interface to facilitate effective communication.

[0890] Furthermore, the system has a function to select farmland suitable for the user by integrating information on abandoned farmland. A generated cultivation plan is applied to the selected farmland, and profit calculations are performed based on that plan. If profits are generated, they are then distributed to the user.

[0891] For example, if a user making their first agricultural investment feels anxious, the emotion engine effectively captures this emotion. The server then provides detailed information about the investment's risks and benefits to reassure the user, supporting them in making a confident decision. In this way, flexible investment suggestions tailored to the user's emotions become possible.

[0892] An example of a prompt to input into the generating AI model is: "Based on the latest agricultural market data, please propose a cultivation plan for the next season. Also, please consider crops the user has shown interest in in the past and provide additional information that the emotion engine should add to alleviate the user's concerns."

[0893] Therefore, this invention can provide an emotion-based, personalized agricultural investment experience.

[0894] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0895] Step 1:

[0896] Users access the application and register through their devices. Input information includes data on the user's emotional state, investment capacity, and interests. This input information is organized by the device and sent to the server. The server receives the data and stores it in a database to create a user profile. This profile forms the basis for future personalized recommendations.

[0897] Step 2:

[0898] The server collects market and weather data using APIs from external data providers. This input data includes information on current market trends and weather conditions. The server stores this data in a database and performs analysis using a generative AI model. Specifically, it generates market demand forecasts and crop cultivation plans based on the data. The output provides forecast information and data necessary for recommendations.

[0899] Step 3:

[0900] The emotion engine receives operation history and emotion information entered from the user's device and analyzes the user's emotional state. This analysis infers the user's emotional state. Based on this inference, the server processes the data to adjust the user interface and the information presented. For example, the order in which information is presented, the colors used, and the font size may be changed.

[0901] Step 4:

[0902] The server incorporates information analyzed by the emotion engine to generate a personalized list of crops and a cultivation plan for each user. Emotional data and predictive information from the generative AI model are used as input. As output, suggestions are created for the user and sent to them via their device.

[0903] Step 5:

[0904] The user receives suggestions from their device and makes an investment choice. The emotion engine monitors the user's reactions in real time as they make their choice, adjusting the suggestions and presentation methods as needed. The output records the final decision based on the user's selection.

[0905] Step 6:

[0906] The server calculates profits based on the selected cultivation plan. It uses projected profits and risk assessments as input data to calculate detailed investment results. The resulting profit information is distributed to the user and notified via their device. Furthermore, the emotion engine updates learning content based on the user's emotional state, supporting continuous education for future investments.

[0907] (Application Example 2)

[0908] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0909] Modern agricultural investment systems require the provision of personalized investment experiences that take into account the individual emotional states of investors. However, conventional systems struggle to provide dynamic suggestions that consider investors' emotions, limiting improvements in the user experience. Therefore, more effective support is needed to enable investors to make investment decisions with confidence.

[0910] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0911] This invention includes a server that uses a generative model to analyze market demand and weather conditions for agricultural products and generates a crop cultivation plan; a server that receives investment information from users and matches it with information on abandoned farmland to select the optimal farmland; and a server that analyzes the user's emotional state, personalizes crop choices based on that, provides real-time emotional feedback, and supports investment decision-making. This enables individualized responses tailored to the user's emotions, making it possible to support safer and more efficient investment decision-making.

[0912] A "generative model" is a system that uses various algorithms and data to create or analyze new information.

[0913] "Market demand" is an indicator that shows the degree of consumer and industry willingness to purchase a particular agricultural product.

[0914] "Weather conditions" refer to atmospheric conditions such as temperature, precipitation, wind speed, and humidity, and are factors that have a significant impact on agricultural production.

[0915] A "cultivation plan" is a detailed plan that specifies which crops to cultivate and how to cultivate them on a particular plot of land.

[0916] "Investment information" refers to information that shows how much money a user will invest and how they will invest it in the agricultural sector.

[0917] "Abandoned farmland" refers to agricultural land that was previously cultivated but has been abandoned for some reason and is no longer in use.

[0918] Personalization is the act of adjusting and optimizing suggestions and services based on an individual's characteristics and preferences.

[0919] "Profit calculation" is the process of quantifying and calculating the profits and losses obtained from a particular investment activity.

[0920] An "emotional state" refers to a set of psychological and physiological responses that an individual experiences at a particular moment.

[0921] "Investment decision support" refers to support activities that provide information and feedback to help users make better investment choices.

[0922] As an embodiment for carrying out this invention, the configuration and operation of a system using an electronic computer will be described.

[0923] First, the server uses a generative model to collect market and weather data from multiple data sources and uses this data to predict market demand for agricultural products. Typically, APIs from external data providers are used to collect market data. The collected data is stored in a database and analyzed by machine learning algorithms. The results of this analysis are then used to generate cultivation plans for the user.

