system

Abstract

Provide a system. 【Solution means】 Solar energy data acquisition means, Information cleaning means for preprocessing the obtained information, Inference means having a machine learning algorithm for analyzing and predicting data, Visualization generation means for visualizing the analysis result in three dimensions, Natural language processing device for collecting and summarizing documents, Hypothesis construction means for generating a new hypothesis based on the generated summary, Quantum computing device for realizing high-precision simulation calculations, Notification generation means for distributing solar wind influence information as a warning on a digital terminal, A system including the above.

Description

Technical Field

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] The behavior of the solar wind is very complex and may have a great impact on communications and power grids on Earth, so accurate and rapid data analysis and prediction are required. However, there are problems that manual data processing and analysis take time and are prone to human errors. Also, in existing systems, it is difficult to perform high-precision prediction and visualization in real time, and it is difficult for researchers to efficiently generate and evaluate new hypotheses.

Means for Solving the Problems

[0005] This invention provides a system that automatically acquires a wide range of solar data and performs real-time analysis and prediction using machine learning models. The obtained analysis results are visualized in three dimensions, making them intuitively understandable to researchers. Furthermore, by utilizing natural language processing technology to summarize the latest academic papers and generate new hypotheses, the system enhances the efficiency and creativity of research. In addition, by using quantum computing means, advanced simulations can be executed at high speed, improving the accuracy of solutions. In this way, the aim is to solve complex problems related to solar wind and support researchers.

[0006] "Solar data acquisition means" refers to a device or program that automatically acquires observational data related to the sun.

[0007] A "data cleaning means" is a device or method that has the function of removing and correcting missing values ​​and outliers from acquired data and preparing it in a format suitable for analysis.

[0008] A "prediction tool" is a device or program that uses machine learning models based on past data to predict future trends in solar wind.

[0009] A "visualization generation means" is a device or method for visually representing analysis results in three dimensions so that users can understand them intuitively.

[0010] "Natural language processing means" refers to a device or method that has the technology to analyze documents such as academic papers written in natural language and perform summarization and information extraction.

[0011] A "hypothesis generation tool" is a device or program that has the function of automatically generating new research hypotheses based on the data and knowledge obtained.

[0012] A "quantum computing device" is a device or method that uses quantum computing technology to perform large-scale calculations at high speed and achieve highly accurate simulations. [Brief explanation of the drawing]

[0013] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Figure 11] This is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] This is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] This is a sequence diagram showing the processing flow of the data processing system in Example 2, which incorporates an emotion engine. [Figure 14] This is a sequence diagram showing the processing flow of the data processing system in Application Example 2, which combines an emotion engine. [Modes for carrying out the invention]

[0014] Hereinafter, an example of an embodiment of a system according to the technology of the present disclosure will be described with reference to the accompanying drawings.

[0015] First, the terms used in the following description will be explained.

[0016] In the following embodiments, a processor with a reference numeral (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of a plurality of arithmetic units. Also, the processor may be a single type of arithmetic unit or a combination of a plurality of types of arithmetic units. Examples of arithmetic units include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), and the like.

[0017] In the following embodiments, a RAM (Random Access Memory) with a reference numeral is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0018] In the following embodiments, a storage with a reference numeral is one or more non-volatile storage devices that store various programs and various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes, and the like.

[0019] In the following embodiments, the signed communication interface (I / F) is an interface that includes a communication processor and an antenna, etc. The communication interface manages communication between multiple computers. Examples of communication standards applicable to the communication interface include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0020] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." That is, "A and / or B" means that it may be A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or."

[0021] [First Embodiment]

[0022] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0023] As shown in Figure 1, the data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0024] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0025] The smart device 14 comprises a computer 36, a reception device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The reception device 38, output device 40, and camera 42 are also connected to the bus 52.

[0026] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0027] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form perceptible to the user 20 (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0028] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

[0029] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0030] As shown in Figure 2, in the data processing device 12, a specific processing is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" related to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0031] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0032] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with a specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0033] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0034] This invention is a system for efficiently analyzing and predicting solar wind data, and is implemented in the following form.

[0035] Data acquisition and preprocessing:

[0036] The server has an interface for acquiring solar observation data in real time. Data is sent to the server via APIs, etc. The acquired data first undergoes a cleaning process and is normalized into a format suitable for analysis. This process includes imputing missing values ​​and detecting and removing outliers.

[0037] Data analysis and prediction:

[0038] The server uses machine learning models to analyze and predict the obtained data. Specifically, it applies models that utilize time-series data (e.g., LSTM networks) to calculate future solar wind trends. This predicted data is recorded in an updated database and used for further analysis and display.

[0039] Generating three-dimensional visualizations:

[0040] The server generates a three-dimensional visualization based on the analysis results. An open-source 3D graphics library is used for the visualization. The generated 3D model visually shows the solar wind's path and impact area. Users can view and interactively manipulate this visualization using their terminals.

[0041] Natural language processing and hypothesis generation:

[0042] The server automatically collects academic papers from around the world and generates summaries using natural language processing. These summaries concisely present the key information extracted from the papers. Furthermore, it has the ability to automatically generate new research hypotheses based on the summarized information. Reinforcement learning is used to evaluate the validity of the generated hypotheses and present promising research topics.

[0043] Advanced simulation:

[0044] The server utilizes quantum computing technology to perform advanced simulations of the solar wind. This allows for high-speed, parallel execution of complex calculations, contributing to improved accuracy in analysis results. These simulation results will be used to further advance the research.

[0045] In this way, the system enables collaboration between servers, terminals, and users, and functions to support researchers in solving problems by efficiently analyzing and predicting solar wind data.

[0046] The following describes the processing flow.

[0047] Step 1:

[0048] The server retrieves observational data from the API using solar data acquisition methods. This includes selecting data sources and configuring data transfer protocols. It supports real-time data streaming.

[0049] Step 2:

[0050] The server cleans the acquired data. Linear interpolation is used to fill in missing values, and statistical methods are used to remove outliers. This data cleansing ensures data consistency and reliability.

[0051] Step 3:

[0052] The server feeds the normalized data into a machine learning model for analysis. Here, a time series analysis using an LSTM network is performed to predict future solar wind trends. The results are recorded in a prediction database.

[0053] Step 4:

[0054] The server generates a three-dimensional visualization based on the analysis results. Utilizing a 3D rendering engine, it visualizes the solar wind's path and influence area, taking into account its positional relationship with the Moon and Earth.

[0055] Step 5:

[0056] The device uses the generated 3D model to provide visualization to the user. The user can use mouse or touch controls to view the behavior of the solar wind from different perspectives.

[0057] Step 6:

[0058] The server automatically collects academic papers on solar wind and creates summaries using natural language processing technology. It extracts important information and stores the summaries in a database.

[0059] Step 7:

[0060] The server generates hypotheses using generative AI based on the summarized information. When proposing new research themes, reinforcement learning is used to test these hypotheses.

[0061] Step 8:

[0062] The server runs simulations using a quantum computing platform. By performing parallel computing under complex conditions, more accurate results are obtained.

[0063] Step 9:

[0064] The server analyzes the obtained simulation results and uses them to further verify 3D models and hypotheses. These results can be used for future research and applications.

[0065] (Example 1)

[0066] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0067] Fluctuations in solar activity affect the Earth's environment and man-made objects, thus requiring highly accurate predictions. However, current technologies have fragmented processes from data acquisition and analysis to visualization, hypothesis generation, and evaluation, lacking efficient and comprehensive solutions. Furthermore, there are issues regarding how to provide the generated information to users and how to utilize it effectively.

[0068] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0069] In this invention, the server includes data acquisition means for acquiring solar physical data, information preprocessing means for preprocessing the acquired data, and prediction means having a computational model for analyzing and predicting the preprocessed data. This enables comprehensive acquisition, analysis, prediction, visualization, hypothesis generation, and evaluation of solar activity data, thereby realizing effective information provision to users.

[0070] "Solar physical data" refers to physical information obtained from the sun, including data on solar activity, radiation, wind, and magnetic fields.

[0071] "Data acquisition means" refers to methods and processes for collecting solar physical data using observation equipment and networks.

[0072] "Information preprocessing means" refers to methods that perform operations such as data cleaning, supplementation, and standardization in order to convert acquired data into an analyzable format.

[0073] A "computational model" is a mathematical model used to analyze data and make predictions, and often incorporates statistical methods and machine learning.

[0074] "Three-dimensional visualization generation means" refers to a technology and method for representing analyzed data in three dimensions and displaying it in an easily understandable visual format.

[0075] "Natural language processing" refers to a technology that mechanically analyzes and processes text data, and is used for information extraction and summary generation.

[0076] "Knowledge generation methods" are techniques for formulating new hypotheses based on collected information, and they utilize the results of data analysis.

[0077] "Computational techniques" refers to a series of technologies that enable advanced computations, and in particular, to advanced technologies such as quantum computing.

[0078] To implement this invention, a server plays a central role. The server acquires solar physical data via observation equipment connected to the internet or through external APIs. For example, a common option is to use a cloud-based data acquisition service.

[0079] The server then performs data cleaning and standardization using advanced data processing software as a preprocessing measure. This typically involves using libraries from Python or R. This allows for efficient completion of missing data and removal of outliers.

[0080] Subsequently, the server analyzes the data preprocessed by the computational model and makes predictions. For example, it uses machine learning frameworks such as TENSORFLOW® or PyTorch to build time series analysis models such as LSTM to predict future solar wind trends.

[0081] The server further utilizes three-dimensional visualization generation methods to visualize the analysis results in three dimensions. In this process, it uses open-source graphics libraries such as Three.js and Matplotlib to generate visualizations that can be easily manipulated by the user in a web browser.

[0082] The device provides these results to the user, allowing the user to visually understand the data through an interactive interface. The device uses a front-end application developed with HTML5, CSS3, JavaScript (registered trademark), etc., to effectively display the visualization results visually.

[0083] In addition, the server utilizes natural language processing capabilities to collect information from relevant academic paper databases and summarize important data. To automatically generate new hypotheses from this summary information, the use of natural language processing libraries such as NLTK and the BERT model can be considered. As a concrete example of a prompt, the following message is entered into the server: "Summarize the latest astronomy papers and generate new research hypotheses."

[0084] Finally, as a computational technique, quantum computers are used to perform simulations with higher accuracy. For example, cloud-based quantum computing services can be used to perform computationally intensive simulations in a short amount of time.

[0085] This system configuration allows users to gain comprehensive insights based on actual solar wind data. By effectively coordinating the entire process from data acquisition to prediction, visualization, and result interpretation, the system improves the efficiency of researchers and engineers.

[0086] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0087] Step 1:

[0088] The server acquires solar physical data via an external API. The input requires the API endpoint and authentication credentials. The server uses this information to send an HTTP request and receives observation data in JSON format as output. Specifically, it sends a GET request with authentication using the API key.

[0089] Step 2:

[0090] The server preprocesses the acquired data. The input is the observation data in JSON format obtained in step 1. The server analyzes the data to impute missing values ​​and remove outliers, and outputs clean data in standard format. Specifically, it uses Python or R and the Pandas library to impute missing values ​​with the median and detect and remove outliers.

[0091] Step 3:

[0092] The server makes predictions using pre-processed data. The input data is the data cleaned in step 2. This is input into a machine learning model to output predictions for future solar physics data. Specifically, an LSTM model is used to train and predict time series data.

[0093] Step 4:

[0094] The server records the prediction results in a database. The input is the prediction results obtained in step 3. The server saves this to the appropriate table in the database, making it available for future analysis and visualization. Specifically, it uses MySQL® or PostgreSQL and stores the prediction results using INSERT statements.

[0095] Step 5:

[0096] The server visualizes prediction data in three dimensions. The input is the prediction results stored in a database. Based on this data, the server generates three-dimensional graphics and provides a user-interactive visualization as output. Specifically, it uses Three.js and renders the results in the browser using WebGL.

[0097] Step 6:

[0098] The terminal displays visualized data to the user. The input is three-dimensional visualization data provided by the server. The terminal displays this data concretely in a browser and enables interaction with the user. Specific operations include the implementation of dynamic content using HTML5 and JavaScript.

[0099] Step 7:

[0100] The server uses natural language processing to extract information from relevant literature and generate summaries. The input is data from an academic paper database. The server extracts key information and outputs a concise summary. Specifically, it applies a text summarization algorithm based on BERT.

[0101] Step 8:

[0102] The server generates new hypotheses and evaluates their validity. The input is the summary information generated in step 7. The server evaluates the hypotheses using a reinforcement learning algorithm and presents promising research topics as output. The specific operation involves training and evaluating models using a reinforcement learning library.

[0103] (Application Example 1)

[0104] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0105] In recent years, the impact of solar wind, associated with solar activity, on Earth's energy infrastructure has attracted considerable attention. However, existing systems have struggled to accurately predict solar wind patterns and notify citizens of their impacts in real time. In particular, there is a need for immediate response measures to enable efficient urban infrastructure management and energy system operation.

[0106] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0107] In this invention, the server includes means for acquiring solar energy data, means for cleaning information, means for making predictions with a machine learning algorithm, means for generating visualizations, a natural language processing device, means for constructing hypotheses, a quantum computing device, and means for generating notifications. This makes it possible to predict the impact of solar wind on urban infrastructure in real time and immediately notify citizens.

[0108] A "solar energy data acquisition device" is a device that has the function of collecting data related to solar activity in real time.

[0109] An "information cleaning device" is a device that performs preprocessing, such as imputing missing values ​​and removing outliers, in order to prepare acquired data into an analyzable format.

[0110] A "predictive tool with a machine learning algorithm" is a device that uses machine learning technology to predict future solar wind trends based on collected data.

[0111] A "visualization generation means" is a device that visualizes analysis results in three dimensions and displays them in a way that users can intuitively understand.

[0112] A "natural language processing device" is a device that automatically collects literature and information, and provides concise information by summarizing it.

[0113] A "hypothesis-building tool" is a device that automatically generates new research hypotheses based on summarized information.

[0114] A "quantum computing device" is a device that can perform complex calculations at high speed in order to achieve highly accurate simulations.

[0115] A "notification generation device" is a device that notifies citizens in real time about the impacts of solar wind and proposes necessary countermeasures.

[0116] The system for realizing this invention functions as follows:

[0117] The server collects solar energy data in real time using an API. This data is then processed using information cleaning tools to impute missing values ​​and remove outliers, preparing it for analysis. Next, the server uses a machine learning algorithm (TensorFlow) to predict solar wind trends. This predicted data is then visualized in three dimensions using a visualization tool (Three.js), allowing users to understand it intuitively.

[0118] Furthermore, the server uses a natural language processing device (spaCy) to automatically collect and summarize literature from around the world. Based on the summarized information, a hypothesis-building tool generates new research hypotheses. These hypotheses are then tested using high-precision simulated computations performed by a quantum computing device.

