system

Abstract

To provide a system capable of efficiently and widely performing water quality investigation and environmental load prediction as compared with a conventional method.SOLUTION: A system includes a unit that provides a user interface for specifying a specific area to a terminal, a unit that acquires satellite image data of the specified area from an external data provider, a unit that preprocesses the acquired satellite image data to specify a water surface portion, a unit that extracts RGB values of the water surface portion, a unit that uses a machine learning model for estimating a water quality parameter from the extracted RGB values, a unit that simulates an environmental load based on the estimated water quality parameter, a unit that summarizes a result of the simulation in a report format and transmits the result to the terminal, and a unit that causes the terminal to display the result on a user interface.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] In recent years, water quality management has become increasingly important due to environmental changes. Conventional water quality survey methods require on-site sampling and detailed laboratory analysis, which is time-consuming and costly. Furthermore, they are limited to certain regions, making it difficult to grasp the water quality situation over a wide area in real time. For this reason, there is a need for efficient, wide-area water quality survey methods. Furthermore, there is a need for methods to improve the accuracy of simulations for predicting the environmental impact of water quality changes. [Means for solving the problem]

[0005] This invention provides a system that uses satellite image data to rapidly estimate water quality parameters and then simulates environmental impacts based on that data. Specifically, a specific area is specified through a user interface, and satellite image data is acquired from an external data provider. The acquired data is then preprocessed to identify the water surface, RGB values ​​are extracted, and water quality parameters are estimated using a machine learning model. The estimated water quality parameters are then used to simulate future environmental impacts, which are compiled into a report format and sent to a terminal, and the results are displayed on the user interface. This series of steps enables more efficient and extensive water quality surveys and environmental impact predictions than conventional methods.

[0006] A "user interface" is something that provides a screen and input means for a user to operate a system.

[0007] A "terminal" is a device used by a user, and is a medium for specifying a specific area and checking results.

[0008] A "server" is a computer system that processes and manages data and coordinates system execution in cooperation with terminals.

[0009] "Satellite image data" refers to image data of the earth's surface or water surface obtained from an earth observation satellite.

[0010] "External data providers" are services or organizations that provide various data such as satellite image data.

[0011] "Preprocessing" is a data processing procedure for converting acquired satellite image data into a form that is easier to analyze.

[0012] The "water surface portion" is the area occupied by a water body in the satellite image data.

[0013] "RGB value" is a number that indicates the intensity of the three colors red (R), green (G), and blue (B) for each pixel in an image.

[0014] "Water quality parameters" are specific indicators that represent the quality of the water being analyzed, and include, for example, turbidity and chlorophyll concentration.

[0015] A "machine learning model" is an algorithm that learns using data and makes inferences and predictions about new data.

[0016] "Environmental load" refers to the total impact that human activities and natural factors have on the environment.

[0017] "Simulation" is a method of modeling real-world phenomena and reproducing their behavior on a computer.

[0018] The "report format" is a document format that organizes and summarizes the results of analysis and simulation in an easy-to-understand format. [Brief explanation of the drawings]

[0019] [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

[0020] 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.

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

[0022] 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).

[0023] 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.

[0024] 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.

[0025] 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.

[0026] 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."

[0027] [First embodiment]

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

[0029] 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.

[0030] 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).

[0031] 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.

[0032] 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.

[0033] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form 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.

[0034] 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.

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

[0036] 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.

[0037] 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.

[0038] 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.

[0039] 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."

[0040] This invention is a system that uses satellite image data to quickly and efficiently estimate water quality parameters and then simulates environmental loads based on that data. The configuration and functions for implementing this system will be described in detail.

[0041] System configuration

[0042] The system mainly consists of the following components:

[0043] 1. User Interface (Terminal)

[0044] 2. Server

[0045] 3. External Data Providers

[0046] User Interface (Terminal)

[0047] The user interface allows users to operate the system and specify a specific area. For example, it can be implemented as a web application or a mobile application. Through the interface, users can enter the coordinates of the area they want to investigate and the investigation period. The interface also provides graphs and reports for visual confirmation of analysis and simulation results.

[0048] server

[0049] The server plays a central role in processing and managing data. The main functions of the server are explained below.

[0050] 1. Data acquisition function

[0051] The server receives the request sent by the user and retrieves satellite image data for the specified area using the API of an external data provider.

[0052] 2. Image analysis function

[0053] The acquired satellite image data is preprocessed and color segmentation is performed to identify the water surface.

[0054] The RGB values ​​of each pixel on the water surface are extracted and temporarily saved.

[0055] 3. Water quality estimation function

[0056] Water quality parameters (turbidity, chlorophyll concentration, etc.) are estimated from the RGB values ​​extracted using a machine learning model.

[0057] 4. Environmental impact simulation function

[0058] Based on the water quality parameters, external data (e.g., meteorological data) necessary for simulating future environmental loads are obtained.

[0059] The simulation model is run and the results are analyzed and compiled in report format.

[0060] 5. Result transmission function

[0061] The generated report and simulation results are sent to the terminal.

[0062] External Data Providers

[0063] External data providers are services or organizations that provide satellite imagery and other necessary data. The server works with these providers to obtain the data and use it for analysis.

[0064] Example of operation

[0065] Below is a specific example of using this system to investigate the water quality of a specific lake.

[0066] 1. User Input

[0067] The user uses the terminal interface to input the coordinates of a particular lake and the date and time range they wish to survey.

[0068] 2. Data Acquisition

[0069] The terminal transmits the input data to the server, which then makes a request to an external data provider to obtain satellite image data for the specified area and period.

[0070] 3. Image Analysis

[0071] The server receives the satellite image data and performs color segmentation to identify the water surface.

[0072] Extract the RGB values ​​and feed them into a machine learning model.

[0073] 4. Water quality estimation

[0074] A machine learning model estimates water quality parameters such as turbidity and chlorophyll concentration from RGB values.

[0075] 5. Environmental Load Simulation

[0076] The server runs an environmental impact simulation, analyzes the results, and compiles them into a report.

[0077] 6. Sending and displaying results

[0078] The server sends the generated report to the terminal, which displays the results on a user interface.

[0079] Users can check the analysis and simulation results via their devices and consider the necessary measures and actions.

[0080] The above process enables faster and more widespread water quality surveys and environmental load predictions than conventional methods, resulting in a system that provides useful information for environmental conservation activities and policy formulation.

[0081] The processing flow will be explained below.

[0082] Step 1:

[0083] The user inputs the coordinates of the area to be surveyed and the survey period through the terminal interface, and the terminal transmits this input data to the server.

[0084] Step 2:

[0085] Based on the request received from the device, the server sends an API request to an external data provider to obtain satellite image data for the specified area and period.

[0086] Step 3:

[0087] The server preprocesses the satellite image data it acquires, specifically adjusting the resolution, cropping unnecessary parts, and adjusting brightness and contrast.

[0088] Step 4:

[0089] The server runs image analysis algorithms to identify water surfaces, for example, using color segmentation techniques such as k-means clustering.

[0090] Step 5:

[0091] The server extracts the RGB values ​​of each pixel from the identified water surface area and temporarily stores them in memory.

[0092] Step 6:

[0093] The server inputs the extracted RGB values ​​into a pre-trained machine learning model to estimate water quality parameters (e.g., turbidity, chlorophyll concentration).

[0094] Step 7:

[0095] The server aggregates the estimated water quality parameters and calculates statistical information such as the mean, median, and standard deviation.

[0096] Step 8:

[0097] The server compares the current water quality situation with past data from the same area and data from other areas.

[0098] Step 9:

[0099] The server obtains external data (e.g., weather data, flow rate data) necessary to simulate future environmental loads.

[0100] Step 10:

[0101] The server builds an environmental model and simulates future changes in water quality and their impacts.

[0102] Step 11:

[0103] The server analyzes the simulation results and compiles them into a report, which includes visual elements such as graphs and heat maps.

[0104] Step 12:

[0105] The server sends the generated report to the terminal.

[0106] Step 13:

[0107] The terminal displays the received report on the user interface, and the user confirms the results.

[0108] Step 14:

[0109] Based on the results displayed, the user considers the necessary measures and actions.

[0110] Example 1

[0111] 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."

[0112] Conventional water quality survey methods require on-site sampling, which is time-consuming and costly, and the scope of data collection is limited. Furthermore, simulations for predicting environmental impacts cannot be performed in real time, making it difficult to take prompt action. The present invention aims to solve these problems.

[0113] 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.

[0114] In this invention, the server includes means for providing a terminal with a user interface for specifying a specific area, means for acquiring satellite image data of the specified area from an external data provider, image processing means for preprocessing the acquired satellite image data and identifying the water surface, means for extracting RGB values ​​of the water surface, means for using a machine learning model to estimate water quality parameters from the extracted RGB values, means for simulating environmental impacts based on the estimated water quality parameters, means for compiling the simulation results in a report format and transmitting the results to the terminal, and means for the terminal to display the results on the user interface, thereby enabling fast and efficient water quality surveys and environmental impact predictions.

[0115] "Specific region" refers to the geographic area to be analyzed using satellite imagery, including coordinates and a time period specified by the user.

[0116] A "user interface" is a means by which a user operates a system, including web applications and mobile applications displayed on a terminal.

[0117] A "terminal" is a device operated by a user, and includes computing devices such as computers, smartphones, and tablets.

[0118] "Satellite image data" refers to image information acquired from cameras and sensors mounted on satellites, and includes visual data of a specific area.

[0119] "External data providers" are services or organizations that provide necessary data, such as satellite image data.

[0120] "Preprocessing" refers to the process of converting satellite image data into an analyzable format, removing noise, and adjusting resolution.

[0121] "Image processing means" refers to software tools and algorithms for analyzing images, including methods such as color segmentation.

[0122] The "water surface portion" refers to the pixel area of ​​the water area to be analyzed in the satellite image data.

[0123] "RGB values" refer to the values ​​of the red, green, and blue color components of each pixel, and represent the color information of a digital image.

[0124] A "machine learning model" refers to an algorithm that learns patterns from data and makes predictions or classifications for new data, and includes methods such as neural networks.

[0125] "Water quality parameters" refer to physical and chemical characteristics of water, such as turbidity and chlorophyll concentration.

[0126] "Environmental impact" refers to the impact on the environment predicted based on estimated water quality parameters, including future changes in water quality.

[0127] "Simulation" refers to a method of creating a virtual environment on a computer and predicting the future by imitating real-world behavior.

[0128] "Report format" refers to a documented analysis or simulation result, including digital formats such as PDF.

[0129] "Means for displaying results" refers to an interface that allows analysis results and simulation results to be visually confirmed on a terminal.

[0130] Overall system overview

[0131] This invention is a system that uses satellite image data to quickly and efficiently estimate water quality parameters and simulate environmental impacts based on that data. In this system, a server acquires the necessary satellite image data from an external data provider based on information about a region specified by a user, estimates water quality parameters using a machine learning model, and provides the results as a report.

[0132] Components and Functions

[0133] User Interface (Terminal)

[0134] The user interface allows users to operate the system and input the coordinates and period of the survey area. This user interface is implemented as a web or mobile application. For example, a user inputs the coordinates of Tokyo Bay (35.6895, 139.6917) and the survey period (April 1, 2023 to April 30, 2023).

[0135] server

[0136] The server is the center of data processing and has multiple functions.

[0137] 1. Data acquisition function

[0138] The server receives user input and uses the API of an external data provider to obtain satellite image data for the specified area, specifically, using a remote sensing service.

[0139] 2. Image analysis function

[0140] The server preprocesses the acquired satellite image data and performs color segmentation to identify the water surface, for example, by extracting RGB values ​​using OpenCV as an image processing tool.

[0141] 3. Water quality estimation function

[0142] The server inputs the extracted RGB values ​​into a machine learning model (e.g., CNN using TENSORFLOW (registered trademark)) to estimate water quality parameters such as turbidity and chlorophyll concentration.

[0143] 4. Environmental impact simulation function

[0144] Based on the estimated water quality parameters, the server obtains the external data (e.g., meteorological data) necessary to perform environmental impact simulations, and predicts future environmental impacts using a simulation tool (e.g., MATLAB (registered trademark)).

[0145] 5. Result transmission function

[0146] The server compiles the simulation results into a report format (e.g., PDF) and sends it to the terminal.

[0147] Terminal

[0148] The terminal receives reports and simulation results sent from the server and displays them on the user interface, allowing the user to visually check the analysis and simulation results.

[0149] Specific operation example

[0150] Below is a specific example of using this system to investigate the water quality of a specific lake.

[0151] 1. User Input

[0152] The user uses the terminal interface to input the coordinates of a particular lake and the date and time range they wish to survey.

[0153] 2. Data Acquisition

[0154] The terminal transmits the input data to the server, which then makes a request to an external data provider to obtain satellite image data for the specified area and period.

[0155] 3. Image Analysis

[0156] The server receives satellite image data, performs color segmentation to identify the water surface, and extracts RGB values.

[0157] 4. Water quality estimation

[0158] A machine learning model estimates water quality parameters such as turbidity and chlorophyll concentration from RGB values.

[0159] 5. Environmental Load Simulation

[0160] The server runs the environmental impact simulation, analyzes the results, and compiles them into a report.

[0161] 6. Sending and displaying results

[0162] The server sends the generated report to the terminal, which displays the results on a user interface.

[0163] Prompt Sentence Examples

[0164] The following are examples of prompts used in this system:

[0165] Using the coordinates (35.6895, 139.6917) for the Tokyo area and the survey period (April 1, 2023 - April 30, 2023), we would like to estimate water quality parameters (turbidity, chlorophyll concentration) from satellite image data and simulate future environmental impacts.

[0166] This system supports rapid and efficient water quality surveys and predictions of environmental impacts, and can provide useful information for environmental conservation activities and policy formulation.

[0167] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0168] Step 1:

[0169] User input

[0170] The user opens the user interface on their device and enters the coordinates of the area to be surveyed and the period they wish to survey. For example, they enter "Tokyo Bay coordinates (35.6895, 139.6917)" and "survey period (April 1, 2023 - April 30, 2023)." The entered data is sent from the device to the server.

[0171] Input: Area coordinates and survey period

[0172] Output: Create input data in JSON format and send it to the server

[0173] Step 2:

[0174] Data retrieval by the server

[0175] Based on the received user input data, the server makes a request to the API of an external data provider to obtain satellite image data for the specified area and period. Specifically, it calls the API of a remote sensing service. For example, it sends a satellite image request for the specified coordinates and period and obtains satellite image data as a response.

[0176] Input: User-entered data

[0177] Output: Satellite image data for a specified area and period

[0178] Step 3:

[0179] Image analysis by server

[0180] The server preprocesses the acquired satellite image data, removing noise and adjusting the resolution. Next, it performs color segmentation using the image processing library OpenCV to identify the water surface. It then extracts RGB values ​​from each pixel in the identified water surface area and temporarily stores them.

[0181] Input: Satellite image data

[0182] Output: A list of RGB values ​​for the water surface

[0183] Step 4:

[0184] Water quality estimation by server

[0185] The server inputs the extracted RGB values ​​into a machine learning model (e.g., a CNN using TensorFlow) to estimate water quality parameters such as turbidity and chlorophyll concentration.

[0186] Input: RGB values ​​of the water surface

[0187] Output: Estimated water quality parameters (turbidity, chlorophyll concentration)

[0188] Step 5:

[0189] Environmental impact simulation using a server

[0190] The server uses the estimated water quality parameters and other necessary external data (e.g., meteorological data) to simulate future environmental impacts using simulation tools such as MATLAB. The simulation results are analyzed and compiled into a report (PDF).

[0191] Input: Estimated water quality parameters, external meteorological data

[0192] Output: Simulation result report (PDF format)

[0193] Step 6:

[0194] Sending and displaying results

[0195] The server sends the generated report to the terminal, which displays the received report on the user interface, where the user can check it and, if necessary, plan the next action.

[0196] Input: Simulation results report

[0197] Output: Report displayed in the user interface

[0198] The above are the specific processing steps of the program in this system.

[0199] (Application example 1)

[0200] 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."

[0201] Existing water quality monitoring systems have the problem of making it difficult to respond quickly when water quality abnormalities occur. While these systems are suitable for detecting abnormalities, they cannot report abnormalities in real time or compare specific environmental impact simulations with past data, which can delay early countermeasures. Furthermore, a lack of visualization and alert functions for water quality data also hinders the ability of relevant parties to respond quickly.

[0202] 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.

[0203] In this invention, the server includes means for providing a terminal with a user interface for specifying a specific area, means for acquiring satellite image data of the specified area from an external data provider, means for preprocessing the acquired satellite image data and identifying the water surface, and means for issuing an alert if the estimated water quality parameter contains an abnormal value. This allows an alert to be issued quickly to relevant parties when the water quality parameter indicates an abnormal value, enabling early countermeasures and responses.

[0204] A "user interface for specifying a specific area" is an input means for a user to select and specify an area of ​​interest, and is a software interface that runs on a terminal.

[0205] "Means for obtaining satellite image data for a specified area from an external data provider" refers to a system for obtaining satellite image data for a specified area from an external data provider, and is a function for collecting data through collaboration with APIs and data banks.

[0206] "Means for pre-processing acquired satellite image data and identifying water surface areas" refers to image processing techniques and algorithms for analyzing satellite image data and identifying water areas, thereby identifying water surface areas.

[0207] The "means for extracting RGB values ​​of the water surface portion" is a function for extracting the RGB (red, green, blue) values ​​of each pixel from the identified water surface portion, and is a means that utilizes image analysis technology.

[0208] "Means for using a machine learning model to estimate water quality parameters from extracted RGB values" refers to a function that uses a machine learning algorithm to predict water quality parameters (e.g., turbidity and chlorophyll concentration) using the extracted RGB values ​​as input.

[0209] The "means for simulating environmental loads based on estimated water quality parameters" is a function that utilizes estimated water quality parameters to execute a simulation model for predicting future environmental impacts.

[0210] The "means for issuing an alert if the estimated water quality parameter contains an abnormal value" is a function that immediately issues a warning if the predicted water quality parameter is determined to be within an abnormal range.

[0211] The "means for compiling the simulation results in a report format and transmitting it to the terminal" is a function for compiling the results of the environmental load simulation, creating a report, and transmitting the results to the user's terminal.

[0212] "Means for the terminal to display results on the user interface" refers to a function that displays the simulation results and predicted results of water quality parameters on the user interface, allowing the user to visually confirm them.

[0213] The present invention is a system for implementing water quality monitoring and environmental load simulation, which enables rapid response to pollution and abnormal water quality conditions. A specific embodiment of this system is described below.

[0214] System configuration

[0215] The system mainly consists of the following components:

[0216] 1. User Interface (Terminal)

[0217] 2. Server

[0218] 3. External Data Providers

[0219] User Interface (Terminal)

[0220] The user interface is the input means through which users operate the system. Through this interface, users input the coordinates of a specific area and the survey period. For example, it is implemented as a smartphone application, allowing users to easily specify an area using a map. This interface also provides graphs and reports for visually checking analysis and simulation results.

[0221] Prompt Sentence Examples

[0222] Enter the coordinates of the lake (e.g. 35.6581,139.7514):

[0223] Enter the period you want to investigate (e.g., 2023-01-01~2023-01-31):

[0224] Send coordinate and time period data to predict water quality parameters for a given area...

[0225] server

[0226] The server is the central point for processing and managing data. It has the following main functions:

[0227] 1. Data acquisition function: Receives a request sent by the user and acquires satellite image data for the specified area using the API of an external data provider.

[0228] 2. Image analysis function: Preprocesses acquired satellite image data to identify water surfaces, and extracts the RGB values ​​of each pixel from the identified water surface.

[0229] 3. Water quality estimation function: Estimates water quality parameters (turbidity, chlorophyll concentration, etc.) from RGB values ​​extracted using a machine learning model.

[0230] 4. Environmental load simulation function: Based on water quality parameters, the necessary data is obtained to simulate future environmental loads, and the simulation model is executed.

[0231] 5. Alert function: If the estimated water quality parameters contain abnormal values, an alert is sent to the relevant parties.

[0232] 6. Result transmission function: Sends the generated report and simulation results to the terminal.

[0233] The hardware used is a high-performance server computer, and the software used includes Flask (a Python framework), scikit-learn (machine learning models), and requests (external API calls).

[0234] External Data Providers

[0235] External data providers are services or organizations that provide satellite imagery and other necessary data. The server works with these providers to acquire the data and use it for analysis. The data is sent to the server via an API, where it undergoes any necessary preprocessing.

[0236] Example of operation

[0237] Below is a specific example of using this system to investigate the water quality of a specific lake and detect outliers.

[0238] 1. User input:

[0239] The user uses the terminal interface to input the coordinates of a particular lake and the date and time range they wish to survey.

[0240] 2. Data Acquisition:

[0241] Based on the data sent by the user, the server obtains satellite image data for the specified area through the API of an external data provider.

[0242] 3. Image Analysis:

[0243] The server preprocesses the acquired satellite image data to identify the water surface area, and then extracts the RGB values ​​of each pixel from the identified water surface area.

[0244] 4. Water quality estimation:

[0245] Using a machine learning model, water quality parameters such as turbidity and chlorophyll concentration are estimated from the extracted RGB values.

[0246] 5. Environmental impact simulation:

[0247] The server runs an environmental impact simulation, analyzes the results, and compiles them into a report.

[0248] 6. Alerting:

[0249] If the server detects abnormal values ​​in the estimated water quality parameters, it immediately sends an alert to relevant parties.

[0250] 7. Sending and viewing results:

[0251] The server sends the generated report to the terminal, which displays the results on the user interface. The user can visually check the analysis and simulation results and consider the necessary countermeasures and actions.

[0252] This will enable quicker and more widespread water quality surveys and environmental load predictions than conventional methods, and will provide a system that provides useful information for environmental conservation activities and policy formulation.

[0253] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0254] Step 1:

[0255] The user inputs the coordinates of a specific area and the survey period through the user interface of the terminal. The input data includes location information (latitude and longitude) and the survey period (date range). This determines the conditions for satellite imagery that the server should acquire.

[0256] Step 2:

[0257] The device sends the coordinates and time period data entered by the user to the server. The input data is sent in JSON format, and the server receives and parses it. The server then creates a request to the external data provider based on this data.

[0258] Step 3:

[0259] The server calls the API of an external data provider to obtain satellite image data for the specified area and period. The satellite image data is returned as a response from the API. The obtained satellite image data is temporarily stored on the server.

[0260] Step 4:

[0261] The server preprocesses the acquired satellite image data, specifically removing noise from the images and standardizing the resolution. Next, image processing algorithms are used to segment and recognize the water surface.

[0262] Step 5:

[0263] The RGB values ​​of each pixel in the water surface area are extracted from the preprocessed image. The extracted RGB values ​​serve as input data for the next processing step, water quality parameter estimation.

[0264] Step 6:

[0265] The server uses a machine learning model to estimate water quality parameters (turbidity, chlorophyll concentration, etc.) from the extracted RGB values. The machine learning model uses a pre-trained generative AI model, which inputs RGB values ​​and outputs water quality parameters.

[0266] Step 7:

[0267] The server simulates environmental loads based on the estimated water quality parameters. To do this, the server obtains meteorological and other environmental data from external data providers as needed and runs the simulation model.

[0268] Step 8:

[0269] The server compiles the simulation results in a report format, which includes the estimated water quality parameters and the simulation results. The report may also include graphs and charts for easy visual understanding.

[0270] Step 9:

[0271] The server sends the generated reports and simulation results to the terminal, where they are displayed on the user interface.

[0272] Step 10:

[0273] Users can visually check the analysis and simulation results through the terminal's user interface, and can consider the necessary countermeasures and actions based on this.

