System

Abstract

To provide a system.SOLUTION: A system comprises: means for collecting crop growth data using IoT devices applicable to agriculture; means for generating crop cultivation advice on the basis of the growth data using generative AI; means for recognizing the emotional state of a user by using an emotion engine and adjusting the cultivation advice by the generative AI on the basis of the emotional state of the user; and means for outputting the adjusted cultivation advice.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] In conventional agriculture, it is difficult to accurately grasp the growth status of crops and provide optimal cultivation advice, as well as to properly adjust the amount of nutrients and water required by growers. [Means for solving the problem]

[0005] This invention uses an IoT device specialized for agriculture to monitor crop growth in real time and provides cultivation advice using generative AI. Furthermore, users can check the status of their crops via smartphone and adjust the amount of nutrients and water they need. This enables agricultural producers to maintain an optimal cultivation environment and produce better quality crops. [Brief explanation of the drawings]

[0006] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 11] FIG. 2 is a sequence diagram showing a flow of processing in the data processing system according to the first embodiment of the first form example. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1 of Embodiment 1. [Figure 13] FIG. 10 is a sequence diagram showing a processing flow of a data processing system in a second embodiment of the second form example. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 of Embodiment Example 2. [Figure 15] FIG. 10 is a sequence diagram showing the flow of processing in a data processing system according to a third embodiment of the third embodiment. [Figure 16]FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 3 of Embodiment 3. [Figure 17] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in the first embodiment of the first form example when an emotion engine is combined. [Figure 18] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1 of Form Example 1 when an emotion engine is combined. [Figure 19] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in the second embodiment of the second form example when an emotion engine is combined. [Figure 20] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 of Form Example 2 when an emotion engine is combined. [Figure 21] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in the third embodiment of the third form example when an emotion engine is combined. [Figure 22] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 3 of Form Example 3 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0007] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

[0008] First, the terms used in the following description will be explained.

[0009] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, the processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), or a TPU (TENSOR PROCESSING UNIT (registered trademark)).

[0010] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

[0011] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0012] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0013] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0014] [First embodiment]

[0015] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0016] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0017] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0018] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0019] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0020] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0021] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

[0022] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0023] 2, in the data processing device 12, a specific process is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0024] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0025] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with the specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0026] Next, the specific processing by the specific processing unit 290 of the data processing device 12 will be described.

[0027] "Example 1"

[0028] As an example of the present invention, an IoT device specialized for agriculture collects data on soil humidity, temperature, pH, nutrient concentration, etc. in real time. This IoT device has wireless communication capabilities and transmits the collected data to a cloud server.

[0029] "Example 2"

[0030] The generative AI analyzes the growth status of crops based on data stored on a cloud server and generates cultivation advice, such as the appropriate amount of nutrients to add, the amount of water to supply, and temperature adjustments to create the optimal environment for crop growth.

[0031] "Example 3"

[0032] Users can receive cultivation advice from generative AI through a dedicated smartphone application. The application also visually displays data collected from IoT devices, allowing users to intuitively understand the growth status of their crops. Specifically, data such as soil humidity, temperature, and nutrient concentration are displayed in graph form, allowing users to understand the growth status of their crops by comparing it with past data.

[0033] The processing flow of each embodiment will be described below.

[0034] "Example 1"

[0035] Step 1: Agriculturally-specific IoT devices collect real-time data such as soil moisture, temperature, pH, and nutrient concentration.

[0036] Step 2: The IoT device has wireless communication capabilities and transmits the collected data to the cloud server.

[0037] "Example 2"

[0038] Step 1: The generative AI analyzes the growth status of crops based on data stored on the cloud server.

[0039] Step 2: The generative AI generates cultivation advice based on the analysis results. The advice generated suggests the optimal environment for growing crops, including the appropriate amount of nutrients to add, the amount of water to supply, and temperature adjustments.

[0040] "Example 3"

[0041] Step 1: Users can receive cultivation advice from generative AI through a dedicated smartphone application.

[0042] Step 2: The application visually displays the data collected from the IoT device, allowing users to intuitively understand the growth status of their crops. Specifically, data such as soil humidity, temperature, and nutrient concentration are displayed in graph form, allowing users to understand the growth status of their crops by comparing it with past data.

[0043] Example 1

[0044] Next, a description will be given of Example 1 of Form Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0045] In conventional agriculture, it is difficult to manually collect data such as soil humidity, temperature, pH, and nutrient concentration to obtain appropriate cultivation advice. Furthermore, because data collection and analysis are not performed in real time, there is a problem in that it is not possible to respond quickly to crop growth conditions. Furthermore, users need specialized knowledge to obtain appropriate cultivation advice, which is a high hurdle for ordinary farmers.

[0046] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0047] In this invention, the server includes: means for collecting soil humidity, temperature, pH, and nutrient concentration in real time using an IoT device specialized for agriculture; means for transmitting the collected data to a cloud server using wireless communication functions; means for the cloud server to receive the data and store it in a database; means for analyzing the data using a generative AI model and generating cultivation advice; and means for the user to check the analysis results on a terminal and adjust the amount of necessary nutrients and water. This enables real-time data collection and analysis, allowing users to obtain appropriate cultivation advice even without specialized knowledge.

[0048] "IoT devices specialized for agriculture" are devices that incorporate sensors and communication modules used in the agricultural field and are used to collect soil and environmental data.

[0049] "Soil moisture" is an indicator of the percentage of water contained in the soil.

[0050] "Temperature" is an indicator of the state of thermal energy in the soil and the environment.

[0051] "pH" is an indicator of the acidity or alkalinity of soil.

[0052] "Nutrient concentration" is an indicator that shows the concentration of nutrients such as nitrogen, phosphorus, and potassium contained in the soil.

[0053] "Wireless communication function" refers to technology for wirelessly sending and receiving data, including Wi-Fi and Bluetooth.

[0054] A "cloud server" is a remote server that stores and processes data over the Internet.

[0055] A "database" is a system for systematically storing and managing collected data.

[0056] A "generative AI model" is an algorithm that uses machine learning and artificial intelligence techniques to analyze data and generate predictions and advice.

[0057] A "terminal" is a device that a user uses to check or operate information, and includes smartphones, tablets, PCs, etc.

[0058] "Analysis results" are the information and advice obtained after analyzing data using a generative AI model.

[0059] "Cultivation advice" is information that provides specific instructions and suggestions for growing crops based on data analyzed by the generative AI model.

[0060] This invention is a system that uses IoT devices specialized for agriculture to collect soil humidity, temperature, pH, and nutrient concentration in real time, and provides cultivation advice using a generative AI model. Specific embodiments of this system are described below.

[0061] Hardware and Software Configuration

[0062] IoT device

[0063] The IoT devices that users install on their farms contain the following sensors:

[0064] Humidity sensor

[0065] temperature sensor

[0066] pH Sensor

[0067] Nutrient Sensor

[0068] These sensors measure soil moisture, temperature, pH, and nutrient concentration. The IoT devices are equipped with a microcontroller to collect data and send it to a cloud server via wireless communication modules (e.g., Wi-Fi, Bluetooth).

[0069] Cloud Server

[0070] The cloud server receives data sent from the IoT devices and stores it in a database (e.g., Amazon® RDS, Google® Cloud Firestore). The server analyzes the data using a generative AI model (e.g., OpenAI®'s GPT-4®) and generates cultivation advice.

[0071] Terminal

[0072] Users can check the analysis results sent from the cloud server using devices such as smartphones, tablets, and PCs. A dedicated application is installed on the device, allowing users to receive cultivation advice in real time.

[0073] Specific examples

[0074] For example, consider a case where a user installs an IoT device on a farm where tomatoes are grown. The IoT device uses a humidity sensor to measure the humidity of the soil and detects that the humidity is 30%. This data is sent to a cloud server using a wireless communication module.

[0075] The cloud server receives the 30% humidity data and stores it in Amazon RDS. The stored data is then input into a generative AI model (GPT-4), which generates advice such as "The soil moisture is decreasing. Please activate the irrigation system."

[0076] This advice is sent from the cloud server to the user's smartphone. The user checks the notification on their smartphone and receives a message saying, "The soil moisture is decreasing. Please operate the irrigation system."

[0077] Prompt Sentence Examples

[0078] "The soil moisture in the farm where I grow tomatoes has dropped to 30%. Please tell me the best way to irrigate them."

[0079] In this way, users can grasp the condition of their farmland in real time and take appropriate measures. This system makes it possible to cultivate crops efficiently, even without specialized knowledge.

[0080] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0081] Step 1:

[0082] The IoT device installed by the user in the farmland uses built-in sensors to measure the humidity, temperature, pH, and nutrient concentration of the soil. For example, a humidity sensor measures the humidity of the soil and detects that the humidity is 30%.

[0083] Inputs: Soil moisture, temperature, pH, nutrient concentration

[0084] Output: Measured data (e.g. humidity 30%)

[0085] Step 2:

[0086] The IoT device sends the collected data to a cloud server via a wireless communication module (e.g., Wi-Fi or Bluetooth). For example, the wireless communication module is used to send data on humidity of 30% to the cloud server.

[0087] Input: Measured data (e.g. humidity 30%)

[0088] Output: Data sent to the cloud server

[0089] Step 3:

[0090] The server receives data sent from IoT devices and stores it in a database (e.g., Amazon RDS, Google Cloud Firestore). The server checks the integrity of the data and stores it in the database in the appropriate format.

[0091] Input: Data sent to the cloud server

[0092] Output: Data stored in the database

[0093] Step 4:

[0094] The server inputs the stored data into a generative AI model (e.g., OpenAI's GPT-4) and analyzes the data. For example, if the soil moisture level is declining, the AI ​​model generates advice such as, "The soil moisture level is declining. Please turn on the irrigation system."

[0095] Input: Data stored in a database

[0096] Output: Generated cultivation advice

[0097] Step 5:

[0098] The server sends the generated analysis results to the user's device, for example, by sending a notification to the user via a smartphone app or web app.

[0099] Input: Generated cultivation advice

[0100] Output: Advice sent to the user's terminal

[0101] Step 6:

[0102] The user checks the analysis results on a device (e.g., smartphone, tablet, or PC). For example, they open a smartphone app and see a notification that says, "The soil moisture is decreasing. Please turn on the irrigation system."

[0103] Input: Advice sent to the user's terminal

[0104] Output: Analysis results confirmed by the user

[0105] In this way, users can understand the condition of their farmland in real time and take appropriate measures.

[0106] (Application example 1)

[0107] Next, a description will be given of Application Example 1 of Embodiment Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0108] Conventional agricultural crop growth monitoring systems lack the ability to collect and analyze data in real time, making it difficult to provide appropriate cultivation advice. Furthermore, environmental monitoring within factories also requires rapid response when an abnormality occurs, but current systems make it difficult to achieve this.

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

[0110] In this invention, the server includes a means for monitoring the growth status of crops using an IoT device specialized for agriculture, a means for providing cultivation advice using generative AI, a means for a user to check the status of crops on a smartphone and adjust the amount of nutrients and water required, a means for collecting environmental data within the factory in real time and sending it to a cloud server, and a means for analyzing the collected data in the cloud and issuing an alert if an abnormality is detected. This makes it possible to monitor the growth status of crops in agriculture in real time and provide appropriate cultivation advice, and also enables rapid detection and response to abnormalities in environmental monitoring within the factory.

[0111] An "IoT device specialized for agriculture" is a device that collects data such as soil humidity, temperature, pH, and nutrient concentration in real time and transmits it to a cloud server using wireless communication functions.

[0112] "Means for monitoring crop growth status" refers to a method of using IoT devices specialized for agriculture to collect and analyze data on crop growth.

[0113] "Generative AI" is an artificial intelligence technology that generates appropriate cultivation advice based on collected data.

[0114] "Means for providing cultivation advice" refers to using generative AI to analyze collected data and suggest appropriate cultivation and adjustment methods to users.

[0115] "A means for users to check the status of crops on their smartphones and adjust the amount of nutrients and water required" refers to a method in which users use their smartphones to receive cultivation advice provided by generative AI, check the status of crops, and adjust the amount of nutrients and water required.

[0116] "Means for collecting environmental data within a factory in real time and transmitting it to a cloud server" refers to a method for collecting environmental data such as temperature, humidity, pH, and chemical substance concentrations within a factory in real time and transmitting it to a cloud server using wireless communication.

[0117] "Means of analyzing collected data on the cloud and issuing an alert if an abnormality is detected" refers to a method of analyzing environmental data collected on a cloud server and issuing a warning to the user if an abnormality is detected.

[0118] The system for implementing this invention includes an IoT device specialized for agriculture, generative AI, a smartphone, and a cloud server. The specific operation of each component and how they work together are described below.

[0119] First, the IoT devices specialized for agriculture collect data such as soil humidity, temperature, pH, and nutrient concentration in real time. These devices have wireless communication capabilities and transmit the collected data to a cloud server. The hardware used includes temperature sensors, humidity sensors, pH sensors, and nutrient concentration sensors.

[0120] The cloud server receives the collected data and analyzes it using generative AI. The generative AI generates appropriate cultivation advice based on the collected data. The software used includes a Python (registered trademark) program and a requests library for sending HTTP requests.

[0121] The generated cultivation advice is sent from the cloud server to the user's smartphone. The smartphone receives the advice from the generative AI and displays it to the user. The user can then use their smartphone to check the status of their crops and adjust the amount of nutrients and water they need.

[0122] This system can also be used for environmental monitoring within factories. It collects environmental data such as temperature, humidity, pH, and chemical concentration in real time and sends it to a cloud server. The cloud server analyzes the collected data and issues an alert if an abnormality is detected.

[0123] As a concrete example, consider a system that issues an alert when the temperature inside a factory exceeds 30 degrees. In this system, temperature sensors monitor the temperature inside the factory in real time and send data to a cloud server when it exceeds 30 degrees. The cloud server detects the abnormality and sends an alert to the user's smartphone.

[0124] An example of a prompt to be input to the generative AI model is as follows:

[0125] "Generate a Python program that will issue an alert if the temperature in the factory exceeds 30 degrees. The temperature data needs to be collected from the sensor and sent to a cloud server."

[0126] In this way, it becomes possible to collect and analyze data in real time, provide appropriate advice, and respond quickly to abnormalities in both agriculture and environmental monitoring within factories.

[0127] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0128] Step 1:

[0129] Agriculturally specialized IoT devices collect real-time data such as soil humidity, temperature, pH, and nutrient concentration. The input is environmental data from the sensors, and the output is the collected environmental data. Specifically, each sensor periodically measures data and stores it in the device's memory.

[0130] Step 2:

[0131] Data collected by IoT devices is sent to a cloud server via wireless communication. The input is environmental data stored in the IoT device, and the output is data sent to the cloud server. Specifically, the communication module in the device converts the data into packets and sends them to the cloud server using a wireless communication protocol.

[0132] Step 3:

[0133] The cloud server analyzes the received data and generates appropriate cultivation advice using generative AI. The input is the environmental data sent to the cloud server, and the output is the generated cultivation advice. Specifically, the analysis program on the cloud server processes the data and inputs it into the generative AI model to generate advice.

[0134] Step 4:

[0135] The cloud server sends the generated cultivation advice to the user's smartphone. The input is the generated cultivation advice, and the output is the advice sent to the smartphone. Specifically, the cloud server converts the advice into a message format and sends it to the smartphone.

[0136] Step 5:

[0137] The user checks the cultivation advice received on their smartphone and adjusts the amount of nutrients and water needed. The input is the cultivation advice displayed on the smartphone, and the output is the user's adjustment of the cultivation environment. Specifically, the user operates the smartphone application and adjusts the cultivation environment according to the advice.

[0138] Step 6:

[0139] Environmental data within the factory is collected in real time and sent to a cloud server. The input is environmental data from sensors within the factory, and the output is the data sent to the cloud server. Specifically, sensors within the factory measure temperature, humidity, pH, and chemical concentration, and send the data to the cloud server.

[0140] Step 7:

[0141] The cloud server analyzes environmental data within the factory and issues an alert if an abnormality is detected. The input is the environmental data sent to the cloud server, and the output is an alert when an abnormality is detected. Specifically, the analysis program on the cloud server monitors the data, and if an abnormality is detected, it generates an alert and sends it to the user's smartphone.

[0142] Step 8:

[0143] The user checks the alert on their smartphone and takes the necessary action. The input is the alert displayed on the smartphone, and the output is the user's response. Specifically, the user operates the smartphone application and takes the necessary action according to the alert.

[0144] Example 2

[0145] Next, a description will be given of Example 2 of Form Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0146] In conventional agriculture, it has been difficult to properly monitor crop growth and provide optimal cultivation advice. In particular, there has been a lack of real-time data collection and analysis, and the provision of specific advice based on the results, making it difficult to optimize the crop growth environment. In addition, the time and effort required for users to manually collect and analyze data has hindered efficient agricultural management.

[0147] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0148] In this invention, the server includes means for monitoring the growth status of crops using agricultural sensor devices, means for providing cultivation advice using a generative AI model based on data stored in the cloud server, means for a user to check the status of the crops on their terminal and adjust the amount of necessary nutrients and water, means for inputting prompts to the generative AI model to analyze the growth status of the crops, and means for transmitting the generated cultivation advice to the user's terminal. This enables real-time data collection and analysis, allowing users to efficiently optimize the growth environment of their crops.

[0149] A "sensor device" is an electronic device that collects data on the growth status of crops in real time.

[0150] A "cloud server" is a remote server that stores, manages, and processes data over the Internet.

[0151] A "generative AI model" is an artificial intelligence model that analyzes input data and generates output for a specific task.

[0152] A "prompt" is an instruction given to a generative AI model that contains information for performing a specific task.

[0153] "Growth advice" means specific instructions or suggestions provided to optimize crop growth.

[0154] A "terminal" is an electronic device used by a user, such as a computer, smartphone, or tablet.

[0155] A "user" is someone who uses the system to manage the growth status of crops and receive cultivation advice.

[0156] This invention is a system that uses agriculturally specialized sensor devices, cloud servers, generative AI models, prompts, and terminals to monitor crop growth and provide optimal cultivation advice.

[0157] The server uses a generative AI model to provide cultivation advice based on data stored on the cloud server. Specifically, the server uses software such as Python and TENSORFLOW® to acquire crop growth data (e.g., temperature, humidity, soil nutrient levels, etc.) stored on the cloud server. It then uses a generative AI model (e.g., GPT-4) to analyze this data and evaluate the crop's growth status. Based on the evaluation results, the server generates appropriate cultivation advice. This advice may include the appropriate amount of nutrients to add, the amount of water to provide, and temperature adjustments.

[0158] A user uses a device to access the cloud server and upload crop growth data. For example, if a user is growing tomatoes, the user uses a device to access the cloud server, input tomato growth data, and upload it. The server receives this data and inputs the following prompt sentence into the generative AI model:

[0159] Example prompt sentence:

[0160] "Analyze the growth status of tomatoes based on the following data and generate appropriate cultivation advice. Data: Temperature 25°C, humidity 60%, soil nitrogen level 20 ppm, soil moisture 30%."

[0161] Based on this prompt, the generative AI model analyzes the tomato's growth status and generates the following advice:

[0162] Example of generated advice:

[0163] "The current temperature and humidity are appropriate. The nitrogen level in the soil is low, so add nitrogen fertilizer. Also, the soil is lacking moisture, so provide an adequate amount of water."

[0164] In this way, the user can optimize the tomato growing environment based on advice provided by the server.

[0165] The system enables real-time data collection and analysis, allowing users to efficiently optimize crop growing environments.

[0166] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0167] Step 1:

[0168] The user accesses the cloud server using a terminal and uploads crop growth data.

[0169] Input: Growth data such as temperature, humidity, and soil nutrient levels.

[0170] Output: Growth data stored on a cloud server.

[0171] How it works: Users access the cloud server using a smartphone or PC, enter crop growth data through a dedicated web application or mobile app, and click the upload button.

[0172] Step 2:

[0173] The server receives the uploaded data and stores it in a database.

[0174] Input: Growth data uploaded by users.

[0175] Output: Growth data stored in a database.

[0176] What happens: The server receives the HTTP request and parses the uploaded data. It connects to the database and inserts the data into the appropriate tables. It performs validation checks to ensure the data is consistent.

[0177] Step 3:

[0178] The server generates prompt sentences based on the stored data and inputs them into the generative AI model.

[0179] Input: Growth data stored in a database.

[0180] Output: The prompt sentence that is input to the generative AI model.

[0181] Specific operation: The server reads the saved data, generates prompt sentences using a Python script, and sends the generated prompt sentences to the generative AI model via an API.

[0182] Step 4:

[0183] The server receives the analysis results from the generative AI model and generates cultivation advice.

[0184] Input: Analysis results from a generative AI model.

[0185] Output: Generated cultivation advice.

[0186] How it works: The server receives a response from the generative AI model, which includes a detailed analysis of the crop's growth status. The server then runs an algorithm based on this information to generate cultivation advice.

[0187] Step 5:

[0188] The server transmits the generated advice to the user's terminal.

[0189] Input: Generated cultivation advice.

[0190] Output: Cultivation advice sent to the user's device.

[0191] Specific operation: The server sends the generated advice to the user's device. The advice is delivered to the user via email or push notification.

[0192] Step 6:

[0193] The user checks the advice on the device and adjusts the cultivation environment.

[0194] Input: Cultivation advice sent to the user's device.

[0195] Output: Regulated growing environment.

[0196] Specific actions: The user checks the advice received on the device. According to the advice, the user adds necessary nutrients and provides water. Based on the advice, the user takes specific actions to optimize the cultivation environment.

[0197] (Application example 2)

[0198] Next, a description will be given of Application Example 2 of Form Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0199] In conventional agriculture, it has been difficult to properly monitor crop growth and maintain an optimal cultivation environment. Users also had to manually adjust the cultivation environment, which was labor-intensive and time-consuming. Furthermore, real-time data collection and analysis was insufficient, making it impossible to quickly identify factors affecting crop growth. To solve these issues, a more efficient and automated system is needed.

[0200] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0201] In this invention, the server includes a means for monitoring the growth status of crops using an IoT device specialized for agriculture, a means for providing cultivation advice using generative AI, a means for a user to check the status of the crops on a smartphone and adjust the amount of necessary nutrients and water, a means for a factory robot to automatically adjust the cultivation environment based on advice from the generative AI, and a means for the generative AI to analyze the growth status of crops based on data stored in the cloud server. This makes it possible to monitor the growth status of crops in real time and automatically maintain an optimal cultivation environment.

[0202] "Agriculturally-specific IoT devices" are internet-connected sensors and devices designed to monitor crop growth.

[0203] "Crop health" refers to the environmental conditions and health of the crop, such as temperature, humidity, and soil nutrient levels, during the growing process.

[0204] "Generative AI" is an artificial intelligence technology that analyzes crop growth conditions and generates optimal cultivation advice based on data stored on a cloud server.

[0205] "Cultivation advice" is a suggestion on the appropriate amount of nutrients to add, the amount of water to supply, temperature adjustments, etc. to maintain the optimal environment for crop growth.

[0206] "A means for users to check the status of crops on their smartphones and adjust the amount of nutrients and water needed" refers to a function that allows users to check the growth status of crops in real time using their smartphones and manually adjust the cultivation environment based on advice from the generative AI.

[0207] A "factory robot" is an automated mechanical device designed to grow crops in a factory, and has the ability to automatically adjust the growing environment based on advice from generative AI.

[0208] A "cloud server" is a remote server for storing, managing, and processing data over the Internet.

[0209] "Real-time collection" means that sensors and devices measure the current situation immediately and transmit that data immediately.

[0210] The system for implementing this invention includes IoT devices specialized for agriculture, generative AI, smartphones, factory robots, and cloud servers. The specific functions of each element and how they work together are described below.

[0211] First, agricultural IoT devices are used to monitor the growth of crops. These devices include temperature sensors, humidity sensors, soil nutrient sensors, etc., and collect data in real time. The collected data is then sent to a cloud server.

[0212] The cloud server stores the collected data, and the generative AI uses this data to analyze the crop's growth status. The generative AI then generates appropriate cultivation advice, including the appropriate amount of nutrients to add, the amount of water to provide, and temperature adjustments. The advice is then sent via the cloud server to smartphones and factory robots.

[0213] Users can use their smartphones to check real-time cultivation advice from the generative AI. The smartphone application displays the status of the crops and provides an interface for adjusting the amount of nutrients and water needed. This allows users to manually adjust the cultivation environment.

[0214] Furthermore, the factory robots can automatically adjust the cultivation environment based on advice from generative AI, for example, adjusting temperature and humidity, or adding necessary nutrients, making it possible to automatically maintain the optimal environment for crop growth.

