system

Abstract

We provide the system. [Solution] A system comprising: means for measuring environmental data; means for transmitting the measured data to a server; means for the server to store the transmitted data in a database; means for the server to analyze past and present data using a generating AI; means for the server to generate training advice based on the analysis results; means for generating control commands based on the generated training advice; means for transmitting the control commands to a corresponding control device; means for the control device to operate according to the control commands; and means for the user to confirm the operation results.

Description

Technical Field

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

Background Art

[0002] Patent Document 1 discloses a method for controlling a persona chatbot, which is performed by at least one processor, and includes steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a character of the chatbot, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance in response to the user utterance.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention Invention

Problems to be Solved by the Invention

[0004] Operations in agriculture have conventionally relied on intuition and experience, and there has been a problem that the hurdle is high, especially for inexperienced or new entrants. In addition, it is difficult to obtain and analyze environmental data in real time, and it is also difficult to determine the optimal operation timing and method. Therefore, a system for realizing efficient growth management is required.

Means for Solving the Problems

[0005] In order to solve the above problems, the present invention provides the following means.

[0006] A system comprising means for measuring environmental data, means for transmitting the measured data to a server, means for the server to store the transmitted data in a database, means for the server to analyze past and present data using a generating AI, means for the server to generate cultivation advice based on the analysis results, means for generating control commands based on the generated cultivation advice, means for transmitting the control commands to a corresponding control device, means for the control device to operate according to the control commands, and means for the user to confirm the operation results enables real-time acquisition of environmental data and its effective utilization, allowing even inexperienced individuals to perform optimal agricultural work.

[0007] "Environmental data" refers to various environmental conditions within farms and cultivation facilities, such as temperature, humidity, sunlight, and moisture content.

[0008] "Means of measurement" refers to methods of acquiring environmental data in real time using measuring devices such as temperature sensors, humidity sensors, solar radiation sensors, and soil moisture sensors.

[0009] "Means of transmission" refers to communication modules and protocols used to send measured environmental data to a server via a network.

[0010] A "server" refers to a computer device that receives measured data, stores it in a database, and performs analysis using AI.

[0011] A "database" refers to a storage device used by a server to store and manage environmental data and historical data it has received.

[0012] "Generative AI" refers to artificial intelligence technology that uses accumulated data to predict optimal growing conditions and future changes in plants, and provides advice accordingly.

[0013] "Means of analysis" refers to the process by which the generative AI analyzes data and generates optimal training advice.

[0014] "Cultivation advice" refers to recommendations regarding the optimal growing conditions and future management methods for plants, derived from the results of analysis by the generated AI.

[0015] A "control command" refers to an instruction given to direct specific actions based on training advice.

[0016] A "control device" refers to a device that adjusts environmental conditions according to control commands received from a server (e.g., a watering system, lighting system, fertilizer spreader, etc.).

[0017] A "user" refers to a person who uses this system to manage farms and cultivation facilities.

[0018] "Means of verification" refers to an interface (e.g., smartphone app, PC software, etc.) that allows the user to check the operation results of the control device and make manual adjustments as needed. [Brief explanation of the drawing]

[0019] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of the data processing device and smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] It is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] It shows an emotion map to which a plurality of emotions are mapped. [Figure 10] It shows an emotion map to which a plurality of emotions are mapped. [Figure 11] It is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] It is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] It is a sequence diagram showing the processing flow of the data processing system in Example 2 when an emotion engine is combined. [Figure 14] It is a sequence diagram showing the processing flow of the data processing system in Application Example 2 when an emotion engine is combined.

Mode for Carrying Out the Invention

[0020] Hereinafter, an example of an embodiment of a system according to the technology of the present disclosure will be described with reference to the accompanying drawings.

[0021] First, the terms used in the following description will be explained.

[0022] In the following embodiments, a processor with a reference numeral (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of a plurality of arithmetic units. Also, the processor may be a single type of arithmetic unit or a combination of a plurality of types of arithmetic units. Examples of arithmetic units include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), and the like.

[0023] In the following embodiments, signed RAM (Random Access Memory) is a memory that temporarily stores information and is used as work memory by the processor.

[0024] In the following embodiments, the signed storage is one or more non-volatile storage devices that store various programs and various parameters. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes.

[0025] In the following embodiments, the signed communication interface (I / F) is an interface that includes a communication processor and an antenna, etc. The communication interface manages communication between multiple computers. Examples of communication standards applicable to the communication interface include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0026] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." That is, "A and / or B" means that it may be A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or."

[0027] [First Embodiment]

[0028] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0029] As shown in Figure 1, the data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0030] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0031] The smart device 14 comprises a computer 36, a reception device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The reception device 38, output device 40, and camera 42 are also connected to the bus 52.

[0032] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0033] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form perceptible to the user 20 (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0034] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

[0035] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0036] As shown in Figure 2, in the data processing device 12, a specific processing is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" related to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0037] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0038] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with a specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0039] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0040] This invention relates to a system that measures environmental data in agriculture in real time, analyzes and predicts it using AI, generates appropriate cultivation advice and control commands, and automatically executes them. The following describes the embodiments for implementing this system.

[0041] (1) Data collection using IoT

[0042] Terminal: Multiple sensors (temperature sensors, humidity sensors, solar radiation sensors, soil moisture sensors, etc.) placed on farms and cultivation facilities measure environmental data for each area in real time every 10 minutes. This ensures that the latest environmental information is always available.

[0043] Terminal: Measured environmental data is transmitted to the server via a communication module built into each sensor, over a stable network. Data transmission is performed periodically, and a certain amount of buffering is also performed to avoid network instability.

[0044] Server: The server saves received data to the database in real time. The saved data is time-stamped and managed centrally, including past data.

[0045] Specific example: At 6:00 AM, a device (sensor) measures temperature (25°C), humidity (60%), sunlight (30,000 lux), and moisture content (20%), and sends this data to the server 10 minutes later. The server stores this data in a database with a timestamp.

[0046] (2) Data analysis and prediction using generative AI

[0047] Server: The server retrieves historical environment data (e.g., the past 3 months) from the database and provides it to the generating AI. This allows for a comparison between historical and current data.

[0048] Server: The generating AI analyzes and predicts plant growing conditions and future environmental changes based on acquired data. The generating AI generates advice on appropriate growing conditions and management methods, and outputs it in text format.

[0049] Specific example: A server retrieves temperature, humidity, sunlight, and moisture content data for the past three months and provides it to a generating AI. The AI ​​determines that "the temperature is appropriate, but the moisture content is low, so 3 liters of watering is necessary" and generates this advice.

[0050] (3) Execution and control based on data prediction using generative AI

[0051] Server: Based on advice from the generating AI, it generates specific control commands (e.g., activate the watering system) and sends them to the corresponding terminal. This automatically performs appropriate environmental adjustments.

[0052] Terminal: The terminal operates the corresponding control device (e.g., watering system, lighting system, fertilizer spreader, etc.) according to the control commands received from the server.

[0053] User: Users access the system via smartphone or PC to check the control results. They verify that the execution was performed correctly and make additional manual adjustments as needed.

[0054] Specific example: Based on the advice of the AI, the server generates a command that says, "To achieve a moisture content of 30%, water with 3 liters of water." The terminal (watering system) receives this command and waters with 3 liters of water. The user checks the watering results on their smartphone and manually instructs the system to water additionally if necessary.

[0055] This system enables the real-time acquisition and effective utilization of environmental data, allowing even inexperienced individuals to perform optimal agricultural tasks.

[0056] The following describes the processing flow.

[0057] (1) Data collection using IoT

[0058] Step 1:

[0059] Terminals: Various sensors, such as temperature sensors, humidity sensors, solar radiation sensors, and soil moisture sensors, measure environmental data in each area.

[0060] Step 2:

[0061] Terminal: Temporarily stores measured environmental data in internal memory. For example, it records data such as temperature 25°C, humidity 60%, solar radiation 30,000 lux, and moisture content 20%.

[0062] Step 3:

[0063] Terminal: At regular intervals (e.g., every 10 minutes), it transmits measurement data to the server via a wireless communication module. Communication methods include Wi-Fi and LoRa.

[0064] Step 4:

[0065] Server: Validates received environmental data and stores it in the database with a timestamp. This ensures data integrity and consistency.

[0066] Specific example: At 6:00 AM, a sensor measures data showing a temperature of 25°C, humidity of 60%, solar radiation of 30,000 lux, and moisture content of 20%, and sends this data to the server at 6:10 AM. The server then stores this data in its database.

[0067] ---

[0068] (2) Data analysis and prediction using generative AI

[0069] Step 1:

[0070] Server: Retrieves environmental data from the database for a specified period (e.g., the past 3 months). The retrieved data includes temperature, humidity, solar radiation, and moisture content.

[0071] Step 2:

[0072] Server: Inputs acquired historical data and current environmental data into the generating AI and begins analysis.

[0073] Step 3:

[0074] Server: The generating AI analyzes the input data and evaluates the optimal conditions for plant growth. Parameters considered here include appropriate temperature range, water content, and light intensity.

[0075] Step 4:

[0076] Server: Based on the analysis results, the generating AI creates cultivation advice (e.g., "The water level is low, so 3 liters of watering is needed") and outputs it in text format.

[0077] Specific example: A server provides data from the past three months to an AI, which determines that "the temperature is appropriate, but there is insufficient moisture. Watering is necessary," and generates advice that 3 liters of watering are required.

[0078] ---

[0079] (3) Execution and control based on data prediction using generative AI

[0080] Step 1:

[0081] Server: Based on AI advice, it generates specific control commands. For example, it might generate a command to sprinkle 3 liters of water to achieve a moisture content of 30%.

[0082] Step 2:

[0083] Server: Sends the generated control commands to the corresponding terminals (watering systems, lighting systems, fertilizer spreaders, etc.).

[0084] Step 3:

[0085] Terminal: In accordance with the received control command, the watering system performs the corresponding action, such as spraying 3 liters of water.

[0086] Step 4:

[0087] User: Access the system from a smartphone or PC and check the control results. Make additional manual adjustments as needed.

[0088] Specific example: The server generates a control command to "water with 3 liters of water" and sends it to the terminal's watering system. The watering system automatically waters with 3 liters of water, and the user checks the watering results on their smartphone and manually instructs additional watering if necessary.

[0089] ---

[0090] This is a detailed explanation of the specific operations at each processing step of the system.

[0091] (Example 1)

[0092] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0093] The challenge lies in creating a system that collects, analyzes, and predicts environmental data in agriculture in real time, providing optimal growing conditions for plants. This will enable the provision of cultivation methods based on highly accurate information that could not be obtained with conventional methods. It is also necessary to address data transfer problems caused by network instability and reduce the burden of manual work performed by users.

[0094] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0095] In this invention, the server includes a device for measuring environmental data, a device for transmitting the measured data to the server, a device for the server to store the transmitted data in a database, a device for the server to analyze past and present data using a generating AI, a device for the server to generate cultivation advice based on the analysis results, a device for generating control commands based on the generated cultivation advice, a device for transmitting the generated control commands to a corresponding control device, a device for the control device to operate according to the control commands, and a device for the user to confirm the operation results. This enables real-time data collection, analysis, and prediction in agriculture, allowing for the provision of optimal plant growing conditions and appropriate environmental adjustments.

[0096] "Environmental data" refers to numerical data that indicates the state of the surrounding environment in agriculture, such as temperature, humidity, solar radiation, and soil moisture content.

[0097] "Measuring devices" refer to sensors and measuring instruments used to collect environmental data.

[0098] "Transmitting device" refers to a communication device used to transfer measured environmental data to a server.

[0099] A "database" is a storage device that centrally manages information stored on a server and allows for searching and analysis as needed.

[0100] "Generative AI" refers to artificial intelligence that analyzes and predicts based on collected data, and then suggests optimal breeding conditions and management methods.

[0101] "Cultivation advice" refers to information provided in text format by a generating AI based on its analysis results, outlining the optimal growing conditions and management methods for plants.

[0102] A "control command" is an instruction sent to each control device based on the advice of the generated AI, providing specific operational instructions.

[0103] A "control device" refers to equipment or systems used to adjust the agricultural environment according to control commands received from a server.

[0104] A "device for checking operation results" refers to an interface device used by the user to check the execution results of the system and perform additional operations as needed.

[0105] "Buffering" is the process of temporarily storing data to avoid network instability and sending it when stable communication becomes possible.

[0106] SQL queries are structured query languages ​​used to retrieve specific information from databases.

[0107] This invention is a system that measures environmental data in agriculture in real time, analyzes and predicts the data using AI generation, generates appropriate cultivation advice and control commands, and automatically executes them. A specific embodiment of this system is described below.

[0108] (1) Data collection using IoT

[0109] Terminal: Multiple sensors (temperature sensors, humidity sensors, solar radiation sensors, soil moisture sensors) placed on farms and cultivation facilities measure environmental data for each area every 10 minutes. This ensures that the latest environmental information is always available.

[0110] Terminal: Measured environmental data is transmitted to the server via a communication module (e.g., LoRaWAN module) built into each sensor, over a stable network (e.g., Wi-Fi, 5G). Data transmission is performed periodically, and a certain amount of buffering is also performed to avoid network instability.

[0111] Server: The server saves received data in real time to a database (e.g., MySQL®, PostgreSQL). The saved data is time-stamped and managed centrally, including past data.

[0112] Specific example: At 6:00 AM, a device (sensor) measures temperature (25°C), humidity (60%), sunlight (30,000 lux), and moisture content (20%), and sends this data to the server 10 minutes later. The server stores this data in a database with a timestamp.

[0113] (2) Data analysis and prediction using generative AI

[0114] Server: The server retrieves historical environment data (e.g., the past 3 months) from the database and provides it to the generating AI (e.g., GPT-4®). This allows for comparison between historical and current data.

[0115] Server: Based on data acquired by the generating AI, it analyzes and predicts plant growing conditions and future environmental changes. The generating AI generates advice on appropriate growing conditions and management methods, and outputs it in text format.

[0116] Specific example: A server retrieves temperature, humidity, sunlight, and moisture content data for the past three months and provides it to a generating AI. The AI ​​determines that "the temperature is appropriate, but the moisture content is low, so 3 liters of watering is necessary" and generates this advice.

[0117] (3) Execution and control based on data prediction using generative AI

[0118] Server: Based on advice from the generating AI, it generates specific control commands (e.g., activate the watering system) and sends them to the corresponding terminal. This automatically performs appropriate environmental adjustments.

[0119] Terminal: The terminal operates the corresponding control device (e.g., watering system, lighting system, fertilizer spreader, etc.) according to the control commands received from the server.

[0120] User: Users access the system via smartphone or PC to check the control results. They verify that the execution was performed correctly and make additional manual adjustments as needed.

[0121] Specific example: Based on the advice of the AI, the server generates a command that says, "To achieve a moisture content of 30%, water with 3 liters of water." The terminal (watering system) receives this command and waters with 3 liters of water. The user checks the watering results on their smartphone and manually instructs the system to water additionally if necessary.

[0122] Specific examples of input prompt sentences for generative AI models

[0123] Prompt: "Based on environmental data from the past three months, please advise on the current plant growing conditions. The data is as follows: Temperature (20°C, 22°C, 25°C), Humidity (50%, 55%, 60%), Sunlight (25,000 lux, 27,000 lux, 30,000 lux), Soil moisture (15%, 18%, 20%)."

[0124] This system enables the real-time acquisition and effective utilization of environmental data, allowing even inexperienced individuals to perform optimal agricultural work.

[0125] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0126] Step 1: Measuring environmental data

[0127] Terminal: Multiple sensors (temperature sensors, humidity sensors, solar radiation sensors, soil moisture sensors) placed in the farm or cultivation facility measure environmental data for each area every 10 minutes. Specifically, the temperature sensor measures the current temperature as 25°C and stores this value in internal memory. This measurement data serves as input.

[0128] Step 2: Send

[0129] Terminal: Measured environmental data is transmitted to the server via a stable network (e.g., Wi-Fi, 5G) using a communication module (e.g., LoRaWAN module) built into each sensor. Data transmission occurs every 10 minutes, with a certain amount of buffering to avoid network instability. Specifically, the sensor measures temperature (25°C), humidity (60%), solar radiation (30,000 lux), and moisture content (20%), combines this data into a single packet, and sends it to the server. This transmitted data becomes the output.

[0130] Step 3: Receiving and saving data

[0131] Server: The server saves received data in real time to a database (e.g., MySQL, PostgreSQL). Saved data is timestamped, and past data is centrally managed. Specifically, the server saves received data using the "Insert into Database" command. This data is the input, and the saved data is the output.

[0132] Step 4: Obtaining historical data

[0133] Server: The server retrieves historical environment data (e.g., the past 3 months) from the database using SQL queries and provides it to the generating AI (e.g., GPT-4). Specifically, the server executes the SQL query "SELECT FROM environmentdata WHERE date > current date - INTERVAL 3 MONTH", formats the retrieved data, and inputs it into the generating AI. This retrieved data is the input.

[0134] Step 5: Data analysis and advice generation

[0135] Server: Based on data acquired by the generating AI, the server analyzes and predicts plant growing conditions and future environmental changes. The generating AI generates advice on appropriate growing conditions and management methods and returns it to the server in text format. Specifically, if the generating AI determines that "the temperature is appropriate, but the moisture level is low, so 3 liters of watering is necessary," it generates this advice. This analyzed data is the input, and the generated advice is the output.

[0136] Step 6: Generating control commands

[0137] Server: Based on advice from the generating AI, the server generates specific control commands (e.g., activating a watering system) and sends them to the corresponding terminal. Specifically, the server analyzes the advice from the generating AI and generates a command, "Water with 3 liters of water to bring the moisture level to 30%", and sends it to the terminal. This advice is the input, and the generated command is the output.

[0138] Step 7: Execute control commands

[0139] Terminal: The terminal operates the corresponding control device (e.g., watering system, lighting system, fertilizer spreader, etc.) according to the control commands received from the server. Specifically, the terminal (watering system) receives a command and activates its internal mechanism to spray 3 liters of water. This control command is the input, and the operation result of each device is the output.

[0140] Step 8: Check the execution results

[0141] User: The user accesses the system via smartphone or PC and checks the control results. Specifically, the user checks the system status on their smartphone to confirm whether watering was performed as scheduled. If necessary, they send a "manual additional watering" command to their terminal. The system's operation results are the input, and the user's confirmation and manual instructions are the output.

[0142] (Application Example 1)

[0143] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0144] Traditional factory production management and environmental control often involve manual processes, leading to inefficiencies and a lack of optimization. Furthermore, real-time monitoring of multiple environmental factors (temperature, humidity, vibration, etc.) and immediate control based on that information are difficult, potentially resulting in problems with production efficiency and quality control. Therefore, the challenge lies in providing new methods to improve production efficiency and optimize quality control.

[0145] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0146] In this invention, the server includes means for measuring environmental data, means for transmitting the measured data to the server, means for the server to store the transmitted data in a database, means for the server to analyze past and present data using a generating AI, means for the server to generate production advice based on the analysis results, means for generating control commands based on the generated production advice, means for transmitting the control commands to a corresponding automated device, means for the automated device to operate according to the control commands, and means for the user to confirm the operation results. This enables real-time monitoring and immediate control of environmental data, making it possible to optimize production efficiency and quality control.

[0147] "Environmental data" refers to data that measures information about the working environment in a factory in real time, such as temperature, humidity, vibration, and illuminance.

[0148] A "server" is a device or system that receives measured environmental data, stores it in a database, and performs analysis and prediction using generating AI.

[0149] A "database" is a digital storage system in which environmental data sent to a server is stored with timestamps and centrally managed.

[0150] "Generative AI" refers to artificial intelligence that performs analysis and prediction based on past and current environmental data, and is used to generate production advice and control commands.

[0151] "Production advice" refers to the process where the generating AI analyzes environmental data and provides specific advice in text format to optimize production efficiency and quality control.

[0152] A "control command" is an instruction sent to automated equipment based on generated production advice, and it is an executable command to adjust the environment and work content.

[0153] "Automated equipment" refers to mechanical devices and robots that operate according to control commands, and is used for environmental adjustment and production work within factories.

[0154] A "user" is a person who accesses the system to check its operation results and make additional adjustments as needed.

[0155] This invention is a system that improves production efficiency and quality control by measuring environmental data within a factory in real time and analyzing and predicting it using generated AI. The specific forms for implementing this system are described below.

[0156] First, temperature sensors, humidity sensors, vibration sensors, and illuminance sensors are installed in each area of ​​the factory. These sensors measure environmental data every 10 minutes. The measured data is transmitted to a server via a stable network through a communication module built into each sensor. Data transmission is performed periodically, and a certain amount of buffering is also performed to avoid network instability.

[0157] The server saves received data to a database in real time. The saved data is time-stamped and managed centrally, including historical data. The server retrieves historical environmental data (e.g., the past three months) from the database and provides it to the generating AI. This allows for a comparison between historical and current data.

[0158] The generating AI analyzes and predicts conditions related to production efficiency and quality control, as well as future environmental changes, based on the acquired data. The generating AI generates advice on appropriate production conditions and management methods, and outputs it in text format. For example, if a server acquires temperature, humidity, vibration, and illuminance data for the past three months and provides it to the generating AI, the generating AI might determine that "the temperature is too high and the cooling system needs to be activated" and generate this advice.

[0159] Based on the advice of the generated AI, the server generates specific control commands (e.g., activate the cooling system) and sends them to the corresponding automated equipment. This automatically performs appropriate environmental adjustments. The automated equipment then operates the corresponding control devices (e.g., cooling system, humidification system, vibration damping device, etc.) according to the control commands received from the server.

[0160] Users access the system via smartphones or PCs to check the control results. They verify that the execution was performed correctly and make additional manual adjustments as needed.

[0161] As a concrete example, a server acquires temperature, humidity, vibration, and illuminance data for the past three months and provides it to a generating AI. The AI ​​determines that "the temperature is too high and the cooling system needs to be activated" and generates this advice. Based on the AI's advice, the server generates a command to "activate the cooling system." The terminal (cooling system) receives this command and activates the system. The user checks the cooling results on their smartphone and manually instructs additional cooling if necessary.

[0162] Examples of prompts to input into a generative AI model:

[0163] Generate advice for improving production efficiency based on environmental data (temperature, humidity, vibration, illuminance). Past data is as follows: Temperature: 25°C, Humidity: 60%, Vibration: 1.2, Illuminance: 420. Current data is as follows: Temperature: 28°C, Humidity: 55%, Vibration: 2.0, Illuminance: 460.

[0164] In this way, real-time monitoring and immediate control of environmental data become possible, enabling the optimization of production efficiency and quality control.

[0165] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0166] Step 1:

[0167] The terminal uses sensors placed in various areas of the factory to measure environmental data (temperature, humidity, vibration, illuminance, etc.) every 10 minutes.

[0168] Input: Real-time environmental data obtained from each sensor

[0169] Output: Measured environmental data

[0170] Specific operation: The sensor detects the surrounding environment and generates data as digital information.

[0171] Step 2:

[0172] The terminal transmits the measured data to the server via its built-in communication module.

[0173] Input: Measured environmental data

[0174] Output: Data to send to the server

[0175] Specific operation: The communication module receives the data generated by the sensor and sends it to the server via the network.

[0176] Step 3:

[0177] The server saves the received data to the database in real time.

[0178] Input: Submitted environmental data

[0179] Output: Data stored in the database (with timestamp)

[0180] Specific operation: The server parses the received data and adds a timestamp when saving it to the database system (e.g., MySQL or PostgreSQL).

[0181] Step 4:

[0182] The server retrieves historical environmental data from the database and provides it to the generating AI along with current data.

[0183] Input: Historical and current environmental data

[0184] Output: Data provided to the generating AI

[0185] Specific operation: The server executes a database query to extract historical data, combines it with current data, and passes it to the generating AI.

[0186] Step 5:

[0187] The generating AI analyzes the provided data to determine the conditions for production efficiency and quality control, and then generates advice.

[0188] Input: Historical and current environmental data

[0189] Output: Production advice (text format)

[0190] Specific operation: A generative AI model (e.g., using TENSORFLOW® or PyTorch) analyzes the data and outputs appropriate advice in text format.

[0191] Step 6:

[0192] Based on the advice of the generating AI, the server generates specific control commands and sends them to the corresponding automated equipment.

