System

Abstract

A system is provided.SOLUTION: A system comprising: means for collecting environmental information; means for transmitting the environmental information; means for generating an indication of an environmental adjustment using a generation AI based on the environmental information; means for receiving the indication; and means for adjusting the environmental based on the indication.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] Describe the "problem that the invention aims to solve" and the "means for solving the problem."

[0005] In conventional aquaculture systems, environmental adjustments are often performed manually, resulting in inefficiency and difficulty in accurate environmental management. In particular, when fine adjustments to water quality or temperature are required, immediate response is not possible, leading to problems such as stress on the organisms and reduced production efficiency. Furthermore, analyzing the collected data requires specialized knowledge, necessitating the intervention of experts, which increases operational costs. [Means for solving the problem]

[0006] The present invention solves the above-mentioned problems by providing a system including a means for collecting environmental data, a means for transmitting the environmental data, a means for generating instructions for environmental adjustment using a generation AI based on the environmental data, a means for receiving the instructions, and a means for adjusting the environment based on the instructions. Furthermore, by including a means for checking the state after environmental adjustment and transmitting feedback to the generation AI, automatic adjustment and optimization of the environment can be continuously performed. Furthermore, since the environmental data includes water temperature, pH level, and dissolved oxygen, it is possible to comprehensively manage the major environmental factors required for aquaculture. This allows efficient and accurate management of the aquaculture environment without specialized knowledge, thereby reducing operating costs and improving production efficiency.

[0007] "Environmental Data" means data collected to indicate the state of the aquaculture environment, including water temperature, pH level, dissolved oxygen, etc.

[0008] "Means of collection" refers to the function of acquiring environmental data using sensors, data acquisition devices, etc.

[0009] "Transmitting means" refers to a function for transmitting collected environmental data to another device or system via a communication means.

[0010] "Generative AI" refers to artificial intelligence that analyzes collected environmental data and generates appropriate instructions for adjusting the environment based on the results of that analysis.

[0011] "Means for generating" refers to the ability of the generative AI to analyze and generate instructions.

[0012] "Means for receiving" refers to a function for receiving instructions sent from a server or other device.

[0013] "Means for adjusting the environment" refers to a device or system that has the function of physically adjusting the water temperature, pH level, etc. of the aquaculture environment based on instructions received.

[0014] "Means for sending feedback" refers to the function of sending the adjusted environmental data back to the server or generating AI, allowing for continuous data exchange.

[0015] "Water temperature" is an environmental data item that indicates the temperature of the water, and is an important element of the aquaculture environment.

[0016] "pH level" is a numerical value that indicates the acidity or alkalinity of water, and is an important factor in managing the water quality in aquaculture environments.

[0017] "Dissolved oxygen" is a numerical value that indicates the concentration of oxygen dissolved in water, and is an essential element for the growth of cultivated organisms. [Brief explanation of the drawings]

[0018] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 11] FIG. 3 is a sequence diagram showing a processing flow of the data processing system according to the first embodiment. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0019] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

[0020] First, the terms used in the following description will be explained.

[0021] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), and an APU (Accelerated Processing Unit).

[0022] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

[0023] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0024] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0025] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0026] [First embodiment]

[0027] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0028] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0029] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0030] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0031] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0032] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0033] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

[0034] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0035] 2, in the data processing device 12, a specific process is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0036] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0037] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with the specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0038] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0039] The present invention provides a system for automatically optimizing an aquaculture environment, which includes a means for collecting environmental data, a means for transmitting the environmental data, a means for generating instructions for adjusting the environment using a generation AI based on the environmental data, a means for receiving the instructions, and a means for adjusting the environment based on the instructions.

[0040] In this system, the terminal first collects environmental data from various sensors. The collected environmental data includes water temperature, pH level, and dissolved oxygen. For example, the terminal measures the water temperature (22.5°C) from the water temperature sensor, the water quality (pH level) (7.4) from the pH sensor, and the dissolved oxygen level (6.8 mg / L) from the dissolved oxygen sensor.

[0041] Next, the device sends the collected environmental data to the server. This data is converted to JSON format and sent to the server using an HTTP POST request. Once the server receives this data, the generating AI analyzes it and generates instructions for optimal environmental adjustment. For example, if the water temperature is high, the generating AI generates the instruction "turn on the cooling device to lower the water temperature to 20.0°C."

[0042] The generated instruction is sent from the server to the device. When the device receives the instruction, it adjusts the environment based on the instruction. Specifically, it turns on the cooling device and adjusts the water temperature to 20.0°C.

[0043] After the environmental adjustment is complete, the device will again collect current environmental data from the sensors and send the new data as feedback to the server. This feedback data is very important for the generative AI and is used by the system to continue optimizing the environment in real time.

[0044] Specific examples

[0045] For example, when a user sets up a new aquaculture system, they first install a terminal and place various sensors (water temperature sensor, pH sensor, dissolved oxygen sensor) in the tank. The terminal then collects initial data from these sensors and sends it to the server. If the server analyzes the data and detects that the water temperature is high at 22.5°C, it generates an instruction to "turn on the cooling device to lower the water temperature to 20.0°C." The instruction is sent to the terminal, which then activates the cooling device and adjusts the water temperature. The terminal then collects data again and sends it to the server as feedback. This process allows users to efficiently and accurately manage the aquaculture environment without any specialized knowledge.

[0046] The above is a form for implementing the present invention, and by automating all processes of environmental data collection, analysis, instruction generation, environmental adjustment, and feedback, it is possible to accurately and efficiently optimize the aquaculture environment.

[0047] The processing flow will be explained below.

[0048] Step 1:

[0049] The device collects environmental data from various sensors.

[0050] Measure the water temperature from the water temperature sensor (e.g. 22.5°C).

[0051] Measure the pH level of the water quality from the pH sensor (e.g. 7.4).

[0052] Measure the amount of dissolved oxygen in the water using a dissolved oxygen sensor (e.g., 6.8 mg / L).

[0053] Step 2:

[0054] The terminal transmits the collected environmental data to the server.

[0055] The device converts the sensor data into JSON format.

[0056] The converted data is sent to the server via an HTTP POST request.

[0057] Step 3:

[0058] The server inputs the received data into the generation AI.

[0059] The server sends the received environmental data to the generated AI.

[0060] Generative AI analyzes the data and generates instructions for adjusting the environment.

[0061] Step 4:

[0062] The server sends the generated instructions to the terminal.

[0063] Convert the generated instructions into JSON format.

[0064] Send instructions to the device via an HTTP GET request.

[0065] Step 5:

[0066] The device adjusts the environment based on the instructions it receives.

[0067] If the "cooling" action is specified, the cooling device is turned on.

[0068] Operate the cooling device as instructed until the water temperature reaches 20.0°C.

[0069] Step 6:

[0070] Check the device status again after adjusting the environment.

[0071] The sensors again measure the water temperature, pH level, and dissolved oxygen.

[0072] Collect new environmental data.

[0073] Step 7:

[0074] The device sends new environmental data to the server as feedback.

[0075] Convert the new data into JSON format and send it to the server.

[0076] At the same time, the data is set to be used for further analysis and for generating the next instruction.

[0077] The above are the specific processing steps of the present invention. By performing various specific operations at each step, the aquaculture environment is automatically and efficiently optimized.

[0078] Example 1

[0079] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0080] Optimal management of the aquaculture environment requires collecting environmental data in real time and taking appropriate measures promptly. However, conventional systems often require specialized knowledge and make efficient management difficult. Furthermore, the difficulty of responding quickly to environmental fluctuations has led to problems such as reduced production efficiency and wasted resources. The present invention aims to solve these problems and provide an aquaculture environment optimization system that can be easily operated even by non-experts.

[0081] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0082] In this invention, the server includes means for measuring environmental data, means for converting and transmitting the environmental data, means for generating instructions for adjusting the environment using an artificial intelligence model based on the environmental data, means for receiving and analyzing the instructions, and means for controlling the environment based on the instructions, thereby enabling real-time collection and analysis of environmental data and rapid environmental adjustment.

[0083] "Environmental data" refers to measurements such as temperature, acidity, and dissolved oxygen levels related to the ecosystem or aquaculture environment.

[0084] "Means of measurement" refers to the sensors and measuring devices used to obtain environmental data.

[0085] "Means for converting and transmitting" refers to a device or software that converts collected environmental data into a specified format and transmits it to other devices such as a server via a network.

[0086] "Artificial intelligence model" refers to machine learning and deep learning techniques used to analyze collected data and generate optimal environmental adjustment instructions.

[0087] "Means for receiving and analyzing instructions" refers to devices or software that receive instructions generated by an AI model via a network, interpret their contents, and identify the required actions.

[0088] "Means for controlling the environment" refers to cooling devices or other control systems for adjusting the temperature and acidity of the aquaculture environment based on instructions received.

[0089] "Means for sending feedback" refers to devices or software that recollect data after adjusting the environment and send it to the artificial intelligence model.

[0090] The present invention provides a system for automatically optimizing an aquaculture environment, the system including means for measuring environmental data, means for converting and transmitting the environmental data, means for generating instructions for adjusting the environment using an artificial intelligence model based on the environmental data, means for receiving and analyzing the instructions, and means for controlling the environment based on the instructions.

[0091] First, the device measures environmental data from various sensors, specifically water temperature, acidity, and dissolved oxygen sensors, to collect the following data:

[0092] Water temperature sensor: Measures water temperature 22.5°C.

[0093] Acidity sensor: Measures pH level 7.4.

[0094] Dissolved oxygen sensor: Measures dissolved oxygen levels of 6.8 mg / L.

[0095] Next, convert the environmental data collected by the device into JSON format. For example, convert the data into the following format.

[0096] json

[0097] {

[0098] "water_temperature": 22.5,

[0099] "ph_level": 7.4,

[0100] "dissolved_oxygen": 6.8

[0101] }

[0102] This JSON data is sent to the server using an HTTP POST request.

[0103] The server receives the data using an HTTP request handler. Based on the received data, the AI ​​model generates instructions for adjusting the environment. For example, the following prompt sentences can be used to analyze the data and generate optimal instructions:

[0104] plaintext

[0105] "Adjust the water temperature to 22.5°C, pH level to 7.4, and dissolved oxygen to 6.8 mg / L. The optimum water temperature should be 20.0°C."

[0106] The generation AI generates the instruction "Turn on the cooling device to lower the water temperature to 20.0°C."

[0107] The generated instructions are sent from the server to the terminal. Specifically, the generated instructions are converted into JSON format and sent to the terminal again using an HTTP POST request.

[0108] The device controls the environment according to the received instructions. For example,

[0109] plaintext

[0110] "Turn on the cooling system and adjust the water temperature to 20.0°C."

[0111] Based on this instruction, the terminal issues a control signal to the cooling device, causing the cooling device to operate.

[0112] After the environmental adjustment is complete, the device again collects current environmental data from the sensors, converts the new data into JSON format again, and sends it to the server as feedback. The server continues to analyze the received feedback data in real time, constantly monitoring whether the environment is being optimized.

[0113] This system allows users to efficiently and accurately manage the aquaculture environment without specialized knowledge, which is expected to improve production efficiency and maximize resource utilization.

[0114] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0115] Step 1:

[0116] The terminal measures environmental data from various sensors. Inputs include data from water temperature sensors, acidity sensors, and dissolved oxygen sensors. Specifically, the terminal collects the following data:

[0117] Water temperature: 22.5°C

[0118] Acidity: pH 7.4

[0119] Dissolved oxygen: 6.8 mg / L

[0120] The output is continuously acquired sensor data.

[0121] Step 2:

[0122] The environmental data collected by the device is converted into JSON format. Specifically, the following data conversion is performed: The input is the value collected by the sensor, and the output is JSON format data.

[0123] {

[0124] "water_temperature": 22.5,

[0125] "ph_level": 7.4,

[0126] "dissolved_oxygen": 6.8

[0127] }

[0128] The converted JSON data is sent to the server via an HTTP POST request.

[0129] Step 3:

[0130] The server receives JSON formatted data. The server retrieves the data using an HTTP request handler. Specifically, the received data is parsed as follows: the input is JSON formatted environment data, and the output is the parsed data.

[0131] {

[0132] "water_temperature": 22.5,

[0133] "ph_level": 7.4,

[0134] "dissolved_oxygen": 6.8

[0135] }

[0136] Step 4:

[0137] Based on the data received by the server, the generative AI model generates instructions for adjusting the environment. The input is the analyzed environmental data and the set reference values. The following prompt sentences are used:

[0138] plaintext

[0139] "Adjust the water temperature to 22.5°C, pH level to 7.4, and dissolved oxygen to 6.8 mg / L. The optimum water temperature should be 20.0°C."

[0140] The generation AI generates the instruction "Turn on the cooling device to lower the water temperature to 20.0°C." The output is a specific environmental adjustment instruction.

[0141] Step 5:

[0142] The server sends the generated instructions to the terminal. The input is the instruction created by the generation AI, and the output is the instruction converted to JSON format.

[0143] json

[0144] {

[0145] "action": "activate_cooling",

[0146] "target_temperature": 20.0

[0147] }

[0148] This data is sent to the device via an HTTP POST request.

[0149] Step 6:

[0150] The terminal receives and analyzes the instructions to control the environment. Specifically, it performs the following operations: The input is the received environment adjustment instruction, and the output is the actual environment adjustment action.

[0151] plaintext

[0152] "Turn on the cooling system and adjust the water temperature to 20.0°C."

[0153] The terminal issues a control signal to the cooling device to activate the cooling device.

[0154] Step 7:

[0155] The device again collects current environmental data from the sensors, converts the new data into JSON format again, and sends it to the server as feedback. The input is the adjusted environmental data, and the output is the JSON data sent again via an HTTP POST request.

[0156] json

[0157] {

[0158] "water_temperature": 20.0,

[0159] "ph_level": 7.4,

[0160] "dissolved_oxygen": 6.8

[0161] }

[0162] Based on the above explanation of each processing step, this system can automatically optimize the aquaculture environment.

[0163] (Application example 1)

[0164] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0165] Properly managing the package storage environment in logistics centers is extremely important. However, manually managing environmental data such as temperature, humidity, and CO2 levels is time-consuming and accuracy is difficult to guarantee. Furthermore, if workers were to perform all environmental adjustments themselves, specialized knowledge would be required, making efficient and accurate environmental management difficult. This invention solves these problems and provides a system that automatically optimizes the package storage environment in logistics centers.

[0166] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0167] In this invention, the server includes means for collecting environmental data, means for generating instructions for adjusting the environment using a generative AI model based on the environmental data, means for generating instructions for optimizing the package storage environment in the logistics center, means for visualizing and executing the instructions on a smartphone, and means for checking the state after the environmental adjustment and sending feedback to the generative AI model. This enables efficient and accurate management of the package storage environment in the logistics center even if the worker does not have specialized knowledge.

[0168] "Environmental Data" is data related to environmental conditions within a logistics center, such as temperature, humidity, and CO2 levels.

[0169] A "generative AI model" is an artificial intelligence model that generates optimal environmental adjustment instructions from collected environmental data.

[0170] "Environmental adjustment instructions" are specific operational instructions for optimizing the environmental conditions within the logistics center, created by the generative AI model based on environmental data.

[0171] "Logistics Center" means a facility where package storage and shipping operations are carried out.

[0172] "Package storage environment" refers to environmental conditions such as temperature, humidity, and CO2 levels that are managed within the logistics center to maintain product quality.

[0173] A "smartphone" is a portable information terminal that can visualize instructions and perform environmental adjustments.

[0174] "Feedback" refers to data sent to the generative AI model after adjusting the environment, to help with the accuracy of the model and the generation of next instructions.

[0175] MODE FOR CARRYING OUT THE INVENTION

[0176] The present invention provides a system for automatically optimizing the package storage environment in a logistics center. Specific embodiments will be described below.

[0177] 1. System Configuration

[0178] The system consists of the following main components:

[0179] Sensors that collect environmental data (temperature sensor, humidity sensor, CO2 sensor)

[0180] A smartphone app that collects environmental data and sends it to a server

[0181] A generative AI model that generates environmental adjustment instructions

[0182] Actuators that receive instructions and adjust the environment (chillers, humidifiers, ventilation systems, etc.)

[0183] A means of collecting feedback data after adjusting the environment and sending it to the server

[0184] 2. System Operation

[0185] The server first receives environmental data (temperature, humidity, CO2 level) collected from each sensor. This data is sent to the server via a smartphone app. The data is converted to JSON format and sent using an HTTP POST request.

[0186] 3. Data analysis and instruction generation

[0187] Once the server receives the environmental data, the generative AI model analyzes the data and generates optimal environmental adjustment instructions. For example, if the collected data is a temperature of 23.5 degrees, humidity of 50%, and CO2 level of 900 ppm, the generative AI model will generate instructions such as "turn on the humidifier to adjust the humidity to 45%."

[0188] 4. Execution of instructions

[0189] Instructions are sent from the server to a smartphone app, which visualizes the instructions and notifies the worker of the necessary operations. The worker follows the notifications and adjusts the environment based on the instructions. Specifically, the smartphone app controls cooling devices to adjust temperature, humidifiers to adjust humidity, and ventilation systems to adjust CO2 levels.

[0190] 5. Gathering Feedback

[0191] After the environmental adjustment is completed, the sensors collect environmental data again and send the new data to the server as feedback. This feedback data is very important for the generative AI model and is used as the basis for generating the next adjustment instructions.

[0192] 6. Examples of concrete examples and prompts

[0193] For example, if humidity levels rise in a logistics center, posing a risk of a decline in the quality of stored packages, a smartphone app will send humidity data collected from sensors to a server. A generative AI model will analyze the data and generate instructions to turn on the ventilation system to reduce humidity. This instruction will then be communicated to a worker via the smartphone app, who will then activate the ventilation system and adjust the environment.

[0194] Example prompts for generative AI models:

[0195] current_temperature: 23.5

[0196] current_humidity: 50

[0197] current_co2_level: 900

[0198] Required adjustments for optimal storage conditions:

[0199] This system makes it possible to monitor the package storage environment in a logistics center in real time and automatically optimize it, allowing the system to efficiently and accurately manage the environment without requiring workers to have specialized knowledge.

[0200] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0201] Step 1:

[0202] The terminal collects environmental data. The terminal obtains data in real time from temperature, humidity, and CO2 sensors installed in the logistics center. For example, the temperature sensor collects 23.5 degrees, the humidity sensor collects 50%, and the CO2 sensor collects 900 ppm (input: data from various environmental sensors, output: collected environmental data).

[0203] Step 2:

[0204] The device sends the collected environmental data to the server. The data is converted to JSON format and sent to the server using an HTTP POST request. For example, the collected data is sent in JSON format as {"temperature": 23.5, "humidity": 50, "co2_level": 900} (Input: Collected environmental data, Output: JSON data sent to the server).

[0205] Step 3:

[0206] The server receives and analyzes environmental data. The generative AI model generates optimal environmental adjustment instructions based on the environmental data. For example, if the humidity is high, the generative AI model generates instructions such as "turn on the humidifier to adjust the humidity to 45%" (Input: received environmental data, Output: generated environmental adjustment instructions).

[0207] Step 4:

[0208] The server generates and sends the environmental adjustment instructions to the device. The instructions are visualized via a smartphone app. For example, an instruction such as "Turn on the humidifier to adjust the humidity to 45%" is sent to the device (Input: Generated environmental adjustment instructions, Output: Visualization of the instructions on the device).

[0209] Step 5:

[0210] The user receives and executes instructions on a smartphone app. The user checks the notification and operates an actuator (such as a cooling device, humidifier, or ventilation system). For example, the user turns on the ventilation system according to the instructions on the smartphone app (input: environmental adjustment instruction from the server, output: executed environmental adjustment).

[0211] Step 6:

[0212] After the environmental adjustment is complete, the device collects environmental data again and sends feedback to the server. The new environmental data is sent as feedback in JSON format. For example, the data after the environmental adjustment is sent in JSON format as {"temperature": 23.0, "humidity": 45, "co2_level": 850} (input: adjusted environmental data, output: sending feedback data).

[0213] Step 7:

[0214] The server receives the feedback data and updates the generative AI model. Based on the feedback data, the generative AI model updates the data used when generating the next environmental adjustment instruction. This allows the system to perform optimal environmental adjustments from the next time onwards (input: feedback data, output: updated generative AI model).

[0215] Furthermore, an emotion engine that estimates the user's emotion may be combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0216] The present invention combines a system for automatically optimizing an aquaculture environment with an emotion engine that recognizes user emotions. The system includes a means for collecting environmental data, a means for transmitting the environmental data, a means for generating instructions for adjusting the environment using a generation AI based on the environmental data, a means for receiving the instructions, a means for adjusting the environment based on the instructions, and an emotion engine.

[0217] In this system, the terminal first collects environmental data from various sensors. The collected environmental data includes water temperature, pH level, and dissolved oxygen. For example, the terminal measures the water temperature (22.5°C) from the water temperature sensor, the water quality (pH level) (7.4) from the pH sensor, and the dissolved oxygen level (6.8 mg / L) from the dissolved oxygen sensor.

