system

Abstract

Provide a system. 【Solution means】 The first means of proposing an optimal calculation model, The second means of performing parameter setting based on the proposed calculation model, The third means of converting the specified calculation code into a form executable by a high-performance computing device, The fourth means of managing the use of resources in a planned manner, The fifth means of performing analysis on a high-performance computing device, The sixth means of verifying the consistency of the analysis results, The seventh means of collecting and analyzing traffic information and energy consumption information in the urban environment, The eighth means of providing the analysis results to users through a 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 character of the chatbot, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance in response to the user utterance.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] Calculations using supercomputers play an important role in scientific research and industrial fields. However, their use requires specialized knowledge and it is difficult for ordinary users to use them easily. Also, the series of processes from the selection of a calculation model, parameter setting, to the verification of results is complex, and efficient execution is required. The present invention aims to solve these problems and provide an environment in which anyone can easily utilize the computing power of a supercomputer.

Means for Solving the Problems

[0005] The present invention provides a first means for proposing an optimal computational model, a second means for setting parameters based on the proposed computational model, a third means for converting a specified computational code into a format executable on a supercomputer, a fourth means for systematically managing resource usage, a fifth means for executing a simulation on a supercomputer, and a sixth means for verifying the consistency of the simulation results. This enables users to perform efficient and precise calculations without specialized knowledge.

[0006] A "computational model" is a mathematical or algorithmic framework designed for a specific computational purpose.

[0007] "Parameter setting" is the process of determining the variables and conditions necessary for a computational model to operate accurately and efficiently.

[0008] A "supercomputer" is a computing system capable of performing large-scale and complex calculations at high speed.

[0009] "Conversion" is the process of changing data or code from one format to another.

[0010] "Resource management" is the process of efficiently using computing resources and making adjustments as needed.

[0011] "Simulation" is a computational method that reproduces real-world processes and systems to perform predictions and analyses.

[0012] "Consistency verification" is the process of confirming that the obtained results are accurate and reliably consistent with other data and conditions. [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]It is a conceptual diagram showing an example of the main functions of a data processing device and a smart device according to the first embodiment. [Figure 3] It is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] It 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] It is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] It 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] It is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] It is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] It shows an emotion map to which a plurality of emotions are mapped. [Figure 10] It shows an emotion map to which a plurality of emotions are mapped. [Figure 11] It is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] It is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] It is a sequence diagram showing the processing flow of the data processing system in Example 2 when an emotion engine is combined. [Figure 14] It is a sequence diagram showing the processing flow of the data processing system in Application Example 2 when an emotion engine is combined.

Embodiments 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, the numbered processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Also, the processor may be a single type of arithmetic unit or a combination of multiple 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, the numbered RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0018] In the following embodiments, the numbered storage 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, etc.

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

[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 provides a system that allows users to easily utilize the computing power of supercomputers. This system automates a series of processes, from selecting a computational model to verifying the results, by utilizing multiple AI agents. Specific embodiments of this system are described below.

[0035] First, users access the computing system through a terminal and input the purpose of the calculation and the dataset. This data can be used for a wide range of purposes, including scientific research, new drug development, and engineering analysis.

[0036] Based on this input data, the server launches a model selection agent. The model selection agent consults a database of available mathematical models and algorithms and automatically selects the model best suited to the user's purpose. The selected model is then presented to the user via the terminal.

[0037] Next, the server uses a parameter tuning agent to calculate the optimal parameters for the selected model. This parameter tuning is crucial for improving the accuracy and efficiency of the calculations, and the agent's automated estimation allows even users without specialized knowledge to start calculations under optimal conditions.

[0038] Subsequently, based on the computational model and parameters, the server activates a supercomputer conversion agent. This agent converts the user's input code and data into a format that can be efficiently executed on a supercomputer. This conversion process involves parallelization and memory optimization.

[0039] As a concrete example, consider molecular simulations used to predict drug efficacy in new drug development. The user simply inputs information about the molecule to be simulated, and the system automatically selects the optimal molecular model, sets appropriate temperature and pressure parameters, and converts the data into a format suitable for a supercomputer.

[0040] This allows users to fully utilize the computing power of a high-performance supercomputer without requiring specialized programming or simulation knowledge. Finally, the system can verify the calculation results and present them to the user in an easy-to-understand visual format. It can also provide feedback tailored to the user's objectives, enabling rapid incorporation into further research and development.

[0041] The following describes the processing flow.

[0042] Step 1:

[0043] The user accesses the system using a terminal and inputs the information and datasets necessary for the calculation. This includes specifying, for example, molecular structure information and the purpose of the simulation.

[0044] Step 2:

[0045] The server launches a model selection agent based on the input information. This agent searches the database for appropriate computational models and algorithms and presents the best option for the user's purpose.

[0046] Step 3:

[0047] The user reviews the presented model and, if necessary, enters additional conditions or requests via the terminal. This input allows the system to configure a more specific model to meet the user's needs.

[0048] Step 4:

[0049] The server uses a parameter tuning agent to set the optimal parameters for the selected model. This agent automatically calculates the parameters based on the model's characteristics and input data.

[0050] Step 5:

[0051] The server activates a supercomputer conversion agent and performs code conversion based on the model and parameters. This process optimizes the user's input code for supercomputers and converts it into a format that can be computed in parallel.

[0052] Step 6:

[0053] The server checks the available computing resources in the scheduling agent and determines the optimal timing for execution. This agent compares and allocates resources efficiently compared to other computing tasks.

[0054] Step 7:

[0055] The server initiates calculations on the supercomputer, and the simulation agent processes the data. The system ensures stability by saving the ongoing data as needed.

[0056] Step 8:

[0057] The server transfers the simulation results to the verification agent for consistency checks. This process verifies the accuracy of the results.

[0058] Step 9:

[0059] The device displays verified results to the user, presenting the data in an easy-to-understand visual format. The user can review the details and, if necessary, be instructed to take the next steps.

[0060] (Example 1)

[0061] 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."

[0062] In fields requiring complex calculations and simulations, a problem exists in that users without specialized knowledge find it difficult to fully utilize the capabilities of high-performance computers. Traditional methods require a specialized understanding of mathematical models, computational parameter selection, and code optimization, which is considered a high hurdle for users. As a result, there are many cases where high-performance computing resources are not effectively utilized.

[0063] 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.

[0064] In this invention, the server includes means for proposing an optimal mathematical model based on the purpose entered by the user, means for automatically adjusting parameters based on the selected mathematical model, and means for converting the input code into an optimized format executable on the computer. This allows the user to make full use of the capabilities of a high-performance computer without specialized knowledge.

[0065] A "mathematical model" is an abstract theoretical framework that expresses real-world phenomena using mathematical methods, making them analyzable through calculations and simulations.

[0066] A "parameter" is a variable in a mathematical model or algorithm that sets specific conditions or characteristics and affects the calculation results or the behavior of the simulation.

[0067] An "input code" is a program description that outlines the instructions to be given to a computer, and it represents a set of calculation procedures.

[0068] A "computer" is a physical or virtual machine used to process data and perform calculations and analyses, and generally includes a processor and memory.

[0069] "Optimization" is the process of adjusting available resources and conditions to the best possible state in order to improve the performance of a system or process.

[0070] A "user" is an entity that operates a system or software and utilizes its functions to achieve a specific purpose.

[0071] "Visualization" is a technique that presents information in an easily understandable way to users by representing calculation results and data in the form of graphs, diagrams, and other visual representations.

[0072] "Efficient" refers to a state in which the greatest results can be obtained with the fewest resources, or a method for achieving such a state.

[0073] This invention is a system for users to perform complex calculations using high-performance computers, and is designed to facilitate large-scale data processing and analysis by utilizing supercomputers. The central element of the system is multiple agents, each operated by a server, which cooperate to automate the selection of computational models, parameter adjustment, and code conversion.

[0074] Users access the interface using a terminal and input calculation objectives and required data into the system using prompt messages. It is recommended that these prompt messages clearly state specific needs. For example, by entering a prompt message such as "I would like to perform a simulation using the following molecular information for new drug development," the system will select the most suitable mathematical model for that purpose and prepare to begin the necessary calculations.

[0075] The server uses configured software to analyze the input data and select the most suitable mathematical model from the database to meet the user's requirements. This process is streamlined by utilizing generative AI models, ensuring highly accurate selection by referencing similar past cases and the latest algorithms.

[0076] Parameter tuning for the selected mathematical model is performed by a dedicated agent on the server, automatically making the necessary configuration changes to maximize computational accuracy and efficiency. This allows users to continue calculations under optimized conditions without requiring any manual adjustments.

[0077] Furthermore, the server converts the user-provided input code, preparing it for execution on a supercomputer. This conversion process includes parallelization and optimization of memory usage, enabling rapid computation even for large datasets.

[0078] This invention enables users to utilize a high-performance computing environment without specialized knowledge, thereby saving considerable time and effort while obtaining accurate and rapid simulation results.

[0079] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0080] Step 1:

[0081] The user accesses the computing system using a terminal and inputs specific calculation objectives and data through prompts. The input data includes, for example, molecular information necessary for new drug development. Based on this information, the user requests a calculation task from the system. The user's input is sent to the server, and processing begins.

[0082] Step 2:

[0083] The server analyzes the received input data and selects the optimal mathematical model using a generated AI model. During this process, the server refers to an internal model database and automatically selects the model best suited to the user's computational objectives. The selected mathematical model, resulting from the data analysis, is then output.

[0084] Step 3:

[0085] The server activates a parameter tuning agent based on the selected mathematical model. The agent automatically calculates appropriate parameters according to the input data and model requirements. For example, in molecular simulations, temperature and pressure parameters are set. This tuning ensures the model achieves maximum accuracy and performance. The tuned parameters are then output for the next process.