[0215] For example, by inputting the following prompt into a generative AI model, appropriate cultivation advice will be generated:

[0216] "Please suggest the optimum growing conditions when the temperature is 25 degrees, humidity is 60%, and the soil nitrogen level is 10, phosphorus level is 5, and potassium level is 8."

[0217] Based on this prompt, the generative AI proposes the optimal cultivation environment and sends the results to a smartphone or factory robot via a cloud server. This allows the user to make manual adjustments or the factory robot to automatically adjust the environment to maintain the optimal environment for crop growth.

[0218] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0219] Step 1:

[0220] IoT devices specialized for agriculture monitor the growth status of crops.

[0221] Input: Environmental data such as temperature, humidity, and soil nutrient levels.

[0222] Data processing: Sensors collect data in real time and convert it into a digital format.

[0223] Output: Collected environmental data.

[0224] Step 2:

[0225] The data collected by the IoT device is sent to a cloud server.

[0226] Input: Environmental data from IoT devices.

[0227] Data calculation: Communication processing for uploading data to the cloud server.

[0228] Output: Environmental data stored on a cloud server.

[0229] Step 3:

[0230] The cloud server uses generative AI to analyze the growth status of crops.

[0231] Input: Environmental data stored on a cloud server.

[0232] Data calculation: Generative AI analyzes environmental data and generates optimal cultivation advice.

[0233] Output: Generated cultivation advice.

[0234] Step 4:

[0235] The cloud server sends the generated cultivation advice to smartphones and factory robots.

[0236] Input: Generated cultivation advice.

[0237] Data calculation: Communication processing for sending advice to smartphones and factory robots.

[0238] Output: Cultivation advice sent to smartphone and factory robot.

[0239] Step 5:

[0240] Users can check cultivation advice on their smartphone and adjust the amount of nutrients and water needed.

[0241] Input: Cultivation advice displayed on smartphone.

[0242] Data processing: The user manually adjusts the cultivation environment based on the advice.

[0243] Output: Regulated growing environment.

[0244] Step 6:

[0245] Factory robots automatically adjust the cultivation environment based on advice from generative AI.

[0246] Input: Cultivation advice sent to the factory robot.

[0247] Data calculation: Automatically adjusts temperature, humidity and nutrient addition amounts based on advice.

[0248] Output: Optimized growing environment.

[0249] Step 7:

[0250] The cloud server inputs prompt statements into the generative AI model and suggests the optimal cultivation environment.

[0251] Input: Prompt text (e.g., "Please suggest the optimal growing environment when the temperature is 25°C, humidity is 60%, and the soil nitrogen level is 10, phosphorus level is 5, and potassium level is 8.").

[0252] Data calculation: A generative AI model suggests the optimal growing environment based on the prompt.

[0253] Output: Suggested optimal growing environment.

[0254] Example 3

[0255] Next, a third embodiment of the third embodiment will be described. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0256] In conventional agriculture, it has been difficult to accurately monitor crop growth and receive appropriate cultivation advice. Users also lacked the means to understand crop conditions in real time and adjust the amount of nutrients and water required. This made it difficult to properly manage factors that affect crop growth, hindering productivity improvements.

[0257] The identification process by the identification processing unit 290 of the data processing device 12 in the third embodiment is realized by the following means. In this invention, the server includes a means for transmitting data collected from the sensor device to the server and storing it, a means for the mobile terminal to acquire the data from the server and visually display it, and a means for the user to input a prompt sentence to the generative artificial intelligence and receive advice. This allows the user to understand the growth status of crops in real time and receive appropriate cultivation advice.

[0258] A "sensor device" is a device for collecting data on the growth status of crops.

[0259] "Generative AI" is an AI technology that generates appropriate cultivation advice based on user input.

[0260] A "mobile terminal" is an electronic device that can be carried by a user and is a device for acquiring and displaying data through applications.

[0261] A "server" is a computer system that receives and stores data sent from sensor devices.

[0262] A "prompt" is a question or instruction that a user inputs to a generative artificial intelligence.

[0263] "Visually displaying" means presenting data in a format such as a graph or chart that is easy for users to view.

[0264] "Growth advice" is specific instructions or suggestions for optimizing crop growth.

[0265] MODE FOR CARRYING OUT THE INVENTION

[0266] This invention is a system that combines agriculturally specialized sensor devices, generative artificial intelligence, mobile terminals, and servers to monitor crop growth and provide appropriate cultivation advice.

[0267] Hardware and software used

[0268] Sensor devices: soil moisture sensors, temperature sensors, nutrient concentration sensors, etc.

[0269] Server: A computer system that receives and stores data (e.g., using a MySQL® database)

[0270] Mobile device: An electronic device that can be carried by a user, such as a smartphone or tablet.

[0271] Generative AI: An AI model that generates cultivation advice based on user prompts

[0272] System Operation

[0273] The server receives the data collected from the sensor devices and stores it in a database, allowing for real-time recording of data such as soil moisture, temperature, and nutrient concentration.

[0274] Users access the server through a dedicated application on their mobile device to retrieve the stored data. The application visually displays the retrieved data in graph form, allowing users to understand the growth status of their crops by comparing it with past data. For example, a line graph can be used to display changes in soil moisture over the past week.

[0275] The user enters a prompt sentence into an input field within the application to send a question or instruction to the generative AI. For example, they might enter, "What is the ideal soil moisture level for growing tomatoes?" The server then sends this prompt sentence to the generative AI, and the AI ​​model generates appropriate advice. The generated advice is then provided to the user via the server.

[0276] Specific examples

[0277] For example, if a user inputs a prompt such as "What is the optimum soil humidity for growing tomatoes?", the generative AI will generate advice such as "The optimum soil humidity for growing tomatoes is 60% to 70%." The user can then adjust the soil humidity based on this advice.

[0278] Prompt Sentence Examples

[0279] "What is the ideal soil moisture level for growing tomatoes?"

[0280] "What should I do if my current soil temperature is too high?"

[0281] "If nutrient concentrations are low, what fertilizer should I add?"

[0282] In this way, the user can grasp the growth status of the crop in real time and receive appropriate cultivation advice. This makes it possible to optimize the growth environment of the crop and improve productivity. The flow of the identification process in Example 3 will be described with reference to FIG. 15.

[0283] Step 1:

[0284] The server collects data from sensor devices. Specifically, it receives data in real time from soil moisture sensors, temperature sensors, nutrient concentration sensors, etc. The input is data from the sensor devices, and the output is raw data stored on the server. The server stores this data in a database.

[0285] Step 2:

[0286] The server processes the stored data and extracts the necessary information. Specifically, it analyzes the raw data stored in the database and extracts information such as soil moisture, temperature, and nutrient concentration. The input is the raw data stored in the database, and the output is the analyzed information. The server organizes this information and converts it into a format that users can access.

[0287] Step 3:

[0288] The user launches a dedicated application on their mobile device and accesses the server. Specifically, the application sends a request to the server to obtain the latest data. The input is the user's request, and the output is the latest data obtained from the server. The device receives this data and prepares it for display.

[0289] Step 4:

[0290] The terminal visually displays the acquired data. Specifically, it displays data such as soil moisture, temperature, and nutrient concentration in graph form. The input is data acquired from the server, and the output is graphs and charts displayed to the user. This allows the user to understand the growth status of crops by comparing it with past data.

[0291] Step 5:

[0292] The user enters a prompt into an input field within the application, such as a question like, "What is the ideal soil moisture level for growing tomatoes?" The input is the user's prompt, and the output is a request sent to the generative AI. The device then sends this prompt to the server.

[0293] Step 6:

[0294] The server sends the prompt from the user to the generative AI. Specifically, it parses the prompt and sends it to the generative AI in an appropriate format. The input is the user's prompt, and the output is a request sent to the generative AI. The generative AI receives this request and generates appropriate advice.

[0295] Step 7:

[0296] The generative AI generates advice based on the prompt sentence and sends it back to the server. Specifically, it analyzes the input prompt sentence and generates appropriate cultivation advice. The input is the prompt sentence and the output is the generated advice. The server receives this advice and provides it to the user.

[0297] Step 8:

[0298] Users receive advice from the generative AI through the application. Specifically, the advice is displayed within the application for the user to review. The input is advice from the server, and the output is advice displayed to the user. The user can adjust their crop cultivation based on this advice.

[0299] (Application example 3)

[0300] Next, a description will be given of Application Example 3 of Form Example 3. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0301] Conventional agricultural systems have difficulty monitoring crop growth in real time and providing appropriate cultivation advice. Furthermore, there was a lack of means to collect environmental data in real time and provide advice on optimal production processes within factories. This made efficient production management difficult, resulting in problems such as reduced productivity and inconsistent quality.

[0302] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 3 is realized by the following means.

[0303] In this invention, the server includes: means for monitoring the growth status of crops using IoT devices specialized for agriculture; means for providing cultivation advice using generative AI; means for users to check the status of crops on their smartphones and adjust the amount of nutrients and water needed; means for collecting environmental data within the factory in real time and providing advice on optimal production processes using generative AI; and means for visually displaying data collected from the IoT devices so that users can intuitively understand the production status. This makes it possible to collect data in real time and provide optimal advice in agricultural and factory production processes, thereby improving productivity and stabilizing quality.

[0304] "IoT devices specialized for agriculture" are devices connected to the Internet, such as sensors and actuators, used in the agricultural field to monitor the growth status of crops in real time.

[0305] "Crop growth conditions" refers to environmental data such as soil moisture, temperature, and nutrient concentration during the crop growth process.

[0306] "Generative AI" is an artificial intelligence technology that generates advice on optimal cultivation methods and production processes based on collected data.

[0307] "Growth advice" means specific instructions or recommendations provided to optimize crop growth.

[0308] A "user" is an individual or organization that uses the system to check the growth status of crops and receive cultivation advice.

[0309] A "smartphone" is a portable information terminal that can connect to the Internet and display and operate data through applications.

[0310] "Environmental data within the factory" refers to data such as temperature, humidity, vibration, and machine operating status within the factory.

[0311] "Production process advice" is specific instructions and recommendations provided to optimize production efficiency within a factory.

[0312] "Visual display" refers to displaying collected data in a way that is easy for users to see, such as in graphs or charts.

[0313] "Real-time collection" means that data is collected immediately and processed and displayed near-simultaneously.

[0314] The system for implementing this invention includes an IoT device specialized for agriculture, generative AI, a smartphone, an environmental data collection device in a factory, and a visualization tool. Specific embodiments of each component are described below.

[0315] First, agricultural IoT devices collect real-time environmental data such as soil humidity, temperature, and nutrient concentration. These devices use sensor technology to monitor crop growth. The collected data is then transmitted wirelessly to a server.

[0316] The server receives the collected data and inputs it into the generative AI model. The generative AI model generates optimal cultivation advice based on this data. The generated advice is sent to the user's smartphone, where the user can check the advice through the application. For example, if the prompt sentence "Factory temperature: 25 degrees, humidity: 60%, vibration: 0.5Hz, machine operation status: running" is input into the generative AI model, optimal production process advice will be provided.

[0317] Next, environmental data collection devices in the factory collect data such as temperature, humidity, vibration, and machine operation status in real time. This data is also sent to a server and input into a generative AI model. The generative AI model generates advice to optimize the production process in the factory. The generated advice is sent to the factory manager's terminal and displayed in graphs and charts using visualization tools.

[0318] The visualization tool uses data visualization libraries such as Matplotlib to display collected data in the form of graphs and charts, allowing users and factory managers to intuitively understand the growth and production status.

[0319] For example, the following prompts can be fed to a generative AI model:

[0320] "Factory temperature: 25°C, humidity: 60%, vibration: 0.5Hz, machine operation status: in operation"

[0321] Based on this prompt, the generative AI model provides advice such as, "The current factory environment is optimal. Please continue to maintain this state. However, if vibrations exceed 0.7 Hz, please consider performing maintenance on the machine."

[0322] In this way, it becomes possible to collect data in real time and provide optimal advice in agricultural and factory production processes, thereby improving productivity and stabilizing quality.

[0323] The flow of the specific processing in Application Example 3 will be described with reference to FIG.

[0324] Step 1:

[0325] Agriculturally specialized IoT devices collect environmental data such as soil humidity, temperature, and nutrient concentration in real time. This data is transmitted to a server via wireless communication. The input is the environmental data from the IoT device, and the output is the data transmitted to the server.

[0326] Step 2:

[0327] The server receives the collected environmental data and stores it in a database. The input is the environmental data sent from the IoT device, and the output is the data stored in the database. Specifically, the server checks the data format, converts it into the appropriate format, and stores it.

[0328] Step 3:

[0329] The server inputs the stored data into the generative AI model. The input is the environmental data stored in the database, and the output is the data input into the generative AI model. Specifically, the server converts the data into an appropriate format and sends it to the API of the generative AI model.

[0330] Step 4:

[0331] The generative AI model generates optimal cultivation advice based on input data. The input is environmental data sent from the server, and the output is the generated cultivation advice. Specifically, the generative AI model analyzes the data, generates prompt sentences, and creates advice.

[0332] Step 5:

[0333] The server sends the generated cultivation advice to the user's smartphone. The input is the cultivation advice from the generative AI model, and the output is the advice sent to the user's smartphone. Specifically, the server converts the advice into an appropriate format and sends it to the smartphone application.

[0334] Step 6:

[0335] The user's smartphone displays the received cultivation advice. The input is the cultivation advice sent from the server, and the output is the advice displayed on the smartphone screen. Specifically, the smartphone application analyzes the advice and displays it in an easy-to-read format for the user.

[0336] Step 7:

[0337] Environmental data collection devices in factories collect data such as temperature, humidity, vibration, and machine operation status in real time. This data is sent to a server via wireless communication. The input is data from the environmental data collection devices, and the output is the data sent to the server.

[0338] Step 8:

[0339] The server receives collected environmental data from within the factory and stores it in a database. The input is data sent from the environmental data collection device, and the output is data stored in the database. Specifically, the server checks the data format, converts it into an appropriate format, and stores it.

[0340] Step 9:

[0341] The server inputs the stored environmental data from within the factory into the generative AI model. The input is the environmental data stored in the database, and the output is the data input into the generative AI model. Specifically, the server converts the data into an appropriate format and sends it to the API of the generative AI model.

[0342] Step 10:

[0343] The generative AI model generates optimal production process advice based on input data. The input is environmental data sent from the server, and the output is the generated production process advice. Specifically, the generative AI model analyzes the data, generates prompt statements, and creates advice.

[0344] Step 11:

[0345] The server sends the generated production process advice to the factory manager's terminal. The input is the production process advice from the generative AI model, and the output is the advice sent to the factory manager's terminal. Specifically, the server converts the advice into an appropriate format and sends it to the terminal.

[0346] Step 12:

[0347] The factory manager's terminal displays the received production process advice using a visualization tool. The input is the production process advice sent from the server, and the output is the advice displayed on the terminal screen. Specifically, the visualization tool analyzes the advice and displays it in the form of graphs and charts.

[0348] Furthermore, an emotion engine that estimates the user's emotion may be combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0349] "Example 1"

[0350] One embodiment of the present invention combines an agricultural IoT device, a generative AI, a smartphone, and an emotion engine. The IoT device collects data on crop growth in real time, and the generative AI generates cultivation advice based on that data. The smartphone then displays the cultivation advice from the generative AI to the user. Furthermore, the emotion engine recognizes the user's emotions, and the generative AI adjusts the cultivation advice based on the user's emotional state.

[0351] "Example 2"

[0352] As a specific example, if a user feels stressed, the emotion engine communicates this information to the generative AI. Based on this information, the generative AI generates cultivation advice that takes into account the user's stress. For example, if the user is feeling stressed, it will only recommend easy tasks. In addition to the cultivation advice from the generative AI, the smartphone also displays the emotion recognition results from the emotion engine. This allows the user to check their own emotional state and understand how it is reflected in the cultivation advice.

[0353] "Example 3"

[0354] One embodiment of the present invention combines an agricultural IoT device, a generative AI, a smartphone, and an emotion engine. The IoT device collects data on crop growth in real time, and the generative AI generates cultivation advice based on that data. The smartphone then displays the cultivation advice from the generative AI to the user. Furthermore, the emotion engine recognizes the user's emotions, and the generative AI adjusts the cultivation advice based on the user's emotional state.

[0355] The processing flow of each embodiment will be described below.

[0356] "Example 1"

[0357] Step 1: IoT devices collect real-time data on crop growth.

[0358] Step 2: Generative AI generates cultivation advice based on data collected from IoT devices.

[0359] Step 3: The smartphone displays cultivation advice from the generative AI to the user.

[0360] Step 4: The emotion engine recognizes the user's emotions, and the generative AI adjusts the cultivation advice based on that emotional state.

[0361] "Example 2"

[0362] Step 1: The emotion engine recognizes the user's emotion.

[0363] Step 2: The emotion engine communicates the recognized emotional state to the generative AI.

[0364] Step 3: The generative AI generates cultivation advice based on information from the emotion engine, taking into account the user's emotional state.

[0365] Step 4: The smartphone displays cultivation advice from the generative AI as well as emotion recognition results from the emotion engine.

[0366] Example 1

[0367] Next, a description will be given of Example 1 of Form Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0368] Conventional agricultural systems have difficulty monitoring crop growth in real time and providing appropriate cultivation advice. Furthermore, the advice provided does not take into account the user's emotional state, which can place a heavy burden on the user. This results in suboptimal crop growth and increased stress for the user.

[0369] The specific processing by the specific processing unit 290 of the data processing device 12 in Example 1 is realized by the following means. In this invention, the server includes a means for monitoring the growth status of crops using a sensor device specialized for agriculture, a means for providing cultivation advice using a generative AI model, a means for a user to check the status of the crops on a mobile device and adjust the amount of nutrients and water required, and a means for recognizing the user's emotions and adjusting the cultivation advice based on the user's emotional state. This makes it possible to grasp the growth status of crops in real time and provide optimal cultivation advice. Furthermore, adjusting the advice taking the user's emotional state into consideration reduces the burden on the user and optimizes crop growth.

[0370] A "sensor device" is a device used to monitor the growth status of crops, collecting data such as soil moisture, temperature, pH, and nutrient concentration in real time.

[0371] A "generative AI model" is an artificial intelligence algorithm that analyzes crop growth conditions based on collected data and generates optimal cultivation advice.

[0372] A "mobile device" is an electronic device that can be carried by a user and that receives cultivation advice from a generative AI model and displays it to the user.

[0373] "Emotion recognition" is a technology that analyzes a user's facial expressions, voice, etc. to determine their emotional state.

[0374] "Crop Advice" refers to instructions and suggestions on how to grow crops provided by the generative AI model based on the crop's growth status.

[0375] This invention is a system that combines agriculturally specialized sensor devices, generative AI models, mobile devices, and emotion recognition engines. Specific embodiments of this system are described below.

[0376] First, sensor devices collect data such as soil humidity, temperature, pH, and nutrient concentration in real time. These sensors include humidity sensors, temperature sensors, pH sensors, and nutrient sensors. These sensor devices have wireless communication capabilities and send the collected data to a cloud server. Specifically, they use communication protocols such as Wi-Fi.

[0377] Next, the server receives the data sent from the sensor devices and stores it in a database, for example, using a database service such as AWS® RDS or Google Cloud Firestore, and provides the stored data to the generative AI model.

[0378] The generative AI model analyzes the growth status of crops based on data provided by the server. It uses machine learning libraries such as Python and TensorFlow to analyze patterns in the data and generate optimal cultivation advice. For example, it generates advice such as "The soil moisture is low, so please increase watering."

[0379] The mobile device displays the cultivation advice sent from the generative AI model to the user. A dedicated app is installed on the mobile device, and is designed to allow users to easily check the advice. For example, the advice can be displayed as a pop-up notification using a notification service such as Firebase (registered trademark) Cloud Messaging.

[0380] The emotion recognition engine uses the mobile device's camera and microphone to recognize the user's emotions. It uses facial expression recognition and voice analysis technology to determine whether the user is feeling stressed. The emotion recognition engine then sends the recognized emotion data to the generative AI model. Specifically, it sends the data via an API.

[0381] The generative AI model adjusts the advice based on emotional data. For example, if the user is feeling stressed, the advice will be changed to something simpler and easier to follow. The adjusted advice is then sent back to the mobile device via the server and displayed to the user.

[0382] As a concrete example, consider the following scenario.

[0383] Imagine a user is growing crops on a farm. A sensor device detects low soil moisture and sends the data to a cloud server. The server provides the data to a generative AI model, which then generates advice such as, "The soil moisture is low, so please water your plants more." The mobile device then displays this advice to the user. Furthermore, if the emotion recognition engine determines from the user's facial expression that they appear stressed, the generative AI model will provide advice to reduce the user's burden, such as, "It would be a good idea to install a system that automates the timing of watering."

[0384] Example prompt sentence:

[0385] "What advice would you generate if soil moisture is low?"

[0386] "How do you tailor your advice if the user is stressed?"

[0387] In this way, the system collects data in real time and provides users with optimal cultivation advice.

[0388] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0389] Step 1:

[0390] Sensor devices collect data

[0391] The sensor device collects real-time data on soil humidity, temperature, pH, nutrient concentration, etc. Specifically, it uses humidity, temperature, pH, and nutrient sensors to measure soil conditions. The input is the physical condition of the soil, and the output is digital data obtained from each sensor.

[0392] Step 2:

[0393] The sensor device sends data to the cloud server.

[0394] The sensor device transmits the collected data to the cloud server using wireless communication functions. Specifically, it uses communication protocols such as Wi-Fi. The input is digital data from the sensor device, and the output is the data transmitted to the cloud server.

[0395] Step 3:

[0396] The server stores the data and provides it to the generative AI model

[0397] The server stores the received data in a database, for example, using AWS's RDS or Google Cloud's Firestore. The stored data is then provided to a generative AI model. The input is the data sent to the cloud server, and the output is the data stored in the database.

[0398] Step 4:

[0399] A generative AI model analyzes the data and generates cultivation advice

[0400] The generative AI model analyzes the growth status of crops based on data provided by the server. It uses machine learning libraries such as Python and TensorFlow to analyze patterns in the data and generate optimal cultivation advice. The input is the data stored in the database, and the output is the generated cultivation advice.

[0401] Step 5:

[0402] The server sends the generated advice to the mobile device.

[0403] The server sends the advice received from the generative AI model to the mobile device using a notification service such as Firebase Cloud Messaging. The input is the generated cultivation advice, and the output is the advice sent to the mobile device.

[0404] Step 6:

[0405] The mobile device displays the advice to the user.

[0406] The mobile device displays the received advice to the user, for example, as a pop-up notification through a dedicated app. The input is the advice sent to the mobile device, and the output is the advice displayed to the user.

[0407] Step 7:

[0408] Emotion recognition engine recognizes user emotions

[0409] The emotion recognition engine uses the mobile device's camera and microphone to recognize the user's emotions. It uses facial expression recognition and voice analysis technology to determine whether the user is feeling stressed. The input is the user's facial expression and voice data, and the output is the recognized emotion data.

[0410] Step 8:

[0411] The emotion recognition engine sends the emotion data to the generative AI model

[0412] The emotion recognition engine sends the recognized emotion data to the generative AI model. Specifically, it sends the data through an API. The input is the recognized emotion data, and the output is the emotion data sent to the generative AI model.

[0413] Step 9:

[0414] Generative AI models tailor advice based on emotional data

[0415] The generative AI model adjusts advice based on emotional data. For example, if the user is feeling stressed, the advice will be changed to something simpler and easier to follow. The input is emotional data and existing gardening advice, and the output is the adjusted gardening advice.

[0416] Step 10:

[0417] The server sends the tailored advice to the mobile device.

[0418] The server sends the adjusted advice to the mobile device, again using a notification service such as Firebase Cloud Messaging. The input is the adjusted cultivation advice, and the output is the adjusted advice sent to the mobile device.

[0419] Step 11:

[0420] The mobile device displays tailored advice to the user.

[0421] The mobile device displays the adjusted advice to the user. For example, it displays advice such as, "It would be a good idea to install a system that automates the timing of watering." The input is the adjustment advice sent to the mobile device, and the output is the adjustment advice displayed to the user.

[0422] (Application example 1)

[0423] Next, a description will be given of Application Example 1 of Embodiment Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0424] Conventional agricultural systems using IoT devices and generative AI are specialized in monitoring crop growth and providing cultivation advice, but there are no systems that can collect environmental data within factories in real time and provide advice on machine maintenance or optimal working environments. Furthermore, they lack the ability to recognize the emotional state of workers and adjust advice based on that state. This results in suboptimal work efficiency and machine maintenance within factories, as well as inadequate stress management for workers.