[0218] The device then sends the collected environmental data to the server. This data is converted to JSON format and sent to the server using an HTTP POST request. Once the server receives this data, the generating AI analyzes it and generates instructions for optimal environmental adjustments. For example, if the water temperature is high, the generating AI generates the instruction "turn on the cooling device to lower the water temperature to 20.0°C."

[0219] The server sends the generated instructions to the device. When the device receives the instructions, it adjusts the environment based on the instructions. Specifically, it turns on the cooling device and adjusts the water temperature to 20.0°C.

[0220] After the environmental adjustment is complete, the device will again collect current environmental data from the sensors and send the new data as feedback to the server. This feedback data is very important for the generative AI and is used by the system to continue optimizing the environment in real time.

[0221] Furthermore, this system incorporates an emotion engine that recognizes the user's emotions. The emotion engine detects the user's emotional state and provides feedback to the generation AI as data. This feedback allows the generation AI to generate more appropriate environmental adjustment instructions, taking the user's emotional state into account. For example, if the user is feeling stressed, the generation AI can flexibly change the environmental adjustment instructions to generate instructions that will improve the user's emotional state.

[0222] Specific examples

[0223] For example, when a user sets up a new aquaculture system, they first install a terminal and place various sensors (water temperature sensor, pH sensor, dissolved oxygen sensor) in the tank. The terminal then collects initial data from these sensors and sends it to the server. If the server analyzes the data and detects that the water temperature is high at 22.5°C, it generates an instruction to "turn on the cooling device to lower the water temperature to 20.0°C." The instruction is sent to the terminal, which then activates the cooling device and adjusts the water temperature. The terminal then collects data again and sends it to the server for feedback.

[0224] The system is also equipped with an emotion engine that recognizes the user's emotions. For example, if the user is worried about raising the fish, the system will detect this emotion. The emotion engine sends this data to the server, and the generation AI can generate new instructions for adjusting the environment taking this information into account. This allows for optimal management of the aquaculture environment, taking the user's emotional state into account.

[0225] The above is a mode for implementing the present invention, and by using the emotion engine and generative AI together, a flexible system is provided that constantly optimizes the aquaculture environment and responds to the user's emotions. It is possible to efficiently and accurately manage the aquaculture environment without any specialized knowledge.

[0226] The processing flow will be explained below.

[0227] Step 1:

[0228] The device collects environmental data from various sensors.

[0229] Measure the water temperature from the water temperature sensor (e.g. 22.5°C).

[0230] Measure the pH level of the water quality from the pH sensor (e.g. 7.4).

[0231] Measure the amount of dissolved oxygen in the water using a dissolved oxygen sensor (e.g., 6.8 mg / L).

[0232] Step 2:

[0233] The terminal transmits the collected environmental data to the server.

[0234] The device converts the sensor data into JSON format.

[0235] The converted data is sent to the server via an HTTP POST request.

[0236] Step 3:

[0237] The server inputs the received data into the generation AI.

[0238] The server sends the received environmental data to the generated AI.

[0239] Generative AI analyzes the data and generates instructions for adjusting the environment.

[0240] Step 4:

[0241] The server sends the generated instructions to the terminal.

[0242] Convert the generated instructions into JSON format.

[0243] Send instructions to the device via an HTTP GET request.

[0244] Step 5:

[0245] The device adjusts the environment based on the instructions it receives.

[0246] If the "cooling" action is specified, the cooling device is turned on.

[0247] Operate the cooling device as instructed until the water temperature reaches 20.0°C.

[0248] Step 6:

[0249] Check the device status again after adjusting the environment.

[0250] The sensors again measure the water temperature, pH level, and dissolved oxygen.

[0251] Collect new environmental data.

[0252] Step 7:

[0253] The device sends new environmental data to the server as feedback.

[0254] Convert the new data into JSON format and send it to the server.

[0255] The server inputs new feedback data into the generation AI and uses it for the next analysis.

[0256] Step 8:

[0257] An emotion engine recognizes the user's emotional state.

[0258] It uses a camera and microphone to detect the user's facial expressions and tone of voice.

[0259] The detection results are generated as emotion data.

[0260] Step 9:

[0261] The emotion data generated by the emotion engine is sent to the server.

[0262] Emotion data is converted into JSON format and sent to the server.

[0263] Step 10:

[0264] The server inputs the emotion data into the generation AI.

[0265] The generative AI analyzes the emotional data and reflects it in instructions for adjusting the environment.

[0266] For example, if the user is feeling stressed, the AI ​​will generate instructions such as "raise the water temperature a little to enhance the relaxation effect."

[0267] Step 11:

[0268] The server generates new instructions and sends them to the terminal.

[0269] The new instructions are converted into JSON format and sent to the device via an HTTP GET request.

[0270] Step 12:

[0271] The device will then adjust the environment again based on the new instructions.

[0272] For example, it makes adjustments according to instructions, such as turning off the cooling device and turning on the heater.

[0273] These are the specific processing steps of the invention that combines the emotion engine. Detailed operations are performed at each step, and the aquaculture environment is automatically and efficiently optimized. Furthermore, by taking the user's emotions into consideration, more personalized environment management is realized.

[0274] Example 2

[0275] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0276] Conventional aquaculture systems can automatically adjust the environment based on environmental data, but they cannot manage the environment taking the user's emotions into account. As a result, if the user feels stressed or anxious, the system cannot respond according to that emotional state, making it difficult to optimally manage the aquaculture environment.

[0277] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0278] In this invention, the server includes means for generating instructions for environmental adjustment using a generating AI based on environmental data, means for detecting the user's emotions, and means for feeding back the user's emotional data to the generating AI, thereby enabling environmental adjustment that takes the user's emotional state into consideration.

[0279] "Environmental data" refers to information that indicates the state of the aquaculture environment, such as water temperature, pH level, and dissolved oxygen.

[0280] "Generative AI" is an artificial intelligence algorithm for automatically generating instructions for environmental adjustments based on collected environmental data and user emotional data.

[0281] "Environmental adjustment instructions" are specific operational instructions for adjusting water temperature, pH levels, and dissolved oxygen, including turning equipment on and off and changing settings.

[0282] "User emotions" refer to psychological states such as stress, anxiety, and relief that users feel while operating the aquaculture system.

[0283] "Collecting means" refers to devices and methods that use sensors to acquire environmental data.

[0284] "Transmission means" refers to the communication means or protocol used to transmit collected data to the server.

[0285] "Means for receiving" refers to a communication means or protocol that allows a terminal to receive instructions sent from a server.

[0286] "Adjustment means" refers to devices or mechanisms for carrying out the environmental adjustment operations instructed by the generating AI, such as cooling devices and pH adjustment devices.

[0287] The "feedback means" is a mechanism for sending the state of the environment after adjustment back to the server, which enables real-time monitoring and adjustment.

[0288] An "emotion engine" is software or hardware that analyzes a user's facial expressions, voice, etc. to detect their psychological state.

[0289] MODE FOR CARRYING OUT THE INVENTION

[0290] The present invention combines a system for automatically optimizing aquaculture environments with an emotion engine that recognizes user emotions. The system includes a means for collecting environmental data, a means for transmitting the environmental data, a means for generating instructions for adjusting the environment using a generative AI model based on the environmental data, a means for receiving the instructions, a means for adjusting the environment based on the instructions, and an emotion engine.

[0291] First, the terminal collects environmental data from various sensors. This terminal uses hardware such as a water temperature sensor, pH sensor, and dissolved oxygen sensor. For example, the terminal measures the water temperature (22.5°C) from the water temperature sensor, the water quality (pH level 7.4) from the pH sensor, and the dissolved oxygen level (6.8 mg / L) from the dissolved oxygen sensor. This allows the terminal to accurately grasp the current state of the aquaculture environment.

[0292] The device then sends the collected environmental data to the server, which converts the data into JSON format and sends it to the server using an HTTP POST request. An example of this data might look like this: {"water_temp": 22.5, "pH_level": 7.4, "dissolved_oxygen": 6.8}.

[0293] Once the server receives this data, the generative AI model analyzes it and generates optimal environmental adjustment instructions. The generative AI model uses pre-programmed algorithms to calculate the optimal adjustment method based on the collected data. For example, if the water temperature is high, the generative AI model generates the instruction "turn on the cooling device to lower the water temperature to 20.0°C."

[0294] The server sends the generated instructions to the device. When the device receives these instructions, it adjusts the environment based on the instructions. Specifically, it turns on the cooling device and adjusts the water temperature to 20.0°C. Once this process is complete, the device again collects current environmental data from the sensors and sends the new data as feedback to the server. This feedback data is crucial for the generative AI model and is used by the system to continue optimizing the environment in real time.

[0295] Furthermore, this system incorporates an emotion engine that recognizes the user's emotions. The emotion engine detects the user's emotional state using sensors such as cameras and microphones and feeds this information back to the generative AI model as data. This feedback allows the generative AI model to take the user's emotional state into account and generate more appropriate environmental adjustment instructions. For example, if the user is feeling stressed, the generative AI model can flexibly change the environmental adjustment instructions to generate instructions that will improve the user's emotional state.

[0296] Specific examples

[0297] For example, when a user sets up a new aquaculture system, they first install a terminal and place various sensors (water temperature sensor, pH sensor, dissolved oxygen sensor) in the tank. The terminal then collects initial data from these sensors and sends it to the server. If the server analyzes the data and detects that the water temperature is high at 22.5°C, it generates an instruction to "turn on the cooling device to lower the water temperature to 20.0°C." The instruction is sent to the terminal, which then activates the cooling device and adjusts the water temperature. The terminal then collects data again and sends it to the server for feedback.

[0298] The system also features an emotion engine that recognizes the user's emotions. For example, if the user is worried about their care, the system will detect their emotions. The emotion engine sends the data to the server, and the generative AI model can generate new environmental adjustment instructions that take this information into account. This allows for optimal management of the aquaculture environment, taking into account the user's emotional state.

[0299] Example prompt sentence:

[0300] Generate environmental adjustment instructions based on data collected from vivarium sensors.

[0301] Initial data:

[0302] Water temperature: 22.5°C

[0303] pH level: 7.4

[0304] Dissolved oxygen: 6.8 mg / L

[0305] User Emotion: Stress

[0306] The above is an embodiment of the present invention, and by using the emotion engine and generative AI model together, a flexible system is provided that constantly optimizes the aquaculture environment and responds to the user's emotions. It is possible to efficiently and accurately manage the aquaculture environment without any specialized knowledge.

[0307] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0308] System program processing flow

[0309] Step 1:

[0310] The device collects environmental data from sensors. The device uses water temperature, pH, and dissolved oxygen sensors to collect each type of data. The collected data is stored in the device's memory.

[0311] input:

[0312] Data from the water temperature sensor

[0313] Data from pH sensors

[0314] Data from a dissolved oxygen sensor

[0315] Specific behavior:

[0316] The water temperature sensor measures a water temperature of 22.5°C.

[0317] The pH sensor measures a pH level of 7.4.

[0318] The dissolved oxygen sensor measures 6.8 mg / L of dissolved oxygen.

[0319] output:

[0320] Collected environmental data (e.g., {"water_temp": 22.5, "pH_level": 7.4, "dissolved_oxygen": 6.8}) is saved on the device.

[0321] Step 2:

[0322] The device sends the collected environmental data to the server, which converts the data into JSON format and sends it using an HTTP POST request.

[0323] input:

[0324] Environmental data stored on the device

[0325] Specific behavior:

[0326] The device converts the environment data into JSON format.

[0327] The device sends an HTTP POST request to the server.

[0328] output:

[0329] Environmental data sent to the server

[0330] Step 3:

[0331] The server receives the data, and the generative AI model generates instructions for adjusting the environment. After the data is received, the generative AI analyzes the data and generates instructions for optimal environmental adjustment.

[0332] input:

[0333] Environmental data received by the server

[0334] Specific behavior:

[0335] The server receives the HTTP request and parses the environment data.

[0336] A generative AI model performs calculations based on the data.

[0337] output:

[0338] Environmental adjustment instructions (e.g., "Turn on the chiller to reduce the water temperature to 20.0°C")

[0339] Step 4:

[0340] The server generates instructions and sends them to the device, where they are again converted to JSON format and sent using an HTTP POST request.

[0341] input:

[0342] Environmental adjustment instructions generated by a generative AI model

[0343] Specific behavior:

[0344] The server converts the instructions into JSON format.

[0345] The server sends an HTTP POST request to the device.

[0346] output:

[0347] Environmental adjustment instructions sent to the device

[0348] Step 5:

[0349] The device adjusts the environment based on instructions. Specifically, it adjusts the environment by operating cooling devices, etc., and performs operations such as turning devices on and off according to instructions.

[0350] input:

[0351] Received environmental adjustment instructions

[0352] Specific behavior:

[0353] The device turns on the cooling device and reduces the water temperature to 20.0°C.

[0354] output:

[0355] Environmental adjustments are made (e.g., a cooling device is turned on)

[0356] Step 6:

[0357] The device collects the data from the sensor again after adjusting the environment and feeds it back to the server. The adjusted data is again converted into JSON format and sent to the server.

[0358] input:

[0359] Adjusted environmental data

[0360] Specific behavior:

[0361] The sensors measure the environmental data again.

[0362] The data collected by the device is converted into JSON format and sent to the server.

[0363] output:

[0364] Adjusted environmental data sent to the server

[0365] Step 7:

[0366] The emotion engine detects the user's emotions and feeds them back to the generative AI model. The camera and microphone are used to analyze the user's emotions and send the data to the server.

[0367] input:

[0368] User's facial expression and voice data

[0369] Specific behavior:

[0370] The camera captures the user's facial expressions.

[0371] A microphone collects the user's voice.

[0372] The emotion engine analyzes this data.

[0373] output:

[0374] User emotional data (e.g., stress level)

[0375] Step 8:

[0376] The generative AI model generates new instructions for adjusting the environment, taking into account the user's emotional state. New instructions that reflect the user's emotional data are generated and applied to the system.

[0377] input:

[0378] User emotion data

[0379] Environmental Data

[0380] Specific behavior:

[0381] A generative AI model analyzes user emotional data.

[0382] Calculations are performed by combining environmental data and emotional data.

[0383] output:

[0384] New environmental adjustment instructions (e.g., "Reduce light levels to provide a relaxing environment")

[0385] The above is a detailed flow of the program processing of this system. By clarifying the specific inputs, outputs, and processing details at each step, the operation of the system is easy to understand.

[0386] (Application example 2)

[0387] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0388] Modern factories and production environments require optimal maintenance of environmental parameters such as temperature, humidity, and air quality. However, continuously monitoring these environmental parameters and optimally adjusting them in real time requires a great deal of effort and specialized knowledge. Furthermore, because workers' emotional states have a significant impact on productivity, it is important to adjust the environment while taking this into account, but this has been difficult to achieve with existing systems. Therefore, there is a strong demand for the development of a system that simultaneously considers environmental parameters and emotional states and maintains both optimally.

[0389] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the system includes means for collecting environmental data, means for transmitting the environmental data, means for generating instructions for environmental adjustment using a generation AI based on the environmental data, means for receiving the instructions, means for adjusting the environment based on the instructions, means for recognizing the user's emotional state, means for transmitting feedback to the generation AI based on the emotional state, and means for the generation AI to generate instructions for environmental adjustment taking the emotional state into consideration. This makes it possible to simultaneously optimize environmental parameters and the user's emotional state, thereby maintaining a safer and more efficient production environment.

[0390] "Environmental Data" is information about environmental parameters such as temperature, humidity, air quality, water temperature, pH levels, and dissolved oxygen.

[0391] "Means for collecting environmental data" refers to a method or device that uses a sensor to measure environmental parameters and acquire them as data.

[0392] The "means for transmitting environmental data" refers to a method or apparatus for transmitting collected environmental data to a server or other device via a network.

[0393] "Generative AI" is a system that uses artificial intelligence to generate optimal environmental adjustment instructions based on input data.

[0394] "Means for generating instructions for environmental adjustment" refers to a method or device that generates optimal instructions for environmental adjustment based on environmental data collected using a generation AI.

[0395] The "means for receiving instructions" refers to a method or apparatus for receiving generated environment adjustment instructions from a server or other device.

[0396] A "means for adjusting the environment" is a method or device for actually adjusting environmental parameters (temperature, humidity, etc.) based on received instructions.

[0397] The "means for recognizing the emotional state of a user" refers to a method or device for recognizing the emotional state of a user by analyzing the user's facial expressions, actions, tone of voice, etc.

[0398] "Means for sending feedback to the generation AI based on emotional state" refers to a method or device for sending the recognized emotional state of the user to the generation AI as feedback.

[0399] "Means for generating environmental adjustment instructions that take into account the emotional state of the user" refers to a method or device that uses a generating AI to generate optimal environmental adjustment instructions that take into account the emotional state of the user.

[0400] In this invention, the system mainly comprises the following components: means for collecting environmental data, means for transmitting the environmental data, means for generating instructions for adjusting the environment using a generating AI based on the environmental data, means for receiving the instructions, and means for adjusting the environment based on the instructions. Furthermore, the system includes means for recognizing the user's emotional state and transmitting it as feedback to the generating AI.

[0401] System Program

[0402] The system uses sensors to collect environmental data (temperature, humidity, air quality, etc.) within the factory. These sensors include temperature sensors, humidity sensors, and air quality sensors. The collected data is sent to a cloud server via the terminal. The data is converted into JSON format and sent to the server using an HTTP POST request.

[0403] The server analyzes the collected environmental data and generates instructions for optimal environmental adjustments. It uses a generative AI model to generate specific instructions for adjusting environmental parameters based on the data. For example, if the temperature is high, the AI ​​generates instructions such as "Turn on the air conditioner and set the temperature to 25°C."

[0404] The generated instructions are then sent back to the device, which then adjusts the environment based on the received instructions. Specifically, it operates equipment such as air conditioners and humidifiers to adjust the temperature and humidity to the specified level.

[0405] On the other hand, cameras and microphones are used to recognize the user's emotional state. The data collected by these devices is analyzed by an emotion recognition engine to identify the user's emotional state (e.g., stress, fatigue, etc.). This emotional data is also sent to a cloud server and used as feedback for the generative AI.

[0406] The generative AI generates instructions for adjusting the environment taking into account the user's emotional state. For example, if the user is feeling stressed, the generative AI can give instructions such as "soften the lighting in the work area" or "play background music."

[0407] Specific examples

[0408] If the temperature in a factory is 30°C, humidity is 45%, and air quality is 90AQI, the system works as follows: The terminal collects this environmental data and sends it to the server. The generative AI model then analyzes the data and generates instructions such as "turn on the air conditioner and set the temperature to 25°C." This instruction is sent to the terminal, which operates the air conditioner to adjust the temperature.

[0409] Additionally, if the user is feeling stressed, the emotion recognition engine will detect this state and generate instructions such as "soften the lighting in the work area to reduce stress." This instruction is also sent to the device, and the actual environmental adjustment is carried out. For example, a prompt might be entered in the form of "The temperature is 30°C, the humidity is 45%, and the air quality is 90AQI. Please generate instructions for optimal temperature and humidity adjustment."

[0410] This allows the environment within the factory to be kept optimal at all times and allows for flexible environmental adjustments that take into account the emotional state of workers.

[0411] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0412] Step 1:

[0413] The terminal collects environmental data from various sensors (temperature, humidity, and air quality sensors). This involves obtaining temperature, humidity, and air quality values ​​from sensors installed at various locations in the factory. The input is the raw data from the sensors. The output is the collected environmental data (e.g., temperature 30°C, humidity 45%, air quality 90 AQI).

[0414] Step 2:

[0415] The environmental data collected by the device is converted into JSON format and sent to the cloud server using an HTTP POST request. This process involves data conversion and network transmission. The input is the environmental data obtained in step 1, and the output is the JSON-formatted data sent to the server.

[0416] Step 3:

[0417] The server receives the environmental data, analyzes it using a generative AI model, and generates instructions for adjusting the environment. At this stage, temperature, humidity, and air quality values ​​are analyzed to determine the optimal adjustment method. The input is the environmental data sent to the server, and the output is the generated adjustment instructions (e.g., turn on the air conditioner and set the temperature to 25°C).

[0418] Step 4:

[0419] The server sends the generated environmental adjustment instructions to the terminal. In this process, the generated instructions are sent to the terminal using an HTTP GET request, etc. The input is the generated adjustment instructions, and the output is the instructions sent to the terminal.

[0420] Step 5:

[0421] The terminal adjusts the environment based on the received instructions. At this stage, it operates equipment such as air conditioners and humidifiers to set the temperature and humidity as instructed. The input is the adjustment instruction received from the server, and the output is the adjusted environmental parameters (e.g., temperature 25°C).

[0422] Step 6:

[0423] The terminal collects the adjusted environmental data again and sends the new data to the server as feedback. This involves collecting the adjusted environmental data and sending it to the server. The input is the adjusted environmental data, and the output is the feedback data sent to the server.