[0193] Input: AI-generated advice

[0194] Output: Control command

[0195] Specific operation: The server analyzes the advice and generates specific operational instructions (e.g., a command to start the cooling system).

[0196] Step 7:

[0197] The automated equipment performs the corresponding action according to the control commands received from the server.

[0198] Input: Control command

[0199] Output: Actions performed

[0200] Specific operation: Based on the commands received by the automated equipment (e.g., cooling system), it performs physical actions (cooling, humidifying, vibration damping, etc.).

[0201] Step 8:

[0202] Users access the system via smartphones or PCs to check the control results.

[0203] Input: Execution result data

[0204] Output: User confirmation and additional instructions as needed.

[0205] Specific operation: Users monitor the execution results via smartphone or PC applications and make additional manual adjustments if necessary.

[0206] This enables a system where environmental data from each sensor is collected and analyzed on a server in real time, and automated equipment is immediately controlled based on optimal advice generated by AI.

[0207] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0208] This invention relates to a system that measures environmental data in agriculture in real time, analyzes and predicts it using generative AI, generates appropriate cultivation advice and control commands, and automatically executes them. Furthermore, by combining it with an emotion engine that recognizes user emotions, it is an advanced system that includes user emotional feedback. The following describes the configuration for implementing this system.

[0209] (1) Data collection using IoT

[0210] Terminal: Multiple sensors (temperature sensors, humidity sensors, solar radiation sensors, soil moisture sensors, etc.) placed on farms and cultivation facilities measure environmental data for each area in real time every 10 minutes. This ensures that the latest environmental information is always available.

[0211] Terminal: Measured environmental data is transmitted to the server via a communication module built into each sensor, over a stable network. Data transmission is performed periodically, and a certain amount of buffering is also performed to avoid network instability.

[0212] Server: The server saves received data to the database in real time. The saved data is time-stamped and managed centrally, including past data.

[0213] Specific example: At 6:00 AM, a sensor measures temperature (25°C), humidity (60%), sunlight (30,000 lux), and moisture content (20%), and sends this data to the server 10 minutes later. The server stores this data in a database with a timestamp.

[0214] (2) Data analysis and prediction using generative AI

[0215] Server: The server retrieves historical environment data (e.g., the past 3 months) from the database and provides it to the generating AI. This allows for a comparison between historical and current data.

[0216] Server: The generating AI analyzes and predicts plant growing conditions and future environmental changes based on acquired data. The generating AI generates advice on appropriate growing conditions and management methods, and outputs it in text format.

[0217] Specific example: A server retrieves temperature, humidity, sunlight, and moisture content data for the past three months and provides it to a generating AI. The AI ​​determines that "the temperature is appropriate, but the moisture content is low, so 3 liters of watering is necessary" and generates this advice.

[0218] (3) Execution and control based on data prediction using generative AI

[0219] Server: Based on AI advice, it generates specific control commands. For example, it might generate a command to sprinkle 3 liters of water to achieve a moisture content of 30%.

[0220] Server: Sends the generated control commands to the corresponding terminals (watering systems, lighting systems, fertilizer spreaders, etc.).

[0221] Terminal: In accordance with the received control command, the watering system performs the corresponding action, such as spraying 3 liters of water.

[0222] User: Access the system from a smartphone or PC and check the control results. Verify that the execution was performed correctly and make any necessary manual adjustments.

[0223] Specific example: The server generates a control command to "water with 3 liters of water" and sends it to the terminal's watering system. The watering system automatically waters with 3 liters of water, and the user checks the watering results on their smartphone and manually instructs additional watering if necessary.

[0224] (4) Recognition and feedback of user emotions by the emotion engine

[0225] User: Communicates emotional information (e.g., satisfaction, dissatisfaction, questions, etc.) to the system through facial expressions, voice, and input actions during operation.

[0226] Device: Uses cameras, microphones, sensors, etc. to capture the user's emotional state in real time and sends it to the emotion engine for analysis.

[0227] Server: The emotion engine processes this data and analyzes the user's emotional state. For example, if the user is expressing dissatisfaction, the emotion engine detects this and provides appropriate feedback.

[0228] Server: Based on the analysis results from the emotion engine, the generating AI adjusts the content of training advice and control commands. For example, if the user feels that things are not going well, the advice can be made more detailed.

[0229] User: Gain feedback and continue using the system. This improves the user experience and promotes the effective use of the system.

[0230] Specific example: A camera captures a user's dissatisfaction with the watering system's results, and an emotion engine recognizes the user's dissatisfaction. The server then provides more detailed advice for the next watering, resolving the user's dissatisfaction.

[0231] This system enables the real-time acquisition and effective utilization of environmental data, allowing even inexperienced individuals to perform optimal agricultural tasks. Furthermore, by incorporating user emotional feedback, it enables more detailed and personalized support.

[0232] The following describes the processing flow.

[0233] (1) Data collection using IoT

[0234] Step 1:

[0235] Terminals: Various sensors (temperature sensors, humidity sensors, solar radiation sensors, soil moisture sensors, etc.) measure environmental data in each area of ​​the farm or cultivation facility.

[0236] Step 2:

[0237] Terminal: Temporarily stores measured environmental data in internal memory. For example, it records data such as temperature 25°C, humidity 60%, solar radiation 30,000 lux, and moisture content 20%.

[0238] Step 3:

[0239] Terminal: Every 10 minutes, it sends measurement data to the server via a wireless communication module (e.g., Wi-Fi, LoRa).

[0240] Step 4:

[0241] Server: Validates received environmental data and stores it in the database with a timestamp. This ensures data integrity and consistency.

[0242] Specific example: At 6:00 AM, a sensor measures temperature at 25°C, humidity at 60%, solar radiation at 30,000 lux, and moisture content at 20%, and sends this data to a server 10 minutes later. The server then stores this data in a database.

[0243] ---

[0244] (2) Data analysis and prediction using generative AI

[0245] Step 1:

[0246] Server: Retrieves environmental data from the database for a specified period (e.g., the past 3 months). The retrieved data includes temperature, humidity, solar radiation, and moisture content.

[0247] Step 2:

[0248] Server: Inputs acquired historical data and current environmental data into the generating AI and begins analysis.

[0249] Step 3:

[0250] Server: The generating AI analyzes the input data and evaluates the optimal conditions for plant growth. Parameters considered here include appropriate temperature range, water content, and light intensity.

[0251] Step 4:

[0252] Server: Based on the analysis results, the generating AI creates cultivation advice (e.g., "The water level is low, so 3 liters of watering is needed") and outputs it in text format.

[0253] Specific example: A server provides the AI ​​with data from the past three months, and the AI ​​determines that "the temperature is appropriate, but there is insufficient moisture, so watering is necessary," and generates advice that 3 liters of watering are required.

[0254] ---

[0255] (3) Execution and control based on data prediction using generative AI

[0256] Step 1:

[0257] Server: Based on AI advice, it generates specific control commands, such as spraying 3 liters of water to achieve a 30% moisture level.

[0258] Step 2:

[0259] Server: Sends the generated control commands to the corresponding terminals (e.g., watering system, lighting system, fertilizer spreader).

[0260] Step 3:

[0261] Terminal: It performs the corresponding action (e.g., the watering system sprays 3 liters of water) according to the control command received.

[0262] Step 4:

[0263] User: Access the system from a smartphone or PC and check the control results. Make additional manual adjustments as needed.

[0264] Specific example: The server generates a control command to "water with 3 liters of water" and sends it to the terminal's watering system. The watering system automatically waters with 3 liters of water, and the user checks the watering results on their smartphone and manually instructs additional watering if necessary.

[0265] ---

[0266] (4) Recognition and feedback of user emotions by the emotion engine

[0267] Step 1:

[0268] User: Communicates emotional information (e.g., satisfaction, dissatisfaction, questions, etc.) to the system through facial expressions, voice, and input actions during operation.

[0269] Step 2:

[0270] Device: Uses cameras, microphones, sensors, etc. to capture the user's emotional state in real time and transmits it to the emotion engine.

[0271] Step 3:

[0272] Server: The emotion engine processes this data and analyzes the user's emotional state (e.g., joy, anger, surprise, etc.).

[0273] Step 4:

[0274] Server: Based on the analysis results of the emotion engine, the generating AI adjusts the content of training advice and control commands. For example, if the user indicates "dissatisfaction," the server will take measures such as making the training advice more detailed.

[0275] Step 5:

[0276] User: Gain feedback and continue using the system. This improves the user experience and ensures the system is used effectively.

[0277] Specific example: A camera captures a user's dissatisfaction with the watering system's results, and an emotion engine recognizes the user's dissatisfaction. The server then refines the next care advice to address the user's dissatisfaction.

[0278] ---

[0279] In this way, a system that combines an emotion engine enables real-time acquisition and effective utilization of environmental data, allowing even inexperienced individuals to perform optimal agricultural tasks. Furthermore, by incorporating emotional feedback from users, even more advanced support becomes possible.

[0280] (Example 2)

[0281] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0282] Conventional agricultural management systems struggled with real-time environmental data collection and its effective utilization, resulting in insufficient provision of appropriate cultivation advice and adequate automated control. Furthermore, systems lacked the ability to incorporate user emotional feedback, leaving challenges in improving the user experience.

[0283] The specific processing by the specific processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes a device for measuring environmental data, a device for transmitting the measured data to the server via a communication module, a device for the server to store the transmitted data in a database, a device for the server to analyze past data and current data by a generative AI, a device for the server to generate cultivation advice based on the analysis results, a device for generating a control command based on the generated cultivation advice, a device for transmitting the control command to a corresponding control device, a device for the control device to operate according to the control command, a device for the user to confirm the operation result, an emotion engine for recognizing the user's emotion and providing feedback, and a device for the generative AI to adjust advice and control commands based on the analysis results of the emotion engine. Thereby, real-time environmental data collection and analysis, provision of appropriate cultivation advice, automatic control are enabled, and advanced support reflecting the user's emotion feedback is realized.

[0284] "Environmental data" refers to data representing the environmental conditions of agriculture and cultivation facilities, such as temperature, humidity, solar radiation amount, soil moisture amount, etc.

[0285] "Measurement device" refers to a device for measuring environmental data in real time, such as a temperature sensor, a humidity sensor, a solar radiation amount sensor, a soil moisture sensor, etc.

[0286] "Communication module" refers to a device that provides communication means for transmitting data from a measurement device to a server.

[0287] "Server" refers to a computer system for storing, managing, and analyzing received environmental data.

[0288] "Database" refers to a system for storing measured data with timestamps and managing it uniformly with past data.

[0289] "Generative AI" is an artificial intelligence system that analyzes measured data and historical data to predict and suggest plant growth conditions and management methods.

[0290] "Cultivation advice" refers to instructions on the optimal growing conditions and management methods for plants, generated by the AI ​​based on its analysis results.

[0291] A "control command" is a command that includes specific work instructions, generated based on the training advice for the generated AI.

[0292] A "control device" is a device that performs a specific action according to a control command, such as a watering system, lighting system, or fertilizer spreader.

[0293] An "emotion engine" is a system that analyzes the user's facial expressions, voice, and input actions during operation to recognize their emotional state and provide feedback.

[0294] A "user" is an agricultural worker or system user who operates the system, checks the control results, and makes manual adjustments as needed.

[0295] This invention is a system that measures environmental data in agriculture in real time, analyzes and predicts it using a generation AI, generates appropriate cultivation advice and control commands, and automatically executes them. Furthermore, by combining it with an emotion engine that recognizes the user's emotions, it is a system that provides advanced support that reflects the user's emotional feedback.

[0296] (1) Data collection using IoT

[0297] Terminals: Temperature sensors, humidity sensors, solar radiation sensors, soil moisture sensors, and other devices placed on farms and cultivation facilities measure environmental data in real time. These sensors measure data every 10 minutes and transmit it to the server via a communication module built into each sensor. Buffering is performed during transmission to maintain network stability.

[0298] Server: The server stores the received data in a database. The stored data is time-stamped and centrally managed with past data. For example, at 6 AM, the temperature sensor measures 25°C, the humidity sensor measures 60%, the solar radiation sensor measures 30,000 lux, and the soil moisture sensor measures 20%, and these data are sent to the server every 10 minutes. The server stores this data in the database with timestamps.

[0299] (2) Data analysis and prediction using generative AI

[0300] Server: The server retrieves historical environmental data (e.g., the past 3 months) from the database and provides it to the generating AI. The generating AI compares and analyzes the historical and current data to predict plant growing conditions and future environmental changes. Based on the analysis results, the generating AI generates cultivation advice in text format.

[0301] Specific example: A server retrieves temperature, humidity, sunlight, and moisture content data for the past three months and provides it to the generating AI. The AI ​​determines that "the temperature is appropriate, but the moisture content is low, so 3 liters of watering is necessary" and generates this advice.

[0302] (3) Execution and control based on data prediction using generative AI

[0303] Server: Based on the advice of the generating AI, it generates specific control commands. For example, it generates a command such as "Water with 3 liters of water to bring the moisture level to 30%."

[0304] Server: Sends the generated control commands to the corresponding control devices (e.g., watering systems, lighting systems, fertilizer spreaders).

[0305] Terminal: A control device operates according to the control commands it receives and performs the instructed task. For example, a watering system automatically sprays 3 liters of water.

[0306] User: Access the system from a smartphone or PC and check the control results. Check whether the execution results are accurate and make additional manual adjustments if necessary. The server generates a control command such as "Spray 3 liters of water" and sends it to the sprinkler system of the terminal. The sprinkler system automatically sprays 3 liters of water, and the user checks the results on the smartphone and instructs additional spraying manually if necessary.

[0307] (4) Recognition and Feedback of User Emotions by the Emotion Engine

[0308] User: Convey emotional information (e.g., satisfaction, dissatisfaction, doubt) to the system through expressions, voices, and input actions during operation.

[0309] Terminal: Use a camera, microphone, and sensors to capture the user's emotional state in real time and send it to the emotion engine for analysis.

[0310] Server: The emotion engine processes these data and analyzes the user's emotional state. If the user shows dissatisfaction, the emotion engine senses this and provides appropriate feedback.

[0311] Server: Based on the analysis results of the emotion engine, the AI generated adjusts the content of the cultivation advice and control commands. For example, when the user feels that things are not going well, the content of the advice can be made more detailed.

[0312] User: By receiving feedback and continuing to operate the system, the user experience is improved and the effective use of the system is promoted. The camera captures the user's dissatisfaction with the results of the sprinkler system, and the emotion engine recognizes the emotion of dissatisfaction. The server provides more detailed cultivation advice next time to eliminate the user's dissatisfaction.

[0313] Examples of Prompt Sentences

[0314] "Please analyze the optimal growing conditions based on temperature, humidity, sunlight, and moisture content data from the past three months."

[0315] "If users express dissatisfaction, please provide detailed training advice for the next session."

[0316] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0317] The program's processing flow is explained in detail, broken down into steps.

[0318] Step 1:

[0319] (Data collection)

[0320] Terminal: Sensors (temperature sensors, humidity sensors, solar radiation sensors, soil moisture sensors, etc.) placed on farms and cultivation facilities measure various environmental data every 10 minutes. The input is the environmental parameters measured by the sensors (e.g., temperature, humidity, solar radiation, moisture content), and the output is the measured environmental data. This data is transmitted to the server via the terminal's communication module.

[0321] Specific operation: At 6:00 AM, the temperature sensor measures 25°C, the humidity sensor measures 60%, the solar radiation sensor measures 30,000 lux, and the soil moisture sensor measures 20%. This data is sent to the server every 10 minutes.

[0322] Step 2:

[0323] (Data saving)

[0324] Server: Receives environmental data and stores it in a database. Input is measurement data sent from the terminal, and output is environmental data stored in the database. The data is timestamped, and past data is managed centrally.

[0325] Specific operation: After measurement data arrives at the server, the server adds a timestamp and saves it to the database. For example, a timestamp is added to data received every 10 minutes and recorded in the database.

[0326] Step 3:

[0327] (Data analysis and prediction)

[0328] Server: Retrieves environmental data for the past three months from the database and provides it to the generating AI. The input is environmental data for the past three months, and the output is the analysis results and cultivation advice from the generating AI. The generating AI compares and analyzes past and current data to predict plant cultivation conditions and environmental changes.

[0329] Specific operation: The server provides the generating AI with temperature, humidity, solar radiation, and moisture content data for the past three months. Based on this data, the generating AI creates cultivation advice such as, "The temperature is appropriate, but the moisture content is low, so 3 liters of watering is needed."

[0330] Step 4:

[0331] (Generating control commands)

[0332] Server: Generates specific control commands based on advice from the generating AI. The input is advice from the generating AI, and the output is a specific control command. For example, it generates a command such as "Water with 3 liters of water to bring the moisture level to 30%."

[0333] Specific operation: Based on the advice of the generating AI, the server generates a control command to "spray 3 liters of water" and sends it to the corresponding control device (watering system).

[0334] Step 5:

[0335] (Execution of control commands)

[0336] Terminal: A control device receives control commands from the server and performs actions according to the instructions. The input is the control command sent from the server, and the output is the actual action (e.g., watering, adjusting lighting, spreading fertilizer).

[0337] Specific operation: The terminal's watering system receives a command to "water with 3 liters" and automatically waters with 3 liters of water as instructed.

[0338] Step 6:

[0339] (Checking the results)

[0340] User: Access the system from a smartphone or PC and check the execution results. Input is the operation result of the control device, and output is the execution result displayed to the user. Additional manual adjustments can be made as needed.

[0341] Specific operation: The user checks the watering results on their smartphone and manually instructs additional watering if necessary.

[0342] Step 7:

[0343] (Emotion recognition and feedback)

[0344] User: Provides emotional information through facial expressions, voice, and input actions during operation. Input is the user's emotional information, and output is data sent to the emotion engine.

[0345] Device: Uses cameras, microphones, and sensors to capture the user's emotional state and sends it to the emotion engine.

[0346] Specific operation: The camera captures the user's facial expressions, the microphone collects audio, and these are sent to the emotion engine.

[0347] Step 8:

[0348] (Emotional analysis and adjustment of advice)

[0349] Server: The emotion engine analyzes the user's emotional state and provides information to the generating AI. The generating AI adjusts the content of advice and control commands based on the analysis results. The input is the user's emotional information and the aforementioned data, and the output is the adjusted advice and control commands.

[0350] Specific operation: The emotion engine recognizes that the user is not satisfied with the results of the watering system, and the server provides more detailed advice for the next cultivation.

[0351] (Application Example 2)

[0352] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as a "server" and the smart device 14 as a "terminal".

[0353] Environmental management in modern agriculture and factories is an extremely complex and labor-intensive task, requiring efficient and accurate responses. However, current systems struggle with real-time, appropriate control because the collection, analysis, and control of environmental data are fragmented. Furthermore, there is no mechanism to acquire and incorporate user emotional feedback into the system, resulting in a lack of improvement in the user experience. To solve these problems, it is essential to manage environmental data in real time, generate appropriate advice and control commands using generative AI, and incorporate user emotional data into the system.

[0354] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0355] In this invention, the server includes means for measuring environmental data, means for transmitting the measured data to the server, means for the server to store the transmitted data in a database, means for the server to analyze past and present data using a generating AI, means for the server to generate training advice based on the analysis results, means for generating control commands based on the generated training advice, means for transmitting the control commands to a corresponding control device, means for the control device to operate according to the control commands, means for the user to confirm the operation results, means for collecting emotional data, means for recognizing the user's emotions based on the emotional data, and means for adjusting the training advice and control commands based on the recognized emotions. This enables real-time management of environmental data and improvement of the user experience.

[0356] "Environmental data" refers to information about the environment in agriculture and factories, such as temperature, humidity, solar radiation, and soil moisture.

[0357] A "server" is a computer system that receives and stores measured environmental data and uses generated AI to analyze and predict the data.

[0358] A "database" is a data storage system for efficiently saving and managing measured environmental data and historical data.

[0359] "Generative AI" is artificial intelligence that analyzes collected data and generates training advice and control commands based on the analysis results.

[0360] A "control command" is an instruction created by the generating AI and sent to the corresponding control device, which then performs a specific action.

[0361] A "control device" is a device or equipment that takes specific actions based on control commands sent from a server.

[0362] "Emotional data" refers to information about emotions obtained through facial expressions, voice, input actions, etc., acquired during user interaction.

[0363] An "emotion engine" is an artificial intelligence system that analyzes emotional data and recognizes the user's current emotional state.

[0364] "Cultivation advice" refers to suggestions regarding the optimal cultivation conditions and management methods for plants and other objects, derived from the results of analysis and predictions performed by the generating AI based on environmental data.

[0365] This invention relates to a system that measures environmental data in a factory in real time, analyzes and predicts it using generative AI, generates appropriate management advice and control commands, and automatically executes them. Furthermore, by incorporating an emotion engine that recognizes user emotions, it is an advanced system that includes user emotional feedback. The following describes the configurations for implementing this system.

[0366] (1) Collection of environmental data

[0367] Terminal: Multiple sensors (temperature sensors, humidity sensors, machine operation status sensors, etc.) placed throughout the factory measure environmental data in each area in real time every 10 minutes. This ensures that the latest environmental information is always available.

[0368] Terminal: Measured environmental data is transmitted to the server via a communication module built into each sensor, over a stable network. Data transmission is performed periodically, and a certain amount of buffering is also performed to avoid network instability.

[0369] Server: The server saves received data to the database in real time. The saved data is time-stamped and managed centrally, including past data.

[0370] Specific example: At 6:00 AM, a sensor measures temperature (25°C), humidity (60%), and machine status (normal), and sends this data to the server 10 minutes later. The server stores this data in a database with a timestamp.

[0371] (2) Data analysis and prediction using generative AI

[0372] Server: The server retrieves historical environment data (e.g., the past 3 months) from the database and provides it to the generating AI. This allows for a comparison between historical and current data.

[0373] Server: The generating AI analyzes and predicts optimal operating conditions and future environmental changes within the factory based on acquired data. The generating AI generates advice on appropriate management conditions and control methods, and outputs it in text format.

[0374] Specific example: A server retrieves data on temperature, humidity, and machine operating status for the past three months and provides it to a generating AI. The AI ​​determines that "the temperature is appropriate, but the humidity is low, so the humidifier needs to be turned on," and generates this advice.

[0375] (3) Execution and control based on data prediction using generative AI

[0376] Server: Based on AI advice, it generates specific control commands. For example, it generates a command to activate a humidifier to set the humidity to 50%.

[0377] Server: Sends the generated control commands to the corresponding control devices (humidifiers, air conditioning systems, inspection robots, etc.).

[0378] Terminal: It performs the corresponding action, such as activating a humidifier, according to the control command it receives.

[0379] User: Access the system from a smartphone or computer and check the control results. Verify that the execution was performed correctly and make any necessary manual adjustments.

[0380] Specific example: The server generates a control command to "start the humidifier" and sends it to the humidifier on the terminal. The humidifier operates automatically, and the user checks the operation results on their smartphone and manually instructs it to operate additionally if necessary.

[0381] (4) Recognition and feedback of user emotions by the emotion engine

[0382] User: Communicates emotional information (e.g., satisfaction, dissatisfaction, questions, etc.) to the system through facial expressions, voice, and input actions during operation.

[0383] Device: Uses cameras, microphones, sensors, etc. to capture the user's emotional state in real time and sends it to the emotion engine for analysis.

[0384] Server: The emotion engine processes this data and analyzes the user's emotional state. For example, if the user is expressing dissatisfaction, the emotion engine detects this and provides appropriate feedback.

[0385] Server: Based on the analysis results from the emotion engine, the generating AI adjusts the content of management advice and control commands. For example, if the user feels that things are not going well, the advice can be made more detailed.

[0386] User: Gain feedback and continue using the system. This improves the user experience and promotes the effective use of the system.

[0387] Specific example: A camera captures a user's dissatisfaction with the humidifier's performance, and an emotion engine recognizes the user's dissatisfaction. The server then provides more detailed management advice for the next time, resolving the user's dissatisfaction.

[0388] Example prompt statements

[0389] Over the past three months, the average temperature was 25°C, the average humidity was 50%, and the machine operated normally 90 out of 100 times, with abnormalities detected 5 times. Based on this, we propose future management methods.