[0119] Through online digital terminals, the server notifies citizens in real time about the impact of solar winds and proposes necessary countermeasures. This will enable more efficient management of energy systems within smart cities.

[0120] One concrete example is a system that notifies citizens 30 minutes in advance via a smartphone application about power outages expected due to solar winds. By inputting prompts such as, "Please describe the effects of solar winds and propose specific countermeasures for the smart city infrastructure in the designated area," into an AI model, it is possible to automatically suggest the most suitable response.

[0121] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0122] Step 1:

[0123] The server acquires solar energy data in real time via an API. It receives observational data on solar activity as input and generates raw data as output. This data is then retrieved for subsequent processing.

[0124] Step 2:

[0125] The server preprocesses the acquired data using information cleaning methods. It uses raw data as input, imputes missing values, removes outliers, and outputs rational data. At this stage, the data is prepared in a format suitable for analysis.

[0126] Step 3:

[0127] The server uses machine learning algorithms to analyze data and predict solar wind trends. It takes pre-processed data as input, performs time-series analysis using an LSTM model, and outputs future solar wind prediction data. This result is used in the next step.

[0128] Step 4:

[0129] The server visualizes the analysis results in three dimensions using visualization generation tools. It receives prediction data as input, generates a three-dimensional model using Three.js, and outputs it. This allows the user to interactively check the extent of the solar wind's influence.

[0130] Step 5:

[0131] The server uses a natural language processing unit (NLP) to collect relevant literature and create summaries. Using the collected literature data as input, it extracts key points through natural language processing and outputs a summary. This summary is useful for providing information concisely.

[0132] Step 6:

[0133] The server generates new research hypotheses based on summaries using hypothesis-building tools. It receives a summary text as input, constructs a new hypothesis using a generative AI model, and outputs that hypothesis. This hypothesis serves as the starting point for the research.

[0134] Step 7:

[0135] The server has a quantum computing device test the hypothesis. Using the generated hypothesis as input, it performs high-precision simulations and outputs the results verifying the validity of the hypothesis. These results are used for further research.

[0136] Step 8:

[0137] The terminal notifies the user of information regarding the impact of solar winds through a notification generation mechanism. It receives solar wind forecast data and verification results as input, generates notifications that present specific countermeasures, and outputs them to the user, thereby supporting real-time infrastructure management.

[0138] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0139] This invention is a system that combines a system that supports the acquisition, analysis, visualization, and hypothesis generation of solar data with an emotion engine that recognizes the user's emotional state, and is implemented in the following form.

[0140] Data acquisition and processing:

[0141] The server receives solar data in real time from observatories around the world. This data includes information such as solar wind speed, density, and temperature. The server cleans and formats the received data for analysis and prediction. This ensures data consistency and accuracy of analysis.

[0142] Data analysis and prediction:

[0143] The server uses machine learning models to analyze received data and predict future trends in solar wind. These models include time series analysis techniques such as LSTM, and the prediction results are used in subsequent visualization and hypothesis generation processes.

[0144] Generating three-dimensional visualizations:

[0145] The server generates a three-dimensional visualization model based on the predicted data. A 3D rendering engine is used to intuitively show the movement and extent of the solar wind's influence. The terminal provides this 3D model to the user, offering an interface that allows the user to freely change their viewpoint and observe the model.

[0146] Natural language processing and hypothesis generation:

[0147] The server collects academic papers from around the world and uses natural language processing techniques to create summaries. It then generates new research hypotheses from this summary information. Reinforcement learning algorithms are used to evaluate the validity of the generated hypotheses and provide new directions for research.

[0148] Advanced simulation and emotion recognition:

[0149] The server performs complex simulations using quantum computing technology. In addition, the system incorporates an emotion engine that recognizes the user's emotions. The terminal analyzes the user's facial expressions and tone of voice through the camera and voice interface to determine their emotional state.

[0150] The device adjusts how visualizations are displayed according to the user's emotions. For example, it uses calmer, less visually burdensome animations for stressed users, while providing detailed, interactive data displays for interested users. In this way, the system can provide flexible, user-friendly feedback and a more enriching experience.

[0151] This system aims to deepen our understanding of solar wind and stimulate researchers' curiosity and learning experiences.

[0152] The following describes the processing flow.

[0153] Step 1:

[0154] The server accesses a designated API to acquire observational data and receives solar data in real time. The data includes basic physical quantities such as solar wind speed, density, and temperature.

[0155] Step 2:

[0156] The server performs a cleaning process on the received raw data. This involves filtering outliers using statistical methods and imputing missing values. Normalization is also performed to maintain data consistency and quality.

[0157] Step 3:

[0158] The server uses the organized data to run machine learning algorithms, including LSTM models, to predict the short-term and long-term behavior of the solar wind. The prediction results are stored in a database and used to improve prediction accuracy.

[0159] Step 4:

[0160] The server generates a 3D model based on the analyzed prediction data. A 3D graphics library is used for visualization, intuitively displaying the extent and path of the solar wind's impact on Earth.

[0161] Step 5:

[0162] The device provides the user with this 3D model as an interactive visualization. The user can observe the solar wind simulation results from various angles while manipulating the viewpoint.

[0163] Step 6:

[0164] The server automatically collects the latest academic papers on solar wind from online databases. It then uses natural language processing techniques to extract key information from the collected papers and create summaries.

[0165] Step 7:

[0166] The server automatically generates new hypotheses using generative AI based on the summarized information. The validity of these generated hypotheses is then evaluated through a verification process using reinforcement learning.

[0167] Step 8:

[0168] The server utilizes quantum computing capabilities to perform advanced simulations. It aims to further improve prediction accuracy by conducting simulations under complex conditions at high speed.

[0169] Step 9:

[0170] The device analyzes the user's emotional state from their facial expressions and voice using an emotion engine. Based on this analysis, it dynamically adjusts the style of visualization and the level of detail of the information displayed.

[0171] Step 10:

[0172] Users experience emotion-recognition-based feedback through a flexible interface presented by the device. This allows users to receive solar wind information optimized for their own psychological state.

[0173] (Example 2)

[0174] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0175] Conventional solar data analysis systems have not adequately achieved real-time data acquisition, high-precision prediction, or automated hypothesis generation, nor have they provided interactive visualizations that respond to user emotions. Therefore, improving the efficiency of research and the user experience remains a challenge.

[0176] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0177] In this invention, the server includes means for acquiring solar data, means for cleaning data, and means for making predictions with a machine learning model. This enables real-time data acquisition, highly accurate predictions, and interactive three-dimensional visualization.

[0178] "Solar data acquisition methods" refer to technologies for collecting information about the sun in real time from observatories around the world.

[0179] "Data cleaning techniques" refer to processing technologies used to remove noise and inconsistencies from collected data and convert it into a format suitable for analysis and prediction.

[0180] "Predictive methods using machine learning models" refer to technologies that use machine learning algorithms to predict future trends based on past data.

[0181] "Visualization generation means" refers to technology for displaying analysis results in a three-dimensional shape so that they can be intuitively understood.

[0182] "Natural language processing methods" refer to technologies that process text data and enable summarization and information extraction.

[0183] "Hypothesis generation method" refers to technology that automatically generates new research hypotheses based on obtained information and summaries.

[0184] "High-performance computing means" refers to technologies that provide advanced computing power to perform complex simulations.

[0185] "Emotion recognition means" refers to technology that analyzes a user's facial expressions and voice to recognize their emotional state.

[0186] "Display means" refers to technologies that provide users with visualized data and enable them to interact with it.

[0187] "Evaluation methods" refer to techniques that utilize reinforcement learning algorithms to evaluate the effectiveness and novelty of generated hypotheses.

[0188] In this invention, the server acquires solar data from an observatory and removes noise from the received data using data cleaning means. Specifically, it utilizes data processing tools such as the Pandas library to prepare formatted data.

[0189] Next, the server runs machine learning models using TensorFlow and Keras, and performs time series analysis using LSTM (Long Short-Term Memory Network) to predict future trends in solar wind.

[0190] The predicted data is visualized in three dimensions using a 3D rendering engine such as Blender. This 3D model is provided to the user via their device, allowing them to intuitively observe the movement and extent of the solar wind's influence while freely changing their viewpoint using a browser-based interface.

[0191] Furthermore, the server collects academic papers via the Google® Scholar API and generates summaries of those papers using natural language processing technology. In addition, it uses a generative AI model (e.g., GPT-4®) to formulate new research hypotheses from the summaries and evaluates those hypotheses using a reinforcement learning algorithm.

[0192] The system also performs complex simulations using high-performance computing capabilities. In addition, the device recognizes the user's emotions through its camera and microphone, and adjusts the visualization method based on the results analyzed by the emotion recognition system. If the system determines that the user is experiencing stress, it uses gentle animations to reduce visual strain.

[0193] As an example, the effects of the Earth's magnetic field over the next week can be simulated and displayed in a 3D model. If the user shows interest, a detailed and interactive model can be provided, allowing the user to perform further analysis using this data.

[0194] An example of a prompt message could be: "Analyze solar wind data and generate a model to visualize the effects of the Earth's magnetic field next week." The system will then perform the appropriate data processing and visualization in response to such prompts.

[0195] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0196] Step 1:

[0197] The server acquires solar data in real time from observatories in various locations. It receives data such as solar wind speed, density, and temperature as input, and then performs noise reduction and missing value imputation using data cleaning methods. The output is a consistent and clean dataset.

[0198] Step 2:

[0199] The server runs an LSTM machine learning model using the clean data obtained in Step 1. Specifically, it performs time series analysis using TensorFlow or Keras to predict future solar wind trends. The input is a formatted dataset, and the output is predicted solar wind trend data.

[0200] Step 3:

[0201] The server processes predicted trend data using a 3D rendering engine such as Blender to generate a three-dimensional visualization model. The input is predicted data, and the output is a three-dimensional model that allows the user to observe the visualization data from various perspectives. The terminal provides this model to the user and displays it through an intuitive interface.

[0202] Step 4:

[0203] The server uses natural language processing to retrieve academic papers from around the world and summarize the information. Specifically, it uses an API to input paper data and generates summaries using NLTK and spaCy. The output is summarized paper information, which is then used by a generative AI model to generate new research hypotheses.

[0204] Step 5:

[0205] The server applies a reinforcement learning algorithm to evaluate the validity of hypotheses formulated by the generative AI model. The input is hypothesis information, and the output is a list of evaluated hypotheses. Based on this, new directions for research can be suggested.

[0206] Step 6:

[0207] The device collects the user's facial expressions and voice through its camera and microphone, and analyzes their emotional state using an emotion recognition API. The input is the user's facial expressions and voice data, and the output is the result of the emotional state analysis. Based on these results, the device adjusts the 3D visualization display mode to provide the user with a relaxing environment.

[0208] (Application Example 2)

[0209] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as a "server" and the smart device 14 as a "terminal".

[0210] The problem this invention aims to solve is to provide information tailored to the user's emotions through the analysis and visualization of solar wind data, thereby offering an intuitive and user-friendly learning experience. In particular, it aims to facilitate understanding of cosmic phenomena and streamline the acquisition of scientific knowledge by displaying appropriate information according to the user's interests and stress levels.

[0211] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0212] In this invention, the server includes means for acquiring solar data, means for cleaning data, means for prediction using a machine learning model, means for visualizing and generating analysis results in three dimensions, means for natural language processing for collecting and summarizing papers, means for generating new hypotheses, means for high-precision simulation using quantum computing, means for recognizing the user's emotional state, and means for interactively providing information. This enables real-time analysis of information related to solar wind and flexible information provision according to the user's emotional state.

[0213] The "solar data acquisition method" is a function that collects data on solar wind in real time from observatories in various locations.

[0214] "Data cleaning methods" are functions that process data to remove noise and outliers in order to prepare the acquired data for analysis and prediction.

[0215] "Prediction methods using machine learning models" refers to a function that uses machine learning technology to analyze future trends in solar wind and provide prediction results.

[0216] A "visualization generation method" is a function that visually represents the analyzed data as a three-dimensional model, making it intuitively understandable to the user.

[0217] "Natural language processing methods" refer to technologies used to analyze collected academic papers and text data and create summaries.

[0218] A "hypothesis generation tool" is a function that carries out the process of creating new research hypotheses based on the generated summaries.

[0219] "High-precision simulation methods using quantum computing" refers to a function that accurately simulates complex astronomical phenomena using quantum computing technology.

[0220] "Emotion recognition means" refers to a function that analyzes the user's facial expressions and tone of voice to determine their current emotional state and adjust the way information is displayed accordingly.

[0221] An "interface means" is a means for interactive communication between a user and a system, and is a function that provides information through visual and auditory means.

[0222] This invention constructs a system that performs real-time data analysis on solar wind and provides scientific information tailored to the user's emotional state. The server first receives solar data from an observatory, removes noise and outliers using data cleaning means, and then performs predictions using a machine learning model. This prediction employs time series analysis methods such as LSTM using TensorFlow.

[0223] Next, based on the analyzed data, the visualization generation system uses the Unity3D engine to generate a three-dimensional model. Through this model, it is possible to intuitively display the movement and affected area of ​​the solar wind.

[0224] Furthermore, the server collects papers and uses natural language processing to create summaries. From the generated summaries, a hypothesis generation tool uses a reinforcement learning algorithm to create and propose new research hypotheses.

[0225] This system incorporates emotion recognition technology that analyzes facial expressions and voice tone through the user's camera and microphone. This allows the interface to adjust its display content according to the user's emotional state, providing content tailored to their interests and stress levels. For example, it can provide calming animations to stressed users and interactively display detailed data to curious users.

[0226] As a concrete example, a scenario could be envisioned where a user observes changes in the movement of the solar wind through this system during a solar eclipse, deepening their scientific understanding. An example of a prompt in this scenario would be: "Please tell me how I can learn about the movement of the solar wind in an interesting and real-time way. It's sunny right now, so I'm feeling motivated."

[0227] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0228] Step 1:

[0229] The server acquires solar data in real time from observatories. This is a process of receiving solar wind data transmitted from various locations, using information such as solar wind speed, density, and temperature as input. In this step, data is received and recorded in a database for subsequent processing.

[0230] Step 2:

[0231] The server performs data cleaning on the received data. The input is the raw data obtained in step 1, and noise reduction and correction of outliers are performed. The output is the cleaned and formatted data, which enables highly accurate analysis. The Python Pandas library is used for data cleaning.

[0232] Step 3:

[0233] The server performs data analysis and prediction using a machine learning model. The pre-processed data obtained in step 2 is used as input. An LSTM model is used to predict future solar wind trends and output the prediction results. TensorFlow is used for the analysis, and the results are stored in a database.

[0234] Step 4:

[0235] The server generates a three-dimensional visualization model based on the analysis results. The input is the prediction results from step 3, and the Unity3D engine is used to render the movement and affected area of ​​the solar wind in three dimensions. The output is a 3D model that the user can freely observe by changing the viewpoint.