[0424] Step 7:

[0425] The device collects the user's emotional state using a camera or microphone. In this process, an emotion recognition engine analyzes facial expressions and tone of voice to recognize the emotional state. The input is the collected audio and video data, and the output is the recognized emotional state (e.g., high stress level).

[0426] Step 8:

[0427] The device converts the user's emotional state into JSON format and sends it to the cloud server using an HTTP POST request. The input is the recognized emotional state, and the output is the emotional data sent to the server.

[0428] Step 9:

[0429] The server receives the emotion data and uses a generative AI model to generate instructions for adjusting the environment that take the emotional state into account. In this process, the emotion data and environmental data are analyzed comprehensively to generate more appropriate adjustment instructions. The input is the emotional state and environmental data, and the output is adjustment instructions that take the emotion into account.

[0430] Step 10:

[0431] The server sends instructions for adjusting the environment taking into account the generated emotions to the terminal, and the terminal then adjusts the environment again based on the instructions received. The input is the adjustment instructions taking into account the emotions, and the output is the further adjusted environmental parameters.

[0432] This allows the system to simultaneously optimize environmental parameters and the user's emotional state, maintaining a safer and more efficient production environment.

[0433] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0434] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0435] In the above embodiment, an example in which the specific process is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0436] [Second embodiment]

[0437] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0438] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0439] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0440] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0441] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0442] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0443] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0444] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0445] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0446] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0447] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0448] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal."

[0449] The present invention provides a system for automatically optimizing an aquaculture environment, which includes a means for collecting environmental data, a means for transmitting the environmental data, a means for generating instructions for adjusting the environment using a generation AI based on the environmental data, a means for receiving the instructions, and a means for adjusting the environment based on the instructions.

[0450] In this system, the terminal first collects environmental data from various sensors. The collected environmental data includes water temperature, pH level, and dissolved oxygen. For example, the terminal measures the water temperature (22.5°C) from the water temperature sensor, the water quality (pH level) (7.4) from the pH sensor, and the dissolved oxygen level (6.8 mg / L) from the dissolved oxygen sensor.

[0451] Next, the device sends the collected environmental data to the server. This data is converted to JSON format and sent to the server using an HTTP POST request. Once the server receives this data, the generating AI analyzes it and generates instructions for optimal environmental adjustment. For example, if the water temperature is high, the generating AI generates the instruction "turn on the cooling device to lower the water temperature to 20.0°C."

[0452] The generated instruction is sent from the server to the device. When the device receives the instruction, it adjusts the environment based on the instruction. Specifically, it turns on the cooling device and adjusts the water temperature to 20.0°C.

[0453] After the environmental adjustment is complete, the device will again collect current environmental data from the sensors and send the new data as feedback to the server. This feedback data is very important for the generative AI and is used by the system to continue optimizing the environment in real time.

[0454] Specific examples

[0455] For example, when a user sets up a new aquaculture system, they first install a terminal and place various sensors (water temperature sensor, pH sensor, dissolved oxygen sensor) in the tank. The terminal then collects initial data from these sensors and sends it to the server. If the server analyzes the data and detects that the water temperature is high at 22.5°C, it generates an instruction to "turn on the cooling device to lower the water temperature to 20.0°C." The instruction is sent to the terminal, which then activates the cooling device and adjusts the water temperature. The terminal then collects data again and sends it to the server as feedback. This process allows users to efficiently and accurately manage the aquaculture environment without any specialized knowledge.

[0456] The above is a form for implementing the present invention, and by automating all processes of environmental data collection, analysis, instruction generation, environmental adjustment, and feedback, it is possible to accurately and efficiently optimize the aquaculture environment.

[0457] The processing flow will be explained below.

[0458] Step 1:

[0459] The device collects environmental data from various sensors.

[0460] Measure the water temperature from the water temperature sensor (e.g. 22.5°C).

[0461] Measure the pH level of the water quality from the pH sensor (e.g. 7.4).

[0462] Measure the amount of dissolved oxygen in the water using a dissolved oxygen sensor (e.g., 6.8 mg / L).

[0463] Step 2:

[0464] The terminal transmits the collected environmental data to the server.

[0465] The device converts the sensor data into JSON format.

[0466] The converted data is sent to the server via an HTTP POST request.

[0467] Step 3:

[0468] The server inputs the received data into the generation AI.

[0469] The server sends the received environmental data to the generated AI.

[0470] Generative AI analyzes the data and generates instructions for adjusting the environment.

[0471] Step 4:

[0472] The server sends the generated instructions to the terminal.

[0473] Convert the generated instructions into JSON format.

[0474] Send instructions to the device via an HTTP GET request.

[0475] Step 5:

[0476] The device adjusts the environment based on the instructions it receives.

[0477] If the "cooling" action is specified, the cooling device is turned on.

[0478] Operate the cooling device as instructed until the water temperature reaches 20.0°C.

[0479] Step 6:

[0480] Check the device status again after adjusting the environment.

[0481] The sensors again measure the water temperature, pH level, and dissolved oxygen.

[0482] Collect new environmental data.

[0483] Step 7:

[0484] The device sends new environmental data to the server as feedback.

[0485] Convert the new data into JSON format and send it to the server.

[0486] At the same time, the data is set to be used for further analysis and for generating the next instruction.

[0487] The above are the specific processing steps of the present invention. By performing various specific operations at each step, the aquaculture environment is automatically and efficiently optimized.

[0488] Example 1

[0489] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0490] Optimal management of the aquaculture environment requires collecting environmental data in real time and taking appropriate measures promptly. However, conventional systems often require specialized knowledge and make efficient management difficult. Furthermore, the difficulty of responding quickly to environmental fluctuations has led to problems such as reduced production efficiency and wasted resources. The present invention aims to solve these problems and provide an aquaculture environment optimization system that can be easily operated even by non-experts.

[0491] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0492] In this invention, the server includes means for measuring environmental data, means for converting and transmitting the environmental data, means for generating instructions for adjusting the environment using an artificial intelligence model based on the environmental data, means for receiving and analyzing the instructions, and means for controlling the environment based on the instructions, thereby enabling real-time collection and analysis of environmental data and rapid environmental adjustment.

[0493] "Environmental data" refers to measurements such as temperature, acidity, and dissolved oxygen levels related to the ecosystem or aquaculture environment.

[0494] "Means of measurement" refers to the sensors and measuring devices used to obtain environmental data.

[0495] "Means for converting and transmitting" refers to a device or software that converts collected environmental data into a specified format and transmits it to other devices such as a server via a network.

[0496] "Artificial intelligence model" refers to machine learning and deep learning techniques used to analyze collected data and generate optimal environmental adjustment instructions.

[0497] "Means for receiving and analyzing instructions" refers to devices or software that receive instructions generated by an AI model via a network, interpret their contents, and identify the required actions.

[0498] "Means for controlling the environment" refers to cooling devices or other control systems for adjusting the temperature and acidity of the aquaculture environment based on instructions received.

[0499] "Means for sending feedback" refers to devices or software that recollect data after adjusting the environment and send it to the artificial intelligence model.

[0500] The present invention provides a system for automatically optimizing an aquaculture environment, the system including means for measuring environmental data, means for converting and transmitting the environmental data, means for generating instructions for adjusting the environment using an artificial intelligence model based on the environmental data, means for receiving and analyzing the instructions, and means for controlling the environment based on the instructions.

[0501] First, the device measures environmental data from various sensors, specifically water temperature, acidity, and dissolved oxygen sensors, to collect the following data:

[0502] Water temperature sensor: Measures water temperature 22.5°C.

[0503] Acidity sensor: Measures pH level 7.4.

[0504] Dissolved oxygen sensor: Measures dissolved oxygen levels of 6.8 mg / L.

[0505] Next, convert the environmental data collected by the device into JSON format. For example, convert the data into the following format.

[0506] json

[0507] {

[0508] "water_temperature": 22.5,

[0509] "ph_level": 7.4,

[0510] "dissolved_oxygen": 6.8

[0511] }

[0512] This JSON data is sent to the server using an HTTP POST request.

[0513] The server receives the data using an HTTP request handler. Based on the received data, the AI ​​model generates instructions for adjusting the environment. For example, the following prompt sentences can be used to analyze the data and generate optimal instructions:

[0514] plaintext

[0515] "Adjust the water temperature to 22.5°C, pH level to 7.4, and dissolved oxygen to 6.8 mg / L. The optimum water temperature should be 20.0°C."

[0516] The generation AI generates the instruction "Turn on the cooling device to lower the water temperature to 20.0°C."

[0517] The generated instructions are sent from the server to the terminal. Specifically, the generated instructions are converted into JSON format and sent to the terminal again using an HTTP POST request.

[0518] The device controls the environment according to the received instructions. For example,

[0519] plaintext

[0520] "Turn on the cooling system and adjust the water temperature to 20.0°C."

[0521] Based on this instruction, the terminal issues a control signal to the cooling device, causing the cooling device to operate.

[0522] After the environmental adjustment is complete, the device again collects current environmental data from the sensors, converts the new data into JSON format again, and sends it to the server as feedback. The server continues to analyze the received feedback data in real time, constantly monitoring whether the environment is being optimized.

[0523] This system allows users to efficiently and accurately manage the aquaculture environment without specialized knowledge, which is expected to improve production efficiency and maximize resource utilization.

[0524] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0525] Step 1:

[0526] The terminal measures environmental data from various sensors. Inputs include data from water temperature sensors, acidity sensors, and dissolved oxygen sensors. Specifically, the terminal collects the following data:

[0527] Water temperature: 22.5°C

[0528] Acidity: pH 7.4

[0529] Dissolved oxygen: 6.8 mg / L

[0530] The output is continuously acquired sensor data.

[0531] Step 2:

[0532] The environmental data collected by the device is converted into JSON format. Specifically, the following data conversion is performed: The input is the value collected by the sensor, and the output is JSON format data.

[0533] {

[0534] "water_temperature": 22.5,

[0535] "ph_level": 7.4,

[0536] "dissolved_oxygen": 6.8

[0537] }

[0538] The converted JSON data is sent to the server via an HTTP POST request.

[0539] Step 3:

[0540] The server receives JSON formatted data. The server retrieves the data using an HTTP request handler. Specifically, the received data is parsed as follows: the input is JSON formatted environment data, and the output is the parsed data.

[0541] {

[0542] "water_temperature": 22.5,

[0543] "ph_level": 7.4,

[0544] "dissolved_oxygen": 6.8

[0545] }

[0546] Step 4:

[0547] Based on the data received by the server, the generative AI model generates instructions for adjusting the environment. The input is the analyzed environmental data and the set reference values. The following prompt sentences are used:

[0548] plaintext

[0549] "Adjust the water temperature to 22.5°C, pH level to 7.4, and dissolved oxygen to 6.8 mg / L. The optimum water temperature should be 20.0°C."

[0550] The generation AI generates the instruction "Turn on the cooling device to lower the water temperature to 20.0°C." The output is a specific environmental adjustment instruction.

[0551] Step 5:

[0552] The server sends the generated instructions to the terminal. The input is the instruction created by the generation AI, and the output is the instruction converted to JSON format.

[0553] json

[0554] {

[0555] "action": "activate_cooling",

[0556] "target_temperature": 20.0

[0557] }

[0558] This data is sent to the device via an HTTP POST request.

[0559] Step 6:

[0560] The terminal receives and analyzes the instructions to control the environment. Specifically, it performs the following operations: The input is the received environment adjustment instruction, and the output is the actual environment adjustment action.

[0561] plaintext

[0562] "Turn on the cooling system and adjust the water temperature to 20.0°C."

[0563] The terminal issues a control signal to the cooling device to activate the cooling device.

[0564] Step 7:

[0565] The device again collects current environmental data from the sensors, converts the new data into JSON format again, and sends it to the server as feedback. The input is the adjusted environmental data, and the output is the JSON data sent again via an HTTP POST request.

[0566] json

[0567] {

[0568] "water_temperature": 20.0,

[0569] "ph_level": 7.4,

[0570] "dissolved_oxygen": 6.8

[0571] }

[0572] Based on the above explanation of each processing step, this system can automatically optimize the aquaculture environment.

[0573] (Application example 1)

[0574] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0575] Properly managing the package storage environment in logistics centers is extremely important. However, manually managing environmental data such as temperature, humidity, and CO2 levels is time-consuming and accuracy is difficult to guarantee. Furthermore, if workers were to perform all environmental adjustments themselves, specialized knowledge would be required, making efficient and accurate environmental management difficult. This invention solves these problems and provides a system that automatically optimizes the package storage environment in logistics centers.

[0576] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0577] In this invention, the server includes means for collecting environmental data, means for generating instructions for adjusting the environment using a generative AI model based on the environmental data, means for generating instructions for optimizing the package storage environment in the logistics center, means for visualizing and executing the instructions on a smartphone, and means for checking the state after the environmental adjustment and sending feedback to the generative AI model. This enables efficient and accurate management of the package storage environment in the logistics center even if the worker does not have specialized knowledge.

[0578] "Environmental Data" is data related to environmental conditions within a logistics center, such as temperature, humidity, and CO2 levels.

[0579] A "generative AI model" is an artificial intelligence model that generates optimal environmental adjustment instructions from collected environmental data.

[0580] "Environmental adjustment instructions" are specific operational instructions for optimizing the environmental conditions within the logistics center, created by the generative AI model based on environmental data.

[0581] "Logistics Center" means a facility where package storage and shipping operations are carried out.

[0582] "Package storage environment" refers to environmental conditions such as temperature, humidity, and CO2 levels that are managed within the logistics center to maintain product quality.

[0583] A "smartphone" is a portable information terminal that can visualize instructions and perform environmental adjustments.

[0584] "Feedback" refers to data sent to the generative AI model after adjusting the environment, to help with the accuracy of the model and the generation of next instructions.

[0585] MODE FOR CARRYING OUT THE INVENTION

[0586] The present invention provides a system for automatically optimizing the package storage environment in a logistics center. Specific embodiments will be described below.

[0587] 1. System Configuration

[0588] The system consists of the following main components:

[0589] Sensors that collect environmental data (temperature sensor, humidity sensor, CO2 sensor)

[0590] A smartphone app that collects environmental data and sends it to a server

[0591] A generative AI model that generates environmental adjustment instructions

[0592] Actuators that receive instructions and adjust the environment (chillers, humidifiers, ventilation systems, etc.)

[0593] A means of collecting feedback data after adjusting the environment and sending it to the server

[0594] 2. System Operation

[0595] The server first receives environmental data (temperature, humidity, CO2 level) collected from each sensor. This data is sent to the server via a smartphone app. The data is converted to JSON format and sent using an HTTP POST request.

[0596] 3. Data analysis and instruction generation

[0597] Once the server receives the environmental data, the generative AI model analyzes the data and generates optimal environmental adjustment instructions. For example, if the collected data is a temperature of 23.5 degrees, humidity of 50%, and CO2 level of 900 ppm, the generative AI model will generate instructions such as "turn on the humidifier to adjust the humidity to 45%."

[0598] 4. Execution of instructions

[0599] Instructions are sent from the server to a smartphone app, which visualizes the instructions and notifies the worker of the necessary operations. The worker follows the notifications and adjusts the environment based on the instructions. Specifically, the smartphone app controls cooling devices to adjust temperature, humidifiers to adjust humidity, and ventilation systems to adjust CO2 levels.

[0600] 5. Gathering Feedback

[0601] After the environmental adjustment is completed, the sensors collect environmental data again and send the new data to the server as feedback. This feedback data is very important for the generative AI model and is used as the basis for generating the next adjustment instructions.

[0602] 6. Examples of concrete examples and prompts

[0603] For example, if humidity levels rise in a logistics center, posing a risk of a decline in the quality of stored packages, a smartphone app will send humidity data collected from sensors to a server. A generative AI model will analyze the data and generate instructions to turn on the ventilation system to reduce humidity. This instruction will then be communicated to a worker via the smartphone app, who will then activate the ventilation system and adjust the environment.

[0604] Example prompts for generative AI models:

[0605] current_temperature: 23.5

[0606] current_humidity: 50

[0607] current_co2_level: 900

[0608] Required adjustments for optimal storage conditions:

[0609] This system makes it possible to monitor the package storage environment in a logistics center in real time and automatically optimize it, allowing the system to efficiently and accurately manage the environment without requiring workers to have specialized knowledge.

[0610] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0611] Step 1:

[0612] The terminal collects environmental data. The terminal obtains data in real time from temperature, humidity, and CO2 sensors installed in the logistics center. For example, the temperature sensor collects 23.5 degrees, the humidity sensor collects 50%, and the CO2 sensor collects 900 ppm (input: data from various environmental sensors, output: collected environmental data).

[0613] Step 2:

[0614] The device sends the collected environmental data to the server. The data is converted to JSON format and sent to the server using an HTTP POST request. For example, the collected data is sent in JSON format as {"temperature": 23.5, "humidity": 50, "co2_level": 900} (Input: Collected environmental data, Output: JSON data sent to the server).

[0615] Step 3:

[0616] The server receives and analyzes environmental data. The generative AI model generates optimal environmental adjustment instructions based on the environmental data. For example, if the humidity is high, the generative AI model generates instructions such as "turn on the humidifier to adjust the humidity to 45%" (Input: received environmental data, Output: generated environmental adjustment instructions).

[0617] Step 4:

[0618] The server generates and sends the environmental adjustment instructions to the device. The instructions are visualized via a smartphone app. For example, an instruction such as "Turn on the humidifier to adjust the humidity to 45%" is sent to the device (Input: Generated environmental adjustment instructions, Output: Visualization of the instructions on the device).

[0619] Step 5:

[0620] The user receives and executes instructions on a smartphone app. The user checks the notification and operates an actuator (such as a cooling device, humidifier, or ventilation system). For example, the user turns on the ventilation system according to the instructions on the smartphone app (input: environmental adjustment instruction from the server, output: executed environmental adjustment).

[0621] Step 6:

[0622] After the environmental adjustment is complete, the device collects environmental data again and sends feedback to the server. The new environmental data is sent as feedback in JSON format. For example, the data after the environmental adjustment is sent in JSON format as {"temperature": 23.0, "humidity": 45, "co2_level": 850} (input: adjusted environmental data, output: sending feedback data).

[0623] Step 7:

[0624] The server receives the feedback data and updates the generative AI model. Based on the feedback data, the generative AI model updates the data used when generating the next environmental adjustment instruction. This allows the system to perform optimal environmental adjustments from the next time onwards (input: feedback data, output: updated generative AI model).

[0625] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0626] The present invention combines a system for automatically optimizing an aquaculture environment with an emotion engine that recognizes user emotions. The system includes a means for collecting environmental data, a means for transmitting the environmental data, a means for generating instructions for adjusting the environment using a generation AI based on the environmental data, a means for receiving the instructions, a means for adjusting the environment based on the instructions, and an emotion engine.

[0627] In this system, the terminal first collects environmental data from various sensors. The collected environmental data includes water temperature, pH level, and dissolved oxygen. For example, the terminal measures the water temperature (22.5°C) from the water temperature sensor, the water quality (pH level) (7.4) from the pH sensor, and the dissolved oxygen level (6.8 mg / L) from the dissolved oxygen sensor.

[0628] The device then sends the collected environmental data to the server. This data is converted to JSON format and sent to the server using an HTTP POST request. Once the server receives this data, the generating AI analyzes it and generates instructions for optimal environmental adjustments. For example, if the water temperature is high, the generating AI generates the instruction "turn on the cooling device to lower the water temperature to 20.0°C."

[0629] The server sends the generated instructions to the device. When the device receives the instructions, it adjusts the environment based on the instructions. Specifically, it turns on the cooling device and adjusts the water temperature to 20.0°C.

[0630] After the environmental adjustment is complete, the device will again collect current environmental data from the sensors and send the new data as feedback to the server. This feedback data is very important for the generative AI and is used by the system to continue optimizing the environment in real time.

[0631] Furthermore, this system incorporates an emotion engine that recognizes the user's emotions. The emotion engine detects the user's emotional state and provides feedback to the generation AI as data. This feedback allows the generation AI to generate more appropriate environmental adjustment instructions, taking the user's emotional state into account. For example, if the user is feeling stressed, the generation AI can flexibly change the environmental adjustment instructions to generate instructions that will improve the user's emotional state.

[0632] Specific examples

[0633] For example, when a user sets up a new aquaculture system, they first install a terminal and place various sensors (water temperature sensor, pH sensor, dissolved oxygen sensor) in the tank. The terminal then collects initial data from these sensors and sends it to the server. If the server analyzes the data and detects that the water temperature is high at 22.5°C, it generates an instruction to "turn on the cooling device to lower the water temperature to 20.0°C." The instruction is sent to the terminal, which then activates the cooling device and adjusts the water temperature. The terminal then collects data again and sends it to the server for feedback.

[0634] The system is also equipped with an emotion engine that recognizes the user's emotions. For example, if the user is worried about raising the fish, the system will detect this emotion. The emotion engine sends this data to the server, and the generation AI can generate new instructions for adjusting the environment taking this information into account. This allows for optimal management of the aquaculture environment, taking the user's emotional state into account.