[0390] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0391] Step 1: Collect environmental data

[0392] Input: Data from temperature sensors, humidity sensors, and machine operating status sensors.

[0393] Operation: The terminal uses sensors placed throughout the factory to measure temperature, humidity, and machine operating status data in real time.

[0394] Data processing: The measured data is buffered through a communication module built into each sensor.

[0395] Output: A set of measured environmental data (e.g., temperature 25°C, humidity 60%, machine condition normal).

[0396] Step 2: Send

[0397] Input: Environmental data measured from sensors.

[0398] Operation: The device sends data obtained from the sensor to the server every 10 minutes.

[0399] Data processing: Data is transmitted over the network after a timestamp is added.

[0400] Output: Environment data with a timestamp is sent to the server.

[0401] Step 3: Save data

[0402] Input: Submitted environmental data.

[0403] Operation: The server saves the received data to the database.

[0404] Data processing: The server centrally manages the database, including historical data.

[0405] Output: Timestamped environment data stored in the database.

[0406] Step 4: Data Analysis and Prediction

[0407] Input: Past and present environment data stored in the database.

[0408] Operation: The server retrieves data from the database for the past three months and provides it to the generating AI.

[0409] Data processing: Generative AI compares and analyzes historical and current data to predict optimal management conditions and future environmental changes.

[0410] Output: Advice text (e.g., "The temperature is appropriate, but the humidity is low, so you need to run the humidifier.").

[0411] Step 5: Generating control commands

[0412] Input: Advice from the generating AI.

[0413] Operation: The server generates specific control commands based on advice from the generating AI.

[0414] Data calculation: Based on the advice provided, generate commands to operate the target device (e.g., humidifier).

[0415] Output: Control command (e.g., "Start the humidifier").

[0416] Step 6: Sending control commands

[0417] Input: Generated control command.

[0418] Operation: The server sends the generated control commands to the corresponding control unit.

[0419] Data processing: Send commands to the corresponding terminal via the network.

[0420] Output: Control commands received by the control device.

[0421] Step 7: Operation of the control unit

[0422] Input: Received control command.

[0423] Operation: The terminal allows the corresponding device (e.g., humidifier) ​​to perform actions according to the control commands it receives.

[0424] Data calculation: Adjusts the target environment (e.g., humidity) based on the command content.

[0425] Output: The result of the executed command (e.g., the humidifier is running).

[0426] Step 8: Check the results

[0427] Input: The result of the operation performed by the control device.

[0428] Operation: Users access the system via smartphone or PC to check the operation results of the control unit.

[0429] Data calculation: Evaluate the execution results and make additional manual adjustments as needed.

[0430] Output: User's operational verification results (e.g., checking the humidifier's operating status on a smartphone).

[0431] Step 9: Collecting emotional data

[0432] Input: User's facial expressions, voice, and input actions during operation.

[0433] Operation: The device captures the user's emotional state through the camera and microphone and sends it to the emotion engine for analysis.

[0434] Data processing: Captured emotion data is transmitted in real time.

[0435] Output: A set of emotion data (e.g., emotion of dissatisfaction).

[0436] Step 10: Emotion Recognition and Feedback

[0437] Input: Sentiment data.

[0438] Operation: The server analyzes the user's emotional state using an emotion engine.

[0439] Data processing: Based on recognized emotions, the generating AI adjusts the content of training advice and control commands.

[0440] Output: Adjusted advice or commands (e.g., make the next advice more detailed).

[0441] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0442] Data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search)<url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0443] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart device 14.

[0444] [Second Embodiment]

[0445] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0446] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0447] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0448] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0449] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0450] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0451] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0452] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0453] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0454] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0455] In the smart glasses 214, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0456] Next, the identification processing performed by the identification processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0457] This invention relates to a system that measures environmental data in agriculture in real time, analyzes and predicts it using AI, generates appropriate cultivation advice and control commands, and automatically executes them. The following describes the embodiments for implementing this system.

[0458] (1) Data collection using IoT

[0459] Terminal: Multiple sensors (temperature sensors, humidity sensors, solar radiation sensors, soil moisture sensors, etc.) placed on farms and cultivation facilities measure environmental data for each area in real time every 10 minutes. This ensures that the latest environmental information is always available.

[0460] Terminal: Measured environmental data is transmitted to the server via a communication module built into each sensor, over a stable network. Data transmission is performed periodically, and a certain amount of buffering is also performed to avoid network instability.

[0461] Server: The server saves received data to the database in real time. The saved data is time-stamped and managed centrally, including past data.

[0462] Specific example: At 6:00 AM, a device (sensor) measures temperature (25°C), humidity (60%), sunlight (30,000 lux), and moisture content (20%), and sends this data to the server 10 minutes later. The server stores this data in a database with a timestamp.

[0463] (2) Data analysis and prediction using generative AI

[0464] Server: The server retrieves historical environment data (e.g., the past 3 months) from the database and provides it to the generating AI. This allows for a comparison between historical and current data.

[0465] Server: The generating AI analyzes and predicts plant growing conditions and future environmental changes based on acquired data. The generating AI generates advice on appropriate growing conditions and management methods, and outputs it in text format.

[0466] Specific example: A server retrieves temperature, humidity, sunlight, and moisture content data for the past three months and provides it to a generating AI. The AI ​​determines that "the temperature is appropriate, but the moisture content is low, so 3 liters of watering is necessary" and generates this advice.

[0467] (3) Execution and control based on data prediction using generative AI

[0468] Server: Based on advice from the generating AI, it generates specific control commands (e.g., activate the watering system) and sends them to the corresponding terminal. This automatically performs appropriate environmental adjustments.

[0469] Terminal: The terminal operates the corresponding control device (e.g., watering system, lighting system, fertilizer spreader, etc.) according to the control commands received from the server.

[0470] User: Users access the system via smartphone or PC to check the control results. They verify that the execution was performed correctly and make additional manual adjustments as needed.

[0471] Specific example: Based on the advice of the AI, the server generates a command that says, "To achieve a moisture content of 30%, water with 3 liters of water." The terminal (watering system) receives this command and waters with 3 liters of water. The user checks the watering results on their smartphone and manually instructs the system to water additionally if necessary.

[0472] This system enables the real-time acquisition and effective utilization of environmental data, allowing even inexperienced individuals to perform optimal agricultural tasks.

[0473] The following describes the processing flow.

[0474] (1) Data collection using IoT

[0475] Step 1:

[0476] Terminals: Various sensors, such as temperature sensors, humidity sensors, solar radiation sensors, and soil moisture sensors, measure environmental data in each area.

[0477] Step 2:

[0478] Terminal: Temporarily stores measured environmental data in internal memory. For example, it records data such as temperature 25°C, humidity 60%, solar radiation 30,000 lux, and moisture content 20%.

[0479] Step 3:

[0480] Terminal: At regular intervals (e.g., every 10 minutes), it transmits measurement data to the server via a wireless communication module. Communication methods include Wi-Fi and LoRa.

[0481] Step 4:

[0482] Server: Validates received environmental data and stores it in the database with a timestamp. This ensures data integrity and consistency.

[0483] Specific example: At 6:00 AM, a sensor measures data showing a temperature of 25°C, humidity of 60%, solar radiation of 30,000 lux, and moisture content of 20%, and sends this data to the server at 6:10 AM. The server then stores this data in its database.

[0484] ---

[0485] (2) Data analysis and prediction using generative AI

[0486] Step 1:

[0487] Server: Retrieves environmental data from the database for a specified period (e.g., the past 3 months). The retrieved data includes temperature, humidity, solar radiation, and moisture content.

[0488] Step 2:

[0489] Server: Inputs acquired historical data and current environmental data into the generating AI and begins analysis.

[0490] Step 3:

[0491] Server: The generating AI analyzes the input data and evaluates the optimal conditions for plant growth. Parameters considered here include appropriate temperature range, water content, and light intensity.

[0492] Step 4:

[0493] Server: Based on the analysis results, the generating AI creates cultivation advice (e.g., "The water level is low, so 3 liters of watering is needed") and outputs it in text format.

[0494] Specific example: A server provides data from the past three months to an AI, which determines that "the temperature is appropriate, but there is insufficient moisture. Watering is necessary," and generates advice that 3 liters of watering are required.

[0495] ---

[0496] (3) Execution and control based on data prediction using generative AI

[0497] Step 1:

[0498] Server: Based on AI advice, it generates specific control commands. For example, it might generate a command to sprinkle 3 liters of water to achieve a moisture content of 30%.

[0499] Step 2:

[0500] Server: Sends the generated control commands to the corresponding terminals (watering systems, lighting systems, fertilizer spreaders, etc.).

[0501] Step 3:

[0502] Terminal: In accordance with the received control command, the watering system performs the corresponding action, such as spraying 3 liters of water.

[0503] Step 4:

[0504] User: Access the system from a smartphone or PC and check the control results. Make additional manual adjustments as needed.

[0505] Specific example: The server generates a control command to "water with 3 liters of water" and sends it to the terminal's watering system. The watering system automatically waters with 3 liters of water, and the user checks the watering results on their smartphone and manually instructs additional watering if necessary.

[0506] ---

[0507] This is a detailed explanation of the specific operations at each processing step of the system.

[0508] (Example 1)

[0509] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0510] The challenge lies in creating a system that collects, analyzes, and predicts environmental data in agriculture in real time, providing optimal growing conditions for plants. This will enable the provision of cultivation methods based on highly accurate information that could not be obtained with conventional methods. It is also necessary to address data transfer problems caused by network instability and reduce the burden of manual work performed by users.

[0511] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0512] In this invention, the server includes a device for measuring environmental data, a device for transmitting the measured data to the server, a device for the server to store the transmitted data in a database, a device for the server to analyze past and present data using a generating AI, a device for the server to generate cultivation advice based on the analysis results, a device for generating control commands based on the generated cultivation advice, a device for transmitting the generated control commands to a corresponding control device, a device for the control device to operate according to the control commands, and a device for the user to confirm the operation results. This enables real-time data collection, analysis, and prediction in agriculture, allowing for the provision of optimal plant growing conditions and appropriate environmental adjustments.

[0513] "Environmental data" refers to numerical data that indicates the state of the surrounding environment in agriculture, such as temperature, humidity, solar radiation, and soil moisture content.

[0514] "Measuring devices" refer to sensors and measuring instruments used to collect environmental data.

[0515] "Transmitting device" refers to a communication device used to transfer measured environmental data to a server.

[0516] A "database" is a storage device that centrally manages information stored on a server and allows for searching and analysis as needed.

[0517] "Generative AI" refers to artificial intelligence that analyzes and predicts based on collected data, and then suggests optimal breeding conditions and management methods.

[0518] "Cultivation advice" refers to information provided in text format by a generating AI based on its analysis results, outlining the optimal growing conditions and management methods for plants.

[0519] A "control command" is an instruction sent to each control device based on the advice of the generated AI, providing specific operational instructions.

[0520] A "control device" refers to equipment or systems used to adjust the agricultural environment according to control commands received from a server.

[0521] A "device for checking operation results" refers to an interface device used by the user to check the execution results of the system and perform additional operations as needed.

[0522] "Buffering" is the process of temporarily storing data to avoid network instability and sending it when stable communication becomes possible.

[0523] SQL queries are structured query languages ​​used to retrieve specific information from databases.

[0524] This invention is a system that measures environmental data in agriculture in real time, analyzes and predicts the data using AI generation, generates appropriate cultivation advice and control commands, and automatically executes them. A specific embodiment of this system is described below.

[0525] (1) Data collection using IoT

[0526] Terminal: Multiple sensors (temperature sensors, humidity sensors, solar radiation sensors, soil moisture sensors) placed on farms and cultivation facilities measure environmental data for each area every 10 minutes. This ensures that the latest environmental information is always available.

[0527] Terminal: Measured environmental data is transmitted to the server via a communication module (e.g., LoRaWAN module) built into each sensor, over a stable network (e.g., Wi-Fi, 5G). Data transmission is performed periodically, and a certain amount of buffering is also performed to avoid network instability.

[0528] Server: The server saves received data in real time to a database (e.g., MySQL, PostgreSQL). The saved data is time-stamped and managed centrally, including past data.

[0529] Specific example: At 6:00 AM, a device (sensor) measures temperature (25°C), humidity (60%), sunlight (30,000 lux), and moisture content (20%), and sends this data to the server 10 minutes later. The server stores this data in a database with a timestamp.

[0530] (2) Data analysis and prediction using generative AI

[0531] Server: The server retrieves historical environment data (e.g., the past 3 months) from the database and provides it to the generating AI (e.g., GPT-4). This allows for a comparison between historical and current data.

[0532] Server: Based on data acquired by the generating AI, it analyzes and predicts plant growing conditions and future environmental changes. The generating AI generates advice on appropriate growing conditions and management methods, and outputs it in text format.

[0533] Specific example: A server retrieves temperature, humidity, sunlight, and moisture content data for the past three months and provides it to a generating AI. The AI ​​determines that "the temperature is appropriate, but the moisture content is low, so 3 liters of watering is necessary" and generates this advice.

[0534] (3) Execution and control based on data prediction using generative AI

[0535] Server: Based on advice from the generating AI, it generates specific control commands (e.g., activate the watering system) and sends them to the corresponding terminal. This automatically performs appropriate environmental adjustments.

[0536] Terminal: The terminal operates the corresponding control device (e.g., watering system, lighting system, fertilizer spreader, etc.) according to the control commands received from the server.

[0537] User: Users access the system via smartphone or PC to check the control results. They verify that the execution was performed correctly and make additional manual adjustments as needed.

[0538] Specific example: Based on the advice of the AI, the server generates a command that says, "To achieve a moisture content of 30%, water with 3 liters of water." The terminal (watering system) receives this command and waters with 3 liters of water. The user checks the watering results on their smartphone and manually instructs the system to water additionally if necessary.

[0539] Specific examples of input prompt sentences for generative AI models

[0540] Prompt: "Based on environmental data from the past three months, please advise on the current plant growing conditions. The data is as follows: Temperature (20°C, 22°C, 25°C), Humidity (50%, 55%, 60%), Sunlight (25,000 lux, 27,000 lux, 30,000 lux), Soil moisture (15%, 18%, 20%)."

[0541] This system enables the real-time acquisition and effective utilization of environmental data, allowing even inexperienced individuals to perform optimal agricultural work.

[0542] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0543] Step 1: Measuring environmental data

[0544] Terminal: Multiple sensors (temperature sensors, humidity sensors, solar radiation sensors, soil moisture sensors) placed in the farm or cultivation facility measure environmental data for each area every 10 minutes. Specifically, the temperature sensor measures the current temperature as 25°C and stores this value in internal memory. This measurement data serves as input.

[0545] Step 2: Send

[0546] Terminal: Measured environmental data is transmitted to the server via a stable network (e.g., Wi-Fi, 5G) using a communication module (e.g., LoRaWAN module) built into each sensor. Data transmission occurs every 10 minutes, with a certain amount of buffering to avoid network instability. Specifically, the sensor measures temperature (25°C), humidity (60%), solar radiation (30,000 lux), and moisture content (20%), combines this data into a single packet, and sends it to the server. This transmitted data becomes the output.

[0547] Step 3: Receiving and saving data

[0548] Server: The server saves received data in real time to a database (e.g., MySQL, PostgreSQL). Saved data is timestamped, and past data is centrally managed. Specifically, the server saves received data using the "Insert into Database" command. This data is the input, and the saved data is the output.

[0549] Step 4: Obtaining historical data

[0550] Server: The server retrieves historical environment data (e.g., the past 3 months) from the database using SQL queries and provides it to the generating AI (e.g., GPT-4). Specifically, the server executes the SQL query "SELECT FROM environmentdata WHERE date > current date - INTERVAL 3 MONTH", formats the retrieved data, and inputs it into the generating AI. This retrieved data is the input.

[0551] Step 5: Data analysis and advice generation

[0552] Server: Based on data acquired by the generating AI, the server analyzes and predicts plant growing conditions and future environmental changes. The generating AI generates advice on appropriate growing conditions and management methods and returns it to the server in text format. Specifically, if the generating AI determines that "the temperature is appropriate, but the moisture level is low, so 3 liters of watering is necessary," it generates this advice. This analyzed data is the input, and the generated advice is the output.

[0553] Step 6: Generating control commands

[0554] Server: Based on advice from the generating AI, the server generates specific control commands (e.g., activating a watering system) and sends them to the corresponding terminal. Specifically, the server analyzes the advice from the generating AI and generates a command, "Water with 3 liters of water to bring the moisture level to 30%", and sends it to the terminal. This advice is the input, and the generated command is the output.

[0555] Step 7: Execute control commands

[0556] Terminal: The terminal operates the corresponding control device (e.g., watering system, lighting system, fertilizer spreader, etc.) according to the control commands received from the server. Specifically, the terminal (watering system) receives a command and activates its internal mechanism to spray 3 liters of water. This control command is the input, and the operation result of each device is the output.

[0557] Step 8: Check the execution results

[0558] User: The user accesses the system via smartphone or PC and checks the control results. Specifically, the user checks the system status on their smartphone to confirm whether watering was performed as scheduled. If necessary, they send a "manual additional watering" command to their terminal. The system's operation results are the input, and the user's confirmation and manual instructions are the output.

[0559] (Application Example 1)

[0560] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0561] Traditional factory production management and environmental control often involve manual processes, leading to inefficiencies and a lack of optimization. Furthermore, real-time monitoring of multiple environmental factors (temperature, humidity, vibration, etc.) and immediate control based on that information are difficult, potentially resulting in problems with production efficiency and quality control. Therefore, the challenge lies in providing new methods to improve production efficiency and optimize quality control.

[0562] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0563] In this invention, the server includes means for measuring environmental data, means for transmitting the measured data to the server, means for the server to store the transmitted data in a database, means for the server to analyze past and present data using a generating AI, means for the server to generate production advice based on the analysis results, means for generating control commands based on the generated production advice, means for transmitting the control commands to a corresponding automated device, means for the automated device to operate according to the control commands, and means for the user to confirm the operation results. This enables real-time monitoring and immediate control of environmental data, making it possible to optimize production efficiency and quality control.

[0564] "Environmental data" refers to data that measures information about the working environment in a factory in real time, such as temperature, humidity, vibration, and illuminance.

[0565] A "server" is a device or system that receives measured environmental data, stores it in a database, and performs analysis and prediction using generating AI.

[0566] A "database" is a digital storage system in which environmental data sent to a server is stored with timestamps and centrally managed.

[0567] "Generative AI" refers to artificial intelligence that performs analysis and prediction based on past and current environmental data, and is used to generate production advice and control commands.

[0568] "Production advice" refers to the process where the generating AI analyzes environmental data and provides specific advice in text format to optimize production efficiency and quality control.

[0569] A "control command" is an instruction sent to automated equipment based on generated production advice, and it is an executable command to adjust the environment and work content.

[0570] "Automated equipment" refers to mechanical devices and robots that operate according to control commands, and is used for environmental adjustment and production work within factories.

[0571] A "user" is a person who accesses the system to check its operation results and make additional adjustments as needed.

[0572] This invention is a system that improves production efficiency and quality control by measuring environmental data within a factory in real time and analyzing and predicting it using generated AI. The specific forms for implementing this system are described below.

[0573] First, temperature sensors, humidity sensors, vibration sensors, and illuminance sensors are installed in each area of ​​the factory. These sensors measure environmental data every 10 minutes. The measured data is transmitted to a server via a stable network through a communication module built into each sensor. Data transmission is performed periodically, and a certain amount of buffering is also performed to avoid network instability.

[0574] The server saves received data to a database in real time. The saved data is time-stamped and managed centrally, including historical data. The server retrieves historical environmental data (e.g., the past three months) from the database and provides it to the generating AI. This allows for a comparison between historical and current data.

[0575] The generating AI analyzes and predicts conditions related to production efficiency and quality control, as well as future environmental changes, based on the acquired data. The generating AI generates advice on appropriate production conditions and management methods, and outputs it in text format. For example, if a server acquires temperature, humidity, vibration, and illuminance data for the past three months and provides it to the generating AI, the generating AI might determine that "the temperature is too high and the cooling system needs to be activated" and generate this advice.

[0576] Based on the advice of the generated AI, the server generates specific control commands (e.g., activate the cooling system) and sends them to the corresponding automated equipment. This automatically performs appropriate environmental adjustments. The automated equipment then operates the corresponding control devices (e.g., cooling system, humidification system, vibration damping device, etc.) according to the control commands received from the server.

[0577] Users access the system via smartphones or PCs to check the control results. They verify that the execution was performed correctly and make additional manual adjustments as needed.

[0578] As a concrete example, a server acquires temperature, humidity, vibration, and illuminance data for the past three months and provides it to a generating AI. The AI ​​determines that "the temperature is too high and the cooling system needs to be activated" and generates this advice. Based on the AI's advice, the server generates a command to "activate the cooling system." The terminal (cooling system) receives this command and activates the system. The user checks the cooling results on their smartphone and manually instructs additional cooling if necessary.

[0579] Examples of prompts to input into a generative AI model:

[0580] Generate advice for improving production efficiency based on environmental data (temperature, humidity, vibration, illuminance). Past data is as follows: Temperature: 25°C, Humidity: 60%, Vibration: 1.2, Illuminance: 420. Current data is as follows: Temperature: 28°C, Humidity: 55%, Vibration: 2.0, Illuminance: 460.

[0581] In this way, real-time monitoring and immediate control of environmental data become possible, enabling the optimization of production efficiency and quality control.

[0582] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0583] Step 1:

[0584] The terminal uses sensors placed in various areas of the factory to measure environmental data (temperature, humidity, vibration, illuminance, etc.) every 10 minutes.

[0585] Input: Real-time environmental data obtained from each sensor

[0586] Output: Measured environmental data

[0587] Specific operation: The sensor detects the surrounding environment and generates data as digital information.

[0588] Step 2:

[0589] The terminal transmits the measured data to the server via its built-in communication module.

[0590] Input: Measured environmental data

[0591] Output: Data to send to the server

[0592] Specific operation: The communication module receives the data generated by the sensor and sends it to the server via the network.

[0593] Step 3:

[0594] The server saves the received data to the database in real time.

[0595] Input: Submitted environmental data

[0596] Output: Data stored in the database (with timestamp)

[0597] Specific operation: The server parses the received data and adds a timestamp when saving it to the database system (e.g., MySQL or PostgreSQL).

[0598] Step 4:

[0599] The server retrieves historical environmental data from the database and provides it to the generating AI along with current data.

[0600] Input: Historical and current environmental data

[0601] Output: Data provided to the generating AI

[0602] Specific operation: The server executes a database query to extract historical data, combines it with current data, and passes it to the generating AI.

[0603] Step 5:

[0604] The generating AI analyzes the provided data to determine the conditions for production efficiency and quality control, and then generates advice.

[0605] Input: Historical and current environmental data

[0606] Output: Production advice (text format)

[0607] Specific operation: A generative AI model (e.g., using TensorFlow or PyTorch) analyzes the data and outputs appropriate advice in text format.

[0608] Step 6:

[0609] Based on the advice of the generating AI, the server generates specific control commands and sends them to the corresponding automated equipment.

[0610] Input: AI-generated advice

[0611] Output: Control command

[0612] Specific operation: The server analyzes the advice and generates specific operational instructions (e.g., a command to start the cooling system).

[0613] Step 7:

[0614] The automated equipment performs the corresponding action according to the control commands received from the server.

[0615] Input: Control command

[0616] Output: Actions performed

[0617] Specific operation: Based on the commands received by the automated equipment (e.g., cooling system), it performs physical actions (cooling, humidifying, vibration damping, etc.).

[0618] Step 8:

[0619] Users access the system via smartphones or PCs to check the control results.

[0620] Input: Execution result data

[0621] Output: User confirmation and additional instructions as needed.

[0622] Specific operation: Users monitor the execution results via smartphone or PC applications and make additional manual adjustments if necessary.

[0623] This enables a system where environmental data from each sensor is collected and analyzed on a server in real time, and automated equipment is immediately controlled based on optimal advice generated by AI.

[0624] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0625] This invention relates to a system that measures environmental data in agriculture in real time, analyzes and predicts it using generative AI, generates appropriate cultivation advice and control commands, and automatically executes them. Furthermore, by combining it with an emotion engine that recognizes user emotions, it is an advanced system that includes user emotional feedback. The following describes the configuration for implementing this system.