[0236] Step 5:

[0237] The server collects academic papers and generates summaries using natural language processing (NLP). The input consists of relevant papers found on the internet. The NLP algorithm generates the summaries, which are then output as data for proposing new hypotheses.

[0238] Step 6:

[0239] The server generates hypotheses based on the summarized data. Reinforcement learning algorithms are used to train predictive models and generate new hypotheses. The output is a list of hypotheses, which can be useful for further scientific research.

[0240] Step 7:

[0241] The device receives a photo of the user's face and voice input, and uses an emotion recognition engine to determine their emotional state. Input is data collected from the camera and microphone. Output is the user's emotional state (e.g., interesting, stressed). The algorithm uses OpenCV and the Google Cloud Speech API.

[0242] Step 8:

[0243] The device adjusts its display based on the emotion data from step 7. The inputs are the user's emotional state and the 3D model from step 4. The output is a customized information display tailored to the specific emotion. For example, if the emotion is deemed interesting, an interactive data display will occur.

[0244] The input, data processing, and output at each processing step are clearly defined, and the entire system provides an intuitive science learning experience that engages the user.

[0245] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0246] Data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0247] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart device 14.

[0248] [Second Embodiment]

[0249] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0250] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0251] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0252] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0253] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0254] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0255] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0256] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0257] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0258] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0259] In the smart glasses 214, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0260] Next, the identification processing performed by the identification processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0261] This invention is a system for efficiently analyzing and predicting solar wind data, and is implemented in the following form.

[0262] Data acquisition and preprocessing:

[0263] The server has an interface for acquiring solar observation data in real time. Data is sent to the server via APIs, etc. The acquired data first undergoes a cleaning process and is normalized into a format suitable for analysis. This process includes imputing missing values ​​and detecting and removing outliers.

[0264] Data analysis and prediction:

[0265] The server uses machine learning models to analyze and predict the obtained data. Specifically, it applies models that utilize time-series data (e.g., LSTM networks) to calculate future solar wind trends. This predicted data is recorded in an updated database and used for further analysis and display.

[0266] Generating three-dimensional visualizations:

[0267] The server generates a three-dimensional visualization based on the analysis results. An open-source 3D graphics library is used for the visualization. The generated 3D model visually shows the solar wind's path and impact area. Users can view and interactively manipulate this visualization using their terminals.

[0268] Natural language processing and hypothesis generation:

[0269] The server automatically collects academic papers from around the world and generates summaries using natural language processing. These summaries concisely present the key information extracted from the papers. Furthermore, it has the ability to automatically generate new research hypotheses based on the summarized information. Reinforcement learning is used to evaluate the validity of the generated hypotheses and present promising research topics.

[0270] Advanced simulation:

[0271] The server utilizes quantum computing technology to perform advanced simulations of the solar wind. This allows for high-speed, parallel execution of complex calculations, contributing to improved accuracy in analysis results. These simulation results will be used to further advance the research.

[0272] In this way, the system enables collaboration between servers, terminals, and users, and functions to support researchers in solving problems by efficiently analyzing and predicting solar wind data.

[0273] The process flow will be described below.

[0274] Step 1:

[0275] The server uses solar data acquisition means to obtain observation data from the API. This includes the selection of data sources and the setting of data transfer protocols. It supports real-time data streaming.

[0276] Step 2:

[0277] The server cleans the acquired data. Linear interpolation is used for filling missing values, and statistical methods are used for removing outliers. The data cleansing here ensures the consistency and reliability of the data.

[0278] Step 3:

[0279] The server inputs the normalized data into a machine learning model for analysis. Here, time series analysis using an LSTM network is performed to predict the future trend of the solar wind. The results are recorded in the prediction database.

[0280] Step 4:

[0281] The server generates 3D visualization based on the analysis results. Utilizing a 3D rendering engine, the path and influence range of the solar wind are visualized considering the positional relationship with the moon and the earth.

[0282] Step 5:

[0283] The terminal uses the generated 3D model to provide visualization to the user. The user can use a mouse or touch operations to view the behavior of the solar wind from different viewpoints.

[0284] Step 6:

[0285] The server automatically collects academic papers on solar wind, creates summaries using natural language processing technology, extracts important information, and stores the summaries in a database.

[0286] Step 7:

[0287] Based on the summarized information, the server generates hypotheses using generative AI. When proposing new research topics, it verifies the hypotheses using reinforcement learning.

[0288] Step 8:

[0289] The server uses a quantum computing platform to perform simulations. By performing parallel calculations under complex conditions, more accurate results can be obtained.

[0290] Step 9:

[0291] The server analyzes the obtained simulation results and utilizes them for further verification of 3D models and hypotheses. These results can be useful for future research and applications.

[0292] (Example 1)

[0293] Next, Example 1 will be described. In the following description, the data processing device 12 is referred to as the "server", and the smart glasses 214 are referred to as the "terminal".

[0294] Fluctuations in solar activity affect the Earth's environment and artificial objects, so highly accurate predictions are required. However, with existing technologies, the processes from data acquisition to analysis, visualization, hypothesis generation, and evaluation are fragmented, lacking an efficient and comprehensive solution. There are also problems such as how to provide the generated information to users and utilize it effectively.

[0295] The specific processing by the specific processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0296] In this invention, the server includes data acquisition means for acquiring solar physical data, information preprocessing means for preprocessing the acquired data, and prediction means having a computational model for analyzing and predicting the preprocessed data. This enables comprehensive acquisition, analysis, prediction, visualization, hypothesis generation, and evaluation of solar activity data, thereby realizing effective information provision to users.

[0297] "Solar physical data" refers to physical information obtained from the sun, including data on solar activity, radiation, wind, and magnetic fields.

[0298] "Data acquisition means" refers to methods and processes for collecting solar physical data using observation equipment and networks.

[0299] "Information preprocessing means" refers to methods that perform operations such as data cleaning, supplementation, and standardization in order to convert acquired data into an analyzable format.

[0300] A "computational model" is a mathematical model used to analyze data and make predictions, and often incorporates statistical methods and machine learning.

[0301] "Three-dimensional visualization generation means" refers to a technology and method for representing analyzed data in three dimensions and displaying it in an easily understandable visual format.

[0302] "Natural language processing" refers to a technology that mechanically analyzes and processes text data, and is used for information extraction and summary generation.

[0303] "Knowledge generation methods" are techniques for formulating new hypotheses based on collected information, and they utilize the results of data analysis.

[0304] "Computational techniques" refers to a series of technologies that enable advanced computations, and in particular, to advanced technologies such as quantum computing.

[0305] To implement this invention, first, the server plays a central role. The server, as a data acquisition means, connects to observation facilities connected to the Internet and obtains solar physics data via external APIs. For example, as a common option, it is possible to utilize cloud-based data acquisition services.

[0306] Next, as an information preprocessing means, the server uses advanced data processing software to perform data cleaning and standardization. It is common to utilize libraries in Python or R for this. This enables efficient completion of missing data and removal of outliers.

[0307] After that, the server analyzes the preprocessed data using a computational model and makes predictions. For example, using machine learning frameworks such as TensorFlow or PyTorch, a time series analysis model such as LSTM is constructed to predict the future trends of the solar wind.

[0308] The server further utilizes three-dimensional visualization generation means to visualize the analysis results in three dimensions. At this time, open-source graphic libraries such as Three.js or Matplotlib are used to generate visualization results that can be easily operated by users on a web browser.

[0309] The terminal provides these results to the user, and through an interactive interface, the user can visually understand the data. The terminal uses a front-end application developed with HTML5, CSS3, JavaScript, etc. to effectively display the visualization results visually.

[0310] In addition, the server utilizes natural language processing capabilities to collect information from relevant academic paper databases and summarize important data. To automatically generate new hypotheses from this summary information, the use of natural language processing libraries such as NLTK and the BERT model can be considered. As a concrete example of a prompt, the following message is entered into the server: "Summarize the latest astronomy papers and generate new research hypotheses."

[0311] Finally, as a computational technique, quantum computers are used to perform simulations with higher accuracy. For example, cloud-based quantum computing services can be used to perform computationally intensive simulations in a short amount of time.

[0312] This system configuration allows users to gain comprehensive insights based on actual solar wind data. By effectively coordinating the entire process from data acquisition to prediction, visualization, and result interpretation, the system improves the efficiency of researchers and engineers.

[0313] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0314] Step 1:

[0315] The server acquires solar physical data via an external API. The input requires the API endpoint and authentication credentials. The server uses this information to send an HTTP request and receives observation data in JSON format as output. Specifically, it sends a GET request with authentication using the API key.

[0316] Step 2:

[0317] The server preprocesses the acquired data. The input is the observation data in JSON format obtained in step 1. The server analyzes the data to impute missing values ​​and remove outliers, and outputs clean data in standard format. Specifically, it uses Python or R and the Pandas library to impute missing values ​​with the median and detect and remove outliers.

[0318] Step 3:

[0319] The server makes predictions using pre-processed data. The input data is the data cleaned in step 2. This is input into a machine learning model to output predictions for future solar physics data. Specifically, an LSTM model is used to train and predict time series data.

[0320] Step 4:

[0321] The server records the prediction results in a database. The input is the prediction results obtained in step 3. The server saves this to the appropriate table in the database, making it available for future analysis and visualization. Specifically, it uses MySQL or PostgreSQL and stores the prediction results using INSERT statements.

[0322] Step 5:

[0323] The server visualizes prediction data in three dimensions. The input is the prediction results stored in a database. Based on this data, the server generates three-dimensional graphics and provides a user-interactive visualization as output. Specifically, it uses Three.js and renders the results in the browser using WebGL.

[0324] Step 6:

[0325] The terminal displays visualized data to the user. The input is three-dimensional visualization data provided by the server. The terminal displays this data concretely in a browser and enables interaction with the user. Specific operations include the implementation of dynamic content using HTML5 and JavaScript.

[0326] Step 7:

[0327] The server uses natural language processing to extract information from relevant literature and generate summaries. The input is data from an academic paper database. The server extracts key information and outputs a concise summary. Specifically, it applies a text summarization algorithm based on BERT.

[0328] Step 8:

[0329] The server generates new hypotheses and evaluates their validity. The input is the summary information generated in step 7. The server evaluates the hypotheses using a reinforcement learning algorithm and presents promising research topics as output. The specific operation involves training and evaluating models using a reinforcement learning library.

[0330] (Application Example 1)

[0331] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0332] In recent years, the impact of solar wind, associated with solar activity, on Earth's energy infrastructure has attracted considerable attention. However, existing systems have struggled to accurately predict solar wind patterns and notify citizens of their impacts in real time. In particular, there is a need for immediate response measures to enable efficient urban infrastructure management and energy system operation.

[0333] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0334] In this invention, the server includes means for acquiring solar energy data, means for cleaning information, means for making predictions with a machine learning algorithm, means for generating visualizations, a natural language processing device, means for constructing hypotheses, a quantum computing device, and means for generating notifications. This makes it possible to predict the impact of solar wind on urban infrastructure in real time and immediately notify citizens.

[0335] A "solar energy data acquisition device" is a device that has the function of collecting data related to solar activity in real time.

[0336] An "information cleaning device" is a device that performs preprocessing, such as imputing missing values ​​and removing outliers, in order to prepare acquired data into an analyzable format.

[0337] A "predictive tool with a machine learning algorithm" is a device that uses machine learning technology to predict future solar wind trends based on collected data.

[0338] A "visualization generation means" is a device that visualizes analysis results in three dimensions and displays them in a way that users can intuitively understand.

[0339] A "natural language processing device" is a device that automatically collects literature and information, and provides concise information by summarizing it.

[0340] A "hypothesis-building tool" is a device that automatically generates new research hypotheses based on summarized information.

[0341] A "quantum computing device" is a device that can perform complex calculations at high speed in order to achieve highly accurate simulations.

[0342] A "notification generation device" is a device that notifies citizens in real time about the impacts of solar wind and proposes necessary countermeasures.

[0343] The system for realizing this invention functions as follows:

[0344] The server collects solar energy data in real time using an API. This data is then processed using information cleaning tools to impute missing values ​​and remove outliers, preparing it for analysis. Next, the server uses a machine learning algorithm (TensorFlow) to predict solar wind trends. This predicted data is then visualized in three dimensions using a visualization tool (Three.js), allowing users to understand it intuitively.

[0345] Furthermore, the server uses a natural language processing device (spaCy) to automatically collect and summarize literature from around the world. Based on the summarized information, a hypothesis-building tool generates new research hypotheses. These hypotheses are then tested using high-precision simulated computations performed by a quantum computing device.

[0346] Through online digital terminals, the server notifies citizens in real time about the impact of solar winds and proposes necessary countermeasures. This will enable more efficient management of energy systems within smart cities.

[0347] One concrete example is a system that notifies citizens 30 minutes in advance via a smartphone application about power outages expected due to solar winds. By inputting prompts such as, "Please describe the effects of solar winds and propose specific countermeasures for the smart city infrastructure in the designated area," into an AI model, it is possible to automatically suggest the most suitable response.

[0348] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0349] Step 1:

[0350] The server acquires solar energy data in real time via an API. It receives observational data on solar activity as input and generates raw data as output. This data is then retrieved for subsequent processing.

[0351] Step 2:

[0352] The server preprocesses the acquired data using information cleaning methods. It uses raw data as input, imputes missing values, removes outliers, and outputs rational data. At this stage, the data is prepared in a format suitable for analysis.

[0353] Step 3:

[0354] The server uses machine learning algorithms to analyze data and predict solar wind trends. It takes pre-processed data as input, performs time-series analysis using an LSTM model, and outputs future solar wind prediction data. This result is used in the next step.

[0355] Step 4:

[0356] The server visualizes the analysis results in three dimensions using visualization generation tools. It receives prediction data as input, generates a three-dimensional model using Three.js, and outputs it. This allows the user to interactively check the extent of the solar wind's influence.

[0357] Step 5:

[0358] The server uses a natural language processing unit (NLP) to collect relevant literature and create summaries. Using the collected literature data as input, it extracts key points through natural language processing and outputs a summary. This summary is useful for providing information concisely.

[0359] Step 6:

[0360] The server generates new research hypotheses based on summaries using hypothesis-building tools. It receives a summary text as input, constructs a new hypothesis using a generative AI model, and outputs that hypothesis. This hypothesis serves as the starting point for the research.

[0361] Step 7:

[0362] The server has a quantum computing device test the hypothesis. Using the generated hypothesis as input, it performs high-precision simulations and outputs the results verifying the validity of the hypothesis. These results are used for further research.

[0363] Step 8:

[0364] The terminal notifies the user of information regarding the impact of solar winds through a notification generation mechanism. It receives solar wind forecast data and verification results as input, generates notifications that present specific countermeasures, and outputs them to the user, thereby supporting real-time infrastructure management.