[0635] The above is a mode for implementing the present invention, and by using the emotion engine and generative AI together, a flexible system is provided that constantly optimizes the aquaculture environment and responds to the user's emotions. It is possible to efficiently and accurately manage the aquaculture environment without any specialized knowledge.

[0636] The processing flow will be explained below.

[0637] Step 1:

[0638] The device collects environmental data from various sensors.

[0639] Measure the water temperature from the water temperature sensor (e.g. 22.5°C).

[0640] Measure the pH level of the water quality from the pH sensor (e.g. 7.4).

[0641] Measure the amount of dissolved oxygen in the water using a dissolved oxygen sensor (e.g., 6.8 mg / L).

[0642] Step 2:

[0643] The terminal transmits the collected environmental data to the server.

[0644] The device converts the sensor data into JSON format.

[0645] The converted data is sent to the server via an HTTP POST request.

[0646] Step 3:

[0647] The server inputs the received data into the generation AI.

[0648] The server sends the received environmental data to the generated AI.

[0649] Generative AI analyzes the data and generates instructions for adjusting the environment.

[0650] Step 4:

[0651] The server sends the generated instructions to the terminal.

[0652] Convert the generated instructions into JSON format.

[0653] Send instructions to the device via an HTTP GET request.

[0654] Step 5:

[0655] The device adjusts the environment based on the instructions it receives.

[0656] If the "cooling" action is specified, the cooling device is turned on.

[0657] Operate the cooling device as instructed until the water temperature reaches 20.0°C.

[0658] Step 6:

[0659] Check the device status again after adjusting the environment.

[0660] The sensors again measure the water temperature, pH level, and dissolved oxygen.

[0661] Collect new environmental data.

[0662] Step 7:

[0663] The device sends new environmental data to the server as feedback.

[0664] Convert the new data into JSON format and send it to the server.

[0665] The server inputs new feedback data into the generation AI and uses it for the next analysis.

[0666] Step 8:

[0667] An emotion engine recognizes the user's emotional state.

[0668] It uses a camera and microphone to detect the user's facial expressions and tone of voice.

[0669] The detection results are generated as emotion data.

[0670] Step 9:

[0671] The emotion data generated by the emotion engine is sent to the server.

[0672] Emotion data is converted into JSON format and sent to the server.

[0673] Step 10:

[0674] The server inputs the emotion data into the generation AI.

[0675] The generative AI analyzes the emotional data and reflects it in instructions for adjusting the environment.

[0676] For example, if the user is feeling stressed, the AI ​​will generate instructions such as "raise the water temperature a little to enhance the relaxation effect."

[0677] Step 11:

[0678] The server generates new instructions and sends them to the terminal.

[0679] The new instructions are converted into JSON format and sent to the device via an HTTP GET request.

[0680] Step 12:

[0681] The device will then adjust the environment again based on the new instructions.

[0682] For example, it makes adjustments according to instructions, such as turning off the cooling device and turning on the heater.

[0683] These are the specific processing steps of the invention that combines the emotion engine. Detailed operations are performed at each step, and the aquaculture environment is automatically and efficiently optimized. Furthermore, by taking the user's emotions into consideration, more personalized environment management is realized.

[0684] Example 2

[0685] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0686] Conventional aquaculture systems can automatically adjust the environment based on environmental data, but they cannot manage the environment taking the user's emotions into account. As a result, if the user feels stressed or anxious, the system cannot respond according to that emotional state, making it difficult to optimally manage the aquaculture environment.

[0687] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0688] In this invention, the server includes means for generating instructions for environmental adjustment using a generating AI based on environmental data, means for detecting the user's emotions, and means for feeding back the user's emotional data to the generating AI, thereby enabling environmental adjustment that takes the user's emotional state into consideration.

[0689] "Environmental data" refers to information that indicates the state of the aquaculture environment, such as water temperature, pH level, and dissolved oxygen.

[0690] "Generative AI" is an artificial intelligence algorithm for automatically generating instructions for environmental adjustments based on collected environmental data and user emotional data.

[0691] "Environmental adjustment instructions" are specific operational instructions for adjusting water temperature, pH levels, and dissolved oxygen, including turning equipment on and off and changing settings.

[0692] "User emotions" refer to psychological states such as stress, anxiety, and relief that users feel while operating the aquaculture system.

[0693] "Collecting means" refers to devices and methods that use sensors to acquire environmental data.

[0694] "Transmission means" refers to the communication means or protocol used to transmit collected data to the server.

[0695] "Means for receiving" refers to a communication means or protocol that allows a terminal to receive instructions sent from a server.

[0696] "Adjustment means" refers to devices or mechanisms for carrying out the environmental adjustment operations instructed by the generating AI, such as cooling devices and pH adjustment devices.

[0697] The "feedback means" is a mechanism for sending the state of the environment after adjustment back to the server, which enables real-time monitoring and adjustment.

[0698] An "emotion engine" is software or hardware that analyzes a user's facial expressions, voice, etc. to detect their psychological state.

[0699] MODE FOR CARRYING OUT THE INVENTION

[0700] The present invention combines a system for automatically optimizing aquaculture environments with an emotion engine that recognizes user emotions. The system includes a means for collecting environmental data, a means for transmitting the environmental data, a means for generating instructions for adjusting the environment using a generative AI model based on the environmental data, a means for receiving the instructions, a means for adjusting the environment based on the instructions, and an emotion engine.

[0701] First, the terminal collects environmental data from various sensors. This terminal uses hardware such as a water temperature sensor, pH sensor, and dissolved oxygen sensor. For example, the terminal measures the water temperature (22.5°C) from the water temperature sensor, the water quality (pH level 7.4) from the pH sensor, and the dissolved oxygen level (6.8 mg / L) from the dissolved oxygen sensor. This allows the terminal to accurately grasp the current state of the aquaculture environment.

[0702] The device then sends the collected environmental data to the server, which converts the data into JSON format and sends it to the server using an HTTP POST request. An example of this data might look like this: {"water_temp": 22.5, "pH_level": 7.4, "dissolved_oxygen": 6.8}.

[0703] Once the server receives this data, the generative AI model analyzes it and generates optimal environmental adjustment instructions. The generative AI model uses pre-programmed algorithms to calculate the optimal adjustment method based on the collected data. For example, if the water temperature is high, the generative AI model generates the instruction "turn on the cooling device to lower the water temperature to 20.0°C."

[0704] The server sends the generated instructions to the device. When the device receives these instructions, it adjusts the environment based on the instructions. Specifically, it turns on the cooling device and adjusts the water temperature to 20.0°C. Once this process is complete, the device again collects current environmental data from the sensors and sends the new data as feedback to the server. This feedback data is crucial for the generative AI model and is used by the system to continue optimizing the environment in real time.

[0705] Furthermore, this system incorporates an emotion engine that recognizes the user's emotions. The emotion engine detects the user's emotional state using sensors such as cameras and microphones and feeds this information back to the generative AI model as data. This feedback allows the generative AI model to take the user's emotional state into account and generate more appropriate environmental adjustment instructions. For example, if the user is feeling stressed, the generative AI model can flexibly change the environmental adjustment instructions to generate instructions that will improve the user's emotional state.

[0706] Specific examples

[0707] For example, when a user sets up a new aquaculture system, they first install a terminal and place various sensors (water temperature sensor, pH sensor, dissolved oxygen sensor) in the tank. The terminal then collects initial data from these sensors and sends it to the server. If the server analyzes the data and detects that the water temperature is high at 22.5°C, it generates an instruction to "turn on the cooling device to lower the water temperature to 20.0°C." The instruction is sent to the terminal, which then activates the cooling device and adjusts the water temperature. The terminal then collects data again and sends it to the server for feedback.

[0708] The system also features an emotion engine that recognizes the user's emotions. For example, if the user is worried about their care, the system will detect their emotions. The emotion engine sends the data to the server, and the generative AI model can generate new environmental adjustment instructions that take this information into account. This allows for optimal management of the aquaculture environment, taking into account the user's emotional state.

[0709] Example prompt sentence:

[0710] Generate environmental adjustment instructions based on data collected from vivarium sensors.

[0711] Initial data:

[0712] Water temperature: 22.5°C

[0713] pH level: 7.4

[0714] Dissolved oxygen: 6.8 mg / L

[0715] User Emotion: Stress

[0716] The above is an embodiment of the present invention, and by using the emotion engine and generative AI model together, a flexible system is provided that constantly optimizes the aquaculture environment and responds to the user's emotions. It is possible to efficiently and accurately manage the aquaculture environment without any specialized knowledge.

[0717] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0718] System program processing flow

[0719] Step 1:

[0720] The device collects environmental data from sensors. The device uses water temperature, pH, and dissolved oxygen sensors to collect each type of data. The collected data is stored in the device's memory.

[0721] input:

[0722] Data from the water temperature sensor

[0723] Data from pH sensors

[0724] Data from a dissolved oxygen sensor

[0725] Specific behavior:

[0726] The water temperature sensor measures a water temperature of 22.5°C.

[0727] The pH sensor measures a pH level of 7.4.

[0728] The dissolved oxygen sensor measures 6.8 mg / L of dissolved oxygen.

[0729] output:

[0730] Collected environmental data (e.g., {"water_temp": 22.5, "pH_level": 7.4, "dissolved_oxygen": 6.8}) is saved on the device.

[0731] Step 2:

[0732] The device sends the collected environmental data to the server, which converts the data into JSON format and sends it using an HTTP POST request.

[0733] input:

[0734] Environmental data stored on the device

[0735] Specific behavior:

[0736] The device converts the environment data into JSON format.

[0737] The device sends an HTTP POST request to the server.

[0738] output:

[0739] Environmental data sent to the server

[0740] Step 3:

[0741] The server receives the data, and the generative AI model generates instructions for adjusting the environment. After the data is received, the generative AI analyzes the data and generates instructions for optimal environmental adjustment.

[0742] input:

[0743] Environmental data received by the server

[0744] Specific behavior:

[0745] The server receives the HTTP request and parses the environment data.

[0746] A generative AI model performs calculations based on the data.

[0747] output:

[0748] Environmental adjustment instructions (e.g., "Turn on the chiller to reduce the water temperature to 20.0°C")

[0749] Step 4:

[0750] The server generates instructions and sends them to the device, where they are again converted to JSON format and sent using an HTTP POST request.

[0751] input:

[0752] Environmental adjustment instructions generated by a generative AI model

[0753] Specific behavior:

[0754] The server converts the instructions into JSON format.

[0755] The server sends an HTTP POST request to the device.

[0756] output:

[0757] Environmental adjustment instructions sent to the device

[0758] Step 5:

[0759] The device adjusts the environment based on instructions. Specifically, it adjusts the environment by operating cooling devices, etc., and performs operations such as turning devices on and off according to instructions.

[0760] input:

[0761] Received environmental adjustment instructions

[0762] Specific behavior:

[0763] The device turns on the cooling device and reduces the water temperature to 20.0°C.

[0764] output:

[0765] Environmental adjustments are made (e.g., a cooling device is turned on)

[0766] Step 6:

[0767] The device collects the data from the sensor again after adjusting the environment and feeds it back to the server. The adjusted data is again converted into JSON format and sent to the server.

[0768] input:

[0769] Adjusted environmental data

[0770] Specific behavior:

[0771] The sensors measure the environmental data again.

[0772] The data collected by the device is converted into JSON format and sent to the server.

[0773] output:

[0774] Adjusted environmental data sent to the server

[0775] Step 7:

[0776] The emotion engine detects the user's emotions and feeds them back to the generative AI model. The camera and microphone are used to analyze the user's emotions and send the data to the server.

[0777] input:

[0778] User's facial expression and voice data

[0779] Specific behavior:

[0780] The camera captures the user's facial expressions.

[0781] A microphone collects the user's voice.

[0782] The emotion engine analyzes this data.

[0783] output:

[0784] User emotional data (e.g., stress level)

[0785] Step 8:

[0786] The generative AI model generates new instructions for adjusting the environment, taking into account the user's emotional state. New instructions that reflect the user's emotional data are generated and applied to the system.

[0787] input:

[0788] User emotion data

[0789] Environmental Data

[0790] Specific behavior:

[0791] A generative AI model analyzes user emotional data.

[0792] Calculations are performed by combining environmental data and emotional data.

[0793] output:

[0794] New environmental adjustment instructions (e.g., "Reduce light levels to provide a relaxing environment")

[0795] The above is a detailed flow of the program processing of this system. By clarifying the specific inputs, outputs, and processing details at each step, the operation of the system is easy to understand.

[0796] (Application example 2)

[0797] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0798] Modern factories and production environments require optimal maintenance of environmental parameters such as temperature, humidity, and air quality. However, continuously monitoring these environmental parameters and optimally adjusting them in real time requires a great deal of effort and specialized knowledge. Furthermore, because workers' emotional states have a significant impact on productivity, it is important to adjust the environment while taking this into account, but this has been difficult to achieve with existing systems. Therefore, there is a strong demand for the development of a system that simultaneously considers environmental parameters and emotional states and maintains both optimally.

[0799] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the system includes means for collecting environmental data, means for transmitting the environmental data, means for generating instructions for environmental adjustment using a generation AI based on the environmental data, means for receiving the instructions, means for adjusting the environment based on the instructions, means for recognizing the user's emotional state, means for transmitting feedback to the generation AI based on the emotional state, and means for the generation AI to generate instructions for environmental adjustment taking the emotional state into consideration. This makes it possible to simultaneously optimize environmental parameters and the user's emotional state, thereby maintaining a safer and more efficient production environment.

[0800] "Environmental Data" is information about environmental parameters such as temperature, humidity, air quality, water temperature, pH levels, and dissolved oxygen.

[0801] "Means for collecting environmental data" refers to a method or device that uses a sensor to measure environmental parameters and acquire them as data.

[0802] The "means for transmitting environmental data" refers to a method or apparatus for transmitting collected environmental data to a server or other device via a network.

[0803] "Generative AI" is a system that uses artificial intelligence to generate optimal environmental adjustment instructions based on input data.

[0804] "Means for generating instructions for environmental adjustment" refers to a method or device that generates optimal instructions for environmental adjustment based on environmental data collected using a generation AI.

[0805] The "means for receiving instructions" refers to a method or apparatus for receiving generated environment adjustment instructions from a server or other device.

[0806] A "means for adjusting the environment" is a method or device for actually adjusting environmental parameters (temperature, humidity, etc.) based on received instructions.

[0807] The "means for recognizing the emotional state of a user" refers to a method or device for recognizing the emotional state of a user by analyzing the user's facial expressions, actions, tone of voice, etc.

[0808] "Means for sending feedback to the generation AI based on emotional state" refers to a method or device for sending the recognized emotional state of the user to the generation AI as feedback.

[0809] "Means for generating environmental adjustment instructions that take into account the emotional state of the user" refers to a method or device that uses a generating AI to generate optimal environmental adjustment instructions that take into account the emotional state of the user.

[0810] In this invention, the system mainly comprises the following components: means for collecting environmental data, means for transmitting the environmental data, means for generating instructions for adjusting the environment using a generating AI based on the environmental data, means for receiving the instructions, and means for adjusting the environment based on the instructions. Furthermore, the system includes means for recognizing the user's emotional state and transmitting it as feedback to the generating AI.

[0811] System Program

[0812] The system uses sensors to collect environmental data (temperature, humidity, air quality, etc.) within the factory. These sensors include temperature sensors, humidity sensors, and air quality sensors. The collected data is sent to a cloud server via the terminal. The data is converted into JSON format and sent to the server using an HTTP POST request.

[0813] The server analyzes the collected environmental data and generates instructions for optimal environmental adjustments. It uses a generative AI model to generate specific instructions for adjusting environmental parameters based on the data. For example, if the temperature is high, the AI ​​generates instructions such as "Turn on the air conditioner and set the temperature to 25°C."

[0814] The generated instructions are then sent back to the device, which then adjusts the environment based on the received instructions. Specifically, it operates equipment such as air conditioners and humidifiers to adjust the temperature and humidity to the specified level.

[0815] On the other hand, cameras and microphones are used to recognize the user's emotional state. The data collected by these devices is analyzed by an emotion recognition engine to identify the user's emotional state (e.g., stress, fatigue, etc.). This emotional data is also sent to a cloud server and used as feedback for the generative AI.

[0816] The generative AI generates instructions for adjusting the environment taking into account the user's emotional state. For example, if the user is feeling stressed, the generative AI can give instructions such as "soften the lighting in the work area" or "play background music."

[0817] Specific examples

[0818] If the temperature in a factory is 30°C, humidity is 45%, and air quality is 90AQI, the system works as follows: The terminal collects this environmental data and sends it to the server. The generative AI model then analyzes the data and generates instructions such as "turn on the air conditioner and set the temperature to 25°C." This instruction is sent to the terminal, which operates the air conditioner to adjust the temperature.

[0819] Additionally, if the user is feeling stressed, the emotion recognition engine will detect this state and generate instructions such as "soften the lighting in the work area to reduce stress." This instruction is also sent to the device, and the actual environmental adjustment is carried out. For example, a prompt might be entered in the form of "The temperature is 30°C, the humidity is 45%, and the air quality is 90AQI. Please generate instructions for optimal temperature and humidity adjustment."

[0820] This allows the environment within the factory to be kept optimal at all times and allows for flexible environmental adjustments that take into account the emotional state of workers.

[0821] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0822] Step 1:

[0823] The terminal collects environmental data from various sensors (temperature, humidity, and air quality sensors). This involves obtaining temperature, humidity, and air quality values ​​from sensors installed at various locations in the factory. The input is the raw data from the sensors. The output is the collected environmental data (e.g., temperature 30°C, humidity 45%, air quality 90 AQI).

[0824] Step 2:

[0825] The environmental data collected by the device is converted into JSON format and sent to the cloud server using an HTTP POST request. This process involves data conversion and network transmission. The input is the environmental data obtained in step 1, and the output is the JSON-formatted data sent to the server.

[0826] Step 3:

[0827] The server receives the environmental data, analyzes it using a generative AI model, and generates instructions for adjusting the environment. At this stage, temperature, humidity, and air quality values ​​are analyzed to determine the optimal adjustment method. The input is the environmental data sent to the server, and the output is the generated adjustment instructions (e.g., turn on the air conditioner and set the temperature to 25°C).

[0828] Step 4:

[0829] The server sends the generated environmental adjustment instructions to the terminal. In this process, the generated instructions are sent to the terminal using an HTTP GET request, etc. The input is the generated adjustment instructions, and the output is the instructions sent to the terminal.

[0830] Step 5:

[0831] The terminal adjusts the environment based on the received instructions. At this stage, it operates equipment such as air conditioners and humidifiers to set the temperature and humidity as instructed. The input is the adjustment instruction received from the server, and the output is the adjusted environmental parameters (e.g., temperature 25°C).

[0832] Step 6:

[0833] The terminal collects the adjusted environmental data again and sends the new data to the server as feedback. This involves collecting the adjusted environmental data and sending it to the server. The input is the adjusted environmental data, and the output is the feedback data sent to the server.

[0834] Step 7:

[0835] The device collects the user's emotional state using a camera or microphone. In this process, an emotion recognition engine analyzes facial expressions and tone of voice to recognize the emotional state. The input is the collected audio and video data, and the output is the recognized emotional state (e.g., high stress level).

[0836] Step 8:

[0837] The device converts the user's emotional state into JSON format and sends it to the cloud server using an HTTP POST request. The input is the recognized emotional state, and the output is the emotional data sent to the server.

[0838] Step 9:

[0839] The server receives the emotion data and uses a generative AI model to generate instructions for adjusting the environment that take the emotional state into account. In this process, the emotion data and environmental data are analyzed comprehensively to generate more appropriate adjustment instructions. The input is the emotional state and environmental data, and the output is adjustment instructions that take the emotion into account.

[0840] Step 10:

[0841] The server sends instructions for adjusting the environment taking into account the generated emotions to the terminal, and the terminal then adjusts the environment again based on the instructions received. The input is the adjustment instructions taking into account the emotions, and the output is the further adjusted environmental parameters.

[0842] This allows the system to simultaneously optimize environmental parameters and the user's emotional state, maintaining a safer and more efficient production environment.

[0843] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0844] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0845] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the smart glasses 214.

[0846] [Third embodiment]

[0847] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0848] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0849] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0850] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0851] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0852] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0853] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0854] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0855] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0856] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0857] In the headset type terminal 314, a reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0858] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the headset type terminal 314 will be referred to as the "terminal."

[0859] The present invention provides a system for automatically optimizing an aquaculture environment, which includes a means for collecting environmental data, a means for transmitting the environmental data, a means for generating instructions for adjusting the environment using a generation AI based on the environmental data, a means for receiving the instructions, and a means for adjusting the environment based on the instructions.