[0626] (1) Data collection using IoT

[0627] Terminal: Multiple sensors (temperature sensors, humidity sensors, solar radiation sensors, soil moisture sensors, etc.) placed on farms and cultivation facilities measure environmental data for each area in real time every 10 minutes. This ensures that the latest environmental information is always available.

[0628] Terminal: Measured environmental data is transmitted to the server via a communication module built into each sensor, over a stable network. Data transmission is performed periodically, and a certain amount of buffering is also performed to avoid network instability.

[0629] Server: The server saves received data to the database in real time. The saved data is time-stamped and managed centrally, including past data.

[0630] Specific example: At 6:00 AM, a sensor measures temperature (25°C), humidity (60%), sunlight (30,000 lux), and moisture content (20%), and sends this data to the server 10 minutes later. The server stores this data in a database with a timestamp.

[0631] (2) Data analysis and prediction using generative AI

[0632] Server: The server retrieves historical environment data (e.g., the past 3 months) from the database and provides it to the generating AI. This allows for a comparison between historical and current data.

[0633] Server: The generating AI analyzes and predicts plant growing conditions and future environmental changes based on acquired data. The generating AI generates advice on appropriate growing conditions and management methods, and outputs it in text format.

[0634] Specific example: A server retrieves temperature, humidity, sunlight, and moisture content data for the past three months and provides it to a generating AI. The AI ​​determines that "the temperature is appropriate, but the moisture content is low, so 3 liters of watering is necessary" and generates this advice.

[0635] (3) Execution and control based on data prediction using generative AI

[0636] Server: Based on AI advice, it generates specific control commands. For example, it might generate a command to sprinkle 3 liters of water to achieve a moisture content of 30%.

[0637] Server: Sends the generated control commands to the corresponding terminals (watering systems, lighting systems, fertilizer spreaders, etc.).

[0638] Terminal: In accordance with the received control command, the watering system performs the corresponding action, such as spraying 3 liters of water.

[0639] User: Access the system from a smartphone or PC and check the control results. Verify that the execution was performed correctly and make any necessary manual adjustments.

[0640] Specific example: The server generates a control command to "water with 3 liters of water" and sends it to the terminal's watering system. The watering system automatically waters with 3 liters of water, and the user checks the watering results on their smartphone and manually instructs additional watering if necessary.

[0641] (4) Recognition and feedback of user emotions by the emotion engine

[0642] User: Communicates emotional information (e.g., satisfaction, dissatisfaction, questions, etc.) to the system through facial expressions, voice, and input actions during operation.

[0643] Device: Uses cameras, microphones, sensors, etc. to capture the user's emotional state in real time and sends it to the emotion engine for analysis.

[0644] Server: The emotion engine processes this data and analyzes the user's emotional state. For example, if the user is expressing dissatisfaction, the emotion engine detects this and provides appropriate feedback.

[0645] Server: Based on the analysis results from the emotion engine, the generating AI adjusts the content of training advice and control commands. For example, if the user feels that things are not going well, the advice can be made more detailed.

[0646] User: Gain feedback and continue using the system. This improves the user experience and promotes the effective use of the system.

[0647] Specific example: A camera captures a user's dissatisfaction with the watering system's results, and an emotion engine recognizes the user's dissatisfaction. The server then provides more detailed advice for the next watering, resolving the user's dissatisfaction.

[0648] This system enables the real-time acquisition and effective utilization of environmental data, allowing even inexperienced individuals to perform optimal agricultural tasks. Furthermore, by incorporating user emotional feedback, it enables more detailed and personalized support.

[0649] The following describes the processing flow.

[0650] (1) Data collection using IoT

[0651] Step 1:

[0652] Terminals: Various sensors (temperature sensors, humidity sensors, solar radiation sensors, soil moisture sensors, etc.) measure environmental data in each area of ​​the farm or cultivation facility.

[0653] Step 2:

[0654] Terminal: Temporarily stores measured environmental data in internal memory. For example, it records data such as temperature 25°C, humidity 60%, solar radiation 30,000 lux, and moisture content 20%.

[0655] Step 3:

[0656] Terminal: Every 10 minutes, it sends measurement data to the server via a wireless communication module (e.g., Wi-Fi, LoRa).

[0657] Step 4:

[0658] Server: Validates received environmental data and stores it in the database with a timestamp. This ensures data integrity and consistency.

[0659] Specific example: At 6:00 AM, a sensor measures temperature at 25°C, humidity at 60%, solar radiation at 30,000 lux, and moisture content at 20%, and sends this data to a server 10 minutes later. The server then stores this data in a database.

[0660] ---

[0661] (2) Data analysis and prediction using generative AI

[0662] Step 1:

[0663] Server: Retrieves environmental data from the database for a specified period (e.g., the past 3 months). The retrieved data includes temperature, humidity, solar radiation, and moisture content.

[0664] Step 2:

[0665] Server: Inputs acquired historical data and current environmental data into the generating AI and begins analysis.

[0666] Step 3:

[0667] Server: The generating AI analyzes the input data and evaluates the optimal conditions for plant growth. Parameters considered here include appropriate temperature range, water content, and light intensity.

[0668] Step 4:

[0669] Server: Based on the analysis results, the generating AI creates cultivation advice (e.g., "The water level is low, so 3 liters of watering is needed") and outputs it in text format.

[0670] Specific example: A server provides the AI ​​with data from the past three months, and the AI ​​determines that "the temperature is appropriate, but there is insufficient moisture, so watering is necessary," and generates advice that 3 liters of watering are required.

[0671] ---

[0672] (3) Execution and control based on data prediction using generative AI

[0673] Step 1:

[0674] Server: Based on AI advice, it generates specific control commands, such as spraying 3 liters of water to achieve a 30% moisture level.

[0675] Step 2:

[0676] Server: Sends the generated control commands to the corresponding terminals (e.g., watering system, lighting system, fertilizer spreader).

[0677] Step 3:

[0678] Terminal: It performs the corresponding action (e.g., the watering system sprays 3 liters of water) according to the control command received.

[0679] Step 4:

[0680] User: Access the system from a smartphone or PC and check the control results. Make additional manual adjustments as needed.

[0681] Specific example: The server generates a control command to "water with 3 liters of water" and sends it to the terminal's watering system. The watering system automatically waters with 3 liters of water, and the user checks the watering results on their smartphone and manually instructs additional watering if necessary.

[0682] ---

[0683] (4) Recognition and feedback of user emotions by the emotion engine

[0684] Step 1:

[0685] User: Communicates emotional information (e.g., satisfaction, dissatisfaction, questions, etc.) to the system through facial expressions, voice, and input actions during operation.

[0686] Step 2:

[0687] Device: Uses cameras, microphones, sensors, etc. to capture the user's emotional state in real time and transmits it to the emotion engine.

[0688] Step 3:

[0689] Server: The emotion engine processes this data and analyzes the user's emotional state (e.g., joy, anger, surprise, etc.).

[0690] Step 4:

[0691] Server: Based on the analysis results of the emotion engine, the generating AI adjusts the content of training advice and control commands. For example, if the user indicates "dissatisfaction," the server will take measures such as making the training advice more detailed.

[0692] Step 5:

[0693] User: Gain feedback and continue using the system. This improves the user experience and ensures the system is used effectively.

[0694] Specific example: A camera captures a user's dissatisfaction with the watering system's results, and an emotion engine recognizes the user's dissatisfaction. The server then refines the next care advice to address the user's dissatisfaction.

[0695] ---

[0696] In this way, a system that combines an emotion engine enables real-time acquisition and effective utilization of environmental data, allowing even inexperienced individuals to perform optimal agricultural tasks. Furthermore, by incorporating emotional feedback from users, even more advanced support becomes possible.

[0697] (Example 2)

[0698] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0699] Conventional agricultural management systems struggled with real-time environmental data collection and its effective utilization, resulting in insufficient provision of appropriate cultivation advice and adequate automated control. Furthermore, systems lacked the ability to incorporate user emotional feedback, leaving challenges in improving the user experience.

[0700] The identification processing by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes a device for measuring environmental data, a device for transmitting the measured data to the server via a communication module, a device for the server to store the transmitted data in a database, a device for the server to analyze past and present data using a generating AI, a device for the server to generate training advice based on the analysis results, a device for generating control commands based on the generated training advice, a device for transmitting the control commands to a corresponding control device, a device for the control device to operate according to the control commands, a device for the user to confirm the operation results, an emotion engine that recognizes the user's emotions and provides feedback, and a device for the generating AI to adjust advice and control commands based on the analysis results of the emotion engine. This enables real-time collection and analysis of environmental data, provision of appropriate training advice, and automatic control, as well as advanced support that reflects the user's emotional feedback.

[0701] "Environmental data" refers to data that represents the environmental conditions of agricultural and cultivation facilities, such as temperature, humidity, solar radiation, and soil moisture content.

[0702] A "measuring device" is a device used to measure environmental data in real time, such as temperature sensors, humidity sensors, solar radiation sensors, and soil moisture sensors.

[0703] A "communication module" is a device that provides a means of communication for transmitting data from a measuring device to a server.

[0704] A "server" is a computer system used to store, manage, and analyze received environmental data.

[0705] A "database" is a system that stores measured data with timestamps and manages it centrally with past data.

[0706] "Generative AI" is an artificial intelligence system that analyzes measured data and historical data to predict and suggest plant growth conditions and management methods.

[0707] "Cultivation advice" refers to instructions on the optimal growing conditions and management methods for plants, generated by the AI ​​based on its analysis results.

[0708] A "control command" is a command that includes specific work instructions, generated based on the training advice for the generated AI.

[0709] A "control device" is a device that performs a specific action according to a control command, such as a watering system, lighting system, or fertilizer spreader.

[0710] An "emotion engine" is a system that analyzes the user's facial expressions, voice, and input actions during operation to recognize their emotional state and provide feedback.

[0711] A "user" is an agricultural worker or system user who operates the system, checks the control results, and makes manual adjustments as needed.

[0712] This invention is a system that measures environmental data in agriculture in real time, analyzes and predicts it using a generation AI, generates appropriate cultivation advice and control commands, and automatically executes them. Furthermore, by combining it with an emotion engine that recognizes the user's emotions, it is a system that provides advanced support that reflects the user's emotional feedback.

[0713] (1) Data collection using IoT

[0714] Terminals: Temperature sensors, humidity sensors, solar radiation sensors, soil moisture sensors, and other devices placed on farms and cultivation facilities measure environmental data in real time. These sensors measure data every 10 minutes and transmit it to the server via a communication module built into each sensor. Buffering is performed during transmission to maintain network stability.

[0715] Server: The server stores the received data in a database. The stored data is time-stamped and centrally managed with past data. For example, at 6 AM, the temperature sensor measures 25°C, the humidity sensor measures 60%, the solar radiation sensor measures 30,000 lux, and the soil moisture sensor measures 20%, and these data are sent to the server every 10 minutes. The server stores this data in the database with timestamps.

[0716] (2) Data analysis and prediction using generative AI

[0717] Server: The server retrieves historical environmental data (e.g., the past 3 months) from the database and provides it to the generating AI. The generating AI compares and analyzes the historical and current data to predict plant growing conditions and future environmental changes. Based on the analysis results, the generating AI generates cultivation advice in text format.

[0718] Specific example: A server retrieves temperature, humidity, sunlight, and moisture content data for the past three months and provides it to the generating AI. The AI ​​determines that "the temperature is appropriate, but the moisture content is low, so 3 liters of watering is necessary" and generates this advice.

[0719] (3) Execution and control based on data prediction using generative AI

[0720] Server: Based on the advice of the generating AI, it generates specific control commands. For example, it generates a command such as "Water with 3 liters of water to bring the moisture level to 30%."

[0721] Server: Sends the generated control commands to the corresponding control devices (e.g., watering systems, lighting systems, fertilizer spreaders).

[0722] Terminal: A control device operates according to the control commands it receives and performs the instructed task. For example, a watering system automatically sprays 3 liters of water.

[0723] User: Accesses the system from a smartphone or PC and checks the control results. They verify the accuracy of the results and make manual adjustments as needed. The server generates a control command, "Spray 3 liters of water," and sends it to the terminal's watering system. The watering system automatically sprays 3 liters of water, and the user checks the results on their smartphone and manually instructs additional watering if necessary.

[0724] (4) Recognition and feedback of user emotions by the emotion engine

[0725] User: Communicates emotional information (e.g., satisfaction, dissatisfaction, questions) to the system through facial expressions, voice, and input actions during operation.

[0726] Device: Uses cameras, microphones, and sensors to capture the user's emotional state in real time and sends it to the emotion engine for analysis.

[0727] Server: The emotion engine processes this data and analyzes the user's emotional state. If the user is expressing dissatisfaction, the emotion engine detects this and provides appropriate feedback.

[0728] Server: Based on the analysis results of the emotion engine, the generated AI adjusts the content of training advice and control commands. For example, if the user feels that things are not going well, the advice can be made more detailed.

[0729] User: By receiving feedback and continuing to operate the system, the user experience improves and the effective use of the system is promoted. The camera captures when the user is dissatisfied with the results of the watering system, and the emotion engine recognizes the feeling of dissatisfaction. The server provides more detailed advice for the next watering, resolving the user's dissatisfaction.

[0730] Example of a prompt

[0731] "Please analyze the optimal growing conditions based on temperature, humidity, sunlight, and moisture content data from the past three months."

[0732] "If users express dissatisfaction, please provide detailed training advice for the next session."

[0733] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0734] The program's processing flow is explained in detail, broken down into steps.

[0735] Step 1:

[0736] (Data collection)

[0737] Terminal: Sensors (temperature sensors, humidity sensors, solar radiation sensors, soil moisture sensors, etc.) placed on farms and cultivation facilities measure various environmental data every 10 minutes. The input is the environmental parameters measured by the sensors (e.g., temperature, humidity, solar radiation, moisture content), and the output is the measured environmental data. This data is transmitted to the server via the terminal's communication module.

[0738] Specific operation: At 6:00 AM, the temperature sensor measures 25°C, the humidity sensor measures 60%, the solar radiation sensor measures 30,000 lux, and the soil moisture sensor measures 20%. This data is sent to the server every 10 minutes.

[0739] Step 2:

[0740] (Data saving)

[0741] Server: Receives environmental data and stores it in a database. Input is measurement data sent from the terminal, and output is environmental data stored in the database. The data is timestamped, and past data is managed centrally.

[0742] Specific operation: After measurement data arrives at the server, the server adds a timestamp and saves it to the database. For example, a timestamp is added to data received every 10 minutes and recorded in the database.

[0743] Step 3:

[0744] (Data analysis and prediction)

[0745] Server: Retrieves environmental data for the past three months from the database and provides it to the generating AI. The input is environmental data for the past three months, and the output is the analysis results and cultivation advice from the generating AI. The generating AI compares and analyzes past and current data to predict plant cultivation conditions and environmental changes.

[0746] Specific operation: The server provides the generating AI with temperature, humidity, solar radiation, and moisture content data for the past three months. Based on this data, the generating AI creates cultivation advice such as, "The temperature is appropriate, but the moisture content is low, so 3 liters of watering is needed."

[0747] Step 4:

[0748] (Generating control commands)

[0749] Server: Generates specific control commands based on advice from the generating AI. The input is advice from the generating AI, and the output is a specific control command. For example, it generates a command such as "Water with 3 liters of water to bring the moisture level to 30%."

[0750] Specific operation: Based on the advice of the generating AI, the server generates a control command to "spray 3 liters of water" and sends it to the corresponding control device (watering system).

[0751] Step 5:

[0752] (Execution of control commands)

[0753] Terminal: A control device receives control commands from the server and performs actions according to the instructions. The input is the control command sent from the server, and the output is the actual action (e.g., watering, adjusting lighting, spreading fertilizer).

[0754] Specific operation: The terminal's watering system receives a command to "water with 3 liters" and automatically waters with 3 liters of water as instructed.

[0755] Step 6:

[0756] (Checking the results)

[0757] User: Access the system from a smartphone or PC and check the execution results. Input is the operation result of the control device, and output is the execution result displayed to the user. Additional manual adjustments can be made as needed.

[0758] Specific operation: The user checks the watering results on their smartphone and manually instructs additional watering if necessary.

[0759] Step 7:

[0760] (Emotion recognition and feedback)

[0761] User: Provides emotional information through facial expressions, voice, and input actions during operation. Input is the user's emotional information, and output is data sent to the emotion engine.

[0762] Device: Uses cameras, microphones, and sensors to capture the user's emotional state and sends it to the emotion engine.

[0763] Specific operation: The camera captures the user's facial expressions, the microphone collects audio, and these are sent to the emotion engine.

[0764] Step 8:

[0765] (Emotional analysis and adjustment of advice)

[0766] Server: The emotion engine analyzes the user's emotional state and provides information to the generating AI. The generating AI adjusts the content of advice and control commands based on the analysis results. The input is the user's emotional information and the aforementioned data, and the output is the adjusted advice and control commands.

[0767] Specific operation: The emotion engine recognizes that the user is not satisfied with the results of the watering system, and the server provides more detailed advice for the next cultivation.

[0768] (Application Example 2)

[0769] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0770] Environmental management in modern agriculture and factories is an extremely complex and labor-intensive task, requiring efficient and accurate responses. However, current systems struggle with real-time, appropriate control because the collection, analysis, and control of environmental data are fragmented. Furthermore, there is no mechanism to acquire and incorporate user emotional feedback into the system, resulting in a lack of improvement in the user experience. To solve these problems, it is essential to manage environmental data in real time, generate appropriate advice and control commands using generative AI, and incorporate user emotional data into the system.

[0771] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0772] In this invention, the server includes means for measuring environmental data, means for transmitting the measured data to the server, means for the server to store the transmitted data in a database, means for the server to analyze past and present data using a generating AI, means for the server to generate training advice based on the analysis results, means for generating control commands based on the generated training advice, means for transmitting the control commands to a corresponding control device, means for the control device to operate according to the control commands, means for the user to confirm the operation results, means for collecting emotional data, means for recognizing the user's emotions based on the emotional data, and means for adjusting the training advice and control commands based on the recognized emotions. This enables real-time management of environmental data and improvement of the user experience.

[0773] "Environmental data" refers to information about the environment in agriculture and factories, such as temperature, humidity, solar radiation, and soil moisture.

[0774] A "server" is a computer system that receives and stores measured environmental data and uses generated AI to analyze and predict the data.

[0775] A "database" is a data storage system for efficiently saving and managing measured environmental data and historical data.

[0776] "Generative AI" is artificial intelligence that analyzes collected data and generates training advice and control commands based on the analysis results.

[0777] A "control command" is an instruction created by the generating AI and sent to the corresponding control device, which then performs a specific action.

[0778] A "control device" is a device or equipment that takes specific actions based on control commands sent from a server.

[0779] "Emotional data" refers to information about emotions obtained through facial expressions, voice, input actions, etc., acquired during user interaction.

[0780] An "emotion engine" is an artificial intelligence system that analyzes emotional data and recognizes the user's current emotional state.

[0781] "Cultivation advice" refers to suggestions regarding the optimal cultivation conditions and management methods for plants and other objects, derived from the results of analysis and predictions performed by the generating AI based on environmental data.

[0782] This invention relates to a system that measures environmental data in a factory in real time, analyzes and predicts it using generative AI, generates appropriate management advice and control commands, and automatically executes them. Furthermore, by incorporating an emotion engine that recognizes user emotions, it is an advanced system that includes user emotional feedback. The following describes the configurations for implementing this system.

[0783] (1) Collection of environmental data

[0784] Terminal: Multiple sensors (temperature sensors, humidity sensors, machine operation status sensors, etc.) placed throughout the factory measure environmental data in each area in real time every 10 minutes. This ensures that the latest environmental information is always available.

[0785] Terminal: Measured environmental data is transmitted to the server via a communication module built into each sensor, over a stable network. Data transmission is performed periodically, and a certain amount of buffering is also performed to avoid network instability.

[0786] Server: The server saves received data to the database in real time. The saved data is time-stamped and managed centrally, including past data.

[0787] Specific example: At 6:00 AM, a sensor measures temperature (25°C), humidity (60%), and machine status (normal), and sends this data to the server 10 minutes later. The server stores this data in a database with a timestamp.

[0788] (2) Data analysis and prediction using generative AI

[0789] Server: The server retrieves historical environment data (e.g., the past 3 months) from the database and provides it to the generating AI. This allows for a comparison between historical and current data.

[0790] Server: The generating AI analyzes and predicts optimal operating conditions and future environmental changes within the factory based on acquired data. The generating AI generates advice on appropriate management conditions and control methods, and outputs it in text format.

[0791] Specific example: A server retrieves data on temperature, humidity, and machine operating status for the past three months and provides it to a generating AI. The AI ​​determines that "the temperature is appropriate, but the humidity is low, so the humidifier needs to be turned on," and generates this advice.

[0792] (3) Execution and control based on data prediction using generative AI

[0793] Server: Based on AI advice, it generates specific control commands. For example, it generates a command to activate a humidifier to set the humidity to 50%.

[0794] Server: Sends the generated control commands to the corresponding control devices (humidifiers, air conditioning systems, inspection robots, etc.).

[0795] Terminal: It performs the corresponding action, such as activating a humidifier, according to the control command it receives.

[0796] User: Access the system from a smartphone or computer and check the control results. Verify that the execution was performed correctly and make any necessary manual adjustments.

[0797] Specific example: The server generates a control command to "start the humidifier" and sends it to the humidifier on the terminal. The humidifier operates automatically, and the user checks the operation results on their smartphone and manually instructs it to operate additionally if necessary.

[0798] (4) Recognition and feedback of user emotions by the emotion engine

[0799] User: Communicates emotional information (e.g., satisfaction, dissatisfaction, questions, etc.) to the system through facial expressions, voice, and input actions during operation.

[0800] Device: Uses cameras, microphones, sensors, etc. to capture the user's emotional state in real time and sends it to the emotion engine for analysis.

[0801] Server: The emotion engine processes this data and analyzes the user's emotional state. For example, if the user is expressing dissatisfaction, the emotion engine detects this and provides appropriate feedback.

[0802] Server: Based on the analysis results from the emotion engine, the generating AI adjusts the content of management advice and control commands. For example, if the user feels that things are not going well, the advice can be made more detailed.

[0803] User: Gain feedback and continue using the system. This improves the user experience and promotes the effective use of the system.

[0804] Specific example: A camera captures a user's dissatisfaction with the humidifier's performance, and an emotion engine recognizes the user's dissatisfaction. The server then provides more detailed management advice for the next time, resolving the user's dissatisfaction.

[0805] Example prompt statements

[0806] Over the past three months, the average temperature was 25°C, the average humidity was 50%, and the machine operated normally 90 out of 100 times, with abnormalities detected 5 times. Based on this, we propose future management methods.

[0807] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0808] Step 1: Collect environmental data

[0809] Input: Data from temperature sensors, humidity sensors, and machine operating status sensors.

[0810] Operation: The terminal uses sensors placed throughout the factory to measure temperature, humidity, and machine operating status data in real time.

[0811] Data processing: The measured data is buffered through a communication module built into each sensor.

[0812] Output: A set of measured environmental data (e.g., temperature 25°C, humidity 60%, machine condition normal).

[0813] Step 2: Send

[0814] Input: Environmental data measured from sensors.

[0815] Operation: The device sends data obtained from the sensor to the server every 10 minutes.

[0816] Data processing: Data is transmitted over the network after a timestamp is added.

[0817] Output: Environment data with a timestamp is sent to the server.

[0818] Step 3: Save data

[0819] Input: Submitted environmental data.

[0820] Operation: The server saves the received data to the database.

[0821] Data processing: The server centrally manages the database, including historical data.

[0822] Output: Timestamped environment data stored in the database.

[0823] Step 4: Data Analysis and Prediction

[0824] Input: Past and present environment data stored in the database.

[0825] Operation: The server retrieves data from the database for the past three months and provides it to the generating AI.

[0826] Data processing: Generative AI compares and analyzes historical and current data to predict optimal management conditions and future environmental changes.

[0827] Output: Advice text (e.g., "The temperature is appropriate, but the humidity is low, so you need to run the humidifier.").

[0828] Step 5: Generating control commands

[0829] Input: Advice from the generating AI.