[0425] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0426] In this invention, the server includes means for monitoring the growth status of crops using an IoT device specialized for agriculture, means for providing cultivation advice using generative AI, means for a user to check the status of crops on a smartphone and adjust the amount of nutrients and water needed, means for collecting environmental data within the factory in real time, means for providing advice on machine maintenance and optimal working environments using generative AI, means for recognizing the emotional state of workers using an emotion engine and adjusting advice based on that state, and means for displaying advice through a user interface. This makes it possible to collect environmental data within the factory in real time, use generative AI to provide advice on machine maintenance and optimal working environments, and further adjust advice based on the emotional state of workers.

[0427] An "IoT device specialized for agriculture" is a device that collects data such as soil humidity, temperature, pH, and nutrient concentration in real time and has wireless communication capabilities to send the data to a cloud server.

[0428] "Means for monitoring the growth status of crops" refers to a method for using IoT devices specialized for agriculture to collect data on crop growth and monitor the condition of the crops based on that data.

[0429] "Generative AI" is artificial intelligence that analyzes collected data and generates optimal advice and instructions based on the results.

[0430] "Means for providing cultivation advice" refers to a means of using generative AI to generate advice on crop cultivation based on collected data and providing it to users.

[0431] "A means for users to check the status of crops on their smartphones and adjust the amount of nutrients and water needed" refers to a means for users to use their smartphones to check cultivation advice provided by generative AI and adjust the amount of nutrients and water needed for crops based on that advice.

[0432] "Means for collecting environmental data within a factory in real time" refers to means for collecting environmental data within a factory in real time using temperature sensors, humidity sensors, vibration sensors, sound sensors, etc.

[0433] "Means for providing advice on machine maintenance and optimal working environments" refers to a means for using generative AI to analyze collected environmental data and, based on the results, provide advice on machine maintenance and optimal working environments.

[0434] The "emotion engine" is an engine that recognizes the emotional state of workers and adjusts the advice provided by the generative AI based on that state.

[0435] "Means for displaying advice through a user interface" refers to a means for displaying advice provided by generative AI to a user using a device such as a smartphone or tablet.

[0436] A system for implementing this invention includes an IoT device specialized for agriculture, a generative AI, a smartphone, an emotion engine, an environmental data collection sensor in a factory, a cloud server, and a user interface device.

[0437] Hardware Configuration

[0438] 1. IoT devices specialized for agriculture:

[0439] Data such as soil humidity, temperature, pH, and nutrient concentration is collected in real time and sent to a cloud server using wireless communication functions.

[0440] 2. Environmental data collection sensors in factories:

[0441] Temperature, humidity, vibration, and sound sensors are used to collect environmental data within the factory in real time.

[0442] 3. Cloud Server:

[0443] We use cloud platforms such as AWS, Google Cloud, and Microsoft® Azure® to store and analyze the collected data.

[0444] 4. User Interface Devices:

[0445] Advice from generative AI is displayed to users via smartphones or tablets.

[0446] Software Configuration

[0447] 1. Data Collection Software:

[0448] A program that collects data from sensors and sends it to a cloud server via a wireless communication module.

[0449] 2. Generative AI Models:

[0450] An AI model (e.g., TensorFlow, PyTorch) that runs on a cloud server and analyzes collected data to generate advice.

[0451] 3. Emotion Engine:

[0452] An engine that recognizes the emotional state of workers and adjusts generative AI advice (e.g., Microsoft Azure Emotion API).

[0453] 4. User Interface App:

[0454] An app that runs on a smartphone or tablet and displays the generated advice (e.g., React Native, Flutter (registered trademark)).

[0455] Processing flow

[0456] The server receives data on crop growth conditions collected from IoT devices specialized for agriculture and uses generative AI to generate cultivation advice. It also receives data from environmental data collection sensors within the factory and uses generative AI to generate advice on machine maintenance and optimal working environments. The emotion engine recognizes the emotional state of workers and adjusts the advice provided by the generative AI based on that state. The generated advice is displayed to the user through a user interface device.

[0457] Specific examples

[0458] For example, if the temperature in a factory gets too high, the generative AI might generate the advice "turn on the cooling system." However, if the emotion engine recognizes that a worker's stress level is high, the advice will be adjusted to "turn on the cooling system and encourage the worker to take a break."

[0459] Prompt Sentence Examples

[0460] An example of a prompt sentence to input to the generative AI model is as follows:

[0461] "The current temperature in the factory is 30 degrees, humidity is 70%, vibration level is low, and sound level is medium. The stress level of workers is high. Please generate the optimal advice."

[0462] Using this prompt, the generative AI model generates appropriate advice, which is then adjusted by the emotion engine.

[0463] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0464] Step 1:

[0465] Data collection

[0466] The terminals (IoT devices specialized for agriculture and environmental data collection sensors in factories) collect environmental data in real time, such as soil humidity, temperature, pH, and nutrient concentration, as well as temperature, humidity, vibration, and sound in the factory. This data is sent to a cloud server via a wireless communication module.

[0467] Input: Environmental data from sensors

[0468] Output: Environmental data sent to the cloud server

[0469] Step 2:

[0470] Data storage

[0471] The server stores the received environmental data in a cloud database, which uses cloud platforms such as AWS, Google Cloud, and Microsoft Azure.

[0472] Input: Environmental data sent from the device

[0473] Output: Environmental data stored in a cloud database

[0474] Step 3:

[0475] Data analysis

[0476] The server inputs the environmental data stored in the cloud database into a generative AI model for data analysis. The generative AI model uses frameworks such as TensorFlow and PyTorch to generate optimal cultivation advice and machine maintenance advice.

[0477] Input: Environmental data stored in a cloud database

[0478] Output: Generated cultivation and maintenance advice

[0479] Step 4:

[0480] Recognition of emotional states

[0481] The device (emotion engine) recognizes the emotional state of the worker. The emotion engine uses the Microsoft Azure Emotion API and other tools to analyze the worker's stress level and emotional state.

[0482] Input: Worker emotion data

[0483] Output: Perceived emotional state

[0484] Step 5:

[0485] Advice adjustment

[0486] The server receives emotional state data from the emotion engine and adjusts the advice generated by the generative AI model. For example, if a worker's stress level is high, the server may recommend taking a break in addition to running the cooling system.

[0487] Input: Generated advice, perceived emotional state

[0488] Output: Adjusted advice

[0489] Step 6:

[0490] Displaying Advice

[0491] The terminal (user interface device) displays the adjusted advice to the user. The advice from the generative AI is visually displayed using a smartphone or tablet.

[0492] Input: Tailored advice

[0493] Output: Advice displayed to the user

[0494] Specific examples

[0495] For example, if the temperature in a factory is 30 degrees, humidity is 70%, vibration level is low, sound level is medium, and the worker's stress level is high, the generative AI model will generate the advice "turn on the cooling system," but the emotion engine will recognize the worker's stress level and adjust the advice to "turn on the cooling system and encourage the worker to take a break," which will be displayed to the user on the user interface device.

[0496] Example 2

[0497] Next, a description will be given of Example 2 of Form Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0498] Conventional agricultural systems can monitor crop growth and provide appropriate cultivation advice, but they are unable to provide advice that takes into account the user's emotional state. As a result, users are required to continue their normal tasks even when they are feeling stressed, which increases the burden on the user. Furthermore, there is a lack of a way for users to check their own emotional state and understand how it is reflected in the cultivation advice.

[0499] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0500] In this invention, the server includes means for monitoring the growth status of crops using an information collection device specialized for agriculture, means for providing cultivation advice using generative artificial intelligence, means for a user to check the status of crops on a mobile device and adjust the amount of nutrients and water required, means for recognizing the user's emotional state, means for adjusting cultivation advice based on the user's emotional state, and means for displaying the user's emotional state and cultivation advice. This makes it possible to provide cultivation advice that takes the user's emotional state into consideration, thereby reducing the burden on the user. Furthermore, the user can check their own emotional state and understand how it is reflected in the cultivation advice.

[0501] The "information collection device" is a device for collecting data on the growth status of crops in real time.

[0502] "Generative AI" is an AI technology that generates cultivation advice based on collected data.

[0503] A "mobile device" is an electronic device that a user can carry with them, and is a device that allows the user to check the status of crops and receive cultivation advice.

[0504] "Emotional state" is information that indicates the psychological state of the user, including stress level and type of emotion.

[0505] "Growth advice" means specific instructions or recommendations provided to optimize crop growth.

[0506] "Monitoring" is the act of continuously observing the growth status of crops and collecting data.

[0507] "Adjustment" refers to the act of changing the content of cultivation advice based on collected data and the user's emotional state.

[0508] "Display" refers to the act of visually presenting information on the screen of a mobile device.

[0509] This invention is a system that combines agriculturally specialized information collection devices, generative artificial intelligence, mobile devices, and emotion recognition technology to monitor the growth status of crops and provide cultivation advice that takes into account the user's emotional state.

[0510] The server runs a generative AI based on crop growth data stored in the cloud. Specifically, the server retrieves data from an AWS S3 bucket and analyzes it using machine learning frameworks such as TensorFlow and PyTorch. The generative AI analyzes the current growth status of the crop and generates appropriate cultivation advice. This advice includes the amount of nutrients to add, the amount of water to provide, and temperature adjustments.

[0511] The device uses an emotion engine to recognize the user's emotional state while using the smartphone. The emotion engine uses, for example, Microsoft Azure's Emotion API. The device analyzes the user's facial expressions and voice through the camera and microphone to recognize the user's stress level and emotional state in real time.

[0512] If the user is feeling stressed, the device transmits this information to the server. The server then has the generative AI generate new advice based on the received user emotional information. The generative AI takes the user's stress level into account and generates cultivation advice that recommends only easy tasks. For example, if the user is experiencing high stress levels, it generates advice such as "Only do easy tasks today."

[0513] The device displays the generated cultivation advice and the emotion recognition results on the screen, allowing users to check their own emotional state and understand how it is reflected in the cultivation advice. Specifically, the device application displays the advice and the emotional state on the screen.

[0514] As a concrete example, we will explain the process when a user is feeling stressed. When a user is using a smartphone, the device captures the user's facial expression through the camera and analyzes the stress level using Microsoft Azure's Emotion API. The analysis results are displayed on the device in real time. The device then sends the analysis results to the server via an HTTP request. The server then has the generative AI generate advice again based on the received stress information. For example, if the user has a high stress level, the server generates advice such as "Only do easy tasks today." The device then displays the generated cultivation advice and the emotion recognition results on the screen. The user can check their emotional state and the cultivation advice based on that through the application.

[0515] An example of a prompt is, "Please explain what kind of cultivation advice the generative AI would generate if the user was feeling stressed." By inputting this prompt into the generative AI model, it is possible to obtain specific cultivation advice that takes into account the user's stress level.

[0516] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0517] Step 1:

[0518] The server collects crop growth data stored in the cloud. Specifically, the server retrieves the latest data from an AWS S3 bucket at 9:00 a.m. every day. The input is information on soil moisture, temperature, and sunshine hours sent from sensors, and the output is a dataset containing this data.

[0519] Step 2:

[0520] The server preprocesses the collected data, specifically by imputing missing values ​​and removing outliers. The input is the dataset collected in step 1, and the output is a preprocessed, clean dataset.

[0521] Step 3:

[0522] The server runs a generative artificial intelligence (AI) based on the preprocessed data. Specifically, it inputs data into an AI model using TensorFlow or PyTorch to analyze the growth status of the crops. The input is the preprocessed dataset, and the output is the analysis results that predict the health status and nutrient needs of the crops.

[0523] Step 4:

[0524] The server generates cultivation advice based on the analysis results. Specifically, it outputs the analysis results generated by the AI ​​model in text format and creates appropriate cultivation advice. The input is the analysis results obtained in step 3, and the output is the text of the cultivation advice.

[0525] Step 5:

[0526] The device recognizes the user's emotional state. Specifically, it analyzes the user's facial expressions and voice through the smartphone's camera and microphone, and analyzes their stress level using Microsoft Azure's Emotion API. The input is data on the user's facial expressions and voice, and the output is data indicating the user's emotional state.

[0527] Step 6:

[0528] The device sends the emotion recognition result to the server. Specifically, it sends the emotional state data to the server using an HTTP request. The input is the emotional state data obtained in step 5, and the output is the emotional state data sent to the server.

[0529] Step 7:

[0530] The server then uses the received emotional state data to generate new advice using the generative AI. Specifically, it generates cultivation advice that takes into account the user's stress level and recommends only easy tasks. The input is the emotional state data and the initial cultivation advice, and the output is the adjusted cultivation advice.

[0531] Step 8:

[0532] The device displays the generated cultivation advice and emotion recognition results on the screen. Specifically, the application provides information visually to the user. The input is the adjusted cultivation advice and emotion recognition results, and the output is the information displayed to the user.

[0533] (Application example 2)

[0534] Next, a description will be given of Application Example 2 of Form Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0535] Conventional agricultural systems can monitor crop growth and provide appropriate cultivation advice, but they are unable to provide advice that takes into account the user's emotional state. As a result, if a user is stressed or mentally fatigued, it can be difficult to perform appropriate cultivation tasks, which can have a negative impact on growth results.

[0536] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0537] In this invention, the server includes means for monitoring the growth status of crops using an IoT device specialized for agriculture, means for providing cultivation advice using a generative AI, means for recognizing the emotional state of the user using an emotion engine and for the generative AI to adjust the cultivation advice based on the emotional state, and means for the smartphone to display the cultivation advice from the generative AI and the emotion recognition results from the emotion engine. This makes it possible to provide optimal cultivation advice that takes the emotional state of the user into consideration.

[0538] "IoT devices specialized for agriculture" are sensors and equipment connected to the Internet that are used in the agricultural sector to monitor the growth status of crops in real time.

[0539] "Means for monitoring crop growth conditions" refers to a method of using IoT devices to continuously observe the growth process of crops and environmental conditions and collect data.

[0540] "Generative AI" is an artificial intelligence that analyzes the growth status of crops based on data stored on a cloud server and generates optimal cultivation advice.

[0541] "Means for providing cultivation advice" refers to a method of giving specific instructions and suggestions to users regarding crop cultivation based on the results of the generative AI's analysis.

[0542] The "emotion engine" is a system that recognizes the user's emotional state and provides that information to generative AI.

[0543] The "means for recognizing emotional states" is a method for detecting the user's emotions using an emotion engine and acquiring the state as data.

[0544] "Means for the generative AI to adjust the cultivation advice" refers to a method by which the generative AI changes the content of the cultivation advice by taking into account the user's emotional state provided by the emotion engine.

[0545] "Means for a smartphone to display cultivation advice from a generative AI and emotion recognition results from an emotion engine" refers to a method that uses a smartphone application to visually present to a user cultivation advice provided by a generative AI and the user's emotional state recognized by an emotion engine.

[0546] The system for implementing this invention includes an IoT device specialized for agriculture, a generative AI, an emotion engine, and a smartphone application. Below, we will explain the details of each component and how they work together.

[0547] 1. Hardware and Software Configuration

[0548] IoT devices: These include agricultural sensors and cameras that monitor crop growth conditions (temperature, humidity, soil nutrients, etc.) in real time.

[0549] Generative AI: Runs on a cloud server, analyzes crop growth conditions based on data collected from IoT devices, and generates optimal cultivation advice.

[0550] Emotion engine: Software that recognizes the user's emotional state, analyzing the user's facial expressions and tone of voice using the smartphone's camera and microphone.

[0551] Smartphone application: Provides an interface for users to check cultivation advice from the generative AI and emotion recognition results from the emotion engine.

[0552] 2. Data processing and calculation

[0553] Data collection from IoT devices: IoT devices send data on the growth status of crops to a cloud server in real time.

[0554] Data analysis using generative AI: Generative AI on a cloud server analyzes the growth status of crops based on collected data and generates optimal cultivation advice.

[0555] Emotion recognition using an emotion engine: The smartphone's camera and microphone are used to recognize the user's emotional state, and that information is sent to a cloud server.

[0556] Advice adjustment by generative AI: The generative AI adjusts the content of cultivation advice taking into account the user's emotional state provided by the emotion engine.

[0557] Display via smartphone application: Cultivation advice from the generative AI and emotion recognition results from the emotion engine are visually presented to the user.

[0558] 3. Specific Examples

[0559] For example, if a user is stressed, the emotion engine relays this information to the generative AI, which then takes the user's stress level into account and recommends simple tasks like "Just water the plants today." On the other hand, if the user is relaxed, the generative AI provides more detailed advice like "Add fertilizer and prune the leaves."

[0560] 4. Examples of prompts

[0561] "Generate optimal farming advice by taking into account the user's emotional state. If the user is stressed, recommend easy tasks, but if they're relaxed, provide detailed advice."

[0562] The above is an embodiment of the present invention. This system makes it possible to provide optimal cultivation advice that takes into account the emotional state of the user.

[0563] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0564] Step 1:

[0565] IoT devices collect data on crop growth in real time and send it to a cloud server.

[0566] Input: Environmental data such as temperature, humidity, soil nutrients, etc.

[0567] Output: Growth status data stored on a cloud server

[0568] Specific operation: IoT devices use sensors to measure environmental data and transmit the data to a cloud server via wireless communication.

[0569] Step 2:

[0570] A generative AI system on a cloud server analyzes the growth status of crops based on the collected data and generates optimal cultivation advice.

[0571] Input: Growth status data stored on the cloud server

[0572] Output: Generated cultivation advice

[0573] How it works: Generative AI uses machine learning algorithms to analyze data and generate advice on things like the amount of nutrients and water needed for crop growth, as well as temperature adjustments.

[0574] Step 3:

[0575] The smartphone's emotion engine recognizes the user's emotional state and sends that information to a cloud server.

[0576] Input: User facial expressions and tone of voice

[0577] Output: Emotional state data stored on a cloud server

[0578] Specific operation: The smartphone's camera and microphone are used to analyze the user's facial expressions and voice, and the emotional state is sent as data to a cloud server.

[0579] Step 4:

[0580] The generative AI on the cloud server adjusts the content of the cultivation advice based on the user's emotional state provided by the emotion engine.

[0581] Input: Generated cultivation advice, emotional state data

[0582] Output: Tailored cultivation advice

[0583] Specific behavior: Based on emotional state data, the generative AI tailors its advice to recommend simple tasks if the user is stressed, and provide detailed advice if the user is relaxed.

[0584] Step 5:

[0585] The smartphone application displays tailored cultivation advice from the generative AI and emotion recognition results from the emotion engine to the user.

[0586] Input: Tailored cultivation advice, emotion recognition results

[0587] Output: Cultivation advice and emotion recognition results displayed to the user

[0588] Specific operation: The smartphone application visually displays tailored cultivation advice and emotion recognition results obtained from the cloud server to the user.

[0589] Example 3

[0590] Next, a third embodiment of the third embodiment will be described. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0591] In conventional agriculture, it has been difficult to grasp the growth status of crops in real time and receive appropriate cultivation advice. In addition, it has not been possible to provide advice that takes into account the user's emotional state, making it impossible to reduce the user's stress and burden. This has made it difficult to cultivate crops efficiently and hindered improvements in productivity.

[0592] The specific processing by the specific processing unit 290 of the data processing device 12 in the third embodiment is realized by the following means.

[0593] In this invention, the server includes a means for monitoring the growth status of crops using agricultural sensor devices, a means for providing cultivation advice using a generative AI model, a means for a user to check the status of the crops on a mobile device and adjust the amount of nutrients and water required, and a means for recognizing the user's emotional state using an emotion recognition engine and for the generative AI model to adjust the cultivation advice based on that emotional state. This allows the user to understand the growth status of crops in real time and receive appropriate cultivation advice. Furthermore, providing advice based on the user's emotional state reduces the user's stress and burden and enables efficient crop cultivation.

[0594] A "sensor device" is a device for collecting data on the growth status of crops in real time.

[0595] A "generative AI model" is an artificial intelligence algorithm that analyzes collected data and generates appropriate cultivation advice.

[0596] A "mobile device" is an electronic device that a user can carry with them to check the status of their crops and receive advice from the generative AI model.

[0597] An "emotion recognition engine" is a software or hardware system that recognizes a user's emotional state and uses that information to adjust the advice provided by a generative AI model.

[0598] "Growth advice" means specific instructions or suggestions provided to optimize crop growth.

[0599] "Monitoring" is the act of continuously observing the growth status of crops using sensor devices and collecting data.

[0600] "Real-time" refers to the immediacy of data being collected, processed immediately, and provided to users.

[0601] "Nutrients" are chemicals necessary for plant growth and are supplied by soil and fertilizer.

[0602] "Moisture" refers to the amount of water needed for crop growth and is necessary to maintain appropriate humidity.

[0603] MODE FOR CARRYING OUT THE INVENTION

[0604] This invention is a system that combines agriculturally specialized sensor devices, generative AI models, mobile devices, and emotion recognition engines to monitor crop growth in real time and provide appropriate cultivation advice.

[0605] Hardware and software used

[0606] Sensor devices: Devices that collect environmental data in real time, such as soil moisture, temperature, and nutrient concentrations. Examples include soil sensors and temperature sensors.

[0607] Generative AI model: An artificial intelligence algorithm that analyzes collected data and generates appropriate cultivation advice. For example, machine learning models and neural networks are used.

[0608] Mobile device: An electronic device that can be carried by the user to monitor crop conditions and receive advice from the generative AI model. This includes smartphones and tablets.

[0609] Emotion Recognition Engine: A software or hardware system that recognizes a user's emotional state and uses that information to tailor the advice provided by a generative AI model, for example using facial recognition or voice analysis technologies.

[0610] Program processing

[0611] The server collects data from the sensor devices in real time and sends it to the generative AI model. The generative AI model analyzes the received data and generates appropriate cultivation advice. The generated advice is then sent to a mobile device via the server. The mobile device visually displays the received advice and data, allowing users to understand the growth status of their crops by comparing it with past data.

[0612] In addition, the emotion recognition engine recognizes the user's emotional state, and the generative AI model adjusts the advice based on that emotional state. For example, if the user is feeling stressed, the generative AI model will provide advice that is easier and more actionable.

[0613] Specific examples

[0614] When a user is growing tomatoes, the sensor device detects low soil moisture. The server receives this data and sends it to the generative AI model. The generative AI model generates advice such as, "The soil moisture is low. Please water the plants." The server sends this advice to the mobile device, which notifies the user by displaying a graph of humidity changes. If the emotion recognition engine detects that the user is stressed, the generative AI model provides advice such as, "Try a simple watering method."

[0615] Prompt Sentence Examples

[0616] "What advice should you give to growing tomatoes if soil moisture is declining?"

[0617] This system allows users to grasp the growth status of crops in real time and receive appropriate cultivation advice. In addition, by providing advice according to the user's emotional state, it is possible to reduce the user's stress and burden and enable efficient crop cultivation. The flow of the identification process in Example 3 will be described with reference to FIG. 21.

[0618] Step 1:

[0619] The server collects data from the sensor devices in real time.

[0620] Input: Environmental data such as soil moisture, temperature, and nutrient concentrations sent from sensor devices.

[0621] Data processing / calculation: The server stores the received data in a database and converts the data format as necessary.

[0622] Output: Environmental data stored in a database.

[0623] Specific operation: The server periodically polls for data sent from the sensor devices and stores the received data in a database.

[0624] Step 2:

[0625] The server sends the collected data to the generative AI model.

[0626] Input: Environmental data stored in a database.

[0627] Data processing / calculation: The server extracts the necessary data from the database and converts it into a format that is easy for the generative AI model to analyze.

[0628] Output: Data sent to the generative AI model for analysis.

[0629] Specific operation: The server calls an API to retrieve the latest environmental data from the database and send it to the generative AI model.

[0630] Step 3:

[0631] The generative AI model analyzes the received data and generates cultivation advice.

[0632] Input: Data for analysis sent from the server.

[0633] Data processing / calculation: The generative AI model uses machine learning algorithms to analyze data and generate appropriate cultivation advice.

[0634] Output: Generated cultivation advice.

[0635] Specific behavior: Based on the data it receives, the generative AI model generates specific advice, such as "The soil moisture is decreasing. Please water the plant."

[0636] Step 4:

[0637] The server transmits the generated advice to the mobile terminal.

[0638] Input: Cultivation advice sent from the generative AI model.

[0639] Data processing / calculation: The server converts the generated advice into a format for notifying the user.

[0640] Output: Notification data sent to mobile device.

[0641] Specific operation: The server calls an API to send the advice received from the generative AI model to the mobile device.

[0642] Step 5:

[0643] The mobile device visually displays the received advice and data.

[0644] Input: Notification data sent by the server.

[0645] Data processing / calculation: The mobile device displays the received data in graph or notification format.

[0646] Output: The advice and data that is displayed to the user.

[0647] What it does: The mobile application displays a graph of humidity changes and notifies the user to "water the plants."

[0648] Step 6:

[0649] An emotion recognition engine recognizes the user's emotional state, and a generative AI model tailors the advice.