[0860] In this system, the terminal first collects environmental data from various sensors. The collected environmental data includes water temperature, pH level, and dissolved oxygen. For example, the terminal measures the water temperature (22.5°C) from the water temperature sensor, the water quality (pH level) (7.4) from the pH sensor, and the dissolved oxygen level (6.8 mg / L) from the dissolved oxygen sensor.

[0861] Next, the device sends the collected environmental data to the server. This data is converted to JSON format and sent to the server using an HTTP POST request. Once the server receives this data, the generating AI analyzes it and generates instructions for optimal environmental adjustment. For example, if the water temperature is high, the generating AI generates the instruction "turn on the cooling device to lower the water temperature to 20.0°C."

[0862] The generated instruction is sent from the server to the device. When the device receives the instruction, it adjusts the environment based on the instruction. Specifically, it turns on the cooling device and adjusts the water temperature to 20.0°C.

[0863] After the environmental adjustment is complete, the device will again collect current environmental data from the sensors and send the new data as feedback to the server. This feedback data is very important for the generative AI and is used by the system to continue optimizing the environment in real time.

[0864] Specific examples

[0865] For example, when a user sets up a new aquaculture system, they first install a terminal and place various sensors (water temperature sensor, pH sensor, dissolved oxygen sensor) in the tank. The terminal then collects initial data from these sensors and sends it to the server. If the server analyzes the data and detects that the water temperature is high at 22.5°C, it generates an instruction to "turn on the cooling device to lower the water temperature to 20.0°C." The instruction is sent to the terminal, which then activates the cooling device and adjusts the water temperature. The terminal then collects data again and sends it to the server as feedback. This process allows users to efficiently and accurately manage the aquaculture environment without any specialized knowledge.

[0866] The above is a form for implementing the present invention, and by automating all processes of environmental data collection, analysis, instruction generation, environmental adjustment, and feedback, it is possible to accurately and efficiently optimize the aquaculture environment.

[0867] The processing flow will be explained below.

[0868] Step 1:

[0869] The device collects environmental data from various sensors.

[0870] Measure the water temperature from the water temperature sensor (e.g. 22.5°C).

[0871] Measure the pH level of the water quality from the pH sensor (e.g. 7.4).

[0872] Measure the amount of dissolved oxygen in the water using a dissolved oxygen sensor (e.g., 6.8 mg / L).

[0873] Step 2:

[0874] The terminal transmits the collected environmental data to the server.

[0875] The device converts the sensor data into JSON format.

[0876] The converted data is sent to the server via an HTTP POST request.

[0877] Step 3:

[0878] The server inputs the received data into the generation AI.

[0879] The server sends the received environmental data to the generated AI.

[0880] Generative AI analyzes the data and generates instructions for adjusting the environment.

[0881] Step 4:

[0882] The server sends the generated instructions to the terminal.

[0883] Convert the generated instructions into JSON format.

[0884] Send instructions to the device via an HTTP GET request.

[0885] Step 5:

[0886] The device adjusts the environment based on the instructions it receives.

[0887] If the "cooling" action is specified, the cooling device is turned on.

[0888] Operate the cooling device as instructed until the water temperature reaches 20.0°C.

[0889] Step 6:

[0890] Check the device status again after adjusting the environment.

[0891] The sensors again measure the water temperature, pH level, and dissolved oxygen.

[0892] Collect new environmental data.

[0893] Step 7:

[0894] The device sends new environmental data to the server as feedback.

[0895] Convert the new data into JSON format and send it to the server.

[0896] At the same time, the data is set to be used for further analysis and for generating the next instruction.

[0897] The above are the specific processing steps of the present invention. By performing various specific operations at each step, the aquaculture environment is automatically and efficiently optimized.

[0898] Example 1

[0899] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0900] Optimal management of the aquaculture environment requires collecting environmental data in real time and taking appropriate measures promptly. However, conventional systems often require specialized knowledge and make efficient management difficult. Furthermore, the difficulty of responding quickly to environmental fluctuations has led to problems such as reduced production efficiency and wasted resources. The present invention aims to solve these problems and provide an aquaculture environment optimization system that can be easily operated even by non-experts.

[0901] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0902] In this invention, the server includes means for measuring environmental data, means for converting and transmitting the environmental data, means for generating instructions for adjusting the environment using an artificial intelligence model based on the environmental data, means for receiving and analyzing the instructions, and means for controlling the environment based on the instructions, thereby enabling real-time collection and analysis of environmental data and rapid environmental adjustment.

[0903] "Environmental data" refers to measurements such as temperature, acidity, and dissolved oxygen levels related to the ecosystem or aquaculture environment.

[0904] "Means of measurement" refers to the sensors and measuring devices used to obtain environmental data.

[0905] "Means for converting and transmitting" refers to a device or software that converts collected environmental data into a specified format and transmits it to other devices such as a server via a network.

[0906] "Artificial intelligence model" refers to machine learning and deep learning techniques used to analyze collected data and generate optimal environmental adjustment instructions.

[0907] "Means for receiving and analyzing instructions" refers to devices or software that receive instructions generated by an AI model via a network, interpret their contents, and identify the required actions.

[0908] "Means for controlling the environment" refers to cooling devices or other control systems for adjusting the temperature and acidity of the aquaculture environment based on instructions received.

[0909] "Means for sending feedback" refers to devices or software that recollect data after adjusting the environment and send it to the artificial intelligence model.

[0910] The present invention provides a system for automatically optimizing an aquaculture environment, the system including means for measuring environmental data, means for converting and transmitting the environmental data, means for generating instructions for adjusting the environment using an artificial intelligence model based on the environmental data, means for receiving and analyzing the instructions, and means for controlling the environment based on the instructions.

[0911] First, the device measures environmental data from various sensors, specifically water temperature, acidity, and dissolved oxygen sensors, to collect the following data:

[0912] Water temperature sensor: Measures water temperature 22.5°C.

[0913] Acidity sensor: Measures pH level 7.4.

[0914] Dissolved oxygen sensor: Measures dissolved oxygen levels of 6.8 mg / L.

[0915] Next, convert the environmental data collected by the device into JSON format. For example, convert the data into the following format.

[0916] json

[0917] {

[0918] "water_temperature": 22.5,

[0919] "ph_level": 7.4,

[0920] "dissolved_oxygen": 6.8

[0921] }

[0922] This JSON data is sent to the server using an HTTP POST request.

[0923] The server receives the data using an HTTP request handler. Based on the received data, the AI ​​model generates instructions for adjusting the environment. For example, the following prompt sentences can be used to analyze the data and generate optimal instructions:

[0924] plaintext

[0925] "Adjust the water temperature to 22.5°C, pH level to 7.4, and dissolved oxygen to 6.8 mg / L. The optimum water temperature should be 20.0°C."

[0926] The generation AI generates the instruction "Turn on the cooling device to lower the water temperature to 20.0°C."

[0927] The generated instructions are sent from the server to the terminal. Specifically, the generated instructions are converted into JSON format and sent to the terminal again using an HTTP POST request.

[0928] The device controls the environment according to the received instructions. For example,

[0929] plaintext

[0930] "Turn on the cooling system and adjust the water temperature to 20.0°C."

[0931] Based on this instruction, the terminal issues a control signal to the cooling device, causing the cooling device to operate.

[0932] After the environmental adjustment is complete, the device again collects current environmental data from the sensors, converts the new data into JSON format again, and sends it to the server as feedback. The server continues to analyze the received feedback data in real time, constantly monitoring whether the environment is being optimized.

[0933] This system allows users to efficiently and accurately manage the aquaculture environment without specialized knowledge, which is expected to improve production efficiency and maximize resource utilization.

[0934] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0935] Step 1:

[0936] The terminal measures environmental data from various sensors. Inputs include data from water temperature sensors, acidity sensors, and dissolved oxygen sensors. Specifically, the terminal collects the following data:

[0937] Water temperature: 22.5°C

[0938] Acidity: pH 7.4

[0939] Dissolved oxygen: 6.8 mg / L

[0940] The output is continuously acquired sensor data.

[0941] Step 2:

[0942] The environmental data collected by the device is converted into JSON format. Specifically, the following data conversion is performed: The input is the value collected by the sensor, and the output is JSON format data.

[0943] {

[0944] "water_temperature": 22.5,

[0945] "ph_level": 7.4,

[0946] "dissolved_oxygen": 6.8

[0947] }

[0948] The converted JSON data is sent to the server via an HTTP POST request.

[0949] Step 3:

[0950] The server receives JSON formatted data. The server retrieves the data using an HTTP request handler. Specifically, the received data is parsed as follows: the input is JSON formatted environment data, and the output is the parsed data.

[0951] {

[0952] "water_temperature": 22.5,

[0953] "ph_level": 7.4,

[0954] "dissolved_oxygen": 6.8

[0955] }

[0956] Step 4:

[0957] Based on the data received by the server, the generative AI model generates instructions for adjusting the environment. The input is the analyzed environmental data and the set reference values. The following prompt sentences are used:

[0958] plaintext

[0959] "Adjust the water temperature to 22.5°C, pH level to 7.4, and dissolved oxygen to 6.8 mg / L. The optimum water temperature should be 20.0°C."

[0960] The generation AI generates the instruction "Turn on the cooling device to lower the water temperature to 20.0°C." The output is a specific environmental adjustment instruction.

[0961] Step 5:

[0962] The server sends the generated instructions to the terminal. The input is the instruction created by the generation AI, and the output is the instruction converted to JSON format.

[0963] json

[0964] {

[0965] "action": "activate_cooling",

[0966] "target_temperature": 20.0

[0967] }

[0968] This data is sent to the device via an HTTP POST request.

[0969] Step 6:

[0970] The terminal receives and analyzes the instructions to control the environment. Specifically, it performs the following operations: The input is the received environment adjustment instruction, and the output is the actual environment adjustment action.

[0971] plaintext

[0972] "Turn on the cooling system and adjust the water temperature to 20.0°C."

[0973] The terminal issues a control signal to the cooling device to activate the cooling device.

[0974] Step 7:

[0975] The device again collects current environmental data from the sensors, converts the new data into JSON format again, and sends it to the server as feedback. The input is the adjusted environmental data, and the output is the JSON data sent again via an HTTP POST request.

[0976] json

[0977] {

[0978] "water_temperature": 20.0,

[0979] "ph_level": 7.4,

[0980] "dissolved_oxygen": 6.8

[0981] }

[0982] Based on the above explanation of each processing step, this system can automatically optimize the aquaculture environment.

[0983] (Application example 1)

[0984] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0985] Properly managing the package storage environment in logistics centers is extremely important. However, manually managing environmental data such as temperature, humidity, and CO2 levels is time-consuming and accuracy is difficult to guarantee. Furthermore, if workers were to perform all environmental adjustments themselves, specialized knowledge would be required, making efficient and accurate environmental management difficult. This invention solves these problems and provides a system that automatically optimizes the package storage environment in logistics centers.

[0986] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0987] In this invention, the server includes means for collecting environmental data, means for generating instructions for adjusting the environment using a generative AI model based on the environmental data, means for generating instructions for optimizing the package storage environment in the logistics center, means for visualizing and executing the instructions on a smartphone, and means for checking the state after the environmental adjustment and sending feedback to the generative AI model. This enables efficient and accurate management of the package storage environment in the logistics center even if the worker does not have specialized knowledge.

[0988] "Environmental Data" is data related to environmental conditions within a logistics center, such as temperature, humidity, and CO2 levels.

[0989] A "generative AI model" is an artificial intelligence model that generates optimal environmental adjustment instructions from collected environmental data.

[0990] "Environmental adjustment instructions" are specific operational instructions for optimizing the environmental conditions within the logistics center, created by the generative AI model based on environmental data.

[0991] "Logistics Center" means a facility where package storage and shipping operations are carried out.

[0992] "Package storage environment" refers to environmental conditions such as temperature, humidity, and CO2 levels that are managed within the logistics center to maintain product quality.

[0993] A "smartphone" is a portable information terminal that can visualize instructions and perform environmental adjustments.

[0994] "Feedback" refers to data sent to the generative AI model after adjusting the environment, to help with the accuracy of the model and the generation of next instructions.

[0995] MODE FOR CARRYING OUT THE INVENTION

[0996] The present invention provides a system for automatically optimizing the package storage environment in a logistics center. Specific embodiments will be described below.

[0997] 1. System Configuration

[0998] The system consists of the following main components:

[0999] Sensors that collect environmental data (temperature sensor, humidity sensor, CO2 sensor)

[1000] A smartphone app that collects environmental data and sends it to a server

[1001] A generative AI model that generates environmental adjustment instructions

[1002] Actuators that receive instructions and adjust the environment (chillers, humidifiers, ventilation systems, etc.)

[1003] A means of collecting feedback data after adjusting the environment and sending it to the server

[1004] 2. System Operation

[1005] The server first receives environmental data (temperature, humidity, CO2 level) collected from each sensor. This data is sent to the server via a smartphone app. The data is converted to JSON format and sent using an HTTP POST request.

[1006] 3. Data analysis and instruction generation

[1007] Once the server receives the environmental data, the generative AI model analyzes the data and generates optimal environmental adjustment instructions. For example, if the collected data is a temperature of 23.5 degrees, humidity of 50%, and CO2 level of 900 ppm, the generative AI model will generate instructions such as "turn on the humidifier to adjust the humidity to 45%."

[1008] 4. Execution of instructions

[1009] Instructions are sent from the server to a smartphone app, which visualizes the instructions and notifies the worker of the necessary operations. The worker follows the notifications and adjusts the environment based on the instructions. Specifically, the smartphone app controls cooling devices to adjust temperature, humidifiers to adjust humidity, and ventilation systems to adjust CO2 levels.

[1010] 5. Gathering Feedback

[1011] After the environmental adjustment is completed, the sensors collect environmental data again and send the new data to the server as feedback. This feedback data is very important for the generative AI model and is used as the basis for generating the next adjustment instructions.

[1012] 6. Examples of concrete examples and prompts

[1013] For example, if humidity levels rise in a logistics center, posing a risk of a decline in the quality of stored packages, a smartphone app will send humidity data collected from sensors to a server. A generative AI model will analyze the data and generate instructions to turn on the ventilation system to reduce humidity. This instruction will then be communicated to a worker via the smartphone app, who will then activate the ventilation system and adjust the environment.

[1014] Example prompts for generative AI models:

[1015] current_temperature: 23.5

[1016] current_humidity: 50

[1017] current_co2_level: 900

[1018] Required adjustments for optimal storage conditions:

[1019] This system makes it possible to monitor the package storage environment in a logistics center in real time and automatically optimize it, allowing the system to efficiently and accurately manage the environment without requiring workers to have specialized knowledge.

[1020] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1021] Step 1:

[1022] The terminal collects environmental data. The terminal obtains data in real time from temperature, humidity, and CO2 sensors installed in the logistics center. For example, the temperature sensor collects 23.5 degrees, the humidity sensor collects 50%, and the CO2 sensor collects 900 ppm (input: data from various environmental sensors, output: collected environmental data).

[1023] Step 2:

[1024] The device sends the collected environmental data to the server. The data is converted to JSON format and sent to the server using an HTTP POST request. For example, the collected data is sent in JSON format as {"temperature": 23.5, "humidity": 50, "co2_level": 900} (Input: Collected environmental data, Output: JSON data sent to the server).

[1025] Step 3:

[1026] The server receives and analyzes environmental data. The generative AI model generates optimal environmental adjustment instructions based on the environmental data. For example, if the humidity is high, the generative AI model generates instructions such as "turn on the humidifier to adjust the humidity to 45%" (Input: received environmental data, Output: generated environmental adjustment instructions).

[1027] Step 4:

[1028] The server generates and sends the environmental adjustment instructions to the device. The instructions are visualized via a smartphone app. For example, an instruction such as "Turn on the humidifier to adjust the humidity to 45%" is sent to the device (Input: Generated environmental adjustment instructions, Output: Visualization of the instructions on the device).

[1029] Step 5:

[1030] The user receives and executes instructions on a smartphone app. The user checks the notification and operates an actuator (such as a cooling device, humidifier, or ventilation system). For example, the user turns on the ventilation system according to the instructions on the smartphone app (input: environmental adjustment instruction from the server, output: executed environmental adjustment).

[1031] Step 6:

[1032] After the environmental adjustment is complete, the device collects environmental data again and sends feedback to the server. The new environmental data is sent as feedback in JSON format. For example, the data after the environmental adjustment is sent in JSON format as {"temperature": 23.0, "humidity": 45, "co2_level": 850} (input: adjusted environmental data, output: sending feedback data).

[1033] Step 7:

[1034] The server receives the feedback data and updates the generative AI model. Based on the feedback data, the generative AI model updates the data used when generating the next environmental adjustment instruction. This allows the system to perform optimal environmental adjustments from the next time onwards (input: feedback data, output: updated generative AI model).

[1035] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1036] The present invention combines a system for automatically optimizing an aquaculture environment with an emotion engine that recognizes user emotions. The system includes a means for collecting environmental data, a means for transmitting the environmental data, a means for generating instructions for adjusting the environment using a generation AI based on the environmental data, a means for receiving the instructions, a means for adjusting the environment based on the instructions, and an emotion engine.

[1037] In this system, the terminal first collects environmental data from various sensors. The collected environmental data includes water temperature, pH level, and dissolved oxygen. For example, the terminal measures the water temperature (22.5°C) from the water temperature sensor, the water quality (pH level) (7.4) from the pH sensor, and the dissolved oxygen level (6.8 mg / L) from the dissolved oxygen sensor.

[1038] The device then sends the collected environmental data to the server. This data is converted to JSON format and sent to the server using an HTTP POST request. Once the server receives this data, the generating AI analyzes it and generates instructions for optimal environmental adjustments. For example, if the water temperature is high, the generating AI generates the instruction "turn on the cooling device to lower the water temperature to 20.0°C."

[1039] The server sends the generated instructions to the device. When the device receives the instructions, it adjusts the environment based on the instructions. Specifically, it turns on the cooling device and adjusts the water temperature to 20.0°C.

[1040] After the environmental adjustment is complete, the device will again collect current environmental data from the sensors and send the new data as feedback to the server. This feedback data is very important for the generative AI and is used by the system to continue optimizing the environment in real time.

[1041] Furthermore, this system incorporates an emotion engine that recognizes the user's emotions. The emotion engine detects the user's emotional state and provides feedback to the generation AI as data. This feedback allows the generation AI to generate more appropriate environmental adjustment instructions, taking the user's emotional state into account. For example, if the user is feeling stressed, the generation AI can flexibly change the environmental adjustment instructions to generate instructions that will improve the user's emotional state.

[1042] Specific examples

[1043] For example, when a user sets up a new aquaculture system, they first install a terminal and place various sensors (water temperature sensor, pH sensor, dissolved oxygen sensor) in the tank. The terminal then collects initial data from these sensors and sends it to the server. If the server analyzes the data and detects that the water temperature is high at 22.5°C, it generates an instruction to "turn on the cooling device to lower the water temperature to 20.0°C." The instruction is sent to the terminal, which then activates the cooling device and adjusts the water temperature. The terminal then collects data again and sends it to the server for feedback.

[1044] The system is also equipped with an emotion engine that recognizes the user's emotions. For example, if the user is worried about raising the fish, the system will detect this emotion. The emotion engine sends this data to the server, and the generation AI can generate new instructions for adjusting the environment taking this information into account. This allows for optimal management of the aquaculture environment, taking the user's emotional state into account.

[1045] The above is a mode for implementing the present invention, and by using the emotion engine and generative AI together, a flexible system is provided that constantly optimizes the aquaculture environment and responds to the user's emotions. It is possible to efficiently and accurately manage the aquaculture environment without any specialized knowledge.

[1046] The processing flow will be explained below.

[1047] Step 1:

[1048] The device collects environmental data from various sensors.

[1049] Measure the water temperature from the water temperature sensor (e.g. 22.5°C).

[1050] Measure the pH level of the water quality from the pH sensor (e.g. 7.4).

[1051] Measure the amount of dissolved oxygen in the water using a dissolved oxygen sensor (e.g., 6.8 mg / L).

[1052] Step 2:

[1053] The terminal transmits the collected environmental data to the server.

[1054] The device converts the sensor data into JSON format.

[1055] The converted data is sent to the server via an HTTP POST request.

[1056] Step 3:

[1057] The server inputs the received data into the generation AI.

[1058] The server sends the received environmental data to the generated AI.

[1059] Generative AI analyzes the data and generates instructions for adjusting the environment.

[1060] Step 4:

[1061] The server sends the generated instructions to the terminal.

[1062] Convert the generated instructions into JSON format.

[1063] Send instructions to the device via an HTTP GET request.

[1064] Step 5:

[1065] The device adjusts the environment based on the instructions it receives.

[1066] If the "cooling" action is specified, the cooling device is turned on.

[1067] Operate the cooling device as instructed until the water temperature reaches 20.0°C.

[1068] Step 6:

[1069] Check the device status again after adjusting the environment.

[1070] The sensors again measure the water temperature, pH level, and dissolved oxygen.

[1071] Collect new environmental data.