[0830] Operation: The server generates specific control commands based on advice from the generating AI.

[0831] Data calculation: Based on the advice provided, generate commands to operate the target device (e.g., humidifier).

[0832] Output: Control command (e.g., "Start the humidifier").

[0833] Step 6: Sending control commands

[0834] Input: Generated control command.

[0835] Operation: The server sends the generated control commands to the corresponding control unit.

[0836] Data processing: Send commands to the corresponding terminal via the network.

[0837] Output: Control commands received by the control device.

[0838] Step 7: Operation of the control unit

[0839] Input: Received control command.

[0840] Operation: The terminal allows the corresponding device (e.g., humidifier) ​​to perform actions according to the control commands it receives.

[0841] Data calculation: Adjusts the target environment (e.g., humidity) based on the command content.

[0842] Output: The result of the executed command (e.g., the humidifier is running).

[0843] Step 8: Check the results

[0844] Input: The result of the operation performed by the control device.

[0845] Operation: Users access the system via smartphone or PC to check the operation results of the control unit.

[0846] Data calculation: Evaluate the execution results and make additional manual adjustments as needed.

[0847] Output: User's operational verification results (e.g., checking the humidifier's operating status on a smartphone).

[0848] Step 9: Collecting emotional data

[0849] Input: User's facial expressions, voice, and input actions during operation.

[0850] Operation: The device captures the user's emotional state through the camera and microphone and sends it to the emotion engine for analysis.

[0851] Data processing: Captured emotion data is transmitted in real time.

[0852] Output: A set of emotion data (e.g., emotion of dissatisfaction).

[0853] Step 10: Emotion Recognition and Feedback

[0854] Input: Sentiment data.

[0855] Operation: The server analyzes the user's emotional state using an emotion engine.

[0856] Data processing: Based on recognized emotions, the generating AI adjusts the content of training advice and control commands.

[0857] Output: Adjusted advice or commands (e.g., make the next advice more detailed).

[0858] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0859] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0860] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart glasses 214.

[0861] [Third Embodiment]

[0862] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0863] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0864] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0865] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0866] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0867] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0868] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0869] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0870] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0871] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0872] In the headset terminal 314, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0873] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the headset terminal 314 will be referred to as the "terminal".

[0874] This invention relates to a system that measures environmental data in agriculture in real time, analyzes and predicts it using AI, generates appropriate cultivation advice and control commands, and automatically executes them. The following describes the embodiments for implementing this system.

[0875] (1) Data collection using IoT

[0876] Terminal: Multiple sensors (temperature sensors, humidity sensors, solar radiation sensors, soil moisture sensors, etc.) placed on farms and cultivation facilities measure environmental data for each area in real time every 10 minutes. This ensures that the latest environmental information is always available.

[0877] Terminal: Measured environmental data is transmitted to the server via a communication module built into each sensor, over a stable network. Data transmission is performed periodically, and a certain amount of buffering is also performed to avoid network instability.

[0878] Server: The server saves received data to the database in real time. The saved data is time-stamped and managed centrally, including past data.

[0879] Specific example: At 6:00 AM, a device (sensor) measures temperature (25°C), humidity (60%), sunlight (30,000 lux), and moisture content (20%), and sends this data to the server 10 minutes later. The server stores this data in a database with a timestamp.

[0880] (2) Data analysis and prediction using generative AI

[0881] Server: The server retrieves historical environment data (e.g., the past 3 months) from the database and provides it to the generating AI. This allows for a comparison between historical and current data.

[0882] Server: The generating AI analyzes and predicts plant growing conditions and future environmental changes based on acquired data. The generating AI generates advice on appropriate growing conditions and management methods, and outputs it in text format.

[0883] Specific example: A server retrieves temperature, humidity, sunlight, and moisture content data for the past three months and provides it to a generating AI. The AI ​​determines that "the temperature is appropriate, but the moisture content is low, so 3 liters of watering is necessary" and generates this advice.

[0884] (3) Execution and control based on data prediction using generative AI

[0885] Server: Based on advice from the generating AI, it generates specific control commands (e.g., activate the watering system) and sends them to the corresponding terminal. This automatically performs appropriate environmental adjustments.

[0886] Terminal: The terminal operates the corresponding control device (e.g., watering system, lighting system, fertilizer spreader, etc.) according to the control commands received from the server.

[0887] User: Users access the system via smartphone or PC to check the control results. They verify that the execution was performed correctly and make additional manual adjustments as needed.

[0888] Specific example: Based on the advice of the AI, the server generates a command that says, "To achieve a moisture content of 30%, water with 3 liters of water." The terminal (watering system) receives this command and waters with 3 liters of water. The user checks the watering results on their smartphone and manually instructs the system to water additionally if necessary.

[0889] This system enables the real-time acquisition and effective utilization of environmental data, allowing even inexperienced individuals to perform optimal agricultural tasks.

[0890] The following describes the processing flow.

[0891] (1) Data collection using IoT

[0892] Step 1:

[0893] Terminals: Various sensors, such as temperature sensors, humidity sensors, solar radiation sensors, and soil moisture sensors, measure environmental data in each area.

[0894] Step 2:

[0895] Terminal: Temporarily stores measured environmental data in internal memory. For example, it records data such as temperature 25°C, humidity 60%, solar radiation 30,000 lux, and moisture content 20%.

[0896] Step 3:

[0897] Terminal: At regular intervals (e.g., every 10 minutes), it transmits measurement data to the server via a wireless communication module. Communication methods include Wi-Fi and LoRa.

[0898] Step 4:

[0899] Server: Validates received environmental data and stores it in the database with a timestamp. This ensures data integrity and consistency.

[0900] Specific example: At 6:00 AM, a sensor measures data showing a temperature of 25°C, humidity of 60%, solar radiation of 30,000 lux, and moisture content of 20%, and sends this data to the server at 6:10 AM. The server then stores this data in its database.

[0901] ---

[0902] (2) Data analysis and prediction using generative AI

[0903] Step 1:

[0904] Server: Retrieves environmental data from the database for a specified period (e.g., the past 3 months). The retrieved data includes temperature, humidity, solar radiation, and moisture content.

[0905] Step 2:

[0906] Server: Inputs acquired historical data and current environmental data into the generating AI and begins analysis.

[0907] Step 3:

[0908] Server: The generating AI analyzes the input data and evaluates the optimal conditions for plant growth. Parameters considered here include appropriate temperature range, water content, and light intensity.

[0909] Step 4:

[0910] Server: Based on the analysis results, the generating AI creates cultivation advice (e.g., "The water level is low, so 3 liters of watering is needed") and outputs it in text format.

[0911] Specific example: A server provides data from the past three months to an AI, which determines that "the temperature is appropriate, but there is insufficient moisture. Watering is necessary," and generates advice that 3 liters of watering are required.

[0912] ---

[0913] (3) Execution and control based on data prediction using generative AI

[0914] Step 1:

[0915] Server: Based on AI advice, it generates specific control commands. For example, it might generate a command to sprinkle 3 liters of water to achieve a moisture content of 30%.

[0916] Step 2:

[0917] Server: Sends the generated control commands to the corresponding terminals (watering systems, lighting systems, fertilizer spreaders, etc.).

[0918] Step 3:

[0919] Terminal: In accordance with the received control command, the watering system performs the corresponding action, such as spraying 3 liters of water.

[0920] Step 4:

[0921] User: Access the system from a smartphone or PC and check the control results. Make additional manual adjustments as needed.

[0922] Specific example: The server generates a control command to "water with 3 liters of water" and sends it to the terminal's watering system. The watering system automatically waters with 3 liters of water, and the user checks the watering results on their smartphone and manually instructs additional watering if necessary.

[0923] ---

[0924] This is a detailed explanation of the specific operations at each processing step of the system.

[0925] (Example 1)

[0926] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0927] The challenge lies in creating a system that collects, analyzes, and predicts environmental data in agriculture in real time, providing optimal growing conditions for plants. This will enable the provision of cultivation methods based on highly accurate information that could not be obtained with conventional methods. It is also necessary to address data transfer problems caused by network instability and reduce the burden of manual work performed by users.

[0928] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0929] In this invention, the server includes a device for measuring environmental data, a device for transmitting the measured data to the server, a device for the server to store the transmitted data in a database, a device for the server to analyze past and present data using a generating AI, a device for the server to generate cultivation advice based on the analysis results, a device for generating control commands based on the generated cultivation advice, a device for transmitting the generated control commands to a corresponding control device, a device for the control device to operate according to the control commands, and a device for the user to confirm the operation results. This enables real-time data collection, analysis, and prediction in agriculture, allowing for the provision of optimal plant growing conditions and appropriate environmental adjustments.

[0930] "Environmental data" refers to numerical data that indicates the state of the surrounding environment in agriculture, such as temperature, humidity, solar radiation, and soil moisture content.

[0931] "Measuring devices" refer to sensors and measuring instruments used to collect environmental data.

[0932] "Transmitting device" refers to a communication device used to transfer measured environmental data to a server.

[0933] A "database" is a storage device that centrally manages information stored on a server and allows for searching and analysis as needed.

[0934] "Generative AI" refers to artificial intelligence that analyzes and predicts based on collected data, and then suggests optimal breeding conditions and management methods.

[0935] "Cultivation advice" refers to information provided in text format by a generating AI based on its analysis results, outlining the optimal growing conditions and management methods for plants.

[0936] A "control command" is an instruction sent to each control device based on the advice of the generated AI, providing specific operational instructions.

[0937] A "control device" refers to equipment or systems used to adjust the agricultural environment according to control commands received from a server.

[0938] A "device for checking operation results" refers to an interface device used by the user to check the execution results of the system and perform additional operations as needed.

[0939] "Buffering" is the process of temporarily storing data to avoid network instability and sending it when stable communication becomes possible.

[0940] SQL queries are structured query languages ​​used to retrieve specific information from databases.

[0941] This invention is a system that measures environmental data in agriculture in real time, analyzes and predicts the data using AI generation, generates appropriate cultivation advice and control commands, and automatically executes them. A specific embodiment of this system is described below.

[0942] (1) Data collection using IoT

[0943] Terminal: Multiple sensors (temperature sensors, humidity sensors, solar radiation sensors, soil moisture sensors) placed on farms and cultivation facilities measure environmental data for each area every 10 minutes. This ensures that the latest environmental information is always available.

[0944] Terminal: Measured environmental data is transmitted to the server via a communication module (e.g., LoRaWAN module) built into each sensor, over a stable network (e.g., Wi-Fi, 5G). Data transmission is performed periodically, and a certain amount of buffering is also performed to avoid network instability.

[0945] Server: The server saves received data in real time to a database (e.g., MySQL, PostgreSQL). The saved data is time-stamped and managed centrally, including past data.

[0946] Specific example: At 6:00 AM, a device (sensor) measures temperature (25°C), humidity (60%), sunlight (30,000 lux), and moisture content (20%), and sends this data to the server 10 minutes later. The server stores this data in a database with a timestamp.

[0947] (2) Data analysis and prediction using generative AI

[0948] Server: The server retrieves historical environment data (e.g., the past 3 months) from the database and provides it to the generating AI (e.g., GPT-4). This allows for a comparison between historical and current data.

[0949] Server: Based on data acquired by the generating AI, it analyzes and predicts plant growing conditions and future environmental changes. The generating AI generates advice on appropriate growing conditions and management methods, and outputs it in text format.

[0950] Specific example: A server retrieves temperature, humidity, sunlight, and moisture content data for the past three months and provides it to a generating AI. The AI ​​determines that "the temperature is appropriate, but the moisture content is low, so 3 liters of watering is necessary" and generates this advice.

[0951] (3) Execution and control based on data prediction using generative AI

[0952] Server: Based on advice from the generating AI, it generates specific control commands (e.g., activate the watering system) and sends them to the corresponding terminal. This automatically performs appropriate environmental adjustments.

[0953] Terminal: The terminal operates the corresponding control device (e.g., watering system, lighting system, fertilizer spreader, etc.) according to the control commands received from the server.

[0954] User: Users access the system via smartphone or PC to check the control results. They verify that the execution was performed correctly and make additional manual adjustments as needed.

[0955] Specific example: Based on the advice of the AI, the server generates a command that says, "To achieve a moisture content of 30%, water with 3 liters of water." The terminal (watering system) receives this command and waters with 3 liters of water. The user checks the watering results on their smartphone and manually instructs the system to water additionally if necessary.

[0956] Specific examples of input prompt sentences for generative AI models

[0957] Prompt: "Based on environmental data from the past three months, please advise on the current plant growing conditions. The data is as follows: Temperature (20°C, 22°C, 25°C), Humidity (50%, 55%, 60%), Sunlight (25,000 lux, 27,000 lux, 30,000 lux), Soil moisture (15%, 18%, 20%)."

[0958] This system enables the real-time acquisition and effective utilization of environmental data, allowing even inexperienced individuals to perform optimal agricultural work.

[0959] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0960] Step 1: Measuring environmental data

[0961] Terminal: Multiple sensors (temperature sensors, humidity sensors, solar radiation sensors, soil moisture sensors) placed in the farm or cultivation facility measure environmental data for each area every 10 minutes. Specifically, the temperature sensor measures the current temperature as 25°C and stores this value in internal memory. This measurement data serves as input.

[0962] Step 2: Send

[0963] Terminal: Measured environmental data is transmitted to the server via a stable network (e.g., Wi-Fi, 5G) using a communication module (e.g., LoRaWAN module) built into each sensor. Data transmission occurs every 10 minutes, with a certain amount of buffering to avoid network instability. Specifically, the sensor measures temperature (25°C), humidity (60%), solar radiation (30,000 lux), and moisture content (20%), combines this data into a single packet, and sends it to the server. This transmitted data becomes the output.

[0964] Step 3: Receiving and saving data

[0965] Server: The server saves received data in real time to a database (e.g., MySQL, PostgreSQL). Saved data is timestamped, and past data is centrally managed. Specifically, the server saves received data using the "Insert into Database" command. This data is the input, and the saved data is the output.

[0966] Step 4: Obtaining historical data

[0967] Server: The server retrieves historical environment data (e.g., the past 3 months) from the database using SQL queries and provides it to the generating AI (e.g., GPT-4). Specifically, the server executes the SQL query "SELECT FROM environmentdata WHERE date > current date - INTERVAL 3 MONTH", formats the retrieved data, and inputs it into the generating AI. This retrieved data is the input.

[0968] Step 5: Data analysis and advice generation

[0969] Server: Based on data acquired by the generating AI, the server analyzes and predicts plant growing conditions and future environmental changes. The generating AI generates advice on appropriate growing conditions and management methods and returns it to the server in text format. Specifically, if the generating AI determines that "the temperature is appropriate, but the moisture level is low, so 3 liters of watering is necessary," it generates this advice. This analyzed data is the input, and the generated advice is the output.

[0970] Step 6: Generating control commands

[0971] Server: Based on advice from the generating AI, the server generates specific control commands (e.g., activating a watering system) and sends them to the corresponding terminal. Specifically, the server analyzes the advice from the generating AI and generates a command, "Water with 3 liters of water to bring the moisture level to 30%", and sends it to the terminal. This advice is the input, and the generated command is the output.

[0972] Step 7: Execute control commands

[0973] Terminal: The terminal operates the corresponding control device (e.g., watering system, lighting system, fertilizer spreader, etc.) according to the control commands received from the server. Specifically, the terminal (watering system) receives a command and activates its internal mechanism to spray 3 liters of water. This control command is the input, and the operation result of each device is the output.

[0974] Step 8: Check the execution results

[0975] User: The user accesses the system via smartphone or PC and checks the control results. Specifically, the user checks the system status on their smartphone to confirm whether watering was performed as scheduled. If necessary, they send a "manual additional watering" command to their terminal. The system's operation results are the input, and the user's confirmation and manual instructions are the output.

[0976] (Application Example 1)

[0977] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0978] Traditional factory production management and environmental control often involve manual processes, leading to inefficiencies and a lack of optimization. Furthermore, real-time monitoring of multiple environmental factors (temperature, humidity, vibration, etc.) and immediate control based on that information are difficult, potentially resulting in problems with production efficiency and quality control. Therefore, the challenge lies in providing new methods to improve production efficiency and optimize quality control.

[0979] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0980] In this invention, the server includes means for measuring environmental data, means for transmitting the measured data to the server, means for the server to store the transmitted data in a database, means for the server to analyze past and present data using a generating AI, means for the server to generate production advice based on the analysis results, means for generating control commands based on the generated production advice, means for transmitting the control commands to a corresponding automated device, means for the automated device to operate according to the control commands, and means for the user to confirm the operation results. This enables real-time monitoring and immediate control of environmental data, making it possible to optimize production efficiency and quality control.

[0981] "Environmental data" refers to data that measures information about the working environment in a factory in real time, such as temperature, humidity, vibration, and illuminance.

[0982] A "server" is a device or system that receives measured environmental data, stores it in a database, and performs analysis and prediction using generating AI.

[0983] A "database" is a digital storage system in which environmental data sent to a server is stored with timestamps and centrally managed.

[0984] "Generative AI" refers to artificial intelligence that performs analysis and prediction based on past and current environmental data, and is used to generate production advice and control commands.

[0985] "Production advice" refers to the process where the generating AI analyzes environmental data and provides specific advice in text format to optimize production efficiency and quality control.

[0986] A "control command" is an instruction sent to automated equipment based on generated production advice, and it is an executable command to adjust the environment and work content.

[0987] "Automated equipment" refers to mechanical devices and robots that operate according to control commands, and is used for environmental adjustment and production work within factories.

[0988] A "user" is a person who accesses the system to check its operation results and make additional adjustments as needed.

[0989] This invention is a system that improves production efficiency and quality control by measuring environmental data within a factory in real time and analyzing and predicting it using generated AI. The specific forms for implementing this system are described below.

[0990] First, temperature sensors, humidity sensors, vibration sensors, and illuminance sensors are installed in each area of ​​the factory. These sensors measure environmental data every 10 minutes. The measured data is transmitted to a server via a stable network through a communication module built into each sensor. Data transmission is performed periodically, and a certain amount of buffering is also performed to avoid network instability.

[0991] The server saves received data to a database in real time. The saved data is time-stamped and managed centrally, including historical data. The server retrieves historical environmental data (e.g., the past three months) from the database and provides it to the generating AI. This allows for a comparison between historical and current data.

[0992] The generating AI analyzes and predicts conditions related to production efficiency and quality control, as well as future environmental changes, based on the acquired data. The generating AI generates advice on appropriate production conditions and management methods, and outputs it in text format. For example, if a server acquires temperature, humidity, vibration, and illuminance data for the past three months and provides it to the generating AI, the generating AI might determine that "the temperature is too high and the cooling system needs to be activated" and generate this advice.

[0993] Based on the advice of the generated AI, the server generates specific control commands (e.g., activate the cooling system) and sends them to the corresponding automated equipment. This automatically performs appropriate environmental adjustments. The automated equipment then operates the corresponding control devices (e.g., cooling system, humidification system, vibration damping device, etc.) according to the control commands received from the server.

[0994] Users access the system via smartphones or PCs to check the control results. They verify that the execution was performed correctly and make additional manual adjustments as needed.

[0995] As a concrete example, a server acquires temperature, humidity, vibration, and illuminance data for the past three months and provides it to a generating AI. The AI ​​determines that "the temperature is too high and the cooling system needs to be activated" and generates this advice. Based on the AI's advice, the server generates a command to "activate the cooling system." The terminal (cooling system) receives this command and activates the system. The user checks the cooling results on their smartphone and manually instructs additional cooling if necessary.

[0996] Examples of prompts to input into a generative AI model:

[0997] Generate advice for improving production efficiency based on environmental data (temperature, humidity, vibration, illuminance). Past data is as follows: Temperature: 25°C, Humidity: 60%, Vibration: 1.2, Illuminance: 420. Current data is as follows: Temperature: 28°C, Humidity: 55%, Vibration: 2.0, Illuminance: 460.

[0998] In this way, real-time monitoring and immediate control of environmental data become possible, enabling the optimization of production efficiency and quality control.

[0999] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[1000] Step 1:

[1001] The terminal uses sensors placed in various areas of the factory to measure environmental data (temperature, humidity, vibration, illuminance, etc.) every 10 minutes.

[1002] Input: Real-time environmental data obtained from each sensor

[1003] Output: Measured environmental data

[1004] Specific operation: The sensor detects the surrounding environment and generates data as digital information.

[1005] Step 2:

[1006] The terminal transmits the measured data to the server via its built-in communication module.

[1007] Input: Measured environmental data

[1008] Output: Data to send to the server

[1009] Specific operation: The communication module receives the data generated by the sensor and sends it to the server via the network.

[1010] Step 3:

[1011] The server saves the received data to the database in real time.

[1012] Input: Submitted environmental data

[1013] Output: Data stored in the database (with timestamp)

[1014] Specific operation: The server parses the received data and adds a timestamp when saving it to the database system (e.g., MySQL or PostgreSQL).

[1015] Step 4:

[1016] The server retrieves historical environmental data from the database and provides it to the generating AI along with current data.

[1017] Input: Historical and current environmental data

[1018] Output: Data provided to the generating AI

[1019] Specific operation: The server executes a database query to extract historical data, combines it with current data, and passes it to the generating AI.

[1020] Step 5:

[1021] The generating AI analyzes the provided data to determine the conditions for production efficiency and quality control, and then generates advice.

[1022] Input: Historical and current environmental data

[1023] Output: Production advice (text format)

[1024] Specific operation: A generative AI model (e.g., using TensorFlow or PyTorch) analyzes the data and outputs appropriate advice in text format.

[1025] Step 6:

[1026] Based on the advice of the generating AI, the server generates specific control commands and sends them to the corresponding automated equipment.

[1027] Input: AI-generated advice

[1028] Output: Control command

[1029] Specific operation: The server analyzes the advice and generates specific operational instructions (e.g., a command to start the cooling system).

[1030] Step 7:

[1031] The automated equipment performs the corresponding action according to the control commands received from the server.

[1032] Input: Control command

[1033] Output: Actions performed

[1034] Specific operation: Based on the commands received by the automated equipment (e.g., cooling system), it performs physical actions (cooling, humidifying, vibration damping, etc.).

[1035] Step 8:

[1036] Users access the system via smartphones or PCs to check the control results.

[1037] Input: Execution result data

[1038] Output: User confirmation and additional instructions as needed.

[1039] Specific operation: Users monitor the execution results via smartphone or PC applications and make additional manual adjustments if necessary.

[1040] This enables a system where environmental data from each sensor is collected and analyzed on a server in real time, and automated equipment is immediately controlled based on optimal advice generated by AI.

[1041] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[1042] This invention relates to a system that measures environmental data in agriculture in real time, analyzes and predicts it using generative AI, generates appropriate cultivation advice and control commands, and automatically executes them. Furthermore, by combining it with an emotion engine that recognizes user emotions, it is an advanced system that includes user emotional feedback. The following describes the configuration for implementing this system.

[1043] (1) Data collection using IoT

[1044] Terminal: Multiple sensors (temperature sensors, humidity sensors, solar radiation sensors, soil moisture sensors, etc.) placed on farms and cultivation facilities measure environmental data for each area in real time every 10 minutes. This ensures that the latest environmental information is always available.

[1045] Terminal: Measured environmental data is transmitted to the server via a communication module built into each sensor, over a stable network. Data transmission is performed periodically, and a certain amount of buffering is also performed to avoid network instability.

[1046] Server: The server saves received data to the database in real time. The saved data is time-stamped and managed centrally, including past data.

[1047] Specific example: At 6:00 AM, a sensor measures temperature (25°C), humidity (60%), sunlight (30,000 lux), and moisture content (20%), and sends this data to the server 10 minutes later. The server stores this data in a database with a timestamp.

[1048] (2) Data analysis and prediction using generative AI

[1049] Server: The server retrieves historical environment data (e.g., the past 3 months) from the database and provides it to the generating AI. This allows for a comparison between historical and current data.

[1050] Server: The generating AI analyzes and predicts plant growing conditions and future environmental changes based on acquired data. The generating AI generates advice on appropriate growing conditions and management methods, and outputs it in text format.

[1051] Specific example: A server retrieves temperature, humidity, sunlight, and moisture content data for the past three months and provides it to a generating AI. The AI ​​determines that "the temperature is appropriate, but the moisture content is low, so 3 liters of watering is necessary" and generates this advice.