[0274] Step 11:

[0275] If the server detects any abnormalities in the estimated water quality parameters, it will immediately issue an alert, which will be sent to relevant parties via email or notification, enabling a prompt response.

[0276] 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.

[0277] This invention provides a system that uses satellite image data to quickly and efficiently estimate water quality parameters and simulate environmental impacts based on that data, as well as a function that recognizes the user's emotions and displays results and alerts accordingly. The configuration and functions for implementing this system are described in detail below.

[0278] System configuration

[0279] The system mainly consists of the following components:

[0280] 1. User Interface (Terminal)

[0281] 2. Server

[0282] 3. External Data Providers

[0283] 4. Emotion Engine

[0284] User Interface (Terminal)

[0285] The user interface allows users to operate the system and specify a specific area. For example, it can be implemented as a web application or a mobile application. Through the interface, users can enter the coordinates of the area they want to investigate and the investigation period. The interface also provides graphs and reports for visual confirmation of analysis and simulation results.

[0286] server

[0287] The server plays a central role in processing and managing data. The main functions of the server are explained below.

[0288] 1. Data acquisition function

[0289] The server receives the request sent by the user and retrieves satellite image data for the specified area using the API of an external data provider.

[0290] 2. Image analysis function

[0291] The acquired satellite image data is preprocessed and color segmentation is performed to identify the water surface.

[0292] The RGB values ​​of each pixel on the water surface are extracted and temporarily saved.

[0293] 3. Water quality estimation function

[0294] Water quality parameters (turbidity, chlorophyll concentration, etc.) are estimated from the RGB values ​​extracted using a machine learning model.

[0295] 4. Environmental impact simulation function

[0296] Based on the water quality parameters, external data (e.g., meteorological data) necessary for simulating future environmental loads are obtained.

[0297] The simulation model is run and the results are analyzed and compiled in report format.

[0298] 5. Result transmission function

[0299] The generated report and simulation results are sent to the terminal.

[0300] Emotion Engine

[0301] The emotion engine recognizes the user's emotions and adjusts the system's operation and display. The main functions of the emotion engine are explained below.

[0302] 1. Emotion recognition function

[0303] The device recognizes the user's emotions in real time based on their facial expressions, voice, input patterns, etc.

[0304] The recognized emotion data is sent to the server.

[0305] 2. Display adjustment function

[0306] The server changes the display format of the results based on the emotional data. For example, if the user is feeling stressed, the results will be displayed in a simpler format.

[0307] 3. Emotional response function

[0308] The server generates alerts and suggestions based on the user's emotions and sends them to the device. For example, if the user is feeling anxious, an alert will be displayed offering additional information or support.

[0309] Example of operation

[0310] Below is a specific example of using this system to investigate the water quality of a specific lake.

[0311] 1. User Input

[0312] The user uses the terminal interface to input the coordinates of a particular lake and the date and time range they wish to survey.

[0313] The terminal transmits the input data to the server.

[0314] 2. Data Acquisition

[0315] The server makes a request to an external data provider to obtain satellite image data for a specified region and time period.

[0316] 3. Image Analysis

[0317] The server preprocesses the acquired satellite image data and performs color segmentation to identify the water surface.

[0318] The RGB values ​​of each pixel on the water surface are extracted and fed into the machine learning model.

[0319] 4. Water quality estimation

[0320] A machine learning model estimates water quality parameters such as turbidity and chlorophyll concentration from RGB values.

[0321] 5. Environmental Load Simulation

[0322] The server runs an environmental impact simulation, analyzes the results, and compiles them into a report.

[0323] 6. Emotion Recognition and Display Adjustment

[0324] The device recognizes the user's emotions and transmits them to the server.

[0325] The server adjusts the display format of the report based on the user's feelings and sends it to the terminal.

[0326] 7. Sending and displaying results

[0327] The terminal displays the received report on the user interface, and the user confirms the results.

[0328] 8. Emotional Response

[0329] Depending on the user's emotions, the server generates additional alerts and suggestions and sends them to the device.

[0330] Through the above process, users can efficiently and widely conduct water quality surveys and predict environmental impacts, and a feedback system that takes users' feelings into consideration makes the system easier to use and more reliable.

[0331] The processing flow will be explained below.

[0332] Step 1:

[0333] The user inputs the coordinates of the area they want to survey and the survey period through the terminal interface, and the terminal sends this input data to the server.

[0334] Step 2:

[0335] Based on the request received from the device, the server sends an API request to an external data provider to obtain satellite image data for the specified area and period.

[0336] Step 3:

[0337] The server preprocesses the satellite image data it acquires, specifically adjusting the resolution, cropping unnecessary parts, and adjusting brightness and contrast.

[0338] Step 4:

[0339] The server runs image analysis algorithms to identify water surfaces, for example, using color segmentation techniques such as k-means clustering.

[0340] Step 5:

[0341] The server extracts the RGB values ​​of each pixel from the identified water surface area and temporarily stores them in memory.

[0342] Step 6:

[0343] The server inputs the extracted RGB values ​​into a pre-trained machine learning model to estimate water quality parameters (e.g., turbidity, chlorophyll concentration).

[0344] Step 7:

[0345] The server aggregates the estimated water quality parameters and calculates statistical information such as the mean, median, and standard deviation.

[0346] Step 8:

[0347] The server compares the current water quality situation with past data from the same area and data from other areas.

[0348] Step 9:

[0349] The server obtains external data (e.g., weather data, flow rate data) necessary to simulate future environmental loads.

[0350] Step 10:

[0351] The server builds an environmental model and simulates future changes in water quality and their impacts.

[0352] Step 11:

[0353] The server analyzes the simulation results and compiles them into a report, which includes visual elements such as graphs and heat maps.

[0354] Step 12:

[0355] The server sends the generated report to the terminal.

[0356] Step 13:

[0357] The terminal displays the received report on the user interface, and the user confirms the results.

[0358] Step 14:

[0359] The device activates an emotion engine to recognize the user's emotions and analyzes the user's facial expressions, voice, and input patterns.

[0360] Step 15:

[0361] The device transmits the recognized emotion data to the server.

[0362] Step 16:

[0363] The server changes the display format of the results based on the emotional data. For example, if the user is feeling stressed, the results will be displayed in a simpler format.

[0364] Step 17:

[0365] The server generates alerts and suggestions based on the user's emotions and sends them to the device. For example, if the user is feeling anxious, an alert will be displayed offering additional information or support.

[0366] Step 18:

[0367] The device displays the generated alerts and suggestions on a user interface.

[0368] Step 19:

[0369] The user considers the necessary measures and actions based on the displayed results and alerts.

[0370] Through this series of steps, users can efficiently conduct water quality surveys and predict environmental impacts, and also receive feedback that takes their own emotions into consideration.

[0371] Example 2

[0372] 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."

[0373] Conventional water quality analysis systems require large-scale data collection and processing, which results in long processing times and makes it difficult for users to obtain results quickly. Furthermore, user operations and information provision are uniform, and the systems are unable to respond to individual users' emotions and situations, resulting in low usability and user satisfaction. Therefore, there is a need for a system that can efficiently and quickly estimate water quality parameters and provide flexible result displays and alerts that respond to the user's emotions.

[0374] 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.

[0375] In this invention, the server includes means for providing a terminal with a user interface for specifying a specific area, means for acquiring satellite image data of the specified area from an external data provider, means for preprocessing the acquired satellite image data to identify the water surface, means for extracting RGB values ​​of the water surface, means for using a machine learning model to estimate water quality parameters from the extracted RGB values, means for simulating environmental impacts based on the estimated water quality parameters, means for compiling the simulation results in a report format and transmitting the results to the terminal, means for the terminal to display the results on the user interface, means for recognizing the user's emotions and adjusting the result display format according to the emotions, and means for generating alerts and suggestions based on the user's emotions. This enables users to quickly and efficiently estimate water quality parameters and receive flexible information provision according to their emotions and circumstances.

[0376] A "user interface" is the means by which a user operates a system and specifies a specific area. Specifically, it is often implemented as a web application or a mobile application.

[0377] "Terminal" refers to the device accessed by the user, and includes electronic devices such as personal computers, smartphones, and tablets.

[0378] A "server" is a computer system that processes data, manages it, and plays a central role in the entire system.

[0379] An "external data provider" is a third-party data provider that provides data from outside, and includes, for example, an organization that provides satellite image data.

[0380] "Satellite image data" refers to image data captured by a satellite, and includes geographical information and environmental information.

[0381] "Preprocessing" refers to the process of preparing acquired data before analyzing it, and includes noise removal and filtering.

[0382] "Water surface area" refers to the area of ​​satellite image data that represents water bodies.

[0383] "RGB value" is the color information contained in a pixel of image data, and is composed of red, green, and blue values.

[0384] "Water quality parameters" are indicators for evaluating water quality, and include turbidity, chlorophyll concentration, etc.

[0385] A "machine learning model" is an algorithm that analyzes data and learns patterns, which are used for prediction and classification.

[0386] "Environmental load" refers to the degree of impact on the environment, including, for example, the amount of pollutants and the impact on the ecosystem.

[0387] "Simulation" is the process of simulating real-world situations and predicting future conditions.

[0388] A "report" is a document or digital file that summarizes the results of an analysis or simulation.

[0389] "Emotion" refers to the user's psychological state, and includes, for example, joy, sadness, anger, anxiety, and the like.

[0390] An "alert" is a notification or warning that conveys information to the user.

[0391] "Suggestion" refers to advice or guidance given to the user.

[0392] "Result display format" refers to the format or style in which analysis results or simulation results are displayed on the user interface.

[0393] "Recognition" is the process by which the system understands the user's state from facial expressions, voice, etc.

[0394] "Flexible information provision" refers to providing information in an appropriate format according to the user's situation and emotions.

[0395] MODE FOR CARRYING OUT THE INVENTION

[0396] The present invention relates to a system for efficiently and quickly estimating water quality parameters and providing flexible result displays and alerts according to the user's emotions. Specific embodiments of the present invention will be described in detail below.

[0397] System configuration

[0398] The system mainly consists of the following components:

[0399] 1. User Interface (Terminal)

[0400] 2. Server

[0401] 3. External Data Providers

[0402] 4. Emotion Engine

[0403] User Interface (Terminal)

[0404] The user interface is the means by which users operate the system and specify a specific area. Specifically, it is implemented as a web application or mobile application. Users can operate their device to enter the coordinates of the area they want to survey and the survey period. Graphs and reports are also provided to visually confirm the analysis and simulation results.

[0405] server

[0406] The server is the central location for processing and managing data. It provides the following functions:

[0407] 1. Data acquisition function

[0408] The server receives the request sent by the user and retrieves satellite image data for the specified area using the API of an external data provider, for example, the NASA Earthdata API.

[0409] 2. Image analysis function

[0410] The server preprocesses the acquired satellite image data to identify the water surface area. Specifically, it performs color segmentation using Python's OpenCV library and extracts the RGB values ​​of each pixel in the water surface area.

[0411] 3. Water quality estimation function

[0412] The server uses a machine learning model (e.g., TensorFlow) to estimate water quality parameters (e.g., turbidity and chlorophyll concentration) from the extracted RGB values.

[0413] 4. Environmental impact simulation function

[0414] The server acquires external data (e.g., meteorological data) necessary to simulate future environmental impacts based on water quality parameters. AnyLogic is used as the simulation model, and the analysis results are compiled in a report format.

[0415] 5. Result transmission function

[0416] The server sends the generated report and simulation results to the terminal, which receives them and displays them on the user interface.

[0417] Emotion Engine

[0418] The emotion engine recognizes the user's emotions and adjusts the system's operation and display accordingly. The emotion engine's functions are as follows:

[0419] 1. Emotion recognition function

[0420] The device uses a camera and microphone to analyze the user's facial expressions and voice to recognize emotions, and this data is sent to a server.

[0421] 2. Display adjustment function

[0422] The server changes the way the results are displayed based on the emotion data, for example, if the user is feeling stressed, the results are displayed in a simpler format.

[0423] 3. Emotional response function

[0424] The server generates alerts and suggestions based on the user's emotions and sends them to the device. For example, if the user is feeling anxious, an alert will be displayed offering additional information or support.

[0425] Example of operation

[0426] 1. User Input

[0427] The user uses the terminal interface to input the coordinates of a specific lake (e.g., latitude 35.6581°, longitude 139.7414°) and the survey period (e.g., May 1, 2023 to May 10, 2023). The terminal then transmits the input data to the server.

[0428] 2. Data Acquisition

[0429] The server makes a request to an external data provider to obtain satellite image data for a specified region and time period.

[0430] 3. Image Analysis

[0431] The server preprocesses the acquired satellite image data and performs color segmentation to identify the water surface area. The RGB values ​​of each pixel in the water surface area are extracted and fed into the machine learning model.

[0432] 4. Water quality estimation

[0433] A machine learning model estimates water quality parameters such as turbidity and chlorophyll concentration from RGB values.

[0434] 5. Environmental Load Simulation

[0435] The server runs an environmental impact simulation, analyzes the results, and compiles them into a report.

[0436] 6. Emotion Recognition and Display Adjustment

[0437] The device recognizes the user's emotions and sends them to the server, which then adjusts the report display format based on the user's emotions and sends it to the device.

[0438] 7. Sending and displaying results

[0439] The terminal displays the received report on the user interface, and the user confirms the results.

[0440] 8. Emotional Response

[0441] Depending on the user's emotions, the server generates additional alerts and suggestions and sends them to the device.

[0442] Prompt Sentence Examples

[0443] An example of a prompt for operating this system is, "Investigate the water quality of the lake at latitude 35.6581 degrees and longitude 139.7414 degrees from May 1, 2023 to May 10, 2023, and display the simulated results of the environmental impact. Also, adjust the display format and alerts according to the user's emotions."

[0444] As described above, this system efficiently and quickly conducts water quality surveys and predicts environmental impacts, and also provides feedback that responds to the user's emotions, thereby realizing a user-friendly interface.

[0445] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0446] Step 1: User Input

[0447] The user uses the device interface to input the coordinates of the area they want to survey and the survey period. For example, the user might input, "Survey a lake at latitude 35.6581 degrees and longitude 139.7414 degrees from May 1, 2023 to May 10, 2023." The device receives this input data and sends it to the server in JSON format.

[0448] Input: Area coordinates, survey period

[0449] Output: Request data in JSON format

[0450] Step 2: Data Acquisition

[0451] The server receives the request sent by the user and retrieves satellite image data for the specified area and period using the API of an external data provider. For example, the server sends a request to the NASA Earthdata API to retrieve the relevant data. The retrieved data is stored on the server.

[0452] Input: Request data in JSON format

[0453] Output: Satellite image data

[0454] Step 3: Image analysis

[0455] The server preprocesses the acquired satellite image data and performs color segmentation to identify the water surface. Specifically, it uses Python's OpenCV library to extract the RGB values ​​of each pixel in the water surface area of ​​the image. This temporarily saves the data on the water surface area from the satellite image.

[0456] Input: Satellite image data

[0457] Output: RGB value data of the water surface

[0458] Step 4: Water quality estimation

[0459] The server uses a machine learning model (e.g., a TensorFlow model) to estimate water quality parameters (e.g., turbidity, chlorophyll concentration) from the extracted RGB values. The machine learning model takes the RGB values ​​as input data and outputs the water quality parameters.

[0460] Input: RGB value data for the water surface

[0461] Output: Water quality parameters (turbidity, chlorophyll concentration)

[0462] Step 5: Environmental impact simulation

[0463] The server acquires external data such as meteorological data to simulate future environmental impacts based on water quality parameters. The server then executes a simulation model (e.g., AnyLogic) and compiles the simulation results in a report format.

[0464] Input: Water quality parameters, meteorological data

[0465] Output: Environmental impact simulation results and report

[0466] Step 6: Emotion Recognition

[0467] The device recognizes the user's emotions. Specifically, the device uses a camera and microphone to analyze the user's facial expressions and voice, and generates emotional data. This emotional data is sent to the server in real time.

[0468] Input: User's facial expression and voice data

[0469] Output: Emotion data

[0470] Step 7: Adjust the results display

[0471] The server receives the emotion data and adjusts the display format of the results based on the user's emotion. For example, if the user is feeling stressed, the display format is simplified to make it easier to understand.

[0472] Input: Emotion data, environmental impact simulation results

[0473] Output: Reconciled report

[0474] Step 8: Send and view results

[0475] The server generates and sends the adjusted report to the terminal, which receives it and displays it on the user interface, where the user can view the results.

[0476] Input: Reconciled report

[0477] Output: The results displayed in the user interface

[0478] Step 9: Emotional response

[0479] The server generates alerts and suggestions based on the user's emotions and sends them to the device. For example, if the user is feeling anxious, an alert offering additional information or support will be displayed. The device receives this and displays it in the user interface.

[0480] Input: Emotion data

[0481] Output: Alerts and suggestions

[0482] The above processing steps realize a system that allows users to efficiently and quickly conduct water quality surveys and predict environmental loads, and receive feedback that takes emotions into consideration.

[0483] (Application example 2)

[0484] 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."

[0485] Existing water quality monitoring systems are inefficient, requiring time and effort to collect and analyze data. Furthermore, in the field of eco-friendly food delivery, it is difficult to select products that take into account the water quality and environmental impact of the production area, and feedback that reflects user stress and emotions is lacking. The present invention aims to solve these issues and realize efficient and widespread water quality monitoring and eco-friendly food delivery.

[0486] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0487] In this invention, the server includes means for providing a user interface for specifying a specific area to a terminal, means for acquiring satellite image data of the specified area from an external information provider, and means for preprocessing the acquired satellite image data to identify water body portions, thereby enabling rapid and efficient prediction of water quality indexes.

[0488] The server also includes means for extracting RGB values ​​of the water body portion, means for using a machine learning model to predict water quality indexes from the extracted RGB values, means for simulating environmental loads based on the predicted water quality indexes, means for compiling the simulation results in report format and sending it to the terminal, means for recognizing the user's emotions and displaying results or issuing alerts according to those emotions, and means for the terminal to display the results on the user interface.This enables users to monitor water quality and predict environmental loads efficiently and over a wide area, and the feedback system that takes user emotions into consideration makes the system easier to use and more secure.

[0489] "User interface" refers to the terminal screen or application that the user operates to specify a specific area or display a result.

[0490] A "terminal" is a device that a user operates directly and uses to access the system through an interface, such as a smartphone or computer.

[0491] "External Information Provider" means an external data provider or information supplier that the System connects with to obtain satellite imagery data or other necessary data.

[0492] "Satellite image data" refers to image data taken from a satellite and used to understand the environmental conditions of a particular region or area.

[0493] "Water area" refers to the area in satellite image data that includes the water surface, and is an area identified using techniques such as color segmentation.

[0494] "RGB value" is a numerical value that indicates the intensity of the red, green, and blue colors of each pixel in satellite image data.

[0495] A "machine learning model" is an algorithm or computational model that learns patterns from data and makes predictions about new data.

[0496] "Water quality index" is an index that indicates the state of the water environment, and includes, for example, turbidity and chlorophyll concentration.

[0497] "Environmental load" refers to the degree of impact of human activities and natural phenomena on a particular environment, and is predicted through simulation.

[0498] "Emotion recognition" is a technology that determines a user's emotions in real time based on their facial expressions, voice, input patterns, etc.

[0499] "Result display" is the process by which the system presents the results of analysis and simulation to the user in a visually understandable manner.

[0500] An "alert" is a message or notification that the system uses to alert the user in response to a specific condition or situation.

[0501] The present invention is a system that uses satellite image data to estimate water quality indexes, simulates environmental impacts based on that data, recognizes the user's emotions, and displays results and alerts accordingly. To implement this system, the following program is configured.

[0502] Hardware and software used

[0503] Satellite imagery acquisition: Web API (e.g. Sentinel Hub API)

[0504] Image processing: OpenCV

[0505] Machine learning models: Keras, TensorFlow

[0506] Emotion recognition: dlib (face recognition), Keras (emotion recognition)

[0507] User Interface: Web and mobile applications

[0508] Processing Overview

[0509] 1. Data acquisition function

[0510] The server uses the API of an external information provider to obtain satellite image data for a specific area and date and time specified by the user via the user interface. The data obtained from the API is stored as image data on the server.

[0511] 2. Image analysis function

[0512] The server preprocesses the acquired satellite image data and identifies water areas using color segmentation, extracts the RGB values ​​of each pixel in the identified water areas, and temporarily stores them.

[0513] 3. Water quality estimation function

[0514] The server feeds the stored RGB values ​​into a machine learning model built using TensorFlow and Keras to estimate water quality indicators (e.g., turbidity and chlorophyll concentration).

[0515] 4. Environmental impact simulation function

[0516] The server simulates the environmental impact based on the estimated water quality index and necessary external data (e.g., meteorological data). The simulation results are analyzed and compiled into a report.

[0517] 5. Result transmission and display function

[0518] The simulation results, compiled in report format, are sent from the server to the terminal, which displays the results through a user interface so that the user can visually check them.

[0519] 6. Emotion recognition and display adjustment function

[0520] The device recognizes the user's emotions in real time based on data such as facial expressions, voice, and input patterns. Dlib and Keras are used for emotion recognition. The server receives the recognized emotion data and adjusts the display format of the results. For example, if the user is feeling stressed, the results will be displayed in a simpler format.

[0521] Specific examples

[0522] We will provide a concrete example of investigating the water quality of a specific lake, predicting the environmental impact, and displaying the results according to the user's emotions.

[0523] 1. User Input: The user enters the coordinates of a particular lake and the date and time they wish to survey on their terminal.

[0524] 2. Obtaining satellite image data: The server obtains satellite image data for the specified coordinates and date and time.

[0525] 3. Image analysis: The server identifies the water areas and extracts the RGB values.

[0526] 4. Water quality estimation: Estimate water quality indicators using machine learning models.

[0527] 5. Environmental Load Simulation: The server simulates the environmental load and creates a report.

[0528] 6. Displaying the results: The server sends the report to the terminal, which displays the results.

[0529] 7. Emotion recognition and display adjustment: The device recognizes the user's emotions, and the server adjusts the display accordingly.

[0530] Prompt Sentence Examples

[0531] "Coordinates of designated area: 35.6895, 139.6917; Survey date: 2023-10-15; Eco-friendly report desired."

[0532] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0533] Step 1:

[0534] User Input

[0535] The user uses the terminal's user interface to input a specific area and the date and time they wish to survey. The input data includes the area's coordinates (latitude and longitude) and the survey date. For example, the input format is "Coordinates of specified area: 35.6895, 139.6917; Survey date: 2023-10-15." This data is then sent from the terminal to the server.

[0536] Input: Area coordinates, survey date

[0537] Output: The request data sent to the server

[0538] Step 2:

[0539] Data Acquisition

[0540] Based on the request data received from the user, the server uses the API of an external information provider to obtain satellite image data for the specified area and date and time. The server sends an API request and receives the image data. This data is temporarily stored on the server.

[0541] Input: Request data (area coordinates, survey date)

[0542] Output: Satellite image data

[0543] Specific operation: The server creates and sends an API request. The acquired satellite image data is saved.

[0544] Step 3:

[0545] Image analysis

[0546] The server preprocesses the acquired satellite image data and uses color segmentation to identify water areas. This process involves converting the image into RGB color space and defining a color range to identify water areas. The image is then masked to extract the water areas.

[0547] Input: Satellite image data

[0548] Output: RGB values ​​of water area

[0549] Specific operation: The server analyzes the satellite image data and applies color segmentation to identify water areas.