[0086] Step 4:

[0087] The server activates a supercomputer conversion agent based on parameters and mathematical models. This agent converts the input code into a format that can run efficiently on a supercomputer. This process involves parallelization and memory optimization of the code. The converted executable code is output, ready for execution on the supercomputer.

[0088] Step 5:

[0089] The server sends the prepared executable code to the supercomputer and starts the calculation. The server monitors the progress of the calculation and manages resources as needed. Once the calculation is complete, the results are returned to the server.

[0090] Step 6:

[0091] The server analyzes the calculation results and verifies their accuracy through a results verification agent. The analysis results are then visualized and presented to the user via a terminal. The user reviews the results based on the provided visual information and provides feedback as needed. This feedback is then incorporated into the system's next processing cycle.

[0092] (Application Example 1)

[0093] 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."

[0094] The challenge lies in performing real-time analysis of complex traffic and energy consumption data in urban environments to enable efficient and appropriate responses. Conventional systems require enormous computing power, making it difficult to select appropriate models and set parameters without specialized knowledge, thus hindering real-time analysis. This results in problems such as the inability to respond quickly to sudden traffic congestion or peak energy consumption.

[0095] 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.

[0096] In this invention, the server includes means for proposing an optimal computational model, means for collecting and analyzing traffic information and energy consumption information within the urban environment, and means for providing the analysis results to the user via a terminal. This enables real-time analysis of complex urban environment data and supports efficient infrastructure operation.

[0097] "The primary method for proposing the optimal computational model" refers to a technology that automatically presents the best computational model for problem solving using an algorithm that selects an appropriate mathematical model based on the user's input information.

[0098] "A second method for setting parameters based on the proposed computational model" refers to an automated estimation technique for setting optimal parameters for the selected model and improving the accuracy and efficiency of the calculations.

[0099] "A third method for converting specified computational code into a format executable on high-performance computing devices" refers to a technology that performs conversion, including parallelization and memory management, in order to efficiently execute input code or data on high-performance computing devices.

[0100] The "fourth means of systematically managing resource usage" refers to management techniques for efficiently allocating computing resources and performing necessary calculations while maintaining optimal performance.

[0101] The "fifth method of performing analysis on a high-performance computing device" is a technique that uses the converted code to perform data analysis on a device with advanced computing capabilities.

[0102] The "sixth method for verifying the consistency of analysis results" refers to verification techniques for confirming that the obtained analysis results are accurate and consistent.

[0103] The "seventh method for collecting and analyzing traffic and energy consumption information within urban environments" refers to a technology that monitors traffic and energy usage in cities, analyzes this information, and derives patterns.

[0104] The "eighth method of providing analysis results to users via a terminal" is a technology that visually organizes the analyzed information in an easy-to-understand manner and provides it to users via their terminals.

[0105] In the system implementing this invention, the server first receives urban environment-related data entered by the user. This data includes traffic information and energy consumption information. Based on this input data, the server executes a program to select the optimal mathematical model. In this process, cloud AI platforms such as Azure® Machine Learning and Amazon SageMaker are used to select the mathematical model.

[0106] After selecting a mathematical model, the server optimizes the parameters on the cloud platform and converts the code for execution on a supercomputer. This conversion process optimizes parallel processing and memory management, generating code that runs efficiently on high-performance computing devices.

[0107] Furthermore, the server uses the generated analysis algorithms to predict traffic congestion and detect peak energy consumption in real time. These results are then presented to the user's device in an easily understandable visual format. The device displays the analysis results in the form of charts and graphs, providing a convenient interface for everyday use.

[0108] A concrete example would be a scenario where a server monitors road congestion in a city and suggests the most suitable alternative route to the user. It could also suggest the best time to use air conditioning on hot days. Through such systems, we aim to improve the efficiency and comfort of urban life.

[0109] An example of a prompt to input into a generative AI model might be: "Using one week's worth of urban traffic data and weather forecasts, predict traffic congestion for the coming weekend."

[0110] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0111] Step 1:

[0112] Users input urban environmental data, such as traffic information and energy consumption data, into the server via their terminals. This data forms the basis for the analysis process across the entire system. The server receives this data and stores it in a database.

[0113] Step 2:

[0114] The server sends the received data to a cloud AI platform, which selects the optimal mathematical model. In this process, the generated AI model chooses algorithms suitable for traffic congestion prediction and energy consumption analysis. This enables the selection of the optimal model according to the user's requirements. The input is urban environment data, and the output is the selected mathematical model.

[0115] Step 3:

[0116] The server sets the model parameters based on the selected mathematical model. In this step, it receives the selected model data as input and calculates the optimized parameters. This output is saved for use in the next analysis step. This is done efficiently by utilizing the automated optimization function of the cloud AI platform.

[0117] Step 4:

[0118] The server uses the constructed mathematical model and parameters to convert the user-specified computation code into a format executable on a high-performance computer. The input consists of the mathematical model, parameters, and computation code, while the output is the converted code that can be executed on the computer. The conversion is performed with parallel processing optimization in mind.

[0119] Step 5:

[0120] Using the converted code, the server performs analysis on a high-performance computing device. Here, the data for analysis is real-time urban environmental information, and the output consists of prediction results and analysis results.

[0121] Step 6:

[0122] The server verifies the consistency of the obtained analysis results. This involves a process that uses data validation algorithms to ensure the accuracy and consistency of the results. The input to this step is the analysis results, and the output is the validated data.

[0123] Step 7:

[0124] Finally, the server sends the verified analysis results to the user's terminal. The terminal displays these results visually, providing information in an easy-to-understand format for the user. Examples of analysis results provided include traffic congestion predictions and power consumption advice.

[0125] 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.

[0126] This invention provides a system that enables a wide range of users to utilize the computing power of supercomputers, and is particularly characterized by its combination with an emotion engine that recognizes user emotions and optimizes the system's behavior based on that emotion information. This system utilizes multiple AI agents and the emotion engine to perform tasks from selecting a computational model to verifying the results. The following describes a specific embodiment of this system.

[0127] First, the user accesses the system via a terminal and registers the calculation project they wish to run. During this process, the emotion engine recognizes the user's emotional state by analyzing their facial expressions and voice tone. This emotional information is then used to adjust the overall operation of the system.

[0128] The server activates a model selection agent based on data received from the user. The emotion engine reflects the user's expectations and stress levels and selects a computational model appropriate to the user's emotions. This process allows for adjustments, such as selecting a more robust model if the user is feeling anxious.

[0129] Next, the server uses a parameter tuning agent to set the optimal parameters for the selected model. Based on the information from the emotion engine, the visualization and presentation methods are also adjusted to support the user's intuitive understanding.

[0130] Subsequently, the supercomputer conversion agent operates, transforming the given model and parameters into a format that can be efficiently executed on a supercomputer. Even during this conversion process, the emotion engine flexibly modifies the conversion method according to user requests.

[0131] As a concrete example, consider a case where a user performs a predictive simulation for a new product. If the emotion engine determines that the user's level of tension is high, the system will select a conservative model that reduces risk in the model selection process and operate in a way that presents the calculation results in a stable manner.

[0132] Finally, after the simulation is complete, the server checks the results using a consistency verification agent. The terminal then displays the results in a visually easy-to-understand format, providing further insights by adding explanations that are sensitive to the user's emotions.

[0133] In this way, by combining it with an emotion engine, we can provide a user experience different from conventional systems and support the effective use of computation.

[0134] The following describes the processing flow.

[0135] Step 1:

[0136] Users access the system using a terminal and input information about the calculation project they wish to undertake. Along with the calculation data, they provide facial expressions and voice tone via camera and microphone.

[0137] Step 2:

[0138] The device sends the collected user emotion data to an emotion engine, which analyzes the user's emotional state. The emotion engine determines whether the user is stressed, relaxed, or otherwise.

[0139] Step 3:

[0140] Based on information from the emotion engine, the server activates a model selection agent to select a computational model appropriate to the user's emotions. For example, if the user is feeling anxious, it will prioritize suggesting a model that emphasizes reliability.

[0141] Step 4:

[0142] Users review the proposed model and input modifications or additional conditions as needed. This feedback is also interpreted by the emotion engine, leading to further adjustments.

[0143] Step 5:

[0144] The server uses a parameter tuning agent to set parameters for the selected model. Based on instructions from the emotion engine, the settings are configured in a way that is intuitively easy for the user to understand.

[0145] Step 6:

[0146] The server activates the supercomputer transformation agent, which converts the parameterized model into code for execution on a supercomputer. During the transformation process, it adjusts the flexibility and efficiency of the transformation based on information from the emotion engine.

[0147] Step 7:

[0148] The server uses a scheduling agent to optimize the timing and resources of calculations and to create an execution plan. It can also leverage sentiment data to adjust priorities.

[0149] Step 8:

[0150] The server starts the simulation on the supercomputer and performs the computational tasks. Data in progress is periodically saved to ensure the stability of the computation.

[0151] Step 9:

[0152] After the simulation is complete, the server verifies the consistency of the results with a validation agent and prepares to provide reliable results.

[0153] Step 10:

[0154] The device visually presents the verified results to the user, adding explanations based on the sentiment engine's judgment. This makes it easier for the user to understand the results and decide on the next action.

[0155] (Example 2)

[0156] 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 will be referred to as the "terminal."

[0157] There is a problem in that it is difficult for ordinary users to intuitively utilize high-performance computers such as supercomputers, and it is also difficult to effectively understand the results. Furthermore, conventional systems do not take into account the user's psychological state, so the operation and display of results may not match the user's expectations or understanding.

[0158] 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.

[0159] In this invention, the server includes means for analyzing the user's emotional state and adjusting the operation of the entire system, means for selecting an appropriate computational model using an emotion engine based on the analyzed emotional information, and means for setting optimal parameters for the selected computational model. As a result, the appropriate computational model and parameters are automatically selected and applied according to the user's emotional state, enabling a more user-friendly and effective understanding of the computational results.