[0650] Input: User emotion data obtained from the mobile device's camera and microphone.

[0651] Data processing / calculation: The emotion recognition engine uses facial recognition and voice analysis technologies to analyze the user's emotional state.

[0652] Output: Advice based on the user's emotional state.

[0653] Specific behavior: If the emotion recognition engine determines that the user is stressed, the generative AI model will provide advice such as, "Try some simple watering methods."

[0654] (Application example 3)

[0655] Next, a description will be given of Application Example 3 of Form Example 3. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0656] Conventional agricultural systems have difficulty monitoring crop growth in real time and providing appropriate cultivation advice. Furthermore, there is a lack of means to provide personalized advice that takes into account the user's emotional state, making it difficult to improve user satisfaction and production efficiency.

[0657] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 3 is realized by the following means. In this invention, the server includes means for monitoring the growth status of crops using an IoT device specialized for agriculture, means for providing cultivation advice using a generative AI, means for a user to check the status of crops on a smartphone and adjust the amount of nutrients and water required, means for recognizing the user's emotional state using an emotion engine and for the generative AI to adjust the cultivation advice based on the emotional state, and means for visually displaying data collected from the IoT device so that the user can intuitively understand the growth status of crops. This allows the user to understand the growth status of crops in real time and receive personalized cultivation advice according to their emotional state.

[0658] "IoT devices specialized for agriculture" are devices connected to the Internet, such as sensors and actuators, used in the agricultural field to monitor the growth status of crops in real time.

[0659] "Means for monitoring crop growth status" refers to a method for using IoT devices to collect data such as soil humidity, temperature, and nutrient concentration to monitor the growth status of crops.

[0660] "Generative AI" is an artificial intelligence technology that automatically generates advice on crop cultivation based on collected data.

[0661] "Means for providing cultivation advice" refers to a method for providing users with cultivation advice generated by the generative AI.

[0662] A "smartphone" is a portable information terminal that can connect to the Internet and run applications.

[0663] An "emotion engine" is a technology that recognizes the user's emotional state and adjusts the system's behavior based on that emotion.

[0664] "Means for recognizing the emotional state of the user and for the generative AI to adjust the cultivation advice based on that emotional state" refers to a method for detecting the user's emotions using an emotion engine and adjusting the content of the advice provided by the generative AI based on that information.

[0665] "Means for visually displaying data collected from IoT devices to enable users to intuitively understand the growth status of crops" refers to a method for displaying collected data in a visual format such as graphs and charts, allowing users to easily understand the status of crops.

[0666] The system for implementing this invention combines IoT devices specialized for agriculture, generative AI, smartphones, and an emotion engine. A specific embodiment of this system is described below.

[0667] First, IoT devices are used to monitor the growth of crops in real time, including temperature sensors, humidity sensors, sensors that measure soil nutrient concentrations, etc. These sensors collect data on the growth of crops and send the data to a server.

[0668] The server receives the collected data and generates cultivation advice using generative AI, which proposes optimal cultivation methods based on past data and current environmental conditions. This advice is then sent from the server to the user's smartphone so that they can review it.

[0669] The smartphone receives cultivation advice from the generative AI and displays it to the user. Through the smartphone application, the user can check the status of their crops and adjust the amount of nutrients and water they need. The smartphone application also visually displays data collected from the IoT device, allowing the user to intuitively understand the growth status of their crops.

[0670] Furthermore, the emotion engine is used to recognize the user's emotional state. The emotion engine detects emotions from the user's facial expressions and voice and sends that information to the server. The server then adjusts the cultivation advice provided by the generative AI based on the data from the emotion engine. For example, if the user is feeling stressed, the advice can be adjusted to include gentler, more encouraging words.

[0671] As a concrete example, the following prompt sentence can be input to a generative AI model:

[0672] Example prompt sentence:

[0673] Temperature: 29.5°C, Humidity: 35%, Machine condition: Abnormal

[0674] Emotional state: sad

[0675] When this prompt is input, the generative AI model will output the following advice:

[0676] Tip: Your machine needs maintenance, but don't worry, it can be fixed quickly.

[0677] In this way, users can understand the growth status of their crops in real time and receive personalized cultivation advice based on their emotional state.

[0678] The flow of the specific processing in Application Example 3 will be described with reference to FIG.

[0679] Step 1:

[0680] IoT devices monitor the growth of crops. Specifically, temperature sensors, humidity sensors, and sensors that measure soil nutrient concentrations collect data. These sensors acquire data such as temperature, humidity, and nutrient concentration in real time and send the data to a server. The input is raw data from the sensors, and the output is the data sent to the server.

[0681] Step 2:

[0682] The server receives data sent from the IoT device. The server stores the received data in a database and prepares it to be passed to the generative AI. The input is data from the IoT device, and the output is data passed to the generative AI.

[0683] Step 3:

[0684] The server generates cultivation advice using generative AI. Generative AI proposes optimal cultivation methods based on past data and current environmental conditions. Specifically, it analyzes data using machine learning algorithms and generates advice. The input is data stored on the server, and the output is the generated cultivation advice.

[0685] Step 4:

[0686] The server sends the generated cultivation advice to the smartphone. The smartphone receives the advice from the server and displays it to the user. The input is advice from the generative AI, and the output is advice displayed on the smartphone.

[0687] Step 5:

[0688] The smartphone visually displays the data collected from the IoT devices. Specifically, the data is displayed in the form of graphs and charts, allowing users to intuitively understand the growth status of their crops. The input is data from the IoT devices, and the output is the visually displayed data.

[0689] Step 6:

[0690] The emotion engine recognizes the user's emotional state. The emotion engine detects emotions from the user's facial expressions and voice and sends that information to the server. The input is the user's facial expressions and voice data, and the output is the recognized emotional state.

[0691] Step 7:

[0692] The server adjusts the cultivation advice provided by the generative AI based on data from the emotion engine. For example, if the user is feeling stressed, the advice content is adjusted to be gentler and include encouraging words. The input is emotion data from the emotion engine, and the output is the adjusted cultivation advice.

[0693] Step 8:

[0694] The server retransmits the adjusted cultivation advice to the smartphone. The smartphone receives the adjusted advice and displays it to the user. The input is the adjusted cultivation advice, and the output is the adjusted advice displayed on the smartphone.

[0695] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0696] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> ) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0697] Another example of generative AI is Gemini (registered trademark) (Internet search engine). <url: https: gemini.google.com ?hl="ja">) are mentioned.

[0698] In the above embodiment, an example in which the specific process is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0699] [Second embodiment]

[0700] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0701] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0702] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0703] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0704] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0705] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0706] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0707] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0708] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0709] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0710] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0711] Next, the specific processing by the specific processing unit 290 of the data processing device 12 will be described.

[0712] "Example 1"

[0713] As an example of the present invention, an IoT device specialized for agriculture collects data on soil humidity, temperature, pH, nutrient concentration, etc. in real time. This IoT device has wireless communication capabilities and transmits the collected data to a cloud server.

[0714] "Example 2"

[0715] The generative AI analyzes the growth status of crops based on data stored on a cloud server and generates cultivation advice, such as the appropriate amount of nutrients to add, the amount of water to supply, and temperature adjustments to create the optimal environment for crop growth.

[0716] "Example 3"

[0717] Users can receive cultivation advice from generative AI through a dedicated smartphone application. The application also visually displays data collected from IoT devices, allowing users to intuitively understand the growth status of their crops. Specifically, data such as soil humidity, temperature, and nutrient concentration are displayed in graph form, allowing users to understand the growth status of their crops by comparing it with past data.

[0718] The processing flow of each embodiment will be described below.

[0719] "Example 1"

[0720] Step 1: Agriculturally-specific IoT devices collect real-time data such as soil moisture, temperature, pH, and nutrient concentration.

[0721] Step 2: The IoT device has wireless communication capabilities and transmits the collected data to the cloud server.

[0722] "Example 2"

[0723] Step 1: The generative AI analyzes the growth status of crops based on data stored on the cloud server.

[0724] Step 2: The generative AI generates cultivation advice based on the analysis results. The advice generated suggests the optimal environment for growing crops, including the appropriate amount of nutrients to add, the amount of water to supply, and temperature adjustments.

[0725] "Example 3"

[0726] Step 1: Users can receive cultivation advice from generative AI through a dedicated smartphone application.

[0727] Step 2: The application visually displays the data collected from the IoT device, allowing users to intuitively understand the growth status of their crops. Specifically, data such as soil humidity, temperature, and nutrient concentration are displayed in graph form, allowing users to understand the growth status of their crops by comparing it with past data.

[0728] Example 1

[0729] Next, a description will be given of Example 1 of Form Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0730] In conventional agriculture, it is difficult to manually collect data such as soil humidity, temperature, pH, and nutrient concentration to obtain appropriate cultivation advice. Furthermore, because data collection and analysis are not performed in real time, there is a problem in that it is not possible to respond quickly to crop growth conditions. Furthermore, users need specialized knowledge to obtain appropriate cultivation advice, which is a high hurdle for ordinary farmers.

[0731] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0732] In this invention, the server includes: means for collecting soil humidity, temperature, pH, and nutrient concentration in real time using an IoT device specialized for agriculture; means for transmitting the collected data to a cloud server using wireless communication functions; means for the cloud server to receive the data and store it in a database; means for analyzing the data using a generative AI model and generating cultivation advice; and means for the user to check the analysis results on a terminal and adjust the amount of necessary nutrients and water. This enables real-time data collection and analysis, allowing users to obtain appropriate cultivation advice even without specialized knowledge.

[0733] "IoT devices specialized for agriculture" are devices that incorporate sensors and communication modules used in the agricultural field and are used to collect soil and environmental data.

[0734] "Soil moisture" is an indicator of the percentage of water contained in the soil.

[0735] "Temperature" is an indicator of the state of thermal energy in the soil and the environment.

[0736] "pH" is an indicator of the acidity or alkalinity of soil.

[0737] "Nutrient concentration" is an indicator that shows the concentration of nutrients such as nitrogen, phosphorus, and potassium contained in the soil.

[0738] "Wireless communication function" refers to technology for wirelessly sending and receiving data, including Wi-Fi and Bluetooth.

[0739] A "cloud server" is a remote server that stores and processes data over the Internet.

[0740] A "database" is a system for systematically storing and managing collected data.

[0741] A "generative AI model" is an algorithm that uses machine learning and artificial intelligence techniques to analyze data and generate predictions and advice.

[0742] A "terminal" is a device that a user uses to check or operate information, and includes smartphones, tablets, PCs, etc.

[0743] "Analysis results" are the information and advice obtained after analyzing data using a generative AI model.

[0744] "Cultivation advice" is information that provides specific instructions and suggestions for growing crops based on data analyzed by the generative AI model.

[0745] This invention is a system that uses IoT devices specialized for agriculture to collect soil humidity, temperature, pH, and nutrient concentration in real time, and provides cultivation advice using a generative AI model. Specific embodiments of this system are described below.

[0746] Hardware and Software Configuration

[0747] IoT device

[0748] The IoT devices that users install on their farms contain the following sensors:

[0749] Humidity sensor

[0750] temperature sensor

[0751] pH Sensor

[0752] Nutrient Sensor

[0753] These sensors measure soil moisture, temperature, pH, and nutrient concentration. The IoT devices are equipped with a microcontroller to collect data and send it to a cloud server via wireless communication modules (e.g., Wi-Fi, Bluetooth).

[0754] Cloud Server

[0755] The cloud server receives data sent from the IoT devices and stores it in a database (e.g., Amazon RDS, Google Cloud Firestore). The server then analyzes the data using a generative AI model (e.g., OpenAI's GPT-4) and generates cultivation advice.

[0756] Terminal

[0757] Users can check the analysis results sent from the cloud server using devices such as smartphones, tablets, and PCs. A dedicated application is installed on the device, allowing users to receive cultivation advice in real time.

[0758] Specific examples

[0759] For example, consider a case where a user installs an IoT device on a farm where tomatoes are grown. The IoT device uses a humidity sensor to measure the humidity of the soil and detects that the humidity is 30%. This data is sent to a cloud server using a wireless communication module.

[0760] The cloud server receives the 30% humidity data and stores it in Amazon RDS. The stored data is then input into a generative AI model (GPT-4), which generates advice such as "The soil moisture is decreasing. Please activate the irrigation system."

[0761] This advice is sent from the cloud server to the user's smartphone. The user checks the notification on their smartphone and receives a message saying, "The soil moisture is decreasing. Please operate the irrigation system."

[0762] Prompt Sentence Examples

[0763] "The soil moisture in the farm where I grow tomatoes has dropped to 30%. Please tell me the best way to irrigate them."

[0764] In this way, users can grasp the condition of their farmland in real time and take appropriate measures. This system makes it possible to cultivate crops efficiently, even without specialized knowledge.

[0765] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0766] Step 1:

[0767] The IoT device installed by the user in the farmland uses built-in sensors to measure the humidity, temperature, pH, and nutrient concentration of the soil. For example, a humidity sensor measures the humidity of the soil and detects that the humidity is 30%.

[0768] Inputs: Soil moisture, temperature, pH, nutrient concentration

[0769] Output: Measured data (e.g. humidity 30%)

[0770] Step 2:

[0771] The IoT device sends the collected data to a cloud server via a wireless communication module (e.g., Wi-Fi or Bluetooth). For example, the wireless communication module is used to send data on humidity of 30% to the cloud server.

[0772] Input: Measured data (e.g. humidity 30%)

[0773] Output: Data sent to the cloud server

[0774] Step 3:

[0775] The server receives data sent from IoT devices and stores it in a database (e.g., Amazon RDS, Google Cloud Firestore). The server checks the integrity of the data and stores it in the database in the appropriate format.

[0776] Input: Data sent to the cloud server

[0777] Output: Data stored in the database

[0778] Step 4:

[0779] The server inputs the stored data into a generative AI model (e.g., OpenAI's GPT-4) and analyzes the data. For example, if the soil moisture level is declining, the AI ​​model generates advice such as, "The soil moisture level is declining. Please turn on the irrigation system."

[0780] Input: Data stored in a database

[0781] Output: Generated cultivation advice

[0782] Step 5:

[0783] The server sends the generated analysis results to the user's device, for example, by sending a notification to the user via a smartphone app or web app.

[0784] Input: Generated cultivation advice

[0785] Output: Advice sent to the user's terminal

[0786] Step 6:

[0787] The user checks the analysis results on a device (e.g., smartphone, tablet, or PC). For example, they open a smartphone app and see a notification that says, "The soil moisture is decreasing. Please turn on the irrigation system."

[0788] Input: Advice sent to the user's terminal

[0789] Output: Analysis results confirmed by the user

[0790] In this way, users can understand the condition of their farmland in real time and take appropriate measures.

[0791] (Application example 1)

[0792] Next, a description will be given of Application Example 1 of Form Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0793] Conventional agricultural crop growth monitoring systems lack the ability to collect and analyze data in real time, making it difficult to provide appropriate cultivation advice. Furthermore, environmental monitoring within factories also requires rapid response when an abnormality occurs, but current systems make it difficult to achieve this.

[0794] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0795] In this invention, the server includes a means for monitoring the growth status of crops using an IoT device specialized for agriculture, a means for providing cultivation advice using generative AI, a means for a user to check the status of crops on a smartphone and adjust the amount of nutrients and water required, a means for collecting environmental data within the factory in real time and sending it to a cloud server, and a means for analyzing the collected data in the cloud and issuing an alert if an abnormality is detected. This makes it possible to monitor the growth status of crops in agriculture in real time and provide appropriate cultivation advice, and also enables rapid detection and response to abnormalities in environmental monitoring within the factory.

[0796] An "IoT device specialized for agriculture" is a device that collects data such as soil humidity, temperature, pH, and nutrient concentration in real time and transmits it to a cloud server using wireless communication functions.

[0797] "Means for monitoring crop growth status" refers to a method of using IoT devices specialized for agriculture to collect and analyze data on crop growth.

[0798] "Generative AI" is an artificial intelligence technology that generates appropriate cultivation advice based on collected data.

[0799] "Means for providing cultivation advice" refers to using generative AI to analyze collected data and suggest appropriate cultivation and adjustment methods to users.

[0800] "A means for users to check the status of crops on their smartphones and adjust the amount of nutrients and water required" refers to a method in which users use their smartphones to receive cultivation advice provided by generative AI, check the status of crops, and adjust the amount of nutrients and water required.

[0801] "Means for collecting environmental data within a factory in real time and transmitting it to a cloud server" refers to a method for collecting environmental data such as temperature, humidity, pH, and chemical substance concentrations within a factory in real time and transmitting it to a cloud server using wireless communication.

[0802] "Means of analyzing collected data on the cloud and issuing an alert if an abnormality is detected" refers to a method of analyzing environmental data collected on a cloud server and issuing a warning to the user if an abnormality is detected.

[0803] The system for implementing this invention includes an IoT device specialized for agriculture, generative AI, a smartphone, and a cloud server. The specific operation of each component and how they work together are described below.

[0804] First, the IoT devices specialized for agriculture collect data such as soil humidity, temperature, pH, and nutrient concentration in real time. These devices have wireless communication capabilities and transmit the collected data to a cloud server. The hardware used includes temperature sensors, humidity sensors, pH sensors, and nutrient concentration sensors.

[0805] The cloud server receives the collected data and analyzes it using generative AI. The generative AI generates appropriate cultivation advice based on the collected data. The software used includes a Python program and a requests library for sending HTTP requests.

[0806] The generated cultivation advice is sent from the cloud server to the user's smartphone. The smartphone receives the advice from the generative AI and displays it to the user. The user can then use their smartphone to check the status of their crops and adjust the amount of nutrients and water they need.

[0807] This system can also be used for environmental monitoring within factories. It collects environmental data such as temperature, humidity, pH, and chemical concentration in real time and sends it to a cloud server. The cloud server analyzes the collected data and issues an alert if an abnormality is detected.

[0808] As a concrete example, consider a system that issues an alert when the temperature inside a factory exceeds 30 degrees. In this system, temperature sensors monitor the temperature inside the factory in real time and send data to a cloud server when it exceeds 30 degrees. The cloud server detects the abnormality and sends an alert to the user's smartphone.

[0809] An example of a prompt to be input to the generative AI model is as follows:

[0810] "Generate a Python program that will issue an alert if the temperature in the factory exceeds 30 degrees. The temperature data needs to be collected from the sensor and sent to a cloud server."

[0811] In this way, it becomes possible to collect and analyze data in real time, provide appropriate advice, and respond quickly to abnormalities in both agriculture and environmental monitoring within factories.

[0812] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0813] Step 1:

[0814] Agriculturally specialized IoT devices collect real-time data such as soil humidity, temperature, pH, and nutrient concentration. The input is environmental data from the sensors, and the output is the collected environmental data. Specifically, each sensor periodically measures data and stores it in the device's memory.

[0815] Step 2:

[0816] Data collected by IoT devices is sent to a cloud server via wireless communication. The input is environmental data stored in the IoT device, and the output is data sent to the cloud server. Specifically, the communication module in the device converts the data into packets and sends them to the cloud server using a wireless communication protocol.

[0817] Step 3:

[0818] The cloud server analyzes the received data and generates appropriate cultivation advice using generative AI. The input is the environmental data sent to the cloud server, and the output is the generated cultivation advice. Specifically, the analysis program on the cloud server processes the data and inputs it into the generative AI model to generate advice.

[0819] Step 4:

[0820] The cloud server sends the generated cultivation advice to the user's smartphone. The input is the generated cultivation advice, and the output is the advice sent to the smartphone. Specifically, the cloud server converts the advice into a message format and sends it to the smartphone.

[0821] Step 5:

[0822] The user checks the cultivation advice received on their smartphone and adjusts the amount of nutrients and water needed. The input is the cultivation advice displayed on the smartphone, and the output is the user's adjustment of the cultivation environment. Specifically, the user operates the smartphone application and adjusts the cultivation environment according to the advice.

[0823] Step 6:

[0824] Environmental data within the factory is collected in real time and sent to a cloud server. The input is environmental data from sensors within the factory, and the output is the data sent to the cloud server. Specifically, sensors within the factory measure temperature, humidity, pH, and chemical concentration, and send the data to the cloud server.

[0825] Step 7:

[0826] The cloud server analyzes environmental data within the factory and issues an alert if an abnormality is detected. The input is the environmental data sent to the cloud server, and the output is an alert when an abnormality is detected. Specifically, the analysis program on the cloud server monitors the data, and if an abnormality is detected, it generates an alert and sends it to the user's smartphone.

[0827] Step 8:

[0828] The user checks the alert on their smartphone and takes the necessary action. The input is the alert displayed on the smartphone, and the output is the user's response. Specifically, the user operates the smartphone application and takes the necessary action according to the alert.

[0829] Example 2

[0830] Next, a description will be given of Example 2 of Form Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0831] In conventional agriculture, it has been difficult to properly monitor crop growth and provide optimal cultivation advice. In particular, there has been a lack of real-time data collection and analysis, and the provision of specific advice based on the results, making it difficult to optimize the crop growth environment. In addition, the time and effort required for users to manually collect and analyze data has hindered efficient agricultural management.

[0832] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0833] In this invention, the server includes means for monitoring the growth status of crops using agricultural sensor devices, means for providing cultivation advice using a generative AI model based on data stored in the cloud server, means for a user to check the status of the crops on their terminal and adjust the amount of necessary nutrients and water, means for inputting prompts to the generative AI model to analyze the growth status of the crops, and means for transmitting the generated cultivation advice to the user's terminal. This enables real-time data collection and analysis, allowing users to efficiently optimize the growth environment of their crops.

[0834] A "sensor device" is an electronic device that collects data on the growth status of crops in real time.

[0835] A "cloud server" is a remote server that stores, manages, and processes data over the Internet.

[0836] A "generative AI model" is an artificial intelligence model that analyzes input data and generates output for a specific task.

[0837] A "prompt" is an instruction given to a generative AI model that contains information for performing a specific task.

[0838] "Growth advice" means specific instructions or suggestions provided to optimize crop growth.

[0839] A "terminal" is an electronic device used by a user, such as a computer, smartphone, or tablet.

[0840] A "user" is someone who uses the system to manage the growth status of crops and receive cultivation advice.

[0841] This invention is a system that uses agriculturally specialized sensor devices, cloud servers, generative AI models, prompts, and terminals to monitor crop growth and provide optimal cultivation advice.

[0842] The server uses a generative AI model to provide cultivation advice based on data stored on the cloud server. Specifically, the server uses software such as Python and TensorFlow to obtain crop growth data (e.g., temperature, humidity, soil nutrient levels, etc.) stored on the cloud server. It then uses a generative AI model (e.g., GPT-4) to analyze this data and evaluate the crop's growth status. Based on the evaluation results, the server generates appropriate cultivation advice. This advice may include the appropriate amount of nutrients to add, the amount of water to provide, and temperature adjustments.

[0843] A user uses a device to access the cloud server and upload crop growth data. For example, if a user is growing tomatoes, the user uses a device to access the cloud server, input tomato growth data, and upload it. The server receives this data and inputs the following prompt sentence into the generative AI model:

[0844] Example prompt sentence:

[0845] "Analyze the growth status of tomatoes based on the following data and generate appropriate cultivation advice. Data: Temperature 25°C, humidity 60%, soil nitrogen level 20 ppm, soil moisture 30%."

[0846] Based on this prompt, the generative AI model analyzes the tomato's growth status and generates the following advice:

[0847] Example of generated advice:

[0848] "The current temperature and humidity are appropriate. The nitrogen level in the soil is low, so add nitrogen fertilizer. Also, the soil is lacking moisture, so provide an adequate amount of water."

[0849] In this way, the user can optimize the tomato growing environment based on advice provided by the server.

[0850] The system enables real-time data collection and analysis, allowing users to efficiently optimize crop growing environments.

[0851] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0852] Step 1:

[0853] The user accesses the cloud server using a terminal and uploads crop growth data.

[0854] Input: Growth data such as temperature, humidity, and soil nutrient levels.

[0855] Output: Growth data stored on a cloud server.

[0856] How it works: Users access the cloud server using a smartphone or PC, enter crop growth data through a dedicated web application or mobile app, and click the upload button.

[0857] Step 2:

[0858] The server receives the uploaded data and stores it in a database.

[0859] Input: Growth data uploaded by users.

[0860] Output: Growth data stored in a database.

[0861] What happens: The server receives the HTTP request and parses the uploaded data. It connects to the database and inserts the data into the appropriate tables. It performs validation checks to ensure the data is consistent.

[0862] Step 3:

[0863] The server generates prompt sentences based on the stored data and inputs them into the generative AI model.

[0864] Input: Growth data stored in a database.

[0865] Output: The prompt sentence that is input to the generative AI model.