[0365] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0366] This invention is a system that combines a system that supports the acquisition, analysis, visualization, and hypothesis generation of solar data with an emotion engine that recognizes the user's emotional state, and is implemented in the following form.

[0367] Data acquisition and processing:

[0368] The server receives solar data in real time from observatories around the world. This data includes information such as solar wind speed, density, and temperature. The server cleans and formats the received data for analysis and prediction. This ensures data consistency and accuracy of analysis.

[0369] Data analysis and prediction:

[0370] The server uses machine learning models to analyze received data and predict future trends in solar wind. These models include time series analysis techniques such as LSTM, and the prediction results are used in subsequent visualization and hypothesis generation processes.

[0371] Generating three-dimensional visualizations:

[0372] The server generates a three-dimensional visualization model based on the predicted data. A 3D rendering engine is used to intuitively show the movement and extent of the solar wind's influence. The terminal provides this 3D model to the user, offering an interface that allows the user to freely change their viewpoint and observe the model.

[0373] Natural language processing and hypothesis generation:

[0374] The server collects academic papers from around the world and uses natural language processing techniques to create summaries. It then generates new research hypotheses from this summary information. Reinforcement learning algorithms are used to evaluate the validity of the generated hypotheses and provide new directions for research.

[0375] Advanced simulation and emotion recognition:

[0376] The server performs complex simulations using quantum computing technology. In addition, the system incorporates an emotion engine that recognizes the user's emotions. The terminal analyzes the user's facial expressions and tone of voice through the camera and voice interface to determine their emotional state.

[0377] The device adjusts how visualizations are displayed according to the user's emotions. For example, it uses calmer, less visually burdensome animations for stressed users, while providing detailed, interactive data displays for interested users. In this way, the system can provide flexible, user-friendly feedback and a more enriching experience.

[0378] This system aims to deepen our understanding of solar wind and stimulate researchers' curiosity and learning experiences.

[0379] The following describes the processing flow.

[0380] Step 1:

[0381] The server accesses a designated API to acquire observational data and receives solar data in real time. The data includes basic physical quantities such as solar wind speed, density, and temperature.

[0382] Step 2:

[0383] The server performs a cleaning process on the received raw data. This involves filtering outliers using statistical methods and imputing missing values. Normalization is also performed to maintain data consistency and quality.

[0384] Step 3:

[0385] The server uses the organized data to run machine learning algorithms, including LSTM models, to predict the short-term and long-term behavior of the solar wind. The prediction results are stored in a database and used to improve prediction accuracy.

[0386] Step 4:

[0387] The server generates a 3D model based on the analyzed prediction data. A 3D graphics library is used for visualization, intuitively displaying the extent and path of the solar wind's impact on Earth.

[0388] Step 5:

[0389] The device provides the user with this 3D model as an interactive visualization. The user can observe the solar wind simulation results from various angles while manipulating the viewpoint.

[0390] Step 6:

[0391] The server automatically collects the latest academic papers on solar wind from online databases. It then uses natural language processing techniques to extract key information from the collected papers and create summaries.

[0392] Step 7:

[0393] The server automatically generates new hypotheses using generative AI based on the summarized information. The validity of these generated hypotheses is then evaluated through a verification process using reinforcement learning.

[0394] Step 8:

[0395] The server utilizes quantum computing capabilities to perform advanced simulations. It aims to further improve prediction accuracy by conducting simulations under complex conditions at high speed.

[0396] Step 9:

[0397] The device analyzes the user's emotional state from their facial expressions and voice using an emotion engine. Based on this analysis, it dynamically adjusts the style of visualization and the level of detail of the information displayed.

[0398] Step 10:

[0399] Users experience emotion-recognition-based feedback through a flexible interface presented by the device. This allows users to receive solar wind information optimized for their own psychological state.

[0400] (Example 2)

[0401] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0402] Conventional solar data analysis systems have not adequately achieved real-time data acquisition, high-precision prediction, or automated hypothesis generation, nor have they provided interactive visualizations that respond to user emotions. Therefore, improving the efficiency of research and the user experience remains a challenge.

[0403] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0404] In this invention, the server includes means for acquiring solar data, means for cleaning data, and means for making predictions with a machine learning model. This enables real-time data acquisition, highly accurate predictions, and interactive three-dimensional visualization.

[0405] "Solar data acquisition methods" refer to technologies for collecting information about the sun in real time from observatories around the world.

[0406] "Data cleaning techniques" refer to processing technologies used to remove noise and inconsistencies from collected data and convert it into a format suitable for analysis and prediction.

[0407] "Predictive methods using machine learning models" refer to technologies that use machine learning algorithms to predict future trends based on past data.

[0408] "Visualization generation means" refers to technology for displaying analysis results in a three-dimensional shape so that they can be intuitively understood.

[0409] "Natural language processing methods" refer to technologies that process text data and enable summarization and information extraction.

[0410] "Hypothesis generation method" refers to technology that automatically generates new research hypotheses based on obtained information and summaries.

[0411] "High-performance computing means" refers to technologies that provide advanced computing power to perform complex simulations.

[0412] "Emotion recognition means" refers to technology that analyzes a user's facial expressions and voice to recognize their emotional state.

[0413] "Display means" refers to technologies that provide users with visualized data and enable them to interact with it.

[0414] "Evaluation methods" refer to techniques that utilize reinforcement learning algorithms to evaluate the effectiveness and novelty of generated hypotheses.

[0415] In this invention, the server acquires solar data from an observatory and removes noise from the received data using data cleaning means. Specifically, it utilizes data processing tools such as the Pandas library to prepare formatted data.

[0416] Next, the server runs machine learning models using TensorFlow and Keras, and performs time series analysis using LSTM (Long Short-Term Memory Network) to predict future trends in solar wind.

[0417] The predicted data is visualized in three dimensions using a 3D rendering engine such as Blender. This 3D model is provided to the user via their device, allowing them to intuitively observe the movement and extent of the solar wind's influence while freely changing their viewpoint using a browser-based interface.

[0418] The server also collects academic papers via the Google Scholar API and generates summaries of those papers using natural language processing technology. Furthermore, it uses a generative AI model (e.g., GPT-4) to formulate new research hypotheses from the summaries and evaluates those hypotheses using a reinforcement learning algorithm.

[0419] The system also performs complex simulations using high-performance computing capabilities. In addition, the device recognizes the user's emotions through its camera and microphone, and adjusts the visualization method based on the results analyzed by the emotion recognition system. If the system determines that the user is experiencing stress, it uses gentle animations to reduce visual strain.

[0420] As an example, the effects of the Earth's magnetic field over the next week can be simulated and displayed in a 3D model. If the user shows interest, a detailed and interactive model can be provided, allowing the user to perform further analysis using this data.

[0421] An example of a prompt message could be: "Analyze solar wind data and generate a model to visualize the effects of the Earth's magnetic field next week." The system will then perform the appropriate data processing and visualization in response to such prompts.

[0422] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0423] Step 1:

[0424] The server acquires solar data in real time from observatories in various locations. It receives data such as solar wind speed, density, and temperature as input, and then performs noise reduction and missing value imputation using data cleaning methods. The output is a consistent and clean dataset.

[0425] Step 2:

[0426] The server runs an LSTM machine learning model using the clean data obtained in Step 1. Specifically, it performs time series analysis using TensorFlow or Keras to predict future solar wind trends. The input is a formatted dataset, and the output is predicted solar wind trend data.

[0427] Step 3:

[0428] The server processes predicted trend data using a 3D rendering engine such as Blender to generate a three-dimensional visualization model. The input is predicted data, and the output is a three-dimensional model that allows the user to observe the visualization data from various perspectives. The terminal provides this model to the user and displays it through an intuitive interface.

[0429] Step 4:

[0430] The server uses natural language processing to retrieve academic papers from around the world and summarize the information. Specifically, it uses an API to input paper data and generates summaries using NLTK and spaCy. The output is summarized paper information, which is then used by a generative AI model to generate new research hypotheses.

[0431] Step 5:

[0432] The server applies a reinforcement learning algorithm to evaluate the validity of hypotheses formulated by the generative AI model. The input is hypothesis information, and the output is a list of evaluated hypotheses. Based on this, new directions for research can be suggested.

[0433] Step 6:

[0434] The device collects the user's facial expressions and voice through its camera and microphone, and analyzes their emotional state using an emotion recognition API. The input is the user's facial expressions and voice data, and the output is the result of the emotional state analysis. Based on these results, the device adjusts the 3D visualization display mode to provide the user with a relaxing environment.

[0435] (Application Example 2)

[0436] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0437] The problem this invention aims to solve is to provide information tailored to the user's emotions through the analysis and visualization of solar wind data, thereby offering an intuitive and user-friendly learning experience. In particular, it aims to facilitate understanding of cosmic phenomena and streamline the acquisition of scientific knowledge by displaying appropriate information according to the user's interests and stress levels.

[0438] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0439] In this invention, the server includes means for acquiring solar data, means for cleaning data, means for prediction using a machine learning model, means for visualizing and generating analysis results in three dimensions, means for natural language processing for collecting and summarizing papers, means for generating new hypotheses, means for high-precision simulation using quantum computing, means for recognizing the user's emotional state, and means for interactively providing information. This enables real-time analysis of information related to solar wind and flexible information provision according to the user's emotional state.

[0440] The "solar data acquisition method" is a function that collects data on solar wind in real time from observatories in various locations.

[0441] "Data cleaning methods" are functions that process data to remove noise and outliers in order to prepare the acquired data for analysis and prediction.

[0442] "Prediction methods using machine learning models" refers to a function that uses machine learning technology to analyze future trends in solar wind and provide prediction results.

[0443] A "visualization generation method" is a function that visually represents the analyzed data as a three-dimensional model, making it intuitively understandable to the user.

[0444] "Natural language processing methods" refer to technologies used to analyze collected academic papers and text data and create summaries.

[0445] A "hypothesis generation tool" is a function that carries out the process of creating new research hypotheses based on the generated summaries.

[0446] "High-precision simulation methods using quantum computing" refers to a function that accurately simulates complex astronomical phenomena using quantum computing technology.

[0447] "Emotion recognition means" refers to a function that analyzes the user's facial expressions and tone of voice to determine their current emotional state and adjust the way information is displayed accordingly.

[0448] An "interface means" is a means for interactive communication between a user and a system, and is a function that provides information through visual and auditory means.

[0449] This invention constructs a system that performs real-time data analysis on solar wind and provides scientific information tailored to the user's emotional state. The server first receives solar data from an observatory, removes noise and outliers using data cleaning means, and then performs predictions using a machine learning model. This prediction employs time series analysis methods such as LSTM using TensorFlow.

[0450] Next, based on the analyzed data, the visualization generation system uses the Unity3D engine to generate a three-dimensional model. Through this model, it is possible to intuitively display the movement and affected area of ​​the solar wind.

[0451] Furthermore, the server collects papers and uses natural language processing to create summaries. From the generated summaries, a hypothesis generation tool uses a reinforcement learning algorithm to create and propose new research hypotheses.

[0452] This system incorporates emotion recognition technology that analyzes facial expressions and voice tone through the user's camera and microphone. This allows the interface to adjust its display content according to the user's emotional state, providing content tailored to their interests and stress levels. For example, it can provide calming animations to stressed users and interactively display detailed data to curious users.

[0453] As a concrete example, a scenario could be envisioned where a user observes changes in the movement of the solar wind through this system during a solar eclipse, deepening their scientific understanding. An example of a prompt in this scenario would be: "Please tell me how I can learn about the movement of the solar wind in an interesting and real-time way. It's sunny right now, so I'm feeling motivated."

[0454] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0455] Step 1:

[0456] The server acquires solar data in real time from observatories. This is a process of receiving solar wind data transmitted from various locations, using information such as solar wind speed, density, and temperature as input. In this step, data is received and recorded in a database for subsequent processing.

[0457] Step 2:

[0458] The server performs data cleaning on the received data. The input is the raw data obtained in step 1, and noise reduction and correction of outliers are performed. The output is the cleaned and formatted data, which enables highly accurate analysis. The Python Pandas library is used for data cleaning.

[0459] Step 3:

[0460] The server performs data analysis and prediction using a machine learning model. The pre-processed data obtained in step 2 is used as input. An LSTM model is used to predict future solar wind trends and output the prediction results. TensorFlow is used for the analysis, and the results are stored in a database.

[0461] Step 4:

[0462] The server generates a three-dimensional visualization model based on the analysis results. The input is the prediction results from step 3, and the Unity3D engine is used to render the movement and affected area of ​​the solar wind in three dimensions. The output is a 3D model that the user can freely observe by changing the viewpoint.

[0463] Step 5:

[0464] The server collects academic papers and generates summaries using natural language processing (NLP). The input consists of relevant papers found on the internet. The NLP algorithm generates the summaries, which are then output as data for proposing new hypotheses.

[0465] Step 6:

[0466] The server generates hypotheses based on the summarized data. Reinforcement learning algorithms are used to train predictive models and generate new hypotheses. The output is a list of hypotheses, which can be useful for further scientific research.

[0467] Step 7:

[0468] The device receives a photo of the user's face and voice input, and uses an emotion recognition engine to determine their emotional state. Input is data collected from the camera and microphone. Output is the user's emotional state (e.g., interesting, stressed). The algorithm uses OpenCV and the Google Cloud Speech API.

[0469] Step 8:

[0470] The device adjusts its display based on the emotion data from step 7. The inputs are the user's emotional state and the 3D model from step 4. The output is a customized information display tailored to the specific emotion. For example, if the emotion is deemed interesting, an interactive data display will occur.

[0471] The input, data processing, and output at each processing step are clearly defined, and the entire system provides an intuitive science learning experience that engages the user.

[0472] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0473] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0474] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart glasses 214.

[0475] [Third Embodiment]

[0476] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0477] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0478] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0479] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0480] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0481] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0482] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0483] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0484] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0485] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0486] In the headset terminal 314, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0487] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the headset terminal 314 will be referred to as the "terminal".

[0488] This invention is a system for efficiently analyzing and predicting solar wind data, and is implemented in the following form.

[0489] Data acquisition and preprocessing:

[0490] The server has an interface for acquiring solar observation data in real time. Data is sent to the server via APIs, etc. The acquired data first undergoes a cleaning process and is normalized into a format suitable for analysis. This process includes imputing missing values ​​and detecting and removing outliers.

[0491] Data analysis and prediction:

[0492] The server uses machine learning models to analyze and predict the obtained data. Specifically, it applies models that utilize time-series data (e.g., LSTM networks) to calculate future solar wind trends. This predicted data is recorded in an updated database and used for further analysis and display.

[0493] Generating three-dimensional visualizations:

[0494] The server generates a three-dimensional visualization based on the analysis results. An open-source 3D graphics library is used for the visualization. The generated 3D model visually shows the solar wind's path and impact area. Users can view and interactively manipulate this visualization using their terminals.