[1052] (3) Execution and control based on data prediction using generative AI

[1053] Server: Based on AI advice, it generates specific control commands. For example, it might generate a command to sprinkle 3 liters of water to achieve a moisture content of 30%.

[1054] Server: Sends the generated control commands to the corresponding terminals (watering systems, lighting systems, fertilizer spreaders, etc.).

[1055] Terminal: In accordance with the received control command, the watering system performs the corresponding action, such as spraying 3 liters of water.

[1056] User: Access the system from a smartphone or PC and check the control results. Verify that the execution was performed correctly and make any necessary manual adjustments.

[1057] Specific example: The server generates a control command to "water with 3 liters of water" and sends it to the terminal's watering system. The watering system automatically waters with 3 liters of water, and the user checks the watering results on their smartphone and manually instructs additional watering if necessary.

[1058] (4) Recognition and feedback of user emotions by the emotion engine

[1059] User: Communicates emotional information (e.g., satisfaction, dissatisfaction, questions, etc.) to the system through facial expressions, voice, and input actions during operation.

[1060] Device: Uses cameras, microphones, sensors, etc. to capture the user's emotional state in real time and sends it to the emotion engine for analysis.

[1061] Server: The emotion engine processes this data and analyzes the user's emotional state. For example, if the user is expressing dissatisfaction, the emotion engine detects this and provides appropriate feedback.

[1062] Server: Based on the analysis results from the emotion engine, the generating AI adjusts the content of training advice and control commands. For example, if the user feels that things are not going well, the advice can be made more detailed.

[1063] User: Gain feedback and continue using the system. This improves the user experience and promotes the effective use of the system.

[1064] Specific example: A camera captures a user's dissatisfaction with the watering system's results, and an emotion engine recognizes the user's dissatisfaction. The server then provides more detailed advice for the next watering, resolving the user's dissatisfaction.

[1065] This system enables the real-time acquisition and effective utilization of environmental data, allowing even inexperienced individuals to perform optimal agricultural tasks. Furthermore, by incorporating user emotional feedback, it enables more detailed and personalized support.

[1066] The following describes the processing flow.

[1067] (1) Data collection using IoT

[1068] Step 1:

[1069] Terminals: Various sensors (temperature sensors, humidity sensors, solar radiation sensors, soil moisture sensors, etc.) measure environmental data in each area of ​​the farm or cultivation facility.

[1070] Step 2:

[1071] Terminal: Temporarily stores measured environmental data in internal memory. For example, it records data such as temperature 25°C, humidity 60%, solar radiation 30,000 lux, and moisture content 20%.

[1072] Step 3:

[1073] Terminal: Every 10 minutes, it sends measurement data to the server via a wireless communication module (e.g., Wi-Fi, LoRa).

[1074] Step 4:

[1075] Server: Validates received environmental data and stores it in the database with a timestamp. This ensures data integrity and consistency.

[1076] Specific example: At 6:00 AM, a sensor measures temperature at 25°C, humidity at 60%, solar radiation at 30,000 lux, and moisture content at 20%, and sends this data to a server 10 minutes later. The server then stores this data in a database.

[1077] ---

[1078] (2) Data analysis and prediction using generative AI

[1079] Step 1:

[1080] Server: Retrieves environmental data from the database for a specified period (e.g., the past 3 months). The retrieved data includes temperature, humidity, solar radiation, and moisture content.

[1081] Step 2:

[1082] Server: Inputs acquired historical data and current environmental data into the generating AI and begins analysis.

[1083] Step 3:

[1084] Server: The generating AI analyzes the input data and evaluates the optimal conditions for plant growth. Parameters considered here include appropriate temperature range, water content, and light intensity.

[1085] Step 4:

[1086] Server: Based on the analysis results, the generating AI creates cultivation advice (e.g., "The water level is low, so 3 liters of watering is needed") and outputs it in text format.

[1087] Specific example: A server provides the AI ​​with data from the past three months, and the AI ​​determines that "the temperature is appropriate, but there is insufficient moisture, so watering is necessary," and generates advice that 3 liters of watering are required.

[1088] ---

[1089] (3) Execution and control based on data prediction using generative AI

[1090] Step 1:

[1091] Server: Based on AI advice, it generates specific control commands, such as spraying 3 liters of water to achieve a 30% moisture level.

[1092] Step 2:

[1093] Server: Sends the generated control commands to the corresponding terminals (e.g., watering system, lighting system, fertilizer spreader).

[1094] Step 3:

[1095] Terminal: It performs the corresponding action (e.g., the watering system sprays 3 liters of water) according to the control command received.

[1096] Step 4:

[1097] User: Access the system from a smartphone or PC and check the control results. Make additional manual adjustments as needed.

[1098] Specific example: The server generates a control command to "water with 3 liters of water" and sends it to the terminal's watering system. The watering system automatically waters with 3 liters of water, and the user checks the watering results on their smartphone and manually instructs additional watering if necessary.

[1099] ---

[1100] (4) Recognition and feedback of user emotions by the emotion engine

[1101] Step 1:

[1102] User: Communicates emotional information (e.g., satisfaction, dissatisfaction, questions, etc.) to the system through facial expressions, voice, and input actions during operation.

[1103] Step 2:

[1104] Device: Uses cameras, microphones, sensors, etc. to capture the user's emotional state in real time and transmits it to the emotion engine.

[1105] Step 3:

[1106] Server: The emotion engine processes this data and analyzes the user's emotional state (e.g., joy, anger, surprise, etc.).

[1107] Step 4:

[1108] Server: Based on the analysis results of the emotion engine, the generating AI adjusts the content of training advice and control commands. For example, if the user indicates "dissatisfaction," the server will take measures such as making the training advice more detailed.

[1109] Step 5:

[1110] User: Gain feedback and continue using the system. This improves the user experience and ensures the system is used effectively.

[1111] Specific example: A camera captures a user's dissatisfaction with the watering system's results, and an emotion engine recognizes the user's dissatisfaction. The server then refines the next care advice to address the user's dissatisfaction.

[1112] ---

[1113] In this way, a system that combines an emotion engine enables real-time acquisition and effective utilization of environmental data, allowing even inexperienced individuals to perform optimal agricultural tasks. Furthermore, by incorporating emotional feedback from users, even more advanced support becomes possible.

[1114] (Example 2)

[1115] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[1116] Conventional agricultural management systems struggled with real-time environmental data collection and its effective utilization, resulting in insufficient provision of appropriate cultivation advice and adequate automated control. Furthermore, systems lacked the ability to incorporate user emotional feedback, leaving challenges in improving the user experience.

[1117] The identification processing by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes a device for measuring environmental data, a device for transmitting the measured data to the server via a communication module, a device for the server to store the transmitted data in a database, a device for the server to analyze past and present data using a generating AI, a device for the server to generate training advice based on the analysis results, a device for generating control commands based on the generated training advice, a device for transmitting the control commands to a corresponding control device, a device for the control device to operate according to the control commands, a device for the user to confirm the operation results, an emotion engine that recognizes the user's emotions and provides feedback, and a device for the generating AI to adjust advice and control commands based on the analysis results of the emotion engine. This enables real-time collection and analysis of environmental data, provision of appropriate training advice, and automatic control, as well as advanced support that reflects the user's emotional feedback.

[1118] "Environmental data" refers to data that represents the environmental conditions of agricultural and cultivation facilities, such as temperature, humidity, solar radiation, and soil moisture content.

[1119] A "measuring device" is a device used to measure environmental data in real time, such as temperature sensors, humidity sensors, solar radiation sensors, and soil moisture sensors.

[1120] A "communication module" is a device that provides a means of communication for transmitting data from a measuring device to a server.

[1121] A "server" is a computer system used to store, manage, and analyze received environmental data.

[1122] A "database" is a system that stores measured data with timestamps and manages it centrally with past data.

[1123] "Generative AI" is an artificial intelligence system that analyzes measured data and historical data to predict and suggest plant growth conditions and management methods.

[1124] "Cultivation advice" refers to instructions on the optimal growing conditions and management methods for plants, generated by the AI ​​based on its analysis results.

[1125] A "control command" is a command that includes specific work instructions, generated based on the training advice for the generated AI.

[1126] A "control device" is a device that performs a specific action according to a control command, such as a watering system, lighting system, or fertilizer spreader.

[1127] An "emotion engine" is a system that analyzes the user's facial expressions, voice, and input actions during operation to recognize their emotional state and provide feedback.

[1128] A "user" is an agricultural worker or system user who operates the system, checks the control results, and makes manual adjustments as needed.

[1129] This invention is a system that measures environmental data in agriculture in real time, analyzes and predicts it using a generation AI, generates appropriate cultivation advice and control commands, and automatically executes them. Furthermore, by combining it with an emotion engine that recognizes the user's emotions, it is a system that provides advanced support that reflects the user's emotional feedback.

[1130] (1) Data collection using IoT

[1131] Terminals: Temperature sensors, humidity sensors, solar radiation sensors, soil moisture sensors, and other devices placed on farms and cultivation facilities measure environmental data in real time. These sensors measure data every 10 minutes and transmit it to the server via a communication module built into each sensor. Buffering is performed during transmission to maintain network stability.

[1132] Server: The server stores the received data in a database. The stored data is time-stamped and centrally managed with past data. For example, at 6 AM, the temperature sensor measures 25°C, the humidity sensor measures 60%, the solar radiation sensor measures 30,000 lux, and the soil moisture sensor measures 20%, and these data are sent to the server every 10 minutes. The server stores this data in the database with timestamps.

[1133] (2) Data analysis and prediction using generative AI

[1134] Server: The server retrieves historical environmental data (e.g., the past 3 months) from the database and provides it to the generating AI. The generating AI compares and analyzes the historical and current data to predict plant growing conditions and future environmental changes. Based on the analysis results, the generating AI generates cultivation advice in text format.

[1135] Specific example: A server retrieves temperature, humidity, sunlight, and moisture content data for the past three months and provides it to the generating AI. The AI ​​determines that "the temperature is appropriate, but the moisture content is low, so 3 liters of watering is necessary" and generates this advice.

[1136] (3) Execution and control based on data prediction using generative AI

[1137] Server: Based on the advice of the generating AI, it generates specific control commands. For example, it generates a command such as "Water with 3 liters of water to bring the moisture level to 30%."

[1138] Server: Sends the generated control commands to the corresponding control devices (e.g., watering systems, lighting systems, fertilizer spreaders).

[1139] Terminal: A control device operates according to the control commands it receives and performs the instructed task. For example, a watering system automatically sprays 3 liters of water.

[1140] User: Accesses the system from a smartphone or PC and checks the control results. They verify the accuracy of the results and make manual adjustments as needed. The server generates a control command, "Spray 3 liters of water," and sends it to the terminal's watering system. The watering system automatically sprays 3 liters of water, and the user checks the results on their smartphone and manually instructs additional watering if necessary.

[1141] (4) Recognition and feedback of user emotions by the emotion engine

[1142] User: Communicates emotional information (e.g., satisfaction, dissatisfaction, questions) to the system through facial expressions, voice, and input actions during operation.

[1143] Device: Uses cameras, microphones, and sensors to capture the user's emotional state in real time and sends it to the emotion engine for analysis.

[1144] Server: The emotion engine processes this data and analyzes the user's emotional state. If the user is expressing dissatisfaction, the emotion engine detects this and provides appropriate feedback.

[1145] Server: Based on the analysis results of the emotion engine, the generated AI adjusts the content of training advice and control commands. For example, if the user feels that things are not going well, the advice can be made more detailed.

[1146] User: By receiving feedback and continuing to operate the system, the user experience improves and the effective use of the system is promoted. The camera captures when the user is dissatisfied with the results of the watering system, and the emotion engine recognizes the feeling of dissatisfaction. The server provides more detailed advice for the next watering, resolving the user's dissatisfaction.

[1147] Example of a prompt

[1148] "Please analyze the optimal growing conditions based on temperature, humidity, sunlight, and moisture content data from the past three months."

[1149] "If users express dissatisfaction, please provide detailed training advice for the next session."

[1150] The flow of the specific processing in Example 2 will be explained using Figure 13.

[1151] The program's processing flow is explained in detail, broken down into steps.

[1152] Step 1:

[1153] (Data collection)

[1154] Terminal: Sensors (temperature sensors, humidity sensors, solar radiation sensors, soil moisture sensors, etc.) placed on farms and cultivation facilities measure various environmental data every 10 minutes. The input is the environmental parameters measured by the sensors (e.g., temperature, humidity, solar radiation, moisture content), and the output is the measured environmental data. This data is transmitted to the server via the terminal's communication module.

[1155] Specific operation: At 6:00 AM, the temperature sensor measures 25°C, the humidity sensor measures 60%, the solar radiation sensor measures 30,000 lux, and the soil moisture sensor measures 20%. This data is sent to the server every 10 minutes.

[1156] Step 2:

[1157] (Data saving)

[1158] Server: Receives environmental data and stores it in a database. Input is measurement data sent from the terminal, and output is environmental data stored in the database. The data is timestamped, and past data is managed centrally.

[1159] Specific operation: After measurement data arrives at the server, the server adds a timestamp and saves it to the database. For example, a timestamp is added to data received every 10 minutes and recorded in the database.

[1160] Step 3:

[1161] (Data analysis and prediction)

[1162] Server: Retrieves environmental data for the past three months from the database and provides it to the generating AI. The input is environmental data for the past three months, and the output is the analysis results and cultivation advice from the generating AI. The generating AI compares and analyzes past and current data to predict plant cultivation conditions and environmental changes.

[1163] Specific operation: The server provides the generating AI with temperature, humidity, solar radiation, and moisture content data for the past three months. Based on this data, the generating AI creates cultivation advice such as, "The temperature is appropriate, but the moisture content is low, so 3 liters of watering is needed."

[1164] Step 4:

[1165] (Generating control commands)

[1166] Server: Generates specific control commands based on advice from the generating AI. The input is advice from the generating AI, and the output is a specific control command. For example, it generates a command such as "Water with 3 liters of water to bring the moisture level to 30%."

[1167] Specific operation: Based on the advice of the generating AI, the server generates a control command to "spray 3 liters of water" and sends it to the corresponding control device (watering system).

[1168] Step 5:

[1169] (Execution of control commands)

[1170] Terminal: A control device receives control commands from the server and performs actions according to the instructions. The input is the control command sent from the server, and the output is the actual action (e.g., watering, adjusting lighting, spreading fertilizer).

[1171] Specific operation: The terminal's watering system receives a command to "water with 3 liters" and automatically waters with 3 liters of water as instructed.

[1172] Step 6:

[1173] (Checking the results)

[1174] User: Access the system from a smartphone or PC and check the execution results. Input is the operation result of the control device, and output is the execution result displayed to the user. Additional manual adjustments can be made as needed.

[1175] Specific operation: The user checks the watering results on their smartphone and manually instructs additional watering if necessary.

[1176] Step 7:

[1177] (Emotion recognition and feedback)

[1178] User: Provides emotional information through facial expressions, voice, and input actions during operation. Input is the user's emotional information, and output is data sent to the emotion engine.

[1179] Device: Uses cameras, microphones, and sensors to capture the user's emotional state and sends it to the emotion engine.

[1180] Specific operation: The camera captures the user's facial expressions, the microphone collects audio, and these are sent to the emotion engine.

[1181] Step 8:

[1182] (Emotional analysis and adjustment of advice)

[1183] Server: The emotion engine analyzes the user's emotional state and provides information to the generating AI. The generating AI adjusts the content of advice and control commands based on the analysis results. The input is the user's emotional information and the aforementioned data, and the output is the adjusted advice and control commands.

[1184] Specific operation: The emotion engine recognizes that the user is not satisfied with the results of the watering system, and the server provides more detailed advice for the next cultivation.

[1185] (Application Example 2)

[1186] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[1187] Environmental management in modern agriculture and factories is an extremely complex and labor-intensive task, requiring efficient and accurate responses. However, current systems struggle with real-time, appropriate control because the collection, analysis, and control of environmental data are fragmented. Furthermore, there is no mechanism to acquire and incorporate user emotional feedback into the system, resulting in a lack of improvement in the user experience. To solve these problems, it is essential to manage environmental data in real time, generate appropriate advice and control commands using generative AI, and incorporate user emotional data into the system.

[1188] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[1189] In this invention, the server includes means for measuring environmental data, means for transmitting the measured data to the server, means for the server to store the transmitted data in a database, means for the server to analyze past and present data using a generating AI, means for the server to generate training advice based on the analysis results, means for generating control commands based on the generated training advice, means for transmitting the control commands to a corresponding control device, means for the control device to operate according to the control commands, means for the user to confirm the operation results, means for collecting emotional data, means for recognizing the user's emotions based on the emotional data, and means for adjusting the training advice and control commands based on the recognized emotions. This enables real-time management of environmental data and improvement of the user experience.

[1190] "Environmental data" refers to information about the environment in agriculture and factories, such as temperature, humidity, solar radiation, and soil moisture.

[1191] A "server" is a computer system that receives and stores measured environmental data and uses generated AI to analyze and predict the data.

[1192] A "database" is a data storage system for efficiently saving and managing measured environmental data and historical data.

[1193] "Generative AI" is artificial intelligence that analyzes collected data and generates training advice and control commands based on the analysis results.

[1194] A "control command" is an instruction created by the generating AI and sent to the corresponding control device, which then performs a specific action.

[1195] A "control device" is a device or equipment that takes specific actions based on control commands sent from a server.

[1196] "Emotional data" refers to information about emotions obtained through facial expressions, voice, input actions, etc., acquired during user interaction.

[1197] An "emotion engine" is an artificial intelligence system that analyzes emotional data and recognizes the user's current emotional state.

[1198] "Cultivation advice" refers to suggestions regarding the optimal cultivation conditions and management methods for plants and other objects, derived from the results of analysis and predictions performed by the generating AI based on environmental data.

[1199] This invention relates to a system that measures environmental data in a factory in real time, analyzes and predicts it using generative AI, generates appropriate management advice and control commands, and automatically executes them. Furthermore, by incorporating an emotion engine that recognizes user emotions, it is an advanced system that includes user emotional feedback. The following describes the configurations for implementing this system.

[1200] (1) Collection of environmental data

[1201] Terminal: Multiple sensors (temperature sensors, humidity sensors, machine operation status sensors, etc.) placed throughout the factory measure environmental data in each area in real time every 10 minutes. This ensures that the latest environmental information is always available.

[1202] Terminal: Measured environmental data is transmitted to the server via a communication module built into each sensor, over a stable network. Data transmission is performed periodically, and a certain amount of buffering is also performed to avoid network instability.

[1203] Server: The server saves received data to the database in real time. The saved data is time-stamped and managed centrally, including past data.

[1204] Specific example: At 6:00 AM, a sensor measures temperature (25°C), humidity (60%), and machine status (normal), and sends this data to the server 10 minutes later. The server stores this data in a database with a timestamp.

[1205] (2) Data analysis and prediction using generative AI

[1206] Server: The server retrieves historical environment data (e.g., the past 3 months) from the database and provides it to the generating AI. This allows for a comparison between historical and current data.

[1207] Server: The generating AI analyzes and predicts optimal operating conditions and future environmental changes within the factory based on acquired data. The generating AI generates advice on appropriate management conditions and control methods, and outputs it in text format.

[1208] Specific example: A server retrieves data on temperature, humidity, and machine operating status for the past three months and provides it to a generating AI. The AI ​​determines that "the temperature is appropriate, but the humidity is low, so the humidifier needs to be turned on," and generates this advice.

[1209] (3) Execution and control based on data prediction using generative AI

[1210] Server: Based on AI advice, it generates specific control commands. For example, it generates a command to activate a humidifier to set the humidity to 50%.

[1211] Server: Sends the generated control commands to the corresponding control devices (humidifiers, air conditioning systems, inspection robots, etc.).

[1212] Terminal: It performs the corresponding action, such as activating a humidifier, according to the control command it receives.

[1213] User: Access the system from a smartphone or computer and check the control results. Verify that the execution was performed correctly and make any necessary manual adjustments.

[1214] Specific example: The server generates a control command to "start the humidifier" and sends it to the humidifier on the terminal. The humidifier operates automatically, and the user checks the operation results on their smartphone and manually instructs it to operate additionally if necessary.

[1215] (4) Recognition and feedback of user emotions by the emotion engine

[1216] User: Communicates emotional information (e.g., satisfaction, dissatisfaction, questions, etc.) to the system through facial expressions, voice, and input actions during operation.

[1217] Device: Uses cameras, microphones, sensors, etc. to capture the user's emotional state in real time and sends it to the emotion engine for analysis.

[1218] Server: The emotion engine processes this data and analyzes the user's emotional state. For example, if the user is expressing dissatisfaction, the emotion engine detects this and provides appropriate feedback.

[1219] Server: Based on the analysis results from the emotion engine, the generating AI adjusts the content of management advice and control commands. For example, if the user feels that things are not going well, the advice can be made more detailed.

[1220] User: Gain feedback and continue using the system. This improves the user experience and promotes the effective use of the system.

[1221] Specific example: A camera captures a user's dissatisfaction with the humidifier's performance, and an emotion engine recognizes the user's dissatisfaction. The server then provides more detailed management advice for the next time, resolving the user's dissatisfaction.

[1222] Example prompt statements

[1223] Over the past three months, the average temperature was 25°C, the average humidity was 50%, and the machine operated normally 90 out of 100 times, with abnormalities detected 5 times. Based on this, we propose future management methods.

[1224] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[1225] Step 1: Collect environmental data

[1226] Input: Data from temperature sensors, humidity sensors, and machine operating status sensors.

[1227] Operation: The terminal uses sensors placed throughout the factory to measure temperature, humidity, and machine operating status data in real time.

[1228] Data processing: The measured data is buffered through a communication module built into each sensor.

[1229] Output: A set of measured environmental data (e.g., temperature 25°C, humidity 60%, machine condition normal).

[1230] Step 2: Send

[1231] Input: Environmental data measured from sensors.

[1232] Operation: The device sends data obtained from the sensor to the server every 10 minutes.

[1233] Data processing: Data is transmitted over the network after a timestamp is added.

[1234] Output: Environment data with a timestamp is sent to the server.

[1235] Step 3: Save data

[1236] Input: Submitted environmental data.

[1237] Operation: The server saves the received data to the database.

[1238] Data processing: The server centrally manages the database, including historical data.

[1239] Output: Timestamped environment data stored in the database.

[1240] Step 4: Data Analysis and Prediction

[1241] Input: Past and present environment data stored in the database.

[1242] Operation: The server retrieves data from the database for the past three months and provides it to the generating AI.

[1243] Data processing: Generative AI compares and analyzes historical and current data to predict optimal management conditions and future environmental changes.

[1244] Output: Advice text (e.g., "The temperature is appropriate, but the humidity is low, so you need to run the humidifier.").

[1245] Step 5: Generating control commands

[1246] Input: Advice from the generating AI.

[1247] Operation: The server generates specific control commands based on advice from the generating AI.

[1248] Data calculation: Based on the advice provided, generate commands to operate the target device (e.g., humidifier).

[1249] Output: Control command (e.g., "Start the humidifier").

[1250] Step 6: Sending control commands

[1251] Input: Generated control command.

[1252] Operation: The server sends the generated control commands to the corresponding control unit.

[1253] Data processing: Send commands to the corresponding terminal via the network.

[1254] Output: Control commands received by the control device.

[1255] Step 7: Operation of the control unit

[1256] Input: Received control command.

[1257] Operation: The terminal allows the corresponding device (e.g., humidifier) ​​to perform actions according to the control commands it receives.

[1258] Data calculation: Adjusts the target environment (e.g., humidity) based on the command content.

[1259] Output: The result of the executed command (e.g., the humidifier is running).

[1260] Step 8: Check the results

[1261] Input: The result of the operation performed by the control device.

[1262] Operation: Users access the system via smartphone or PC to check the operation results of the control unit.

[1263] Data calculation: Evaluate the execution results and make additional manual adjustments as needed.

[1264] Output: User's operational verification results (e.g., checking the humidifier's operating status on a smartphone).

[1265] Step 9: Collecting emotional data

[1266] Input: User's facial expressions, voice, and input actions during operation.