[0866] Specific operation: The server reads the saved data, generates prompt sentences using Python scripts, and sends the generated prompt sentences to the generative AI model via API.

[0867] Step 4:

[0868] The server receives the analysis results from the generative AI model and generates cultivation advice.

[0869] Input: Analysis results from a generative AI model.

[0870] Output: Generated cultivation advice.

[0871] How it works: The server receives a response from the generative AI model, which includes a detailed analysis of the crop's growth status. The server then runs an algorithm based on this information to generate cultivation advice.

[0872] Step 5:

[0873] The server transmits the generated advice to the user's terminal.

[0874] Input: Generated cultivation advice.

[0875] Output: Cultivation advice sent to the user's device.

[0876] Specific operation: The server sends the generated advice to the user's device. The advice is delivered to the user via email or push notification.

[0877] Step 6:

[0878] The user checks the advice on the device and adjusts the cultivation environment.

[0879] Input: Cultivation advice sent to the user's device.

[0880] Output: Regulated growing environment.

[0881] Specific actions: The user checks the advice received on the device. According to the advice, the user adds necessary nutrients and provides water. Based on the advice, the user takes specific actions to optimize the cultivation environment.

[0882] (Application example 2)

[0883] Next, a description will be given of Application Example 2 of Form Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0884] In conventional agriculture, it has been difficult to properly monitor crop growth and maintain an optimal cultivation environment. Users also had to manually adjust the cultivation environment, which was labor-intensive and time-consuming. Furthermore, real-time data collection and analysis was insufficient, making it impossible to quickly identify factors affecting crop growth. To solve these issues, a more efficient and automated system is needed.

[0885] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0886] In this invention, the server includes a means for monitoring the growth status of crops using an IoT device specialized for agriculture, a means for providing cultivation advice using generative AI, a means for a user to check the status of the crops on a smartphone and adjust the amount of necessary nutrients and water, a means for a factory robot to automatically adjust the cultivation environment based on advice from the generative AI, and a means for the generative AI to analyze the growth status of crops based on data stored in the cloud server. This makes it possible to monitor the growth status of crops in real time and automatically maintain an optimal cultivation environment.

[0887] "Agriculturally-specific IoT devices" are internet-connected sensors and devices designed to monitor crop growth.

[0888] "Crop health" refers to the environmental conditions and health of the crop, such as temperature, humidity, and soil nutrient levels, during the growing process.

[0889] "Generative AI" is an artificial intelligence technology that analyzes crop growth conditions and generates optimal cultivation advice based on data stored on a cloud server.

[0890] "Cultivation advice" is a suggestion on the appropriate amount of nutrients to add, the amount of water to supply, temperature adjustments, etc. to maintain the optimal environment for crop growth.

[0891] "A means for users to check the status of crops on their smartphones and adjust the amount of nutrients and water needed" refers to a function that allows users to check the growth status of crops in real time using their smartphones and manually adjust the cultivation environment based on advice from the generative AI.

[0892] A "factory robot" is an automated mechanical device designed to grow crops in a factory, and has the ability to automatically adjust the growing environment based on advice from generative AI.

[0893] A "cloud server" is a remote server for storing, managing, and processing data over the Internet.

[0894] "Real-time collection" means that sensors and devices measure the current situation immediately and transmit that data immediately.

[0895] The system for implementing this invention includes IoT devices specialized for agriculture, generative AI, smartphones, factory robots, and cloud servers. The specific functions of each element and how they work together are described below.

[0896] First, agricultural IoT devices are used to monitor crop growth. These devices include temperature sensors, humidity sensors, soil nutrient sensors, etc., and collect data in real time, which is then sent to a cloud server.

[0897] The cloud server stores the collected data, and the generative AI uses this data to analyze the crop's growth status. The generative AI then generates appropriate cultivation advice, including the appropriate amount of nutrients to add, the amount of water to provide, and temperature adjustments. The advice is then sent via the cloud server to smartphones and factory robots.

[0898] Users can use their smartphones to check real-time cultivation advice from the generative AI. The smartphone application displays the status of the crops and provides an interface for adjusting the amount of nutrients and water needed. This allows users to manually adjust the cultivation environment.

[0899] Furthermore, the factory robots can automatically adjust the cultivation environment based on advice from generative AI, for example, adjusting temperature and humidity, or adding necessary nutrients, making it possible to automatically maintain the optimal environment for crop growth.

[0900] For example, by inputting the following prompt into a generative AI model, appropriate cultivation advice will be generated:

[0901] "Please suggest the optimum growing conditions when the temperature is 25 degrees, humidity is 60%, and the soil nitrogen level is 10, phosphorus level is 5, and potassium level is 8."

[0902] Based on this prompt, the generative AI proposes the optimal cultivation environment and sends the results to a smartphone or factory robot via a cloud server. This allows the user to make manual adjustments or the factory robot to automatically adjust the environment to maintain the optimal environment for crop growth.

[0903] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0904] Step 1:

[0905] IoT devices specialized for agriculture monitor the growth status of crops.

[0906] Input: Environmental data such as temperature, humidity, and soil nutrient levels.

[0907] Data processing: Sensors collect data in real time and convert it into a digital format.

[0908] Output: Collected environmental data.

[0909] Step 2:

[0910] The data collected by the IoT device is sent to a cloud server.

[0911] Input: Environmental data from IoT devices.

[0912] Data calculation: Communication processing for uploading data to the cloud server.

[0913] Output: Environmental data stored on a cloud server.

[0914] Step 3:

[0915] The cloud server uses generative AI to analyze the growth status of crops.

[0916] Input: Environmental data stored on a cloud server.

[0917] Data calculation: Generative AI analyzes environmental data and generates optimal cultivation advice.

[0918] Output: Generated cultivation advice.

[0919] Step 4:

[0920] The cloud server sends the generated cultivation advice to smartphones and factory robots.

[0921] Input: Generated cultivation advice.

[0922] Data calculation: Communication processing for sending advice to smartphones and factory robots.

[0923] Output: Cultivation advice sent to smartphone and factory robot.

[0924] Step 5:

[0925] Users can check cultivation advice on their smartphone and adjust the amount of nutrients and water needed.

[0926] Input: Cultivation advice displayed on smartphone.

[0927] Data processing: The user manually adjusts the cultivation environment based on the advice.

[0928] Output: Regulated growing environment.

[0929] Step 6:

[0930] Factory robots automatically adjust the cultivation environment based on advice from generative AI.

[0931] Input: Cultivation advice sent to the factory robot.

[0932] Data calculation: Automatically adjusts temperature, humidity and nutrient addition amounts based on advice.

[0933] Output: Optimized growing environment.

[0934] Step 7:

[0935] The cloud server inputs prompt statements into the generative AI model and suggests the optimal cultivation environment.

[0936] Input: Prompt text (e.g., "Please suggest the optimal growing environment when the temperature is 25°C, humidity is 60%, and the soil nitrogen level is 10, phosphorus level is 5, and potassium level is 8.").

[0937] Data calculation: A generative AI model suggests the optimal growing environment based on the prompt.

[0938] Output: Suggested optimal growing environment.

[0939] Example 3

[0940] Next, a description will be given of Example 3 of Form Example 3. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0941] In conventional agriculture, it has been difficult to accurately monitor crop growth and receive appropriate cultivation advice. Users also lacked the means to understand crop conditions in real time and adjust the amount of nutrients and water required. This made it difficult to properly manage factors that affect crop growth, hindering productivity improvements.

[0942] The identification process by the identification processing unit 290 of the data processing device 12 in the third embodiment is realized by the following means. In this invention, the server includes a means for transmitting data collected from the sensor device to the server and storing it, a means for the mobile terminal to acquire the data from the server and visually display it, and a means for the user to input a prompt sentence to the generative artificial intelligence and receive advice. This allows the user to understand the growth status of crops in real time and receive appropriate cultivation advice.

[0943] A "sensor device" is a device for collecting data on the growth status of crops.

[0944] "Generative AI" is an AI technology that generates appropriate cultivation advice based on user input.

[0945] A "mobile terminal" is an electronic device that can be carried by a user and is a device for acquiring and displaying data through applications.

[0946] A "server" is a computer system that receives and stores data sent from sensor devices.

[0947] A "prompt" is a question or instruction that a user inputs to a generative artificial intelligence.

[0948] "Visually displaying" means presenting data in a format such as a graph or chart that is easy for users to view.

[0949] "Growth advice" is specific instructions or suggestions for optimizing crop growth.

[0950] MODE FOR CARRYING OUT THE INVENTION

[0951] This invention is a system that combines agriculturally specialized sensor devices, generative artificial intelligence, mobile terminals, and servers to monitor crop growth and provide appropriate cultivation advice.

[0952] Hardware and software used

[0953] Sensor devices: soil moisture sensors, temperature sensors, nutrient concentration sensors, etc.

[0954] Server: A computer system that receives and stores data (e.g., using a MySQL database).

[0955] Mobile device: An electronic device that can be carried by a user, such as a smartphone or tablet.

[0956] Generative AI: An AI model that generates cultivation advice based on user prompts

[0957] System Operation

[0958] The server receives the data collected from the sensor devices and stores it in a database, allowing for real-time recording of data such as soil moisture, temperature, and nutrient concentration.

[0959] Users access the server through a dedicated application on their mobile device to retrieve the stored data. The application visually displays the retrieved data in graph form, allowing users to understand the growth status of their crops by comparing it with past data. For example, a line graph can be used to display changes in soil moisture over the past week.

[0960] The user enters a prompt sentence into an input field within the application to send a question or instruction to the generative AI. For example, they might enter, "What is the ideal soil moisture level for growing tomatoes?" The server then sends this prompt sentence to the generative AI, and the AI ​​model generates appropriate advice. The generated advice is then provided to the user via the server.

[0961] Specific examples

[0962] For example, if a user inputs a prompt such as "What is the optimum soil humidity for growing tomatoes?", the generative AI will generate advice such as "The optimum soil humidity for growing tomatoes is 60% to 70%." The user can then adjust the soil humidity based on this advice.

[0963] Prompt Sentence Examples

[0964] "What is the ideal soil moisture level for growing tomatoes?"

[0965] "What should I do if my current soil temperature is too high?"

[0966] "If nutrient concentrations are low, what fertilizer should I add?"

[0967] In this way, the user can grasp the growth status of the crop in real time and receive appropriate cultivation advice. This makes it possible to optimize the growth environment of the crop and improve productivity. The flow of the identification process in Example 3 will be described with reference to FIG. 15.

[0968] Step 1:

[0969] The server collects data from sensor devices. Specifically, it receives data in real time from soil moisture sensors, temperature sensors, nutrient concentration sensors, etc. The input is data from the sensor devices, and the output is raw data stored on the server. The server stores this data in a database.

[0970] Step 2:

[0971] The server processes the stored data and extracts the necessary information. Specifically, it analyzes the raw data stored in the database and extracts information such as soil moisture, temperature, and nutrient concentration. The input is the raw data stored in the database, and the output is the analyzed information. The server organizes this information and converts it into a format that users can access.

[0972] Step 3:

[0973] The user launches a dedicated application on their mobile device and accesses the server. Specifically, the application sends a request to the server to obtain the latest data. The input is the user's request, and the output is the latest data obtained from the server. The device receives this data and prepares it for display.

[0974] Step 4:

[0975] The terminal visually displays the acquired data. Specifically, it displays data such as soil moisture, temperature, and nutrient concentration in graph form. The input is data acquired from the server, and the output is graphs and charts displayed to the user. This allows the user to understand the growth status of crops by comparing it with past data.

[0976] Step 5:

[0977] The user enters a prompt into an input field within the application, such as a question like, "What is the ideal soil moisture level for growing tomatoes?" The input is the user's prompt, and the output is a request sent to the generative AI. The device then sends this prompt to the server.

[0978] Step 6:

[0979] The server sends the prompt from the user to the generative AI. Specifically, it parses the prompt and sends it to the generative AI in an appropriate format. The input is the user's prompt, and the output is a request sent to the generative AI. The generative AI receives this request and generates appropriate advice.

[0980] Step 7:

[0981] The generative AI generates advice based on the prompt sentence and sends it back to the server. Specifically, it analyzes the input prompt sentence and generates appropriate cultivation advice. The input is the prompt sentence and the output is the generated advice. The server receives this advice and provides it to the user.

[0982] Step 8:

[0983] Users receive advice from the generative AI through the application. Specifically, the advice is displayed within the application for the user to review. The input is advice from the server, and the output is advice displayed to the user. The user can adjust their crop cultivation based on this advice.

[0984] (Application example 3)

[0985] Next, a description will be given of Application Example 3 of Form Example 3. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0986] Conventional agricultural systems have difficulty monitoring crop growth in real time and providing appropriate cultivation advice. Furthermore, there was a lack of means to collect environmental data in real time and provide advice on optimal production processes within factories. This made efficient production management difficult, resulting in problems such as reduced productivity and inconsistent quality.

[0987] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 3 is realized by the following means.

[0988] In this invention, the server includes: means for monitoring the growth status of crops using IoT devices specialized for agriculture; means for providing cultivation advice using generative AI; means for users to check the status of crops on their smartphones and adjust the amount of nutrients and water needed; means for collecting environmental data within the factory in real time and providing advice on optimal production processes using generative AI; and means for visually displaying data collected from the IoT devices so that users can intuitively understand the production status. This makes it possible to collect data in real time and provide optimal advice in agricultural and factory production processes, thereby improving productivity and stabilizing quality.

[0989] "IoT devices specialized for agriculture" are devices connected to the Internet, such as sensors and actuators, used in the agricultural field to monitor the growth status of crops in real time.

[0990] "Crop growth conditions" refers to environmental data such as soil humidity, temperature, and nutrient concentration during the crop growth process.

[0991] "Generative AI" is an artificial intelligence technology that generates advice on optimal cultivation methods and production processes based on collected data.

[0992] "Growth advice" means specific instructions or recommendations provided to optimize crop growth.

[0993] A "user" is an individual or organization that uses the system to check the growth status of crops and receive cultivation advice.

[0994] A "smartphone" is a portable information terminal that can connect to the Internet and display and operate data through applications.

[0995] "Environmental data within the factory" refers to data such as temperature, humidity, vibration, and machine operating status within the factory.

[0996] "Production process advice" is specific instructions and recommendations provided to optimize production efficiency within a factory.

[0997] "Visual display" refers to displaying collected data in a way that is easy for users to see, such as in graphs or charts.

[0998] "Real-time collection" means that data is collected immediately and processed and displayed near-simultaneously.

[0999] The system for implementing this invention includes an IoT device specialized for agriculture, generative AI, a smartphone, an environmental data collection device in a factory, and a visualization tool. Specific embodiments of each component are described below.

[1000] First, agricultural IoT devices collect real-time environmental data such as soil humidity, temperature, and nutrient concentration. These devices use sensor technology to monitor crop growth. The collected data is then transmitted wirelessly to a server.

[1001] The server receives the collected data and inputs it into the generative AI model. The generative AI model generates optimal cultivation advice based on this data. The generated advice is sent to the user's smartphone, where the user can check the advice through the application. For example, if the prompt sentence "Factory temperature: 25 degrees, humidity: 60%, vibration: 0.5Hz, machine operation status: running" is input into the generative AI model, optimal production process advice will be provided.

[1002] Next, environmental data collection devices in the factory collect data such as temperature, humidity, vibration, and machine operation status in real time. This data is also sent to a server and input into a generative AI model. The generative AI model generates advice to optimize the production process in the factory. The generated advice is sent to the factory manager's terminal and displayed in graphs and charts using visualization tools.

[1003] The visualization tool uses data visualization libraries such as Matplotlib to display collected data in the form of graphs and charts, allowing users and factory managers to intuitively understand the growth and production status.

[1004] For example, the following prompts can be fed to a generative AI model:

[1005] "Factory temperature: 25°C, humidity: 60%, vibration: 0.5Hz, machine operation status: in operation"

[1006] Based on this prompt, the generative AI model provides advice such as, "The current factory environment is optimal. Please continue to maintain this state. However, if vibrations exceed 0.7 Hz, please consider performing maintenance on the machine."

[1007] In this way, it becomes possible to collect data in real time and provide optimal advice in agricultural and factory production processes, thereby improving productivity and stabilizing quality.

[1008] The flow of the specific processing in Application Example 3 will be described with reference to FIG.

[1009] Step 1:

[1010] Agriculturally specialized IoT devices collect environmental data such as soil humidity, temperature, and nutrient concentration in real time. This data is transmitted to a server via wireless communication. The input is the environmental data from the IoT device, and the output is the data transmitted to the server.

[1011] Step 2:

[1012] The server receives the collected environmental data and stores it in a database. The input is the environmental data sent from the IoT device, and the output is the data stored in the database. Specifically, the server checks the data format, converts it into the appropriate format, and stores it.

[1013] Step 3:

[1014] The server inputs the stored data into the generative AI model. The input is the environmental data stored in the database, and the output is the data input into the generative AI model. Specifically, the server converts the data into an appropriate format and sends it to the API of the generative AI model.

[1015] Step 4:

[1016] The generative AI model generates optimal cultivation advice based on input data. The input is environmental data sent from the server, and the output is the generated cultivation advice. Specifically, the generative AI model analyzes the data, generates prompt sentences, and creates advice.

[1017] Step 5:

[1018] The server sends the generated cultivation advice to the user's smartphone. The input is the cultivation advice from the generative AI model, and the output is the advice sent to the user's smartphone. Specifically, the server converts the advice into an appropriate format and sends it to the smartphone application.

[1019] Step 6:

[1020] The user's smartphone displays the received cultivation advice. The input is the cultivation advice sent from the server, and the output is the advice displayed on the smartphone screen. Specifically, the smartphone application analyzes the advice and displays it in an easy-to-read format for the user.

[1021] Step 7:

[1022] Environmental data collection devices in factories collect data such as temperature, humidity, vibration, and machine operation status in real time. This data is sent to a server via wireless communication. The input is data from the environmental data collection devices, and the output is the data sent to the server.

[1023] Step 8:

[1024] The server receives collected environmental data from within the factory and stores it in a database. The input is data sent from the environmental data collection device, and the output is data stored in the database. Specifically, the server checks the data format, converts it into an appropriate format, and stores it.

[1025] Step 9:

[1026] The server inputs the stored environmental data from within the factory into the generative AI model. The input is the environmental data stored in the database, and the output is the data input into the generative AI model. Specifically, the server converts the data into an appropriate format and sends it to the API of the generative AI model.

[1027] Step 10:

[1028] The generative AI model generates optimal production process advice based on input data. The input is environmental data sent from the server, and the output is the generated production process advice. Specifically, the generative AI model analyzes the data, generates prompt statements, and creates advice.

[1029] Step 11:

[1030] The server sends the generated production process advice to the factory manager's terminal. The input is the production process advice from the generative AI model, and the output is the advice sent to the factory manager's terminal. Specifically, the server converts the advice into an appropriate format and sends it to the terminal.

[1031] Step 12:

[1032] The factory manager's terminal displays the received production process advice using a visualization tool. The input is the production process advice sent from the server, and the output is the advice displayed on the terminal screen. Specifically, the visualization tool analyzes the advice and displays it in the form of graphs and charts.

[1033] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1034] "Example 1"

[1035] One embodiment of the present invention combines an agricultural IoT device, a generative AI, a smartphone, and an emotion engine. The IoT device collects data on crop growth in real time, and the generative AI generates cultivation advice based on that data. The smartphone then displays the cultivation advice from the generative AI to the user. Furthermore, the emotion engine recognizes the user's emotions, and the generative AI adjusts the cultivation advice based on the user's emotional state.

[1036] "Example 2"

[1037] As a specific example, if a user feels stressed, the emotion engine communicates this information to the generative AI. Based on this information, the generative AI generates cultivation advice that takes into account the user's stress. For example, if the user is feeling stressed, it will only recommend easy tasks. In addition to the cultivation advice from the generative AI, the smartphone also displays the emotion recognition results from the emotion engine. This allows the user to check their own emotional state and understand how it is reflected in the cultivation advice.

[1038] "Example 3"

[1039] One embodiment of the present invention combines an agricultural IoT device, a generative AI, a smartphone, and an emotion engine. The IoT device collects data on crop growth in real time, and the generative AI generates cultivation advice based on that data. The smartphone then displays the cultivation advice from the generative AI to the user. Furthermore, the emotion engine recognizes the user's emotions, and the generative AI adjusts the cultivation advice based on the user's emotional state.

[1040] The processing flow of each embodiment will be described below.

[1041] "Example 1"

[1042] Step 1: IoT devices collect real-time data on crop growth.

[1043] Step 2: Generative AI generates cultivation advice based on data collected from IoT devices.

[1044] Step 3: The smartphone displays cultivation advice from the generative AI to the user.

[1045] Step 4: The emotion engine recognizes the user's emotions, and the generative AI adjusts the cultivation advice based on that emotional state.

[1046] "Example 2"

[1047] Step 1: The emotion engine recognizes the user's emotion.

[1048] Step 2: The emotion engine communicates the recognized emotional state to the generative AI.

[1049] Step 3: The generative AI generates cultivation advice based on information from the emotion engine, taking into account the user's emotional state.

[1050] Step 4: The smartphone displays cultivation advice from the generative AI as well as emotion recognition results from the emotion engine.

[1051] Example 1

[1052] Next, a description will be given of Example 1 of Form Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[1053] Conventional agricultural systems have difficulty monitoring crop growth in real time and providing appropriate cultivation advice. Furthermore, the advice provided does not take into account the user's emotional state, which can place a heavy burden on the user. This results in suboptimal crop growth and increased stress for the user.

[1054] The specific processing by the specific processing unit 290 of the data processing device 12 in Example 1 is realized by the following means. In this invention, the server includes a means for monitoring the growth status of crops using a sensor device specialized for agriculture, a means for providing cultivation advice using a generative AI model, a means for a user to check the status of the crops on a mobile device and adjust the amount of nutrients and water required, and a means for recognizing the user's emotions and adjusting the cultivation advice based on the user's emotional state. This makes it possible to grasp the growth status of crops in real time and provide optimal cultivation advice. Furthermore, adjusting the advice taking the user's emotional state into consideration reduces the burden on the user and optimizes crop growth.

[1055] A "sensor device" is a device used to monitor the growth status of crops, collecting data such as soil moisture, temperature, pH, and nutrient concentration in real time.

[1056] A "generative AI model" is an artificial intelligence algorithm that analyzes the growth status of crops based on collected data and generates optimal cultivation advice.

[1057] "Mobile device" means an electronic device that can be carried by a user and that receives cultivation advice from a generative AI model and displays it to the user.

[1058] "Emotion recognition" is a technology that analyzes a user's facial expressions, voice, etc. to determine their emotional state.

[1059] "Crop Advice" refers to instructions and suggestions on how to grow crops provided by a generative AI model based on the crop's growth status.

[1060] This invention is a system that combines agriculturally specialized sensor devices, generative AI models, mobile devices, and emotion recognition engines. Specific embodiments of this system are described below.

[1061] First, sensor devices collect data such as soil humidity, temperature, pH, and nutrient concentration in real time. These sensors include humidity sensors, temperature sensors, pH sensors, and nutrient sensors. These sensor devices have wireless communication capabilities and send the collected data to a cloud server. Specifically, they use communication protocols such as Wi-Fi.

[1062] The server then receives the data sent from the sensor devices and stores it in a database, using a database service such as AWS's RDS or Google Cloud's Firestore, before providing the data to the generative AI model.

[1063] The generative AI model analyzes the growth status of crops based on data provided by the server. It uses machine learning libraries such as Python and TensorFlow to analyze patterns in the data and generate optimal cultivation advice. For example, it generates advice such as "The soil moisture is low, so please increase watering."

[1064] The mobile device displays the cultivation advice sent from the generative AI model to the user. A dedicated app is installed on the mobile device, and the advice is designed to be easily checked by the user. For example, the advice is displayed as a pop-up notification using a notification service such as Firebase Cloud Messaging.

[1065] The emotion recognition engine uses the mobile device's camera and microphone to recognize the user's emotions. It uses facial expression recognition and voice analysis technology to determine whether the user is feeling stressed. The emotion recognition engine then sends the recognized emotion data to the generative AI model. Specifically, it sends the data via an API.

[1066] The generative AI model adjusts the advice based on emotional data. For example, if the user is feeling stressed, the advice will be changed to something simpler and easier to follow. The adjusted advice is then sent back to the mobile device via the server and displayed to the user.

[1067] As a concrete example, consider the following scenario.

[1068] Imagine a user is growing crops on a farm. A sensor device detects low soil moisture and sends the data to a cloud server. The server provides the data to a generative AI model, which then generates advice such as, "The soil moisture is low, so please water your plants more." The mobile device then displays this advice to the user. Furthermore, if the emotion recognition engine determines from the user's facial expression that they appear stressed, the generative AI model will provide advice to reduce the user's burden, such as, "It would be a good idea to install a system that automates the timing of watering."