[0495] Natural language processing and hypothesis generation:

[0496] The server automatically collects academic papers from around the world and generates summaries using natural language processing. These summaries concisely present the key information extracted from the papers. Furthermore, it has the ability to automatically generate new research hypotheses based on the summarized information. Reinforcement learning is used to evaluate the validity of the generated hypotheses and present promising research topics.

[0497] Advanced simulation:

[0498] The server utilizes quantum computing technology to perform advanced simulations of the solar wind. This allows for high-speed, parallel execution of complex calculations, contributing to improved accuracy in analysis results. These simulation results will be used to further advance the research.

[0499] In this way, the system enables collaboration between servers, terminals, and users, and functions to support researchers in solving problems by efficiently analyzing and predicting solar wind data.

[0500] The following describes the processing flow.

[0501] Step 1:

[0502] The server retrieves observational data from the API using solar data acquisition methods. This includes selecting data sources and configuring data transfer protocols. It supports real-time data streaming.

[0503] Step 2:

[0504] The server cleans the acquired data. Linear interpolation is used to fill in missing values, and statistical methods are used to remove outliers. This data cleansing ensures data consistency and reliability.

[0505] Step 3:

[0506] The server feeds the normalized data into a machine learning model for analysis. Here, a time series analysis using an LSTM network is performed to predict future solar wind trends. The results are recorded in a prediction database.

[0507] Step 4:

[0508] The server generates a three-dimensional visualization based on the analysis results. Utilizing a 3D rendering engine, it visualizes the solar wind's path and influence area, taking into account its positional relationship with the Moon and Earth.

[0509] Step 5:

[0510] The device uses the generated 3D model to provide visualization to the user. The user can use mouse or touch controls to view the behavior of the solar wind from different perspectives.

[0511] Step 6:

[0512] The server automatically collects academic papers on solar wind and creates summaries using natural language processing technology. It extracts important information and stores the summaries in a database.

[0513] Step 7:

[0514] The server generates hypotheses using generative AI based on the summarized information. When proposing new research themes, reinforcement learning is used to test these hypotheses.

[0515] Step 8:

[0516] The server runs simulations using a quantum computing platform. By performing parallel computing under complex conditions, more accurate results are obtained.

[0517] Step 9:

[0518] The server analyzes the obtained simulation results and uses them to further verify 3D models and hypotheses. These results can be used for future research and applications.

[0519] (Example 1)

[0520] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0521] Fluctuations in solar activity affect the Earth's environment and man-made objects, thus requiring highly accurate predictions. However, current technologies have fragmented processes from data acquisition and analysis to visualization, hypothesis generation, and evaluation, lacking efficient and comprehensive solutions. Furthermore, there are issues regarding how to provide the generated information to users and how to utilize it effectively.

[0522] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0523] In this invention, the server includes data acquisition means for acquiring solar physical data, information preprocessing means for preprocessing the acquired data, and prediction means having a computational model for analyzing and predicting the preprocessed data. This enables comprehensive acquisition, analysis, prediction, visualization, hypothesis generation, and evaluation of solar activity data, thereby realizing effective information provision to users.

[0524] "Solar physical data" refers to physical information obtained from the sun, including data on solar activity, radiation, wind, and magnetic fields.

[0525] "Data acquisition means" refers to methods and processes for collecting solar physical data using observation equipment and networks.

[0526] "Information preprocessing means" refers to methods that perform operations such as data cleaning, supplementation, and standardization in order to convert acquired data into an analyzable format.

[0527] A "computational model" is a mathematical model used to analyze data and make predictions, and often incorporates statistical methods and machine learning.

[0528] "Three-dimensional visualization generation means" refers to a technology and method for representing analyzed data in three dimensions and displaying it in an easily understandable visual format.

[0529] "Natural language processing" refers to a technology that mechanically analyzes and processes text data, and is used for information extraction and summary generation.

[0530] "Knowledge generation methods" are techniques for formulating new hypotheses based on collected information, and they utilize the results of data analysis.

[0531] "Computational techniques" refers to a series of technologies that enable advanced computations, and in particular, to advanced technologies such as quantum computing.

[0532] To implement this invention, a server plays a central role. The server acquires solar physical data via observation equipment connected to the internet or through external APIs. For example, a common option is to use a cloud-based data acquisition service.

[0533] The server then performs data cleaning and standardization using advanced data processing software as a preprocessing measure. This typically involves using libraries from Python or R. This allows for efficient completion of missing data and removal of outliers.

[0534] Subsequently, the server analyzes the data preprocessed by the computational model and makes predictions. For example, it uses machine learning frameworks such as TensorFlow and PyTorch to build time series analysis models such as LSTM to predict future solar wind trends.

[0535] The server further utilizes three-dimensional visualization generation methods to visualize the analysis results in three dimensions. In this process, it uses open-source graphics libraries such as Three.js and Matplotlib to generate visualizations that can be easily manipulated by the user in a web browser.

[0536] The device provides these results to the user, allowing the user to visually understand the data through an interactive interface. The device uses a front-end application developed with HTML5, CSS3, JavaScript, etc., to effectively display the visualization results visually.

[0537] In addition, the server utilizes natural language processing capabilities to collect information from relevant academic paper databases and summarize important data. To automatically generate new hypotheses from this summary information, the use of natural language processing libraries such as NLTK and the BERT model can be considered. As a concrete example of a prompt, the following message is entered into the server: "Summarize the latest astronomy papers and generate new research hypotheses."

[0538] Finally, as a computational technique, quantum computers are used to perform simulations with higher accuracy. For example, cloud-based quantum computing services can be used to perform computationally intensive simulations in a short amount of time.

[0539] This system configuration allows users to gain comprehensive insights based on actual solar wind data. By effectively coordinating the entire process from data acquisition to prediction, visualization, and result interpretation, the system improves the efficiency of researchers and engineers.

[0540] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0541] Step 1:

[0542] The server acquires solar physical data via an external API. The input requires the API endpoint and authentication credentials. The server uses this information to send an HTTP request and receives observation data in JSON format as output. Specifically, it sends a GET request with authentication using the API key.

[0543] Step 2:

[0544] The server preprocesses the acquired data. The input is the observation data in JSON format obtained in step 1. The server analyzes the data to impute missing values ​​and remove outliers, and outputs clean data in standard format. Specifically, it uses Python or R and the Pandas library to impute missing values ​​with the median and detect and remove outliers.

[0545] Step 3:

[0546] The server makes predictions using pre-processed data. The input data is the data cleaned in step 2. This is input into a machine learning model to output predictions for future solar physics data. Specifically, an LSTM model is used to train and predict time series data.

[0547] Step 4:

[0548] The server records the prediction results in a database. The input is the prediction results obtained in step 3. The server saves this to the appropriate table in the database, making it available for future analysis and visualization. Specifically, it uses MySQL or PostgreSQL and stores the prediction results using INSERT statements.

[0549] Step 5:

[0550] The server visualizes prediction data in three dimensions. The input is the prediction results stored in a database. Based on this data, the server generates three-dimensional graphics and provides a user-interactive visualization as output. Specifically, it uses Three.js and renders the results in the browser using WebGL.

[0551] Step 6:

[0552] The terminal displays visualized data to the user. The input is three-dimensional visualization data provided by the server. The terminal displays this data concretely in a browser and enables interaction with the user. Specific operations include the implementation of dynamic content using HTML5 and JavaScript.

[0553] Step 7:

[0554] The server uses natural language processing to extract information from relevant literature and generate summaries. The input is data from an academic paper database. The server extracts key information and outputs a concise summary. Specifically, it applies a text summarization algorithm based on BERT.

[0555] Step 8:

[0556] The server generates new hypotheses and evaluates their validity. The input is the summary information generated in step 7. The server evaluates the hypotheses using a reinforcement learning algorithm and presents promising research topics as output. The specific operation involves training and evaluating models using a reinforcement learning library.

[0557] (Application Example 1)

[0558] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0559] In recent years, the impact of solar wind, associated with solar activity, on Earth's energy infrastructure has attracted considerable attention. However, existing systems have struggled to accurately predict solar wind patterns and notify citizens of their impacts in real time. In particular, there is a need for immediate response measures to enable efficient urban infrastructure management and energy system operation.

[0560] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0561] In this invention, the server includes means for acquiring solar energy data, means for cleaning information, means for making predictions with a machine learning algorithm, means for generating visualizations, a natural language processing device, means for constructing hypotheses, a quantum computing device, and means for generating notifications. This makes it possible to predict the impact of solar wind on urban infrastructure in real time and immediately notify citizens.

[0562] A "solar energy data acquisition device" is a device that has the function of collecting data related to solar activity in real time.

[0563] An "information cleaning device" is a device that performs preprocessing, such as imputing missing values ​​and removing outliers, to prepare acquired data into an analyzable format.

[0564] A "predictive tool with a machine learning algorithm" is a device that uses machine learning technology to predict future solar wind trends based on collected data.

[0565] A "visualization generation means" is a device that visualizes analysis results in three dimensions and displays them in a way that users can intuitively understand.

[0566] A "natural language processing device" is a device that automatically collects literature and information, and provides concise information by summarizing it.

[0567] A "hypothesis-building tool" is a device that automatically generates new research hypotheses based on summarized information.

[0568] A "quantum computing device" is a device that can perform complex calculations at high speed in order to achieve highly accurate simulations.

[0569] A "notification generation device" is a device that notifies citizens in real time about the impacts of solar wind and proposes necessary countermeasures.

[0570] The system for realizing this invention functions as follows:

[0571] The server collects solar energy data in real time using an API. This data is then processed using information cleaning tools to impute missing values ​​and remove outliers, preparing it for analysis. Next, the server uses a machine learning algorithm (TensorFlow) to predict solar wind trends. This predicted data is then visualized in three dimensions using a visualization tool (Three.js), allowing users to understand it intuitively.

[0572] Furthermore, the server uses a natural language processing device (spaCy) to automatically collect and summarize literature from around the world. Based on the summarized information, a hypothesis-building tool generates new research hypotheses. These hypotheses are then tested using high-precision simulated computations performed by a quantum computing device.

[0573] Through online digital terminals, the server notifies citizens in real time about the impact of solar winds and proposes necessary countermeasures. This will enable more efficient management of energy systems within smart cities.

[0574] One concrete example is a system that notifies citizens 30 minutes in advance via a smartphone application about power outages expected due to solar winds. By inputting prompts such as, "Please describe the effects of solar winds and propose specific countermeasures for the smart city infrastructure in the designated area," into an AI model, it is possible to automatically suggest the most suitable response.

[0575] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0576] Step 1:

[0577] The server acquires solar energy data in real time via an API. It receives observational data on solar activity as input and generates raw data as output. This data is then retrieved for subsequent processing.

[0578] Step 2:

[0579] The server preprocesses the acquired data using information cleaning methods. It uses raw data as input, imputes missing values, removes outliers, and outputs rational data. At this stage, the data is prepared in a format suitable for analysis.

[0580] Step 3:

[0581] The server uses machine learning algorithms to analyze data and predict solar wind trends. It takes pre-processed data as input, performs time-series analysis using an LSTM model, and outputs future solar wind prediction data. This result is used in the next step.

[0582] Step 4:

[0583] The server visualizes the analysis results in three dimensions using visualization generation tools. It receives prediction data as input, generates a three-dimensional model using Three.js, and outputs it. This allows the user to interactively check the extent of the solar wind's influence.

[0584] Step 5:

[0585] The server uses a natural language processing unit (NLP) to collect relevant literature and create summaries. Using the collected literature data as input, it extracts key points through natural language processing and outputs a summary. This summary is useful for providing information concisely.

[0586] Step 6:

[0587] The server generates new research hypotheses based on summaries using hypothesis-building tools. It receives a summary text as input, constructs a new hypothesis using a generative AI model, and outputs that hypothesis. This hypothesis serves as the starting point for the research.

[0588] Step 7:

[0589] The server has a quantum computing device test the hypothesis. Using the generated hypothesis as input, it performs high-precision simulations and outputs the results verifying the validity of the hypothesis. These results are used for further research.

[0590] Step 8:

[0591] The terminal notifies the user of information regarding the impact of solar winds through a notification generation mechanism. It receives solar wind forecast data and verification results as input, generates notifications that present specific countermeasures, and outputs them to the user, thereby supporting real-time infrastructure management.

[0592] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0593] This invention is a system that combines a system that supports the acquisition, analysis, visualization, and hypothesis generation of solar data with an emotion engine that recognizes the user's emotional state, and is implemented in the following form.

[0594] Data acquisition and processing:

[0595] The server receives solar data in real time from observatories around the world. This data includes information such as solar wind speed, density, and temperature. The server cleans and formats the received data for analysis and prediction. This ensures data consistency and accuracy of analysis.

[0596] Data analysis and prediction:

[0597] The server uses machine learning models to analyze received data and predict future trends in solar wind. These models include time series analysis techniques such as LSTM, and the prediction results are used in subsequent visualization and hypothesis generation processes.

[0598] Generating three-dimensional visualizations:

[0599] The server generates a three-dimensional visualization model based on the predicted data. A 3D rendering engine is used to intuitively show the movement and extent of the solar wind's influence. The terminal provides this 3D model to the user, offering an interface that allows the user to freely change their viewpoint and observe the model.

[0600] Natural language processing and hypothesis generation:

[0601] The server collects academic papers from around the world and uses natural language processing techniques to create summaries. It then generates new research hypotheses from this summary information. Reinforcement learning algorithms are used to evaluate the validity of the generated hypotheses and provide new directions for research.

[0602] Advanced simulation and emotion recognition:

[0603] The server performs complex simulations using quantum computing technology. In addition, the system incorporates an emotion engine that recognizes the user's emotions. The terminal analyzes the user's facial expressions and tone of voice through the camera and voice interface to determine their emotional state.

[0604] The device adjusts how visualizations are displayed according to the user's emotions. For example, it uses calmer, less visually burdensome animations for stressed users, while providing detailed, interactive data displays for interested users. In this way, the system can provide flexible, user-friendly feedback and a more enriching experience.

[0605] This system aims to deepen our understanding of solar wind and stimulate researchers' curiosity and learning experiences.

[0606] The following describes the processing flow.

[0607] Step 1:

[0608] The server accesses a designated API to acquire observational data and receives solar data in real time. The data includes basic physical quantities such as solar wind speed, density, and temperature.

[0609] Step 2:

[0610] The server performs a cleaning process on the received raw data. This involves filtering outliers using statistical methods and imputing missing values. Normalization is also performed to maintain data consistency and quality.

[0611] Step 3:

[0612] The server uses the organized data to run machine learning algorithms, including LSTM models, to predict the short-term and long-term behavior of the solar wind. The prediction results are stored in a database and used to improve prediction accuracy.