[1267] Operation: The device captures the user's emotional state through the camera and microphone and sends it to the emotion engine for analysis.

[1268] Data processing: Captured emotion data is transmitted in real time.

[1269] Output: A set of emotion data (e.g., emotion of dissatisfaction).

[1270] Step 10: Emotion Recognition and Feedback

[1271] Input: Sentiment data.

[1272] Operation: The server analyzes the user's emotional state using an emotion engine.

[1273] Data processing: Based on recognized emotions, the generating AI adjusts the content of training advice and control commands.

[1274] Output: Adjusted advice or commands (e.g., make the next advice more detailed).

[1275] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[1276] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1277] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and specific processing may also be performed by the headset terminal 314.

[1278] [Fourth Embodiment]

[1279] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[1280] As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[1281] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1282] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[1283] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[1284] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[1285] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[1286] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. Furthermore, the robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[1287] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[1288] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[1289] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1290] In robot 414, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[1291] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1292] This invention relates to a system that measures environmental data in agriculture in real time, analyzes and predicts it using AI, generates appropriate cultivation advice and control commands, and automatically executes them. The following describes the embodiments for implementing this system.

[1293] (1) Data collection using IoT

[1294] Terminal: Multiple sensors (temperature sensors, humidity sensors, solar radiation sensors, soil moisture sensors, etc.) placed on farms and cultivation facilities measure environmental data for each area in real time every 10 minutes. This ensures that the latest environmental information is always available.

[1295] Terminal: Measured environmental data is transmitted to the server via a communication module built into each sensor, over a stable network. Data transmission is performed periodically, and a certain amount of buffering is also performed to avoid network instability.

[1296] Server: The server saves received data to the database in real time. The saved data is time-stamped and managed centrally, including past data.

[1297] Specific example: At 6:00 AM, a device (sensor) measures temperature (25°C), humidity (60%), sunlight (30,000 lux), and moisture content (20%), and sends this data to the server 10 minutes later. The server stores this data in a database with a timestamp.

[1298] (2) Data analysis and prediction using generative AI

[1299] Server: The server retrieves historical environment data (e.g., the past 3 months) from the database and provides it to the generating AI. This allows for a comparison between historical and current data.

[1300] Server: The generating AI analyzes and predicts plant growing conditions and future environmental changes based on acquired data. The generating AI generates advice on appropriate growing conditions and management methods, and outputs it in text format.

[1301] Specific example: A server retrieves temperature, humidity, sunlight, and moisture content data for the past three months and provides it to a generating AI. The AI ​​determines that "the temperature is appropriate, but the moisture content is low, so 3 liters of watering is necessary" and generates this advice.

[1302] (3) Execution and control based on data prediction using generative AI

[1303] Server: Based on advice from the generating AI, it generates specific control commands (e.g., activate the watering system) and sends them to the corresponding terminal. This automatically performs appropriate environmental adjustments.

[1304] Terminal: The terminal operates the corresponding control device (e.g., watering system, lighting system, fertilizer spreader, etc.) according to the control commands received from the server.

[1305] User: Users access the system via smartphone or PC to check the control results. They verify that the execution was performed correctly and make additional manual adjustments as needed.

[1306] Specific example: Based on the advice of the AI, the server generates a command that says, "To achieve a moisture content of 30%, water with 3 liters of water." The terminal (watering system) receives this command and waters with 3 liters of water. The user checks the watering results on their smartphone and manually instructs the system to water additionally if necessary.

[1307] This system enables the real-time acquisition and effective utilization of environmental data, allowing even inexperienced individuals to perform optimal agricultural tasks.

[1308] The following describes the processing flow.

[1309] (1) Data collection using IoT

[1310] Step 1:

[1311] Terminals: Various sensors, such as temperature sensors, humidity sensors, solar radiation sensors, and soil moisture sensors, measure environmental data in each area.

[1312] Step 2:

[1313] Terminal: Temporarily stores measured environmental data in internal memory. For example, it records data such as temperature 25°C, humidity 60%, solar radiation 30,000 lux, and moisture content 20%.

[1314] Step 3:

[1315] Terminal: At regular intervals (e.g., every 10 minutes), it transmits measurement data to the server via a wireless communication module. Communication methods include Wi-Fi and LoRa.

[1316] Step 4:

[1317] Server: Validates received environmental data and stores it in the database with a timestamp. This ensures data integrity and consistency.

[1318] Specific example: At 6:00 AM, a sensor measures data showing a temperature of 25°C, humidity of 60%, solar radiation of 30,000 lux, and moisture content of 20%, and sends this data to the server at 6:10 AM. The server then stores this data in its database.

[1319] ---

[1320] (2) Data analysis and prediction using generative AI

[1321] Step 1:

[1322] Server: Retrieves environmental data from the database for a specified period (e.g., the past 3 months). The retrieved data includes temperature, humidity, solar radiation, and moisture content.

[1323] Step 2:

[1324] Server: Inputs acquired historical data and current environmental data into the generating AI and begins analysis.

[1325] Step 3:

[1326] Server: The generating AI analyzes the input data and evaluates the optimal conditions for plant growth. Parameters considered here include appropriate temperature range, water content, and light intensity.

[1327] Step 4:

[1328] Server: Based on the analysis results, the generating AI creates cultivation advice (e.g., "The water level is low, so 3 liters of watering is needed") and outputs it in text format.

[1329] Specific example: A server provides data from the past three months to an AI, which determines that "the temperature is appropriate, but there is insufficient moisture. Watering is necessary," and generates advice that 3 liters of watering are required.

[1330] ---

[1331] (3) Execution and control based on data prediction using generative AI

[1332] Step 1:

[1333] Server: Based on AI advice, it generates specific control commands. For example, it might generate a command to sprinkle 3 liters of water to achieve a moisture content of 30%.

[1334] Step 2:

[1335] Server: Sends the generated control commands to the corresponding terminals (watering systems, lighting systems, fertilizer spreaders, etc.).

[1336] Step 3:

[1337] Terminal: In accordance with the received control command, the watering system performs the corresponding action, such as spraying 3 liters of water.

[1338] Step 4:

[1339] User: Access the system from a smartphone or PC and check the control results. Make additional manual adjustments as needed.

[1340] Specific example: The server generates a control command to "water with 3 liters of water" and sends it to the terminal's watering system. The watering system automatically waters with 3 liters of water, and the user checks the watering results on their smartphone and manually instructs additional watering if necessary.

[1341] ---

[1342] This is a detailed explanation of the specific operations at each processing step of the system.

[1343] (Example 1)

[1344] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1345] The challenge lies in creating a system that collects, analyzes, and predicts environmental data in agriculture in real time, providing optimal growing conditions for plants. This will enable the provision of cultivation methods based on highly accurate information that could not be obtained with conventional methods. It is also necessary to address data transfer problems caused by network instability and reduce the burden of manual work performed by users.

[1346] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[1347] In this invention, the server includes a device for measuring environmental data, a device for transmitting the measured data to the server, a device for the server to store the transmitted data in a database, a device for the server to analyze past and present data using a generating AI, a device for the server to generate cultivation advice based on the analysis results, a device for generating control commands based on the generated cultivation advice, a device for transmitting the generated control commands to a corresponding control device, a device for the control device to operate according to the control commands, and a device for the user to confirm the operation results. This enables real-time data collection, analysis, and prediction in agriculture, allowing for the provision of optimal plant growing conditions and appropriate environmental adjustments.

[1348] "Environmental data" refers to numerical data that indicates the state of the surrounding environment in agriculture, such as temperature, humidity, solar radiation, and soil moisture content.

[1349] "Measuring devices" refer to sensors and measuring instruments used to collect environmental data.

[1350] "Transmitting device" refers to a communication device used to transfer measured environmental data to a server.

[1351] A "database" is a storage device that centrally manages information stored on a server and allows for searching and analysis as needed.

[1352] "Generative AI" refers to artificial intelligence that analyzes and predicts based on collected data, and then suggests optimal breeding conditions and management methods.

[1353] "Cultivation advice" refers to information provided in text format by a generating AI based on its analysis results, outlining the optimal growing conditions and management methods for plants.

[1354] A "control command" is an instruction sent to each control device based on the advice of the generated AI, providing specific operational instructions.

[1355] A "control device" refers to equipment or systems used to adjust the agricultural environment according to control commands received from a server.

[1356] A "device for checking operation results" refers to an interface device used by the user to check the execution results of the system and perform additional operations as needed.

[1357] "Buffering" is the process of temporarily storing data to avoid network instability and sending it when stable communication becomes possible.

[1358] SQL queries are structured query languages ​​used to retrieve specific information from databases.

[1359] This invention is a system that measures environmental data in agriculture in real time, analyzes and predicts the data using AI generation, generates appropriate cultivation advice and control commands, and automatically executes them. A specific embodiment of this system is described below.

[1360] (1) Data collection using IoT

[1361] Terminal: Multiple sensors (temperature sensors, humidity sensors, solar radiation sensors, soil moisture sensors) placed on farms and cultivation facilities measure environmental data for each area every 10 minutes. This ensures that the latest environmental information is always available.

[1362] Terminal: Measured environmental data is transmitted to the server via a communication module (e.g., LoRaWAN module) built into each sensor, over a stable network (e.g., Wi-Fi, 5G). Data transmission is performed periodically, and a certain amount of buffering is also performed to avoid network instability.

[1363] Server: The server saves received data in real time to a database (e.g., MySQL, PostgreSQL). The saved data is time-stamped and managed centrally, including past data.

[1364] Specific example: At 6:00 AM, a device (sensor) measures temperature (25°C), humidity (60%), sunlight (30,000 lux), and moisture content (20%), and sends this data to the server 10 minutes later. The server stores this data in a database with a timestamp.

[1365] (2) Data analysis and prediction using generative AI

[1366] Server: The server retrieves historical environment data (e.g., the past 3 months) from the database and provides it to the generating AI (e.g., GPT-4). This allows for a comparison between historical and current data.

[1367] Server: Based on data acquired by the generating AI, it analyzes and predicts plant growing conditions and future environmental changes. The generating AI generates advice on appropriate growing conditions and management methods, and outputs it in text format.

[1368] Specific example: A server retrieves temperature, humidity, sunlight, and moisture content data for the past three months and provides it to a generating AI. The AI ​​determines that "the temperature is appropriate, but the moisture content is low, so 3 liters of watering is necessary" and generates this advice.

[1369] (3) Execution and control based on data prediction using generative AI

[1370] Server: Based on advice from the generating AI, it generates specific control commands (e.g., activate the watering system) and sends them to the corresponding terminal. This automatically performs appropriate environmental adjustments.

[1371] Terminal: The terminal operates the corresponding control device (e.g., watering system, lighting system, fertilizer spreader, etc.) according to the control commands received from the server.

[1372] User: Users access the system via smartphone or PC to check the control results. They verify that the execution was performed correctly and make additional manual adjustments as needed.

[1373] Specific example: Based on the advice of the AI, the server generates a command that says, "To achieve a moisture content of 30%, water with 3 liters of water." The terminal (watering system) receives this command and waters with 3 liters of water. The user checks the watering results on their smartphone and manually instructs the system to water additionally if necessary.

[1374] Specific examples of input prompt sentences for generative AI models

[1375] Prompt: "Based on environmental data from the past three months, please advise on the current plant growing conditions. The data is as follows: Temperature (20°C, 22°C, 25°C), Humidity (50%, 55%, 60%), Sunlight (25,000 lux, 27,000 lux, 30,000 lux), Soil moisture (15%, 18%, 20%)."

[1376] This system enables the real-time acquisition and effective utilization of environmental data, allowing even inexperienced individuals to perform optimal agricultural work.

[1377] The flow of the specific processing in Example 1 will be explained using Figure 11.

[1378] Step 1: Measuring environmental data

[1379] Terminal: Multiple sensors (temperature sensors, humidity sensors, solar radiation sensors, soil moisture sensors) placed in the farm or cultivation facility measure environmental data for each area every 10 minutes. Specifically, the temperature sensor measures the current temperature as 25°C and stores this value in internal memory. This measurement data serves as input.

[1380] Step 2: Send

[1381] Terminal: Measured environmental data is transmitted to the server via a stable network (e.g., Wi-Fi, 5G) using a communication module (e.g., LoRaWAN module) built into each sensor. Data transmission occurs every 10 minutes, with a certain amount of buffering to avoid network instability. Specifically, the sensor measures temperature (25°C), humidity (60%), solar radiation (30,000 lux), and moisture content (20%), combines this data into a single packet, and sends it to the server. This transmitted data becomes the output.

[1382] Step 3: Receiving and saving data

[1383] Server: The server saves received data in real time to a database (e.g., MySQL, PostgreSQL). Saved data is timestamped, and past data is centrally managed. Specifically, the server saves received data using the "Insert into Database" command. This data is the input, and the saved data is the output.

[1384] Step 4: Obtaining historical data

[1385] Server: The server retrieves historical environment data (e.g., the past 3 months) from the database using SQL queries and provides it to the generating AI (e.g., GPT-4). Specifically, the server executes the SQL query "SELECT FROM environmentdata WHERE date > current date - INTERVAL 3 MONTH", formats the retrieved data, and inputs it into the generating AI. This retrieved data is the input.

[1386] Step 5: Data analysis and advice generation

[1387] Server: Based on data acquired by the generating AI, the server analyzes and predicts plant growing conditions and future environmental changes. The generating AI generates advice on appropriate growing conditions and management methods and returns it to the server in text format. Specifically, if the generating AI determines that "the temperature is appropriate, but the moisture level is low, so 3 liters of watering is necessary," it generates this advice. This analyzed data is the input, and the generated advice is the output.

[1388] Step 6: Generating control commands

[1389] Server: Based on advice from the generating AI, the server generates specific control commands (e.g., activating a watering system) and sends them to the corresponding terminal. Specifically, the server analyzes the advice from the generating AI and generates a command, "Water with 3 liters of water to bring the moisture level to 30%", and sends it to the terminal. This advice is the input, and the generated command is the output.

[1390] Step 7: Execute control commands

[1391] Terminal: The terminal operates the corresponding control device (e.g., watering system, lighting system, fertilizer spreader, etc.) according to the control commands received from the server. Specifically, the terminal (watering system) receives a command and activates its internal mechanism to spray 3 liters of water. This control command is the input, and the operation result of each device is the output.

[1392] Step 8: Check the execution results

[1393] User: The user accesses the system via smartphone or PC and checks the control results. Specifically, the user checks the system status on their smartphone to confirm whether watering was performed as scheduled. If necessary, they send a "manual additional watering" command to their terminal. The system's operation results are the input, and the user's confirmation and manual instructions are the output.

[1394] (Application Example 1)

[1395] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1396] Traditional factory production management and environmental control often involve manual processes, leading to inefficiencies and a lack of optimization. Furthermore, real-time monitoring of multiple environmental factors (temperature, humidity, vibration, etc.) and immediate control based on that information are difficult, potentially resulting in problems with production efficiency and quality control. Therefore, the challenge lies in providing new methods to improve production efficiency and optimize quality control.

[1397] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[1398] In this invention, the server includes means for measuring environmental data, means for transmitting the measured data to the server, means for the server to store the transmitted data in a database, means for the server to analyze past and present data using a generating AI, means for the server to generate production advice based on the analysis results, means for generating control commands based on the generated production advice, means for transmitting the control commands to a corresponding automated device, means for the automated device to operate according to the control commands, and means for the user to confirm the operation results. This enables real-time monitoring and immediate control of environmental data, making it possible to optimize production efficiency and quality control.

[1399] "Environmental data" refers to data that measures information about the working environment in a factory in real time, such as temperature, humidity, vibration, and illuminance.

[1400] A "server" is a device or system that receives measured environmental data, stores it in a database, and performs analysis and prediction using generating AI.

[1401] A "database" is a digital storage system in which environmental data sent to a server is stored with timestamps and centrally managed.

[1402] "Generative AI" refers to artificial intelligence that performs analysis and prediction based on past and current environmental data, and is used to generate production advice and control commands.

[1403] "Production advice" refers to the process where the generating AI analyzes environmental data and provides specific advice in text format to optimize production efficiency and quality control.

[1404] A "control command" is an instruction sent to automated equipment based on generated production advice, and it is an executable command to adjust the environment and work content.

[1405] "Automated equipment" refers to mechanical devices and robots that operate according to control commands, and is used for environmental adjustment and production work within factories.

[1406] A "user" is a person who accesses the system to check its operation results and make additional adjustments as needed.

[1407] This invention is a system that improves production efficiency and quality control by measuring environmental data within a factory in real time and analyzing and predicting it using generated AI. The specific forms for implementing this system are described below.

[1408] First, temperature sensors, humidity sensors, vibration sensors, and illuminance sensors are installed in each area of ​​the factory. These sensors measure environmental data every 10 minutes. The measured data is transmitted to a server via a stable network through a communication module built into each sensor. Data transmission is performed periodically, and a certain amount of buffering is also performed to avoid network instability.

[1409] The server saves received data to a database in real time. The saved data is time-stamped and managed centrally, including historical data. The server retrieves historical environmental data (e.g., the past three months) from the database and provides it to the generating AI. This allows for a comparison between historical and current data.

[1410] The generating AI analyzes and predicts conditions related to production efficiency and quality control, as well as future environmental changes, based on the acquired data. The generating AI generates advice on appropriate production conditions and management methods, and outputs it in text format. For example, if a server acquires temperature, humidity, vibration, and illuminance data for the past three months and provides it to the generating AI, the generating AI might determine that "the temperature is too high and the cooling system needs to be activated" and generate this advice.

[1411] Based on the advice of the generated AI, the server generates specific control commands (e.g., activate the cooling system) and sends them to the corresponding automated equipment. This automatically performs appropriate environmental adjustments. The automated equipment then operates the corresponding control devices (e.g., cooling system, humidification system, vibration damping device, etc.) according to the control commands received from the server.

[1412] Users access the system via smartphones or PCs to check the control results. They verify that the execution was performed correctly and make additional manual adjustments as needed.

[1413] As a concrete example, a server acquires temperature, humidity, vibration, and illuminance data for the past three months and provides it to a generating AI. The AI ​​determines that "the temperature is too high and the cooling system needs to be activated" and generates this advice. Based on the AI's advice, the server generates a command to "activate the cooling system." The terminal (cooling system) receives this command and activates the system. The user checks the cooling results on their smartphone and manually instructs additional cooling if necessary.

[1414] Examples of prompts to input into a generative AI model:

[1415] Generate advice for improving production efficiency based on environmental data (temperature, humidity, vibration, illuminance). Past data is as follows: Temperature: 25°C, Humidity: 60%, Vibration: 1.2, Illuminance: 420. Current data is as follows: Temperature: 28°C, Humidity: 55%, Vibration: 2.0, Illuminance: 460.

[1416] In this way, real-time monitoring and immediate control of environmental data become possible, enabling the optimization of production efficiency and quality control.

[1417] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[1418] Step 1:

[1419] The terminal uses sensors placed in various areas of the factory to measure environmental data (temperature, humidity, vibration, illuminance, etc.) every 10 minutes.

[1420] Input: Real-time environmental data obtained from each sensor

[1421] Output: Measured environmental data

[1422] Specific operation: The sensor detects the surrounding environment and generates data as digital information.

[1423] Step 2:

[1424] The terminal transmits the measured data to the server via its built-in communication module.

[1425] Input: Measured environmental data

[1426] Output: Data to send to the server

[1427] Specific operation: The communication module receives the data generated by the sensor and sends it to the server via the network.

[1428] Step 3:

[1429] The server saves the received data to the database in real time.

[1430] Input: Submitted environmental data

[1431] Output: Data stored in the database (with timestamp)

[1432] Specific operation: The server parses the received data and adds a timestamp when saving it to the database system (e.g., MySQL or PostgreSQL).

[1433] Step 4:

[1434] The server retrieves historical environmental data from the database and provides it to the generating AI along with current data.

[1435] Input: Historical and current environmental data

[1436] Output: Data provided to the generating AI

[1437] Specific operation: The server executes a database query to extract historical data, combines it with current data, and passes it to the generating AI.

[1438] Step 5:

[1439] The generating AI analyzes the provided data to determine the conditions for production efficiency and quality control, and then generates advice.

[1440] Input: Historical and current environmental data

[1441] Output: Production advice (text format)

[1442] Specific operation: A generative AI model (e.g., using TensorFlow or PyTorch) analyzes the data and outputs appropriate advice in text format.

[1443] Step 6:

[1444] Based on the advice of the generating AI, the server generates specific control commands and sends them to the corresponding automated equipment.

[1445] Input: AI-generated advice

[1446] Output: Control command

[1447] Specific operation: The server analyzes the advice and generates specific operational instructions (e.g., a command to start the cooling system).

[1448] Step 7:

[1449] The automated equipment performs the corresponding action according to the control commands received from the server.

[1450] Input: Control command

[1451] Output: Actions performed

[1452] Specific operation: Based on the commands received by the automated equipment (e.g., cooling system), it performs physical actions (cooling, humidifying, vibration damping, etc.).

[1453] Step 8:

[1454] Users access the system via smartphones or PCs to check the control results.

[1455] Input: Execution result data

[1456] Output: User confirmation and additional instructions as needed.

[1457] Specific operation: Users monitor the execution results via smartphone or PC applications and make additional manual adjustments if necessary.

[1458] This enables a system where environmental data from each sensor is collected and analyzed on a server in real time, and automated equipment is immediately controlled based on optimal advice generated by AI.

[1459] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[1460] This invention relates to a system that measures environmental data in agriculture in real time, analyzes and predicts it using generative AI, generates appropriate cultivation advice and control commands, and automatically executes them. Furthermore, by combining it with an emotion engine that recognizes user emotions, it is an advanced system that includes user emotional feedback. The following describes the configuration for implementing this system.

[1461] (1) Data collection using IoT

[1462] Terminal: Multiple sensors (temperature sensors, humidity sensors, solar radiation sensors, soil moisture sensors, etc.) placed on farms and cultivation facilities measure environmental data for each area in real time every 10 minutes. This ensures that the latest environmental information is always available.

[1463] Terminal: Measured environmental data is transmitted to the server via a communication module built into each sensor, over a stable network. Data transmission is performed periodically, and a certain amount of buffering is also performed to avoid network instability.

[1464] Server: The server saves received data to the database in real time. The saved data is time-stamped and managed centrally, including past data.

[1465] Specific example: At 6:00 AM, a sensor measures temperature (25°C), humidity (60%), sunlight (30,000 lux), and moisture content (20%), and sends this data to the server 10 minutes later. The server stores this data in a database with a timestamp.

[1466] (2) Data analysis and prediction using generative AI

[1467] Server: The server retrieves historical environment data (e.g., the past 3 months) from the database and provides it to the generating AI. This allows for a comparison between historical and current data.

[1468] Server: The generating AI analyzes and predicts plant growing conditions and future environmental changes based on acquired data. The generating AI generates advice on appropriate growing conditions and management methods, and outputs it in text format.

[1469] Specific example: A server retrieves temperature, humidity, sunlight, and moisture content data for the past three months and provides it to a generating AI. The AI ​​determines that "the temperature is appropriate, but the moisture content is low, so 3 liters of watering is necessary" and generates this advice.

[1470] (3) Execution and control based on data prediction using generative AI

[1471] Server: Based on AI advice, it generates specific control commands. For example, it might generate a command to sprinkle 3 liters of water to achieve a moisture content of 30%.

[1472] Server: Sends the generated control commands to the corresponding terminals (watering systems, lighting systems, fertilizer spreaders, etc.).

[1473] Terminal: In accordance with the received control command, the watering system performs the corresponding action, such as spraying 3 liters of water.

[1474] User: Access the system from a smartphone or PC and check the control results. Verify that the execution was performed correctly and make any necessary manual adjustments.

[1475] Specific example: The server generates a control command to "water with 3 liters of water" and sends it to the terminal's watering system. The watering system automatically waters with 3 liters of water, and the user checks the watering results on their smartphone and manually instructs additional watering if necessary.

[1476] (4) Recognition and feedback of user emotions by the emotion engine

[1477] User: Communicates emotional information (e.g., satisfaction, dissatisfaction, questions, etc.) to the system through facial expressions, voice, and input actions during operation.

[1478] Device: Uses cameras, microphones, sensors, etc. to capture the user's emotional state in real time and sends it to the emotion engine for analysis.