[1069] Example prompt sentence:

[1070] "What advice would you generate if soil moisture is low?"

[1071] "How do you tailor your advice if the user is stressed?"

[1072] In this way, the system collects data in real time and provides users with optimal cultivation advice.

[1073] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1074] Step 1:

[1075] Sensor devices collect data

[1076] The sensor device collects real-time data on soil humidity, temperature, pH, nutrient concentration, etc. Specifically, it uses humidity, temperature, pH, and nutrient sensors to measure soil conditions. The input is the physical condition of the soil, and the output is digital data obtained from each sensor.

[1077] Step 2:

[1078] The sensor device sends data to the cloud server.

[1079] The sensor device transmits the collected data to the cloud server using wireless communication functions. Specifically, it uses communication protocols such as Wi-Fi. The input is digital data from the sensor device, and the output is the data transmitted to the cloud server.

[1080] Step 3:

[1081] The server stores the data and provides it to the generative AI model

[1082] The server stores the received data in a database, for example, using AWS's RDS or Google Cloud's Firestore. The stored data is then provided to a generative AI model. The input is the data sent to the cloud server, and the output is the data stored in the database.

[1083] Step 4:

[1084] A generative AI model analyzes the data and generates cultivation advice

[1085] The generative AI model analyzes the growth status of crops based on data provided by the server. It uses machine learning libraries such as Python and TensorFlow to analyze patterns in the data and generate optimal cultivation advice. The input is the data stored in the database, and the output is the generated cultivation advice.

[1086] Step 5:

[1087] The server sends the generated advice to the mobile device.

[1088] The server sends the advice received from the generative AI model to the mobile device using a notification service such as Firebase Cloud Messaging. The input is the generated cultivation advice, and the output is the advice sent to the mobile device.

[1089] Step 6:

[1090] The mobile device displays the advice to the user.

[1091] The mobile device displays the received advice to the user, for example, as a pop-up notification through a dedicated app. The input is the advice sent to the mobile device, and the output is the advice displayed to the user.

[1092] Step 7:

[1093] Emotion recognition engine recognizes user emotions

[1094] The emotion recognition engine uses the mobile device's camera and microphone to recognize the user's emotions. It uses facial expression recognition and voice analysis technology to determine whether the user is feeling stressed. The input is the user's facial expression and voice data, and the output is the recognized emotion data.

[1095] Step 8:

[1096] The emotion recognition engine sends the emotion data to the generative AI model

[1097] The emotion recognition engine sends the recognized emotion data to the generative AI model. Specifically, it sends the data through an API. The input is the recognized emotion data, and the output is the emotion data sent to the generative AI model.

[1098] Step 9:

[1099] Generative AI models tailor advice based on emotional data

[1100] The generative AI model adjusts advice based on emotional data. For example, if the user is feeling stressed, the advice will be changed to something simpler and easier to follow. The input is emotional data and existing gardening advice, and the output is the adjusted gardening advice.

[1101] Step 10:

[1102] The server sends the tailored advice to the mobile device.

[1103] The server sends the adjusted advice to the mobile device, again using a notification service such as Firebase Cloud Messaging. The input is the adjusted cultivation advice, and the output is the adjusted advice sent to the mobile device.

[1104] Step 11:

[1105] The mobile device displays tailored advice to the user.

[1106] The mobile device displays the adjusted advice to the user. For example, it displays advice such as, "It would be a good idea to install a system that automates the timing of watering." The input is the adjustment advice sent to the mobile device, and the output is the adjustment advice displayed to the user.

[1107] (Application example 1)

[1108] Next, a description will be given of Application Example 1 of Form Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[1109] Conventional agricultural systems using IoT devices and generative AI are specialized in monitoring crop growth and providing cultivation advice, but there are no systems that can collect environmental data within factories in real time and provide advice on machine maintenance or optimal working environments. Furthermore, they lack the ability to recognize the emotional state of workers and adjust advice based on that state. This results in suboptimal work efficiency and machine maintenance within factories, as well as inadequate stress management for workers.

[1110] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1111] In this invention, the server includes means for monitoring the growth status of crops using an IoT device specialized for agriculture, means for providing cultivation advice using generative AI, means for a user to check the status of crops on a smartphone and adjust the amount of nutrients and water needed, means for collecting environmental data within the factory in real time, means for providing advice on machine maintenance and optimal working environments using generative AI, means for recognizing the emotional state of workers using an emotion engine and adjusting advice based on that state, and means for displaying advice through a user interface. This makes it possible to collect environmental data within the factory in real time, use generative AI to provide advice on machine maintenance and optimal working environments, and further adjust advice based on the emotional state of workers.

[1112] An "IoT device specialized for agriculture" is a device that collects data such as soil humidity, temperature, pH, and nutrient concentration in real time and has wireless communication capabilities to send the data to a cloud server.

[1113] "Means for monitoring the growth status of crops" refers to a method for using IoT devices specialized for agriculture to collect data on crop growth and monitor the condition of the crops based on that data.

[1114] "Generative AI" is artificial intelligence that analyzes collected data and generates optimal advice and instructions based on the results.

[1115] "Means for providing cultivation advice" refers to a means of using generative AI to generate advice on crop cultivation based on collected data and providing it to users.

[1116] "A means for users to check the status of crops on their smartphones and adjust the amount of nutrients and water needed" refers to a means for users to use their smartphones to check cultivation advice provided by generative AI and adjust the amount of nutrients and water needed for crops based on that advice.

[1117] "Means for collecting environmental data within a factory in real time" refers to means for collecting environmental data within a factory in real time using temperature sensors, humidity sensors, vibration sensors, sound sensors, etc.

[1118] "Means for providing advice on machine maintenance and optimal working environments" refers to a means for using generative AI to analyze collected environmental data and, based on the results, provide advice on machine maintenance and optimal working environments.

[1119] The "emotion engine" is an engine that recognizes the emotional state of workers and adjusts the advice provided by the generative AI based on that state.

[1120] "Means for displaying advice through a user interface" refers to a means for displaying advice provided by generative AI to a user using a device such as a smartphone or tablet.

[1121] A system for implementing this invention includes an IoT device specialized for agriculture, a generative AI, a smartphone, an emotion engine, an environmental data collection sensor in a factory, a cloud server, and a user interface device.

[1122] Hardware Configuration

[1123] 1. IoT devices specialized for agriculture:

[1124] Data such as soil humidity, temperature, pH, and nutrient concentration is collected in real time and sent to a cloud server using wireless communication functions.

[1125] 2. Environmental data collection sensors in factories:

[1126] Temperature, humidity, vibration, and sound sensors are used to collect environmental data within the factory in real time.

[1127] 3. Cloud Server:

[1128] We use cloud platforms such as AWS, Google Cloud, and Microsoft Azure to store and analyze the collected data.

[1129] 4. User Interface Devices:

[1130] Advice from generative AI is displayed to users via smartphones or tablets.

[1131] Software Configuration

[1132] 1. Data Collection Software:

[1133] A program that collects data from sensors and sends it to a cloud server via a wireless communication module.

[1134] 2. Generative AI Models:

[1135] An AI model (e.g., TensorFlow, PyTorch) that runs on a cloud server and analyzes collected data to generate advice.

[1136] 3. Emotion Engine:

[1137] An engine that recognizes the emotional state of workers and adjusts generative AI advice (e.g., Microsoft Azure Emotion API).

[1138] 4. User Interface App:

[1139] An app (e.g., React Native, Flutter) that runs on a smartphone or tablet and displays the generated advice.

[1140] Processing flow

[1141] The server receives data on crop growth conditions collected from IoT devices specialized for agriculture and uses generative AI to generate cultivation advice. It also receives data from environmental data collection sensors within the factory and uses generative AI to generate advice on machine maintenance and optimal working environments. The emotion engine recognizes the emotional state of workers and adjusts the advice provided by the generative AI based on that state. The generated advice is displayed to the user through a user interface device.

[1142] Specific examples

[1143] For example, if the temperature in a factory gets too high, the generative AI might generate the advice "turn on the cooling system." However, if the emotion engine recognizes that a worker's stress level is high, the advice will be adjusted to "turn on the cooling system and encourage the worker to take a break."

[1144] Prompt Sentence Examples

[1145] An example of a prompt sentence to input to the generative AI model is as follows:

[1146] "The current temperature in the factory is 30 degrees, humidity is 70%, vibration level is low, and sound level is medium. The stress level of workers is high. Please generate the optimal advice."

[1147] Using this prompt, the generative AI model generates appropriate advice, which is then adjusted by the emotion engine.

[1148] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1149] Step 1:

[1150] Data collection

[1151] The terminals (IoT devices specialized for agriculture and environmental data collection sensors in factories) collect environmental data in real time, such as soil humidity, temperature, pH, and nutrient concentration, as well as temperature, humidity, vibration, and sound in the factory. This data is sent to a cloud server via a wireless communication module.

[1152] Input: Environmental data from sensors

[1153] Output: Environmental data sent to the cloud server

[1154] Step 2:

[1155] Data storage

[1156] The server stores the received environmental data in a cloud database, which uses cloud platforms such as AWS, Google Cloud, and Microsoft Azure.

[1157] Input: Environmental data sent from the device

[1158] Output: Environmental data stored in a cloud database

[1159] Step 3:

[1160] Data analysis

[1161] The server inputs the environmental data stored in the cloud database into a generative AI model for data analysis. The generative AI model uses frameworks such as TensorFlow and PyTorch to generate optimal cultivation advice and machine maintenance advice.

[1162] Input: Environmental data stored in a cloud database

[1163] Output: Generated cultivation and maintenance advice

[1164] Step 4:

[1165] Recognition of emotional states

[1166] The device (emotion engine) recognizes the emotional state of the worker. The emotion engine uses the Microsoft Azure Emotion API and other tools to analyze the worker's stress level and emotional state.

[1167] Input: Worker emotion data

[1168] Output: Perceived emotional state

[1169] Step 5:

[1170] Advice adjustment

[1171] The server receives emotional state data from the emotion engine and adjusts the advice generated by the generative AI model. For example, if a worker's stress level is high, the server may recommend taking a break in addition to running the cooling system.

[1172] Input: Generated advice, perceived emotional state

[1173] Output: Adjusted advice

[1174] Step 6:

[1175] Displaying Advice

[1176] The terminal (user interface device) displays the adjusted advice to the user. The advice from the generative AI is visually displayed using a smartphone or tablet.

[1177] Input: Tailored advice

[1178] Output: Advice displayed to the user

[1179] Specific examples

[1180] For example, if the temperature in a factory is 30 degrees, humidity is 70%, vibration level is low, sound level is medium, and the worker's stress level is high, the generative AI model will generate the advice "turn on the cooling system," but the emotion engine will recognize the worker's stress level and adjust the advice to "turn on the cooling system and encourage the worker to take a break," which will be displayed to the user on the user interface device.

[1181] Example 2

[1182] Next, a description will be given of Example 2 of Form Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[1183] Conventional agricultural systems can monitor crop growth and provide appropriate cultivation advice, but they are unable to provide advice that takes into account the user's emotional state. As a result, users are required to continue their normal tasks even when they are feeling stressed, which increases the burden on the user. Furthermore, there is a lack of a way for users to check their own emotional state and understand how it is reflected in the cultivation advice.

[1184] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1185] In this invention, the server includes means for monitoring the growth status of crops using an information collection device specialized for agriculture, means for providing cultivation advice using generative artificial intelligence, means for a user to check the status of crops on a mobile device and adjust the amount of nutrients and water required, means for recognizing the user's emotional state, means for adjusting cultivation advice based on the user's emotional state, and means for displaying the user's emotional state and cultivation advice. This makes it possible to provide cultivation advice that takes the user's emotional state into consideration, thereby reducing the burden on the user. Furthermore, the user can check their own emotional state and understand how it is reflected in the cultivation advice.

[1186] The "information collection device" is a device for collecting data on the growth status of crops in real time.

[1187] "Generative AI" is an AI technology that generates cultivation advice based on collected data.

[1188] A "mobile device" is an electronic device that a user can carry with them, and is a device that allows the user to check the status of crops and receive cultivation advice.

[1189] "Emotional state" is information that indicates the psychological state of the user, including stress level and type of emotion.

[1190] "Growth advice" means specific instructions or recommendations provided to optimize crop growth.

[1191] "Monitoring" is the act of continuously observing the growth status of crops and collecting data.

[1192] "Adjustment" refers to the act of changing the content of cultivation advice based on collected data and the user's emotional state.

[1193] "Display" refers to the act of visually presenting information on the screen of a mobile device.

[1194] This invention is a system that combines agriculturally specialized information collection devices, generative artificial intelligence, mobile devices, and emotion recognition technology to monitor the growth status of crops and provide cultivation advice that takes into account the user's emotional state.

[1195] The server runs a generative AI based on crop growth data stored in the cloud. Specifically, the server retrieves data from an AWS S3 bucket and analyzes it using machine learning frameworks such as TensorFlow and PyTorch. The generative AI analyzes the current growth status of the crop and generates appropriate cultivation advice. This advice includes the amount of nutrients to add, the amount of water to provide, and temperature adjustments.

[1196] The device uses an emotion engine to recognize the user's emotional state while using the smartphone. The emotion engine uses, for example, Microsoft Azure's Emotion API. The device analyzes the user's facial expressions and voice through the camera and microphone to recognize the user's stress level and emotional state in real time.

[1197] If the user is feeling stressed, the device transmits this information to the server. The server then has the generative AI generate new advice based on the received user emotional information. The generative AI takes the user's stress level into account and generates cultivation advice that recommends only easy tasks. For example, if the user is experiencing high stress levels, it generates advice such as "Only do easy tasks today."

[1198] The device displays the generated cultivation advice and emotion recognition results on the screen, allowing users to check their own emotional state and understand how it is reflected in the cultivation advice. Specifically, the device application displays the advice and emotional state on the screen.

[1199] As a concrete example, we will explain the process when a user is feeling stressed. When a user is using a smartphone, the device captures the user's facial expression through the camera and analyzes the stress level using Microsoft Azure's Emotion API. The analysis results are displayed on the device in real time. The device then sends the analysis results to the server via an HTTP request. The server then has the generative AI generate advice again based on the received stress information. For example, if the user has a high stress level, the server generates advice such as "Only do easy tasks today." The device then displays the generated cultivation advice and the emotion recognition results on the screen. The user can check their emotional state and the cultivation advice based on that through the application.

[1200] An example of a prompt sentence is, "Please explain what kind of cultivation advice the generative AI would generate if the user was feeling stressed." By inputting this prompt sentence into the generative AI model, it is possible to obtain specific cultivation advice that takes into account the user's stress level.

[1201] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1202] Step 1:

[1203] The server collects crop growth data stored in the cloud. Specifically, the server retrieves the latest data from an AWS S3 bucket at 9:00 a.m. every day. The input is information on soil moisture, temperature, and sunshine hours sent from sensors, and the output is a dataset containing this data.

[1204] Step 2:

[1205] The server preprocesses the collected data, specifically by imputing missing values ​​and removing outliers. The input is the dataset collected in step 1, and the output is a preprocessed, clean dataset.

[1206] Step 3:

[1207] The server runs a generative artificial intelligence (AI) based on the preprocessed data. Specifically, it inputs data into an AI model using TensorFlow or PyTorch to analyze the growth status of the crops. The input is the preprocessed dataset, and the output is the analysis results that predict the health status and nutrient needs of the crops.

[1208] Step 4:

[1209] The server generates cultivation advice based on the analysis results. Specifically, it outputs the analysis results generated by the AI ​​model in text format and creates appropriate cultivation advice. The input is the analysis results obtained in step 3, and the output is the text of the cultivation advice.

[1210] Step 5:

[1211] The device recognizes the user's emotional state. Specifically, it analyzes the user's facial expressions and voice through the smartphone's camera and microphone, and analyzes their stress level using Microsoft Azure's Emotion API. The input is data on the user's facial expressions and voice, and the output is data indicating the user's emotional state.

[1212] Step 6:

[1213] The device sends the emotion recognition result to the server. Specifically, it sends the emotional state data to the server using an HTTP request. The input is the emotional state data obtained in step 5, and the output is the emotional state data sent to the server.

[1214] Step 7:

[1215] The server then uses the received emotional state data to generate new advice using the generative AI. Specifically, it generates cultivation advice that takes into account the user's stress level and recommends only easy tasks. The input is the emotional state data and the initial cultivation advice, and the output is the adjusted cultivation advice.

[1216] Step 8:

[1217] The device displays the generated cultivation advice and emotion recognition results on the screen. Specifically, the application provides information visually to the user. The input is the adjusted cultivation advice and emotion recognition results, and the output is the information displayed to the user.

[1218] (Application example 2)

[1219] Next, a description will be given of Application Example 2 of Form Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[1220] Conventional agricultural systems can monitor crop growth and provide appropriate cultivation advice, but they are unable to provide advice that takes into account the user's emotional state. As a result, if a user is stressed or mentally fatigued, it can be difficult to perform appropriate cultivation tasks, which can have a negative impact on growth results.

[1221] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1222] In this invention, the server includes means for monitoring the growth status of crops using an IoT device specialized for agriculture, means for providing cultivation advice using a generative AI, means for recognizing the emotional state of the user using an emotion engine and for the generative AI to adjust the cultivation advice based on the emotional state, and means for the smartphone to display the cultivation advice from the generative AI and the emotion recognition results from the emotion engine. This makes it possible to provide optimal cultivation advice that takes the emotional state of the user into consideration.

[1223] "IoT devices specialized for agriculture" are sensors and equipment connected to the internet used in the agricultural sector, and are devices for monitoring the growth status of crops in real time.

[1224] "Means for monitoring crop growth conditions" refers to a method of using IoT devices to continuously observe the growth process of crops and environmental conditions and collect data.

[1225] "Generative AI" is an artificial intelligence that analyzes the growth status of crops based on data stored on a cloud server and generates optimal cultivation advice.

[1226] "Means for providing cultivation advice" refers to a method of providing specific instructions and suggestions to users regarding crop cultivation based on the results of the generative AI's analysis.

[1227] The "emotion engine" is a system that recognizes the user's emotional state and provides that information to generative AI.

[1228] The "means for recognizing emotional states" is a method for detecting the user's emotions using an emotion engine and acquiring the state as data.

[1229] "Means for the generative AI to adjust the cultivation advice" refers to a method by which the generative AI changes the content of the cultivation advice by taking into account the user's emotional state provided by the emotion engine.

[1230] "Means for a smartphone to display cultivation advice from a generative AI and emotion recognition results from an emotion engine" refers to a method that uses a smartphone application to visually present to a user cultivation advice provided by a generative AI and the user's emotional state recognized by an emotion engine.

[1231] The system for implementing this invention includes an IoT device specialized for agriculture, a generative AI, an emotion engine, and a smartphone application. Below, we will explain the details of each component and how they work together.

[1232] 1. Hardware and Software Configuration

[1233] IoT devices: These include agricultural sensors and cameras that monitor crop growth conditions (temperature, humidity, soil nutrients, etc.) in real time.

[1234] Generative AI: Runs on a cloud server, analyzes crop growth conditions based on data collected from IoT devices, and generates optimal cultivation advice.

[1235] Emotion engine: Software that recognizes the user's emotional state, analyzing the user's facial expressions and tone of voice using the smartphone's camera and microphone.

[1236] Smartphone application: Provides an interface for users to check cultivation advice from the generative AI and emotion recognition results from the emotion engine.

[1237] 2. Data processing and calculation

[1238] Data collection from IoT devices: IoT devices send data on the growth status of crops to a cloud server in real time.

[1239] Data analysis using generative AI: Generative AI on a cloud server analyzes the growth status of crops based on collected data and generates optimal cultivation advice.

[1240] Emotion recognition using an emotion engine: The smartphone's camera and microphone are used to recognize the user's emotional state, and that information is sent to a cloud server.

[1241] Advice adjustment by generative AI: The generative AI adjusts the content of cultivation advice taking into account the user's emotional state provided by the emotion engine.

[1242] Display via smartphone application: Cultivation advice from the generative AI and emotion recognition results from the emotion engine are visually presented to the user.

[1243] 3. Specific Examples

[1244] For example, if a user is stressed, the emotion engine relays this information to the generative AI, which then takes the user's stress level into account and recommends simple tasks like "Just water the plants today." On the other hand, if the user is relaxed, the generative AI provides more detailed advice like "Add fertilizer and prune the leaves."

[1245] 4. Examples of prompts

[1246] "Generate optimal farming advice by taking into account the user's emotional state. If the user is stressed, recommend easy tasks, but if they're relaxed, provide detailed advice."

[1247] The above is an embodiment of the present invention. This system makes it possible to provide optimal cultivation advice that takes into account the emotional state of the user.

[1248] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1249] Step 1:

[1250] IoT devices collect data on crop growth in real time and send it to a cloud server.

[1251] Input: Environmental data such as temperature, humidity, soil nutrients, etc.

[1252] Output: Growth status data stored on a cloud server

[1253] Specific operation: IoT devices use sensors to measure environmental data and transmit the data to a cloud server via wireless communication.

[1254] Step 2:

[1255] A generative AI system on a cloud server analyzes the growth status of crops based on the collected data and generates optimal cultivation advice.

[1256] Input: Growth status data stored on the cloud server

[1257] Output: Generated cultivation advice

[1258] How it works: Generative AI uses machine learning algorithms to analyze data and generate advice on things like the amount of nutrients and water needed for crop growth, as well as temperature adjustments.

[1259] Step 3:

[1260] The smartphone's emotion engine recognizes the user's emotional state and sends that information to a cloud server.

[1261] Input: User facial expressions and tone of voice

[1262] Output: Emotional state data stored on a cloud server

[1263] Specific operation: The smartphone's camera and microphone are used to analyze the user's facial expressions and voice, and the emotional state is sent as data to a cloud server.

[1264] Step 4:

[1265] The generative AI on the cloud server adjusts the content of the cultivation advice based on the user's emotional state provided by the emotion engine.

[1266] Input: Generated cultivation advice, emotional state data

[1267] Output: Tailored cultivation advice

[1268] Specific behavior: Based on emotional state data, the generative AI tailors its advice to recommend simple tasks if the user is stressed, and provide detailed advice if the user is relaxed.

[1269] Step 5:

[1270] The smartphone application displays tailored cultivation advice from the generative AI and emotion recognition results from the emotion engine to the user.

[1271] Input: Tailored cultivation advice, emotion recognition results

[1272] Output: Cultivation advice and emotion recognition results displayed to the user

[1273] Specific operation: The smartphone application visually displays tailored cultivation advice and emotion recognition results obtained from the cloud server to the user.

[1274] Example 3

[1275] Next, a description will be given of Example 3 of Form Example 3. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[1276] In conventional agriculture, it has been difficult to grasp the growth status of crops in real time and receive appropriate cultivation advice. In addition, it has not been possible to provide advice that takes into account the user's emotional state, making it impossible to reduce the user's stress and burden. This has made it difficult to cultivate crops efficiently and hindered improvements in productivity.

[1277] The specific processing by the specific processing unit 290 of the data processing device 12 in the third embodiment is realized by the following means.

[1278] In this invention, the server includes a means for monitoring the growth status of crops using agricultural sensor devices, a means for providing cultivation advice using a generative AI model, a means for a user to check the status of the crops on a mobile device and adjust the amount of nutrients and water required, and a means for recognizing the user's emotional state using an emotion recognition engine and for the generative AI model to adjust the cultivation advice based on that emotional state. This allows the user to understand the growth status of crops in real time and receive appropriate cultivation advice. Furthermore, providing advice based on the user's emotional state reduces the user's stress and burden and enables efficient crop cultivation.

[1279] A "sensor device" is a device for collecting data on the growth status of crops in real time.

[1280] A "generative AI model" is an artificial intelligence algorithm that analyzes collected data and generates appropriate cultivation advice.

[1281] A "mobile device" is an electronic device that a user can carry with them to check the status of their crops and receive advice from the generative AI model.

[1282] An "emotion recognition engine" is a software or hardware system that recognizes a user's emotional state and uses that information to adjust the advice provided by a generative AI model.

[1283] "Growth advice" means specific instructions or suggestions provided to optimize crop growth.

[1284] "Monitoring" is the act of continuously observing the growth status of crops using sensor devices and collecting data.

[1285] "Real-time" refers to the immediacy of data being collected, processed immediately, and provided to users.

[1286] "Nutrients" are chemicals necessary for plant growth and are supplied by soil and fertilizer.

[1287] "Moisture" refers to the amount of water needed for crop growth and is necessary to maintain appropriate humidity.