[0613] Step 4:

[0614] The server generates a 3D model based on the analyzed prediction data. A 3D graphics library is used for visualization, intuitively displaying the extent and path of the solar wind's impact on Earth.

[0615] Step 5:

[0616] The device provides the user with this 3D model as an interactive visualization. The user can observe the solar wind simulation results from various angles while manipulating the viewpoint.

[0617] Step 6:

[0618] The server automatically collects the latest academic papers on solar wind from online databases. It then uses natural language processing techniques to extract key information from the collected papers and create summaries.

[0619] Step 7:

[0620] The server automatically generates new hypotheses using generative AI based on the summarized information. The validity of these hypotheses is then evaluated through a verification process using reinforcement learning.

[0621] Step 8:

[0622] The server utilizes quantum computing capabilities to perform advanced simulations. It aims to further improve prediction accuracy by conducting simulations under complex conditions at high speed.

[0623] Step 9:

[0624] The device analyzes the user's emotional state from their facial expressions and voice using an emotion engine. Based on this analysis, it dynamically adjusts the style of visualization and the level of detail of the information displayed.

[0625] Step 10:

[0626] Users experience emotion-recognition-based feedback through a flexible interface presented by the device. This allows users to receive solar wind information optimized for their own psychological state.

[0627] (Example 2)

[0628] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0629] Conventional solar data analysis systems have not adequately achieved real-time data acquisition, high-precision prediction, or automated hypothesis generation, nor have they provided interactive visualizations that respond to user emotions. Therefore, improving the efficiency of research and the user experience remains a challenge.

[0630] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0631] In this invention, the server includes means for acquiring solar data, means for cleaning data, and means for making predictions with a machine learning model. This enables real-time data acquisition, highly accurate predictions, and interactive three-dimensional visualization.

[0632] "Solar data acquisition methods" refer to technologies for collecting information about the sun in real time from observatories around the world.

[0633] "Data cleaning techniques" refer to processing technologies used to remove noise and inconsistencies from collected data and convert it into a format suitable for analysis and prediction.

[0634] "Predictive methods using machine learning models" refer to technologies that use machine learning algorithms to predict future trends based on past data.

[0635] "Visualization generation means" refers to technology for displaying analysis results in a three-dimensional shape so that they can be intuitively understood.

[0636] "Natural language processing methods" refer to technologies that process text data and enable summarization and information extraction.

[0637] "Hypothesis generation method" refers to technology that automatically generates new research hypotheses based on obtained information and summaries.

[0638] "High-performance computing means" refers to technologies that provide advanced computing power to perform complex simulations.

[0639] "Emotion recognition means" refers to technology that analyzes a user's facial expressions and voice to recognize their emotional state.

[0640] "Display means" refers to technologies that provide users with visualized data and enable them to interact with it.

[0641] "Evaluation methods" refer to techniques that utilize reinforcement learning algorithms to evaluate the effectiveness and novelty of generated hypotheses.

[0642] In this invention, the server acquires solar data from an observatory and removes noise from the received data using data cleaning means. Specifically, it utilizes data processing tools such as the Pandas library to prepare formatted data.

[0643] Next, the server runs machine learning models using TensorFlow and Keras, and performs time series analysis using LSTM (Long Short-Term Memory Network) to predict future trends in solar wind.

[0644] The predicted data is visualized in three dimensions using a 3D rendering engine such as Blender. This 3D model is provided to the user via their device, allowing them to intuitively observe the movement and extent of the solar wind's influence while freely changing their viewpoint using a browser-based interface.

[0645] The server also collects academic papers via the Google Scholar API and generates summaries of those papers using natural language processing technology. Furthermore, it uses a generative AI model (e.g., GPT-4) to formulate new research hypotheses from the summaries and evaluates those hypotheses using a reinforcement learning algorithm.

[0646] The system also performs complex simulations using high-performance computing capabilities. In addition, the device recognizes the user's emotions through its camera and microphone, and adjusts the visualization method based on the results analyzed by the emotion recognition system. If the system determines that the user is experiencing stress, it uses gentle animations to reduce visual strain.

[0647] As an example, the effects of the Earth's magnetic field over the next week may be simulated and displayed in a 3D model. If the user shows interest, a detailed and interactive model will be provided, allowing the user to perform further analysis using this data.

[0648] An example of a prompt message could be: "Analyze solar wind data and generate a model to visualize the effects of the Earth's magnetic field next week." The system will then perform the appropriate data processing and visualization in response to such prompts.

[0649] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0650] Step 1:

[0651] The server acquires solar data in real time from observatories in various locations. It receives data such as solar wind speed, density, and temperature as input, and then performs noise reduction and missing value imputation using data cleaning methods. The output is a consistent and clean dataset.

[0652] Step 2:

[0653] The server runs an LSTM machine learning model using the clean data obtained in Step 1. Specifically, it performs time series analysis using TensorFlow or Keras to predict future solar wind trends. The input is a formatted dataset, and the output is predicted solar wind trend data.

[0654] Step 3:

[0655] The server processes predicted trend data using a 3D rendering engine such as Blender to generate a three-dimensional visualization model. The input is predicted data, and the output is a three-dimensional model that allows the user to observe the visualization data from various perspectives. The terminal provides this model to the user and displays it through an intuitive interface.

[0656] Step 4:

[0657] The server retrieves academic papers from around the world using natural language processing tools and summarizes the information. Specifically, it uses an API to input paper data and generates summaries using NLTK and spaCy. The output is summarized paper information, which is then used by a generative AI model to generate new research hypotheses.

[0658] Step 5:

[0659] The server applies a reinforcement learning algorithm to evaluate the validity of hypotheses formulated by the generative AI model. The input is hypothesis information, and the output is a list of evaluated hypotheses. Based on this, new directions for research can be suggested.

[0660] Step 6:

[0661] The device collects the user's facial expressions and voice through its camera and microphone, and analyzes their emotional state using an emotion recognition API. The input is the user's facial expressions and voice data, and the output is the result of the emotional state analysis. Based on these results, the device adjusts the 3D visualization display mode to provide the user with a relaxing environment.

[0662] (Application Example 2)

[0663] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0664] The problem this invention aims to solve is to provide information tailored to the user's emotions through the analysis and visualization of solar wind data, thereby offering an intuitive and user-friendly learning experience. In particular, it aims to facilitate understanding of cosmic phenomena and streamline the acquisition of scientific knowledge by displaying appropriate information according to the user's interests and stress levels.

[0665] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0666] In this invention, the server includes means for acquiring solar data, means for cleaning data, means for prediction using a machine learning model, means for visualizing and generating analysis results in three dimensions, means for natural language processing for collecting and summarizing papers, means for generating new hypotheses, means for high-precision simulation using quantum computing, means for recognizing the user's emotional state, and means for interactively providing information. This enables real-time analysis of information related to solar wind and flexible information provision according to the user's emotional state.

[0667] The "solar data acquisition method" is a function that collects data on solar wind in real time from observatories in various locations.

[0668] "Data cleaning methods" are functions that process data to remove noise and outliers in order to prepare the acquired data for analysis and prediction.

[0669] "Prediction methods using machine learning models" refers to a function that uses machine learning technology to analyze future trends in solar wind and provide prediction results.

[0670] A "visualization generation method" is a function that visually represents the analyzed data as a three-dimensional model, making it intuitively understandable to the user.

[0671] "Natural language processing methods" refer to technologies used to analyze collected academic papers and text data and create summaries.

[0672] A "hypothesis generation tool" is a function that carries out the process of creating new research hypotheses based on the generated summaries.

[0673] "High-precision simulation methods using quantum computing" refers to a function that accurately simulates complex astronomical phenomena using quantum computing technology.

[0674] "Emotion recognition means" refers to a function that analyzes the user's facial expressions and tone of voice to determine their current emotional state and adjust the way information is displayed accordingly.

[0675] An "interface means" is a means for interactive communication between a user and a system, and is a function that provides information through visual and auditory means.

[0676] This invention constructs a system that performs real-time data analysis on solar wind and provides scientific information tailored to the user's emotional state. The server first receives solar data from an observatory, removes noise and outliers using data cleaning means, and then performs predictions using a machine learning model. This prediction employs time series analysis methods such as LSTM using TensorFlow.

[0677] Next, based on the analyzed data, the visualization generation system uses the Unity3D engine to generate a three-dimensional model. Through this model, it is possible to intuitively display the movement and affected area of ​​the solar wind.

[0678] Furthermore, the server collects papers and uses natural language processing to create summaries. From the generated summaries, a hypothesis generation tool uses a reinforcement learning algorithm to create and propose new research hypotheses.

[0679] This system incorporates emotion recognition technology that analyzes facial expressions and voice tone through the user's camera and microphone. This allows the interface to adjust its display content according to the user's emotional state, providing content tailored to their interests and stress levels. For example, it can provide calming animations to stressed users and interactively display detailed data to curious users.

[0680] As a concrete example, a scenario could be envisioned where a user observes changes in the movement of the solar wind through this system during a solar eclipse, deepening their scientific understanding. An example of a prompt in this scenario would be: "Please tell me how I can learn about the movement of the solar wind in an interesting and real-time way. It's sunny right now, so I'm feeling motivated."

[0681] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0682] Step 1:

[0683] The server acquires solar data in real time from observatories. This is a process of receiving solar wind data transmitted from various locations, using information such as solar wind speed, density, and temperature as input. In this step, data is received and recorded in a database for subsequent processing.

[0684] Step 2:

[0685] The server performs data cleaning on the received data. The input is the raw data obtained in step 1, and noise reduction and correction of outliers are performed. The output is the cleaned and formatted data, which enables highly accurate analysis. The Python Pandas library is used for data cleaning.

[0686] Step 3:

[0687] The server performs data analysis and prediction using a machine learning model. The pre-processed data obtained in step 2 is used as input. An LSTM model is used to predict future solar wind trends and output the prediction results. TensorFlow is used for the analysis, and the results are stored in a database.

[0688] Step 4:

[0689] The server generates a three-dimensional visualization model based on the analysis results. The input is the prediction results from step 3, and the Unity3D engine is used to render the movement and affected area of ​​the solar wind in three dimensions. The output is a 3D model that the user can freely observe by changing the viewpoint.

[0690] Step 5:

[0691] The server collects academic papers and generates summaries using natural language processing (NLP). The input consists of relevant papers found on the internet. The NLP algorithm generates the summaries, which are then output as data for proposing new hypotheses.

[0692] Step 6:

[0693] The server generates hypotheses based on the summarized data. Reinforcement learning algorithms are used to train predictive models and generate new hypotheses. The output is a list of hypotheses, which can be useful for further scientific research.

[0694] Step 7:

[0695] The device receives a photo of the user's face and voice input, and uses an emotion recognition engine to determine their emotional state. Input is data collected from the camera and microphone. Output is the user's emotional state (e.g., interesting, stressed). The algorithm uses OpenCV and the Google Cloud Speech API.

[0696] Step 8:

[0697] The device adjusts its display based on the emotion data from step 7. The inputs are the user's emotional state and the 3D model from step 4. The output is a customized information display tailored to the specific emotion. For example, if the emotion is deemed interesting, an interactive data display will occur.

[0698] The input, data processing, and output at each processing step are clearly defined, and the entire system provides an intuitive science learning experience that engages the user.

[0699] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0700] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0701] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and specific processing may also be performed by the headset terminal 314.

[0702] [Fourth Embodiment]

[0703] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0704] As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0705] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0706] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0707] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0708] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0709] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0710] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. Furthermore, the robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0711] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0712] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0713] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0714] In robot 414, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0715] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0716] This invention is a system for efficiently analyzing and predicting solar wind data, and is implemented in the following form.

[0717] Data acquisition and preprocessing:

[0718] The server has an interface for acquiring solar observation data in real time. Data is sent to the server via APIs, etc. The acquired data first undergoes a cleaning process and is normalized into a format suitable for analysis. This process includes imputing missing values ​​and detecting and removing outliers.

[0719] Data analysis and prediction:

[0720] The server uses machine learning models to analyze and predict the obtained data. Specifically, it applies models that utilize time-series data (e.g., LSTM networks) to calculate future solar wind trends. This predicted data is recorded in an updated database and used for further analysis and display.

[0721] Generating three-dimensional visualizations:

[0722] The server generates a three-dimensional visualization based on the analysis results. An open-source 3D graphics library is used for the visualization. The generated 3D model visually shows the solar wind's path and impact area. Users can view and interactively manipulate this visualization using their terminals.

[0723] Natural language processing and hypothesis generation:

[0724] The server automatically collects academic papers from around the world and generates summaries using natural language processing. These summaries concisely present the key information extracted from the papers. Furthermore, it has the ability to automatically generate new research hypotheses based on the summarized information. Reinforcement learning is used to evaluate the validity of the generated hypotheses and present promising research topics.

[0725] Advanced simulation:

[0726] The server utilizes quantum computing technology to perform advanced simulations of the solar wind. This allows for high-speed, parallel execution of complex calculations, contributing to improved accuracy in analysis results. These simulation results will be used to further advance the research.

[0727] In this way, the system enables collaboration between servers, terminals, and users, and functions to support researchers in solving problems by efficiently analyzing and predicting solar wind data.

[0728] The following describes the processing flow.

[0729] Step 1:

[0730] The server retrieves observational data from the API using solar data acquisition methods. This includes selecting data sources and configuring data transfer protocols. It supports real-time data streaming.

[0731] Step 2:

[0732] The server cleans the acquired data. Linear interpolation is used to fill in missing values, and statistical methods are used to remove outliers. This data cleansing ensures data consistency and reliability.

[0733] Step 3:

[0734] The server feeds the normalized data into a machine learning model for analysis. Here, a time series analysis using an LSTM network is performed to predict future solar wind trends. The results are recorded in a prediction database.

[0735] Step 4:

[0736] The server generates a three-dimensional visualization based on the analysis results. Utilizing a 3D rendering engine, it visualizes the solar wind's path and influence area, taking into account its positional relationship with the Moon and Earth.

[0737] Step 5:

[0738] The device uses the generated 3D model to provide visualization to the user. The user can use mouse or touch controls to view the behavior of the solar wind from different perspectives.

[0739] Step 6:

[0740] The server automatically collects academic papers on solar wind and creates summaries using natural language processing technology. It extracts important information and stores the summaries in a database.

[0741] Step 7:

[0742] The server generates hypotheses using generative AI based on the summarized information. When proposing new research themes, reinforcement learning is used to test these hypotheses.

[0743] Step 8:

[0744] The server runs simulations using a quantum computing platform. By performing parallel computing under complex conditions, more accurate results are obtained.

[0745] Step 9:

[0746] The server analyzes the obtained simulation results and uses them to further verify 3D models and hypotheses. These results can be used for future research and applications.