[0924] Users access the system from devices such as smartphones and input their investment information. The data entered on the device is sent to a server and cross-referenced with information on abandoned farmland. This allows for the selection of the most suitable farmland and the creation of a cultivation plan tailored to the user.

[0925] Furthermore, the device uses its built-in camera to analyze the user's emotional state in real time. This emotional analysis utilizes facial recognition and voice analysis technologies to capture the user's feelings. Based on the emotional state, the service content and presentation methods are personalized, providing the user with a selection of agricultural products that are suitable for them.

[0926] If a user agrees with the proposal, they can quickly invest funds using an electronic payment API. The profits resulting from the investment are calculated through a profit calculation process and distributed to the user.

[0927] For example, if the emotion engine analyzes that a user is in a relaxed mood on holiday, it will suggest a low-risk, small-scale investment plan and provide basic educational content about agriculture (for example, a video introducing the crop growing process).

[0928] Examples of prompts for a generative AI model include:

[0929] "Based on an analysis of the user's current emotional state, which is relaxed, please suggest a recommended low-risk agricultural investment plan."

[0930] These are some examples.

[0931] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0932] Step 1:

[0933] The server uses APIs from external data providers to collect market and weather data. The input is data retrieved from the API, and the output is a well-organized dataset. Before being stored in the database, the data undergoes preprocessing, including format conversion and imputation of missing values.

[0934] Step 2:

[0935] The server uses a generative model to analyze collected market and weather data. The input is a pre-processed dataset, and the output is forecast information about future market demand. Machine learning algorithms are used for the analysis, including multivariate and time series analysis.

[0936] Step 3:

[0937] The user enters their investment information from the terminal. This information includes the user's investment amount, risk tolerance, and types of crops they are interested in, and the output is user profile information. The terminal sends the entered information to the server and updates the profile.

[0938] Step 4:

[0939] The server selects the most suitable farmland based on the user profile. Inputs are user profiles and data on abandoned farmland, while output is information on the selected farmland. This process utilizes a Geographic Information System (GIS) for map analysis.

[0940] Step 5:

[0941] The device uses its built-in camera to analyze the user's emotional state. The input is real-time image data, and the output is an estimated emotional state (e.g., relaxed, excited, anxious). It utilizes an emotion analysis library to analyze emotions from facial expressions and voice.

[0942] Step 6:

[0943] The server proposes a personalized cultivation plan based on estimated emotional states and user profiles. Inputs are emotional states, user profiles, and predicted market demand; output is the proposed agricultural investment plan. A generative AI model is used to develop appropriate crop selections and investment plans.

[0944] Step 7:

[0945] The user reviews the proposal and decides whether to invest. The input is the proposed investment plan, and the output is the instruction to execute the investment. The user reviews it on their terminal and prepares to make the payment.

[0946] Step 8:

[0947] The server uses an electronic payment API to execute user investments and complete transactions. Input is the user's payment information, and output is a transaction completion notification. A secure communication protocol is used for the payment process.

[0948] Step 9:

[0949] The server calculates profits and distributes them to users. Inputs are investment results and market data, and output is a notification of profit results to users. A profit distribution algorithm is used to ensure fair distribution.

[0950] Step 10:

[0951] The device updates and provides learning content to the user based on their emotional state. The input is the updated emotional state and learning history, and the output is new educational content. An educational plan is then executed using a generative AI model.

[0952] 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 controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0953] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0954] 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 this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[0955] Furthermore, the emotion identification model 59, acting 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 a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0956] Figure 9 shows an emotion map 400 in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0957] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0958] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0959] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, motorcycles, etc., emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0960] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is 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 the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0961] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0962] The above description primarily focuses on the functions of the data processing device 12 in relation to this disclosure. However, the system related to this disclosure is not necessarily implemented on a server. The system related to this disclosure may be implemented as a general information processing system. This disclosure may be implemented, for example, as a software program that runs on a personal computer or as an application that runs on a smartphone. The method related to this disclosure may be provided to users in SaaS (Software as a Service) format.

[0963] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing of the specific process may be performed by multiple computers, including computer 22. For example, a data generation model 58 may be provided in an external device of the data processing device 12, and the external device may generate data according to the input data.

[0964] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0965] 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.

[0966] Furthermore, it is not necessary to store the entirety 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 the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0967] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0968] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of 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). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0969] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0970] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0971] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and the like that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0972] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted as being incorporated by reference.

[0973] The following is further disclosed regarding the embodiments described above.

[0974] (Claim 1)

[0975] A processing means for analyzing market demand and weather conditions for agricultural products using a generative model, and for generating a cultivation plan for agricultural products.