[0160] "User emotional state" refers to the psychological or emotional state of the user as recognized by the system from the user's facial expressions, voice tone, etc.

[0161] An "emotion engine" refers to a technology that analyzes the user's emotional state and uses that information to optimize the overall operation of the system.

[0162] A "computational model" refers to a set of procedures or algorithms prepared to perform a specific computational task.

[0163] "Parameter setting" refers to the process of determining the specific numerical values ​​and settings used in the calculation model.

[0164] A "supercomputer" refers to a high-performance computer capable of performing large-scale and complex calculations at high speed.

[0165] "Visually displaying" refers to presenting information on a screen in a graphical format in order to help users understand the information.

[0166] A "consistency verification agent" refers to an automated software process used to check whether calculation results are accurate.

[0167] A "generative AI model" refers to a set of algorithms that are generated using artificial intelligence technology and perform specific information processing or data analysis.

[0168] The system in this invention is designed around the user, terminal, and server, and is intended to recognize the user's emotional state and use that to efficiently carry out computational projects.

[0169] Users access the system using a terminal to carry out computational projects. The terminal is equipped with a camera and microphone, which capture the user's facial expressions and voice tone. This data is sent to a server for later analysis by an emotion engine.

[0170] The server receives this data and uses a generative AI model to analyze the user's emotional state. For example, if the system recognizes that the user is feeling anxious, this emotional information is reflected in the selection of a computational model, ensuring that a robust model is chosen. The emotion engine plays a crucial role in this process, optimizing the overall system operation.

[0171] The selected computational model has its optimal parameters set using a parameter tuning agent. This model is then transformed by a supercomputer conversion agent into a format suitable for execution on a supercomputer. A supercomputer is a high-performance computer capable of processing large-scale and complex calculations at high speed.

[0172] The device displays the final calculation results in a visually easy-to-understand format for the user. Based on information obtained from the emotion engine, explanations are added to the results to make them easier for the user to understand. This allows the user to intuitively grasp the results and use them to aid in decision-making.

[0173] A concrete example is a market forecast simulation for a new product. An example of a prompt message might be, "Perform a market forecast simulation for the new product and select a method for presenting the results based on user sentiment."

[0174] This system aims to make the execution of computational projects more flexible and user-friendly by taking user emotions into consideration.

[0175] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0176] Step 1:

[0177] Users register their calculation projects with the system using a terminal. They enter details of the project they want to run and upload the necessary data. This information includes the calculation type, purpose, and associated datasets. Once this information is sent to the server, the project is initially configured.

[0178] Step 2:

[0179] The device collects the user's facial expressions and voice tone using its camera and microphone. This data is used as input to infer the user's emotional state. The device then transfers this information to a server for preprocessing of emotion analysis.

[0180] Step 3:

[0181] The server inputs the received facial expression and voice data into a generating AI model. This model analyzes the user's emotional state, specifically identifying emotions such as joy, surprise, and anxiety. The output provides the type and intensity of the emotion. This result is used to select a subsequent computational model.

[0182] Step 4:

[0183] The server selects an appropriate computational model by referencing the emotion engine. The user's emotional state significantly influences this selection process. For example, if the user is showing anxiety, a robust model will be chosen to ensure stable results. The results of this model selection are reflected in the parameter tuning in the next step.

[0184] Step 5:

[0185] The server sets parameters for the selected computational model. Based on the input from the emotion engine, the parameters are adjusted to produce results that are easy to understand intuitively. The adjusted parameters are output as the specific execution specifications for the model.

[0186] Step 6:

[0187] On the server, the adjusted model and parameters are converted into a format executable by the supercomputer. A supercomputer conversion agent handles this conversion, optimizing parallel processing. The converted code is generated as the final output and sent to the supercomputer.

[0188] Step 7:

[0189] The server initiates computation on the supercomputer. Once the computation is complete, the resulting data is generated. This data is checked by an integrity verification agent to ensure its accuracy and reliability.

[0190] Step 8:

[0191] The terminal receives the calculation results sent from the server. The system selects a method to visually display the results based on the user's emotional state. An explanatory visualization is provided, allowing the user to intuitively understand the results and gain insights for analysis.

[0192] (Application Example 2)

[0193] 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".

[0194] In modern urban environments, residents and administrators are required to make appropriate decisions using vast amounts of data. However, conventional systems have provided uniform information and decision-making support without considering the user's emotional state, which can lead to stress and confusion. This invention aims to recognize the user's emotions, adjust the computational structure and information presentation based on those emotions, and provide the user with a more personalized experience.

[0195] 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.

[0196] In this invention, the server includes means for presenting an optimal computational structure, means for converting a specified computational code into a format executable by a high-speed computer, and means for recognizing the user's emotional state and optimizing the presentation of the computational structure and results based on that state. This enables the provision of customized information according to each user's emotional state.

[0197] An "optimal computational structure" is a theoretical framework for selecting the computational model or algorithm that best suits the user's specific needs and objectives.

[0198] "Condition setting" is a procedure for controlling the accuracy and efficiency of calculations by setting initial values ​​and ranges of variation for each element in the calculation structure.

[0199] A "high-speed computer" is a computer system that can process vast amounts of data and perform complex calculations quickly.

[0200] "Systematic management of resource use" refers to management techniques that optimize the use of computing power, memory, and other resources necessary for computation, thereby enabling efficient and effective computation.

[0201] A "simulated experiment" is a computational method used to virtually reproduce real-world events and predict their behavior and results.

[0202] "Recognizing emotional state" is a technology that analyzes information such as a user's facial expressions and voice tone to determine their psychological state.

[0203] "Optimizing information presentation" means adjusting the way calculation results and data are displayed and their content according to the user's emotional state, providing information in a way that is easy for the user to understand and beneficial to them.

[0204] In this embodiment of the invention, an application system for use by residents and city administrators is constructed based on data from a smart city environment. The server selects the optimal computational structure based on the user's emotional state and efficiently processes the relevant information. In this process, a high-speed computer is essential for computation execution and data processing.

[0205] The server performs simulation experiments using a high-speed computer and sends the results to the user's terminal. During this process, it recognizes the user's emotional state and optimizes the information presentation. For example, if the user is experiencing stress regarding traffic information or public services, it provides reassuring route recommendations and service information. The terminal then presents the data visually in a way that is easy for the user to understand.

[0206] Specifically, the hardware will consist of high-speed computers equipped with multi-core processors, and user terminals will include smartphones and smart glasses. For software, emotion recognition will utilize Microsoft® Azure's Face API and voice tone analysis capabilities.

[0207] An example of a prompt message might be, "Please tell me how to suggest an optimized commute route when a user is experiencing stress." Based on this, the system provides information tailored to the user's needs. It can intuitively present a variety of options to users aiming to shorten their commute time or improve comfort.

[0208] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0209] Step 1:

[0210] The server receives initial input data and sentiment information from the user's terminal. The input data includes questions and requirements related to transportation and public services. The sentiment engine analyzes the user's facial expressions and voice to determine their emotional state and adds the results to the data. The output is a dataset containing the emotional states for selecting the necessary computational structure.

[0211] Step 2:

[0212] The server uses a dataset containing emotional states to select the optimal computational structure. This process analyzes the data using a generative AI model and configures a computational structure tailored to the user's needs. The output is the selected computational model and its initial configuration parameters.

[0213] Step 3:

[0214] The server uses the computation model and initial parameters to generate computation code for the high-speed computer. Here, transformations are performed to optimize parallel processing. The output is code in a format executable on the high-speed computer.

[0215] Step 4:

[0216] The server sends code to a high-speed computer to perform the necessary simulations and data processing. The calculation results are returned to the server and output as simulation data.

[0217] Step 5:

[0218] The server analyzes the simulation results and optimizes them while taking the user's emotional state into consideration. Here, the focus is on presenting information in a way that reassures the user, for example, by offering flexible transportation route options. The output is data that can be presented in a way that minimizes user stress.

[0219] Step 6:

[0220] The terminal visually presents information based on optimized data received from the server. Users can review the presented data and route suggestions and make selections as appropriate. The output is easy to understand and visualized, better meeting the user's needs.

[0221] 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.

[0222] 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.

[0223] 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.

[0224] [Second Embodiment]

[0225] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0226] 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.

[0227] 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).

[0228] 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.

[0229] 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.

[0230] 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).

[0231] 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.

[0232] 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.

[0233] 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.

[0234] 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.

[0235] 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.

[0236] 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".

[0237] This invention provides a system that allows users to easily utilize the computing power of supercomputers. This system automates a series of processes, from selecting a computational model to verifying the results, by utilizing multiple AI agents. Specific embodiments of this system are described below.

[0238] First, users access the computing system through a terminal and input the purpose of the calculation and the dataset. This data can be used for a wide range of purposes, including scientific research, new drug development, and engineering analysis.

[0239] Based on this input data, the server launches a model selection agent. The model selection agent consults a database of available mathematical models and algorithms and automatically selects the model best suited to the user's purpose. The selected model is then presented to the user via the terminal.

[0240] Next, the server uses a parameter tuning agent to calculate the optimal parameters for the selected model. This parameter tuning is crucial for improving the accuracy and efficiency of the calculations, and the agent's automated estimation allows even users without specialized knowledge to start calculations under optimal conditions.

[0241] Subsequently, based on the computational model and parameters, the server activates a supercomputer conversion agent. This agent converts the user's input code and data into a format that can be efficiently executed on a supercomputer. This conversion process involves parallelization and memory optimization.

[0242] As a concrete example, consider molecular simulations used to predict drug efficacy in new drug development. The user simply inputs information about the molecule to be simulated, and the system automatically selects the optimal molecular model, sets appropriate temperature and pressure parameters, and converts the data into a format suitable for a supercomputer.