[0550] Step 4:

[0551] Water quality estimation

[0552] The server inputs the extracted RGB values ​​into a machine learning model to estimate water quality indices (e.g., turbidity and chlorophyll concentration). The model is pre-trained and outputs water quality indices based on the RGB values.

[0553] Input: RGB values ​​of water area

[0554] Output: Estimated water quality index

[0555] Specific operation: The server inputs the RGB values ​​into a machine learning model, which then predicts the water quality index.

[0556] Step 5:

[0557] Environmental impact simulation

[0558] The server simulates the environmental load based on the predicted water quality index and necessary external data (e.g., meteorological data). The simulation uses the water quality index and other environmental parameters to predict future environmental loads.

[0559] Input: Estimated water quality index, external data

[0560] Output: Environmental impact simulation results

[0561] Specific operation: The server obtains external data and executes the simulation model.

[0562] Step 6:

[0563] Report generation and transmission

[0564] The server analyzes the simulation results and compiles them into a report, which includes water quality indicators, predicted environmental impacts, and graphs and charts. The report is then sent to the terminal.

[0565] Input: Environmental load simulation results

[0566] Output: Report

[0567] Specific operation: The server compiles the analysis results into a report format and sends it to the terminal.

[0568] Step 7:

[0569] Results display

[0570] The terminal displays the report received from the server on the user interface, allowing the user to visually check the water quality status and environmental impact forecast for the area they entered.

[0571] Input: report

[0572] Output: The results displayed in the user interface

[0573] Specific operation: The terminal receives the report and displays it on the interface.

[0574] Step 8:

[0575] Emotion recognition and response

[0576] The device recognizes the user's emotions in real time, such as facial expressions and voice. This data is sent to a server, which then adjusts the display format of the results based on the recognized emotion. For example, if the user is feeling stressed, the server will change the display format to make the results easier to understand.

[0577] Input: User's facial expressions, voice, and input patterns

[0578] Output: Adjusted results display

[0579] Specific operation: The device collects emotion data and sends it to the server. The server adjusts the display of the results and causes the device to update the display.

[0580] Through these steps, users can efficiently and widely monitor water quality and predict environmental impacts, and the feedback system that responds to users' emotions makes the system easier to use and safer to use.

[0581] 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.

[0582] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (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.

[0583] 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.

[0584] [Second embodiment]

[0585] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0586] 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.

[0587] 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).

[0588] 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.

[0589] 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.

[0590] 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).

[0591] 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.

[0592] 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.

[0593] 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.

[0594] 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.

[0595] 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.

[0596] 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."

[0597] This invention is a system that uses satellite image data to quickly and efficiently estimate water quality parameters and then simulates environmental loads based on that data. The configuration and functions for implementing this system will be described in detail.

[0598] System configuration

[0599] The system mainly consists of the following components:

[0600] 1. User Interface (Terminal)

[0601] 2. Server

[0602] 3. External Data Providers

[0603] User Interface (Terminal)

[0604] The user interface allows users to operate the system and specify a specific area. For example, it can be implemented as a web application or a mobile application. Through the interface, users can enter the coordinates of the area they want to investigate and the investigation period. The interface also provides graphs and reports for visual confirmation of analysis and simulation results.

[0605] server

[0606] The server plays a central role in processing and managing data. The main functions of the server are explained below.

[0607] 1. Data acquisition function

[0608] The server receives the request sent by the user and retrieves satellite image data for the specified area using the API of an external data provider.

[0609] 2. Image analysis function

[0610] The acquired satellite image data is preprocessed and color segmentation is performed to identify the water surface.

[0611] The RGB values ​​of each pixel on the water surface are extracted and temporarily saved.

[0612] 3. Water quality estimation function

[0613] Water quality parameters (turbidity, chlorophyll concentration, etc.) are estimated from the RGB values ​​extracted using a machine learning model.

[0614] 4. Environmental impact simulation function

[0615] Based on the water quality parameters, external data (e.g., meteorological data) necessary for simulating future environmental loads are obtained.

[0616] The simulation model is run and the results are analyzed and compiled in report format.

[0617] 5. Result transmission function

[0618] The generated report and simulation results are sent to the terminal.

[0619] External Data Providers

[0620] External data providers are services or organizations that provide satellite imagery and other necessary data. The server works with these providers to obtain the data and use it for analysis.

[0621] Example of operation

[0622] Below is a specific example of using this system to investigate the water quality of a specific lake.

[0623] 1. User Input

[0624] The user uses the terminal interface to input the coordinates of a particular lake and the date and time range they wish to survey.

[0625] 2. Data Acquisition

[0626] The terminal transmits the input data to the server, which then makes a request to an external data provider to obtain satellite image data for the specified area and period.

[0627] 3. Image Analysis

[0628] The server receives the satellite image data and performs color segmentation to identify the water surface.

[0629] Extract the RGB values ​​and feed them into a machine learning model.

[0630] 4. Water quality estimation

[0631] A machine learning model estimates water quality parameters such as turbidity and chlorophyll concentration from RGB values.

[0632] 5. Environmental Load Simulation

[0633] The server runs an environmental impact simulation, analyzes the results, and compiles them into a report.

[0634] 6. Sending and displaying results

[0635] The server sends the generated report to the terminal, which displays the results on a user interface.

[0636] Users can check the analysis and simulation results via their devices and consider the necessary measures and actions.

[0637] The above process enables faster and more widespread water quality surveys and environmental load predictions than conventional methods, resulting in a system that provides useful information for environmental conservation activities and policy formulation.

[0638] The processing flow will be explained below.

[0639] Step 1:

[0640] The user inputs the coordinates of the area to be surveyed and the survey period through the terminal interface, and the terminal transmits this input data to the server.

[0641] Step 2:

[0642] Based on the request received from the device, the server sends an API request to an external data provider to obtain satellite image data for the specified area and period.

[0643] Step 3:

[0644] The server preprocesses the satellite image data it acquires, specifically adjusting the resolution, cropping unnecessary parts, and adjusting brightness and contrast.

[0645] Step 4:

[0646] The server runs image analysis algorithms to identify water surfaces, for example, using color segmentation techniques such as k-means clustering.

[0647] Step 5:

[0648] The server extracts the RGB values ​​of each pixel from the identified water surface area and temporarily stores them in memory.

[0649] Step 6:

[0650] The server inputs the extracted RGB values ​​into a pre-trained machine learning model to estimate water quality parameters (e.g., turbidity, chlorophyll concentration).

[0651] Step 7:

[0652] The server aggregates the estimated water quality parameters and calculates statistical information such as the mean, median, and standard deviation.

[0653] Step 8:

[0654] The server compares the current water quality situation with past data from the same area and data from other areas.

[0655] Step 9:

[0656] The server obtains external data (e.g., weather data, flow rate data) necessary to simulate future environmental loads.

[0657] Step 10:

[0658] The server builds an environmental model and simulates future changes in water quality and their impacts.

[0659] Step 11:

[0660] The server analyzes the simulation results and compiles them into a report, which includes visual elements such as graphs and heat maps.

[0661] Step 12:

[0662] The server sends the generated report to the terminal.

[0663] Step 13:

[0664] The terminal displays the received report on the user interface, and the user confirms the results.

[0665] Step 14:

[0666] Based on the results displayed, the user considers the necessary measures and actions.

[0667] Example 1

[0668] 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."

[0669] Conventional water quality survey methods require on-site sampling, which is time-consuming and costly, and the scope of data collection is limited. Furthermore, simulations for predicting environmental impacts cannot be performed in real time, making it difficult to take prompt action. The present invention aims to solve these problems.

[0670] 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.

[0671] In this invention, the server includes means for providing a terminal with a user interface for specifying a specific area, means for acquiring satellite image data of the specified area from an external data provider, image processing means for preprocessing the acquired satellite image data and identifying the water surface, means for extracting RGB values ​​of the water surface, means for using a machine learning model to estimate water quality parameters from the extracted RGB values, means for simulating environmental impacts based on the estimated water quality parameters, means for compiling the simulation results in a report format and transmitting the results to the terminal, and means for the terminal to display the results on the user interface, thereby enabling fast and efficient water quality surveys and environmental impact predictions.

[0672] "Specific region" refers to the geographic area to be analyzed using satellite imagery, including coordinates and a time period specified by the user.

[0673] A "user interface" is a means by which a user operates a system, including web applications and mobile applications displayed on a terminal.

[0674] A "terminal" is a device operated by a user, and includes computing devices such as computers, smartphones, and tablets.

[0675] "Satellite image data" refers to image information acquired from cameras and sensors mounted on satellites, and includes visual data of a specific area.

[0676] "External data providers" are services or organizations that provide necessary data, such as satellite image data.

[0677] "Preprocessing" refers to the process of converting satellite image data into an analyzable format, removing noise, and adjusting resolution.

[0678] "Image processing means" refers to software tools and algorithms for analyzing images, including methods such as color segmentation.

[0679] The "water surface portion" refers to the pixel area of ​​the water area to be analyzed in the satellite image data.

[0680] "RGB values" refer to the values ​​of the red, green, and blue color components of each pixel, and represent the color information of a digital image.

[0681] A "machine learning model" refers to an algorithm that learns patterns from data and makes predictions or classifications for new data, and includes methods such as neural networks.

[0682] "Water quality parameters" refer to physical and chemical characteristics of water, such as turbidity and chlorophyll concentration.

[0683] "Environmental impact" refers to the impact on the environment predicted based on estimated water quality parameters, including future changes in water quality.

[0684] "Simulation" refers to a method of creating a virtual environment on a computer and predicting the future by imitating real-world behavior.

[0685] "Report format" refers to a documented analysis or simulation result, including digital formats such as PDF.

[0686] "Means for displaying results" refers to an interface that allows analysis results and simulation results to be visually confirmed on a terminal.

[0687] Overall system overview

[0688] This invention is a system that uses satellite image data to quickly and efficiently estimate water quality parameters and simulate environmental impacts based on that data. In this system, a server acquires the necessary satellite image data from an external data provider based on information about a region specified by a user, estimates water quality parameters using a machine learning model, and provides the results as a report.

[0689] Components and Functions

[0690] User Interface (Terminal)

[0691] The user interface allows users to operate the system and input the coordinates and period of the survey area. This user interface is implemented as a web or mobile application. For example, a user inputs the coordinates of Tokyo Bay (35.6895, 139.6917) and the survey period (April 1, 2023 to April 30, 2023).

[0692] server

[0693] The server is the center of data processing and has multiple functions.

[0694] 1. Data acquisition function

[0695] The server receives user input and uses the API of an external data provider to obtain satellite image data for the specified area, specifically, using a remote sensing service.

[0696] 2. Image analysis function

[0697] The server preprocesses the acquired satellite image data and performs color segmentation to identify the water surface, for example, by extracting RGB values ​​using OpenCV as an image processing tool.

[0698] 3. Water quality estimation function

[0699] The server inputs the extracted RGB values ​​into a machine learning model (e.g., a CNN using TensorFlow) to estimate water quality parameters such as turbidity and chlorophyll concentration.

[0700] 4. Environmental impact simulation function

[0701] Based on the estimated water quality parameters, the server obtains the external data (e.g., meteorological data) necessary to perform environmental impact simulations, and predicts future environmental impacts using a simulation tool (e.g., MATLAB).

[0702] 5. Result transmission function

[0703] The server compiles the simulation results into a report format (e.g., PDF) and sends it to the terminal.

[0704] Terminal

[0705] The terminal receives reports and simulation results sent from the server and displays them on the user interface, allowing the user to visually check the analysis and simulation results.

[0706] Specific operation example

[0707] Below is a specific example of using this system to investigate the water quality of a specific lake.

[0708] 1. User Input

[0709] The user uses the terminal interface to input the coordinates of a particular lake and the date and time range they wish to survey.

[0710] 2. Data Acquisition

[0711] The terminal transmits the input data to the server, which then makes a request to an external data provider to obtain satellite image data for the specified area and period.

[0712] 3. Image Analysis

[0713] The server receives satellite image data, performs color segmentation to identify the water surface, and extracts RGB values.

[0714] 4. Water quality estimation

[0715] A machine learning model estimates water quality parameters such as turbidity and chlorophyll concentration from RGB values.

[0716] 5. Environmental Load Simulation

[0717] The server runs the environmental impact simulation, analyzes the results, and compiles them into a report.

[0718] 6. Sending and displaying results

[0719] The server sends the generated report to the terminal, which displays the results on a user interface.

[0720] Prompt Sentence Examples

[0721] The following are examples of prompts used in this system:

[0722] Using the coordinates (35.6895, 139.6917) for the Tokyo area and the survey period (April 1, 2023 - April 30, 2023), we would like to estimate water quality parameters (turbidity, chlorophyll concentration) from satellite image data and simulate future environmental impacts.

[0723] This system supports rapid and efficient water quality surveys and predictions of environmental impacts, and can provide useful information for environmental conservation activities and policy formulation.

[0724] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0725] Step 1:

[0726] User input

[0727] The user opens the user interface on their device and enters the coordinates of the area to be surveyed and the period they wish to survey. For example, they enter "Tokyo Bay coordinates (35.6895, 139.6917)" and "survey period (April 1, 2023 - April 30, 2023)." The entered data is sent from the device to the server.

[0728] Input: Area coordinates and survey period

[0729] Output: Create input data in JSON format and send it to the server

[0730] Step 2:

[0731] Data retrieval by the server

[0732] Based on the received user input data, the server makes a request to the API of an external data provider to obtain satellite image data for the specified area and period. Specifically, it calls the API of a remote sensing service. For example, it sends a satellite image request for the specified coordinates and period and obtains satellite image data as a response.

[0733] Input: User-entered data

[0734] Output: Satellite image data for a specified area and period

[0735] Step 3:

[0736] Image analysis by server

[0737] The server preprocesses the acquired satellite image data, removing noise and adjusting the resolution. Next, it performs color segmentation using the image processing library OpenCV to identify the water surface. It then extracts RGB values ​​from each pixel in the identified water surface area and temporarily stores them.

[0738] Input: Satellite image data

[0739] Output: A list of RGB values ​​for the water surface

[0740] Step 4:

[0741] Water quality estimation by server

[0742] The server inputs the extracted RGB values ​​into a machine learning model (e.g., a CNN using TensorFlow) to estimate water quality parameters such as turbidity and chlorophyll concentration.

[0743] Input: RGB values ​​of the water surface

[0744] Output: Estimated water quality parameters (turbidity, chlorophyll concentration)

[0745] Step 5:

[0746] Environmental impact simulation using a server

[0747] The server uses the estimated water quality parameters and other necessary external data (e.g., meteorological data) to simulate future environmental impacts using simulation tools such as MATLAB. The simulation results are analyzed and compiled into a report (PDF).

[0748] Input: Estimated water quality parameters, external meteorological data

[0749] Output: Simulation result report (PDF format)

[0750] Step 6:

[0751] Sending and displaying results

[0752] The server sends the generated report to the terminal, which displays the received report on the user interface, where the user can check it and, if necessary, plan the next action.

[0753] Input: Simulation results report

[0754] Output: Report displayed in the user interface

[0755] The above are the specific processing steps of the program in this system.

[0756] (Application example 1)

[0757] 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."

[0758] Existing water quality monitoring systems have the problem of making it difficult to respond quickly when water quality abnormalities occur. While these systems are suitable for detecting abnormalities, they cannot report abnormalities in real time or compare specific environmental impact simulations with past data, which can delay early countermeasures. Furthermore, a lack of visualization and alert functions for water quality data also hinders the ability of relevant parties to respond quickly.

[0759] 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.

[0760] In this invention, the server includes means for providing a terminal with a user interface for specifying a specific area, means for acquiring satellite image data of the specified area from an external data provider, means for preprocessing the acquired satellite image data and identifying the water surface, and means for issuing an alert if the estimated water quality parameter contains an abnormal value. This allows an alert to be issued quickly to relevant parties when the water quality parameter indicates an abnormal value, enabling early countermeasures and responses.

[0761] A "user interface for specifying a specific area" is an input means for a user to select and specify an area of ​​interest, and is a software interface that runs on a terminal.

[0762] "Means for obtaining satellite image data for a specified area from an external data provider" refers to a system for obtaining satellite image data for a specified area from an external data provider, and is a function for collecting data through collaboration with APIs and data banks.

[0763] "Means for pre-processing acquired satellite image data and identifying water surface areas" refers to image processing techniques and algorithms for analyzing satellite image data and identifying water areas, thereby identifying water surface areas.

[0764] The "means for extracting RGB values ​​of the water surface portion" is a function for extracting the RGB (red, green, blue) values ​​of each pixel from the identified water surface portion, and is a means that utilizes image analysis technology.

[0765] "Means for using a machine learning model to estimate water quality parameters from extracted RGB values" refers to a function that uses a machine learning algorithm to predict water quality parameters (e.g., turbidity and chlorophyll concentration) using the extracted RGB values ​​as input.

[0766] The "means for simulating environmental loads based on estimated water quality parameters" is a function that utilizes estimated water quality parameters to execute a simulation model for predicting future environmental impacts.

[0767] The "means for issuing an alert if the estimated water quality parameter contains an abnormal value" is a function that immediately issues a warning if the predicted water quality parameter is determined to be within an abnormal range.

[0768] The "means for compiling the simulation results in a report format and transmitting it to the terminal" is a function for compiling the results of the environmental load simulation, creating a report, and transmitting the results to the user's terminal.

[0769] "Means for the terminal to display results on the user interface" refers to a function that displays the simulation results and predicted results of water quality parameters on the user interface, allowing the user to visually confirm them.

[0770] The present invention is a system for implementing water quality monitoring and environmental load simulation, which enables rapid response to pollution and abnormal water quality conditions. A specific embodiment of this system is described below.

[0771] System configuration

[0772] The system mainly consists of the following components:

[0773] 1. User Interface (Terminal)

[0774] 2. Server

[0775] 3. External Data Providers

[0776] User Interface (Terminal)

[0777] The user interface is the input means through which users operate the system. Through this interface, users input the coordinates of a specific area and the survey period. For example, it is implemented as a smartphone application, allowing users to easily specify an area using a map. This interface also provides graphs and reports for visually checking analysis and simulation results.

[0778] Prompt Sentence Examples

[0779] Enter the coordinates of the lake (e.g. 35.6581,139.7514):

[0780] Enter the period you want to investigate (e.g., 2023-01-01~2023-01-31):

[0781] Send coordinate and time period data to predict water quality parameters for a given area...

[0782] server

[0783] The server is the central point for processing and managing data. It has the following main functions:

[0784] 1. Data acquisition function: Receives a request sent by the user and acquires satellite image data for the specified area using the API of an external data provider.

[0785] 2. Image analysis function: Preprocesses acquired satellite image data to identify water surfaces, and extracts the RGB values ​​of each pixel from the identified water surface.

[0786] 3. Water quality estimation function: Estimates water quality parameters (turbidity, chlorophyll concentration, etc.) from RGB values ​​extracted using a machine learning model.

[0787] 4. Environmental load simulation function: Based on water quality parameters, the necessary data is obtained to simulate future environmental loads, and the simulation model is executed.

[0788] 5. Alert function: If the estimated water quality parameters contain abnormal values, an alert is sent to the relevant parties.

[0789] 6. Result transmission function: Sends the generated report and simulation results to the terminal.

[0790] The hardware used is a high-performance server computer, and the software used includes Flask (a Python framework), scikit-learn (machine learning models), and requests (external API calls).

[0791] External Data Providers

[0792] External data providers are services or organizations that provide satellite imagery and other necessary data. The server works with these providers to acquire the data and use it for analysis. The data is sent to the server via an API, where it undergoes any necessary preprocessing.

[0793] Example of operation

[0794] Below is a specific example of using this system to investigate the water quality of a specific lake and detect outliers.

[0795] 1. User input:

[0796] The user uses the terminal interface to input the coordinates of a particular lake and the date and time range they wish to survey.

[0797] 2. Data Acquisition:

[0798] Based on the data sent by the user, the server obtains satellite image data for the specified area through the API of an external data provider.

[0799] 3. Image Analysis:

[0800] The server preprocesses the acquired satellite image data to identify the water surface area, and then extracts the RGB values ​​of each pixel from the identified water surface area.

[0801] 4. Water quality estimation:

[0802] Using a machine learning model, water quality parameters such as turbidity and chlorophyll concentration are estimated from the extracted RGB values.

[0803] 5. Environmental impact simulation:

[0804] The server runs an environmental impact simulation, analyzes the results, and compiles them into a report.

[0805] 6. Alerting:

[0806] If the server detects abnormal values ​​in the estimated water quality parameters, it immediately sends an alert to relevant parties.

[0807] 7. Sending and viewing results:

[0808] The server sends the generated report to the terminal, which displays the results on the user interface. The user can visually check the analysis and simulation results and consider the necessary countermeasures and actions.

[0809] This will enable quicker and more widespread water quality surveys and environmental load predictions than conventional methods, and will provide a system that provides useful information for environmental conservation activities and policy formulation.

[0810] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0811] Step 1:

[0812] The user inputs the coordinates of a specific area and the survey period through the user interface of the terminal. The input data includes location information (latitude and longitude) and the survey period (date range). This determines the conditions for satellite imagery that the server should acquire.

[0813] Step 2:

[0814] The device sends the coordinates and time period data entered by the user to the server. The input data is sent in JSON format, and the server receives and parses it. The server then creates a request to the external data provider based on this data.

[0815] Step 3:

[0816] The server calls the API of an external data provider to obtain satellite image data for the specified area and period. The satellite image data is returned as a response from the API. The obtained satellite image data is temporarily stored on the server.

[0817] Step 4:

[0818] The server preprocesses the acquired satellite image data, specifically removing noise from the images and standardizing the resolution. Next, image processing algorithms are used to segment and recognize the water surface.

[0819] Step 5:

[0820] The RGB values ​​of each pixel in the water surface area are extracted from the preprocessed image. The extracted RGB values ​​serve as input data for the next processing step, water quality parameter estimation.

[0821] Step 6:

[0822] The server uses a machine learning model to estimate water quality parameters (turbidity, chlorophyll concentration, etc.) from the extracted RGB values. The machine learning model uses a pre-trained generative AI model, which inputs RGB values ​​and outputs water quality parameters.

[0823] Step 7:

[0824] The server simulates environmental loads based on the estimated water quality parameters. To do this, the server obtains meteorological and other environmental data from external data providers as needed and runs the simulation model.

[0825] Step 8:

[0826] The server compiles the simulation results in a report format, which includes the estimated water quality parameters and the simulation results. The report may also include graphs and charts for easy visual understanding.

[0827] Step 9:

[0828] The server sends the generated reports and simulation results to the terminal, where they are displayed on the user interface.

[0829] Step 10:

[0830] Users can visually check the analysis and simulation results through the terminal's user interface, and can consider the necessary countermeasures and actions based on this.

[0831] Step 11:

[0832] If the server detects any abnormalities in the estimated water quality parameters, it will immediately issue an alert, which will be sent to relevant parties via email or notification, enabling a prompt response.

[0833] 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.

[0834] This invention provides a system that uses satellite image data to quickly and efficiently estimate water quality parameters and simulate environmental impacts based on that data, as well as a function that recognizes the user's emotions and displays results and alerts accordingly. The configuration and functions for implementing this system are described in detail below.

[0835] System configuration

[0836] The system mainly consists of the following components:

[0837] 1. User Interface (Terminal)

[0838] 2. Server

[0839] 3. External Data Providers

[0840] 4. Emotion Engine

[0841] User Interface (Terminal)

[0842] The user interface allows users to operate the system and specify a specific area. For example, it can be implemented as a web application or a mobile application. Through the interface, users can enter the coordinates of the area they want to investigate and the investigation period. The interface also provides graphs and reports for visual confirmation of analysis and simulation results.