[1288] MODE FOR CARRYING OUT THE INVENTION

[1289] This invention is a system that combines agriculturally specialized sensor devices, generative AI models, mobile devices, and emotion recognition engines to monitor crop growth in real time and provide appropriate cultivation advice.

[1290] Hardware and software used

[1291] Sensor devices: Devices that collect environmental data in real time, such as soil moisture, temperature, and nutrient concentrations. Examples include soil sensors and temperature sensors.

[1292] Generative AI model: An artificial intelligence algorithm that analyzes collected data and generates appropriate cultivation advice. For example, machine learning models and neural networks are used.

[1293] Mobile device: An electronic device that can be carried by the user to monitor crop conditions and receive advice from the generative AI model. This includes smartphones and tablets.

[1294] Emotion Recognition Engine: A software or hardware system that recognizes a user's emotional state and uses that information to tailor the advice provided by a generative AI model, for example using facial recognition or voice analysis technologies.

[1295] Program processing

[1296] The server collects data from the sensor devices in real time and sends it to the generative AI model. The generative AI model analyzes the received data and generates appropriate cultivation advice. The generated advice is then sent to a mobile device via the server. The mobile device visually displays the received advice and data, allowing users to understand the growth status of their crops by comparing it with past data.

[1297] In addition, the emotion recognition engine recognizes the user's emotional state, and the generative AI model adjusts the advice based on that emotional state. For example, if the user is feeling stressed, the generative AI model will provide advice that is easier and more actionable.

[1298] Specific examples

[1299] When a user is growing tomatoes, the sensor device detects low soil moisture. The server receives this data and sends it to the generative AI model. The generative AI model generates advice such as, "The soil moisture is low. Please water the plants." The server sends this advice to the mobile device, which notifies the user by displaying a graph of humidity changes. If the emotion recognition engine detects that the user is stressed, the generative AI model provides advice such as, "Try a simple watering method."

[1300] Prompt Sentence Examples

[1301] "What advice should you give to growing tomatoes if soil moisture is declining?"

[1302] This system allows users to grasp the growth status of crops in real time and receive appropriate cultivation advice. In addition, by providing advice according to the user's emotional state, it reduces the user's stress and burden and enables efficient crop cultivation. The flow of the identification process in Example 3 will be described with reference to FIG. 21.

[1303] Step 1:

[1304] The server collects data from the sensor devices in real time.

[1305] Input: Environmental data such as soil moisture, temperature, and nutrient concentrations sent from sensor devices.

[1306] Data processing / calculation: The server stores the received data in a database and converts the data format as necessary.

[1307] Output: Environmental data stored in a database.

[1308] Specific operation: The server periodically polls for data sent from the sensor devices and stores the received data in a database.

[1309] Step 2:

[1310] The server sends the collected data to the generative AI model.

[1311] Input: Environmental data stored in a database.

[1312] Data processing / calculation: The server extracts the necessary data from the database and converts it into a format that is easy for the generative AI model to analyze.

[1313] Output: Data sent to the generative AI model for analysis.

[1314] Specific operation: The server calls an API to retrieve the latest environmental data from the database and send it to the generative AI model.

[1315] Step 3:

[1316] The generative AI model analyzes the received data and generates cultivation advice.

[1317] Input: Data for analysis sent from the server.

[1318] Data processing / calculation: The generative AI model uses machine learning algorithms to analyze data and generate appropriate cultivation advice.

[1319] Output: Generated cultivation advice.

[1320] Specific behavior: Based on the data it receives, the generative AI model generates specific advice, such as "The soil moisture is decreasing. Please water the plant."

[1321] Step 4:

[1322] The server transmits the generated advice to the mobile terminal.

[1323] Input: Cultivation advice sent from the generative AI model.

[1324] Data processing / calculation: The server converts the generated advice into a format for notifying the user.

[1325] Output: Notification data sent to mobile device.

[1326] Specific operation: The server calls an API to send the advice received from the generative AI model to the mobile device.

[1327] Step 5:

[1328] The mobile device visually displays the received advice and data.

[1329] Input: Notification data sent by the server.

[1330] Data processing / calculation: The mobile device displays the received data in graph or notification format.

[1331] Output: The advice and data that is displayed to the user.

[1332] What it does: The mobile application displays a graph of humidity changes and notifies the user to "water the plants."

[1333] Step 6:

[1334] An emotion recognition engine recognizes the user's emotional state, and a generative AI model tailors the advice.

[1335] Input: User emotion data obtained from the mobile device's camera and microphone.

[1336] Data processing / calculation: The emotion recognition engine uses facial recognition and voice analysis technologies to analyze the user's emotional state.

[1337] Output: Advice based on the user's emotional state.

[1338] Specific behavior: If the emotion recognition engine determines that the user is stressed, the generative AI model will provide advice such as, "Try some simple watering methods."

[1339] (Application example 3)

[1340] Next, a description will be given of Application Example 3 of Form Example 3. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[1341] Conventional agricultural systems have difficulty monitoring crop growth in real time and providing appropriate cultivation advice. Furthermore, there is a lack of means to provide personalized advice that takes into account the user's emotional state, making it difficult to improve user satisfaction and production efficiency.

[1342] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 3 is realized by the following means. In this invention, the server includes means for monitoring the growth status of crops using an IoT device specialized for agriculture, means for providing cultivation advice using a generative AI, means for a user to check the status of crops on a smartphone and adjust the amount of nutrients and water required, means for recognizing the user's emotional state using an emotion engine and for the generative AI to adjust the cultivation advice based on the emotional state, and means for visually displaying data collected from the IoT device so that the user can intuitively understand the growth status of crops. This allows the user to understand the growth status of crops in real time and receive personalized cultivation advice according to their emotional state.

[1343] "IoT devices specialized for agriculture" are devices connected to the Internet, such as sensors and actuators, used in the agricultural field to monitor the growth status of crops in real time.

[1344] "Means for monitoring crop growth status" refers to a method for using IoT devices to collect data such as soil humidity, temperature, and nutrient concentration to monitor the growth status of crops.

[1345] "Generative AI" is an artificial intelligence technology that automatically generates advice on crop cultivation based on collected data.

[1346] "Means for providing cultivation advice" refers to a method for providing users with cultivation advice generated by the generative AI.

[1347] A "smartphone" is a portable information terminal that can connect to the Internet and run applications.

[1348] An "emotion engine" is a technology that recognizes the user's emotional state and adjusts the system's behavior based on that emotion.

[1349] "Means for recognizing the user's emotional state and for the generative AI to adjust cultivation advice based on that emotional state" refers to a method for detecting the user's emotions using an emotion engine and adjusting the content of the advice provided by the generative AI based on that information.

[1350] "Means for visually displaying data collected from IoT devices to enable users to intuitively understand the growth status of crops" refers to a method for displaying collected data in a visual format such as graphs and charts, allowing users to easily understand the status of crops.

[1351] The system for implementing this invention combines IoT devices specialized for agriculture, generative AI, smartphones, and an emotion engine. A specific embodiment of this system is described below.

[1352] First, IoT devices are used to monitor the growth of crops in real time, including temperature sensors, humidity sensors, sensors that measure soil nutrient concentrations, etc. These sensors collect data on the growth of crops and send the data to a server.

[1353] The server receives the collected data and generates cultivation advice using generative AI, which proposes optimal cultivation methods based on past data and current environmental conditions. This advice is then sent from the server to the user's smartphone so that they can review it.

[1354] The smartphone receives cultivation advice from the generative AI and displays it to the user. Through the smartphone application, the user can check the status of their crops and adjust the amount of nutrients and water they need. The smartphone application also visually displays data collected from the IoT device, allowing the user to intuitively understand the growth status of their crops.

[1355] Furthermore, the emotion engine is used to recognize the user's emotional state. The emotion engine detects emotions from the user's facial expressions and voice and sends that information to the server. The server then adjusts the cultivation advice provided by the generative AI based on the data from the emotion engine. For example, if the user is feeling stressed, the advice can be adjusted to include gentler, more encouraging words.

[1356] As a concrete example, the following prompt sentence can be input to a generative AI model:

[1357] Example prompt sentence:

[1358] Temperature: 29.5°C, Humidity: 35%, Machine condition: Abnormal

[1359] Emotional state: sad

[1360] When this prompt is input, the generative AI model will output the following advice:

[1361] Tip: Your machine needs maintenance, but don't worry, it can be fixed quickly.

[1362] In this way, users can understand the growth status of their crops in real time and receive personalized cultivation advice based on their emotional state.

[1363] The flow of the specific processing in Application Example 3 will be described with reference to FIG.

[1364] Step 1:

[1365] IoT devices monitor the growth of crops. Specifically, temperature sensors, humidity sensors, and sensors that measure soil nutrient concentrations collect data. These sensors acquire data such as temperature, humidity, and nutrient concentration in real time and send the data to a server. The input is raw data from the sensors, and the output is the data sent to the server.

[1366] Step 2:

[1367] The server receives data sent from the IoT device. The server stores the received data in a database and prepares it to be passed to the generative AI. The input is data from the IoT device, and the output is data passed to the generative AI.

[1368] Step 3:

[1369] The server generates cultivation advice using generative AI. Generative AI proposes optimal cultivation methods based on past data and current environmental conditions. Specifically, it analyzes data using machine learning algorithms and generates advice. The input is data stored on the server, and the output is the generated cultivation advice.

[1370] Step 4:

[1371] The server sends the generated cultivation advice to the smartphone. The smartphone receives the advice from the server and displays it to the user. The input is advice from the generative AI, and the output is advice displayed on the smartphone.

[1372] Step 5:

[1373] The smartphone visually displays the data collected from the IoT devices. Specifically, the data is displayed in the form of graphs and charts, allowing users to intuitively understand the growth status of their crops. The input is data from the IoT devices, and the output is the visually displayed data.

[1374] Step 6:

[1375] The emotion engine recognizes the user's emotional state. The emotion engine detects emotions from the user's facial expressions and voice and sends that information to the server. The input is the user's facial expressions and voice data, and the output is the recognized emotional state.

[1376] Step 7:

[1377] The server adjusts the cultivation advice provided by the generative AI based on data from the emotion engine. For example, if the user is feeling stressed, the advice content is adjusted to be gentler and include encouraging words. The input is emotion data from the emotion engine, and the output is the adjusted cultivation advice.

[1378] Step 8:

[1379] The server retransmits the adjusted cultivation advice to the smartphone. The smartphone receives the adjusted advice and displays it to the user. The input is the adjusted cultivation advice, and the output is the adjusted advice displayed on the smartphone.

[1380] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[1381] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1382] Another example of generative AI is Gemini (internet search engine). <url: https: gemini.google.com ?hl="ja">) are mentioned.

[1383] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the smart glasses 214.

[1384] [Third embodiment]

[1385] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[1386] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[1387] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1388] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[1389] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[1390] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[1391] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1392] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1393] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[1394] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1395] In the headset type terminal 314, a reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1396] Next, the specific processing by the specific processing unit 290 of the data processing device 12 will be described.

[1397] "Example 1"

[1398] As an example of the present invention, an IoT device specialized for agriculture collects data on soil humidity, temperature, pH, nutrient concentration, etc. in real time. This IoT device has wireless communication capabilities and transmits the collected data to a cloud server.

[1399] "Example 2"

[1400] The generative AI analyzes the growth status of crops based on data stored on a cloud server and generates cultivation advice, such as the appropriate amount of nutrients to add, the amount of water to supply, and temperature adjustments to create the optimal environment for crop growth.

[1401] "Example 3"

[1402] Users can receive cultivation advice from generative AI through a dedicated smartphone application. The application also visually displays data collected from IoT devices, allowing users to intuitively understand the growth status of their crops. Specifically, data such as soil humidity, temperature, and nutrient concentration are displayed in graph form, allowing users to understand the growth status of their crops by comparing it with past data.

[1403] The processing flow of each embodiment will be described below.

[1404] "Example 1"

[1405] Step 1: Agriculturally-specific IoT devices collect real-time data such as soil moisture, temperature, pH, and nutrient concentration.

[1406] Step 2: The IoT device has wireless communication capabilities and transmits the collected data to the cloud server.

[1407] "Example 2"

[1408] Step 1: The generative AI analyzes the growth status of crops based on data stored on the cloud server.

[1409] Step 2: The generative AI generates cultivation advice based on the analysis results. The advice generated suggests the optimal environment for growing crops, including the appropriate amount of nutrients to add, the amount of water to supply, and temperature adjustments.

[1410] "Example 3"

[1411] Step 1: Users can receive cultivation advice from generative AI through a dedicated smartphone application.

[1412] Step 2: The application visually displays the data collected from the IoT device, allowing users to intuitively understand the growth status of their crops. Specifically, data such as soil humidity, temperature, and nutrient concentration are displayed in graph form, allowing users to understand the growth status of their crops by comparing it with past data.

[1413] Example 1

[1414] Next, a description will be given of Example 1 of Form Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1415] In conventional agriculture, it is difficult to manually collect data such as soil humidity, temperature, pH, and nutrient concentration to obtain appropriate cultivation advice. Furthermore, because data collection and analysis are not performed in real time, there is a problem in that it is not possible to respond quickly to crop growth conditions. Furthermore, users need specialized knowledge to obtain appropriate cultivation advice, which is a high hurdle for ordinary farmers.

[1416] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1417] In this invention, the server includes: means for collecting soil humidity, temperature, pH, and nutrient concentration in real time using an IoT device specialized for agriculture; means for transmitting the collected data to a cloud server using wireless communication functions; means for the cloud server to receive the data and store it in a database; means for analyzing the data using a generative AI model and generating cultivation advice; and means for the user to check the analysis results on a terminal and adjust the amount of necessary nutrients and water. This enables real-time data collection and analysis, allowing users to obtain appropriate cultivation advice even without specialized knowledge.

[1418] "IoT devices specialized for agriculture" are devices that incorporate sensors and communication modules used in the agricultural field and are used to collect soil and environmental data.

[1419] "Soil moisture" is an indicator of the percentage of water contained in the soil.

[1420] "Temperature" is an indicator of the state of thermal energy in the soil and the environment.

[1421] "pH" is an indicator of the acidity or alkalinity of soil.

[1422] "Nutrient concentration" is an indicator that shows the concentration of nutrients such as nitrogen, phosphorus, and potassium contained in the soil.

[1423] "Wireless communication function" refers to technology for wirelessly sending and receiving data, including Wi-Fi and Bluetooth.

[1424] A "cloud server" is a remote server that stores and processes data over the Internet.

[1425] A "database" is a system for systematically storing and managing collected data.

[1426] A "generative AI model" is an algorithm that uses machine learning and artificial intelligence techniques to analyze data and generate predictions and advice.

[1427] A "terminal" is a device that a user uses to check or operate information, and includes smartphones, tablets, PCs, etc.

[1428] "Analysis results" are the information and advice obtained after analyzing data using a generative AI model.

[1429] "Cultivation advice" is information that provides specific instructions and suggestions for growing crops based on data analyzed by the generative AI model.

[1430] This invention is a system that uses IoT devices specialized for agriculture to collect soil humidity, temperature, pH, and nutrient concentration in real time, and provides cultivation advice using a generative AI model. Specific embodiments of this system are described below.

[1431] Hardware and Software Configuration

[1432] IoT device

[1433] The IoT devices that users install on their farms contain the following sensors:

[1434] Humidity sensor

[1435] temperature sensor

[1436] pH Sensor

[1437] Nutrient Sensor

[1438] These sensors measure soil moisture, temperature, pH, and nutrient concentration. The IoT devices are equipped with a microcontroller to collect data and send it to a cloud server via wireless communication modules (e.g., Wi-Fi, Bluetooth).

[1439] Cloud Server

[1440] The cloud server receives data sent from the IoT devices and stores it in a database (e.g., Amazon RDS, Google Cloud Firestore). The server then analyzes the data using a generative AI model (e.g., OpenAI's GPT-4) and generates cultivation advice.

[1441] Terminal

[1442] Users can check the analysis results sent from the cloud server using devices such as smartphones, tablets, and PCs. A dedicated application is installed on the device, allowing users to receive cultivation advice in real time.

[1443] Specific examples

[1444] For example, consider a case where a user installs an IoT device on a farm where tomatoes are grown. The IoT device uses a humidity sensor to measure the humidity of the soil and detects that the humidity is 30%. This data is sent to a cloud server using a wireless communication module.

[1445] The cloud server receives the 30% humidity data and stores it in Amazon RDS. The stored data is then input into a generative AI model (GPT-4), which generates advice such as "The soil moisture is decreasing. Please activate the irrigation system."

[1446] This advice is sent from the cloud server to the user's smartphone. The user checks the notification on their smartphone and receives a message saying, "The soil moisture is decreasing. Please operate the irrigation system."

[1447] Prompt Sentence Examples

[1448] "The soil moisture in the farm where I grow tomatoes has dropped to 30%. Please tell me the best way to irrigate them."

[1449] In this way, users can grasp the condition of their farmland in real time and take appropriate measures. This system makes it possible to cultivate crops efficiently, even without specialized knowledge.

[1450] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1451] Step 1:

[1452] The IoT device installed by the user in the farmland uses built-in sensors to measure the humidity, temperature, pH, and nutrient concentration of the soil. For example, a humidity sensor measures the humidity of the soil and detects that the humidity is 30%.

[1453] Inputs: Soil moisture, temperature, pH, nutrient concentration

[1454] Output: Measured data (e.g. humidity 30%)

[1455] Step 2:

[1456] The IoT device sends the collected data to a cloud server via a wireless communication module (e.g., Wi-Fi or Bluetooth). For example, the wireless communication module is used to send data on humidity of 30% to the cloud server.

[1457] Input: Measured data (e.g. humidity 30%)

[1458] Output: Data sent to the cloud server

[1459] Step 3:

[1460] The server receives data sent from IoT devices and stores it in a database (e.g., Amazon RDS, Google Cloud Firestore). The server checks the integrity of the data and stores it in the database in the appropriate format.

[1461] Input: Data sent to the cloud server

[1462] Output: Data stored in the database

[1463] Step 4:

[1464] The server inputs the stored data into a generative AI model (e.g., OpenAI's GPT-4) and analyzes the data. For example, if the soil moisture level is declining, the AI ​​model generates advice such as, "The soil moisture level is declining. Please turn on the irrigation system."

[1465] Input: Data stored in a database

[1466] Output: Generated cultivation advice

[1467] Step 5:

[1468] The server sends the generated analysis results to the user's device, for example, by sending a notification to the user via a smartphone app or web app.

[1469] Input: Generated cultivation advice

[1470] Output: Advice sent to the user's terminal

[1471] Step 6:

[1472] The user checks the analysis results on a device (e.g., smartphone, tablet, or PC). For example, they open a smartphone app and see a notification that says, "The soil moisture is decreasing. Please turn on the irrigation system."

[1473] Input: Advice sent to the user's terminal

[1474] Output: Analysis results confirmed by the user

[1475] In this way, users can understand the condition of their farmland in real time and take appropriate measures.

[1476] (Application example 1)

[1477] Next, a description will be given of Application Example 1 of Form Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1478] Conventional agricultural crop growth monitoring systems lack the ability to collect and analyze data in real time, making it difficult to provide appropriate cultivation advice. Furthermore, environmental monitoring within factories also requires rapid response when an abnormality occurs, but current systems make it difficult to achieve this.

[1479] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1480] In this invention, the server includes a means for monitoring the growth status of crops using an IoT device specialized for agriculture, a means for providing cultivation advice using generative AI, a means for a user to check the status of crops on a smartphone and adjust the amount of nutrients and water required, a means for collecting environmental data within the factory in real time and sending it to a cloud server, and a means for analyzing the collected data in the cloud and issuing an alert if an abnormality is detected. This makes it possible to monitor the growth status of crops in agriculture in real time and provide appropriate cultivation advice, and also enables rapid detection and response to abnormalities in environmental monitoring within the factory.

[1481] An "IoT device specialized for agriculture" is a device that collects data such as soil humidity, temperature, pH, and nutrient concentration in real time and transmits it to a cloud server using wireless communication functions.

[1482] "Means for monitoring crop growth status" refers to a method of using IoT devices specialized for agriculture to collect and analyze data on crop growth.

[1483] "Generative AI" is an artificial intelligence technology that generates appropriate cultivation advice based on collected data.

[1484] "Means for providing cultivation advice" refers to using generative AI to analyze collected data and suggest appropriate cultivation and adjustment methods to users.

[1485] "A means for users to check the status of crops on their smartphones and adjust the amount of nutrients and water required" refers to a method in which users use their smartphones to receive cultivation advice provided by generative AI, check the status of crops, and adjust the amount of nutrients and water required.

[1486] "Means for collecting environmental data within a factory in real time and transmitting it to a cloud server" refers to a method for collecting environmental data such as temperature, humidity, pH, and chemical substance concentrations within a factory in real time and transmitting it to a cloud server using wireless communication.

[1487] "Means of analyzing collected data on the cloud and issuing an alert if an abnormality is detected" refers to a method of analyzing environmental data collected on a cloud server and issuing a warning to the user if an abnormality is detected.

[1488] The system for implementing this invention includes an IoT device specialized for agriculture, generative AI, a smartphone, and a cloud server. The specific operation of each component and how they work together are described below.

[1489] First, the IoT devices specialized for agriculture collect data such as soil humidity, temperature, pH, and nutrient concentration in real time. These devices have wireless communication capabilities and transmit the collected data to a cloud server. The hardware used includes temperature sensors, humidity sensors, pH sensors, and nutrient concentration sensors.

[1490] The cloud server receives the collected data and analyzes it using generative AI. The generative AI generates appropriate cultivation advice based on the collected data. The software used includes a Python program and a requests library for sending HTTP requests.

[1491] The generated cultivation advice is sent from the cloud server to the user's smartphone. The smartphone receives the advice from the generative AI and displays it to the user. The user can then use their smartphone to check the status of their crops and adjust the amount of nutrients and water they need.

[1492] This system can also be used for environmental monitoring within factories. It collects environmental data such as temperature, humidity, pH, and chemical concentration in real time and sends it to a cloud server. The cloud server analyzes the collected data and issues an alert if an abnormality is detected.

[1493] As a concrete example, consider a system that issues an alert when the temperature inside a factory exceeds 30 degrees. In this system, temperature sensors monitor the temperature inside the factory in real time and send data to a cloud server when it exceeds 30 degrees. The cloud server detects the abnormality and sends an alert to the user's smartphone.

[1494] An example of a prompt to be input to the generative AI model is as follows:

[1495] "Generate a Python program that will issue an alert if the temperature in the factory exceeds 30 degrees. The temperature data needs to be collected from the sensor and sent to a cloud server."

[1496] In this way, it becomes possible to collect and analyze data in real time, provide appropriate advice, and respond quickly to abnormalities in both agriculture and environmental monitoring within factories.

[1497] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1498] Step 1:

[1499] Agricultural IoT devices collect real-time data such as soil humidity, temperature, pH, and nutrient concentration. The input is environmental data from the sensors, and the output is the collected environmental data. Specifically, each sensor periodically measures data and stores it in the device's memory.

[1500] Step 2:

[1501] Data collected by IoT devices is sent to a cloud server via wireless communication. The input is environmental data stored in the IoT device, and the output is data sent to the cloud server. Specifically, the communication module in the device converts the data into packets and sends them to the cloud server using a wireless communication protocol.

[1502] Step 3:

[1503] The cloud server analyzes the received data and generates appropriate cultivation advice using generative AI. The input is the environmental data sent to the cloud server, and the output is the generated cultivation advice. Specifically, the analysis program on the cloud server processes the data and inputs it into the generative AI model to generate advice.

[1504] Step 4:

[1505] The cloud server sends the generated cultivation advice to the user's smartphone. The input is the generated cultivation advice, and the output is the advice sent to the smartphone. Specifically, the cloud server converts the advice into a message format and sends it to the smartphone.

[1506] Step 5:

[1507] The user checks the cultivation advice received on their smartphone and adjusts the amount of nutrients and water needed. The input is the cultivation advice displayed on the smartphone, and the output is the user's adjustment of the cultivation environment. Specifically, the user operates the smartphone application and adjusts the cultivation environment according to the advice.

[1508] Step 6:

[1509] Environmental data within the factory is collected in real time and sent to a cloud server. The input is environmental data from sensors within the factory, and the output is the data sent to the cloud server. Specifically, sensors within the factory measure temperature, humidity, pH, and chemical concentration, and send the data to the cloud server.

[1510] Step 7:

[1511] The cloud server analyzes environmental data within the factory and issues an alert if an abnormality is detected. The input is the environmental data sent to the cloud server, and the output is an alert when an abnormality is detected. Specifically, the analysis program on the cloud server monitors the data, and if an abnormality is detected, it generates an alert and sends it to the user's smartphone.