[0243] This allows users to fully utilize the computing power of a high-performance supercomputer without requiring specialized programming or simulation knowledge. Finally, the system can verify the calculation results and present them to the user in an easy-to-understand visual format. It can also provide feedback tailored to the user's objectives, enabling rapid incorporation into further research and development.

[0244] The following describes the processing flow.

[0245] Step 1:

[0246] The user accesses the system using a terminal and inputs the information and datasets necessary for the calculation. This includes specifying, for example, molecular structure information and the purpose of the simulation.

[0247] Step 2:

[0248] The server launches a model selection agent based on the input information. This agent searches the database for appropriate computational models and algorithms and presents the best option for the user's purpose.

[0249] Step 3:

[0250] The user reviews the presented model and, if necessary, enters additional conditions or requests via the terminal. This input allows the system to configure a more specific model to meet the user's needs.

[0251] Step 4:

[0252] The server uses a parameter tuning agent to set the optimal parameters for the selected model. This agent automatically calculates the parameters based on the model's characteristics and input data.

[0253] Step 5:

[0254] The server activates a supercomputer conversion agent and performs code conversion based on the model and parameters. This process optimizes the user's input code for supercomputers and converts it into a format that can be computed in parallel.

[0255] Step 6:

[0256] The server checks the available computing resources in the scheduling agent and determines the optimal timing for execution. This agent compares and allocates resources efficiently compared to other computing tasks.

[0257] Step 7:

[0258] The server initiates calculations on the supercomputer, and the simulation agent processes the data. The system ensures stability by saving the ongoing data as needed.

[0259] Step 8:

[0260] The server transfers the simulation results to the verification agent for consistency checks. This process verifies the accuracy of the results.

[0261] Step 9:

[0262] The device displays verified results to the user, presenting the data in an easy-to-understand visual format. The user can review the details and, if necessary, be instructed to take the next steps.

[0263] (Example 1)

[0264] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0265] In fields requiring complex calculations and simulations, a problem exists in that users without specialized knowledge find it difficult to fully utilize the capabilities of high-performance computers. Traditional methods require a specialized understanding of mathematical models, computational parameter selection, and code optimization, which is considered a high hurdle for users. As a result, there are many cases where high-performance computing resources are not effectively utilized.

[0266] 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.

[0267] In this invention, the server includes means for proposing an optimal mathematical model based on the purpose entered by the user, means for automatically adjusting parameters based on the selected mathematical model, and means for converting the input code into an optimized format executable on the computer. This allows the user to make full use of the capabilities of a high-performance computer without specialized knowledge.

[0268] A "mathematical model" is an abstract theoretical framework that expresses real-world phenomena using mathematical methods, making them analyzable through calculations and simulations.

[0269] A "parameter" is a variable in a mathematical model or algorithm that sets specific conditions or characteristics and affects the calculation results or the behavior of the simulation.

[0270] An "input code" is a program description that outlines the instructions to be given to a computer, and it represents a set of calculation procedures.

[0271] A "computer" is a physical or virtual machine used to process data and perform calculations and analyses, and generally includes a processor and memory.

[0272] "Optimization" is the process of adjusting available resources and conditions to the best possible state in order to improve the performance of a system or process.

[0273] A "user" is an entity that operates a system or software and utilizes its functions to achieve a specific purpose.

[0274] "Visualization" is a technique that presents information in an easily understandable way to users by representing calculation results and data in the form of graphs, diagrams, and other visual representations.

[0275] "Efficient" refers to a state in which the greatest results can be obtained with the fewest resources, or a method for achieving such a state.

[0276] This invention is a system for users to perform complex calculations using high-performance computers, and is designed to facilitate large-scale data processing and analysis by utilizing supercomputers. The central element of the system is multiple agents, each operated by a server, which cooperate to automate the selection of computational models, parameter adjustment, and code conversion.

[0277] Users access the interface using a terminal and input calculation objectives and required data into the system using prompt messages. It is recommended that these prompt messages clearly state specific needs. For example, by entering a prompt message such as "I would like to perform a simulation using the following molecular information for new drug development," the system will select the most suitable mathematical model for that purpose and prepare to begin the necessary calculations.

[0278] The server uses configured software to analyze the input data and select the most suitable mathematical model from the database to meet the user's requirements. This process is streamlined by utilizing generative AI models, ensuring highly accurate selection by referencing similar past cases and the latest algorithms.

[0279] Parameter tuning for the selected mathematical model is performed by a dedicated agent on the server, automatically making the necessary configuration changes to maximize computational accuracy and efficiency. This allows users to continue calculations under optimized conditions without requiring any manual adjustments.

[0280] Furthermore, the server converts the user-provided input code, preparing it for execution on a supercomputer. This conversion process includes parallelization and optimization of memory usage, enabling rapid computation even for large datasets.

[0281] According to this invention, users can utilize a high-performance computing environment without specialized knowledge, thereby reducing a great deal of time and effort while obtaining accurate and rapid simulation results.

[0282] The flow of the specific process in Example 1 will be described using FIG. 11.

[0283] Step 1:

[0284] The user uses a terminal to access the computing system and inputs specific calculation purposes and data through a prompt sentence. The input data includes, for example, molecular information necessary for new drug development. Based on this information, the user requests a calculation task from the system. The user's input is sent to the server and the processing starts.

[0285] Step 2:

[0286] The server analyzes the received input data and selects an optimal mathematical model using a generated AI model. At this time, the server refers to the internal model database and automatically selects the model most suitable for the user's calculation purpose. The mathematical model selected as a result of the data analysis is output.

[0287] Step 3:

[0288] The server activates a parameter adjustment agent based on the selected mathematical model. The agent automatically calculates appropriate parameters according to the input data and the requirements of the model. For example, in molecular simulation, temperature and pressure parameters are set. By this adjustment, the model can exhibit maximum accuracy and performance. The adjusted parameters are output for the next process.

[0289] Step 4:

[0290] The server activates a supercomputer conversion agent based on parameters and mathematical models. This agent converts the input code into a format that can run efficiently on a supercomputer. This process involves parallelization and memory optimization of the code. The converted executable code is output, ready for execution on the supercomputer.

[0291] Step 5:

[0292] The server sends the prepared executable code to the supercomputer and starts the calculation. The server monitors the progress of the calculation and manages resources as needed. Once the calculation is complete, the results are returned to the server.

[0293] Step 6:

[0294] The server analyzes the calculation results and verifies their accuracy through a results verification agent. The analysis results are then visualized and presented to the user via a terminal. The user reviews the results based on the provided visual information and provides feedback as needed. This feedback is then incorporated into the system's next processing cycle.

[0295] (Application Example 1)

[0296] 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."

[0297] The challenge lies in performing real-time analysis of complex traffic and energy consumption data in urban environments to enable efficient and appropriate responses. Conventional systems require enormous computing power, making it difficult to select appropriate models and set parameters without specialized knowledge, thus hindering real-time analysis. This results in problems such as the inability to respond quickly to sudden traffic congestion or peak energy consumption.

[0298] 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.

[0299] In this invention, the server includes means for proposing an optimal computational model, means for collecting and analyzing traffic information and energy consumption information within the urban environment, and means for providing the analysis results to the user via a terminal. This enables real-time analysis of complex urban environment data and supports efficient infrastructure operation.

[0300] "The primary method for proposing the optimal computational model" refers to a technology that automatically presents the best computational model for problem solving using an algorithm that selects an appropriate mathematical model based on the user's input information.

[0301] "A second method for setting parameters based on the proposed computational model" refers to an automated estimation technique for setting optimal parameters for the selected model and improving the accuracy and efficiency of the calculations.

[0302] "A third method for converting specified computational code into a format executable on high-performance computing devices" refers to a technology that performs conversion, including parallelization and memory management, in order to efficiently execute input code or data on high-performance computing devices.

[0303] The "fourth means of systematically managing resource usage" refers to management techniques for efficiently allocating computing resources and performing necessary calculations while maintaining optimal performance.

[0304] The "fifth method of performing analysis on a high-performance computing device" is a technique that uses the converted code to perform data analysis on a device with advanced computing capabilities.

[0305] The "sixth method for verifying the consistency of analysis results" refers to verification techniques for confirming that the obtained analysis results are accurate and consistent.

[0306] The "seventh means of collecting and analyzing traffic information and energy consumption information within the urban environment" refers to a technology that monitors the utilization status of traffic and energy in the city, analyzes this information, and derives patterns.

[0307] The "eighth means of providing the analysis results to users through terminals" refers to a technology that visually and clearly organizes the analyzed information and provides it via the terminals used by users.

[0308] In the system for implementing this invention, the server first receives data related to the urban environment input by the user. The data includes traffic information and energy consumption information. Based on this input data, the server executes a program for selecting an optimal mathematical model. In this process, cloud AI platforms such as Azure Machine Learning and Amazon SageMaker are utilized to select the mathematical model.

[0309] After selecting the mathematical model, the server performs optimal parameter settings on the cloud platform and converts the code for execution on a supercomputer. In this conversion process, parallel processing and memory management are optimized to generate code that operates efficiently on high-performance computing devices.

[0310] Furthermore, the server uses the generated analysis algorithm to predict traffic congestion in real time and detect energy consumption peaks. This result is provided to the user's terminal in a visually clear manner. The terminal displays the analysis results in the form of charts and graphs, etc., and provides an interface convenient for daily use.

[0311] As a specific example, there is a scenario where the server monitors the road congestion situation in the city and proposes an optimal detour route to the user. It is also possible to suggest the timing of using air conditioning on hot days. Through such a system, the efficiency and comfort of urban life are realized.

[0312] An example of a prompt to input into a generative AI model might be: "Using one week's worth of urban traffic data and weather forecasts, predict traffic congestion for the coming weekend."

[0313] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0314] Step 1:

[0315] Users input urban environmental data, such as traffic information and energy consumption data, into the server via their terminals. This data forms the basis for the analysis process across the entire system. The server receives this data and stores it in a database.