[0843] server

[0844] The server plays a central role in processing and managing data. The main functions of the server are explained below.

[0845] 1. Data acquisition function

[0846] The server receives the request sent by the user and retrieves satellite image data for the specified area using the API of an external data provider.

[0847] 2. Image analysis function

[0848] The acquired satellite image data is preprocessed and color segmentation is performed to identify the water surface.

[0849] The RGB values ​​of each pixel on the water surface are extracted and temporarily saved.

[0850] 3. Water quality estimation function

[0851] Water quality parameters (turbidity, chlorophyll concentration, etc.) are estimated from the RGB values ​​extracted using a machine learning model.

[0852] 4. Environmental impact simulation function

[0853] Based on the water quality parameters, external data (e.g., meteorological data) necessary for simulating future environmental loads are obtained.

[0854] The simulation model is run and the results are analyzed and compiled in report format.

[0855] 5. Result transmission function

[0856] The generated report and simulation results are sent to the terminal.

[0857] Emotion Engine

[0858] The emotion engine recognizes the user's emotions and adjusts the system's operation and display. The main functions of the emotion engine are explained below.

[0859] 1. Emotion recognition function

[0860] The device recognizes the user's emotions in real time based on their facial expressions, voice, input patterns, etc.

[0861] The recognized emotion data is sent to the server.

[0862] 2. Display adjustment function

[0863] The server changes the display format of the results based on the emotional data. For example, if the user is feeling stressed, the results will be displayed in a simpler format.

[0864] 3. Emotional response function

[0865] The server generates alerts and suggestions based on the user's emotions and sends them to the device. For example, if the user is feeling anxious, an alert will be displayed offering additional information or support.

[0866] Example of operation

[0867] Below is a specific example of using this system to investigate the water quality of a specific lake.

[0868] 1. User Input

[0869] The user uses the terminal interface to input the coordinates of a particular lake and the date and time range they wish to survey.

[0870] The terminal transmits the input data to the server.

[0871] 2. Data Acquisition

[0872] The server makes a request to an external data provider to obtain satellite image data for a specified region and time period.

[0873] 3. Image Analysis

[0874] The server preprocesses the acquired satellite image data and performs color segmentation to identify the water surface.

[0875] The RGB values ​​of each pixel on the water surface are extracted and fed into the machine learning model.

[0876] 4. Water quality estimation

[0877] A machine learning model estimates water quality parameters such as turbidity and chlorophyll concentration from RGB values.

[0878] 5. Environmental Load Simulation

[0879] The server runs an environmental impact simulation, analyzes the results, and compiles them into a report.

[0880] 6. Emotion Recognition and Display Adjustment

[0881] The device recognizes the user's emotions and transmits them to the server.

[0882] The server adjusts the display format of the report based on the user's feelings and sends it to the terminal.

[0883] 7. Sending and displaying results

[0884] The terminal displays the received report on the user interface, and the user confirms the results.

[0885] 8. Emotional Response

[0886] Depending on the user's emotions, the server generates additional alerts and suggestions and sends them to the device.

[0887] Through the above process, users can efficiently and widely conduct water quality surveys and predict environmental impacts, and a feedback system that takes users' feelings into consideration makes the system easier to use and more reliable.

[0888] The processing flow will be explained below.

[0889] Step 1:

[0890] The user inputs the coordinates of the area they want to survey and the survey period through the terminal interface, and the terminal sends this input data to the server.

[0891] Step 2:

[0892] Based on the request received from the device, the server sends an API request to an external data provider to obtain satellite image data for the specified area and period.

[0893] Step 3:

[0894] The server preprocesses the satellite image data it acquires, specifically adjusting the resolution, cropping unnecessary parts, and adjusting brightness and contrast.

[0895] Step 4:

[0896] The server runs image analysis algorithms to identify water surfaces, for example, using color segmentation techniques such as k-means clustering.

[0897] Step 5:

[0898] The server extracts the RGB values ​​of each pixel from the identified water surface area and temporarily stores them in memory.

[0899] Step 6:

[0900] The server inputs the extracted RGB values ​​into a pre-trained machine learning model to estimate water quality parameters (e.g., turbidity, chlorophyll concentration).

[0901] Step 7:

[0902] The server aggregates the estimated water quality parameters and calculates statistical information such as the mean, median, and standard deviation.

[0903] Step 8:

[0904] The server compares the current water quality situation with past data from the same area and data from other areas.

[0905] Step 9:

[0906] The server obtains external data (e.g., weather data, flow rate data) necessary to simulate future environmental loads.

[0907] Step 10:

[0908] The server builds an environmental model and simulates future changes in water quality and their impacts.

[0909] Step 11:

[0910] The server analyzes the simulation results and compiles them into a report, which includes visual elements such as graphs and heat maps.

[0911] Step 12:

[0912] The server sends the generated report to the terminal.

[0913] Step 13:

[0914] The terminal displays the received report on the user interface, and the user confirms the results.

[0915] Step 14:

[0916] The device activates an emotion engine to recognize the user's emotions and analyzes the user's facial expressions, voice, and input patterns.

[0917] Step 15:

[0918] The device transmits the recognized emotion data to the server.

[0919] Step 16:

[0920] The server changes the display format of the results based on the emotional data. For example, if the user is feeling stressed, the results will be displayed in a simpler format.

[0921] Step 17:

[0922] The server generates alerts and suggestions based on the user's emotions and sends them to the device. For example, if the user is feeling anxious, an alert will be displayed offering additional information or support.

[0923] Step 18:

[0924] The device displays the generated alerts and suggestions on a user interface.

[0925] Step 19:

[0926] The user considers the necessary measures and actions based on the displayed results and alerts.

[0927] Through this series of steps, users can efficiently conduct water quality surveys and predict environmental impacts, and also receive feedback that takes their own emotions into consideration.

[0928] Example 2

[0929] 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."

[0930] Conventional water quality analysis systems require large-scale data collection and processing, which results in long processing times and makes it difficult for users to obtain results quickly. Furthermore, user operations and information provision are uniform, and the systems are unable to respond to individual users' emotions and situations, resulting in low usability and user satisfaction. Therefore, there is a need for a system that can efficiently and quickly estimate water quality parameters and provide flexible result displays and alerts that respond to the user's emotions.

[0931] 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.

[0932] In this invention, the server includes means for providing a terminal with a user interface for specifying a specific area, means for acquiring satellite image data of the specified area from an external data provider, means for preprocessing the acquired satellite image data to identify the water surface, means for extracting RGB values ​​of the water surface, means for using a machine learning model to estimate water quality parameters from the extracted RGB values, means for simulating environmental impacts based on the estimated water quality parameters, means for compiling the simulation results in a report format and transmitting the results to the terminal, means for the terminal to display the results on the user interface, means for recognizing the user's emotions and adjusting the result display format according to the emotions, and means for generating alerts and suggestions based on the user's emotions. This enables users to quickly and efficiently estimate water quality parameters and receive flexible information provision according to their emotions and circumstances.

[0933] A "user interface" is the means by which a user operates a system and specifies a specific area. Specifically, it is often implemented as a web application or a mobile application.

[0934] "Terminal" refers to the device accessed by the user, and includes electronic devices such as personal computers, smartphones, and tablets.

[0935] A "server" is a computer system that processes data, manages it, and plays a central role in the entire system.

[0936] An "external data provider" is a third-party data provider that provides data from outside, and includes, for example, an organization that provides satellite image data.

[0937] "Satellite image data" refers to image data captured by a satellite, and includes geographical information and environmental information.

[0938] "Preprocessing" refers to the process of preparing acquired data before analyzing it, and includes noise removal and filtering.

[0939] "Water surface area" refers to the area of ​​satellite image data that represents water bodies.

[0940] "RGB value" is the color information contained in a pixel of image data, and is composed of red, green, and blue values.

[0941] "Water quality parameters" are indicators for evaluating water quality, and include turbidity, chlorophyll concentration, etc.

[0942] A "machine learning model" is an algorithm that analyzes data and learns patterns, which are used for prediction and classification.

[0943] "Environmental load" refers to the degree of impact on the environment, including, for example, the amount of pollutants and the impact on the ecosystem.

[0944] "Simulation" is the process of simulating real-world situations and predicting future conditions.

[0945] A "report" is a document or digital file that summarizes the results of an analysis or simulation.

[0946] "Emotion" refers to the user's psychological state, and includes, for example, joy, sadness, anger, anxiety, and the like.

[0947] An "alert" is a notification or warning that conveys information to the user.

[0948] "Suggestion" refers to advice or guidance given to the user.

[0949] "Result display format" refers to the format or style in which analysis results or simulation results are displayed on the user interface.

[0950] "Recognition" is the process by which the system understands the user's state from facial expressions, voice, etc.

[0951] "Flexible information provision" refers to providing information in an appropriate format according to the user's situation and emotions.

[0952] MODE FOR CARRYING OUT THE INVENTION

[0953] The present invention relates to a system for efficiently and quickly estimating water quality parameters and providing flexible result displays and alerts according to the user's emotions. Specific embodiments of the present invention will be described in detail below.

[0954] System configuration

[0955] The system mainly consists of the following components:

[0956] 1. User Interface (Terminal)

[0957] 2. Server

[0958] 3. External Data Providers

[0959] 4. Emotion Engine

[0960] User Interface (Terminal)

[0961] The user interface is the means by which users operate the system and specify a specific area. Specifically, it is implemented as a web application or mobile application. Users can operate their device to enter the coordinates of the area they want to survey and the survey period. Graphs and reports are also provided to visually confirm the analysis and simulation results.

[0962] server

[0963] The server is the central location for processing and managing data. It provides the following functions:

[0964] 1. Data acquisition function

[0965] The server receives the request sent by the user and retrieves satellite image data for the specified area using the API of an external data provider, for example, the NASA Earthdata API.

[0966] 2. Image analysis function

[0967] The server preprocesses the acquired satellite image data to identify the water surface area. Specifically, it performs color segmentation using Python's OpenCV library and extracts the RGB values ​​of each pixel in the water surface area.

[0968] 3. Water quality estimation function

[0969] The server uses a machine learning model (e.g., TensorFlow) to estimate water quality parameters (e.g., turbidity and chlorophyll concentration) from the extracted RGB values.

[0970] 4. Environmental impact simulation function

[0971] The server acquires external data (e.g., meteorological data) necessary to simulate future environmental impacts based on water quality parameters. AnyLogic is used as the simulation model, and the analysis results are compiled in a report format.

[0972] 5. Result transmission function

[0973] The server sends the generated report and simulation results to the terminal, which receives them and displays them on the user interface.

[0974] Emotion Engine

[0975] The emotion engine recognizes the user's emotions and adjusts the system's operation and display accordingly. The emotion engine's functions are as follows:

[0976] 1. Emotion recognition function

[0977] The device uses a camera and microphone to analyze the user's facial expressions and voice to recognize emotions, and this data is sent to a server.

[0978] 2. Display adjustment function

[0979] The server changes the way the results are displayed based on the emotion data, for example, if the user is feeling stressed, the results are displayed in a simpler format.

[0980] 3. Emotional response function

[0981] The server generates alerts and suggestions based on the user's emotions and sends them to the device. For example, if the user is feeling anxious, an alert will be displayed offering additional information or support.

[0982] Example of operation

[0983] 1. User Input

[0984] The user uses the terminal interface to input the coordinates of a specific lake (e.g., latitude 35.6581°, longitude 139.7414°) and the survey period (e.g., May 1, 2023 to May 10, 2023). The terminal then transmits the input data to the server.

[0985] 2. Data Acquisition

[0986] The server makes a request to an external data provider to obtain satellite image data for a specified region and time period.

[0987] 3. Image Analysis

[0988] The server preprocesses the acquired satellite image data and performs color segmentation to identify the water surface area. The RGB values ​​of each pixel in the water surface area are extracted and fed into the machine learning model.

[0989] 4. Water quality estimation

[0990] A machine learning model estimates water quality parameters such as turbidity and chlorophyll concentration from RGB values.

[0991] 5. Environmental Load Simulation

[0992] The server runs an environmental impact simulation, analyzes the results, and compiles them into a report.

[0993] 6. Emotion Recognition and Display Adjustment

[0994] The device recognizes the user's emotions and sends them to the server, which then adjusts the report display format based on the user's emotions and sends it to the device.

[0995] 7. Sending and displaying results

[0996] The terminal displays the received report on the user interface, and the user confirms the results.

[0997] 8. Emotional Response

[0998] Depending on the user's emotions, the server generates additional alerts and suggestions and sends them to the device.

[0999] Prompt Sentence Examples

[1000] An example of a prompt for operating this system is, "Investigate the water quality of the lake at latitude 35.6581 degrees and longitude 139.7414 degrees from May 1, 2023 to May 10, 2023, and display the simulated results of the environmental impact. Also, adjust the display format and alerts according to the user's emotions."

[1001] As described above, this system efficiently and quickly conducts water quality surveys and predicts environmental impacts, and also provides feedback that responds to the user's emotions, thereby realizing a user-friendly interface.

[1002] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1003] Step 1: User Input

[1004] The user uses the device interface to input the coordinates of the area they want to survey and the survey period. For example, the user might input, "Survey a lake at latitude 35.6581 degrees and longitude 139.7414 degrees from May 1, 2023 to May 10, 2023." The device receives this input data and sends it to the server in JSON format.

[1005] Input: Area coordinates, survey period

[1006] Output: Request data in JSON format

[1007] Step 2: Data Acquisition

[1008] The server receives the request sent by the user and retrieves satellite image data for the specified area and period using the API of an external data provider. For example, the server sends a request to the NASA Earthdata API to retrieve the relevant data. The retrieved data is stored on the server.

[1009] Input: Request data in JSON format

[1010] Output: Satellite image data

[1011] Step 3: Image analysis

[1012] The server preprocesses the acquired satellite image data and performs color segmentation to identify the water surface. Specifically, it uses Python's OpenCV library to extract the RGB values ​​of each pixel in the water surface area of ​​the image. This temporarily saves the data on the water surface area from the satellite image.

[1013] Input: Satellite image data

[1014] Output: RGB value data of the water surface

[1015] Step 4: Water quality estimation

[1016] The server uses a machine learning model (e.g., a TensorFlow model) to estimate water quality parameters (e.g., turbidity, chlorophyll concentration) from the extracted RGB values. The machine learning model takes the RGB values ​​as input data and outputs the water quality parameters.

[1017] Input: RGB value data for the water surface

[1018] Output: Water quality parameters (turbidity, chlorophyll concentration)

[1019] Step 5: Environmental impact simulation

[1020] The server acquires external data such as meteorological data to simulate future environmental impacts based on water quality parameters. The server then executes a simulation model (e.g., AnyLogic) and compiles the simulation results in a report format.

[1021] Input: Water quality parameters, meteorological data

[1022] Output: Environmental impact simulation results and report

[1023] Step 6: Emotion Recognition

[1024] The device recognizes the user's emotions. Specifically, the device uses a camera and microphone to analyze the user's facial expressions and voice, and generates emotional data. This emotional data is sent to the server in real time.

[1025] Input: User's facial expression and voice data

[1026] Output: Emotion data

[1027] Step 7: Adjust the results display

[1028] The server receives the emotion data and adjusts the display format of the results based on the user's emotion. For example, if the user is feeling stressed, the display format is simplified to make it easier to understand.

[1029] Input: Emotion data, environmental impact simulation results

[1030] Output: Reconciled report

[1031] Step 8: Send and view results

[1032] The server generates and sends the adjusted report to the terminal, which receives it and displays it on the user interface, where the user can view the results.

[1033] Input: Reconciled report

[1034] Output: The results displayed in the user interface

[1035] Step 9: Emotional response

[1036] The server generates alerts and suggestions based on the user's emotions and sends them to the device. For example, if the user is feeling anxious, an alert offering additional information or support will be displayed. The device receives this and displays it in the user interface.

[1037] Input: Emotion data

[1038] Output: Alerts and suggestions

[1039] The above processing steps realize a system that allows users to efficiently and quickly conduct water quality surveys and predict environmental loads, and receive feedback that takes emotions into consideration.

[1040] (Application example 2)

[1041] 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."

[1042] Existing water quality monitoring systems are inefficient, requiring time and effort to collect and analyze data. Furthermore, in the field of eco-friendly food delivery, it is difficult to select products that take into account the water quality and environmental impact of the production area, and feedback that reflects user stress and emotions is lacking. The present invention aims to solve these issues and realize efficient and widespread water quality monitoring and eco-friendly food delivery.

[1043] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1044] In this invention, the server includes means for providing a user interface for specifying a specific area to a terminal, means for acquiring satellite image data of the specified area from an external information provider, and means for preprocessing the acquired satellite image data to identify water body portions, thereby enabling rapid and efficient prediction of water quality indexes.

[1045] The server also includes means for extracting RGB values ​​of the water body portion, means for using a machine learning model to predict water quality indexes from the extracted RGB values, means for simulating environmental loads based on the predicted water quality indexes, means for compiling the simulation results in report format and sending it to the terminal, means for recognizing the user's emotions and displaying results or issuing alerts according to those emotions, and means for the terminal to display the results on the user interface.This enables users to monitor water quality and predict environmental loads efficiently and over a wide area, and the feedback system that takes user emotions into consideration makes the system easier to use and more secure.

[1046] "User interface" refers to the terminal screen or application that the user operates to specify a specific area or display a result.

[1047] A "terminal" is a device that a user operates directly and uses to access the system through an interface, such as a smartphone or computer.

[1048] "External Information Provider" means an external data provider or information supplier that the System connects with to obtain satellite imagery data or other necessary data.

[1049] "Satellite image data" refers to image data taken from a satellite and used to understand the environmental conditions of a particular region or area.

[1050] "Water area" refers to the area in satellite image data that includes the water surface, and is an area identified using techniques such as color segmentation.

[1051] "RGB value" is a numerical value that indicates the intensity of the red, green, and blue colors of each pixel in satellite image data.

[1052] A "machine learning model" is an algorithm or computational model that learns patterns from data and makes predictions about new data.

[1053] "Water quality index" is an index that indicates the state of the water environment, and includes, for example, turbidity and chlorophyll concentration.

[1054] "Environmental load" refers to the degree of impact of human activities and natural phenomena on a particular environment, and is predicted through simulation.

[1055] "Emotion recognition" is a technology that determines a user's emotions in real time based on their facial expressions, voice, input patterns, etc.

[1056] "Result display" is the process by which the system presents the results of analysis and simulation to the user in a visually understandable manner.

[1057] An "alert" is a message or notification that the system uses to alert the user in response to a specific condition or situation.

[1058] The present invention is a system that uses satellite image data to estimate water quality indexes, simulates environmental impacts based on that data, recognizes the user's emotions, and displays results and alerts accordingly. To implement this system, the following program is configured.

[1059] Hardware and software used

[1060] Satellite imagery acquisition: Web API (e.g. Sentinel Hub API)

[1061] Image processing: OpenCV

[1062] Machine learning models: Keras, TensorFlow

[1063] Emotion recognition: dlib (face recognition), Keras (emotion recognition)

[1064] User Interface: Web and mobile applications

[1065] Processing Overview

[1066] 1. Data acquisition function

[1067] The server uses the API of an external information provider to obtain satellite image data for a specific area and date and time specified by the user via the user interface. The data obtained from the API is stored as image data on the server.

[1068] 2. Image analysis function

[1069] The server preprocesses the acquired satellite image data and identifies water areas using color segmentation, extracts the RGB values ​​of each pixel in the identified water areas, and temporarily stores them.

[1070] 3. Water quality estimation function

[1071] The server feeds the stored RGB values ​​into a machine learning model built using TensorFlow and Keras to estimate water quality indicators (e.g., turbidity and chlorophyll concentration).

[1072] 4. Environmental impact simulation function

[1073] The server simulates the environmental impact based on the estimated water quality index and necessary external data (e.g., meteorological data). The simulation results are analyzed and compiled into a report.

[1074] 5. Result transmission and display function

[1075] The simulation results, compiled in report format, are sent from the server to the terminal, which displays the results through a user interface so that the user can visually check them.

[1076] 6. Emotion recognition and display adjustment function

[1077] The device recognizes the user's emotions in real time based on data such as facial expressions, voice, and input patterns. Dlib and Keras are used for emotion recognition. The server receives the recognized emotion data and adjusts the display format of the results. For example, if the user is feeling stressed, the results will be displayed in a simpler format.

[1078] Specific examples

[1079] We will provide a concrete example of investigating the water quality of a specific lake, predicting the environmental impact, and displaying the results according to the user's emotions.

[1080] 1. User Input: The user enters the coordinates of a particular lake and the date and time they wish to survey on their terminal.

[1081] 2. Obtaining satellite image data: The server obtains satellite image data for the specified coordinates and date and time.

[1082] 3. Image analysis: The server identifies the water areas and extracts the RGB values.

[1083] 4. Water quality estimation: Estimate water quality indicators using machine learning models.

[1084] 5. Environmental Load Simulation: The server simulates the environmental load and creates a report.

[1085] 6. Displaying the results: The server sends the report to the terminal, which displays the results.

[1086] 7. Emotion recognition and display adjustment: The device recognizes the user's emotions, and the server adjusts the display accordingly.

[1087] Prompt Sentence Examples

[1088] "Coordinates of designated area: 35.6895, 139.6917; Survey date: 2023-10-15; Eco-friendly report desired."

[1089] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1090] Step 1:

[1091] User Input

[1092] The user uses the terminal's user interface to input a specific area and the date and time they wish to survey. The input data includes the area's coordinates (latitude and longitude) and the survey date. For example, the input format is "Coordinates of specified area: 35.6895, 139.6917; Survey date: 2023-10-15." This data is then sent from the terminal to the server.

[1093] Input: Area coordinates, survey date

[1094] Output: The request data sent to the server

[1095] Step 2:

[1096] Data Acquisition

[1097] Based on the request data received from the user, the server uses the API of an external information provider to obtain satellite image data for the specified area and date and time. The server sends an API request and receives the image data. This data is temporarily stored on the server.

[1098] Input: Request data (area coordinates, survey date)

[1099] Output: Satellite image data

[1100] Specific operation: The server creates and sends an API request. The acquired satellite image data is saved.

[1101] Step 3:

[1102] Image analysis

[1103] The server preprocesses the acquired satellite image data and uses color segmentation to identify water areas. This process involves converting the image into RGB color space and defining a color range to identify water areas. The image is then masked to extract the water areas.

[1104] Input: Satellite image data

[1105] Output: RGB values ​​of water area

[1106] Specific operation: The server analyzes the satellite image data and applies color segmentation to identify water areas.

[1107] Step 4:

[1108] Water quality estimation

[1109] The server inputs the extracted RGB values ​​into a machine learning model to estimate water quality indices (e.g., turbidity and chlorophyll concentration). The model is pre-trained and outputs water quality indices based on the RGB values.

[1110] Input: RGB values ​​of water area

[1111] Output: Estimated water quality index

[1112] Specific operation: The server inputs the RGB values ​​into a machine learning model, which then predicts the water quality index.

[1113] Step 5:

[1114] Environmental impact simulation

[1115] The server simulates the environmental load based on the predicted water quality index and necessary external data (e.g., meteorological data). The simulation uses the water quality index and other environmental parameters to predict future environmental loads.

[1116] Input: Estimated water quality index, external data

[1117] Output: Environmental impact simulation results

[1118] Specific operation: The server obtains external data and executes the simulation model.

[1119] Step 6:

[1120] Report generation and transmission

[1121] The server analyzes the simulation results and compiles them into a report, which includes water quality indicators, predicted environmental impacts, and graphs and charts. The report is then sent to the terminal.