[0747] (Example 1)

[0748] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0749] Fluctuations in solar activity affect the Earth's environment and man-made objects, thus requiring highly accurate predictions. However, current technologies have fragmented processes from data acquisition and analysis to visualization, hypothesis generation, and evaluation, lacking efficient and comprehensive solutions. Furthermore, there are issues regarding how to provide the generated information to users and how to utilize it effectively.

[0750] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0751] In this invention, the server includes data acquisition means for acquiring solar physical data, information preprocessing means for preprocessing the acquired data, and prediction means having a computational model for analyzing and predicting the preprocessed data. This enables comprehensive acquisition, analysis, prediction, visualization, hypothesis generation, and evaluation of solar activity data, thereby realizing effective information provision to users.

[0752] "Solar physical data" refers to physical information obtained from the sun, including data on solar activity, radiation, wind, and magnetic fields.

[0753] "Data acquisition means" refers to methods and processes for collecting solar physical data using observation equipment and networks.

[0754] "Information preprocessing means" refers to methods that perform operations such as data cleaning, supplementation, and standardization in order to convert acquired data into an analyzable format.

[0755] A "computational model" is a mathematical model used to analyze data and make predictions, and often incorporates statistical methods and machine learning.

[0756] "Three-dimensional visualization generation means" refers to a technology and method for representing analyzed data in three dimensions and displaying it in an easily understandable visual format.

[0757] "Natural language processing" refers to a technology that mechanically analyzes and processes text data, and is used for information extraction and summary generation.

[0758] "Knowledge generation methods" are techniques for formulating new hypotheses based on collected information, and they utilize the results of data analysis.

[0759] "Computational techniques" refers to a series of technologies that enable advanced computations, and in particular, to advanced technologies such as quantum computing.

[0760] To implement this invention, a server plays a central role. The server acquires solar physical data via observation equipment connected to the internet or through external APIs. For example, a common option is to use a cloud-based data acquisition service.

[0761] The server then performs data cleaning and standardization using advanced data processing software as a preprocessing measure. This typically involves using libraries from Python or R. This allows for efficient completion of missing data and removal of outliers.

[0762] Subsequently, the server analyzes the data preprocessed by the computational model and makes predictions. For example, it uses machine learning frameworks such as TensorFlow and PyTorch to build time series analysis models such as LSTM to predict future solar wind trends.

[0763] The server further utilizes three-dimensional visualization generation methods to visualize the analysis results in three dimensions. In this process, it uses open-source graphics libraries such as Three.js and Matplotlib to generate visualizations that can be easily manipulated by the user in a web browser.

[0764] The device provides these results to the user, allowing the user to visually understand the data through an interactive interface. The device uses a front-end application developed with HTML5, CSS3, JavaScript, etc., to effectively display the visualization results visually.

[0765] In addition, the server utilizes natural language processing capabilities to collect information from relevant academic paper databases and summarize important data. To automatically generate new hypotheses from this summary information, the use of natural language processing libraries such as NLTK and the BERT model can be considered. As a concrete example of a prompt, the following message is entered into the server: "Summarize the latest astronomy papers and generate new research hypotheses."

[0766] Finally, as a computational technique, quantum computers are used to perform simulations with higher accuracy. For example, cloud-based quantum computing services can be used to perform computationally intensive simulations in a short amount of time.

[0767] This system configuration allows users to gain comprehensive insights based on actual solar wind data. By effectively coordinating the entire process from data acquisition to prediction, visualization, and result interpretation, the system improves the efficiency of researchers and engineers.

[0768] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0769] Step 1:

[0770] The server acquires solar physical data via an external API. The input requires the API endpoint and authentication credentials. The server uses this information to send an HTTP request and receives observation data in JSON format as output. Specifically, it sends a GET request with authentication using the API key.

[0771] Step 2:

[0772] The server preprocesses the acquired data. The input is the observation data in JSON format obtained in step 1. The server analyzes the data to impute missing values ​​and remove outliers, and outputs clean data in standard format. Specifically, it uses Python or R and the Pandas library to impute missing values ​​with the median and detect and remove outliers.

[0773] Step 3:

[0774] The server makes predictions using pre-processed data. The input data is the data cleaned in step 2. This is input into a machine learning model to output predictions for future solar physics data. Specifically, an LSTM model is used to train and predict time series data.

[0775] Step 4:

[0776] The server records the prediction results in a database. The input is the prediction results obtained in step 3. The server saves this to the appropriate table in the database, making it available for future analysis and visualization. Specifically, it uses MySQL or PostgreSQL and stores the prediction results using INSERT statements.

[0777] Step 5:

[0778] The server visualizes prediction data in three dimensions. The input is the prediction results stored in a database. Based on this data, the server generates three-dimensional graphics and provides a user-interactive visualization as output. Specifically, it uses Three.js and renders the results in the browser using WebGL.

[0779] Step 6:

[0780] The terminal displays visualized data to the user. The input is three-dimensional visualization data provided by the server. The terminal displays this data concretely in a browser and enables interaction with the user. Specific operations include the implementation of dynamic content using HTML5 and JavaScript.

[0781] Step 7:

[0782] The server uses natural language processing to extract information from relevant literature and generate summaries. The input is data from an academic paper database. The server extracts key information and outputs a concise summary. Specifically, it applies a text summarization algorithm based on BERT.

[0783] Step 8:

[0784] The server generates new hypotheses and evaluates their validity. The input is the summary information generated in step 7. The server evaluates the hypotheses using a reinforcement learning algorithm and presents promising research topics as output. The specific operation involves training and evaluating models using a reinforcement learning library.

[0785] (Application Example 1)

[0786] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0787] In recent years, the impact of solar wind, associated with solar activity, on Earth's energy infrastructure has attracted considerable attention. However, existing systems have struggled to accurately predict solar wind patterns and notify citizens of their impacts in real time. In particular, there is a need for immediate response measures to enable efficient urban infrastructure management and energy system operation.

[0788] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0789] In this invention, the server includes means for acquiring solar energy data, means for cleaning information, means for making predictions with a machine learning algorithm, means for generating visualizations, a natural language processing device, means for constructing hypotheses, a quantum computing device, and means for generating notifications. This makes it possible to predict the impact of solar wind on urban infrastructure in real time and immediately notify citizens.

[0790] A "solar energy data acquisition device" is a device that has the function of collecting data related to solar activity in real time.

[0791] An "information cleaning device" is a device that performs preprocessing, such as imputing missing values ​​and removing outliers, to prepare acquired data into an analyzable format.

[0792] A "predictive tool with a machine learning algorithm" is a device that uses machine learning technology to predict future solar wind trends based on collected data.

[0793] A "visualization generation means" is a device that visualizes analysis results in three dimensions and displays them in a way that users can intuitively understand.

[0794] A "natural language processing device" is a device that automatically collects literature and information, and provides concise information by summarizing it.

[0795] A "hypothesis-building tool" is a device that automatically generates new research hypotheses based on summarized information.

[0796] A "quantum computing device" is a device that can perform complex calculations at high speed in order to achieve highly accurate simulations.

[0797] A "notification generation device" is a device that notifies citizens in real time about the impacts of solar wind and proposes necessary countermeasures.

[0798] The system for realizing this invention functions as follows:

[0799] The server collects solar energy data in real time using an API. This data is then processed using information cleaning tools to impute missing values ​​and remove outliers, preparing it for analysis. Next, the server uses a machine learning algorithm (TensorFlow) to predict solar wind trends. This predicted data is then visualized in three dimensions using a visualization tool (Three.js), allowing users to understand it intuitively.

[0800] Furthermore, the server uses a natural language processing device (spaCy) to automatically collect and summarize literature from around the world. Based on the summarized information, a hypothesis-building tool generates new research hypotheses. These hypotheses are then tested using high-precision simulated computations performed by a quantum computing device.

[0801] Through online digital terminals, the server notifies citizens in real time about the impact of solar winds and proposes necessary countermeasures. This will enable more efficient management of energy systems within smart cities.

[0802] One concrete example is a system that notifies citizens 30 minutes in advance via a smartphone application about power outages expected due to solar winds. By inputting prompts such as, "Please describe the effects of solar winds and propose specific countermeasures for the smart city infrastructure in the designated area," into an AI model, it is possible to automatically suggest the most suitable response.

[0803] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0804] Step 1:

[0805] The server acquires solar energy data in real time via an API. It receives observational data on solar activity as input and generates raw data as output. This data is then retrieved for subsequent processing.

[0806] Step 2:

[0807] The server preprocesses the acquired data using information cleaning methods. It uses raw data as input, imputes missing values, removes outliers, and outputs rational data. At this stage, the data is prepared in a format suitable for analysis.

[0808] Step 3:

[0809] The server uses machine learning algorithms to analyze data and predict solar wind trends. It takes pre-processed data as input, performs time-series analysis using an LSTM model, and outputs future solar wind prediction data. This result is used in the next step.

[0810] Step 4:

[0811] The server visualizes the analysis results in three dimensions using visualization generation tools. It receives prediction data as input, generates a three-dimensional model using Three.js, and outputs it. This allows the user to interactively check the extent of the solar wind's influence.

[0812] Step 5:

[0813] The server uses a natural language processing unit (NLP) to collect relevant literature and create summaries. Using the collected literature data as input, it extracts key points through natural language processing and outputs a summary. This summary is useful for providing information concisely.

[0814] Step 6:

[0815] The server generates new research hypotheses based on summaries using hypothesis-building tools. It receives a summary text as input, constructs a new hypothesis using a generative AI model, and outputs that hypothesis. This hypothesis serves as the starting point for the research.

[0816] Step 7:

[0817] The server has a quantum computing device test the hypothesis. Using the generated hypothesis as input, it performs high-precision simulations and outputs the results verifying the validity of the hypothesis. These results are used for further research.

[0818] Step 8:

[0819] The terminal notifies the user of information regarding the impact of solar winds through a notification generation mechanism. It receives solar wind forecast data and verification results as input, generates notifications that present specific countermeasures, and outputs them to the user, thereby supporting real-time infrastructure management.

[0820] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0821] This invention is a system that combines a system that supports the acquisition, analysis, visualization, and hypothesis generation of solar data with an emotion engine that recognizes the user's emotional state, and is implemented in the following form.

[0822] Data acquisition and processing:

[0823] The server receives solar data in real time from observatories around the world. This data includes information such as solar wind speed, density, and temperature. The server cleans and formats the received data for analysis and prediction. This ensures data consistency and accuracy of analysis.

[0824] Data analysis and prediction:

[0825] The server uses machine learning models to analyze received data and predict future trends in solar wind. These models include time series analysis techniques such as LSTM, and the prediction results are used in subsequent visualization and hypothesis generation processes.

[0826] Generating three-dimensional visualizations:

[0827] The server generates a three-dimensional visualization model based on the predicted data. A 3D rendering engine is used to intuitively show the movement and extent of the solar wind's influence. The terminal provides this 3D model to the user, offering an interface that allows the user to freely change their viewpoint and observe the model.

[0828] Natural language processing and hypothesis generation:

[0829] The server collects academic papers from around the world and uses natural language processing techniques to create summaries. It then generates new research hypotheses from this summary information. Reinforcement learning algorithms are used to evaluate the validity of the generated hypotheses and provide new directions for research.

[0830] Advanced simulation and emotion recognition:

[0831] The server performs complex simulations using quantum computing technology. In addition, the system incorporates an emotion engine that recognizes the user's emotions. The terminal analyzes the user's facial expressions and tone of voice through the camera and voice interface to determine their emotional state.

[0832] The device adjusts how visualizations are displayed according to the user's emotions. For example, it uses calmer, less visually burdensome animations for stressed users, while providing detailed, interactive data displays for interested users. In this way, the system can provide flexible, user-friendly feedback and a more enriching experience.

[0833] This system aims to deepen our understanding of solar wind and stimulate researchers' curiosity and learning experiences.

[0834] The following describes the processing flow.

[0835] Step 1:

[0836] The server accesses a designated API to acquire observational data and receives solar data in real time. The data includes basic physical quantities such as solar wind speed, density, and temperature.

[0837] Step 2:

[0838] The server performs a cleaning process on the received raw data. This involves filtering outliers using statistical methods and imputing missing values. Normalization is also performed to maintain data consistency and quality.

[0839] Step 3:

[0840] The server uses the organized data to run machine learning algorithms, including LSTM models, to predict the short-term and long-term behavior of the solar wind. The prediction results are stored in a database and used to improve prediction accuracy.

[0841] Step 4:

[0842] The server generates a 3D model based on the analyzed prediction data. A 3D graphics library is used for visualization, intuitively displaying the extent and path of the solar wind's impact on Earth.

[0843] Step 5:

[0844] The device provides the user with this 3D model as an interactive visualization. The user can observe the solar wind simulation results from various angles while manipulating the viewpoint.

[0845] Step 6:

[0846] The server automatically collects the latest academic papers on solar wind from online databases. It then uses natural language processing techniques to extract key information from the collected papers and create summaries.

[0847] Step 7:

[0848] The server automatically generates new hypotheses using generative AI based on the summarized information. The validity of these hypotheses is then evaluated through a verification process using reinforcement learning.

[0849] Step 8:

[0850] The server utilizes quantum computing capabilities to perform advanced simulations. It aims to further improve prediction accuracy by conducting simulations under complex conditions at high speed.

[0851] Step 9:

[0852] The device analyzes the user's emotional state from their facial expressions and voice using an emotion engine. Based on this analysis, it dynamically adjusts the style of visualization and the level of detail of the information displayed.

[0853] Step 10:

[0854] Users experience emotion-recognition-based feedback through a flexible interface presented by the device. This allows users to receive solar wind information optimized for their own psychological state.

[0855] (Example 2)

[0856] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0857] Conventional solar data analysis systems have not adequately achieved real-time data acquisition, high-precision prediction, or automated hypothesis generation, nor have they provided interactive visualizations that respond to user emotions. Therefore, improving the efficiency of research and the user experience remains a challenge.

[0858] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0859] In this invention, the server includes means for acquiring solar data, means for cleaning data, and means for making predictions with a machine learning model. This enables real-time data acquisition, highly accurate predictions, and interactive three-dimensional visualization.

[0860] "Solar data acquisition methods" refer to technologies for collecting information about the sun in real time from observatories around the world.

[0861] "Data cleaning techniques" refer to processing technologies used to remove noise and inconsistencies from collected data and convert it into a format suitable for analysis and prediction.

[0862] "Predictive methods using machine learning models" refer to technologies that use machine learning algorithms to predict future trends based on past data.

[0863] "Visualization generation means" refers to technology for displaying analysis results in a three-dimensional shape so that they can be intuitively understood.

[0864] "Natural language processing methods" refer to technologies that process text data and enable summarization and information extraction.

[0865] "Hypothesis generation method" refers to technology that automatically generates new research hypotheses based on obtained information and summaries.

[0866] "High-performance computing means" refers to technologies that provide advanced computing power to perform complex simulations.