[0316] Step 2:

[0317] The server sends the received data to a cloud AI platform, which selects the optimal mathematical model. In this process, the generated AI model chooses algorithms suitable for traffic congestion prediction and energy consumption analysis. This enables the selection of the optimal model according to the user's requirements. The input is urban environment data, and the output is the selected mathematical model.

[0318] Step 3:

[0319] The server sets the model parameters based on the selected mathematical model. In this step, it receives the selected model data as input and calculates the optimized parameters. This output is saved for use in the next analysis step. This is done efficiently by utilizing the automated optimization function of the cloud AI platform.

[0320] Step 4:

[0321] The server uses the constructed mathematical model and parameters to convert the user-specified computation code into a format executable on a high-performance computer. The input consists of the mathematical model, parameters, and computation code, while the output is the converted code that can be executed on the computer. The conversion is performed with parallel processing optimization in mind.

[0322] Step 5:

[0323] Using the converted code, the server performs analysis on a high-performance computing device. Here, the data for analysis is real-time urban environmental information, and the output consists of prediction results and analysis results.

[0324] Step 6:

[0325] The server verifies the consistency of the obtained analysis results. This involves a process that uses data validation algorithms to ensure the accuracy and consistency of the results. The input to this step is the analysis results, and the output is the validated data.

[0326] Step 7:

[0327] Finally, the server sends the verified analysis results to the user's terminal. The terminal displays these results visually, providing information in an easy-to-understand format for the user. Examples of analysis results provided include traffic congestion predictions and power consumption advice.

[0328] 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.

[0329] This invention provides a system that enables a wide range of users to utilize the computing power of supercomputers, and is particularly characterized by its combination with an emotion engine that recognizes user emotions and optimizes the system's behavior based on that emotion information. This system utilizes multiple AI agents and the emotion engine to perform tasks from selecting a computational model to verifying the results. The following describes a specific embodiment of this system.

[0330] First, the user accesses the system via a terminal and registers the calculation project they wish to run. During this process, the emotion engine recognizes the user's emotional state by analyzing their facial expressions and voice tone. This emotional information is then used to adjust the overall operation of the system.

[0331] The server activates a model selection agent based on data received from the user. The emotion engine reflects the user's expectations and stress levels and selects a computational model appropriate to the user's emotions. This process allows for adjustments, such as selecting a more robust model if the user is feeling anxious.

[0332] Next, the server uses a parameter tuning agent to set the optimal parameters for the selected model. Based on the information from the emotion engine, the visualization and presentation methods are also adjusted to support the user's intuitive understanding.

[0333] Subsequently, the supercomputer conversion agent operates, transforming the given model and parameters into a format that can be efficiently executed on a supercomputer. Even during this conversion process, the emotion engine flexibly modifies the conversion method according to user requests.

[0334] As a concrete example, consider a case where a user performs a predictive simulation for a new product. If the emotion engine determines that the user's level of tension is high, the system will select a conservative model that reduces risk in the model selection process and operate in a way that presents the calculation results in a stable manner.

[0335] Finally, after the simulation is complete, the server checks the results using a consistency verification agent. The terminal then displays the results in a visually easy-to-understand format, providing further insights by adding explanations that are sensitive to the user's emotions.

[0336] In this way, by combining it with an emotion engine, we can provide a user experience different from conventional systems and support the effective use of computation.

[0337] The following describes the processing flow.

[0338] Step 1:

[0339] Users access the system using a terminal and input information about the calculation project they wish to undertake. Along with the calculation data, they provide facial expressions and voice tone via camera and microphone.

[0340] Step 2:

[0341] The device sends the collected user emotion data to an emotion engine, which analyzes the user's emotional state. The emotion engine determines whether the user is stressed, relaxed, or otherwise.

[0342] Step 3:

[0343] Based on information from the emotion engine, the server activates a model selection agent to select a computational model appropriate to the user's emotions. For example, if the user is feeling anxious, it will prioritize suggesting a model that emphasizes reliability.

[0344] Step 4:

[0345] Users review the proposed model and input modifications or additional conditions as needed. This feedback is also interpreted by the emotion engine, leading to further adjustments.

[0346] Step 5:

[0347] The server uses a parameter tuning agent to set parameters for the selected model. Based on instructions from the emotion engine, the settings are configured in a way that is intuitively easy for the user to understand.

[0348] Step 6:

[0349] The server activates the supercomputer transformation agent, which converts the parameterized model into code for execution on a supercomputer. During the transformation process, it adjusts the flexibility and efficiency of the transformation based on information from the emotion engine.

[0350] Step 7:

[0351] The server uses a scheduling agent to optimize the timing and resources of calculations and to create an execution plan. It can also leverage sentiment data to adjust priorities.

[0352] Step 8:

[0353] The server starts the simulation on the supercomputer and performs the computational tasks. Data in progress is periodically saved to ensure the stability of the computation.

[0354] Step 9:

[0355] After the simulation is complete, the server verifies the consistency of the results with a validation agent and prepares to provide reliable results.

[0356] Step 10:

[0357] The device visually presents the verified results to the user, adding explanations based on the sentiment engine's judgment. This makes it easier for the user to understand the results and decide on the next action.

[0358] (Example 2)

[0359] 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".

[0360] There is a problem in that it is difficult for ordinary users to intuitively utilize high-performance computers such as supercomputers, and it is also difficult to effectively understand the results. Furthermore, conventional systems do not take into account the user's psychological state, so the operation and display of results may not match the user's expectations or understanding.

[0361] 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.

[0362] In this invention, the server includes means for analyzing the user's emotional state and adjusting the operation of the entire system, means for selecting an appropriate computational model using an emotion engine based on the analyzed emotional information, and means for setting optimal parameters for the selected computational model. As a result, the appropriate computational model and parameters are automatically selected and applied according to the user's emotional state, enabling a more user-friendly and effective understanding of the computational results.

[0363] "User emotional state" refers to the psychological or emotional state of the user as recognized by the system from the user's facial expressions, voice tone, etc.

[0364] An "emotion engine" refers to a technology that analyzes the user's emotional state and uses that information to optimize the overall operation of the system.

[0365] A "computational model" refers to a set of procedures or algorithms prepared to perform a specific computational task.

[0366] "Parameter setting" refers to the process of determining the specific numerical values ​​and settings used in the calculation model.

[0367] A "supercomputer" refers to a high-performance computer capable of performing large-scale and complex calculations at high speed.

[0368] "Visually displaying" refers to presenting information on a screen in a graphical format in order to help users understand the information.

[0369] A "consistency verification agent" refers to an automated software process used to check whether calculation results are accurate.

[0370] A "generative AI model" refers to a set of algorithms that are generated using artificial intelligence technology and perform specific information processing or data analysis.

[0371] The system in this invention is designed around the user, terminal, and server, and is intended to recognize the user's emotional state and use that to efficiently carry out computational projects.

[0372] Users access the system using a terminal to carry out computational projects. The terminal is equipped with a camera and microphone, which capture the user's facial expressions and voice tone. This data is sent to a server for later analysis by an emotion engine.

[0373] The server receives this data and uses a generative AI model to analyze the user's emotional state. For example, if the system recognizes that the user is feeling anxious, this emotional information is reflected in the selection of a computational model, ensuring that a robust model is chosen. The emotion engine plays a crucial role in this process, optimizing the overall system operation.

[0374] The selected computational model has its optimal parameters set using a parameter tuning agent. This model is then transformed by a supercomputer conversion agent into a format suitable for execution on a supercomputer. A supercomputer is a high-performance computer capable of processing large-scale and complex calculations at high speed.

[0375] The device displays the final calculation results in a visually easy-to-understand format for the user. Based on information obtained from the emotion engine, explanations are added to the results to make them easier for the user to understand. This allows the user to intuitively grasp the results and use them to aid in decision-making.

[0376] A concrete example is a market forecast simulation for a new product. An example of a prompt message might be, "Perform a market forecast simulation for the new product and select a method for presenting the results based on user sentiment."

[0377] This system aims to make the execution of computational projects more flexible and user-friendly by taking user emotions into consideration.

[0378] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0379] Step 1:

[0380] Users register their calculation projects with the system using a terminal. They enter details of the project they want to run and upload the necessary data. This information includes the calculation type, purpose, and associated datasets. Once this information is sent to the server, the project is initially configured.

[0381] Step 2:

[0382] The device collects the user's facial expressions and voice tone using its camera and microphone. This data is used as input to infer the user's emotional state. The device then transfers this information to a server for preprocessing of emotion analysis.

[0383] Step 3:

[0384] The server inputs the received facial expression and voice data into a generating AI model. This model analyzes the user's emotional state, specifically identifying emotions such as joy, surprise, and anxiety. The output provides the type and intensity of the emotion. This result is used to select a subsequent computational model.

[0385] Step 4:

[0386] The server selects an appropriate computational model by referencing the emotion engine. The user's emotional state significantly influences this selection process. For example, if the user is showing anxiety, a robust model will be chosen to ensure stable results. The results of this model selection are reflected in the parameter tuning in the next step.

[0387] Step 5:

[0388] The server sets parameters for the selected computational model. Based on the input from the emotion engine, the parameters are adjusted to produce results that are easy to understand intuitively. The adjusted parameters are output as the specific execution specifications for the model.

[0389] Step 6:

[0390] On the server, the adjusted model and parameters are converted into a format executable by the supercomputer. A supercomputer conversion agent handles this conversion, optimizing parallel processing. The converted code is generated as the final output and sent to the supercomputer.

[0391] Step 7:

[0392] The server initiates computation on the supercomputer. Once the computation is complete, the resulting data is generated. This data is checked by an integrity verification agent to ensure its accuracy and reliability.

[0393] Step 8:

[0394] The terminal receives the calculation results sent from the server. The system selects a method to visually display the results based on the user's emotional state. An explanatory visualization is provided, allowing the user to intuitively understand the results and gain insights for analysis.