[1122] Input: Environmental load simulation results

[1123] Output: Report

[1124] Specific operation: The server compiles the analysis results into a report format and sends it to the terminal.

[1125] Step 7:

[1126] Results display

[1127] The terminal displays the report received from the server on the user interface, allowing the user to visually check the water quality status and environmental impact forecast for the area they entered.

[1128] Input: report

[1129] Output: The results displayed in the user interface

[1130] Specific operation: The terminal receives the report and displays it on the interface.

[1131] Step 8:

[1132] Emotion recognition and response

[1133] The device recognizes the user's emotions in real time, such as facial expressions and voice. This data is sent to a server, which then adjusts the display format of the results based on the recognized emotion. For example, if the user is feeling stressed, the server will change the display format to make the results easier to understand.

[1134] Input: User's facial expressions, voice, and input patterns

[1135] Output: Adjusted results display

[1136] Specific operation: The device collects emotion data and sends it to the server. The server adjusts the display of the results and causes the device to update the display.

[1137] Through these steps, users can efficiently and widely monitor water quality and predict environmental impacts, and the feedback system that responds to users' emotions makes the system easier to use and safer to use.

[1138] 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.

[1139] 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.

[1140] 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.

[1141] [Third embodiment]

[1142] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[1143] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[1144] 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).

[1145] 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.

[1146] 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.

[1147] 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).

[1148] 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.

[1149] 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.

[1150] 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.

[1151] 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.

[1152] 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.

[1153] 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."

[1154] This invention is a system that uses satellite image data to quickly and efficiently estimate water quality parameters and then simulates environmental loads based on that data. The configuration and functions for implementing this system will be described in detail.

[1155] System configuration

[1156] The system mainly consists of the following components:

[1157] 1. User Interface (Terminal)

[1158] 2. Server

[1159] 3. External Data Providers

[1160] User Interface (Terminal)

[1161] The user interface allows users to operate the system and specify a specific area. For example, it can be implemented as a web application or a mobile application. Through the interface, users can enter the coordinates of the area they want to investigate and the investigation period. The interface also provides graphs and reports for visual confirmation of analysis and simulation results.

[1162] server

[1163] The server plays a central role in processing and managing data. The main functions of the server are explained below.

[1164] 1. Data acquisition function

[1165] The server receives the request sent by the user and retrieves satellite image data for the specified area using the API of an external data provider.

[1166] 2. Image analysis function

[1167] The acquired satellite image data is preprocessed and color segmentation is performed to identify the water surface.

[1168] The RGB values ​​of each pixel on the water surface are extracted and temporarily saved.

[1169] 3. Water quality estimation function

[1170] Water quality parameters (turbidity, chlorophyll concentration, etc.) are estimated from the RGB values ​​extracted using a machine learning model.

[1171] 4. Environmental impact simulation function

[1172] Based on the water quality parameters, external data (e.g., meteorological data) necessary for simulating future environmental loads are obtained.

[1173] The simulation model is run and the results are analyzed and compiled in report format.

[1174] 5. Result transmission function

[1175] The generated report and simulation results are sent to the terminal.

[1176] External Data Providers

[1177] External data providers are services or organizations that provide satellite imagery and other necessary data. The server works with these providers to obtain the data and use it for analysis.

[1178] Example of operation

[1179] Below is a specific example of using this system to investigate the water quality of a specific lake.

[1180] 1. User Input

[1181] The user uses the terminal interface to input the coordinates of a particular lake and the date and time range they wish to survey.

[1182] 2. Data Acquisition

[1183] The terminal transmits the input data to the server, which then makes a request to an external data provider to obtain satellite image data for the specified area and period.

[1184] 3. Image Analysis

[1185] The server receives the satellite image data and performs color segmentation to identify the water surface.

[1186] Extract the RGB values ​​and feed them into a machine learning model.

[1187] 4. Water quality estimation

[1188] A machine learning model estimates water quality parameters such as turbidity and chlorophyll concentration from RGB values.

[1189] 5. Environmental Load Simulation

[1190] The server runs an environmental impact simulation, analyzes the results, and compiles them into a report.

[1191] 6. Sending and displaying results

[1192] The server sends the generated report to the terminal, which displays the results on a user interface.

[1193] Users can check the analysis and simulation results via their devices and consider the necessary measures and actions.

[1194] The above process enables faster and more widespread water quality surveys and environmental load predictions than conventional methods, resulting in a system that provides useful information for environmental conservation activities and policy formulation.

[1195] The processing flow will be explained below.

[1196] Step 1:

[1197] The user inputs the coordinates of the area to be surveyed and the survey period through the terminal interface, and the terminal transmits this input data to the server.

[1198] Step 2:

[1199] Based on the request received from the device, the server sends an API request to an external data provider to obtain satellite image data for the specified area and period.

[1200] Step 3:

[1201] The server preprocesses the satellite image data it acquires, specifically adjusting the resolution, cropping unnecessary parts, and adjusting brightness and contrast.

[1202] Step 4:

[1203] The server runs image analysis algorithms to identify water surfaces, for example, using color segmentation techniques such as k-means clustering.

[1204] Step 5:

[1205] The server extracts the RGB values ​​of each pixel from the identified water surface area and temporarily stores them in memory.

[1206] Step 6:

[1207] The server inputs the extracted RGB values ​​into a pre-trained machine learning model to estimate water quality parameters (e.g., turbidity, chlorophyll concentration).

[1208] Step 7:

[1209] The server aggregates the estimated water quality parameters and calculates statistical information such as the mean, median, and standard deviation.

[1210] Step 8:

[1211] The server compares the current water quality situation with past data from the same area and data from other areas.

[1212] Step 9:

[1213] The server obtains external data (e.g., weather data, flow rate data) necessary to simulate future environmental loads.

[1214] Step 10:

[1215] The server builds an environmental model and simulates future changes in water quality and their impacts.

[1216] Step 11:

[1217] The server analyzes the simulation results and compiles them into a report, which includes visual elements such as graphs and heat maps.

[1218] Step 12:

[1219] The server sends the generated report to the terminal.

[1220] Step 13:

[1221] The terminal displays the received report on the user interface, and the user confirms the results.

[1222] Step 14:

[1223] Based on the results displayed, the user considers the necessary measures and actions.

[1224] Example 1

[1225] 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."

[1226] Conventional water quality survey methods require on-site sampling, which is time-consuming and costly, and the scope of data collection is limited. Furthermore, simulations for predicting environmental impacts cannot be performed in real time, making it difficult to take prompt action. The present invention aims to solve these problems.

[1227] 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.

[1228] In this invention, the server includes means for providing a terminal with a user interface for specifying a specific area, means for acquiring satellite image data of the specified area from an external data provider, image processing means for preprocessing the acquired satellite image data and identifying the water surface, means for extracting RGB values ​​of the water surface, means for using a machine learning model to estimate water quality parameters from the extracted RGB values, means for simulating environmental impacts based on the estimated water quality parameters, means for compiling the simulation results in a report format and transmitting the results to the terminal, and means for the terminal to display the results on the user interface, thereby enabling fast and efficient water quality surveys and environmental impact predictions.

[1229] "Specific region" refers to the geographic area to be analyzed using satellite imagery, including coordinates and a time period specified by the user.

[1230] A "user interface" is a means by which a user operates a system, including web applications and mobile applications displayed on a terminal.

[1231] A "terminal" is a device operated by a user, and includes computing devices such as computers, smartphones, and tablets.

[1232] "Satellite image data" refers to image information acquired from cameras and sensors mounted on satellites, and includes visual data of a specific area.

[1233] "External data providers" are services or organizations that provide necessary data, such as satellite image data.

[1234] "Preprocessing" refers to the process of converting satellite image data into an analyzable format, removing noise, and adjusting resolution.

[1235] "Image processing means" refers to software tools and algorithms for analyzing images, including methods such as color segmentation.

[1236] The "water surface portion" refers to the pixel area of ​​the water area to be analyzed in the satellite image data.

[1237] "RGB values" refer to the values ​​of the red, green, and blue color components of each pixel, and represent the color information of a digital image.

[1238] A "machine learning model" refers to an algorithm that learns patterns from data and makes predictions or classifications for new data, and includes methods such as neural networks.

[1239] "Water quality parameters" refer to physical and chemical characteristics of water, such as turbidity and chlorophyll concentration.

[1240] "Environmental impact" refers to the impact on the environment predicted based on estimated water quality parameters, including future changes in water quality.

[1241] "Simulation" refers to a method of creating a virtual environment on a computer and predicting the future by imitating real-world behavior.

[1242] "Report format" refers to a documented analysis or simulation result, including digital formats such as PDF.

[1243] "Means for displaying results" refers to an interface that allows analysis results and simulation results to be visually confirmed on a terminal.

[1244] Overall system overview

[1245] This invention is a system that uses satellite image data to quickly and efficiently estimate water quality parameters and simulate environmental impacts based on that data. In this system, a server acquires the necessary satellite image data from an external data provider based on information about a region specified by a user, estimates water quality parameters using a machine learning model, and provides the results as a report.

[1246] Components and Functions

[1247] User Interface (Terminal)

[1248] The user interface allows users to operate the system and input the coordinates and period of the survey area. This user interface is implemented as a web or mobile application. For example, a user inputs the coordinates of Tokyo Bay (35.6895, 139.6917) and the survey period (April 1, 2023 to April 30, 2023).

[1249] server

[1250] The server is the center of data processing and has multiple functions.

[1251] 1. Data acquisition function

[1252] The server receives user input and uses the API of an external data provider to obtain satellite image data for the specified area, specifically, using a remote sensing service.

[1253] 2. Image analysis function

[1254] The server preprocesses the acquired satellite image data and performs color segmentation to identify the water surface, for example, by extracting RGB values ​​using OpenCV as an image processing tool.

[1255] 3. Water quality estimation function

[1256] The server inputs the extracted RGB values ​​into a machine learning model (e.g., a CNN using TensorFlow) to estimate water quality parameters such as turbidity and chlorophyll concentration.

[1257] 4. Environmental impact simulation function

[1258] Based on the estimated water quality parameters, the server obtains the external data (e.g., meteorological data) necessary to perform environmental impact simulations, and predicts future environmental impacts using a simulation tool (e.g., MATLAB).

[1259] 5. Result transmission function

[1260] The server compiles the simulation results into a report format (e.g., PDF) and sends it to the terminal.

[1261] Terminal

[1262] The terminal receives reports and simulation results sent from the server and displays them on the user interface, allowing the user to visually check the analysis and simulation results.

[1263] Specific operation example

[1264] Below is a specific example of using this system to investigate the water quality of a specific lake.

[1265] 1. User Input

[1266] The user uses the terminal interface to input the coordinates of a particular lake and the date and time range they wish to survey.

[1267] 2. Data Acquisition

[1268] The terminal transmits the input data to the server, which then makes a request to an external data provider to obtain satellite image data for the specified area and period.

[1269] 3. Image Analysis

[1270] The server receives satellite image data, performs color segmentation to identify the water surface, and extracts RGB values.

[1271] 4. Water quality estimation

[1272] A machine learning model estimates water quality parameters such as turbidity and chlorophyll concentration from RGB values.

[1273] 5. Environmental Load Simulation

[1274] The server runs the environmental impact simulation, analyzes the results, and compiles them into a report.

[1275] 6. Sending and displaying results

[1276] The server sends the generated report to the terminal, which displays the results on a user interface.

[1277] Prompt Sentence Examples

[1278] The following are examples of prompts used in this system:

[1279] Using the coordinates (35.6895, 139.6917) for the Tokyo area and the survey period (April 1, 2023 - April 30, 2023), we would like to estimate water quality parameters (turbidity, chlorophyll concentration) from satellite image data and simulate future environmental impacts.

[1280] This system supports rapid and efficient water quality surveys and predictions of environmental impacts, and can provide useful information for environmental conservation activities and policy formulation.

[1281] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1282] Step 1:

[1283] User input

[1284] The user opens the user interface on their device and enters the coordinates of the area to be surveyed and the period they wish to survey. For example, they enter "Tokyo Bay coordinates (35.6895, 139.6917)" and "survey period (April 1, 2023 - April 30, 2023)." The entered data is sent from the device to the server.

[1285] Input: Area coordinates and survey period

[1286] Output: Create input data in JSON format and send it to the server

[1287] Step 2:

[1288] Data retrieval by the server

[1289] Based on the received user input data, the server makes a request to the API of an external data provider to obtain satellite image data for the specified area and period. Specifically, it calls the API of a remote sensing service. For example, it sends a satellite image request for the specified coordinates and period and obtains satellite image data as a response.

[1290] Input: User-entered data

[1291] Output: Satellite image data for a specified area and period

[1292] Step 3:

[1293] Image analysis by server

[1294] The server preprocesses the acquired satellite image data, removing noise and adjusting the resolution. Next, it performs color segmentation using the image processing library OpenCV to identify the water surface. It then extracts RGB values ​​from each pixel in the identified water surface area and temporarily stores them.

[1295] Input: Satellite image data

[1296] Output: A list of RGB values ​​for the water surface

[1297] Step 4:

[1298] Water quality estimation by server

[1299] The server inputs the extracted RGB values ​​into a machine learning model (e.g., a CNN using TensorFlow) to estimate water quality parameters such as turbidity and chlorophyll concentration.

[1300] Input: RGB values ​​of the water surface

[1301] Output: Estimated water quality parameters (turbidity, chlorophyll concentration)

[1302] Step 5:

[1303] Environmental impact simulation using a server

[1304] The server uses the estimated water quality parameters and other necessary external data (e.g., meteorological data) to simulate future environmental impacts using simulation tools such as MATLAB. The simulation results are analyzed and compiled into a report (PDF).

[1305] Input: Estimated water quality parameters, external meteorological data

[1306] Output: Simulation result report (PDF format)

[1307] Step 6:

[1308] Sending and displaying results

[1309] The server sends the generated report to the terminal, which displays the received report on the user interface, where the user can check it and, if necessary, plan the next action.

[1310] Input: Simulation results report

[1311] Output: Report displayed in the user interface

[1312] The above are the specific processing steps of the program in this system.

[1313] (Application example 1)

[1314] 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."

[1315] Existing water quality monitoring systems have the problem of making it difficult to respond quickly when water quality abnormalities occur. While these systems are suitable for detecting abnormalities, they cannot report abnormalities in real time or compare specific environmental impact simulations with past data, which can delay early countermeasures. Furthermore, a lack of visualization and alert functions for water quality data also hinders the ability of relevant parties to respond quickly.

[1316] 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.

[1317] In this invention, the server includes means for providing a terminal with a user interface for specifying a specific area, means for acquiring satellite image data of the specified area from an external data provider, means for preprocessing the acquired satellite image data and identifying the water surface, and means for issuing an alert if the estimated water quality parameter contains an abnormal value. This allows an alert to be issued quickly to relevant parties when the water quality parameter indicates an abnormal value, enabling early countermeasures and responses.

[1318] A "user interface for specifying a specific area" is an input means for a user to select and specify an area of ​​interest, and is a software interface that runs on a terminal.

[1319] "Means for obtaining satellite image data for a specified area from an external data provider" refers to a system for obtaining satellite image data for a specified area from an external data provider, and is a function for collecting data through collaboration with APIs and data banks.

[1320] "Means for pre-processing acquired satellite image data and identifying water surface areas" refers to image processing techniques and algorithms for analyzing satellite image data and identifying water areas, thereby identifying water surface areas.

[1321] The "means for extracting RGB values ​​of the water surface portion" is a function for extracting the RGB (red, green, blue) values ​​of each pixel from the identified water surface portion, and is a means that utilizes image analysis technology.

[1322] "Means for using a machine learning model to estimate water quality parameters from extracted RGB values" refers to a function that uses a machine learning algorithm to predict water quality parameters (e.g., turbidity and chlorophyll concentration) using the extracted RGB values ​​as input.

[1323] The "means for simulating environmental loads based on estimated water quality parameters" is a function that utilizes estimated water quality parameters to execute a simulation model for predicting future environmental impacts.

[1324] The "means for issuing an alert if the estimated water quality parameter contains an abnormal value" is a function that immediately issues a warning if the predicted water quality parameter is determined to be within an abnormal range.

[1325] The "means for compiling the simulation results in a report format and transmitting it to the terminal" is a function for compiling the results of the environmental load simulation, creating a report, and transmitting the results to the user's terminal.

[1326] "Means for the terminal to display results on the user interface" refers to a function that displays the simulation results and predicted results of water quality parameters on the user interface, allowing the user to visually confirm them.

[1327] The present invention is a system for implementing water quality monitoring and environmental load simulation, which enables rapid response to pollution and abnormal water quality conditions. A specific embodiment of this system is described below.

[1328] System configuration

[1329] The system mainly consists of the following components:

[1330] 1. User Interface (Terminal)

[1331] 2. Server

[1332] 3. External Data Providers

[1333] User Interface (Terminal)

[1334] The user interface is the input means through which users operate the system. Through this interface, users input the coordinates of a specific area and the survey period. For example, it is implemented as a smartphone application, allowing users to easily specify an area using a map. This interface also provides graphs and reports for visually checking analysis and simulation results.

[1335] Prompt Sentence Examples

[1336] Enter the coordinates of the lake (e.g. 35.6581,139.7514):

[1337] Enter the period you want to investigate (e.g., 2023-01-01~2023-01-31):

[1338] Send coordinate and time period data to predict water quality parameters for a given area...

[1339] server

[1340] The server is the central point for processing and managing data. It has the following main functions:

[1341] 1. Data acquisition function: Receives a request sent by the user and acquires satellite image data for the specified area using the API of an external data provider.

[1342] 2. Image analysis function: Preprocesses acquired satellite image data to identify water surfaces, and extracts the RGB values ​​of each pixel from the identified water surface.

[1343] 3. Water quality estimation function: Estimates water quality parameters (turbidity, chlorophyll concentration, etc.) from RGB values ​​extracted using a machine learning model.

[1344] 4. Environmental load simulation function: Based on water quality parameters, the necessary data is obtained to simulate future environmental loads, and the simulation model is executed.

[1345] 5. Alert function: If the estimated water quality parameters contain abnormal values, an alert is sent to the relevant parties.

[1346] 6. Result transmission function: Sends the generated report and simulation results to the terminal.

[1347] The hardware used is a high-performance server computer, and the software used includes Flask (a Python framework), scikit-learn (machine learning models), and requests (external API calls).

[1348] External Data Providers

[1349] External data providers are services or organizations that provide satellite imagery and other necessary data. The server works with these providers to acquire the data and use it for analysis. The data is sent to the server via an API, where it undergoes any necessary preprocessing.

[1350] Example of operation

[1351] Below is a specific example of using this system to investigate the water quality of a specific lake and detect outliers.

[1352] 1. User input:

[1353] The user uses the terminal interface to input the coordinates of a particular lake and the date and time range they wish to survey.

[1354] 2. Data Acquisition:

[1355] Based on the data sent by the user, the server obtains satellite image data for the specified area through the API of an external data provider.

[1356] 3. Image Analysis:

[1357] The server preprocesses the acquired satellite image data to identify the water surface area, and then extracts the RGB values ​​of each pixel from the identified water surface area.

[1358] 4. Water quality estimation:

[1359] Using a machine learning model, water quality parameters such as turbidity and chlorophyll concentration are estimated from the extracted RGB values.

[1360] 5. Environmental impact simulation:

[1361] The server runs an environmental impact simulation, analyzes the results, and compiles them into a report.

[1362] 6. Alerting:

[1363] If the server detects abnormal values ​​in the estimated water quality parameters, it immediately sends an alert to relevant parties.

[1364] 7. Sending and viewing results:

[1365] The server sends the generated report to the terminal, which displays the results on the user interface. The user can visually check the analysis and simulation results and consider the necessary countermeasures and actions.

[1366] This will enable quicker and more widespread water quality surveys and environmental load predictions than conventional methods, and will provide a system that provides useful information for environmental conservation activities and policy formulation.

[1367] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1368] Step 1:

[1369] The user inputs the coordinates of a specific area and the survey period through the user interface of the terminal. The input data includes location information (latitude and longitude) and the survey period (date range). This determines the conditions for satellite imagery that the server should acquire.

[1370] Step 2:

[1371] The device sends the coordinates and time period data entered by the user to the server. The input data is sent in JSON format, and the server receives and parses it. The server then creates a request to the external data provider based on this data.

[1372] Step 3:

[1373] The server calls the API of an external data provider to obtain satellite image data for the specified area and period. The satellite image data is returned as a response from the API. The obtained satellite image data is temporarily stored on the server.

[1374] Step 4:

[1375] The server preprocesses the acquired satellite image data, specifically removing noise from the images and standardizing the resolution. Next, image processing algorithms are used to segment and recognize the water surface.

[1376] Step 5:

[1377] The RGB values ​​of each pixel in the water surface area are extracted from the preprocessed image. The extracted RGB values ​​serve as input data for the next processing step, water quality parameter estimation.

[1378] Step 6:

[1379] The server uses a machine learning model to estimate water quality parameters (turbidity, chlorophyll concentration, etc.) from the extracted RGB values. The machine learning model uses a pre-trained generative AI model, which inputs RGB values ​​and outputs water quality parameters.

[1380] Step 7:

[1381] The server simulates environmental loads based on the estimated water quality parameters. To do this, the server obtains meteorological and other environmental data from external data providers as needed and runs the simulation model.

[1382] Step 8:

[1383] The server compiles the simulation results in a report format, which includes the estimated water quality parameters and the simulation results. The report may also include graphs and charts for easy visual understanding.

[1384] Step 9:

[1385] The server sends the generated reports and simulation results to the terminal, where they are displayed on the user interface.

[1386] Step 10:

[1387] Users can visually check the analysis and simulation results through the terminal's user interface, and can consider the necessary countermeasures and actions based on this.

[1388] Step 11:

[1389] If the server detects any abnormalities in the estimated water quality parameters, it will immediately issue an alert, which will be sent to relevant parties via email or notification, enabling a prompt response.

[1390] 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.

[1391] This invention provides a system that uses satellite image data to quickly and efficiently estimate water quality parameters and simulate environmental impacts based on that data, as well as a function that recognizes the user's emotions and displays results and alerts accordingly. The configuration and functions for implementing this system are described in detail below.

[1392] System configuration

[1393] The system mainly consists of the following components:

[1394] 1. User Interface (Terminal)

[1395] 2. Server

[1396] 3. External Data Providers

[1397] 4. Emotion Engine

[1398] User Interface (Terminal)

[1399] The user interface allows users to operate the system and specify a specific area. For example, it can be implemented as a web application or a mobile application. Through the interface, users can enter the coordinates of the area they want to investigate and the investigation period. The interface also provides graphs and reports for visual confirmation of analysis and simulation results.

[1400] server

[1401] The server plays a central role in processing and managing data. The main functions of the server are explained below.

[1402] 1. Data acquisition function

[1403] The server receives the request sent by the user and retrieves satellite image data for the specified area using the API of an external data provider.

[1404] 2. Image analysis function

[1405] The acquired satellite image data is preprocessed and color segmentation is performed to identify the water surface.

[1406] The RGB values ​​of each pixel on the water surface are extracted and temporarily saved.

[1407] 3. Water quality estimation function

[1408] Water quality parameters (turbidity, chlorophyll concentration, etc.) are estimated from the RGB values ​​extracted using a machine learning model.

[1409] 4. Environmental impact simulation function

[1410] Based on the water quality parameters, external data (e.g., meteorological data) necessary for simulating future environmental loads are obtained.

[1411] The simulation model is run and the results are analyzed and compiled in report format.

[1412] 5. Result transmission function

[1413] The generated report and simulation results are sent to the terminal.