[1512] Step 8:

[1513] The user checks the alert on their smartphone and takes the necessary action. The input is the alert displayed on the smartphone, and the output is the user's response. Specifically, the user operates the smartphone application and takes the necessary action according to the alert.

[1514] Example 2

[1515] Next, a description will be given of Example 2 of Form Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1516] In conventional agriculture, it has been difficult to properly monitor crop growth and provide optimal cultivation advice. In particular, there has been a lack of real-time data collection and analysis, and the provision of specific advice based on the results, making it difficult to optimize the crop growth environment. In addition, the time and effort required for users to manually collect and analyze data has hindered efficient agricultural management.

[1517] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1518] In this invention, the server includes means for monitoring the growth status of crops using agricultural sensor devices, means for providing cultivation advice using a generative AI model based on data stored in the cloud server, means for a user to check the status of the crops on their terminal and adjust the amount of necessary nutrients and water, means for inputting prompts to the generative AI model to analyze the growth status of the crops, and means for transmitting the generated cultivation advice to the user's terminal. This enables real-time data collection and analysis, allowing users to efficiently optimize the growth environment of their crops.

[1519] A "sensor device" is an electronic device that collects data on the growth status of crops in real time.

[1520] A "cloud server" is a remote server that stores, manages, and processes data over the Internet.

[1521] A "generative AI model" is an artificial intelligence model that analyzes input data and generates output for a specific task.

[1522] A "prompt" is an instruction given to a generative AI model that contains information for performing a specific task.

[1523] "Growth advice" means specific instructions or suggestions provided to optimize crop growth.

[1524] A "terminal" is an electronic device used by a user, such as a computer, smartphone, or tablet.

[1525] A "user" is someone who uses the system to manage the growth status of crops and receive cultivation advice.

[1526] This invention is a system that uses agriculturally specialized sensor devices, cloud servers, generative AI models, prompts, and terminals to monitor crop growth and provide optimal cultivation advice.

[1527] The server uses a generative AI model to provide cultivation advice based on data stored on the cloud server. Specifically, the server uses software such as Python and TensorFlow to obtain crop growth data (e.g., temperature, humidity, soil nutrient levels, etc.) stored on the cloud server. It then uses a generative AI model (e.g., GPT-4) to analyze this data and evaluate the crop's growth status. Based on the evaluation results, the server generates appropriate cultivation advice. This advice may include the appropriate amount of nutrients to add, the amount of water to provide, and temperature adjustments.

[1528] A user uses a device to access the cloud server and upload crop growth data. For example, if a user is growing tomatoes, the user uses a device to access the cloud server, input tomato growth data, and upload it. The server receives this data and inputs the following prompt sentence into the generative AI model:

[1529] Example prompt sentence:

[1530] "Analyze the growth status of tomatoes based on the following data and generate appropriate cultivation advice. Data: Temperature 25°C, humidity 60%, soil nitrogen level 20 ppm, soil moisture 30%."

[1531] Based on this prompt, the generative AI model analyzes the tomato's growth status and generates the following advice:

[1532] Example of generated advice:

[1533] "The current temperature and humidity are appropriate. The nitrogen level in the soil is low, so add nitrogen fertilizer. Also, the soil is lacking moisture, so provide an adequate amount of water."

[1534] In this way, the user can optimize the tomato growing environment based on advice provided by the server.

[1535] The system enables real-time data collection and analysis, allowing users to efficiently optimize crop growing environments.

[1536] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1537] Step 1:

[1538] The user accesses the cloud server using a terminal and uploads crop growth data.

[1539] Input: Growth data such as temperature, humidity, and soil nutrient levels.

[1540] Output: Growth data stored on a cloud server.

[1541] How it works: Users access the cloud server using a smartphone or PC, enter crop growth data through a dedicated web application or mobile app, and click the upload button.

[1542] Step 2:

[1543] The server receives the uploaded data and stores it in a database.

[1544] Input: Growth data uploaded by users.

[1545] Output: Growth data stored in a database.

[1546] What happens: The server receives the HTTP request and parses the uploaded data. It connects to the database and inserts the data into the appropriate tables. It performs validation checks to ensure the data is consistent.

[1547] Step 3:

[1548] The server generates prompt sentences based on the stored data and inputs them into the generative AI model.

[1549] Input: Growth data stored in a database.

[1550] Output: The prompt sentence that is input to the generative AI model.

[1551] Specific operation: The server reads the saved data, generates prompt sentences using a Python script, and sends the generated prompt sentences to the generative AI model via an API.

[1552] Step 4:

[1553] The server receives the analysis results from the generative AI model and generates cultivation advice.

[1554] Input: Analysis results from a generative AI model.

[1555] Output: Generated cultivation advice.

[1556] How it works: The server receives a response from the generative AI model, which includes a detailed analysis of the crop's growth status. The server then runs an algorithm based on this information to generate cultivation advice.

[1557] Step 5:

[1558] The server transmits the generated advice to the user's terminal.

[1559] Input: Generated cultivation advice.

[1560] Output: Cultivation advice sent to the user's device.

[1561] Specific operation: The server sends the generated advice to the user's device. The advice is delivered to the user via email or push notification.

[1562] Step 6:

[1563] The user checks the advice on the device and adjusts the cultivation environment.

[1564] Input: Cultivation advice sent to the user's device.

[1565] Output: Regulated growing environment.

[1566] Specific actions: The user checks the advice received on the device. According to the advice, the user adds necessary nutrients and provides water. Based on the advice, the user takes specific actions to optimize the cultivation environment.

[1567] (Application example 2)

[1568] Next, a description will be given of Application Example 2 of Form Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1569] In conventional agriculture, it has been difficult to properly monitor crop growth and maintain an optimal cultivation environment. Users also had to manually adjust the cultivation environment, which was labor-intensive and time-consuming. Furthermore, real-time data collection and analysis was insufficient, making it impossible to quickly identify factors affecting crop growth. To solve these issues, a more efficient and automated system is needed.

[1570] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1571] In this invention, the server includes a means for monitoring the growth status of crops using an IoT device specialized for agriculture, a means for providing cultivation advice using generative AI, a means for a user to check the status of the crops on a smartphone and adjust the amount of necessary nutrients and water, a means for a factory robot to automatically adjust the cultivation environment based on advice from the generative AI, and a means for the generative AI to analyze the growth status of crops based on data stored in the cloud server. This makes it possible to monitor the growth status of crops in real time and automatically maintain an optimal cultivation environment.

[1572] "Agriculturally-specific IoT devices" are internet-connected sensors and devices designed to monitor crop growth.

[1573] "Crop health" refers to the environmental conditions and health of the crop, such as temperature, humidity, and soil nutrient levels, during the growing process.

[1574] "Generative AI" is an artificial intelligence technology that analyzes crop growth conditions and generates optimal cultivation advice based on data stored on a cloud server.

[1575] "Cultivation advice" is a suggestion on the appropriate amount of nutrients to add, the amount of water to supply, temperature adjustments, etc. to maintain the optimal environment for crop growth.

[1576] "A means for users to check the status of crops on their smartphones and adjust the amount of nutrients and water needed" refers to a function that allows users to check the growth status of crops in real time using their smartphones and manually adjust the cultivation environment based on advice from the generative AI.

[1577] A "factory robot" is an automated mechanical device designed to grow crops in a factory, and has the ability to automatically adjust the growing environment based on advice from generative AI.

[1578] A "cloud server" is a remote server for storing, managing, and processing data over the Internet.

[1579] "Real-time collection" means that sensors and devices measure the current situation immediately and transmit that data immediately.

[1580] The system for implementing this invention includes IoT devices specialized for agriculture, generative AI, smartphones, factory robots, and cloud servers. The specific functions of each element and how they work together are described below.

[1581] First, agricultural IoT devices are used to monitor the growth of crops. These devices include temperature sensors, humidity sensors, soil nutrient sensors, etc., and collect data in real time. The collected data is then sent to a cloud server.

[1582] The cloud server stores the collected data, and the generative AI uses this data to analyze the crop's growth status. The generative AI then generates appropriate cultivation advice, including the appropriate amount of nutrients to add, the amount of water to provide, and temperature adjustments. The advice is then sent via the cloud server to smartphones and factory robots.

[1583] Users can use their smartphones to check real-time cultivation advice from the generative AI. The smartphone application displays the status of the crops and provides an interface for adjusting the amount of nutrients and water needed. This allows users to manually adjust the cultivation environment.

[1584] Furthermore, the factory robots can automatically adjust the cultivation environment based on advice from generative AI, for example, adjusting temperature and humidity, or adding necessary nutrients, making it possible to automatically maintain the optimal environment for crop growth.

[1585] For example, by inputting the following prompt into a generative AI model, appropriate cultivation advice will be generated:

[1586] "Please suggest the optimum growing conditions when the temperature is 25 degrees, humidity is 60%, and the soil nitrogen level is 10, phosphorus level is 5, and potassium level is 8."

[1587] Based on this prompt, the generative AI proposes the optimal cultivation environment and sends the results to a smartphone or factory robot via a cloud server. This allows the user to make manual adjustments or the factory robot to automatically adjust the environment to maintain the optimal environment for crop growth.

[1588] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1589] Step 1:

[1590] IoT devices specialized for agriculture monitor the growth status of crops.

[1591] Input: Environmental data such as temperature, humidity, and soil nutrient levels.

[1592] Data processing: Sensors collect data in real time and convert it into a digital format.

[1593] Output: Collected environmental data.

[1594] Step 2:

[1595] The data collected by the IoT device is sent to a cloud server.

[1596] Input: Environmental data from IoT devices.

[1597] Data calculation: Communication processing for uploading data to the cloud server.

[1598] Output: Environmental data stored on a cloud server.

[1599] Step 3:

[1600] The cloud server uses generative AI to analyze the growth status of crops.

[1601] Input: Environmental data stored on a cloud server.

[1602] Data calculation: Generative AI analyzes environmental data and generates optimal cultivation advice.

[1603] Output: Generated cultivation advice.

[1604] Step 4:

[1605] The cloud server sends the generated cultivation advice to smartphones and factory robots.

[1606] Input: Generated cultivation advice.

[1607] Data calculation: Communication processing for sending advice to smartphones and factory robots.

[1608] Output: Cultivation advice sent to smartphone and factory robot.

[1609] Step 5:

[1610] Users can check cultivation advice on their smartphone and adjust the amount of nutrients and water needed.

[1611] Input: Cultivation advice displayed on smartphone.

[1612] Data processing: The user manually adjusts the cultivation environment based on the advice.

[1613] Output: Regulated growing environment.

[1614] Step 6:

[1615] Factory robots automatically adjust the cultivation environment based on advice from generative AI.

[1616] Input: Cultivation advice sent to the factory robot.

[1617] Data calculation: Automatically adjusts temperature, humidity and nutrient addition amounts based on advice.

[1618] Output: Optimized growing environment.

[1619] Step 7:

[1620] The cloud server inputs prompt statements into the generative AI model and suggests the optimal cultivation environment.

[1621] Input: Prompt statement (e.g., "Please suggest the optimal growing environment when the temperature is 25°C, humidity is 60%, and the soil nitrogen level is 10, phosphorus level is 5, and potassium level is 8.").

[1622] Data calculation: A generative AI model suggests the optimal growing environment based on the prompt.

[1623] Output: Suggested optimal growing environment.

[1624] Example 3

[1625] Next, a third embodiment of the third embodiment will be described. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1626] In conventional agriculture, it has been difficult to accurately monitor crop growth and receive appropriate cultivation advice. Users also lacked the means to understand crop conditions in real time and adjust the amount of nutrients and water required. This made it difficult to properly manage factors that affect crop growth, hindering productivity improvements.

[1627] The identification process by the identification processing unit 290 of the data processing device 12 in the third embodiment is realized by the following means. In this invention, the server includes a means for transmitting data collected from the sensor device to the server and storing it, a means for the mobile terminal to acquire the data from the server and visually display it, and a means for the user to input a prompt sentence to the generative artificial intelligence and receive advice. This allows the user to understand the growth status of crops in real time and receive appropriate cultivation advice.

[1628] A "sensor device" is a device for collecting data on the growth status of crops.

[1629] "Generative AI" is an AI technology that generates appropriate cultivation advice based on user input.

[1630] A "mobile terminal" is an electronic device that can be carried by a user and is a device for acquiring and displaying data through applications.

[1631] A "server" is a computer system that receives and stores data sent from sensor devices.

[1632] A "prompt" is a question or instruction that a user inputs to a generative artificial intelligence.

[1633] "Visually displaying" means presenting data in a format such as a graph or chart that is easy for users to view.

[1634] "Growth advice" is specific instructions or suggestions for optimizing crop growth.

[1635] MODE FOR CARRYING OUT THE INVENTION

[1636] This invention is a system that combines agriculturally specialized sensor devices, generative artificial intelligence, mobile terminals, and servers to monitor the growth status of crops and provide appropriate cultivation advice.

[1637] Hardware and software used

[1638] Sensor devices: soil moisture sensors, temperature sensors, nutrient concentration sensors, etc.

[1639] Server: A computer system that receives and stores data (e.g., using a MySQL database).

[1640] Mobile device: An electronic device that can be carried by a user, such as a smartphone or tablet.

[1641] Generative AI: An AI model that generates cultivation advice based on user prompts

[1642] System Operation

[1643] The server receives the data collected from the sensor devices and stores it in a database, allowing for real-time recording of data such as soil moisture, temperature, and nutrient concentration.

[1644] Users access the server through a dedicated application on their mobile device to retrieve the stored data. The application visually displays the retrieved data in graph form, allowing users to understand the growth status of their crops by comparing it with past data. For example, a line graph can be used to display changes in soil moisture over the past week.

[1645] The user enters a prompt sentence into an input field within the application to send a question or instruction to the generative AI. For example, they might enter, "What is the ideal soil moisture level for growing tomatoes?" The server then sends this prompt sentence to the generative AI, and the AI ​​model generates appropriate advice. The generated advice is then provided to the user via the server.

[1646] Specific examples

[1647] For example, if a user inputs a prompt such as "What is the optimum soil humidity for growing tomatoes?", the generative AI will generate advice such as "The optimum soil humidity for growing tomatoes is 60% to 70%." The user can then adjust the soil humidity based on this advice.

[1648] Prompt Sentence Examples

[1649] "What is the ideal soil moisture level for growing tomatoes?"

[1650] "What should I do if my current soil temperature is too high?"

[1651] "If nutrient concentrations are low, what fertilizer should I add?"

[1652] In this way, the user can grasp the growth status of the crop in real time and receive appropriate cultivation advice. This makes it possible to optimize the growth environment of the crop and improve productivity. The flow of the identification process in Example 3 will be described with reference to FIG. 15.

[1653] Step 1:

[1654] The server collects data from sensor devices. Specifically, it receives data in real time from soil moisture sensors, temperature sensors, nutrient concentration sensors, etc. The input is data from the sensor devices, and the output is raw data stored on the server. The server stores this data in a database.

[1655] Step 2:

[1656] The server processes the stored data and extracts the necessary information. Specifically, it analyzes the raw data stored in the database and extracts information such as soil moisture, temperature, and nutrient concentration. The input is the raw data stored in the database, and the output is the analyzed information. The server organizes this information and converts it into a format that users can access.

[1657] Step 3:

[1658] The user launches a dedicated application on their mobile device and accesses the server. Specifically, the application sends a request to the server to obtain the latest data. The input is the user's request, and the output is the latest data obtained from the server. The device receives this data and prepares it for display.

[1659] Step 4:

[1660] The terminal visually displays the acquired data. Specifically, it displays data such as soil moisture, temperature, and nutrient concentration in graph form. The input is data acquired from the server, and the output is graphs and charts displayed to the user. This allows the user to understand the growth status of crops by comparing it with past data.

[1661] Step 5:

[1662] The user enters a prompt into an input field within the application, such as a question like, "What is the ideal soil moisture level for growing tomatoes?" The input is the user's prompt, and the output is a request sent to the generative AI. The device then sends this prompt to the server.

[1663] Step 6:

[1664] The server sends the prompt from the user to the generative AI. Specifically, it parses the prompt and sends it to the generative AI in an appropriate format. The input is the user's prompt, and the output is a request sent to the generative AI. The generative AI receives this request and generates appropriate advice.

[1665] Step 7:

[1666] The generative AI generates advice based on the prompt sentence and sends it back to the server. Specifically, it analyzes the input prompt sentence and generates appropriate cultivation advice. The input is the prompt sentence and the output is the generated advice. The server receives this advice and provides it to the user.

[1667] Step 8:

[1668] Users receive advice from the generative AI through the application. Specifically, the advice is displayed within the application for the user to review. The input is advice from the server, and the output is advice displayed to the user. The user can adjust their crop cultivation based on this advice.

[1669] (Application example 3)

[1670] Next, a description will be given of Application Example 3 of Form Example 3. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1671] Conventional agricultural systems have difficulty monitoring crop growth in real time and providing appropriate cultivation advice. Furthermore, there was a lack of means to collect environmental data in real time and provide advice on optimal production processes within factories. This made efficient production management difficult, resulting in problems such as reduced productivity and inconsistent quality.

[1672] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 3 is realized by the following means.

[1673] In this invention, the server includes: means for monitoring the growth status of crops using IoT devices specialized for agriculture; means for providing cultivation advice using generative AI; means for users to check the status of crops on their smartphones and adjust the amount of nutrients and water needed; means for collecting environmental data within the factory in real time and providing advice on optimal production processes using generative AI; and means for visually displaying data collected from the IoT devices so that users can intuitively understand the production status. This makes it possible to collect data in real time and provide optimal advice in agricultural and factory production processes, thereby improving productivity and stabilizing quality.

[1674] "IoT devices specialized for agriculture" are devices connected to the Internet, such as sensors and actuators, used in the agricultural field to monitor the growth status of crops in real time.

[1675] "Crop growth conditions" refers to environmental data such as soil moisture, temperature, and nutrient concentration during the crop growth process.

[1676] "Generative AI" is an artificial intelligence technology that generates advice on optimal cultivation methods and production processes based on collected data.

[1677] "Growth advice" means specific instructions or recommendations provided to optimize crop growth.

[1678] A "user" is an individual or organization that uses the system to check the growth status of crops and receive cultivation advice.

[1679] A "smartphone" is a portable information terminal that can connect to the Internet and display and operate data through applications.

[1680] "Environmental data within the factory" refers to data such as temperature, humidity, vibration, and machine operating status within the factory.

[1681] "Production process advice" is specific instructions and recommendations provided to optimize production efficiency within a factory.

[1682] "Visual display" refers to displaying collected data in a way that is easy for users to see, such as in graphs or charts.

[1683] "Real-time collection" means that data is collected immediately and processed and displayed near-simultaneously.

[1684] The system for implementing this invention includes an IoT device specialized for agriculture, generative AI, a smartphone, an environmental data collection device in a factory, and a visualization tool. Specific embodiments of each component are described below.

[1685] First, agricultural IoT devices collect real-time environmental data such as soil humidity, temperature, and nutrient concentration. These devices use sensor technology to monitor crop growth. The collected data is then transmitted wirelessly to a server.

[1686] The server receives the collected data and inputs it into the generative AI model. The generative AI model generates optimal cultivation advice based on this data. The generated advice is sent to the user's smartphone, where the user can check the advice through the application. For example, if the prompt sentence "Factory temperature: 25 degrees, humidity: 60%, vibration: 0.5Hz, machine operation status: running" is input into the generative AI model, optimal production process advice will be provided.

[1687] Next, environmental data collection devices in the factory collect data such as temperature, humidity, vibration, and machine operation status in real time. This data is also sent to a server and input into a generative AI model. The generative AI model generates advice to optimize the production process in the factory. The generated advice is sent to the factory manager's terminal and displayed in graphs and charts using visualization tools.

[1688] The visualization tool uses data visualization libraries such as Matplotlib to display collected data in the form of graphs and charts, allowing users and factory managers to intuitively understand the growth and production status.

[1689] For example, the following prompts can be fed to a generative AI model:

[1690] "Factory temperature: 25°C, humidity: 60%, vibration: 0.5Hz, machine operation status: in operation"

[1691] Based on this prompt, the generative AI model provides advice such as, "The current factory environment is optimal. Please continue to maintain this state. However, if vibrations exceed 0.7 Hz, please consider performing maintenance on the machine."

[1692] In this way, it becomes possible to collect data in real time and provide optimal advice in agricultural and factory production processes, thereby improving productivity and stabilizing quality.

[1693] The flow of the specific processing in Application Example 3 will be described with reference to FIG.

[1694] Step 1:

[1695] Agriculturally specialized IoT devices collect environmental data such as soil humidity, temperature, and nutrient concentration in real time. This data is transmitted to a server via wireless communication. The input is the environmental data from the IoT device, and the output is the data transmitted to the server.

[1696] Step 2:

[1697] The server receives the collected environmental data and stores it in a database. The input is the environmental data sent from the IoT device, and the output is the data stored in the database. Specifically, the server checks the data format, converts it into the appropriate format, and stores it.

[1698] Step 3:

[1699] The server inputs the stored data into the generative AI model. The input is the environmental data stored in the database, and the output is the data input into the generative AI model. Specifically, the server converts the data into an appropriate format and sends it to the API of the generative AI model.

[1700] Step 4:

[1701] The generative AI model generates optimal cultivation advice based on input data. The input is environmental data sent from the server, and the output is the generated cultivation advice. Specifically, the generative AI model analyzes the data, generates prompt sentences, and creates advice.

[1702] Step 5:

[1703] The server sends the generated cultivation advice to the user's smartphone. The input is the cultivation advice from the generative AI model, and the output is the advice sent to the user's smartphone. Specifically, the server converts the advice into an appropriate format and sends it to the smartphone application.

[1704] Step 6:

[1705] The user's smartphone displays the received cultivation advice. The input is the cultivation advice sent from the server, and the output is the advice displayed on the smartphone screen. Specifically, the smartphone application analyzes the advice and displays it in an easy-to-read format for the user.

[1706] Step 7:

[1707] Environmental data collection devices in factories collect data such as temperature, humidity, vibration, and machine operation status in real time. This data is sent to a server via wireless communication. The input is the data from the environmental data collection devices, and the output is the data sent to the server.

[1708] Step 8:

[1709] The server receives collected environmental data from within the factory and stores it in a database. The input is data sent from the environmental data collection device, and the output is data stored in the database. Specifically, the server checks the data format, converts it into an appropriate format, and stores it.

[1710] Step 9:

[1711] The server inputs the stored environmental data from within the factory into the generative AI model. The input is the environmental data stored in the database, and the output is the data input into the generative AI model. Specifically, the server converts the data into an appropriate format and sends it to the API of the generative AI model.

[1712] Step 10:

[1713] The generative AI model generates optimal production process advice based on input data. The input is environmental data sent from the server, and the output is the generated production process advice. Specifically, the generative AI model analyzes the data, generates prompt statements, and creates advice.

[1714] Step 11:

[1715] The server sends the generated production process advice to the factory manager's terminal. The input is the production process advice from the generative AI model, and the output is the advice sent to the factory manager's terminal. Specifically, the server converts the advice into an appropriate format and sends it to the terminal.

[1716] Step 12:

[1717] The factory manager's terminal displays the received production process advice using a visualization tool. The input is the production process advice sent from the server, and the output is the advice displayed on the terminal screen. Specifically, the visualization tool analyzes the advice and displays it in the form of graphs and charts.

[1718] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1719] "Example 1"

[1720] One embodiment of the present invention combines an agricultural IoT device, a generative AI, a smartphone, and an emotion engine. The IoT device collects data on crop growth in real time, and the generative AI generates cultivation advice based on that data. The smartphone then displays the cultivation advice from the generative AI to the user. Furthermore, the emotion engine recognizes the user's emotions, and the generative AI adjusts the cultivation advice based on the user's emotional state.

[1721] "Example 2"

[1722] As a specific example, if a user feels stressed, the emotion engine communicates this information to the generative AI. Based on this information, the generative AI generates cultivation advice that takes into account the user's stress. For example, if the user is feeling stressed, it will only recommend easy tasks. In addition to the cultivation advice from the generative AI, the smartphone also displays the emotion recognition results from the emotion engine. This allows the user to check their own emotional state an...

Claims

1. A means for collecting crop growth data using an IoT device that can be used in agriculture; A means for generating cultivation advice for the crop based on the growth data using a generation system AI; A means for recognizing an emotional state of a user using an emotion engine, and for the generating AI to adjust the cultivation advice based on the emotional state of the user; A means for outputting the adjusted cultivation advice; A system including:

2. The adjusting means adjusts the cultivation advice based on a prompt sentence corresponding to an emotional state of the user. The system of claim 1 .

3. The output means visually displays the emotional state of the user and the cultivation advice. The system of claim 1 .

Images