[0867] "Emotion recognition means" refers to technology that analyzes a user's facial expressions and voice to recognize their emotional state.

[0868] "Display means" refers to technologies that provide users with visualized data and enable them to interact with it.

[0869] "Evaluation methods" refer to techniques that utilize reinforcement learning algorithms to evaluate the effectiveness and novelty of generated hypotheses.

[0870] In this invention, the server acquires solar data from an observatory and removes noise from the received data using data cleaning means. Specifically, it utilizes data processing tools such as the Pandas library to prepare formatted data.

[0871] Next, the server runs machine learning models using TensorFlow and Keras, and performs time series analysis using LSTM (Long Short-Term Memory Network) to predict future trends in solar wind.

[0872] The predicted data is visualized in three dimensions using a 3D rendering engine such as Blender. This 3D model is provided to the user via their device, allowing them to intuitively observe the movement and extent of the solar wind's influence while freely changing their viewpoint using a browser-based interface.

[0873] The server also collects academic papers via the Google Scholar API and generates summaries of those papers using natural language processing technology. Furthermore, it uses a generative AI model (e.g., GPT-4) to formulate new research hypotheses from the summaries and evaluates those hypotheses using a reinforcement learning algorithm.

[0874] The system also performs complex simulations using high-performance computing capabilities. In addition, the device recognizes the user's emotions through its camera and microphone, and adjusts the visualization method based on the results analyzed by the emotion recognition system. If the system determines that the user is experiencing stress, it uses gentle animations to reduce visual strain.

[0875] As an example, the effects of the Earth's magnetic field over the next week may be simulated and displayed in a 3D model. If the user shows interest, a detailed and interactive model will be provided, allowing the user to perform further analysis using this data.

[0876] An example of a prompt message could be: "Analyze solar wind data and generate a model to visualize the effects of the Earth's magnetic field next week." The system will then perform the appropriate data processing and visualization in response to such prompts.

[0877] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0878] Step 1:

[0879] The server acquires solar data in real time from observatories in various locations. It receives data such as solar wind speed, density, and temperature as input, and then performs noise reduction and missing value imputation using data cleaning methods. The output is a consistent and clean dataset.

[0880] Step 2:

[0881] The server runs an LSTM machine learning model using the clean data obtained in Step 1. Specifically, it performs time series analysis using TensorFlow or Keras to predict future solar wind trends. The input is a formatted dataset, and the output is predicted solar wind trend data.

[0882] Step 3:

[0883] The server processes predicted trend data using a 3D rendering engine such as Blender to generate a three-dimensional visualization model. The input is predicted data, and the output is a three-dimensional model that allows the user to observe the visualization data from various perspectives. The terminal provides this model to the user and displays it through an intuitive interface.

[0884] Step 4:

[0885] The server retrieves academic papers from around the world using natural language processing tools and summarizes the information. Specifically, it uses an API to input paper data and generates summaries using NLTK and spaCy. The output is summarized paper information, which is then used by a generative AI model to generate new research hypotheses.

[0886] Step 5:

[0887] The server applies a reinforcement learning algorithm to evaluate the validity of hypotheses formulated by the generative AI model. The input is hypothesis information, and the output is a list of evaluated hypotheses. Based on this, new directions for research can be suggested.

[0888] Step 6:

[0889] The device collects the user's facial expressions and voice through its camera and microphone, and analyzes their emotional state using an emotion recognition API. The input is the user's facial expressions and voice data, and the output is the result of the emotional state analysis. Based on these results, the device adjusts the 3D visualization display mode to provide the user with a relaxing environment.

[0890] (Application Example 2)

[0891] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0892] The problem this invention aims to solve is to provide information tailored to the user's emotions through the analysis and visualization of solar wind data, thereby offering an intuitive and user-friendly learning experience. In particular, it aims to facilitate understanding of cosmic phenomena and streamline the acquisition of scientific knowledge by displaying appropriate information according to the user's interests and stress levels.

[0893] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0894] In this invention, the server includes means for acquiring solar data, means for cleaning data, means for prediction using a machine learning model, means for visualizing and generating analysis results in three dimensions, means for natural language processing for collecting and summarizing papers, means for generating new hypotheses, means for high-precision simulation using quantum computing, means for recognizing the user's emotional state, and means for interactively providing information. This enables real-time analysis of information related to solar wind and flexible information provision according to the user's emotional state.

[0895] The "solar data acquisition method" is a function that collects data on solar wind in real time from observatories in various locations.

[0896] "Data cleaning methods" are functions that process data to remove noise and outliers in order to prepare the acquired data for analysis and prediction.

[0897] "Prediction methods using machine learning models" refers to a function that uses machine learning technology to analyze future trends in solar wind and provide prediction results.

[0898] A "visualization generation method" is a function that visually represents the analyzed data as a three-dimensional model, making it intuitively understandable to the user.

[0899] "Natural language processing methods" refer to technologies used to analyze collected academic papers and text data and create summaries.

[0900] A "hypothesis generation tool" is a function that carries out the process of creating new research hypotheses based on the generated summaries.

[0901] "High-precision simulation methods using quantum computing" refers to a function that accurately simulates complex astronomical phenomena using quantum computing technology.

[0902] "Emotion recognition means" refers to a function that analyzes the user's facial expressions and tone of voice to determine their current emotional state and adjust the way information is displayed accordingly.

[0903] An "interface means" is a means for interactive communication between a user and a system, and is a function that provides information through visual and auditory means.

[0904] This invention constructs a system that performs real-time data analysis on solar wind and provides scientific information tailored to the user's emotional state. The server first receives solar data from an observatory, removes noise and outliers using data cleaning means, and then performs predictions using a machine learning model. This prediction employs time series analysis methods such as LSTM using TensorFlow.

[0905] Next, based on the analyzed data, the visualization generation system uses the Unity3D engine to generate a three-dimensional model. Through this model, it is possible to intuitively display the movement and affected area of ​​the solar wind.

[0906] Furthermore, the server collects papers and uses natural language processing to create summaries. From the generated summaries, a hypothesis generation tool uses a reinforcement learning algorithm to create and propose new research hypotheses.

[0907] This system incorporates emotion recognition technology that analyzes facial expressions and voice tone through the user's camera and microphone. This allows the interface to adjust its display content according to the user's emotional state, providing content tailored to their interests and stress levels. For example, it can provide calming animations to stressed users and interactively display detailed data to curious users.

[0908] As a concrete example, a scenario could be envisioned where a user observes changes in the movement of the solar wind through this system during a solar eclipse, deepening their scientific understanding. An example of a prompt in this scenario would be: "Please tell me how I can learn about the movement of the solar wind in an interesting and real-time way. It's sunny right now, so I'm feeling motivated."

[0909] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0910] Step 1:

[0911] The server acquires solar data in real time from observatories. This is a process of receiving solar wind data transmitted from various locations, using information such as solar wind speed, density, and temperature as input. In this step, data is received and recorded in a database for subsequent processing.

[0912] Step 2:

[0913] The server performs data cleaning on the received data. The input is the raw data obtained in step 1, and noise reduction and correction of outliers are performed. The output is the cleaned and formatted data, which enables highly accurate analysis. The Python Pandas library is used for data cleaning.

[0914] Step 3:

[0915] The server performs data analysis and prediction using a machine learning model. The pre-processed data obtained in step 2 is used as input. An LSTM model is used to predict future solar wind trends and output the prediction results. TensorFlow is used for the analysis, and the results are stored in a database.

[0916] Step 4:

[0917] The server generates a three-dimensional visualization model based on the analysis results. The input is the prediction results from step 3, and the Unity3D engine is used to render the movement and affected area of ​​the solar wind in three dimensions. The output is a 3D model that the user can freely observe by changing the viewpoint.

[0918] Step 5:

[0919] The server collects academic papers and generates summaries using natural language processing (NLP). The input consists of relevant papers found on the internet. The NLP algorithm generates the summaries, which are then output as data for proposing new hypotheses.

[0920] Step 6:

[0921] The server generates hypotheses based on the summarized data. Reinforcement learning algorithms are used to train predictive models and generate new hypotheses. The output is a list of hypotheses, which can be useful for further scientific research.

[0922] Step 7:

[0923] The device receives a photo of the user's face and voice input, and uses an emotion recognition engine to determine their emotional state. Input is data collected from the camera and microphone. Output is the user's emotional state (e.g., interesting, stressed). The algorithm uses OpenCV and the Google Cloud Speech API.

[0924] Step 8:

[0925] The device adjusts its display based on the emotion data from step 7. The inputs are the user's emotional state and the 3D model from step 4. The output is a customized information display tailored to the specific emotion. For example, if the emotion is deemed interesting, an interactive data display will occur.

[0926] The input, data processing, and output at each processing step are clearly defined, and the entire system provides an intuitive science learning experience that engages the user.

[0927] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0928] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0929] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[0930] Furthermore, the emotion identification model 59, acting as an emotion engine, may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0931] Figure 9 shows an emotion map 400 in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0932] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0933] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0934] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, motorcycles, etc., emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0935] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0936] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0937] The above description primarily focuses on the functions of the data processing device 12 in relation to this disclosure. However, the system related to this disclosure is not necessarily implemented on a server. The system related to this disclosure may be implemented as a general information processing system. This disclosure may be implemented, for example, as a software program that runs on a personal computer or as an application that runs on a smartphone. The method related to this disclosure may be provided to users in SaaS (Software as a Service) format.

[0938] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing of the specific process may be performed by multiple computers, including computer 22. For example, a data generation model 58 may be provided in an external device of the data processing device 12, and the external device may generate data according to the input data.

[0939] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0940] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[0941] Furthermore, it is not necessary to store the entirety of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0942] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0943] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0944] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0945] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0946] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and the like that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0947] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0948] The following is further disclosed regarding the embodiments described above.

[0949] (Claim 1)

[0950] Methods for acquiring solar data,

[0951] A data cleaning means for preprocessing the obtained data,

[0952] A prediction means having a machine learning model for data analysis and prediction,

[0953] A visualization generation method for visualizing analysis results in three dimensions,

[0954] A natural language processing method for collecting and summarizing papers,

[0955] A hypothesis generation means for generating new hypotheses based on the generated summary,

[0956] Quantum computing means for achieving high-precision simulations,

[0957] A system that includes this.

[0958] (Claim 2)

[0959] The system according to claim 1, further comprising display means for providing a three-dimensional visualization to a user.

[0960] (Claim 3)

[0961] The system according to claim 1, further comprising an evaluation means for evaluating the effectiveness of a hypothesis using a reinforcement learning algorithm.

[0962] "Example 1"

[0963] (Claim 1)

[0964] A data acquisition method for obtaining solar physical data,

[0965] Information preprocessing means for preprocessing acquired data,

[0966] Prediction means having a computational model for analyzing and predicting preprocessed data,

[0967] A three-dimensional visualization generation means for representing the analysis results in three dimensions,

[0968] Information processing means equipped with natural language processing capabilities for collecting and summarizing texts,

[0969] A knowledge generation method for generating new hypotheses based on the generated summary,

[0970] Computational techniques and means for achieving high-precision simulations,

[0971] A system that includes this.

[0972] (Claim 2)

[0973] The system according to claim 1, further comprising visual display means for providing visualized information to a user.

[0974] (Claim 3)

[0975] The system according to claim 1, further comprising a hypothesis evaluation means for evaluating the effectiveness of a hypothesis using a reinforcement learning method.

[0976] "Application Example 1"

[0977] (Claim 1)

[0978] Methods for acquiring solar energy data,

[0979] Information cleaning means for preprocessing the obtained information,

[0980] An inference method having a machine learning algorithm for analyzing and predicting data,

[0981] A visualization generation means for creating a three-dimensional image of the analysis results,

[0982] A natural language processing device for collecting and summarizing literature,

[0983] A hypothesis-building method for generating new hypotheses based on the generated outline,

[0984] A quantum computing device for realizing highly accurate simulated calculations,

[0985] A notification generation method for distributing information about the effects of solar wind as a warning on digital devices,

[0986] A system that includes this.

[0987] (Claim 2)

[0988] The system according to claim 1, further comprising a presentation device for providing a three-dimensional image to a user.

[0989] (Claim 3)

[0990] The system according to claim 1, further comprising a means for verifying the effectiveness of a hypothesis using a reinforcement learning algorithm.

[0991] "Example 2 of combining an emotion engine"

[0992] (Claim 1)

[0993] Methods for acquiring solar data,

[0994] A data cleaning means for preprocessing the obtained data,

[0995] A prediction means having a machine learning model for data analysis and prediction,

[0996] A visualization generation method for visualizing analysis results in three dimensions,

[0997] A natural language processing method for collecting and summarizing papers,

[0998] A hypothesis generation means for generating new hypotheses based on the generated summary,

[0999] High-performance computing means for achieving highly accurate simulations,

[1000] A means of recognizing the emotional state of a user,

[1001] A system that includes this.

[1002] (Claim 2)

[1003] The system according to claim 1, further comprising display means for providing a three-dimensional visualization to a user.

[1004] (Claim 3)

[1005] The system according to claim 1, further comprising an evaluation means for evaluating the effectiveness of a hypothesis using a reinforcement learning algorithm.

[1006] "Application example 2 when combining with an emotional engine"

[1007] (Claim 1)

[1008] Methods for acquiring solar data,

[1009] A data cleaning means for preprocessing the obtained data,

[1010] A prediction means having a machine learning model for data analysis and prediction,

[1011] A visualization generation method for visualizing analysis results in three dimensions,

[1012] A natural language processing method for collecting and summarizing papers,

[1013] A hypothesis generation means for generating new hypotheses based on the generated summary,

[1014] Quantum computing means for achieving high-precision simulations,

[1015] A means for recognizing emotions to determine the user's emotional state and adjust the displayed content,

[1016] An interface means for providing information interactively via a user terminal,

[1017] A system that includes this.

[1018] (Claim 2)

[1019] The system according to claim 1, further comprising display means for providing a three-dimensional visualization to a user.

[1020] (Claim 3)

[1021] The system according to claim 1, further comprising an evaluation means for evaluating the effectiveness of a hypothesis using a reinforcement learning algorithm. [Explanation of Symbols]

[1022] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. Methods for acquiring solar energy data, Information cleaning means for preprocessing the obtained information, An inference method having a machine learning algorithm for analyzing and predicting data, A visualization generation means for creating a three-dimensional image of the analysis results, A natural language processing device for collecting and summarizing literature, A hypothesis-building method for generating new hypotheses based on the generated outline, A quantum computing device for realizing highly accurate simulated calculations, A notification generation method for distributing information about the effects of solar wind as a warning on digital devices, A system that includes this.

2. The system according to claim 1, further comprising a presentation device for providing a three-dimensional image to a user.

3. The system according to claim 1, further comprising a means for verifying the effectiveness of a hypothesis using a reinforcement learning algorithm.

Images