[1414] Emotion Engine

[1415] The emotion engine recognizes the user's emotions and adjusts the system's operation and display. The main functions of the emotion engine are explained below.

[1416] 1. Emotion recognition function

[1417] The device recognizes the user's emotions in real time based on their facial expressions, voice, input patterns, etc.

[1418] The recognized emotion data is sent to the server.

[1419] 2. Display adjustment function

[1420] The server changes the display format of the results based on the emotional data. For example, if the user is feeling stressed, the results will be displayed in a simpler format.

[1421] 3. Emotional response function

[1422] The server generates alerts and suggestions based on the user's emotions and sends them to the device. For example, if the user is feeling anxious, an alert will be displayed offering additional information or support.

[1423] Example of operation

[1424] Below is a specific example of using this system to investigate the water quality of a specific lake.

[1425] 1. User Input

[1426] The user uses the terminal interface to input the coordinates of a particular lake and the date and time range they wish to survey.

[1427] The terminal transmits the input data to the server.

[1428] 2. Data Acquisition

[1429] The server makes a request to an external data provider to obtain satellite image data for a specified region and time period.

[1430] 3. Image Analysis

[1431] The server preprocesses the acquired satellite image data and performs color segmentation to identify the water surface.

[1432] The RGB values ​​of each pixel on the water surface are extracted and fed into the machine learning model.

[1433] 4. Water quality estimation

[1434] A machine learning model estimates water quality parameters such as turbidity and chlorophyll concentration from RGB values.

[1435] 5. Environmental Load Simulation

[1436] The server runs an environmental impact simulation, analyzes the results, and compiles them into a report.

[1437] 6. Emotion Recognition and Display Adjustment

[1438] The device recognizes the user's emotions and transmits them to the server.

[1439] The server adjusts the display format of the report based on the user's feelings and sends it to the terminal.

[1440] 7. Sending and displaying results

[1441] The terminal displays the received report on the user interface, and the user confirms the results.

[1442] 8. Emotional Response

[1443] Depending on the user's emotions, the server generates additional alerts and suggestions and sends them to the device.

[1444] Through the above process, users can efficiently and widely conduct water quality surveys and predict environmental impacts, and a feedback system that takes users' feelings into consideration makes the system easier to use and more reliable.

[1445] The processing flow will be explained below.

[1446] Step 1:

[1447] The user inputs the coordinates of the area they want to survey and the survey period through the terminal interface, and the terminal sends this input data to the server.

[1448] Step 2:

[1449] Based on the request received from the device, the server sends an API request to an external data provider to obtain satellite image data for the specified area and period.

[1450] Step 3:

[1451] The server preprocesses the satellite image data it acquires, specifically adjusting the resolution, cropping unnecessary parts, and adjusting brightness and contrast.

[1452] Step 4:

[1453] The server runs image analysis algorithms to identify water surfaces, for example, using color segmentation techniques such as k-means clustering.

[1454] Step 5:

[1455] The server extracts the RGB values ​​of each pixel from the identified water surface area and temporarily stores them in memory.

[1456] Step 6:

[1457] The server inputs the extracted RGB values ​​into a pre-trained machine learning model to estimate water quality parameters (e.g., turbidity, chlorophyll concentration).

[1458] Step 7:

[1459] The server aggregates the estimated water quality parameters and calculates statistical information such as the mean, median, and standard deviation.

[1460] Step 8:

[1461] The server compares the current water quality situation with past data from the same area and data from other areas.

[1462] Step 9:

[1463] The server obtains external data (e.g., weather data, flow rate data) necessary to simulate future environmental loads.

[1464] Step 10:

[1465] The server builds an environmental model and simulates future changes in water quality and their impacts.

[1466] Step 11:

[1467] The server analyzes the simulation results and compiles them into a report, which includes visual elements such as graphs and heat maps.

[1468] Step 12:

[1469] The server sends the generated report to the terminal.

[1470] Step 13:

[1471] The terminal displays the received report on the user interface, and the user confirms the results.

[1472] Step 14:

[1473] The device activates an emotion engine to recognize the user's emotions and analyzes the user's facial expressions, voice, and input patterns.

[1474] Step 15:

[1475] The device transmits the recognized emotion data to the server.

[1476] Step 16:

[1477] The server changes the display format of the results based on the emotional data. For example, if the user is feeling stressed, the results will be displayed in a simpler format.

[1478] Step 17:

[1479] The server generates alerts and suggestions based on the user's emotions and sends them to the device. For example, if the user is feeling anxious, an alert will be displayed offering additional information or support.

[1480] Step 18:

[1481] The device displays the generated alerts and suggestions on a user interface.

[1482] Step 19:

[1483] The user considers the necessary measures and actions based on the displayed results and alerts.

[1484] Through this series of steps, users can efficiently conduct water quality surveys and predict environmental impacts, and also receive feedback that takes their own emotions into consideration.

[1485] Example 2

[1486] 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."

[1487] Conventional water quality analysis systems require large-scale data collection and processing, which results in long processing times and makes it difficult for users to obtain results quickly. Furthermore, user operations and information provision are uniform, and the systems are unable to respond to individual users' emotions and situations, resulting in low usability and user satisfaction. Therefore, there is a need for a system that can efficiently and quickly estimate water quality parameters and provide flexible result displays and alerts that respond to the user's emotions.

[1488] 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.

[1489] In this invention, the server includes means for providing a terminal with a user interface for specifying a specific area, means for acquiring satellite image data of the specified area from an external data provider, means for preprocessing the acquired satellite image data to identify the water surface, means for extracting RGB values ​​of the water surface, means for using a machine learning model to estimate water quality parameters from the extracted RGB values, means for simulating environmental impacts based on the estimated water quality parameters, means for compiling the simulation results in a report format and transmitting the results to the terminal, means for the terminal to display the results on the user interface, means for recognizing the user's emotions and adjusting the result display format according to the emotions, and means for generating alerts and suggestions based on the user's emotions. This enables users to quickly and efficiently estimate water quality parameters and receive flexible information provision according to their emotions and circumstances.

[1490] A "user interface" is the means by which a user operates a system and specifies a specific area. Specifically, it is often implemented as a web application or a mobile application.

[1491] "Terminal" refers to the device accessed by the user, and includes electronic devices such as personal computers, smartphones, and tablets.

[1492] A "server" is a computer system that processes data, manages it, and plays a central role in the entire system.

[1493] An "external data provider" is a third-party data provider that provides data from outside, and includes, for example, an organization that provides satellite image data.

[1494] "Satellite image data" refers to image data captured by a satellite, and includes geographical information and environmental information.

[1495] "Preprocessing" refers to the process of preparing acquired data before analyzing it, and includes noise removal and filtering.

[1496] "Water surface area" refers to the area of ​​satellite image data that represents water bodies.

[1497] "RGB value" is the color information contained in a pixel of image data, and is composed of red, green, and blue values.

[1498] "Water quality parameters" are indicators for evaluating water quality, and include turbidity, chlorophyll concentration, etc.

[1499] A "machine learning model" is an algorithm that analyzes data and learns patterns, which are used for prediction and classification.

[1500] "Environmental load" refers to the degree of impact on the environment, including, for example, the amount of pollutants and the impact on the ecosystem.

[1501] "Simulation" is the process of simulating real-world situations and predicting future conditions.

[1502] A "report" is a document or digital file that summarizes the results of an analysis or simulation.

[1503] "Emotion" refers to the user's psychological state, and includes, for example, joy, sadness, anger, anxiety, and the like.

[1504] An "alert" is a notification or warning that conveys information to the user.

[1505] "Suggestion" refers to advice or guidance given to the user.

[1506] "Result display format" refers to the format or style in which analysis results or simulation results are displayed on the user interface.

[1507] "Recognition" is the process by which the system understands the user's state from facial expressions, voice, etc.

[1508] "Flexible information provision" refers to providing information in an appropriate format according to the user's situation and emotions.

[1509] MODE FOR CARRYING OUT THE INVENTION

[1510] The present invention relates to a system for efficiently and quickly estimating water quality parameters and providing flexible result displays and alerts according to the user's emotions. Specific embodiments of the present invention will be described in detail below.

[1511] System configuration

[1512] The system mainly consists of the following components:

[1513] 1. User Interface (Terminal)

[1514] 2. Server

[1515] 3. External Data Providers

[1516] 4. Emotion Engine

[1517] User Interface (Terminal)

[1518] The user interface is the means by which users operate the system and specify a specific area. Specifically, it is implemented as a web application or mobile application. Users can operate their device to enter the coordinates of the area they want to survey and the survey period. Graphs and reports are also provided to visually confirm the analysis and simulation results.

[1519] server

[1520] The server is the central location for processing and managing data. It provides the following functions:

[1521] 1. Data acquisition function

[1522] The server receives the request sent by the user and retrieves satellite image data for the specified area using the API of an external data provider, for example, the NASA Earthdata API.

[1523] 2. Image analysis function

[1524] The server preprocesses the acquired satellite image data to identify the water surface area. Specifically, it performs color segmentation using Python's OpenCV library and extracts the RGB values ​​of each pixel in the water surface area.

[1525] 3. Water quality estimation function

[1526] The server uses a machine learning model (e.g., TensorFlow) to estimate water quality parameters (e.g., turbidity and chlorophyll concentration) from the extracted RGB values.

[1527] 4. Environmental impact simulation function

[1528] The server acquires external data (e.g., meteorological data) necessary to simulate future environmental impacts based on water quality parameters. AnyLogic is used as the simulation model, and the analysis results are compiled in a report format.

[1529] 5. Result transmission function

[1530] The server sends the generated report and simulation results to the terminal, which receives them and displays them on the user interface.

[1531] Emotion Engine

[1532] The emotion engine recognizes the user's emotions and adjusts the system's operation and display accordingly. The emotion engine's functions are as follows:

[1533] 1. Emotion recognition function

[1534] The device uses a camera and microphone to analyze the user's facial expressions and voice to recognize emotions, and this data is sent to a server.

[1535] 2. Display adjustment function

[1536] The server changes the way the results are displayed based on the emotion data, for example, if the user is feeling stressed, the results are displayed in a simpler format.

[1537] 3. Emotional response function

[1538] The server generates alerts and suggestions based on the user's emotions and sends them to the device. For example, if the user is feeling anxious, an alert will be displayed offering additional information or support.

[1539] Example of operation

[1540] 1. User Input

[1541] The user uses the terminal interface to input the coordinates of a specific lake (e.g., latitude 35.6581°, longitude 139.7414°) and the survey period (e.g., May 1, 2023 to May 10, 2023). The terminal then transmits the input data to the server.

[1542] 2. Data Acquisition

[1543] The server makes a request to an external data provider to obtain satellite image data for a specified region and time period.

[1544] 3. Image Analysis

[1545] The server preprocesses the acquired satellite image data and performs color segmentation to identify the water surface area. The RGB values ​​of each pixel in the water surface area are extracted and fed into the machine learning model.

[1546] 4. Water quality estimation

[1547] A machine learning model estimates water quality parameters such as turbidity and chlorophyll concentration from RGB values.

[1548] 5. Environmental Load Simulation

[1549] The server runs an environmental impact simulation, analyzes the results, and compiles them into a report.

[1550] 6. Emotion Recognition and Display Adjustment

[1551] The device recognizes the user's emotions and sends them to the server, which then adjusts the report display format based on the user's emotions and sends it to the device.

[1552] 7. Sending and displaying results

[1553] The terminal displays the received report on the user interface, and the user confirms the results.

[1554] 8. Emotional Response

[1555] Depending on the user's emotions, the server generates additional alerts and suggestions and sends them to the device.

[1556] Prompt Sentence Examples

[1557] An example of a prompt for operating this system is, "Investigate the water quality of the lake at latitude 35.6581 degrees and longitude 139.7414 degrees from May 1, 2023 to May 10, 2023, and display the simulated results of the environmental impact. Also, adjust the display format and alerts according to the user's emotions."

[1558] As described above, this system efficiently and quickly conducts water quality surveys and predicts environmental impacts, and also provides feedback that responds to the user's emotions, thereby realizing a user-friendly interface.

[1559] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1560] Step 1: User Input

[1561] The user uses the device interface to input the coordinates of the area they want to survey and the survey period. For example, the user might input, "Survey a lake at latitude 35.6581 degrees and longitude 139.7414 degrees from May 1, 2023 to May 10, 2023." The device receives this input data and sends it to the server in JSON format.

[1562] Input: Area coordinates, survey period

[1563] Output: Request data in JSON format

[1564] Step 2: Data Acquisition

[1565] The server receives the request sent by the user and retrieves satellite image data for the specified area and period using the API of an external data provider. For example, the server sends a request to the NASA Earthdata API to retrieve the relevant data. The retrieved data is stored on the server.

[1566] Input: Request data in JSON format

[1567] Output: Satellite image data

[1568] Step 3: Image analysis

[1569] The server preprocesses the acquired satellite image data and performs color segmentation to identify the water surface. Specifically, it uses Python's OpenCV library to extract the RGB values ​​of each pixel in the water surface area of ​​the image. This temporarily saves the data on the water surface area from the satellite image.

[1570] Input: Satellite image data

[1571] Output: RGB value data of the water surface

[1572] Step 4: Water quality estimation

[1573] The server uses a machine learning model (e.g., a TensorFlow model) to estimate water quality parameters (e.g., turbidity, chlorophyll concentration) from the extracted RGB values. The machine learning model takes the RGB values ​​as input data and outputs the water quality parameters.

[1574] Input: RGB value data for the water surface

[1575] Output: Water quality parameters (turbidity, chlorophyll concentration)

[1576] Step 5: Environmental impact simulation

[1577] The server acquires external data such as meteorological data to simulate future environmental impacts based on water quality parameters. The server then executes a simulation model (e.g., AnyLogic) and compiles the simulation results in a report format.

[1578] Input: Water quality parameters, meteorological data

[1579] Output: Environmental impact simulation results and report

[1580] Step 6: Emotion Recognition

[1581] The device recognizes the user's emotions. Specifically, the device uses a camera and microphone to analyze the user's facial expressions and voice, and generates emotional data. This emotional data is sent to the server in real time.

[1582] Input: User's facial expression and voice data

[1583] Output: Emotion data

[1584] Step 7: Adjust the results display

[1585] The server receives the emotion data and adjusts the display format of the results based on the user's emotion. For example, if the user is feeling stressed, the display format is simplified to make it easier to understand.

[1586] Input: Emotion data, environmental impact simulation results

[1587] Output: Reconciled report

[1588] Step 8: Send and view results

[1589] The server generates and sends the adjusted report to the terminal, which receives it and displays it on the user interface, where the user can view the results.

[1590] Input: Reconciled report

[1591] Output: The results displayed in the user interface

[1592] Step 9: Emotional response

[1593] The server generates alerts and suggestions based on the user's emotions and sends them to the device. For example, if the user is feeling anxious, an alert offering additional information or support will be displayed. The device receives this and displays it in the user interface.

[1594] Input: Emotion data

[1595] Output: Alerts and suggestions

[1596] The above processing steps realize a system that allows users to efficiently and quickly conduct water quality surveys and predict environmental loads, and receive feedback that takes emotions into consideration.

[1597] (Application example 2)

[1598] 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."

[1599] Existing water quality monitoring systems are inefficient, requiring time and effort to collect and analyze data. Furthermore, in the field of eco-friendly food delivery, it is difficult to select products that take into account the water quality and environmental impact of the production area, and feedback that reflects user stress and emotions is lacking. The present invention aims to solve these issues and realize efficient and widespread water quality monitoring and eco-friendly food delivery.

[1600] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1601] In this invention, the server includes means for providing a user interface for specifying a specific area to a terminal, means for acquiring satellite image data of the specified area from an external information provider, and means for preprocessing the acquired satellite image data to identify water body portions, thereby enabling rapid and efficient prediction of water quality indexes.

[1602] The server also includes means for extracting RGB values ​​of the water body portion, means for using a machine learning model to predict water quality indexes from the extracted RGB values, means for simulating environmental loads based on the predicted water quality indexes, means for compiling the simulation results in report format and sending it to the terminal, means for recognizing the user's emotions and displaying results or issuing alerts according to those emotions, and means for the terminal to display the results on the user interface.This enables users to monitor water quality and predict environmental loads efficiently and over a wide area, and the feedback system that takes user emotions into consideration makes the system easier to use and more secure.

[1603] "User interface" refers to the terminal screen or application that the user operates to specify a specific area or display a result.

[1604] A "terminal" is a device that a user operates directly and uses to access the system through an interface, such as a smartphone or computer.

[1605] "External Information Provider" means an external data provider or information supplier that the System connects with to obtain satellite imagery data or other necessary data.

[1606] "Satellite image data" refers to image data taken from a satellite and used to understand the environmental conditions of a particular region or area.

[1607] "Water area" refers to the area in satellite image data that includes the water surface, and is an area identified using techniques such as color segmentation.

[1608] "RGB value" is a numerical value that indicates the intensity of the red, green, and blue colors of each pixel in satellite image data.

[1609] A "machine learning model" is an algorithm or computational model that learns patterns from data and makes predictions about new data.

[1610] "Water quality index" is an index that indicates the state of the water environment, and includes, for example, turbidity and chlorophyll concentration.

[1611] "Environmental load" refers to the degree of impact of human activities and natural phenomena on a particular environment, and is predicted through simulation.

[1612] "Emotion recognition" is a technology that determines a user's emotions in real time based on their facial expressions, voice, input patterns, etc.

[1613] "Result display" is the process by which the system presents the results of analysis and simulation to the user in a visually understandable manner.

[1614] An "alert" is a message or notification that the system uses to alert the user in response to a specific condition or situation.

[1615] The present invention is a system that uses satellite image data to estimate water quality indexes, simulates environmental impacts based on that data, recognizes the user's emotions, and displays results and alerts accordingly. To implement this system, the following program is configured.

[1616] Hardware and software used

[1617] Satellite imagery acquisition: Web API (e.g. Sentinel Hub API)

[1618] Image processing: OpenCV

[1619] Machine learning models: Keras, TensorFlow

[1620] Emotion recognition: dlib (face recognition), Keras (emotion recognition)

[1621] User Interface: Web and mobile applications

[1622] Processing Overview

[1623] 1. Data acquisition function

[1624] The server uses the API of an external information provider to obtain satellite image data for a specific area and date and time specified by the user via the user interface. The data obtained from the API is stored as image data on the server.

[1625] 2. Image analysis function

[1626] The server preprocesses the acquired satellite image data and identifies water areas using color segmentation, extracts the RGB values ​​of each pixel in the identified water areas, and temporarily stores them.

[1627] 3. Water quality estimation function

[1628] The server feeds the stored RGB values ​​into a machine learning model built using TensorFlow and Keras to estimate water quality indicators (e.g., turbidity and chlorophyll concentration).

[1629] 4. Environmental impact simulation function

[1630] The server simulates the environmental impact based on the estimated water quality index and necessary external data (e.g., meteorological data). The simulation results are analyzed and compiled into a report.

[1631] 5. Result transmission and display function

[1632] The simulation results, compiled in report format, are sent from the server to the terminal, which displays the results through a user interface so that the user can visually check them.

[1633] 6. Emotion recognition and display adjustment function

[1634] The device recognizes the user's emotions in real time based on data such as facial expressions, voice, and input patterns. Dlib and Keras are used for emotion recognition. The server receives the recognized emotion data and adjusts the display format of the results. For example, if the user is feeling stressed, the results will be displayed in a simpler format.

[1635] Specific examples

[1636] We will provide a concrete example of investigating the water quality of a specific lake, predicting the environmental impact, and displaying the results according to the user's emotions.

[1637] 1. User Input: The user enters the coordinates of a particular lake and the date and time they wish to survey on their terminal.

[1638] 2. Obtaining satellite image data: The server obtains satellite image data for the specified coordinates and date and time.

[1639] 3. Image analysis: The server identifies the water areas and extracts the RGB values.

[1640] 4. Water quality estimation: Estimate water quality indicators using machine learning models.

[1641] 5. Environmental Load Simulation: The server simulates the environmental load and creates a report.

[1642] 6. Displaying the results: The server sends the report to the terminal, which displays the results.

[1643] 7. Emotion recognition and display adjustment: The device recognizes the user's emotions, and the server adjusts the display accordingly.

[1644] Prompt Sentence Examples

[1645] "Coordinates of designated area: 35.6895, 139.6917; Survey date: 2023-10-15; Eco-friendly report desired."

[1646] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1647] Step 1:

[1648] User Input

[1649] The user uses the terminal's user interface to input a specific area and the date and time they wish to survey. The input data includes the area's coordinates (latitude and longitude) and the survey date. For example, the input format is "Coordinates of specified area: 35.6895, 139.6917; Survey date: 2023-10-15." This data is then sent from the terminal to the server.

[1650] Input: Area coordinates, survey date

[1651] Output: The request data sent to the server

[1652] Step 2:

[1653] Data Acquisition

[1654] Based on the request data received from the user, the server uses the API of an external information provider to obtain satellite image data for the specified area and date and time. The server sends an API request and receives the image data. This data is temporarily stored on the server.

[1655] Input: Request data (area coordinates, survey date)

[1656] Output: Satellite image data

[1657] Specific operation: The server creates and sends an API request. The acquired satellite image data is saved.

[1658] Step 3:

[1659] Image analysis

[1660] The server preprocesses the acquired satellite image data and uses color segmentation to identify water areas. This process involves converting the image into RGB color space and defining a color range to identify water areas. The image is then masked to extract the water areas.

[1661] Input: Satellite image data

[1662] Output: RGB values ​​of water area

[1663] Specific operation: The server analyzes the satellite image data and applies color segmentation to identify water areas.

[1664] Step 4:

[1665] Water quality estimation

[1666] The server inputs the extracted RGB values ​​into a machine learning model to estimate water quality indices (e.g., turbidity and chlorophyll concentration). The model is pre-trained and outputs water quality indices based on the RGB values.

[1667] Input: RGB values ​​of water area

[1668] Output: Estimated water quality index

[1669] Specific operation: The server inputs the RGB values ​​into a machine learning model, which then predicts the water quality index.

[1670] Step 5:

[1671] Environmental impact simulation

[1672] The server simulates the environmental load based on the predicted water quality index and necessary external data (e.g., meteorological data). The simulation uses the water quality index and other environmental parameters to predict future environmental loads.

[1673] Input: Estimated water quality index, external data

[1674] Output: Environmental impact simulation results

[1675] Specific operation: The server obtains external data and executes the simulation model.

[1676] Step 6:

[1677] Report generation and transmission

[1678] The server analyzes the simulation results and compiles them into a report, which includes water quality indicators, predicted environmental impacts, and graphs and charts. The report is then sent to the terminal.

[1679] Input: Environmental load simulation results

[1680] Output: Report

[1681] Specific operation: The server compiles the analysis results into a report format and sends it to the terminal.

[1682] Step 7:

[1683] Results display

[1684] The terminal displays the report received from the server on the user interface, allowing the user to visually check the water quality status and environmental impact forecast for the area they entered.

[1685] Input: report

[1686] Output: The results displayed in the user interface

[1687] Specific operation: The terminal receives the report and displays it on the interface.

[1688] Step 8:

[1689] Emotion recognition and response

[1690] The device recognizes the user's emotions in real time, such as facial expressions and voice. This data is sent to a server, which then adjusts the display format of the results based on the recognized emotion. For example, if the user is feeling stressed, the server will change the display format to make the results easier to understand.

[1691] Input: User's facial expressions, voice, and input patterns

[1692] Output: Adjusted results display

[1693] Specific operation: The device collects emotion data and sends it to the server. The server adjusts the display of the results and causes the device to update the display.