[0395] (Application Example 2)

[0396] 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."

[0397] In modern urban environments, residents and administrators are required to make appropriate decisions using vast amounts of data. However, conventional systems have provided uniform information and decision-making support without considering the user's emotional state, which can lead to stress and confusion. This invention aims to recognize the user's emotions, adjust the computational structure and information presentation based on those emotions, and provide the user with a more personalized experience.

[0398] 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.

[0399] In this invention, the server includes means for presenting an optimal computational structure, means for converting a specified computational code into a format executable by a high-speed computer, and means for recognizing the user's emotional state and optimizing the presentation of the computational structure and results based on that state. This enables the provision of customized information according to each user's emotional state.

[0400] An "optimal computational structure" is a theoretical framework for selecting the computational model or algorithm that best suits the user's specific needs and objectives.

[0401] "Condition setting" is a procedure for controlling the accuracy and efficiency of calculations by setting initial values ​​and ranges of variation for each element in the calculation structure.

[0402] A "high-speed computer" is a computer system that can process vast amounts of data and perform complex calculations quickly.

[0403] "Systematic management of resource use" refers to management techniques that optimize the use of computing power, memory, and other resources necessary for computation, thereby enabling efficient and effective computation.

[0404] A "simulated experiment" is a computational method used to virtually reproduce real-world events and predict their behavior and results.

[0405] "Recognizing emotional state" is a technology that analyzes information such as a user's facial expressions and voice tone to determine their psychological state.

[0406] "Optimizing information presentation" means adjusting the way calculation results and data are displayed and their content according to the user's emotional state, providing information in a way that is easy for the user to understand and beneficial to them.

[0407] In this embodiment of the invention, an application system for use by residents and city administrators is constructed based on data from a smart city environment. The server selects the optimal computational structure based on the user's emotional state and efficiently processes the relevant information. In this process, a high-speed computer is essential for computation execution and data processing.

[0408] The server performs simulation experiments using a high-speed computer and sends the results to the user's terminal. During this process, it recognizes the user's emotional state and optimizes the information presentation. For example, if the user is experiencing stress regarding traffic information or public services, it provides reassuring route recommendations and service information. The terminal then presents the data visually in a way that is easy for the user to understand.

[0409] Specifically, the hardware will consist of high-speed computers equipped with multi-core processors, and user terminals will include smartphones and smart glasses. For software, emotion recognition will utilize Microsoft Azure's Face API and voice tone analysis capabilities.

[0410] An example of a prompt message might be, "Please tell me how to suggest an optimized commute route when a user is experiencing stress." Based on this, the system provides information tailored to the user's needs. It can intuitively present a variety of options to users aiming to shorten their commute time or improve comfort.

[0411] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0412] Step 1:

[0413] The server receives initial input data and sentiment information from the user's terminal. The input data includes questions and requirements related to transportation and public services. The sentiment engine analyzes the user's facial expressions and voice to determine their emotional state and adds the results to the data. The output is a dataset containing the emotional states for selecting the necessary computational structure.

[0414] Step 2:

[0415] The server uses a dataset containing emotional states to select the optimal computational structure. This process analyzes the data using a generative AI model and configures a computational structure tailored to the user's needs. The output is the selected computational model and its initial configuration parameters.

[0416] Step 3:

[0417] The server uses the computation model and initial parameters to generate computation code for the high-speed computer. Here, transformations are performed to optimize parallel processing. The output is code in a format executable on the high-speed computer.

[0418] Step 4:

[0419] The server sends code to a high-speed computer to perform the necessary simulations and data processing. The calculation results are returned to the server and output as simulation data.

[0420] Step 5:

[0421] The server analyzes the simulation results and optimizes them while taking the user's emotional state into consideration. Here, the focus is on presenting information in a way that reassures the user, for example, by offering flexible transportation route options. The output is data that can be presented in a way that minimizes user stress.

[0422] Step 6:

[0423] The terminal visually presents information based on optimized data received from the server. Users can review the presented data and route suggestions and make selections as appropriate. The output is easy to understand and visualized, better meeting the user's needs.

[0424] 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.

[0425] 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.

[0426] 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.

[0427] [Third Embodiment]

[0428] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0429] 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.

[0430] 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).

[0431] 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.

[0432] 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.

[0433] 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).

[0434] 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.

[0435] 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.

[0436] 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.

[0437] 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.

[0438] 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.

[0439] 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".

[0440] This invention provides a system that allows users to easily utilize the computing power of supercomputers. This system automates a series of processes, from selecting a computational model to verifying the results, by utilizing multiple AI agents. Specific embodiments of this system are described below.

[0441] First, users access the computing system through a terminal and input the purpose of the calculation and the dataset. This data can be used for a wide range of purposes, including scientific research, new drug development, and engineering analysis.

[0442] Based on this input data, the server launches a model selection agent. The model selection agent consults a database of available mathematical models and algorithms and automatically selects the model best suited to the user's purpose. The selected model is then presented to the user via the terminal.

[0443] Next, the server uses a parameter tuning agent to calculate the optimal parameters for the selected model. This parameter tuning is crucial for improving the accuracy and efficiency of the calculations, and the agent's automated estimation allows even users without specialized knowledge to start calculations under optimal conditions.

[0444] Subsequently, based on the computational model and parameters, the server activates a supercomputer conversion agent. This agent converts the user's input code and data into a format that can be efficiently executed on a supercomputer. This conversion process involves parallelization and memory optimization.

[0445] As a concrete example, consider molecular simulations used to predict drug efficacy in new drug development. The user simply inputs information about the molecule to be simulated, and the system automatically selects the optimal molecular model, sets appropriate temperature and pressure parameters, and converts the data into a format suitable for a supercomputer.

[0446] This allows users to fully utilize the computing power of a high-performance supercomputer without requiring specialized programming or simulation knowledge. Finally, the system can verify the calculation results and present them to the user in an easy-to-understand visual format. It can also provide feedback tailored to the user's objectives, enabling rapid incorporation into further research and development.

[0447] The following describes the processing flow.

[0448] Step 1:

[0449] The user accesses the system using a terminal and inputs the information and datasets necessary for the calculation. This includes specifying, for example, molecular structure information and the purpose of the simulation.

[0450] Step 2:

[0451] The server launches a model selection agent based on the input information. This agent searches the database for appropriate computational models and algorithms and presents the best option for the user's purpose.

[0452] Step 3:

[0453] The user reviews the presented model and, if necessary, enters additional conditions or requests via the terminal. This input allows the system to configure a more specific model to meet the user's needs.

[0454] Step 4:

[0455] The server uses a parameter tuning agent to set the optimal parameters for the selected model. This agent automatically calculates the parameters based on the model's characteristics and input data.

[0456] Step 5:

[0457] The server activates a supercomputer conversion agent and performs code conversion based on the model and parameters. This process optimizes the user's input code for supercomputers and converts it into a format that can be computed in parallel.

[0458] Step 6:

[0459] The server checks the available computing resources in the scheduling agent and determines the optimal timing for execution. This agent compares and allocates resources efficiently compared to other computing tasks.

[0460] Step 7:

[0461] The server initiates calculations on the supercomputer, and the simulation agent processes the data. The system ensures stability by saving the ongoing data as needed.

[0462] Step 8:

[0463] The server transfers the simulation results to the verification agent for consistency checks. This process verifies the accuracy of the results.

[0464] Step 9:

[0465] The device displays verified results to the user, presenting the data in an easy-to-understand visual format. The user can review the details and, if necessary, be instructed to take the next steps.

[0466] (Example 1)

[0467] 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."

[0468] In fields requiring complex calculations and simulations, a problem exists in that users without specialized knowledge find it difficult to fully utilize the capabilities of high-performance computers. Traditional methods require a specialized understanding of mathematical models, computational parameter selection, and code optimization, which is considered a high hurdle for users. As a result, there are many cases where high-performance computing resources are not effectively utilized.

[0469] 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.

[0470] In this invention, the server includes means for proposing an optimal mathematical model based on the purpose entered by the user, means for automatically adjusting parameters based on the selected mathematical model, and means for converting the input code into an optimized format executable on the computer. This allows the user to make full use of the capabilities of a high-performance computer without specialized knowledge.

[0471] A "mathematical model" is an abstract theoretical framework that expresses real-world phenomena using mathematical methods, making them analyzable through calculations and simulations.

[0472] A "parameter" is a variable in a mathematical model or algorithm that sets specific conditions or characteristics and affects the calculation results or the behavior of the simulation.

[0473] An "input code" is a program description that outlines the instructions to be given to a computer, and it represents a set of calculation procedures.

[0474] A "computer" is a physical or virtual machine used to process data and perform calculations and analyses, and generally includes a processor and memory.

[0475] "Optimization" is the process of adjusting available resources and conditions to the best possible state in order to improve the performance of a system or process.

[0476] A "user" is an entity that operates a system or software and utilizes its functions to achieve a specific purpose.

[0477] "Visualization" is a technique that presents information in an easily understandable way to users by representing calculation results and data in the form of graphs, diagrams, and other visual representations.

[0478] "Efficient" refers to a state in which the greatest results can be obtained with the fewest resources, or a method for achieving such a state.

[0479] This invention is a system for users to perform complex calculations using high-performance computers, and is designed to facilitate large-scale data processing and analysis by utilizing supercomputers. The central element of the system is multiple agents, each operated by a server, which cooperate to automate the selection of computational models, parameter adjustment, and code conversion.

[0480] Users access the interface using a terminal and input calculation objectives and required data into the system using prompt messages. It is recommended that these prompt messages clearly state specific needs. For example, by entering a prompt message such as "I would like to perform a simulation using the following molecular information for new drug development," the system will select the most suitable mathematical model for that purpose and prepare to begin the necessary calculations.