[1479] Server: The emotion engine processes this data and analyzes the user's emotional state. For example, if the user is expressing dissatisfaction, the emotion engine detects this and provides appropriate feedback.

[1480] Server: Based on the analysis results from the emotion engine, the generating AI adjusts the content of training advice and control commands. For example, if the user feels that things are not going well, the advice can be made more detailed.

[1481] User: Gain feedback and continue using the system. This improves the user experience and promotes the effective use of the system.

[1482] Specific example: A camera captures a user's dissatisfaction with the watering system's results, and an emotion engine recognizes the user's dissatisfaction. The server then provides more detailed advice for the next watering, resolving the user's dissatisfaction.

[1483] This system enables the real-time acquisition and effective utilization of environmental data, allowing even inexperienced individuals to perform optimal agricultural tasks. Furthermore, by incorporating user emotional feedback, it enables more detailed and personalized support.

[1484] The following describes the processing flow.

[1485] (1) Data collection using IoT

[1486] Step 1:

[1487] Terminals: Various sensors (temperature sensors, humidity sensors, solar radiation sensors, soil moisture sensors, etc.) measure environmental data in each area of ​​the farm or cultivation facility.

[1488] Step 2:

[1489] Terminal: Temporarily stores measured environmental data in internal memory. For example, it records data such as temperature 25°C, humidity 60%, solar radiation 30,000 lux, and moisture content 20%.

[1490] Step 3:

[1491] Terminal: Every 10 minutes, it sends measurement data to the server via a wireless communication module (e.g., Wi-Fi, LoRa).

[1492] Step 4:

[1493] Server: Validates received environmental data and stores it in the database with a timestamp. This ensures data integrity and consistency.

[1494] Specific example: At 6:00 AM, a sensor measures temperature at 25°C, humidity at 60%, solar radiation at 30,000 lux, and moisture content at 20%, and sends this data to a server 10 minutes later. The server then stores this data in a database.

[1495] ---

[1496] (2) Data analysis and prediction using generative AI

[1497] Step 1:

[1498] Server: Retrieves environmental data from the database for a specified period (e.g., the past 3 months). The retrieved data includes temperature, humidity, solar radiation, and moisture content.

[1499] Step 2:

[1500] Server: Inputs acquired historical data and current environmental data into the generating AI and begins analysis.

[1501] Step 3:

[1502] Server: The generating AI analyzes the input data and evaluates the optimal conditions for plant growth. Parameters considered here include appropriate temperature range, water content, and light intensity.

[1503] Step 4:

[1504] Server: Based on the analysis results, the generating AI creates cultivation advice (e.g., "The water level is low, so 3 liters of watering is needed") and outputs it in text format.

[1505] Specific example: A server provides the AI ​​with data from the past three months, and the AI ​​determines that "the temperature is appropriate, but there is insufficient moisture, so watering is necessary," and generates advice that 3 liters of watering are required.

[1506] ---

[1507] (3) Execution and control based on data prediction using generative AI

[1508] Step 1:

[1509] Server: Based on AI advice, it generates specific control commands, such as spraying 3 liters of water to achieve a 30% moisture level.

[1510] Step 2:

[1511] Server: Sends the generated control commands to the corresponding terminals (e.g., watering system, lighting system, fertilizer spreader).

[1512] Step 3:

[1513] Terminal: It performs the corresponding action (e.g., the watering system sprays 3 liters of water) according to the control command received.

[1514] Step 4:

[1515] User: Access the system from a smartphone or PC and check the control results. Make additional manual adjustments as needed.

[1516] Specific example: The server generates a control command to "water with 3 liters of water" and sends it to the terminal's watering system. The watering system automatically waters with 3 liters of water, and the user checks the watering results on their smartphone and manually instructs additional watering if necessary.

[1517] ---

[1518] (4) Recognition and feedback of user emotions by the emotion engine

[1519] Step 1:

[1520] User: Communicates emotional information (e.g., satisfaction, dissatisfaction, questions, etc.) to the system through facial expressions, voice, and input actions during operation.

[1521] Step 2:

[1522] Device: Uses cameras, microphones, sensors, etc. to capture the user's emotional state in real time and transmits it to the emotion engine.

[1523] Step 3:

[1524] Server: The emotion engine processes this data and analyzes the user's emotional state (e.g., joy, anger, surprise, etc.).

[1525] Step 4:

[1526] Server: Based on the analysis results of the emotion engine, the generating AI adjusts the content of training advice and control commands. For example, if the user indicates "dissatisfaction," the server will take measures such as making the training advice more detailed.

[1527] Step 5:

[1528] User: Gain feedback and continue using the system. This improves the user experience and ensures the system is used effectively.

[1529] Specific example: A camera captures a user's dissatisfaction with the watering system's results, and an emotion engine recognizes the user's dissatisfaction. The server then refines the next care advice to address the user's dissatisfaction.

[1530] ---

[1531] In this way, a system that combines an emotion engine enables real-time acquisition and effective utilization of environmental data, allowing even inexperienced individuals to perform optimal agricultural tasks. Furthermore, by incorporating emotional feedback from users, even more advanced support becomes possible.

[1532] (Example 2)

[1533] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1534] Conventional agricultural management systems struggled with real-time environmental data collection and its effective utilization, resulting in insufficient provision of appropriate cultivation advice and adequate automated control. Furthermore, systems lacked the ability to incorporate user emotional feedback, leaving challenges in improving the user experience.

[1535] The identification processing by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes a device for measuring environmental data, a device for transmitting the measured data to the server via a communication module, a device for the server to store the transmitted data in a database, a device for the server to analyze past and present data using a generating AI, a device for the server to generate training advice based on the analysis results, a device for generating control commands based on the generated training advice, a device for transmitting the control commands to a corresponding control device, a device for the control device to operate according to the control commands, a device for the user to confirm the operation results, an emotion engine that recognizes the user's emotions and provides feedback, and a device for the generating AI to adjust advice and control commands based on the analysis results of the emotion engine. This enables real-time collection and analysis of environmental data, provision of appropriate training advice, and automatic control, as well as advanced support that reflects the user's emotional feedback.

[1536] "Environmental data" refers to data that represents the environmental conditions of agricultural and cultivation facilities, such as temperature, humidity, solar radiation, and soil moisture content.

[1537] A "measuring device" is a device used to measure environmental data in real time, such as temperature sensors, humidity sensors, solar radiation sensors, and soil moisture sensors.

[1538] A "communication module" is a device that provides a means of communication for transmitting data from a measuring device to a server.

[1539] A "server" is a computer system used to store, manage, and analyze received environmental data.

[1540] A "database" is a system that stores measured data with timestamps and manages it centrally with past data.

[1541] "Generative AI" is an artificial intelligence system that analyzes measured data and historical data to predict and suggest plant growth conditions and management methods.

[1542] "Cultivation advice" refers to instructions on the optimal growing conditions and management methods for plants, generated by the AI ​​based on its analysis results.

[1543] A "control command" is a command that includes specific work instructions, generated based on the training advice for the generated AI.

[1544] A "control device" is a device that performs a specific action according to a control command, such as a watering system, lighting system, or fertilizer spreader.

[1545] An "emotion engine" is a system that analyzes the user's facial expressions, voice, and input actions during operation to recognize their emotional state and provide feedback.

[1546] A "user" is an agricultural worker or system user who operates the system, checks the control results, and makes manual adjustments as needed.

[1547] This invention is a system that measures environmental data in agriculture in real time, analyzes and predicts it using a generation AI, generates appropriate cultivation advice and control commands, and automatically executes them. Furthermore, by combining it with an emotion engine that recognizes the user's emotions, it is a system that provides advanced support that reflects the user's emotional feedback.

[1548] (1) Data collection using IoT

[1549] Terminals: Temperature sensors, humidity sensors, solar radiation sensors, soil moisture sensors, and other devices placed on farms and cultivation facilities measure environmental data in real time. These sensors measure data every 10 minutes and transmit it to the server via a communication module built into each sensor. Buffering is performed during transmission to maintain network stability.

[1550] Server: The server stores the received data in a database. The stored data is time-stamped and centrally managed with past data. For example, at 6 AM, the temperature sensor measures 25°C, the humidity sensor measures 60%, the solar radiation sensor measures 30,000 lux, and the soil moisture sensor measures 20%, and these data are sent to the server every 10 minutes. The server stores this data in the database with timestamps.

[1551] (2) Data analysis and prediction using generative AI

[1552] Server: The server retrieves historical environmental data (e.g., the past 3 months) from the database and provides it to the generating AI. The generating AI compares and analyzes the historical and current data to predict plant growing conditions and future environmental changes. Based on the analysis results, the generating AI generates cultivation advice in text format.

[1553] Specific example: A server retrieves temperature, humidity, sunlight, and moisture content data for the past three months and provides it to the generating AI. The AI ​​determines that "the temperature is appropriate, but the moisture content is low, so 3 liters of watering is necessary" and generates this advice.

[1554] (3) Execution and control based on data prediction using generative AI

[1555] Server: Based on the advice of the generating AI, it generates specific control commands. For example, it generates a command such as "Water with 3 liters of water to bring the moisture level to 30%."

[1556] Server: Sends the generated control commands to the corresponding control devices (e.g., watering systems, lighting systems, fertilizer spreaders).

[1557] Terminal: A control device operates according to the control commands it receives and performs the instructed task. For example, a watering system automatically sprays 3 liters of water.

[1558] User: Accesses the system from a smartphone or PC and checks the control results. They verify the accuracy of the results and make manual adjustments as needed. The server generates a control command, "Spray 3 liters of water," and sends it to the terminal's watering system. The watering system automatically sprays 3 liters of water, and the user checks the results on their smartphone and manually instructs additional watering if necessary.

[1559] (4) Recognition and feedback of user emotions by the emotion engine

[1560] User: Communicates emotional information (e.g., satisfaction, dissatisfaction, questions) to the system through facial expressions, voice, and input actions during operation.

[1561] Device: Uses cameras, microphones, and sensors to capture the user's emotional state in real time and sends it to the emotion engine for analysis.

[1562] Server: The emotion engine processes this data and analyzes the user's emotional state. If the user is expressing dissatisfaction, the emotion engine detects this and provides appropriate feedback.

[1563] Server: Based on the analysis results of the emotion engine, the generated AI adjusts the content of training advice and control commands. For example, if the user feels that things are not going well, the advice can be made more detailed.

[1564] User: By receiving feedback and continuing to operate the system, the user experience improves and the effective use of the system is promoted. The camera captures when the user is dissatisfied with the results of the watering system, and the emotion engine recognizes the feeling of dissatisfaction. The server provides more detailed advice for the next watering, resolving the user's dissatisfaction.

[1565] Example of a prompt

[1566] "Please analyze the optimal growing conditions based on temperature, humidity, sunlight, and moisture content data from the past three months."

[1567] "If users express dissatisfaction, please provide detailed training advice for the next session."

[1568] The flow of the specific processing in Example 2 will be explained using Figure 13.

[1569] The program's processing flow is explained in detail, broken down into steps.

[1570] Step 1:

[1571] (Data collection)

[1572] Terminal: Sensors (temperature sensors, humidity sensors, solar radiation sensors, soil moisture sensors, etc.) placed on farms and cultivation facilities measure various environmental data every 10 minutes. The input is the environmental parameters measured by the sensors (e.g., temperature, humidity, solar radiation, moisture content), and the output is the measured environmental data. This data is transmitted to the server via the terminal's communication module.

[1573] Specific operation: At 6:00 AM, the temperature sensor measures 25°C, the humidity sensor measures 60%, the solar radiation sensor measures 30,000 lux, and the soil moisture sensor measures 20%. This data is sent to the server every 10 minutes.

[1574] Step 2:

[1575] (Data saving)

[1576] Server: Receives environmental data and stores it in a database. Input is measurement data sent from the terminal, and output is environmental data stored in the database. The data is timestamped, and past data is managed centrally.

[1577] Specific operation: After measurement data arrives at the server, the server adds a timestamp and saves it to the database. For example, a timestamp is added to data received every 10 minutes and recorded in the database.

[1578] Step 3:

[1579] (Data analysis and prediction)

[1580] Server: Retrieves environmental data for the past three months from the database and provides it to the generating AI. The input is environmental data for the past three months, and the output is the analysis results and cultivation advice from the generating AI. The generating AI compares and analyzes past and current data to predict plant cultivation conditions and environmental changes.

[1581] Specific operation: The server provides the generating AI with temperature, humidity, solar radiation, and moisture content data for the past three months. Based on this data, the generating AI creates cultivation advice such as, "The temperature is appropriate, but the moisture content is low, so 3 liters of watering is needed."

[1582] Step 4:

[1583] (Generating control commands)

[1584] Server: Generates specific control commands based on advice from the generating AI. The input is advice from the generating AI, and the output is a specific control command. For example, it generates a command such as "Water with 3 liters of water to bring the moisture level to 30%."

[1585] Specific operation: Based on the advice of the generating AI, the server generates a control command to "spray 3 liters of water" and sends it to the corresponding control device (watering system).

[1586] Step 5:

[1587] (Execution of control commands)

[1588] Terminal: A control device receives control commands from the server and performs actions according to the instructions. The input is the control command sent from the server, and the output is the actual action (e.g., watering, adjusting lighting, spreading fertilizer).

[1589] Specific operation: The terminal's watering system receives a command to "water with 3 liters" and automatically waters with 3 liters of water as instructed.

[1590] Step 6:

[1591] (Checking the results)

[1592] User: Access the system from a smartphone or PC and check the execution results. Input is the operation result of the control device, and output is the execution result displayed to the user. Additional manual adjustments can be made as needed.

[1593] Specific operation: The user checks the watering results on their smartphone and manually instructs additional watering if necessary.

[1594] Step 7:

[1595] (Emotion recognition and feedback)

[1596] User: Provides emotional information through facial expressions, voice, and input actions during operation. Input is the user's emotional information, and output is data sent to the emotion engine.

[1597] Device: Uses cameras, microphones, and sensors to capture the user's emotional state and sends it to the emotion engine.

[1598] Specific operation: The camera captures the user's facial expressions, the microphone collects audio, and these are sent to the emotion engine.

[1599] Step 8:

[1600] (Emotional analysis and adjustment of advice)

[1601] Server: The emotion engine analyzes the user's emotional state and provides information to the generating AI. The generating AI adjusts the content of advice and control commands based on the analysis results. The input is the user's emotional information and the aforementioned data, and the output is the adjusted advice and control commands.

[1602] Specific operation: The emotion engine recognizes that the user is not satisfied with the results of the watering system, and the server provides more detailed advice for the next cultivation.

[1603] (Application Example 2)

[1604] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1605] Environmental management in modern agriculture and factories is an extremely complex and labor-intensive task, requiring efficient and accurate responses. However, current systems struggle with real-time, appropriate control because the collection, analysis, and control of environmental data are fragmented. Furthermore, there is no mechanism to acquire and incorporate user emotional feedback into the system, resulting in a lack of improvement in the user experience. To solve these problems, it is essential to manage environmental data in real time, generate appropriate advice and control commands using generative AI, and incorporate user emotional data into the system.

[1606] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[1607] In this invention, the server includes means for measuring environmental data, means for transmitting the measured data to the server, means for the server to store the transmitted data in a database, means for the server to analyze past and present data using a generating AI, means for the server to generate training advice based on the analysis results, means for generating control commands based on the generated training advice, means for transmitting the control commands to a corresponding control device, means for the control device to operate according to the control commands, means for the user to confirm the operation results, means for collecting emotional data, means for recognizing the user's emotions based on the emotional data, and means for adjusting the training advice and control commands based on the recognized emotions. This enables real-time management of environmental data and improvement of the user experience.

[1608] "Environmental data" refers to information about the environment in agriculture and factories, such as temperature, humidity, solar radiation, and soil moisture.

[1609] A "server" is a computer system that receives and stores measured environmental data and uses generated AI to analyze and predict the data.

[1610] A "database" is a data storage system for efficiently saving and managing measured environmental data and historical data.

[1611] "Generative AI" is artificial intelligence that analyzes collected data and generates training advice and control commands based on the analysis results.

[1612] A "control command" is an instruction created by the generating AI and sent to the corresponding control device, which then performs a specific action.

[1613] A "control device" is a device or equipment that takes specific actions based on control commands sent from a server.

[1614] "Emotional data" refers to information about emotions obtained through facial expressions, voice, input actions, etc., acquired during user interaction.

[1615] An "emotion engine" is an artificial intelligence system that analyzes emotional data and recognizes the user's current emotional state.

[1616] "Cultivation advice" refers to suggestions regarding the optimal cultivation conditions and management methods for plants and other objects, derived from the results of analysis and predictions performed by the generating AI based on environmental data.

[1617] This invention relates to a system that measures environmental data in a factory in real time, analyzes and predicts it using generative AI, generates appropriate management advice and control commands, and automatically executes them. Furthermore, by incorporating an emotion engine that recognizes user emotions, it is an advanced system that includes user emotional feedback. The following describes the configurations for implementing this system.

[1618] (1) Collection of environmental data

[1619] Terminal: Multiple sensors (temperature sensors, humidity sensors, machine operation status sensors, etc.) placed throughout the factory measure environmental data in each area in real time every 10 minutes. This ensures that the latest environmental information is always available.

[1620] Terminal: Measured environmental data is transmitted to the server via a communication module built into each sensor, over a stable network. Data transmission is performed periodically, and a certain amount of buffering is also performed to avoid network instability.

[1621] Server: The server saves received data to the database in real time. The saved data is time-stamped and managed centrally, including past data.

[1622] Specific example: At 6:00 AM, a sensor measures temperature (25°C), humidity (60%), and machine status (normal), and sends this data to the server 10 minutes later. The server stores this data in a database with a timestamp.

[1623] (2) Data analysis and prediction using generative AI

[1624] Server: The server retrieves historical environment data (e.g., the past 3 months) from the database and provides it to the generating AI. This allows for a comparison between historical and current data.

[1625] Server: The generating AI analyzes and predicts optimal operating conditions and future environmental changes within the factory based on acquired data. The generating AI generates advice on appropriate management conditions and control methods, and outputs it in text format.

[1626] Specific example: A server retrieves data on temperature, humidity, and machine operating status for the past three months and provides it to a generating AI. The AI ​​determines that "the temperature is appropriate, but the humidity is low, so the humidifier needs to be turned on," and generates this advice.

[1627] (3) Execution and control based on data prediction using generative AI

[1628] Server: Based on AI advice, it generates specific control commands. For example, it generates a command to activate a humidifier to set the humidity to 50%.

[1629] Server: Sends the generated control commands to the corresponding control devices (humidifiers, air conditioning systems, inspection robots, etc.).

[1630] Terminal: It performs the corresponding action, such as activating a humidifier, according to the control command it receives.

[1631] User: Access the system from a smartphone or computer and check the control results. Verify that the execution was performed correctly and make any necessary manual adjustments.

[1632] Specific example: The server generates a control command to "start the humidifier" and sends it to the humidifier on the terminal. The humidifier operates automatically, and the user checks the operation results on their smartphone and manually instructs it to operate additionally if necessary.

[1633] (4) Recognition and feedback of user emotions by the emotion engine

[1634] User: Communicates emotional information (e.g., satisfaction, dissatisfaction, questions, etc.) to the system through facial expressions, voice, and input actions during operation.

[1635] Device: Uses cameras, microphones, sensors, etc. to capture the user's emotional state in real time and sends it to the emotion engine for analysis.

[1636] Server: The emotion engine processes this data and analyzes the user's emotional state. For example, if the user is expressing dissatisfaction, the emotion engine detects this and provides appropriate feedback.

[1637] Server: Based on the analysis results from the emotion engine, the generating AI adjusts the content of management advice and control commands. For example, if the user feels that things are not going well, the advice can be made more detailed.

[1638] User: Gain feedback and continue using the system. This improves the user experience and promotes the effective use of the system.

[1639] Specific example: A camera captures a user's dissatisfaction with the humidifier's performance, and an emotion engine recognizes the user's dissatisfaction. The server then provides more detailed management advice for the next time, resolving the user's dissatisfaction.

[1640] Example prompt statements

[1641] Over the past three months, the average temperature was 25°C, the average humidity was 50%, and the machine operated normally 90 out of 100 times, with abnormalities detected 5 times. Based on this, we propose future management methods.

[1642] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[1643] Step 1: Collect environmental data

[1644] Input: Data from temperature sensors, humidity sensors, and machine operating status sensors.

[1645] Operation: The terminal uses sensors placed throughout the factory to measure temperature, humidity, and machine operating status data in real time.

[1646] Data processing: The measured data is buffered through a communication module built into each sensor.

[1647] Output: A set of measured environmental data (e.g., temperature 25°C, humidity 60%, machine condition normal).

[1648] Step 2: Send

[1649] Input: Environmental data measured from sensors.

[1650] Operation: The device sends data obtained from the sensor to the server every 10 minutes.

[1651] Data processing: Data is transmitted over the network after a timestamp is added.

[1652] Output: Environment data with a timestamp is sent to the server.

[1653] Step 3: Save data

[1654] Input: Submitted environmental data.

[1655] Operation: The server saves the received data to the database.

[1656] Data processing: The server centrally manages the database, including historical data.

[1657] Output: Timestamped environment data stored in the database.

[1658] Step 4: Data Analysis and Prediction

[1659] Input: Past and present environment data stored in the database.

[1660] Operation: The server retrieves data from the database for the past three months and provides it to the generating AI.

[1661] Data processing: Generative AI compares and analyzes historical and current data to predict optimal management conditions and future environmental changes.

[1662] Output: Advice text (e.g., "The temperature is appropriate, but the humidity is low, so you need to run the humidifier.").

[1663] Step 5: Generating control commands

[1664] Input: Advice from the generating AI.

[1665] Operation: The server generates specific control commands based on advice from the generating AI.

[1666] Data calculation: Based on the advice provided, generate commands to operate the target device (e.g., humidifier).

[1667] Output: Control command (e.g., "Start the humidifier").

[1668] Step 6: Sending control commands

[1669] Input: Generated control command.

[1670] Operation: The server sends the generated control commands to the corresponding control unit.

[1671] Data processing: Send commands to the corresponding terminal via the network.

[1672] Output: Control commands received by the control device.

[1673] Step 7: Operation of the control unit

[1674] Input: Received control command.

[1675] Operation: The terminal allows the corresponding device (e.g., humidifier) ​​to perform actions according to the control commands it receives.

[1676] Data calculation: Adjusts the target environment (e.g., humidity) based on the command content.

[1677] Output: The result of the executed command (e.g., the humidifier is running).

[1678] Step 8: Check the results

[1679] Input: The result of the operation performed by the control device.

[1680] Operation: Users access the system via smartphone or PC to check the operation results of the control unit.

[1681] Data calculation: Evaluate the execution results and make additional manual adjustments as needed.

[1682] Output: User's operational verification results (e.g., checking the humidifier's operating status on a smartphone).

[1683] Step 9: Collecting emotional data

[1684] Input: User's facial expressions, voice, and input actions during operation.

[1685] Operation: The device captures the user's emotional state through the camera and microphone and sends it to the emotion engine for analysis.

[1686] Data processing: Captured emotion data is transmitted in real time.

[1687] Output: A set of emotion data (e.g., emotion of dissatisfaction).

[1688] Step 10: Emotion Recognition and Feedback

[1689] Input: Sentiment data.

[1690] Operation: The server analyzes the user's emotional state using an emotion engine.

[1691] Data processing: Based on recognized emotions, the generating AI adjusts the content of training advice and control commands.

[1692] Output: Adjusted advice or commands (e.g., make the next advice more detailed).

[1693] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the dat...

Claims

1. Means for measuring environmental data, Means for transmitting the measured data to a server, The server provides means for storing the transmitted data in a database, The aforementioned server has means for analyzing historical and current data using generating AI, The server provides means for generating training advice based on the analysis results, Means for generating control commands based on the generated training advice, means for transmitting the control command to the corresponding control device, The control device includes means for operating in accordance with the control command, A means for the user to confirm the results of the operation, A system that includes this.

2. The system according to claim 1, wherein the control command includes means for controlling at least one of watering, sunlight, and fertilizer application.

3. The system according to claim 1, which includes means for the generating AI to predict the optimal growing conditions for plants.

Images