[1694] Through these steps, users can efficiently and widely monitor water quality and predict environmental impacts, and the feedback system that responds to users' emotions makes the system easier to use and safer to use.

[1695] 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.

[1696] 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.

[1697] 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.

[1698] [Fourth embodiment]

[1699] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1700] 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.

[1701] 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).

[1702] 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.

[1703] 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.

[1704] 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).

[1705] 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.

[1706] 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.

[1707] 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.

[1708] 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.

[1709] 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.

[1710] 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.

[1711] 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."

[1712] This invention is a system that uses satellite image data to quickly and efficiently estimate water quality parameters and then simulates environmental loads based on that data. The configuration and functions for implementing this system will be described in detail.

[1713] System configuration

[1714] The system mainly consists of the following components:

[1715] 1. User Interface (Terminal)

[1716] 2. Server

[1717] 3. External Data Providers

[1718] User Interface (Terminal)

[1719] The user interface allows users to operate the system and specify a specific area. For example, it can be implemented as a web application or a mobile application. Through the interface, users can enter the coordinates of the area they want to investigate and the investigation period. The interface also provides graphs and reports for visual confirmation of analysis and simulation results.

[1720] server

[1721] The server plays a central role in processing and managing data. The main functions of the server are explained below.

[1722] 1. Data acquisition function

[1723] The server receives the request sent by the user and retrieves satellite image data for the specified area using the API of an external data provider.

[1724] 2. Image analysis function

[1725] The acquired satellite image data is preprocessed and color segmentation is performed to identify the water surface.

[1726] The RGB values ​​of each pixel on the water surface are extracted and temporarily saved.

[1727] 3. Water quality estimation function

[1728] Water quality parameters (turbidity, chlorophyll concentration, etc.) are estimated from the RGB values ​​extracted using a machine learning model.

[1729] 4. Environmental impact simulation function

[1730] Based on the water quality parameters, external data (e.g., meteorological data) necessary for simulating future environmental loads are obtained.

[1731] The simulation model is run and the results are analyzed and compiled in report format.

[1732] 5. Result transmission function

[1733] The generated report and simulation results are sent to the terminal.

[1734] External Data Providers

[1735] External data providers are services or organizations that provide satellite imagery and other necessary data. The server works with these providers to obtain the data and use it for analysis.

[1736] Example of operation

[1737] Below is a specific example of using this system to investigate the water quality of a specific lake.

[1738] 1. User Input

[1739] The user uses the terminal interface to input the coordinates of a particular lake and the date and time range they wish to survey.

[1740] 2. Data Acquisition

[1741] The terminal transmits the input data to the server, which then makes a request to an external data provider to obtain satellite image data for the specified area and period.

[1742] 3. Image Analysis

[1743] The server receives the satellite image data and performs color segmentation to identify the water surface.

[1744] Extract the RGB values ​​and feed them into a machine learning model.

[1745] 4. Water quality estimation

[1746] A machine learning model estimates water quality parameters such as turbidity and chlorophyll concentration from RGB values.

[1747] 5. Environmental Load Simulation

[1748] The server runs an environmental impact simulation, analyzes the results, and compiles them into a report.

[1749] 6. Sending and displaying results

[1750] The server sends the generated report to the terminal, which displays the results on a user interface.

[1751] Users can check the analysis and simulation results via their devices and consider the necessary measures and actions.

[1752] The above process enables faster and more widespread water quality surveys and environmental load predictions than conventional methods, resulting in a system that provides useful information for environmental conservation activities and policy formulation.

[1753] The processing flow will be explained below.

[1754] Step 1:

[1755] The user inputs the coordinates of the area to be surveyed and the survey period through the terminal interface, and the terminal transmits this input data to the server.

[1756] Step 2:

[1757] Based on the request received from the device, the server sends an API request to an external data provider to obtain satellite image data for the specified area and period.

[1758] Step 3:

[1759] The server preprocesses the satellite image data it acquires, specifically adjusting the resolution, cropping unnecessary parts, and adjusting brightness and contrast.

[1760] Step 4:

[1761] The server runs image analysis algorithms to identify water surfaces, for example, using color segmentation techniques such as k-means clustering.

[1762] Step 5:

[1763] The server extracts the RGB values ​​of each pixel from the identified water surface area and temporarily stores them in memory.

[1764] Step 6:

[1765] The server inputs the extracted RGB values ​​into a pre-trained machine learning model to estimate water quality parameters (e.g., turbidity, chlorophyll concentration).

[1766] Step 7:

[1767] The server aggregates the estimated water quality parameters and calculates statistical information such as the mean, median, and standard deviation.

[1768] Step 8:

[1769] The server compares the current water quality situation with past data from the same area and data from other areas.

[1770] Step 9:

[1771] The server obtains external data (e.g., weather data, flow rate data) necessary to simulate future environmental loads.

[1772] Step 10:

[1773] The server builds an environmental model and simulates future changes in water quality and their impacts.

[1774] Step 11:

[1775] The server analyzes the simulation results and compiles them into a report, which includes visual elements such as graphs and heat maps.

[1776] Step 12:

[1777] The server sends the generated report to the terminal.

[1778] Step 13:

[1779] The terminal displays the received report on the user interface, and the user confirms the results.

[1780] Step 14:

[1781] Based on the results displayed, the user considers the necessary measures and actions.

[1782] Example 1

[1783] 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."

[1784] Conventional water quality survey methods require on-site sampling, which is time-consuming and costly, and the scope of data collection is limited. Furthermore, simulations for predicting environmental impacts cannot be performed in real time, making it difficult to take prompt action. The present invention aims to solve these problems.

[1785] 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.

[1786] In this invention, the server includes means for providing a terminal with a user interface for specifying a specific area, means for acquiring satellite image data of the specified area from an external data provider, image processing means for preprocessing the acquired satellite image data and identifying the water surface, means for extracting RGB values ​​of the water surface, means for using a machine learning model to estimate water quality parameters from the extracted RGB values, means for simulating environmental impacts based on the estimated water quality parameters, means for compiling the simulation results in a report format and transmitting the results to the terminal, and means for the terminal to display the results on the user interface, thereby enabling fast and efficient water quality surveys and environmental impact predictions.

[1787] "Specific region" refers to the geographic area to be analyzed using satellite imagery, including coordinates and a time period specified by the user.

[1788] A "user interface" is a means by which a user operates a system, including web applications and mobile applications displayed on a terminal.

[1789] A "terminal" is a device operated by a user, and includes computing devices such as computers, smartphones, and tablets.

[1790] "Satellite image data" refers to image information acquired from cameras and sensors mounted on satellites, and includes visual data of a specific area.

[1791] "External data providers" are services or organizations that provide necessary data, such as satellite image data.

[1792] "Preprocessing" refers to the process of converting satellite image data into an analyzable format, removing noise, and adjusting resolution.

[1793] "Image processing means" refers to software tools and algorithms for analyzing images, including methods such as color segmentation.

[1794] The "water surface portion" refers to the pixel area of ​​the water area to be analyzed in the satellite image data.

[1795] "RGB values" refer to the values ​​of the red, green, and blue color components of each pixel, and represent the color information of a digital image.

[1796] A "machine learning model" refers to an algorithm that learns patterns from data and makes predictions or classifications for new data, and includes methods such as neural networks.

[1797] "Water quality parameters" refer to physical and chemical characteristics of water, such as turbidity and chlorophyll concentration.

[1798] "Environmental impact" refers to the impact on the environment predicted based on estimated water quality parameters, including future changes in water quality.

[1799] "Simulation" refers to a method of creating a virtual environment on a computer and predicting the future by imitating real-world behavior.

[1800] "Report format" refers to a documented analysis or simulation result, including digital formats such as PDF.

[1801] "Means for displaying results" refers to an interface that allows analysis results and simulation results to be visually confirmed on a terminal.

[1802] Overall system overview

[1803] This invention is a system that uses satellite image data to quickly and efficiently estimate water quality parameters and simulate environmental impacts based on that data. In this system, a server acquires the necessary satellite image data from an external data provider based on information about a region specified by a user, estimates water quality parameters using a machine learning model, and provides the results as a report.

[1804] Components and Functions

[1805] User Interface (Terminal)

[1806] The user interface allows users to operate the system and input the coordinates and period of the survey area. This user interface is implemented as a web or mobile application. For example, a user inputs the coordinates of Tokyo Bay (35.6895, 139.6917) and the survey period (April 1, 2023 to April 30, 2023).

[1807] server

[1808] The server is the center of data processing and has multiple functions.

[1809] 1. Data acquisition function

[1810] The server receives user input and uses the API of an external data provider to obtain satellite image data for the specified area, specifically, using a remote sensing service.

[1811] 2. Image analysis function

[1812] The server preprocesses the acquired satellite image data and performs color segmentation to identify the water surface, for example, by extracting RGB values ​​using OpenCV as an image processing tool.

[1813] 3. Water quality estimation function

[1814] The server inputs the extracted RGB values ​​into a machine learning model (e.g., a CNN using TensorFlow) to estimate water quality parameters such as turbidity and chlorophyll concentration.

[1815] 4. Environmental impact simulation function

[1816] Based on the estimated water quality parameters, the server obtains the external data (e.g., meteorological data) necessary to perform environmental impact simulations, and predicts future environmental impacts using a simulation tool (e.g., MATLAB).

[1817] 5. Result transmission function

[1818] The server compiles the simulation results into a report format (e.g., PDF) and sends it to the terminal.

[1819] Terminal

[1820] The terminal receives reports and simulation results sent from the server and displays them on the user interface, allowing the user to visually check the analysis and simulation results.

[1821] Specific operation example

[1822] Below is a specific example of using this system to investigate the water quality of a specific lake.

[1823] 1. User Input

[1824] The user uses the terminal interface to input the coordinates of a particular lake and the date and time range they wish to survey.

[1825] 2. Data Acquisition

[1826] The terminal transmits the input data to the server, which then makes a request to an external data provider to obtain satellite image data for the specified area and period.

[1827] 3. Image Analysis

[1828] The server receives satellite image data, performs color segmentation to identify the water surface, and extracts RGB values.

[1829] 4. Water quality estimation

[1830] A machine learning model estimates water quality parameters such as turbidity and chlorophyll concentration from RGB values.

[1831] 5. Environmental Load Simulation

[1832] The server runs the environmental impact simulation, analyzes the results, and compiles them into a report.

[1833] 6. Sending and displaying results

[1834] The server sends the generated report to the terminal, which displays the results on a user interface.

[1835] Prompt Sentence Examples

[1836] The following are examples of prompts used in this system:

[1837] Using the coordinates (35.6895, 139.6917) for the Tokyo area and the survey period (April 1, 2023 - April 30, 2023), we would like to estimate water quality parameters (turbidity, chlorophyll concentration) from satellite image data and simulate future environmental impacts.

[1838] This system supports rapid and efficient water quality surveys and predictions of environmental impacts, and can provide useful information for environmental conservation activities and policy formulation.

[1839] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1840] Step 1:

[1841] User input

[1842] The user opens the user interface on their device and enters the coordinates of the area to be surveyed and the period they wish to survey. For example, they enter "Tokyo Bay coordinates (35.6895, 139.6917)" and "survey period (April 1, 2023 - April 30, 2023)." The entered data is sent from the device to the server.

[1843] Input: Area coordinates and survey period

[1844] Output: Create input data in JSON format and send it to the server

[1845] Step 2:

[1846] Data retrieval by the server

[1847] Based on the received user input data, the server makes a request to the API of an external data provider to obtain satellite image data for the specified area and period. Specifically, it calls the API of a remote sensing service. For example, it sends a satellite image request for the specified coordinates and period and obtains satellite image data as a response.

[1848] Input: User-entered data

[1849] Output: Satellite image data for a specified area and period

[1850] Step 3:

[1851] Image analysis by server

[1852] The server preprocesses the acquired satellite image data, removing noise and adjusting the resolution. Next, it performs color segmentation using the image processing library OpenCV to identify the water surface. It then extracts RGB values ​​from each pixel in the identified water surface area and temporarily stores them.

[1853] Input: Satellite image data

[1854] Output: A list of RGB values ​​for the water surface

[1855] Step 4:

[1856] Water quality estimation by server

[1857] The server inputs the extracted RGB values ​​into a machine learning model (e.g., a CNN using TensorFlow) to estimate water quality parameters such as turbidity and chlorophyll concentration.

[1858] Input: RGB values ​​of the water surface

[1859] Output: Estimated water quality parameters (turbidity, chlorophyll concentration)

[1860] Step 5:

[1861] Environmental impact simulation using a server

[1862] The server uses the estimated water quality parameters and other necessary external data (e.g., meteorological data) to simulate future environmental impacts using simulation tools such as MATLAB. The simulation results are analyzed and compiled into a report (PDF).

[1863] Input: Estimated water quality parameters, external meteorological data

[1864] Output: Simulation result report (PDF format)

[1865] Step 6:

[1866] Sending and displaying results

[1867] The server sends the generated report to the terminal, which displays the received report on the user interface, where the user can check it and, if necessary, plan the next action.

[1868] Input: Simulation results report

[1869] Output: Report displayed in the user interface

[1870] The above are the specific processing steps of the program in this system.

[1871] (Application example 1)

[1872] 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."

[1873] Existing water quality monitoring systems have the problem of making it difficult to respond quickly when water quality abnormalities occur. While these systems are suitable for detecting abnormalities, they cannot report abnormalities in real time or compare specific environmental impact simulations with past data, which can delay early countermeasures. Furthermore, a lack of visualization and alert functions for water quality data also hinders the ability of relevant parties to respond quickly.

[1874] 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.

[1875] In this invention, the server includes means for providing a terminal with a user interface for specifying a specific area, means for acquiring satellite image data of the specified area from an external data provider, means for preprocessing the acquired satellite image data and identifying the water surface, and means for issuing an alert if the estimated water quality parameter contains an abnormal value. This allows an alert to be issued quickly to relevant parties when the water quality parameter indicates an abnormal value, enabling early countermeasures and responses.

[1876] A "user interface for specifying a specific area" is an input means for a user to select and specify an area of ​​interest, and is a software interface that runs on a terminal.

[1877] "Means for obtaining satellite image data for a specified area from an external data provider" refers to a system for obtaining satellite image data for a specified area from an external data provider, and is a function for collecting data through collaboration with APIs and data banks.

[1878] "Means for pre-processing acquired satellite image data and identifying water surface areas" refers to image processing techniques and algorithms for analyzing satellite image data and identifying water areas, thereby identifying water surface areas.

[1879] The "means for extracting RGB values ​​of the water surface portion" is a function for extracting the RGB (red, green, blue) values ​​of each pixel from the identified water surface portion, and is a means that utilizes image analysis technology.

[1880] "Means for using a machine learning model to estimate water quality parameters from extracted RGB values" refers to a function that uses a machine learning algorithm to predict water quality parameters (e.g., turbidity and chlorophyll concentration) using the extracted RGB values ​​as input.

[1881] The "means for simulating environmental loads based on estimated water quality parameters" is a function that utilizes estimated water quality parameters to execute a simulation model for predicting future environmental impacts.

[1882] The "means for issuing an alert if the estimated water quality parameter contains an abnormal value" is a function that immediately issues a warning if the predicted water quality parameter is determined to be within an abnormal range.

[1883] The "means for compiling the simulation results in a report format and transmitting it to the terminal" is a function for compiling the results of the environmental load simulation, creating a report, and transmitting the results to the user's terminal.

[1884] "Means for the terminal to display results on the user interface" refers to a function that displays the simulation results and predicted results of water quality parameters on the user interface, allowing the user to visually confirm them.

[1885] The present invention is a system for implementing water quality monitoring and environmental load simulation, which enables rapid response to pollution and abnormal water quality conditions. A specific embodiment of this system is described below.

[1886] System configuration

[1887] The system mainly consists of the following components:

[1888] 1. User Interface (Terminal)

[1889] 2. Server

[1890] 3. External Data Providers

[1891] User Interface (Terminal)

[1892] The user interface is the input means through which users operate the system. Through this interface, users input the coordinates of a specific area and the survey period. For example, it is implemented as a smartphone application, allowing users to easily specify an area using a map. This interface also provides graphs and reports for visually checking analysis and simulation results.

[1893] Prompt Sentence Examples

[1894] Enter the coordinates of the lake (e.g. 35.6581,139.7514):

[1895] Enter the period you want to investigate (e.g., 2023-01-01~2023-01-31):

[1896] Send coordinate and time period data to predict water quality parameters for a given area...

[1897] server

[1898] The server is the central point for processing and managing data. It has the following main functions:

[1899] 1. Data acquisition function: Receives a request sent by the user and acquires satellite image data for the specified area using the API of an external data provider.

[1900] 2. Image analysis function: Preprocesses acquired satellite image data to identify water surfaces, and extracts the RGB values ​​of each pixel from the identified water surface.

[1901] 3. Water quality estimation function: Estimates water quality parameters (turbidity, chlorophyll concentration, etc.) from RGB values ​​extracted using a machine learning model.

[1902] 4. Environmental load simulation function: Based on water quality parameters, the necessary data is obtained to simulate future environmental loads, and the simulation model is executed.

[1903] 5. Alert function: If the estimated water quality parameters contain abnormal values, an alert is sent to the relevant parties.

[1904] 6. Result transmission function: Sends the generated report and simulation results to the terminal.

[1905] The hardware used is a high-performance server computer, and the software used includes Flask (a Python framework), scikit-learn (machine learning models), and requests (external API calls).

[1906] External Data Providers

[1907] External data providers are services or organizations that provide satellite imagery and other necessary data. The server works with these providers to acquire the data and use it for analysis. The data is sent to the server via an API, where it undergoes any necessary preprocessing.

[1908] Example of operation

[1909] Below is a specific example of using this system to investigate the water quality of a specific lake and detect outliers.

[1910] 1. User input:

[1911] The user uses the terminal interface to input the coordinates of a particular lake and the date and time range they wish to survey.

[1912] 2. Data Acquisition:

[1913] Based on the data sent by the user, the server obtains satellite image data for the specified area through the API of an external data provider.

[1914] 3. Image Analysis:

[1915] The server preprocesses the acquired satellite image data to identify the water surface area, and then extracts the RGB values ​​of each pixel from the identified water surface area.

[1916] 4. Water quality estimation:

[1917] Using a machine learning model, water quality parameters such as turbidity and chlorophyll concentration are estimated from the extracted RGB values.

[1918] 5. Environmental impact simulation:

[1919] The server runs an environmental impact simulation, analyzes the results, and compiles them into a report.

[1920] 6. Alerting:

[1921] If the server detects abnormal values ​​in the estimated water quality parameters, it immediately sends an alert to relevant parties.

[1922] 7. Sending and viewing results:

[1923] The server sends the generated report to the terminal, which displays the results on the user interface. The user can visually check the analysis and simulation results and consider the necessary countermeasures and actions.

[1924] This will enable quicker and more widespread water quality surveys and environmental load predictions than conventional methods, and will provide a system that provides useful information for environmental conservation activities and policy formulation.

[1925] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1926] Step 1:

[1927] The user inputs the coordinates of a specific area and the survey period through the user interface of the terminal. The input data includes location information (latitude and longitude) and the survey period (date range). This determines the conditions for satellite imagery that the server should acquire.

[1928] Step 2:

[1929] The device sends the coordinates and time period data entered by the user to the server. The input data is sent in JSON format, and the server receives and parses it. The server then creates a request to the external data provider based on this data.

[1930] Step 3:

[1931] The server calls the API of an external data provider to obtain satellite image data for the specified area and period. The satellite image data is returned as a response from the API. The obtained satellite image data is temporarily stored on the server.

[1932] Step 4:

[1933] The server preprocesses the acquired satellite image data, specifically removing noise from the images and standardizing the resolution. Next, image processing algorithms are used to segment and recognize the water surface.

[1934] Step 5:

[1935] The RGB values ​​of each pixel in the water surface area are extracted from the preprocessed image. The extracted RGB values ​​serve as input data for the next processing step, water quality parameter estimation.

[1936] Step 6:

[1937] The server uses a machine learning model to estimate water quality parameters (turbidity, chlorophyll concentration, etc.) from the extracted RGB values. The machine learning model uses a pre-trained generative AI model, which inputs RGB values ​​and outputs water quality parameters.

[1938] Step 7:

[1939] The server simulates environmental loads based on the estimated water quality parameters. To do this, the server obtains meteorological and other environmental data from external data providers as needed and runs the simulation model.

[1940] Step 8:

[1941] The server compiles the simulation results in a report format, which includes the estimated water quality parameters and the simulation results. The report may also include graphs and charts for easy visual understanding.

[1942] Step 9:

[1943] The server sends the generated reports and simulation results to the terminal, where they are displayed on the user interface.

[1944] Step 10:

[1945] Users can visually check the analysis and simulation results through the terminal's user interface, and can consider the necessary countermeasures and actions based on this.

[1946] Step 11:

[1947] If the server detects any abnormalities in the estimated water quality parameters, it will immediately issue an alert, which will be sent to relevant parties via email or notification, enabling a prompt response.

[1948] 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.

[1949] This invention provides a system that uses satellite image data to quickly and efficiently estimate water quality parameters and simulate environmental impacts based on that data, as well as a function that recognizes the user's emotions and displays results and alerts accordingly. The configuration and functions for implementing this system are described in detail below.

[1950] System configuration

[1951] The system mainly consists of the following components:

[1952] 1. User Interface (Terminal)

[1953] 2. Server

[1954] 3. External Data Providers

[1955] 4. Emotion Engine

[1956] User Interface (Terminal)

[1957] The user interface allows users to operate the system and specify a specific area. For example, it can be implemented as a web application or a mobile application. Through the interface, users can enter the coordinates of the area they want to investigate and the investigation period. The interface also provides graphs and reports for visual confirmation of analysis and simulation results.

[1958] server

[1959] The server plays a central role in processing and managing data. The main functions of the server are explained below.

[1960] 1. Data acquisition function

[1961] The server receives the request sent by the user and retrieves satellite image data for the specified area using the API of an external data provider.

[1962] 2. Image analysis function

[1963] The acquired satellite image data is preprocessed and color segmentation is performed to identify the water surface.

[1964] The RGB values ​​of each pixel on the water surface are extracted and temporarily saved.

[1965] 3. Water quality estimation function

[1966] Water quality parameters (turbidity, chlorophyll concentration, etc.) are estimated from the RGB values ​​extracted using a machine learning model.

[1967] 4. Environmental impact simulation function

[1968] Based on the water quality parameters, external data (e.g., meteorological data) necessary for simulating future environmental loads are obtained.

[1969] The simulation model is run and the results are analyzed and compiled in report format.

[1970] 5. Result transmission function

[1971] The generated report and simulation results are sent to the terminal.

[1972] Emotion Engine

[1973] The emotion engine recognizes the user's emotions and adjusts the system's operation and display. The main functions of the emotion engine are explained below.

[1974] 1. Emotion recognition function

[1975] The device recognizes the user's emotions in real time based on their facial expressions, voice, input patterns, etc.

[1976] The recognized emotion data is sent to the server.

[1977] 2. Display adjustment function

[1978] The server changes the display format of the results based on the emotional data. For example, if the user is feeling stressed, the results will be displayed in a simpler format.

[1979] 3. Emotional response function

[1980] The server generates alerts and suggestions based on the user's emotions and sends them to the device. For example, if the user is feeling anxious, an alert will be displayed offering additional information or support.

[1981] Example of operation

[1982] Below is a specific example of using this system to investigate the water quality of a specific lake.

[1983] 1. User Input

[1984] The user uses the terminal interface to input the coordinates of a particular lake and the date and time range they wish to survey.

[1985] The terminal transmits the input data to the server.