[0976] A method for receiving investment information from users, comparing it with information on abandoned farmland, and selecting the most suitable farmland,

[0977] A means of applying a cultivation plan to selected farmland, calculating profits, and distributing those profits to users,

[0978] A system that includes this.

[0979] (Claim 2)

[0980] The system according to claim 1, wherein the generative model uses a machine learning algorithm that uses market data and weather data from multiple data sources.

[0981] (Claim 3)

[0982] The system according to claim 1, which provides a learning platform based on a generative model for educating the user on agricultural experiences.

[0983] "Example 1"

[0984] (Claim 1)

[0985] A computational means for analyzing market demand and weather conditions for agricultural products using a generative model and generating a crop cultivation plan,

[0986] A method for receiving investment information from users, comparing it with information on abandoned farmland, and selecting the most suitable farmland,

[0987] An information processing means that applies a cultivation plan using a generative model to selected farmland and supports the execution of the plan,

[0988] A means of calculating revenue and distributing it to users,

[0989] A system that includes this.

[0990] (Claim 2)

[0991] The system according to claim 1, wherein the generative model uses market data and weather data from multiple sources and uses a predictive model algorithm.

[0992] (Claim 3)

[0993] The system according to claim 1, which provides an educational platform based on a generative model for providing the user with practical experience related to agriculture.

[0994] "Application Example 1"

[0995] (Claim 1)

[0996] A processing means for analyzing market demand and weather conditions for agricultural products using a generative model, and for generating a cultivation plan for agricultural products.

[0997] A method for receiving investment information from users, comparing it with information on abandoned farmland, and selecting the most suitable farmland,

[0998] A means of applying a cultivation plan to selected farmland, calculating profits, and distributing those profits to users,

[0999] A support system that enables urban residents to participate in agricultural projects through smart devices and manage the efficient use of abandoned farmland,

[1000] A system that includes this.

[1001] (Claim 2)

[1002] The system according to claim 1, wherein the generative model uses a machine learning algorithm that uses market data and weather data from multiple data sources.

[1003] (Claim 3)

[1004] The system according to claim 1, which provides a learning platform based on a generative model for educating the user on agricultural experiences.

[1005] "Example 2 of combining an emotion engine"

[1006] (Claim 1)

[1007] A means for analyzing market demand and weather conditions for agricultural products using a generative model and generating a crop cultivation plan,

[1008] A method for receiving investment information from users, comparing it with information on abandoned farmland, and selecting the most suitable farmland,

[1009] A means of applying a cultivation plan to selected farmland, calculating profits, and distributing those profits to users,

[1010] A means of analyzing a user's emotional state using an emotion engine and adjusting the user interface and content accordingly.

[1011] A method for incorporating emotional data to suggest a customized list of crops and cultivation plan to the user,

[1012] A system that includes this.

[1013] (Claim 2)

[1014] The system according to claim 1, wherein the generative model uses a machine learning algorithm that employs market data and weather data from multiple data sources, and further, an emotion engine analyzes the user's operation history.

[1015] (Claim 3)

[1016] The system according to claim 1, which provides a learning platform based on a generative model for educating the user on agricultural experiences, and further adjusts the learning content based on the user's emotional state.

[1017] "Application example 2 when combining with an emotional engine"

[1018] (Claim 1)

[1019] A processing means for analyzing market demand and weather conditions for agricultural products using a generative model, and for generating a cultivation plan for agricultural products.

[1020] A method for receiving investment information from users, comparing it with information on abandoned farmland, and selecting the most suitable farmland,

[1021] A means of applying a cultivation plan to selected farmland, calculating profits, and distributing those profits to users,

[1022] A means of analyzing the user's emotional state and personalizing the selection of agricultural products based on that,

[1023] A means of providing real-time emotional feedback to support investment decision-making,

[1024] A system that includes this.

[1025] (Claim 2)

[1026] The system according to claim 1, wherein the generative model uses a machine learning algorithm with market data and weather data from multiple data sources.

[1027] (Claim 3)

[1028] The system according to claim 1, which provides a learning platform that updates educational content based on the user's emotional state and supports the agricultural investment experience. [Explanation of symbols]

[1029] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. A processing means for analyzing market demand and weather conditions for agricultural products using a generative model, and for generating a cultivation plan for agricultural products. A method for receiving investment information from users, comparing it with information on abandoned farmland, and selecting the most suitable farmland, A means of applying a cultivation plan to selected farmland, calculating profits, and distributing those profits to users, A system that includes this.

2. The system according to claim 1, wherein the generative model uses a machine learning algorithm that uses market data and weather data from multiple data sources.

3. The system according to claim 1, which provides a learning platform based on a generative model for educating the user on agricultural experiences.

Images