[0481] The server uses configured software to analyze the input data and select the most suitable mathematical model from the database to meet the user's requirements. This process is streamlined by utilizing generative AI models, ensuring highly accurate selection by referencing similar past cases and the latest algorithms.

[0482] Parameter tuning for the selected mathematical model is performed by a dedicated agent on the server, automatically making the necessary configuration changes to maximize computational accuracy and efficiency. This allows users to continue calculations under optimized conditions without requiring any manual adjustments.

[0483] Furthermore, the server converts the user-provided input code, preparing it for execution on a supercomputer. This conversion process includes parallelization and optimization of memory usage, enabling rapid computation even for large datasets.

[0484] This invention enables users to utilize a high-performance computing environment without specialized knowledge, thereby saving considerable time and effort while obtaining accurate and rapid simulation results.

[0485] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0486] Step 1:

[0487] The user accesses the computing system using a terminal and inputs specific calculation objectives and data through prompts. The input data includes, for example, molecular information necessary for new drug development. Based on this information, the user requests a calculation task from the system. The user's input is sent to the server, and processing begins.

[0488] Step 2:

[0489] The server analyzes the received input data and selects the optimal mathematical model using a generated AI model. During this process, the server refers to an internal model database and automatically selects the model best suited to the user's computational objectives. The selected mathematical model, resulting from the data analysis, is then output.

[0490] Step 3:

[0491] The server activates a parameter tuning agent based on the selected mathematical model. The agent automatically calculates appropriate parameters according to the input data and model requirements. For example, in molecular simulations, temperature and pressure parameters are set. This tuning ensures the model achieves maximum accuracy and performance. The tuned parameters are then output for the next process.

[0492] Step 4:

[0493] The server activates a supercomputer conversion agent based on parameters and mathematical models. This agent converts the input code into a format that can run efficiently on a supercomputer. This process involves parallelization and memory optimization of the code. The converted executable code is output, ready for execution on the supercomputer.

[0494] Step 5:

[0495] The server sends the prepared executable code to the supercomputer and starts the calculation. The server monitors the progress of the calculation and manages resources as needed. Once the calculation is complete, the results are returned to the server.

[0496] Step 6:

[0497] The server analyzes the calculation results and verifies their accuracy through a results verification agent. The analysis results are then visualized and presented to the user via a terminal. The user reviews the results based on the provided visual information and provides feedback as needed. This feedback is then incorporated into the system's next processing cycle.

[0498] (Application Example 1)

[0499] 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."

[0500] The challenge lies in performing real-time analysis of complex traffic and energy consumption data in urban environments to enable efficient and appropriate responses. Conventional systems require enormous computing power, making it difficult to select appropriate models and set parameters without specialized knowledge, thus hindering real-time analysis. This results in problems such as the inability to respond quickly to sudden traffic congestion or peak energy consumption.

[0501] 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.

[0502] In this invention, the server includes means for proposing an optimal computational model, means for collecting and analyzing traffic information and energy consumption information within the urban environment, and means for providing the analysis results to the user via a terminal. This enables real-time analysis of complex urban environment data and supports efficient infrastructure operation.

[0503] "The primary method for proposing the optimal computational model" refers to a technology that automatically presents the best computational model for problem solving using an algorithm that selects an appropriate mathematical model based on the user's input information.

[0504] "A second method for setting parameters based on the proposed computational model" refers to an automated estimation technique for setting optimal parameters for the selected model and improving the accuracy and efficiency of the calculations.

[0505] "A third method for converting specified computational code into a format executable on high-performance computing devices" refers to a technology that performs conversion, including parallelization and memory management, in order to efficiently execute input code or data on high-performance computing devices.

[0506] The "fourth means of systematically managing resource usage" refers to management techniques for efficiently allocating computing resources and performing necessary calculations while maintaining optimal performance.

[0507] The "fifth method of performing analysis on a high-performance computing device" is a technique that uses the converted code to perform data analysis on a device with advanced computing capabilities.

[0508] The "sixth method for verifying the consistency of analysis results" refers to verification techniques for confirming that the obtained analysis results are accurate and consistent.

[0509] The "seventh method for collecting and analyzing traffic and energy consumption information within urban environments" refers to a technology that monitors traffic and energy usage in cities, analyzes this information, and derives patterns.

[0510] The "eighth method of providing analysis results to users via a terminal" is a technology that visually organizes the analyzed information in an easy-to-understand manner and provides it to users via their terminals.

[0511] In the system implementing this invention, the server first receives urban environment-related data entered by the user. This data includes traffic information and energy consumption information. Based on this input data, the server executes a program to select the optimal mathematical model. In this process, cloud AI platforms such as Azure Machine Learning and Amazon SageMaker are used to select the mathematical model.

[0512] After selecting a mathematical model, the server optimizes the parameters on the cloud platform and converts the code for execution on a supercomputer. This conversion process optimizes parallel processing and memory management, generating code that runs efficiently on high-performance computing devices.

[0513] Furthermore, the server uses the generated analysis algorithms to predict traffic congestion and detect peak energy consumption in real time. These results are then presented to the user's device in an easily understandable visual format. The device displays the analysis results in the form of charts and graphs, providing a convenient interface for everyday use.

[0514] A concrete example would be a scenario where a server monitors road congestion in a city and suggests the most suitable alternative route to the user. It could also suggest the best time to use air conditioning on hot days. Through such systems, we aim to improve the efficiency and comfort of urban life.

[0515] An example of a prompt to input into a generative AI model might be: "Using one week's worth of urban traffic data and weather forecasts, predict traffic congestion for the coming weekend."

[0516] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0517] Step 1:

[0518] Users input urban environmental data, such as traffic information and energy consumption data, into the server via their terminals. This data forms the basis for the analysis process across the entire system. The server receives this data and stores it in a database.

[0519] Step 2:

[0520] The server sends the received data to a cloud AI platform, which selects the optimal mathematical model. In this process, the generated AI model chooses algorithms suitable for traffic congestion prediction and energy consumption analysis. This enables the selection of the optimal model according to the user's requirements. The input is urban environment data, and the output is the selected mathematical model.

[0521] Step 3:

[0522] The server sets the model parameters based on the selected mathematical model. In this step, it receives the selected model data as input and calculates the optimized parameters. This output is saved for use in the next analysis step. This is done efficiently by utilizing the automated optimization function of the cloud AI platform.

[0523] Step 4:

[0524] The server uses the constructed mathematical model and parameters to convert the user-specified computation code into a format executable on a high-performance computer. The input consists of the mathematical model, parameters, and computation code, while the output is the converted code that can be executed on the computer. The conversion is performed with parallel processing optimization in mind.

[0525] Step 5:

[0526] Using the converted code, the server performs analysis on a high-performance computing device. Here, the data for analysis is real-time urban environmental information, and the output consists of prediction results and analysis results.

[0527] Step 6:

[0528] The server verifies the consistency of the obtained analysis results. This involves a process that uses data validation algorithms to ensure the accuracy and consistency of the results. The input to this step is the analysis results, and the output is the validated data.

[0529] Step 7:

[0530] Finally, the server sends the verified analysis results to the user's terminal. The terminal displays these results visually, providing information in an easy-to-understand format for the user. Examples of analysis results provided include traffic congestion predictions and power consumption advice.

[0531] 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.

[0532] This invention provides a system that enables a wide range of users to utilize the computing power of supercomputers, and is particularly characterized by its combination with an emotion engine that recognizes user emotions and optimizes the system's behavior based on that emotion information. This system utilizes multiple AI agents and the emotion engine to perform tasks from selecting a computational model to verifying the results. The following describes a specific embodiment of this system.

[0533] First, the user accesses the system via a terminal and registers the calculation project they wish to run. During this process, the emotion engine recognizes the user's emotional state by analyzing their facial expressions and voice tone. This emotional information is then used to adjust the overall operation of the system.

[0534] The server activates a model selection agent based on data received from the user. The emotion engine reflects the user's expectations and stress levels and selects a computational model appropriate to the user's emotions. This process allows for adjustments, such as selecting a more robust model if the user is feeling anxious.

[0535] Next, the server uses a parameter tuning agent to set the optimal parameters for the selected model. Based on the information from the emotion engine, the visualization and presentation methods are also adjusted to support the user's intuitive understanding.

[0536] Subsequently, the supercomputer conversion agent operates, transforming the given model and parameters into a format that can be efficiently executed on a supercomputer. Even during this conversion process, the emotion engine flexibly modifies the conversion method according to user requests.

[0537] As a concrete example, consider a case where a user performs a predictive simulation for a new product. If the emotion engine determines that the user's level of tension is high, the system will select a conservative model that reduces risk in the model selection process and operate in a way that presents the calculation results in a stable manner.

[0538] Finally, after the simulation is complete, the server checks the results using a consistency verification agent. The terminal then displays the results in a visually easy-to-understand format, providing further insights by adding explanations that are sensitive to the user's emotions.

[0539] In this way, by combining it with an emotion engine, we can provide a user experience different from conventional systems and support the effective use of computation.

[0540] The following describes the processing flow.

[0541] Step 1:

[0542] Users access the system using a terminal and input information about the calculation project they wish to undertake. Along with the calculation data, they provide facial expressions and voice tone via camera and microphone.

[0543] Step 2:

[0544] The device sends the collected user emotion data to an emotion engine, which analyzes the user's emotional state. The emotion engine determines whether the user is stressed, relaxed, or otherwise.

[0545] Step 3:

[0546] Based on information from the emotion engine, the server activates a model selection agent to select a computational model appropriate to the user's emotions. For example, if the user is feeling anxious, it will prioritize suggesting a model that emphasizes reliability.

[0547] Step 4:

[0548] Users review the proposed model and input modifications or additional conditions as needed. This feedback is also interpreted by the emotion engine, leading to further adjustments.