[1986] 2. Data Acquisition

[1987] The server makes a request to an external data provider to obtain satellite image data for a specified region and time period.

[1988] 3. Image Analysis

[1989] The server preprocesses the acquired satellite image data and performs color segmentation to identify the water surface.

[1990] The RGB values ​​of each pixel on the water surface are extracted and fed into the machine learning model.

[1991] 4. Water quality estimation

[1992] A machine learning model estimates water quality parameters such as turbidity and chlorophyll concentration from RGB values.

[1993] 5. Environmental Load Simulation

[1994] The server runs an environmental impact simulation, analyzes the results, and compiles them into a report.

[1995] 6. Emotion Recognition and Display Adjustment

[1996] The device recognizes the user's emotions and transmits them to the server.

[1997] The server adjusts the display format of the report based on the user's feelings and sends it to the terminal.

[1998] 7. Sending and displaying results

[1999] The terminal displays the received report on the user interface, and the user confirms the results.

[2000] 8. Emotional Response

[2001] Depending on the user's emotions, the server generates additional alerts and suggestions and sends them to the device.

[2002] Through the above process, users can efficiently and widely conduct water quality surveys and predict environmental impacts, and a feedback system that takes users' feelings into consideration makes the system easier to use and more reliable.

[2003] The processing flow will be explained below.

[2004] Step 1:

[2005] The user inputs the coordinates of the area they want to survey and the survey period through the terminal interface, and the terminal sends this input data to the server.

[2006] Step 2:

[2007] Based on the request received from the device, the server sends an API request to an external data provider to obtain satellite image data for the specified area and period.

[2008] Step 3:

[2009] The server preprocesses the satellite image data it acquires, specifically adjusting the resolution, cropping unnecessary parts, and adjusting brightness and contrast.

[2010] Step 4:

[2011] The server runs image analysis algorithms to identify water surfaces, for example, using color segmentation techniques such as k-means clustering.

[2012] Step 5:

[2013] The server extracts the RGB values ​​of each pixel from the identified water surface area and temporarily stores them in memory.

[2014] Step 6:

[2015] The server inputs the extracted RGB values ​​into a pre-trained machine learning model to estimate water quality parameters (e.g., turbidity, chlorophyll concentration).

[2016] Step 7:

[2017] The server aggregates the estimated water quality parameters and calculates statistical information such as the mean, median, and standard deviation.

[2018] Step 8:

[2019] The server compares the current water quality situation with past data from the same area and data from other areas.

[2020] Step 9:

[2021] The server obtains external data (e.g., weather data, flow rate data) necessary to simulate future environmental loads.

[2022] Step 10:

[2023] The server builds an environmental model and simulates future changes in water quality and their impacts.

[2024] Step 11:

[2025] The server analyzes the simulation results and compiles them into a report, which includes visual elements such as graphs and heat maps.

[2026] Step 12:

[2027] The server sends the generated report to the terminal.

[2028] Step 13:

[2029] The terminal displays the received report on the user interface, and the user confirms the results.

[2030] Step 14:

[2031] The device activates an emotion engine to recognize the user's emotions and analyzes the user's facial expressions, voice, and input patterns.

[2032] Step 15:

[2033] The device transmits the recognized emotion data to the server.

[2034] Step 16:

[2035] The server changes the display format of the results based on the emotional data. For example, if the user is feeling stressed, the results will be displayed in a simpler format.

[2036] Step 17:

[2037] The server generates alerts and suggestions based on the user's emotions and sends them to the device. For example, if the user is feeling anxious, an alert will be displayed offering additional information or support.

[2038] Step 18:

[2039] The device displays the generated alerts and suggestions on a user interface.

[2040] Step 19:

[2041] The user considers the necessary measures and actions based on the displayed results and alerts.

[2042] Through this series of steps, users can efficiently conduct water quality surveys and predict environmental impacts, and also receive feedback that takes their own emotions into consideration.

[2043] Example 2

[2044] 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."

[2045] Conventional water quality analysis systems require large-scale data collection and processing, which results in long processing times and makes it difficult for users to obtain results quickly. Furthermore, user operations and information provision are uniform, and the systems are unable to respond to individual users' emotions and situations, resulting in low usability and user satisfaction. Therefore, there is a need for a system that can efficiently and quickly estimate water quality parameters and provide flexible result displays and alerts that respond to the user's emotions.

[2046] 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.

[2047] In this invention, the server includes means for providing a terminal with a user interface for specifying a specific area, means for acquiring satellite image data of the specified area from an external data provider, means for preprocessing the acquired satellite image data to identify the water surface, means for extracting RGB values ​​of the water surface, means for using a machine learning model to estimate water quality parameters from the extracted RGB values, means for simulating environmental impacts based on the estimated water quality parameters, means for compiling the simulation results in a report format and transmitting the results to the terminal, means for the terminal to display the results on the user interface, means for recognizing the user's emotions and adjusting the result display format according to the emotions, and means for generating alerts and suggestions based on the user's emotions. This enables users to quickly and efficiently estimate water quality parameters and receive flexible information provision according to their emotions and circumstances.

[2048] A "user interface" is the means by which a user operates a system and specifies a specific area. Specifically, it is often implemented as a web application or a mobile application.

[2049] "Terminal" refers to the device accessed by the user, and includes electronic devices such as personal computers, smartphones, and tablets.

[2050] A "server" is a computer system that processes data, manages it, and plays a central role in the entire system.

[2051] An "external data provider" is a third-party data provider that provides data from outside, and includes, for example, an organization that provides satellite image data.

[2052] "Satellite image data" refers to image data captured by a satellite, and includes geographical information and environmental information.

[2053] "Preprocessing" refers to the process of preparing acquired data before analyzing it, and includes noise removal and filtering.

[2054] "Water surface area" refers to the area of ​​satellite image data that represents water bodies.

[2055] "RGB value" is the color information contained in a pixel of image data, and is composed of red, green, and blue values.

[2056] "Water quality parameters" are indicators for evaluating water quality, and include turbidity, chlorophyll concentration, etc.

[2057] A "machine learning model" is an algorithm that analyzes data and learns patterns, which are used for prediction and classification.

[2058] "Environmental load" refers to the degree of impact on the environment, including, for example, the amount of pollutants and the impact on the ecosystem.

[2059] "Simulation" is the process of simulating real-world situations and predicting future conditions.

[2060] A "report" is a document or digital file that summarizes the results of an analysis or simulation.

[2061] "Emotion" refers to the user's psychological state, and includes, for example, joy, sadness, anger, anxiety, and the like.

[2062] An "alert" is a notification or warning that conveys information to the user.

[2063] "Suggestion" refers to advice or guidance given to the user.

[2064] "Result display format" refers to the format or style in which analysis results or simulation results are displayed on the user interface.

[2065] "Recognition" is the process by which the system understands the user's state from facial expressions, voice, etc.

[2066] "Flexible information provision" refers to providing information in an appropriate format according to the user's situation and emotions.

[2067] MODE FOR CARRYING OUT THE INVENTION

[2068] The present invention relates to a system for efficiently and quickly estimating water quality parameters and providing flexible result displays and alerts according to the user's emotions. Specific embodiments of the present invention will be described in detail below.

[2069] System configuration

[2070] The system mainly consists of the following components:

[2071] 1. User Interface (Terminal)

[2072] 2. Server

[2073] 3. External Data Providers

[2074] 4. Emotion Engine

[2075] User Interface (Terminal)

[2076] The user interface is the means by which users operate the system and specify a specific area. Specifically, it is implemented as a web application or mobile application. Users can operate their device to enter the coordinates of the area they want to survey and the survey period. Graphs and reports are also provided to visually confirm the analysis and simulation results.

[2077] server

[2078] The server is the central location for processing and managing data. It provides the following functions:

[2079] 1. Data acquisition function

[2080] The server receives the request sent by the user and retrieves satellite image data for the specified area using the API of an external data provider, for example, the NASA Earthdata API.

[2081] 2. Image analysis function

[2082] The server preprocesses the acquired satellite image data to identify the water surface area. Specifically, it performs color segmentation using Python's OpenCV library and extracts the RGB values ​​of each pixel in the water surface area.

[2083] 3. Water quality estimation function

[2084] The server uses a machine learning model (e.g., TensorFlow) to estimate water quality parameters (e.g., turbidity and chlorophyll concentration) from the extracted RGB values.

[2085] 4. Environmental impact simulation function

[2086] The server acquires external data (e.g., meteorological data) necessary to simulate future environmental impacts based on water quality parameters. AnyLogic is used as the simulation model, and the analysis results are compiled in a report format.

[2087] 5. Result transmission function

[2088] The server sends the generated report and simulation results to the terminal, which receives them and displays them on the user interface.

[2089] Emotion Engine

[2090] The emotion engine recognizes the user's emotions and adjusts the system's operation and display accordingly. The emotion engine's functions are as follows:

[2091] 1. Emotion recognition function

[2092] The device uses a camera and microphone to analyze the user's facial expressions and voice to recognize emotions, and this data is sent to a server.

[2093] 2. Display adjustment function

[2094] The server changes the way the results are displayed based on the emotion data, for example, if the user is feeling stressed, the results are displayed in a simpler format.

[2095] 3. Emotional response function

[2096] The server generates alerts and suggestions based on the user's emotions and sends them to the device. For example, if the user is feeling anxious, an alert will be displayed offering additional information or support.

[2097] Example of operation

[2098] 1. User Input

[2099] The user uses the terminal interface to input the coordinates of a specific lake (e.g., latitude 35.6581°, longitude 139.7414°) and the survey period (e.g., May 1, 2023 to May 10, 2023). The terminal then transmits the input data to the server.

[2100] 2. Data Acquisition

[2101] The server makes a request to an external data provider to obtain satellite image data for a specified region and time period.

[2102] 3. Image Analysis

[2103] The server preprocesses the acquired satellite image data and performs color segmentation to identify the water surface area. The RGB values ​​of each pixel in the water surface area are extracted and fed into the machine learning model.

[2104] 4. Water quality estimation

[2105] A machine learning model estimates water quality parameters such as turbidity and chlorophyll concentration from RGB values.

[2106] 5. Environmental Load Simulation

[2107] The server runs an environmental impact simulation, analyzes the results, and compiles them into a report.

[2108] 6. Emotion Recognition and Display Adjustment

[2109] The device recognizes the user's emotions and sends them to the server, which then adjusts the report display format based on the user's emotions and sends it to the device.

[2110] 7. Sending and displaying results

[2111] The terminal displays the received report on the user interface, and the user confirms the results.

[2112] 8. Emotional Response

[2113] Depending on the user's emotions, the server generates additional alerts and suggestions and sends them to the device.

[2114] Prompt Sentence Examples

[2115] An example of a prompt for operating this system is, "Investigate the water quality of the lake at latitude 35.6581 degrees and longitude 139.7414 degrees from May 1, 2023 to May 10, 2023, and display the simulated results of the environmental impact. Also, adjust the display format and alerts according to the user's emotions."

[2116] As described above, this system efficiently and quickly conducts water quality surveys and predicts environmental impacts, and also provides feedback that responds to the user's emotions, thereby realizing a user-friendly interface.

[2117] The flow of the identification process in the second embodiment will be described with reference to FIG.

[2118] Step 1: User Input

[2119] The user uses the device interface to input the coordinates of the area they want to survey and the survey period. For example, the user might input, "Survey a lake at latitude 35.6581 degrees and longitude 139.7414 degrees from May 1, 2023 to May 10, 2023." The device receives this input data and sends it to the server in JSON format.

[2120] Input: Area coordinates, survey period

[2121] Output: Request data in JSON format

[2122] Step 2: Data Acquisition

[2123] The server receives the request sent by the user and retrieves satellite image data for the specified area and period using the API of an external data provider. For example, the server sends a request to the NASA Earthdata API to retrieve the relevant data. The retrieved data is stored on the server.

[2124] Input: Request data in JSON format

[2125] Output: Satellite image data

[2126] Step 3: Image analysis

[2127] The server preprocesses the acquired satellite image data and performs color segmentation to identify the water surface. Specifically, it uses Python's OpenCV library to extract the RGB values ​​of each pixel in the water surface area of ​​the image. This temporarily saves the data on the water surface area from the satellite image.

[2128] Input: Satellite image data

[2129] Output: RGB value data of the water surface

[2130] Step 4: Water quality estimation

[2131] The server uses a machine learning model (e.g., a TensorFlow model) to estimate water quality parameters (e.g., turbidity, chlorophyll concentration) from the extracted RGB values. The machine learning model takes the RGB values ​​as input data and outputs the water quality parameters.

[2132] Input: RGB value data for the water surface

[2133] Output: Water quality parameters (turbidity, chlorophyll concentration)

[2134] Step 5: Environmental impact simulation

[2135] The server acquires external data such as meteorological data to simulate future environmental impacts based on water quality parameters. The server then executes a simulation model (e.g., AnyLogic) and compiles the simulation results in a report format.

[2136] Input: Water quality parameters, meteorological data

[2137] Output: Environmental impact simulation results and report

[2138] Step 6: Emotion Recognition

[2139] The device recognizes the user's emotions. Specifically, the device uses a camera and microphone to analyze the user's facial expressions and voice, and generates emotional data. This emotional data is sent to the server in real time.

[2140] Input: User's facial expression and voice data

[2141] Output: Emotion data

[2142] Step 7: Adjust the results display

[2143] The server receives the emotion data and adjusts the display format of the results based on the user's emotion. For example, if the user is feeling stressed, the display format is simplified to make it easier to understand.

[2144] Input: Emotion data, environmental impact simulation results

[2145] Output: Reconciled report

[2146] Step 8: Send and view results

[2147] The server generates and sends the adjusted report to the terminal, which receives it and displays it on the user interface, where the user can view the results.

[2148] Input: Reconciled report

[2149] Output: The results displayed in the user interface

[2150] Step 9: Emotional response

[2151] The server generates alerts and suggestions based on the user's emotions and sends them to the device. For example, if the user is feeling anxious, an alert offering additional information or support will be displayed. The device receives this and displays it in the user interface.

[2152] Input: Emotion data

[2153] Output: Alerts and suggestions

[2154] The above processing steps realize a system that allows users to efficiently and quickly conduct water quality surveys and predict environmental loads, and receive feedback that takes emotions into consideration.

[2155] (Application example 2)

[2156] 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."

[2157] Existing water quality monitoring systems are inefficient, requiring time and effort to collect and analyze data. Furthermore, in the field of eco-friendly food delivery, it is difficult to select products that take into account the water quality and environmental impact of the production area, and feedback that reflects user stress and emotions is lacking. The present invention aims to solve these issues and realize efficient and widespread water quality monitoring and eco-friendly food delivery.

[2158] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[2159] In this invention, the server includes means for providing a user interface for specifying a specific area to a terminal, means for acquiring satellite image data of the specified area from an external information provider, and means for preprocessing the acquired satellite image data to identify water body portions, thereby enabling rapid and efficient prediction of water quality indexes.

[2160] The server also includes means for extracting RGB values ​​of the water body portion, means for using a machine learning model to predict water quality indexes from the extracted RGB values, means for simulating environmental loads based on the predicted water quality indexes, means for compiling the simulation results in report format and sending it to the terminal, means for recognizing the user's emotions and displaying results or issuing alerts according to those emotions, and means for the terminal to display the results on the user interface.This enables users to monitor water quality and predict environmental loads efficiently and over a wide area, and the feedback system that takes user emotions into consideration makes the system easier to use and more secure.

[2161] "User interface" refers to the terminal screen or application that the user operates to specify a specific area or display a result.

[2162] A "terminal" is a device that a user operates directly and uses to access the system through an interface, such as a smartphone or computer.

[2163] "External Information Provider" means an external data provider or information supplier that the System connects with to obtain satellite imagery data or other necessary data.

[2164] "Satellite image data" refers to image data taken from a satellite and used to understand the environmental conditions of a particular region or area.

[2165] "Water area" refers to the area in satellite image data that includes the water surface, and is an area identified using techniques such as color segmentation.

[2166] "RGB value" is a numerical value that indicates the intensity of the red, green, and blue colors of each pixel in satellite image data.

[2167] A "machine learning model" is an algorithm or computational model that learns patterns from data and makes predictions about new data.

[2168] "Water quality index" is an index that indicates the state of the water environment, and includes, for example, turbidity and chlorophyll concentration.

[2169] "Environmental load" refers to the degree of impact of human activities and natural phenomena on a particular environment, and is predicted through simulation.

[2170] "Emotion recognition" is a technology that determines a user's emotions in real time based on their facial expressions, voice, input patterns, etc.

[2171] "Result display" is the process by which the system presents the results of analysis and simulation to the user in a visually understandable manner.

[2172] An "alert" is a message or notification that the system uses to alert the user in response to a specific condition or situation.

[2173] The present invention is a system that uses satellite image data to estimate water quality indexes, simulates environmental impacts based on that data, recognizes the user's emotions, and displays results and alerts accordingly. To implement this system, the following program is configured.

[2174] Hardware and software used

[2175] Satellite imagery acquisition: Web API (e.g. Sentinel Hub API)

[2176] Image processing: OpenCV

[2177] Machine learning models: Keras, TensorFlow

[2178] Emotion recognition: dlib (face recognition), Keras (emotion recognition)

[2179] User Interface: Web and mobile applications

[2180] Processing Overview

[2181] 1. Data acquisition function

[2182] The server uses the API of an external information provider to obtain satellite image data for a specific area and date and time specified by the user via the user interface. The data obtained from the API is stored as image data on the server.

[2183] 2. Image analysis function

[2184] The server preprocesses the acquired satellite image data and identifies water areas using color segmentation, extracts the RGB values ​​of each pixel in the identified water areas, and temporarily stores them.

[2185] 3. Water quality estimation function

[2186] The server feeds the stored RGB values ​​into a machine learning model built using TensorFlow and Keras to estimate water quality indicators (e.g., turbidity and chlorophyll concentration).

[2187] 4. Environmental impact simulation function

[2188] The server simulates the environmental impact based on the estimated water quality index and necessary external data (e.g., meteorological data). The simulation results are analyzed and compiled into a report.

[2189] 5. Result transmission and display function

[2190] The simulation results, compiled in report format, are sent from the server to the terminal, which displays the results through a user interface so that the user can visually check them.

[2191] 6. Emotion recognition and display adjustment function

[2192] The device recognizes the user's emotions in real time based on data such as facial expressions, voice, and input patterns. Dlib and Keras are used for emotion recognition. The server receives the recognized emotion data and adjusts the display format of the results. For example, if the user is feeling stressed, the results will be displayed in a simpler format.

[2193] Specific examples

[2194] We will provide a concrete example of investigating the water quality of a specific lake, predicting the environmental impact, and displaying the results according to the user's emotions.

[2195] 1. User Input: The user enters the coordinates of a particular lake and the date and time they wish to survey on their terminal.

[2196] 2. Obtaining satellite image data: The server obtains satellite image data for the specified coordinates and date and time.

[2197] 3. Image analysis: The server identifies the water areas and extracts the RGB values.

[2198] 4. Water quality estimation: Estimate water quality indicators using machine learning models.

[2199] 5. Environmental Load Simulation: The server simulates the environmental load and creates a report.

[2200] 6. Displaying the results: The server sends the report to the terminal, which displays the results.

[2201] 7. Emotion recognition and display adjustment: The device recognizes the user's emotions, and the server adjusts the display accordingly.

[2202] Prompt Sentence Examples

[2203] "Coordinates of designated area: 35.6895, 139.6917; Survey date: 2023-10-15; Eco-friendly report desired."

[2204] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[2205] Step 1:

[2206] User Input

[2207] The user uses the terminal's user interface to input a specific area and the date and time they wish to survey. The input data includes the area's coordinates (latitude and longitude) and the survey date. For example, the input format is "Coordinates of specified area: 35.6895, 139.6917; Survey date: 2023-10-15." This data is then sent from the terminal to the server.

[2208] Input: Area coordinates, survey date

[2209] Output: The request data sent to the server

[2210] Step 2:

[2211] Data Acquisition

[2212] Based on the request data received from the user, the server uses the API of an external information provider to obtain satellite image data for the specified area and date and time. The server sends an API request and receives the image data. This data is temporarily stored on the server.

[2213] Input: Request data (area coordinates, survey date)

[2214] Output: Satellite image data

[2215] Specific operation: The server creates and sends an API request. The acquired satellite image data is saved.

[2216] Step 3:

[2217] Image analysis

[2218] The server preprocesses the acquired satellite image data and uses color segmentation to identify water areas. This process involves converting the image into RGB color space and defining a color range to identify water areas. The image is then masked to extract the water areas.

[2219] Input: Satellite image data

[2220] Output: RGB values ​​of water area

[2221] Specific operation: The server analyzes the satellite image data and applies color segmentation to identify water areas.

[2222] Step 4:

[2223] Water quality estimation

[2224] The server inputs the extracted RGB values ​​into a machine learning model to estimate water quality indices (e.g., turbidity and chlorophyll concentration). The model is pre-trained and outputs water quality indices based on the RGB values.

[2225] Input: RGB values ​​of water area

[2226] Output: Estimated water quality index

[2227] Specific operation: The server inputs the RGB values ​​into a machine learning model, which then predicts the water quality index.

[2228] Step 5:

[2229] Environmental impact simulation

[2230] The server simulates the environmental load based on the predicted water quality index and necessary external data (e.g., meteorological data). The simulation uses the water quality index and other environmental parameters to predict future environmental loads.

[2231] Input: Estimated water quality index, external data

[2232] Output: Environmental impact simulation results

[2233] Specific operation: The server obtains external data and executes the simulation model.

[2234] Step 6:

[2235] Report generation and transmission

[2236] The server analyzes the simulation results and compiles them into a report, which includes water quality indicators, predicted environmental impacts, and graphs and charts. The report is then sent to the terminal.

[2237] Input: Environmental load simulation results

[2238] Output: Report

[2239] Specific operation: The server compiles the analysis results into a report format and sends it to the terminal.

[2240] Step 7:

[2241] Results display

[2242] The terminal displays the report received from the server on the user interface, allowing the user to visually check the water quality status and environmental impact forecast for the area they entered.

[2243] Input: report

[2244] Output: The results displayed in the user interface

[2245] Specific operation: The terminal receives the report and displays it on the interface.

[2246] Step 8:

[2247] Emotion recognition and response

[2248] The device recognizes the user's emotions in real time, such as facial expressions and voice. This data is sent to a server, which then adjusts the display format of the results based on the recognized emotion. For example, if the user is feeling stressed, the server will change the display format to make the results easier to understand.

[2249] Input: User's facial expressions, voice, and input patterns

[2250] Output: Adjusted results display

[2251] Specific operation: The device collects emotion data and sends it to the server. The server adjusts the display of the results and causes the device to update the display.

[2252] Through these steps, users can efficiently and widely monitor water quality and predict environmental impacts, and the feedback system that responds to users' emotions makes the system easier to use and safer to use.

[2253] 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.

[2254] 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.

[2255] 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.

[2256] 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.

[2257] 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 em...

Claims

1. means for providing a user interface for designating a specific region to a terminal; means for obtaining satellite image data for a specified area from an external data provider; A means for preprocessing the acquired satellite image data and identifying the water surface portion; A means for extracting the RGB values ​​of the water surface; a means for using a machine learning model to estimate water quality parameters from the extracted RGB values; A means for simulating environmental loads based on the estimated water quality parameters; A means for compiling the simulation results in a report format and transmitting the report to the terminal; means for the terminal to display the results on a user interface; A system including:

2. 10. The system of claim 1, further comprising means for comparing water quality parameters with historical data to assess current water quality conditions.

3. 10. The system of claim 1, further comprising means for acquiring external data required for the simulation.

Images