[1072] Step 7:

[1073] The device sends new environmental data to the server as feedback.

[1074] Convert the new data into JSON format and send it to the server.

[1075] The server inputs new feedback data into the generation AI and uses it for the next analysis.

[1076] Step 8:

[1077] An emotion engine recognizes the user's emotional state.

[1078] It uses a camera and microphone to detect the user's facial expressions and tone of voice.

[1079] The detection results are generated as emotion data.

[1080] Step 9:

[1081] The emotion data generated by the emotion engine is sent to the server.

[1082] Emotion data is converted into JSON format and sent to the server.

[1083] Step 10:

[1084] The server inputs the emotion data into the generation AI.

[1085] The generative AI analyzes the emotional data and reflects it in instructions for adjusting the environment.

[1086] For example, if the user is feeling stressed, the AI ​​will generate instructions such as "raise the water temperature a little to enhance the relaxation effect."

[1087] Step 11:

[1088] The server generates new instructions and sends them to the terminal.

[1089] The new instructions are converted into JSON format and sent to the device via an HTTP GET request.

[1090] Step 12:

[1091] The device will then adjust the environment again based on the new instructions.

[1092] For example, it makes adjustments according to instructions, such as turning off the cooling device and turning on the heater.

[1093] These are the specific processing steps of the invention that combines the emotion engine. Detailed operations are performed at each step, and the aquaculture environment is automatically and efficiently optimized. Furthermore, by taking the user's emotions into consideration, more personalized environment management is realized.

[1094] Example 2

[1095] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1096] Conventional aquaculture systems can automatically adjust the environment based on environmental data, but they cannot manage the environment taking the user's emotions into account. As a result, if the user feels stressed or anxious, the system cannot respond according to that emotional state, making it difficult to optimally manage the aquaculture environment.

[1097] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1098] In this invention, the server includes means for generating instructions for environmental adjustment using a generating AI based on environmental data, means for detecting the user's emotions, and means for feeding back the user's emotional data to the generating AI, thereby enabling environmental adjustment that takes the user's emotional state into consideration.

[1099] "Environmental data" refers to information that indicates the state of the aquaculture environment, such as water temperature, pH level, and dissolved oxygen.

[1100] "Generative AI" is an artificial intelligence algorithm for automatically generating instructions for environmental adjustments based on collected environmental data and user emotional data.

[1101] "Environmental adjustment instructions" are specific operational instructions for adjusting water temperature, pH levels, and dissolved oxygen, including turning equipment on and off and changing settings.

[1102] "User emotions" refer to psychological states such as stress, anxiety, and relief that users feel while operating the aquaculture system.

[1103] "Collecting means" refers to devices and methods that use sensors to acquire environmental data.

[1104] "Transmission means" refers to the communication means or protocol used to transmit collected data to the server.

[1105] "Means for receiving" refers to a communication means or protocol that allows a terminal to receive instructions sent from a server.

[1106] "Adjustment means" refers to devices or mechanisms for carrying out the environmental adjustment operations instructed by the generating AI, such as cooling devices and pH adjustment devices.

[1107] The "feedback means" is a mechanism for sending the state of the environment after adjustment back to the server, which enables real-time monitoring and adjustment.

[1108] An "emotion engine" is software or hardware that analyzes a user's facial expressions, voice, etc. to detect their psychological state.

[1109] MODE FOR CARRYING OUT THE INVENTION

[1110] The present invention combines a system for automatically optimizing aquaculture environments with an emotion engine that recognizes user emotions. The system includes a means for collecting environmental data, a means for transmitting the environmental data, a means for generating instructions for adjusting the environment using a generative AI model based on the environmental data, a means for receiving the instructions, a means for adjusting the environment based on the instructions, and an emotion engine.

[1111] First, the terminal collects environmental data from various sensors. This terminal uses hardware such as a water temperature sensor, pH sensor, and dissolved oxygen sensor. For example, the terminal measures the water temperature (22.5°C) from the water temperature sensor, the water quality (pH level 7.4) from the pH sensor, and the dissolved oxygen level (6.8 mg / L) from the dissolved oxygen sensor. This allows the terminal to accurately grasp the current state of the aquaculture environment.

[1112] The device then sends the collected environmental data to the server, which converts the data into JSON format and sends it to the server using an HTTP POST request. An example of this data might look like this: {"water_temp": 22.5, "pH_level": 7.4, "dissolved_oxygen": 6.8}.

[1113] Once the server receives this data, the generative AI model analyzes it and generates optimal environmental adjustment instructions. The generative AI model uses pre-programmed algorithms to calculate the optimal adjustment method based on the collected data. For example, if the water temperature is high, the generative AI model generates the instruction "turn on the cooling device to lower the water temperature to 20.0°C."

[1114] The server sends the generated instructions to the device. When the device receives these instructions, it adjusts the environment based on the instructions. Specifically, it turns on the cooling device and adjusts the water temperature to 20.0°C. Once this process is complete, the device again collects current environmental data from the sensors and sends the new data as feedback to the server. This feedback data is crucial for the generative AI model and is used by the system to continue optimizing the environment in real time.

[1115] Furthermore, this system incorporates an emotion engine that recognizes the user's emotions. The emotion engine detects the user's emotional state using sensors such as cameras and microphones and feeds this information back to the generative AI model as data. This feedback allows the generative AI model to take the user's emotional state into account and generate more appropriate environmental adjustment instructions. For example, if the user is feeling stressed, the generative AI model can flexibly change the environmental adjustment instructions to generate instructions that will improve the user's emotional state.

[1116] Specific examples

[1117] For example, when a user sets up a new aquaculture system, they first install a terminal and place various sensors (water temperature sensor, pH sensor, dissolved oxygen sensor) in the tank. The terminal then collects initial data from these sensors and sends it to the server. If the server analyzes the data and detects that the water temperature is high at 22.5°C, it generates an instruction to "turn on the cooling device to lower the water temperature to 20.0°C." The instruction is sent to the terminal, which then activates the cooling device and adjusts the water temperature. The terminal then collects data again and sends it to the server for feedback.

[1118] The system also features an emotion engine that recognizes the user's emotions. For example, if the user is worried about their care, the system will detect their emotions. The emotion engine sends the data to the server, and the generative AI model can generate new environmental adjustment instructions that take this information into account. This allows for optimal management of the aquaculture environment, taking into account the user's emotional state.

[1119] Example prompt sentence:

[1120] Generate environmental adjustment instructions based on data collected from vivarium sensors.

[1121] Initial data:

[1122] Water temperature: 22.5°C

[1123] pH level: 7.4

[1124] Dissolved oxygen: 6.8 mg / L

[1125] User Emotion: Stress

[1126] The above is an embodiment of the present invention, and by using the emotion engine and generative AI model together, a flexible system is provided that constantly optimizes the aquaculture environment and responds to the user's emotions. It is possible to efficiently and accurately manage the aquaculture environment without any specialized knowledge.

[1127] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1128] System program processing flow

[1129] Step 1:

[1130] The device collects environmental data from sensors. The device uses water temperature, pH, and dissolved oxygen sensors to collect each type of data. The collected data is stored in the device's memory.

[1131] input:

[1132] Data from the water temperature sensor

[1133] Data from pH sensors

[1134] Data from a dissolved oxygen sensor

[1135] Specific behavior:

[1136] The water temperature sensor measures a water temperature of 22.5°C.

[1137] The pH sensor measures a pH level of 7.4.

[1138] The dissolved oxygen sensor measures 6.8 mg / L of dissolved oxygen.

[1139] output:

[1140] Collected environmental data (e.g., {"water_temp": 22.5, "pH_level": 7.4, "dissolved_oxygen": 6.8}) is saved on the device.

[1141] Step 2:

[1142] The device sends the collected environmental data to the server, which converts the data into JSON format and sends it using an HTTP POST request.

[1143] input:

[1144] Environmental data stored on the device

[1145] Specific behavior:

[1146] The device converts the environment data into JSON format.

[1147] The device sends an HTTP POST request to the server.

[1148] output:

[1149] Environmental data sent to the server

[1150] Step 3:

[1151] The server receives the data, and the generative AI model generates instructions for adjusting the environment. After the data is received, the generative AI analyzes the data and generates instructions for optimal environmental adjustment.

[1152] input:

[1153] Environmental data received by the server

[1154] Specific behavior:

[1155] The server receives the HTTP request and parses the environment data.

[1156] A generative AI model performs calculations based on the data.

[1157] output:

[1158] Environmental adjustment instructions (e.g., "Turn on the chiller to reduce the water temperature to 20.0°C")

[1159] Step 4:

[1160] The server generates instructions and sends them to the device, where they are again converted to JSON format and sent using an HTTP POST request.

[1161] input:

[1162] Environmental adjustment instructions generated by a generative AI model

[1163] Specific behavior:

[1164] The server converts the instructions into JSON format.

[1165] The server sends an HTTP POST request to the device.

[1166] output:

[1167] Environmental adjustment instructions sent to the device

[1168] Step 5:

[1169] The device adjusts the environment based on instructions. Specifically, it adjusts the environment by operating cooling devices, etc., and performs operations such as turning devices on and off according to instructions.

[1170] input:

[1171] Received environmental adjustment instructions

[1172] Specific behavior:

[1173] The device turns on the cooling device and reduces the water temperature to 20.0°C.

[1174] output:

[1175] Environmental adjustments are made (e.g., a cooling device is turned on)

[1176] Step 6:

[1177] The device collects the data from the sensor again after adjusting the environment and feeds it back to the server. The adjusted data is again converted into JSON format and sent to the server.

[1178] input:

[1179] Adjusted environmental data

[1180] Specific behavior:

[1181] The sensors measure the environmental data again.

[1182] The data collected by the device is converted into JSON format and sent to the server.

[1183] output:

[1184] Adjusted environmental data sent to the server

[1185] Step 7:

[1186] The emotion engine detects the user's emotions and feeds them back to the generative AI model. The camera and microphone are used to analyze the user's emotions and send the data to the server.

[1187] input:

[1188] User's facial expression and voice data

[1189] Specific behavior:

[1190] The camera captures the user's facial expressions.

[1191] A microphone collects the user's voice.

[1192] The emotion engine analyzes this data.

[1193] output:

[1194] User emotional data (e.g., stress level)

[1195] Step 8:

[1196] The generative AI model generates new instructions for adjusting the environment, taking into account the user's emotional state. New instructions that reflect the user's emotional data are generated and applied to the system.

[1197] input:

[1198] User emotion data

[1199] Environmental Data

[1200] Specific behavior:

[1201] A generative AI model analyzes user emotional data.

[1202] Calculations are performed by combining environmental data and emotional data.

[1203] output:

[1204] New environmental adjustment instructions (e.g., "Reduce light levels to provide a relaxing environment")

[1205] The above is a detailed flow of the program processing of this system. By clarifying the specific inputs, outputs, and processing details at each step, the operation of the system is easy to understand.

[1206] (Application example 2)

[1207] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1208] Modern factories and production environments require optimal maintenance of environmental parameters such as temperature, humidity, and air quality. However, continuously monitoring these environmental parameters and optimally adjusting them in real time requires a great deal of effort and specialized knowledge. Furthermore, because workers' emotional states have a significant impact on productivity, it is important to adjust the environment while taking this into account, but this has been difficult to achieve with existing systems. Therefore, there is a strong demand for the development of a system that simultaneously considers environmental parameters and emotional states and maintains both optimally.

[1209] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the system includes means for collecting environmental data, means for transmitting the environmental data, means for generating instructions for environmental adjustment using a generation AI based on the environmental data, means for receiving the instructions, means for adjusting the environment based on the instructions, means for recognizing the user's emotional state, means for transmitting feedback to the generation AI based on the emotional state, and means for the generation AI to generate instructions for environmental adjustment taking the emotional state into consideration. This makes it possible to simultaneously optimize environmental parameters and the user's emotional state, thereby maintaining a safer and more efficient production environment.

[1210] "Environmental Data" is information about environmental parameters such as temperature, humidity, air quality, water temperature, pH levels, and dissolved oxygen.

[1211] "Means for collecting environmental data" refers to a method or device that uses a sensor to measure environmental parameters and acquire them as data.

[1212] The "means for transmitting environmental data" refers to a method or apparatus for transmitting collected environmental data to a server or other device via a network.

[1213] "Generative AI" is a system that uses artificial intelligence to generate optimal environmental adjustment instructions based on input data.

[1214] "Means for generating instructions for environmental adjustment" refers to a method or device that generates optimal instructions for environmental adjustment based on environmental data collected using a generation AI.

[1215] The "means for receiving instructions" refers to a method or apparatus for receiving generated environment adjustment instructions from a server or other device.

[1216] A "means for adjusting the environment" is a method or device for actually adjusting environmental parameters (temperature, humidity, etc.) based on received instructions.

[1217] The "means for recognizing the emotional state of a user" refers to a method or device for recognizing the emotional state of a user by analyzing the user's facial expressions, actions, tone of voice, etc.

[1218] "Means for sending feedback to the generation AI based on emotional state" refers to a method or device for sending the recognized emotional state of the user to the generation AI as feedback.

[1219] "Means for generating environmental adjustment instructions that take into account the emotional state of the user" refers to a method or device that uses a generating AI to generate optimal environmental adjustment instructions that take into account the emotional state of the user.

[1220] In this invention, the system mainly comprises the following components: means for collecting environmental data, means for transmitting the environmental data, means for generating instructions for adjusting the environment using a generating AI based on the environmental data, means for receiving the instructions, and means for adjusting the environment based on the instructions. Furthermore, the system includes means for recognizing the user's emotional state and transmitting it as feedback to the generating AI.

[1221] System Program

[1222] The system uses sensors to collect environmental data (temperature, humidity, air quality, etc.) within the factory. These sensors include temperature sensors, humidity sensors, and air quality sensors. The collected data is sent to a cloud server via the terminal. The data is converted into JSON format and sent to the server using an HTTP POST request.

[1223] The server analyzes the collected environmental data and generates instructions for optimal environmental adjustments. It uses a generative AI model to generate specific instructions for adjusting environmental parameters based on the data. For example, if the temperature is high, the AI ​​generates instructions such as "Turn on the air conditioner and set the temperature to 25°C."

[1224] The generated instructions are then sent back to the device, which then adjusts the environment based on the received instructions. Specifically, it operates equipment such as air conditioners and humidifiers to adjust the temperature and humidity to the specified level.

[1225] On the other hand, cameras and microphones are used to recognize the user's emotional state. The data collected by these devices is analyzed by an emotion recognition engine to identify the user's emotional state (e.g., stress, fatigue, etc.). This emotional data is also sent to a cloud server and used as feedback for the generative AI.

[1226] The generative AI generates instructions for adjusting the environment taking into account the user's emotional state. For example, if the user is feeling stressed, the generative AI can give instructions such as "soften the lighting in the work area" or "play background music."

[1227] Specific examples

[1228] If the temperature in a factory is 30°C, humidity is 45%, and air quality is 90AQI, the system works as follows: The terminal collects this environmental data and sends it to the server. The generative AI model then analyzes the data and generates instructions such as "turn on the air conditioner and set the temperature to 25°C." This instruction is sent to the terminal, which operates the air conditioner to adjust the temperature.

[1229] Additionally, if the user is feeling stressed, the emotion recognition engine will detect this state and generate instructions such as "soften the lighting in the work area to reduce stress." This instruction is also sent to the device, and the actual environmental adjustment is carried out. For example, a prompt might be entered in the form of "The temperature is 30°C, the humidity is 45%, and the air quality is 90AQI. Please generate instructions for optimal temperature and humidity adjustment."

[1230] This allows the environment within the factory to be kept optimal at all times and allows for flexible environmental adjustments that take into account the emotional state of workers.

[1231] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1232] Step 1:

[1233] The terminal collects environmental data from various sensors (temperature, humidity, and air quality sensors). This involves obtaining temperature, humidity, and air quality values ​​from sensors installed at various locations in the factory. The input is the raw data from the sensors. The output is the collected environmental data (e.g., temperature 30°C, humidity 45%, air quality 90 AQI).

[1234] Step 2:

[1235] The environmental data collected by the device is converted into JSON format and sent to the cloud server using an HTTP POST request. This process involves data conversion and network transmission. The input is the environmental data obtained in step 1, and the output is the JSON-formatted data sent to the server.

[1236] Step 3:

[1237] The server receives the environmental data, analyzes it using a generative AI model, and generates instructions for adjusting the environment. At this stage, temperature, humidity, and air quality values ​​are analyzed to determine the optimal adjustment method. The input is the environmental data sent to the server, and the output is the generated adjustment instructions (e.g., turn on the air conditioner and set the temperature to 25°C).

[1238] Step 4:

[1239] The server sends the generated environmental adjustment instructions to the terminal. In this process, the generated instructions are sent to the terminal using an HTTP GET request, etc. The input is the generated adjustment instructions, and the output is the instructions sent to the terminal.

[1240] Step 5:

[1241] The terminal adjusts the environment based on the received instructions. At this stage, it operates equipment such as air conditioners and humidifiers to set the temperature and humidity as instructed. The input is the adjustment instruction received from the server, and the output is the adjusted environmental parameters (e.g., temperature 25°C).

[1242] Step 6:

[1243] The terminal collects the adjusted environmental data again and sends the new data to the server as feedback. This involves collecting the adjusted environmental data and sending it to the server. The input is the adjusted environmental data, and the output is the feedback data sent to the server.

[1244] Step 7:

[1245] The device collects the user's emotional state using a camera or microphone. In this process, an emotion recognition engine analyzes facial expressions and tone of voice to recognize the emotional state. The input is the collected audio and video data, and the output is the recognized emotional state (e.g., high stress level).

[1246] Step 8:

[1247] The device converts the user's emotional state into JSON format and sends it to the cloud server using an HTTP POST request. The input is the recognized emotional state, and the output is the emotional data sent to the server.

[1248] Step 9:

[1249] The server receives the emotion data and uses a generative AI model to generate instructions for adjusting the environment that take the emotional state into account. In this process, the emotion data and environmental data are analyzed comprehensively to generate more appropriate adjustment instructions. The input is the emotional state and environmental data, and the output is adjustment instructions that take the emotion into account.

[1250] Step 10:

[1251] The server sends instructions for adjusting the environment taking into account the generated emotions to the terminal, and the terminal then adjusts the environment again based on the instructions received. The input is the adjustment instructions taking into account the emotions, and the output is the further adjusted environmental parameters.

[1252] This allows the system to simultaneously optimize environmental parameters and the user's emotional state, maintaining a safer and more efficient production environment.

[1253] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[1254] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1255] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314.

[1256] [Fourth embodiment]

[1257] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1258] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[1259] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1260] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[1261] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[1262] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[1263] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1264] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[1265] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1266] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[1267] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1268] In the robot 414, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1269] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1270] The present invention provides a system for automatically optimizing an aquaculture environment, which includes a means for collecting environmental data, a means for transmitting the environmental data, a means for generating instructions for adjusting the environment using a generation AI based on the environmental data, a means for receiving the instructions, and a means for adjusting the environment based on the instructions.

[1271] In this system, the terminal first collects environmental data from various sensors. The collected environmental data includes water temperature, pH level, and dissolved oxygen. For example, the terminal measures the water temperature (22.5°C) from the water temperature sensor, the water quality (pH level) (7.4) from the pH sensor, and the dissolved oxygen level (6.8 mg / L) from the dissolved oxygen sensor.

[1272] Next, the device sends the collected environmental data to the server. This data is converted to JSON format and sent to the server using an HTTP POST request. Once the server receives this data, the generating AI analyzes it and generates instructions for optimal environmental adjustment. For example, if the water temperature is high, the generating AI generates the instruction "turn on the cooling device to lower the water temperature to 20.0°C."

[1273] The generated instruction is sent from the server to the device. When the device receives the instruction, it adjusts the environment based on the instruction. Specifically, it turns on the cooling device and adjusts the water temperature to 20.0°C.

[1274] After the environmental adjustment is complete, the device will again collect current environmental data from the sensors and send the new data as feedback to the server. This feedback data is very important for the generative AI and is used by the system to continue optimizing the environment in real time.

[1275] Specific examples

[1276] For example, when a user sets up a new aquaculture system, they first install a terminal and place various sensors (water temperature sensor, pH sensor, dissolved oxygen sensor) in the tank. The terminal then collects initial data from these sensors and sends it to the server. If the server analyzes the data and detects that the water temperature is high at 22.5°C, it generates an instruction to "turn on the cooling device to lower the water temperature to 20.0°C." The instruction is sent to the terminal, which then activates the cooling device and adjusts the water temperature. The terminal then collects data again and sends it to the server as feedback. This process allows users to efficiently and accurately manage the aquaculture environment without any specialized knowledge.

[1277] The above is a form for implementing the present invention, and by automating all processes of environmental data collection, analysis, instruction generation, environmental adjustment, and feedback, it is possible to accurately and efficiently optimize the aquaculture environment.

[1278] The processing flow will be explained below.

[1279] Step 1:

[1280] The device collects environmental data from various sensors.

[1281] Measure the water temperature from the water temperature sensor (e.g. 22.5°C).

[1282] Measure the pH level of the water quality from the pH sensor (e.g. 7.4).

[1283] Measure the amount of dissolved oxygen in the water using a dissolved oxygen sensor (e.g., 6.8 mg / L).

[1284] Step 2:

[1285] The terminal transmits the collected environmental data to the server.

[1286] The device converts the sensor data into JSON format.

[1287] The converted data is sent to the server via an HTTP POST request.

[1288] Step 3:

[1289] The server inputs the received data into the generation AI.

[1290] The server sends the received environmental data to the generated AI.

[1291] Generative AI analyzes the data and generates instructions for adjusting the environment.

[1292] Step 4:

[1293] The server sends the generated instructions to the terminal.

[1294] Convert the generated instructions into JSON format.

[1295] Send instructions to the device via an HTTP GET request.

[1296] Step 5:

[1297] The device adjusts the environment based on the instructions it receives.

[1298] If the "cooling" action is specified, the cooling device is turned on.

[1299] Operate the cooling device as instructed until the water temperature reaches 20.0°C.

[1300] Step 6:

[1301] Check the device status again after adjusting the environment.

[1302] The sensors again measure the water temperature, pH level, and dissolved oxygen.

[1303] Collect new environmental data.

[1304] Step 7:

[1305] The device sends new environmental data to the server as feedback.

[1306] Convert the new data into JSON format and send it to the server.

[1307] At the same time, the data is set to be used for further analysis and for generating the next instruction.

[1308] The above are the specific processing steps of the present invention. By performing various specific operations at each step, the aquaculture environment is automatically and efficiently optimized.

[1309] Example 1

[1310] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1311] Optimal management of the aquaculture environment requires collecting environmental data in real time and taking appropriate measures promptly. However, conventional systems often require specialized knowledge and make efficient management difficult. Furthermore, the difficulty of responding quickly to environmental fluctuations has led to problems such as reduced production efficiency and wasted resources. The present invention aims to solve these problems and provide an aquaculture environment optimization system that can be easily operated even by non-experts.

[1312] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1313] In this invention, the server includes means for measuring environmental data, means for converting and transmitting the environmental data, means for generating instructions for adjusting the environment using an artificial intelligence model based on the environmental data, means for receiving and analyzing the instructions, and means for controlling the environment based on the instructions, thereby enabling real-time collection and analysis of environmental data and rapid environmental adjustment.

[1314] "Environmental data" refers to measurements such as temperature, acidity, and dissolved oxygen levels related to the ecosystem or aquaculture environment.

[1315] "Means of measurement" refers to the sensors and measuring devices used to obtain environmental data.

[1316] "Means for converting and transmitting" refers to a device or software that converts collected environmental data into a specified format and transmits it to other devices such as a server via a network.

[1317] "Artificial intelligence model" refers to machine learning and deep learning techniques used to analyze collected data and generate optimal environmental adjustment instructions.

[1318] "Means for receiving and analyzing instructions" refers to devices or software that receive instructions generated by an AI model via a network, interpret their contents, and identify the required actions.

[1319] "Means for controlling the environment" refers to cooling devices or other control systems for adjusting the temperature and acidity of the aquaculture environment based on instructions received.

[1320] "Means for sending feedback" refers to devices or software that recollect data after adjusting the environment and send it to the artificial intelligence model.

[1321] The present invention provides a system for automatically optimizing an aquaculture environment, the system including means for measuring environmental data, means for converting and transmitting the environmental data, means for generating instructions for adjusting the environment using an artificial intelligence model based on the environmental data, means for receiving and analyzing the instructions, and means for controlling the environment based on the instructions.

[1322] First, the device measures environmental data from various sensors, specifically water temperature, acidity, and dissolved oxygen sensors, to collect the following data:

[1323] Water temperature sensor: Measures water temperature 22.5°C.

[1324] Acidity sensor: Measures pH level 7.4.

[1325] Dissolved oxygen sensor: Measures dissolved oxygen levels of 6.8 mg / L.

[1326] Next, convert the environmental data collected by the device into JSON format. For example, convert the data into the following format.

[1327] json

[1328] {

[1329] "water_temperature": 22.5,

[1330] "ph_level": 7.4,

[1331] "dissolved_oxygen": 6.8

[1332] }

[1333] This JSON data is sent to the server using an HTTP POST request.

[1334] The server receives the data using an HTTP request handler. Based on the received data, the AI ​​model generates instructions for adjusting the environment. For example, the following prompt sentences can be used to analyze the data and generate optimal instructions:

[1335] plaintext

[1336] "Adjust the water temperature to 22.5°C, pH level to 7.4, and dissolved oxygen to 6.8 mg / L. The optimum water temperature should be 20.0°C."

[1337] The generation AI generates the instruction "Turn on the cooling device to lower the water temperature to 20.0°C."

[1338] The generated instructions are sent from the server to the terminal. Specifically, the generated instructions are converted into JSON format and sent to the terminal again using an HTTP POST request.

[1339] The device controls the environment according to the received instructions. For example,

[1340] plaintext

[1341] "Turn on the cooling system and adjust the water temperature to 20.0°C."

[1342] Based on this instruction, the terminal issues a control signal to the cooling device, causing the cooling device to operate.

[1343] After the environmental adjustment is complete, the device again collects current environmental data from the sensors, converts the new data into JSON format again, and sends it to the server as feedback. The server continues to analyze the received feedback data in real time, constantly monitoring whether the environment is being optimized.

[1344] This system allows users to efficiently and accurately manage the aquaculture environment without specialized knowledge, which is expected to improve production efficiency and maximize resource utilization.

[1345] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1346] Step 1:

[1347] The terminal measures environmental data from various sensors. Inputs include data from water temperature sensors, acidity sensors, and dissolved oxygen sensors. Specifically, the terminal collects the following data:

[1348] Water temperature: 22.5°C

[1349] Acidity: pH 7.4

[1350] Dissolved oxygen: 6.8 mg / L

[1351] The output is continuously acquired sensor data.

[1352] Step 2:

[1353] The environmental data collected by the device is converted into JSON format. Specifically, the following data conversion is performed: The input is the value collected by the sensor, and the output is JSON format data.

[1354] {

[1355] "water_temperature": 22.5,

[1356] "ph_level": 7.4,

[1357] "dissolved_oxygen": 6.8

[1358] }

[1359] The converted JSON data is sent to the server via an HTTP POST request.

[1360] Step 3:

[1361] The server receives JSON formatted data. The server retrieves the data using an HTTP request handler. Specifically, the received data is parsed as follows: the input is JSON formatted environment data, and the output is the parsed data.

[1362] {

[1363] "water_temperature": 22.5,

[1364] "ph_level": 7.4,

[1365] "dissolved_oxygen": 6.8

[1366] }

[1367] Step 4:

[1368] Based on the data received by the server, the generative AI model generates instructions for adjusting the environment. The input is the analyzed environmental data and the set reference values. The following prompt sentences are used:

[1369] plaintext

[1370] "Adjust the water temperature to 22.5°C, pH level to 7.4, and dissolved oxygen to 6.8 mg / L. The optimum water temperature should be 20.0°C."

[1371] The generation AI generates the instruction "Turn on the cooling device to lower the water temperature to 20.0°C." The output is a specific environmental adjustment instruction.

[1372] Step 5:

[1373] The server sends the generated instructions to the terminal. The input is the instruction created by the generation AI, and the output is the instruction converted to JSON format.

[1374] json

[1375] {

[1376] "action": "activate_cooling",

[1377] "target_temperature": 20.0

[1378] }

[1379] This data is sent to the device via an HTTP POST request.

[1380] Step 6:

[1381] The terminal receives and analyzes the instructions to control the environment. Specifically, it performs the following operations: The input is the received environment adjustment instruction, and the output is the actual environment adjustment action.

[1382] plaintext

[1383] "Turn on the cooling system and adjust the water temperature to 20.0°C."

[1384] The terminal issues a control signal to the cooling device to activate the cooling device.

[1385] Step 7:

[1386] The device again collects current environmental data from the sensors, converts the new data into JSON format again, and sends it to the server as feedback. The input is the adjusted environmental data, and the output is the JSON data sent again via an HTTP POST request.

[1387] json

[1388] {

[1389] "water_temperature": 20.0,

[1390] "ph_level": 7.4,

[1391] "dissolved_oxygen": 6.8

[1392] }

[1393] Based on the above explanation of each processing step, this system can automatically optimize the aquaculture environment.

[1394] (Application example 1)

[1395] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1396] Properly managing the package storage environment in logistics centers is extremely important. However, manually managing environmental data such as temperature, humidity, and CO2 levels is time-consuming and accuracy is difficult to guarantee. Furthermore, if workers were to perform all environmental adjustments themselves, specialized knowledge would be required, making efficient and accurate environmental management difficult. This invention solves these problems and provides a system that automatically optimizes the package storage environment in logistics centers.

[1397] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1398] In this invention, the server includes means for collecting environmental data, means for generating instructions for adjusting the environment using a generative AI model based on the environmental data, means for generating instructions for optimizing the package storage environment in the logistics center, means for visualizing and executing the instructions on a smartphone, and means for checking the state after the environmental adjustment and sending feedback to the generative AI model. This enables efficient and accurate management of the package storage environment in the logistics center even if the worker does not have specialized knowledge.

[1399] "Environmental Data" is data related to environmental conditions within a logistics center, such as temperature, humidity, and CO2 levels.

[1400] A "generative AI model" is an artificial intelligence model that generates optimal environmental adjustment instructions from collected environmental data.

[1401] "Environmental adjustment instructions" are specific operational instructions for optimizing the environmental conditions within the logistics center, created by the generative AI model based on environmental data.

[1402] "Logistics Center" means a facility where package storage and shipping operations are carried out.

[1403] "Package storage environment" refers to environmental conditions such as temperature, humidity, and CO2 levels that are managed within the logistics center to maintain product quality.

[1404] A "smartphone" is a portable information terminal that can visualize instructions and perform environmental adjustments.

[1405] "Feedback" refers to data sent to the generative AI model after adjusting the environment, to help with the accuracy of the model and the generation of next instructions.

[1406] MODE FOR CARRYING OUT THE INVENTION

[1407] The present invention provides a system for automatically optimizing the package storage environment in a logistics center. Specific embodiments will be described below.

[1408] 1. System Configuration

[1409] The system consists of the following main components:

[1410] Sensors that collect environmental data (temperature sensor, humidity sensor, CO2 sensor)

[1411] A smartphone app that collects environmental data and sends it to a server

[1412] A generative AI model that generates environmental adjustment instructions

[1413] Actuators that receive instructions and adjust the environment (chillers, humidifiers, ventilation systems, etc.)

[1414] A means of collecting feedback data after adjusting the environment and sending it to the server

[1415] 2. System Operation

[1416] The server first receives environmental data (temperature, humidity, CO2 level) collected from each sensor. This data is sent to the server via a smartphone app. The data is converted to JSON format and sent using an HTTP POST request.

[1417] 3. Data analysis and instruction generation

[1418] Once the server receives the environmental data, the generative AI model analyzes the data and generates optimal environmental adjustment instructions. For example, if the collected data is a temperature of 23.5 degrees, humidity of 50%, and CO2 level of 900 ppm, the generative AI model will generate instructions such as "turn on the humidifier to adjust the humidity to 45%."

[1419] 4. Execution of instructions

[1420] Instructions are sent from the server to a smartphone app, which visualizes the instructions and notifies the worker of the necessary operations. The worker follows the notifications and adjusts the environment based on the instructions. Specifically, the smartphone app controls cooling devices to adjust temperature, humidifiers to adjust humidity, and ventilation systems to adjust CO2 levels.

[1421] 5. Gathering Feedback

[1422] After the environmental adjustment is completed, the sensors collect environmental data again and send the new data to the server as feedback. This feedback data is very important for the generative AI model and is used as the basis for generating the next adjustment instructions.

[1423] 6. Examples of concrete examples and prompts

[1424] For example, if humidity levels rise in a logistics center, posing a risk of a decline in the quality of stored packages, a smartphone app will send humidity data collected from sensors to a server. A generative AI model will analyze the data and generate instructions to turn on the ventilation system to reduce humidity. This instruction will then be communicated to a worker via the smartphone app, who will then activate the ventilation system and adjust the environment.

[1425] Example prompts for generative AI models:

[1426] current_temperature: 23.5

[1427] current_humidity: 50

[1428] current_co2_level: 900

[1429] Required adjustments for optimal storage conditions:

[1430] This system makes it possible to monitor the package storage environment in a logistics center in real time and automatically optimize it, allowing the system to efficiently and accurately manage the environment without requiring workers to have specialized knowledge.

[1431] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1432] Step 1:

[1433] The terminal collects environmental data. The terminal obtains data in real time from temperature, humidity, and CO2 sensors installed in the logistics center. For example, the temperature sensor collects 23.5 degrees, the humidity sensor collects 50%, and the CO2 sensor collects 900 ppm (input: data from various environmental sensors, output: collected environmental data).

[1434] Step 2:

[1435] The device sends the collected environmental data to the server. The data is converted to JSON format and sent to the server using an HTTP POST request. For example, the collected data is sent in JSON format as {"temperature": 23.5, "humidity": 50, "co2_level": 900} (Input: Collected environmental data, Output: JSON data sent to the server).

[1436] Step 3:

[1437] The server receives and analyzes environmental data. The generative AI model generates optimal environmental adjustment instructions based on the environmental data. For example, if the humidity is high, the generative AI model generates instructions such as "turn on the humidifier to adjust the humidity to 45%" (Input: received environmental data, Output: generated environmental adjustment instructions).

[1438] Step 4:

[1439] The server generates and sends the environmental adjustment instructions to the device. The instructions are visualized via a smartphone app. For example, an instruction such as "Turn on the humidifier to adjust the humidity to 45%" is sent to the device (Input: Generated environmental adjustment instructions, Output: Visualization of the instructions on the device).

[1440] Step 5:

[1441] The user receives and executes instructions on a smartphone app. The user checks the notification and operates an actuator (such as a cooling device, humidifier, or ventilation system). For example, the user turns on the ventilation system according to the instructions on the smartphone app (input: environmental adjustment instruction from the server, output: executed environmental adjustment).

[1442] Step 6:

[1443] After the environmental adjustment is complete, the device collects environmental data again and sends feedback to the server. The new environmental data is sent as feedback in JSON format. For example, the data after the environmental adjustment is sent in JSON format as {"temperature": 23.0, "humidity": 45, "co2_level": 850} (input: adjusted environmental data, output: sending feedback data).

[1444] Step 7:

[1445] The server receives the feedback data and updates the generative AI model. Based on the feedback data, the generative AI model updates the data used when generating the next environmental adjustment instruction. This allows the system to perform optimal environmental adjustments from the next time onwards (input: feedback data, output: updated generative AI model).

[1446] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1447] The present invention combines a system for automatically optimizing an aquaculture environment with an emotion engine that recognizes user emotions. The system includes a means for collecting environmental data, a means for transmitting the environmental data, a means for generating instructions for adjusting the environment using a generation AI based on the environmental data, a means for receiving the instructions, a means for adjusting the environment based on the instructions, and an emotion engine.

[1448] In this system, the terminal first collects environmental data from various sensors. The collected environmental data includes water temperature, pH level, and dissolved oxygen. For example, the terminal measures the water temperature (22.5°C) from the water temperature sensor, the water quality (pH level) (7.4) from the pH sensor, and the dissolved oxygen level (6.8 mg / L) from the dissolved oxygen sensor.

[1449] The device then sends the collected environmental data to the server. This data is converted to JSON format and sent to the server using an HTTP POST request. Once the server receives this data, the generating AI analyzes it and generates instructions for optimal environmental adjustments. For example, if the water temperature is high, the generating AI generates the instruction "turn on the cooling device to lower the water temperature to 20.0°C."

[1450] The server sends the generated instructions to the device. When the device receives the instructions, it adjusts the environment based on the instructions. Specifically, it turns on the cooling device and adjusts the water temperature to 20.0°C.

[1451] After the environmental adjustment is complete, the device will again collect current environmental data from the sensors and send the new data as feedback to the server. This feedback data is very important for the generative AI and is used by the system to continue optimizing the environment in real time.

[1452] Furthermore, this system incorporates an emotion engine that recognizes the user's emotions. The emotion engine detects the user's emotional state and provides feedback to the generation AI as data. This feedback allows the generation AI to generate more appropriate environmental adjustment instructions, taking the user's emotional state into account. For example, if the user is feeling stressed, the generation AI can flexibly change the environmental adjustment instructions to generate instructions that will improve the user's emotional state.

[1453] Specific examples

[1454] For example, when a user sets up a new aquaculture system, they first install a terminal and place various sensors (water temperature sensor, pH sensor, dissolved oxygen sensor) in the tank. The terminal then collects initial data from these sensors and sends it to the server. If the server analyzes the data and detects that the water temperature is high at 22.5°C, it generates an instruction to "turn on the cooling device to lower the water temperature to 20.0°C." The instruction is sent to the terminal, which then activates the cooling device and adjusts the water temperature. The terminal then collects data again and sends it to the server for feedback.

[1455] The system is also equipped with an emotion engine that recognizes the user's emotions. For example, if the user is worried about raising the fish, the system will detect this emotion. The emotion engine sends this data to the server, and the generation AI can generate new instructions for adjusting the environment taking this information into account. This allows for optimal management of the aquaculture environment, taking the user's emotional state into account.

[1456] The above is a mode for implementing the present invention, and by using the emotion engine and generative AI together, a flexible system is provided that constantly optimizes the aquaculture environment and responds to the user's emotions. It is possible to efficiently and accurately manage the aquaculture environment without any specialized knowledge.

[1457] The processing flow will be explained below.

[1458] Step 1:

[1459] The device collects environmental data from various sensors.

[1460] Measure the water temperature from the water temperature sensor (e.g. 22.5°C).

[1461] Measure the pH level of the water quality from the pH sensor (e.g. 7.4).

[1462] Measure the amount of dissolved oxygen in the water using a dissolved oxygen sensor (e.g., 6.8 mg / L).

[1463] Step 2:

[1464] The terminal transmits the collected environmental data to the server.

[1465] The device converts the sensor data into JSON format.

[1466] The converted data is sent to the server via an HTTP POST request.

[1467] Step 3:

[1468] The server inputs the received data into the generation AI.

[1469] The server sends the received environmental data to the generated AI.

[1470] Generative AI analyzes the data and generates instructions for adjusting the environment.

[1471] Step 4:

[1472] The server sends the generated instructions to the terminal.

[1473] Convert the generated instructions into JSON format.

[1474] Send instructions to the device via an HTTP GET request.

[1475] Step 5:

[1476] The device adjusts the environment based on the instructions it receives.

[1477] If the "cooling" action is specified, the cooling device is turned on.

[1478] Operate the cooling device as instructed until the water temperature reaches 20.0°C.

[1479] Step 6:

[1480] Check the device status again after adjusting the environment.

[1481] The sensors again measure the water temperature, pH level, and dissolved oxygen.

[1482] Collect new environmental data.

[1483] Step 7:

[1484] The device sends new environmental data to the server as feedback.

[1485] Convert the new data into JSON format and send it to the server.

[1486] The server inputs new feedback data into the generation AI and uses it for the next analysis.

[1487] Step 8:

[1488] An emotion engine recognizes the user's emotional state.

[1489] It uses a camera and microphone to detect the user's facial expressions and tone of voice.

[1490] The detection results are generated as emotion data.

[1491] Step 9:

[1492] The emotion data generated by the emotion engine is sent to the server.

[1493] Emotion data is converted into JSON format and sent to the server.

[1494] Step 10:

[1495] The server inputs the emotion data into the generation AI.

[1496] The generative AI analyzes the emotional data and reflects it in instructions for adjusting the environment.

[1497] For example, if the user is feeling stressed, the AI ​​will generate instructions such as "raise the water temperature a little to enhance the relaxation effect."

[1498] Step 11:

[1499] The server generates new instructions and sends them to the terminal.

[1500] The new instructions are converted into JSON format and sent to the device via an HTTP GET request.

[1501] Step 12:

[1502] The device will then adjust the environment again based on the new instructions.

[1503] For example, it makes adjustments according to instructions, such as turning off the cooling device and turning on the heater.

[1504] These are the specific processing steps of the invention that combines the emotion engine. Detailed operations are performed at each step, and the aquaculture environment is automatically and efficiently optimized. Furthermore, by taking the user's emotions into consideration, more personalized environment management is realized.

[1505] Example 2

[1506] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1507] Conventional aquaculture systems can automatically adjust the environment based on environmental data, but they cannot manage the environment taking the user's emotions into account. As a result, if the user feels stressed or anxious, the system cannot respond according to that emotional state, making it difficult to optimally manage the aquaculture environment.

[1508] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1509] In this invention, the server includes means for generating instructions for environmental adjustment using a generating AI based on environmental data, means for detecting the user's emotions, and means for feeding back the user's emotional data to the generating AI, thereby enabling environmental adjustment that takes the user's emotional state into consideration.

[1510] "Environmental data" refers to information that indicates the state of the aquaculture environment, such as water temperature, pH level, and dissolved oxygen.

[1511] "Generative AI" is an artificial intelligence algorithm for automatically generating instructions for environmental adjustments based on collected environmental data and user emotional data.

[1512] "Environmental adjustment instructions" are specific operational instructions for adjusting water temperature, pH levels, and dissolved oxygen, including turning equipment on and off and changing settings.

[1513] "User emotions" refer to psychological states such as stress, anxiety, and relief that users feel while operating the aquaculture system.

[1514] "Collecting means" refers to devices and methods that use sensors to acquire environmental data.

[1515] "Transmission means" refers to the communication means or protocol used to transmit collected data to the server.

[1516] "Means for receiving" refers to a communication means or protocol that allows a terminal to receive instructions sent from a server.

[1517] "Adjustment means" refers to devices or mechanisms for carrying out the environmental adjustment operations instructed by the generating AI, such as cooling devices and pH adjustment devices.

[1518] The "feedback means" is a mechanism for sending the state of the environment after adjustment back to the server, which enables real-time monitoring and adjustment.

[1519] An "emotion engine" is software or hardware that analyzes a user's facial expressions, voice, etc. to detect their psychological state.

[1520] MODE FOR CARRYING OUT THE INVENTION

[1521] The present invention combines a system for automatically optimizing aquaculture environments with an emotion engine that recognizes user emotions. The system includes a means for collecting environmental data, a means for transmitting the environmental data, a means for generating instructions for adjusting the environment using a generative AI model based on the environmental data, a means for receiving the instructions, a means for adjusting the environment based on the instructions, and an emotion engine.

[1522] First, the terminal collects environmental data from various sensors. This terminal uses hardware such as a water temperature sensor, pH sensor, and dissolved oxygen sensor. For example, the terminal measures the water temperature (22.5°C) from the water temperature sensor, the water quality (pH level 7.4) from the pH sensor, and the dissolved oxygen level (6.8 mg / L) from the dissolved oxygen sensor. This allows the terminal to accurately grasp the current state of the aquaculture environment.

[1523] The device then sends the collected environmental data to the server, which converts the data into JSON format and sends it to the server using an HTTP POST request. An example of this data might look like this: {"water_temp": 22.5, "pH_level": 7.4, "dissolved_oxygen": 6.8}.

[1524] Once the server receives this data, the generative AI model analyzes it and generates optimal environmental adjustment instructions. The generative AI model uses pre-programmed algorithms to calculate the optimal adjustment method based on the collected data. For example, if the water temperature is high, the generative AI model generates the instruction "turn on the cooling device to lower the water temperature to 20.0°C."

[1525] The server sends the generated instructions to the device. When the device receives these instructions, it adjusts the environment based on the instructions. Specifically, it turns on the cooling device and adjusts the water temperature to 20.0°C. Once this process is complete, the device again collects current environmental data from the sensors and sends the new data as feedback to the server. This feedback data is crucial for the generative AI model and is used by the system to continue optimizing the environment in real time.

[1526] Furthermore, this system incorporates an emotion engine that recognizes the user's emotions. The emotion engine detects the user's emotional state using sensors such as cameras and microphones and feeds this information back to the generative AI model as data. This feedback allows the generative AI model to take the user's emotional state into account and generate more appropriate environmental adjustment instructions. For example, if the user is feeling stressed, the generative AI model can flexibly change the environmental adjustment instructions to generate instructions that will improve the user's emotional state.

[1527] Specific examples

[1528] For example, when a user sets up a new aquaculture system, they first install a terminal and place various sensors (water temperature sensor, pH sensor, dissolved oxygen sensor) in the tank. The terminal then collects initial data from these sensors and sends it to the server. If the server analyzes the data and detects that the water temperature is high at 22.5°C, it generates an instruction to "turn on the cooling device to lower the water temperature to 20.0°C." The instruction is sent to the terminal, which then activates the cooling device and adjusts the water temperature. The terminal then collects data again and sends it to the server for feedback.

[1529] The system also features an emotion engine that recognizes the user's emotions. For example, if the user is worried about their care, the system will detect their emotions. The emotion engine sends the data to the server, and the generative AI model can generate new environmental adjustment instructions that take this information into account. This allows for optimal management of the aquaculture environment, taking into account the user's emotional state.

[1530] Example prompt sentence:

[1531] Generate environmental adjustment instructions based on data collected from vivarium sensors.

[1532] Initial data:

[1533] Water temperature: 22.5°C

[1534] pH level: 7.4

[1535] Dissolved oxygen: 6.8 mg / L

[1536] User Emotion: Stress

[1537] The above is an embodiment of the present invention, and by using the emotion engine and generative AI model together, a flexible system is provided that constantly optimizes the aquaculture environment and responds to the user's emotions. It is possible to efficiently and accurately manage the aquaculture environment without any specialized knowledge.

[1538] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1539] System program processing flow

[1540] Step 1:

[1541] The device collects environmental data from sensors. The device uses water temperature, pH, and dissolved oxygen sensors to collect each type of data. The collected data is stored in the device's memory.

[1542] input:

[1543] Data from the water temperature sensor

[1544] Data from pH sensors

[1545] Data from a dissolved oxygen sensor

[1546] Specific behavior:

[1547] The water temperature sensor measures a water temperature of 22.5°C.

[1548] The pH sensor measures a pH level of 7.4.

[1549] The dissolved oxygen sensor measures 6.8 mg / L of dissolved oxygen.

[1550] output:

[1551] Collected environmental data (e.g., {"water_temp": 22.5, "pH_level": 7.4, "dissolved_oxygen": 6.8}) is saved on the device.

[1552] Step 2:

[1553] The device sends the collected environmental data to the server, which converts the data into JSON format and sends it using an HTTP POST request.

[1554] input:

[1555] Environmental data stored on the device

[1556] Specific behavior:

[1557] The device converts the environment data into JSON format.

[1558] The device sends an HTTP POST request to the server.

[1559] output:

[1560] Environmental data sent to the server

[1561] Step 3:

[1562] The server receives the data, and the generative AI model generates instructions for adjusting the environment. After the data is received, the generative AI analyzes the data and generates instructions for optimal environmental adjustment.

[1563] input:

[1564] Environmental data received by the server

[1565] Specific behavior:

[1566] The server receives the HTTP request and parses the environment data.

[1567] A generative AI model performs calculations based on the data.

[1568] output:

[1569] Environmental adjustment instructions (e.g., "Turn on the chiller to reduce the water temperature to 20.0°C")

[1570] Step 4:

[1571] The server generates instructions and sends them to the device, where they are again converted to JSON format and sent using an HTTP POST request.

[1572] input:

[1573] Environmental adjustment instructions generated by a generative AI model

[1574] Specific behavior:

[1575] The server converts the instructions into JSON format.

[1576] The server sends an HTTP POST request to the device.

[1577] output:

[1578] Environmental adjustment instructions sent to the device

[1579] Step 5:

[1580] The device adjusts the environment based on instructions. Specifically, it adjusts the environment by operating cooling devices, etc., and performs operations such as turning devices on and off according to instructions.

[1581] input:

[1582] Received environmental adjustment instructions

[1583] Specific behavior:

[1584] The device turns on the cooling device and reduces the water temperature to 20.0°C.

[1585] output:

[1586] Environmental adjustments are made (e.g., a cooling device is turned on)

[1587] Step 6:

[1588] The device collects the data from the sensor again after adjusting the environment and feeds it back to the server. The adjusted data is again converted into JSON format and sent to the server.

[1589] input:

[1590] Adjusted environmental data

[1591] Specific behavior:

[1592] The sensors measure the environmental data again.

[1593] The data collected by the device is converted into JSON format and sent to the server.

[1594] output:

[1595] Adjusted environmental data sent to the server

[1596] Step 7:

[1597] The emotion engine detects the user's emotions and feeds them back to the generative AI model. The camera and microphone are used to analyze the user's emotions and send the data to the server.

[1598] input:

[1599] User's facial expression and voice data

[1600] Specific behavior:

[1601] The camera captures the user's facial expressions.

[1602] A microphone collects the user's voice.

[1603] The emotion engine analyzes this data.

[1604] output:

[1605] User emotional data (e.g., stress level)

[1606] Step 8:

[1607] The generative AI model generates new instructions for adjusting the environment, taking into account the user's emotional state. New instructions that reflect the user's emotional data are generated and applied to the system.

[1608] input:

[1609] User emotion data

[1610] Environmental Data

[1611] Specific behavior:

[1612] A generative AI model analyzes user emotional data.

[1613] Calculations are performed by combining environmental data and emotional data.

[1614] output:

[1615] New environmental adjustment instructions (e.g., "Reduce light levels to provide a relaxing environment")

[1616] The above is a detailed flow of the program processing of this system. By clarifying the specific inputs, outputs, and processing details at each step, the operation of the system is easy to understand.

[1617] (Application example 2)

[1618] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1619] Modern factories and production environments require optimal maintenance of environmental parameters such as temperature, humidity, and air quality. However, continuously monitoring these environmental parameters and optimally adjusting them in real time requires a great deal of effort and specialized knowledge. Furthermore, because workers' emotional states have a significant impact on productivity, it is important to adjust the environment while taking this into account, but this has been difficult to achieve with existing systems. Therefore, there is a strong demand for the development of a system that simultaneously considers environmental parameters and emotional states and maintains both optimally.

[1620] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the system includes means for collecting environmental data, means for transmitting the environmental data, means for generating instructions for environmental adjustment using a generation AI based on the environmental data, means for receiving the instructions, means for adjusting the environment based on the instructions, means for recognizing the user's emotional state, means for transmitting feedback to the generation AI based on the emotional state, and means for the generation AI to generate instructions for environmental adjustment taking the emotional state into consideration. This makes it possible to simultaneously optimize environmental parameters and the user's emotional state, thereby maintaining a safer and more efficient production environment.

[1621] "Environmental Data" is information about environmental parameters such as temperature, humidity, air quality, water temperature, pH levels, and dissolved oxygen.

[1622] "Means for collecting environmental data" refers to a method or device that uses a sensor to measure environmental parameters and acquire them as data.

[1623] The "means for transmitting environmental data" refers to a method or apparatus for transmitting collected environmental data to a server or other device via a network.

[1624] "Generative AI" is a system that uses artificial intelligence to generate optimal environmental adjustment instructions based on input data.

[1625] "Means for generating instructions for environmental adjustment" refers to a method or device that generates optimal instructions for environmental adjustment based on environmental data collected using a generation AI.

[1626] The "means for receiving instructions" refers to a method or apparatus for receiving generated environment adjustment instructions from a server or other device.

[1627] A "means for adjusting the environment" is a method or device for actually adjusting environmental parameters (temperature, humidity, etc.) based on received instructions.

[1628] The "means for recognizing the emotional state of a user" refers to a method or device for recognizing the emotional state of a user by analyzing the user's facial expressions, actions, tone of voice, etc.

[1629] "Means for sending feedback to the generation AI based on emotional state" refers to a method or device for sending the recognized emotional state of the user to the generation AI as feedback.

[1630] "Means for generating environmental adjustment instructions that take into account the emotional state of the user" refers to a method or device that uses a generating AI to generate optimal environmental adjustment instructions that take into account the emotional state of the user.

[1631] In this invention, the system mainly comprises the following components: means for collecting environmental data, means for transmitting the environmental data, means for generating instructions for adjusting the environment using a generating AI based on the environmental data, means for receiving the instructions, and means for adjusting the environment based on the instructions. Furthermore, the system includes means for recognizing the user's emotional state and transmitting it as feedback to the generating AI.

[1632] System Program

[1633] The system uses sensors to collect environmental data (temperature, humidity, air quality, etc.) within the factory. These sensors include temperature sensors, humidity sensors, and air quality sensors. The collected data is sent to a cloud server via the terminal. The data is converted into JSON format and sent to the server using an HTTP POST request.

[1634] The server analyzes the collected environmental data and generates instructions for optimal environmental adjustments. It uses a generative AI model to generate specific instructions for adjusting environmental parameters based on the data. For example, if the temperature is high, the AI ​​generates instructions such as "Turn on the air conditioner and set the temperature to 25°C."

[1635] The generated instructions are then sent back to the device, which then adjusts the environment based on the received instructions. Specifically, it operates equipment such as air conditioners and humidifiers to adjust the temperature and humidity to the specified level.

[1636] On the other hand, cameras and microphones are used to recognize the user's emotional state. The data collected by these devices is analyzed by an emotion recognition engine to identify the user's emotional state (e.g., stress, fatigue, etc.). This emotional data is also sent to a cloud server and used as feedback for the generative AI.

[1637] The generative AI generates instructions for adjusting the environment taking into account the user's emotional state. For example, if the user is feeling stressed, the generative AI can give instructions such as "soften the lighting in the work area" or "play background music."

[1638] Specific examples

[1639] If the temperature in a factory is 30°C, humidity is 45%, and air quality is 90AQI, the system works as follows: The terminal collects this environmental data and sends it to the server. The generative AI model then analyzes the data and generates instructions such as "turn on the air conditioner and set the temperature to 25°C." This instruction is sent to the terminal, which operates the air conditioner to adjust the temperature.

[1640] Additionally, if the user is feeling stressed, the emotion recognition engine will detect this state and generate instructions such as "soften the lighting in the work area to reduce stress." This instruction is also sent to the device, and the actual environmental adjustment is carried out. For example, a prompt might be entered in the form of "The temperature is 30°C, the humidity is 45%, and the air quality is 90AQI. Please generate instructions for optimal temperature and humidity adjustment."

[1641] This allows the environment within the factory to be kept optimal at all times and allows for flexible environmental adjustments that take into account the emotional state of workers.

[1642] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1643] Step 1:

[1644] The terminal collects environmental data from various sensors (temperature, humidity, and air quality sensors). This involves obtaining temperature, humidity, and air quality values ​​from sensors installed at various locations in the factory. The input is the raw data from the sensors. The output is the collected environmental data (e.g., temperature 30°C, humidity 45%, air quality 90 AQI).

[1645] Step 2:

[1646] The environmental data collected by the device is converted into JSON format and sent to the cloud server using an HTTP POST request. This process involves data conversion and network transmission. The input is the environmental data obtained in step 1, and the output is the JSON-formatted data sent to the server.

[1647] Step 3:

[1648] The server receives the environmental data, analyzes it using a generative AI model, and generates instructions for adjusting the environment. At this stage, temperature, humidity, and air quality values ​​are analyzed to determine the optimal adjustment method. The input is the environmental data sent to the server, and the output is the generated adjustment instructions (e.g., turn on the air conditioner and set the temperature to 25°C).

[1649] Step 4:

[1650] The server sends the generated environmental adjustment instructions to the terminal. In this process, the generated instructions are sent to the terminal using an HTTP GET request, etc. The input is the generated adjustment instructions, and the output is the instructions sent to the terminal.

[1651] Step 5:

[1652] The terminal adjusts the environment based on the received instructions. At this stage, it operates equipment such as air conditioners and humidifiers to set the temperature and humidity as instructed. The input is the adjustment instruction received from the server, and the output is the adjusted environmental parameters (e.g., temperature 25°C).

[1653] Step 6:

[1654] The terminal collects the adjusted environmental data again and sends the new data to the server as feedback. This involves collecting the adjusted environmental data and sending it to the server. The input is the adjusted environmental data, and the output is the feedback data sent to the server.

[1655] Step 7:

[1656] The device collects the user's emotional state using a camera or microphone. In this process, an emotion recognition engine analyzes facial expressions and tone of voice to recognize the emotional state. The input is the collected audio and video data, and the output is the recognized emotional state (e.g., high stress level).

[1657] Step 8:

[1658] The device converts the user's emotional state into JSON format and sends it to the cloud server using an HTTP POST request. The input is the recognized emotional state, and the output is the emotional data sent to the server.

[1659] Step 9:

[1660] The server receives the emotion data and uses a generative AI model to generate instructions for adjusting the environment that take the emotional state into account. In this process, the emotion data and environmental data are analyzed comprehensively to generate more appropriate adjustment instructions. The input is the emotional state and environmental data, and the output is adjustment instructions that take the emotion into account.

[1661] Step 10:

[1662] The server sends instructions for adjusting the environment taking into account the generated emotions to the terminal, and the terminal then adjusts the environment again based on the instructions received. The input is the adjustment instructions taking into account the emotions, and the output is the further adjusted environmental parameters.

[1663] This allows the system to simultaneously optimize environmental parameters and the user's emotional state, maintaining a safer and more efficient production environment.

[1664] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[1665] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1666] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1667] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1668] FIG. 9 is a diagram illustrating an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1669] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[1670] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[1671] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[1672] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[1673] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[1674] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[1675] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[1676] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[1677] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[1678] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[1679] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[1680] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific processing may be a single processor.

[1681] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[1682] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[1683] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[1684] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[1685] The following is further disclosed regarding the above embodiment.

[1686] (Claim 1)

[1687] a means for collecting environmental data;

[1688] means for transmitting the environmental data;

[1689] means for generating an instruction for adjusting the environment using a generation AI based on the environmental data;

[1690] means for receiving the instruction;

[1691] and means for adjusting the environment based on said instructions.

[1692] (Claim 2)

[1693] The system of claim 1, further comprising means for checking the state after the environmental adjustment and sending feedback to the generating AI.

[1694] (Claim 3)

[1695] 10. The system of claim 1, wherein the environmental data includes water temperature, pH level, and dissolved oxygen.

[1696] "Example 1"

[1697] (Claim 1)

[1698] a means for measuring environmental data;

[1699] means for converting and transmitting the environmental data;

[1700] means for generating instructions for adjusting the environment using an artificial intelligence model based on the environmental data;

[1701] means for receiving and analyzing said instructions;

[1702] means for controlling the environment based on said instructions;

[1703] A system including:

[1704] (Claim 2)

[1705] 10. The system of claim 1, further comprising means for re-measuring the state after the environmental adjustment and sending feedback to the artificial intelligence model.

[1706] (Claim 3)

[1707] 10. The system of claim 1, wherein the environmental data includes water temperature, acidity level, and dissolved oxygen.

[1708] "Application Example 1"

[1709] (Claim 1)

[1710] a means for collecting environmental data;

[1711] means for transmitting the environmental data;

[1712] means for generating an instruction for adjusting the environment using a generative AI model based on the environmental data;

[1713] means for receiving the instruction;

[1714] means for adjusting the environment based on said instructions;

[1715] means for generating instructions for optimizing the package storage environment within the distribution center;

[1716] The system includes means for visualizing and executing said instructions on a smartphone.

[1717] (Claim 2)

[1718] 10. The system of claim 1, further comprising means for verifying a state after an environmental adjustment and sending feedback to the generative AI model.

[1719] (Claim 3)

[1720] The system of claim 1 , wherein the environmental data includes temperature, humidity, and CO2 levels.

[1721] "Example 2: Combining Emotion Engines"

[1722] (Claim 1)

[1723] a means for collecting environmental data;

[1724] means for transmitting the environmental data;

[1725] means for generating an instruction for adjusting the environment using a generation AI based on the environmental data;

[1726] means for receiving the instruction;

[1727] means for adjusting the environment based on said instructions;

[1728] means for detecting a user's emotion;

[1729] A system including a means for feeding back the user's emotional data to the generation AI.

[1730] (Claim 2)

[1731] The system of claim 1, further comprising means for checking the state after the environmental adjustment and sending feedback to the generating AI.

[1732] (Claim 3)

[1733] 10. The system of claim 1, wherein the environmental data includes water temperature, pH level, and dissolved oxygen.

[1734] "Application example 2 when combining emotion engines"

[1735] (Claim 1)

[1736] a means for collecting environmental data;

[1737] means for transmitting the environmental data;

[1738] means for generating an instruction for adjusting the environment using a generation AI based on the environmental data;

[1739] means for receiving the instruction;

[1740] means for adjusting the environment based on said instructions;

[1741] means for recognizing the emotional state of a user;

[1742] means for transmitting feedback to the generating AI based on said emotional state;

[1743] A means for generating instructions for adjusting the environment by the generation AI taking into account the emotional state.

[1744] A system including:

[1745] (Claim 2)

[1746] The system of claim 1, further comprising means for checking the state after the environmental adjustment and sending feedback to the generating AI.

[1747] (Claim 3)

[1748] 10. The system of claim 1, wherein the environmental data includes water temperature, pH level, dissolved oxygen, temperature, humidity, and air quality. [Explanation of symbols]

[1749] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. a means for collecting environmental data; means for transmitting the environmental data; means for generating an instruction for adjusting the environment using a generation AI based on the environmental data; means for receiving the instruction; and means for adjusting the environment based on said instructions.

2. The system according to claim 1 , further comprising means for confirming a state after the environmental adjustment and sending feedback to the generating AI.

3. The system of claim 1 , wherein the environmental data includes water temperature, pH level, and dissolved oxygen.

Images