[0549] Step 5:

[0550] The server uses a parameter tuning agent to set parameters for the selected model. Based on instructions from the emotion engine, the settings are configured in a way that is intuitively easy for the user to understand.

[0551] Step 6:

[0552] The server activates the supercomputer transformation agent, which converts the parameterized model into code for execution on a supercomputer. During the transformation process, it adjusts the flexibility and efficiency of the transformation based on information from the emotion engine.

[0553] Step 7:

[0554] The server uses a scheduling agent to optimize the timing and resources of calculations and to create an execution plan. It can also leverage sentiment data to adjust priorities.

[0555] Step 8:

[0556] The server starts the simulation on the supercomputer and performs the computational tasks. Data in progress is periodically saved to ensure the stability of the computation.

[0557] Step 9:

[0558] After the simulation is complete, the server verifies the consistency of the results with a validation agent and prepares to provide reliable results.

[0559] Step 10:

[0560] The device visually presents the verified results to the user, adding explanations based on the sentiment engine's judgment. This makes it easier for the user to understand the results and decide on the next action.

[0561] (Example 2)

[0562] 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."

[0563] There is a problem in that it is difficult for ordinary users to intuitively utilize high-performance computers such as supercomputers, and it is also difficult to effectively understand the results. Furthermore, conventional systems do not take into account the user's psychological state, so the operation and display of results may not match the user's expectations or understanding.

[0564] 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.

[0565] In this invention, the server includes means for analyzing the user's emotional state and adjusting the operation of the entire system, means for selecting an appropriate computational model using an emotion engine based on the analyzed emotional information, and means for setting optimal parameters for the selected computational model. As a result, the appropriate computational model and parameters are automatically selected and applied according to the user's emotional state, enabling a more user-friendly and effective understanding of the computational results.

[0566] "User emotional state" refers to the psychological or emotional state of the user as recognized by the system from the user's facial expressions, voice tone, etc.

[0567] An "emotion engine" refers to a technology that analyzes the user's emotional state and uses that information to optimize the overall operation of the system.

[0568] A "computational model" refers to a set of procedures or algorithms prepared to perform a specific computational task.

[0569] "Parameter setting" refers to the process of determining the specific numerical values ​​and settings used in the calculation model.

[0570] A "supercomputer" refers to a high-performance computer capable of performing large-scale and complex calculations at high speed.

[0571] "Visually displaying" refers to presenting information on a screen in a graphical format in order to help users understand the information.

[0572] A "consistency verification agent" refers to an automated software process used to check whether calculation results are accurate.

[0573] A "generative AI model" refers to a set of algorithms that are generated using artificial intelligence technology and perform specific information processing or data analysis.

[0574] The system in this invention is designed around the user, terminal, and server, and is intended to recognize the user's emotional state and use that to efficiently carry out computational projects.

[0575] Users access the system using a terminal to carry out computational projects. The terminal is equipped with a camera and microphone, which capture the user's facial expressions and voice tone. This data is sent to a server for later analysis by an emotion engine.

[0576] The server receives this data and uses a generative AI model to analyze the user's emotional state. For example, if the system recognizes that the user is feeling anxious, this emotional information is reflected in the selection of a computational model, ensuring that a robust model is chosen. The emotion engine plays a crucial role in this process, optimizing the overall system operation.

[0577] The selected computational model has its optimal parameters set using a parameter tuning agent. This model is then transformed by a supercomputer conversion agent into a format suitable for execution on a supercomputer. A supercomputer is a high-performance computer capable of processing large-scale and complex calculations at high speed.

[0578] The device displays the final calculation results in a visually easy-to-understand format for the user. Based on information obtained from the emotion engine, explanations are added to the results to make them easier for the user to understand. This allows the user to intuitively grasp the results and use them to aid in decision-making.

[0579] A concrete example is a market forecast simulation for a new product. An example of a prompt message might be, "Perform a market forecast simulation for the new product and select a method for presenting the results based on user sentiment."

[0580] This system aims to make the execution of computational projects more flexible and user-friendly by taking user emotions into consideration.

[0581] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0582] Step 1:

[0583] Users register their calculation projects with the system using a terminal. They enter details of the project they want to run and upload the necessary data. This information includes the calculation type, purpose, and associated datasets. Once this information is sent to the server, the project is initially configured.

[0584] Step 2:

[0585] The device collects the user's facial expressions and voice tone using its camera and microphone. This data is used as input to infer the user's emotional state. The device then transfers this information to a server for preprocessing of emotion analysis.

[0586] Step 3:

[0587] The server inputs the received facial expression and voice data into a generating AI model. This model analyzes the user's emotional state, specifically identifying emotions such as joy, surprise, and anxiety. The output provides the type and intensity of the emotion. This result is used to select a subsequent computational model.

[0588] Step 4:

[0589] The server selects an appropriate computational model by referencing the emotion engine. The user's emotional state significantly influences this selection process. For example, if the user is showing anxiety, a robust model will be chosen to ensure stable results. The results of this model selection are reflected in the parameter tuning in the next step.

[0590] Step 5:

[0591] The server sets parameters for the selected computational model. Based on the input from the emotion engine, the parameters are adjusted to produce results that are easy to understand intuitively. The adjusted parameters are output as the specific execution specifications for the model.

[0592] Step 6:

[0593] On the server, the adjusted model and parameters are converted into a format executable by the supercomputer. A supercomputer conversion agent handles this conversion, optimizing parallel processing. The converted code is generated as the final output and sent to the supercomputer.

[0594] Step 7:

[0595] The server initiates computation on the supercomputer. Once the computation is complete, the resulting data is generated. This data is checked by an integrity verification agent to ensure its accuracy and reliability.

[0596] Step 8:

[0597] The terminal receives the calculation results sent from the server. The system selects a method to visually display the results based on the user's emotional state. An explanatory visualization is provided, allowing the user to intuitively understand the results and gain insights for analysis.

[0598] (Application Example 2)

[0599] 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."

[0600] In modern urban environments, residents and administrators are required to make appropriate decisions using vast amounts of data. However, conventional systems have provided uniform information and decision-making support without considering the user's emotional state, which can lead to stress and confusion. This invention aims to recognize the user's emotions, adjust the computational structure and information presentation based on those emotions, and provide the user with a more personalized experience.

[0601] 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.

[0602] In this invention, the server includes means for presenting an optimal computational structure, means for converting a specified computational code into a format executable by a high-speed computer, and means for recognizing the user's emotional state and optimizing the presentation of the computational structure and results based on that state. This enables the provision of customized information according to each user's emotional state.

[0603] An "optimal computational structure" is a theoretical framework for selecting the computational model or algorithm that best suits the user's specific needs and objectives.

[0604] "Condition setting" is a procedure for controlling the accuracy and efficiency of calculations by setting initial values ​​and ranges of variation for each element in the calculation structure.

[0605] A "high-speed computer" is a computer system that can process vast amounts of data and perform complex calculations quickly.

[0606] "Systematic management of resource use" refers to management techniques that optimize the use of computing power, memory, and other resources necessary for computation, thereby enabling efficient and effective computation.

[0607] A "simulated experiment" is a computational method used to virtually reproduce real-world events and predict their behavior and results.

[0608] "Recognizing emotional state" is a technology that analyzes information such as a user's facial expressions and voice tone to determine their psychological state.

[0609] "Optimizing information presentation" means adjusting the way calculation results and data are displayed and their content according to the user's emotional state, providing information in a way that is easy for the user to understand and beneficial to them.

[0610] In this embodiment of the invention, an application system for use by residents and city administrators is constructed based on data from a smart city environment. The server selects the optimal computational structure based on the user's emotional state and efficiently processes the relevant information. In this process, a high-speed computer is essential for computation execution and data processing.

[0611] The server performs simulation experiments using a high-speed computer and sends the results to the user's terminal. During this process, it recognizes the user's emotional state and optimizes the information presentation. For example, if the user is experiencing stress regarding traffic information or public services, it provides reassuring route recommendations and service information. The terminal then presents the data visually in a way that is easy for the user to understand.

[0612] Specifically, the hardware will consist of high-speed computers equipped with multi-core processors, and user terminals will include smartphones and smart glasses. For software, emotion recognition will utilize Microsoft Azure's Face API and voice tone analysis capabilities.

[0613] An example of a prompt message might be, "Please tell me how to suggest an optimized commute route when a user is experiencing stress." Based on this, the system provides information tailored to the user's needs. It can intuitively present a variety of options to users aiming to shorten their commute time or improve comfort.

[0614] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0615] Step 1:

[0616] The server receives initial input data and sentiment information from the user's terminal. The input data includes questions and requirements related to transportation and public services. The sentiment engine analyzes the user's facial expressions and voice to determine their emotional state and adds the results to the data. The output is a dataset containing the emotional states for selecting the necessary computational structure.

[0617] Step 2:

[0618] The server uses a dataset containing emotional states to select the optimal computational structure. This process analyzes the data using a generative AI model and configures a computational structure tailored to the user's needs. The output is the selected computational model and its initial configuration parameters.

[0619] Step 3:

[0620] The server uses the computation model and initial parameters to generate computation code for the high-speed computer. Here, transformations are performed to optimize parallel processing. The output is code in a format executable on the high-speed computer.

[0621] Step 4:

[0622] The server sends code to a high-speed computer to perform the necessary simulations and data processing. The calculation results are returned to the server and output as simulation data.

[0623] Step 5:

[0624] The server analyzes the simulation results and optimizes them while taking the user's emotional state into consideration. Here, the focus is on presenting information in a way that reassures the user, for example, by offering flexible transportation route options. The output is data that can be presented in a way that minimizes user stress.

[0625] Step 6:

[0626] The terminal visually presents information based on optimized data received from the server. Users can review the presented data and route suggestions and make selections as appropriate. The output is easy to understand and visualized, better meeting the user's needs.

[0627] 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.

[0628] 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.

[0629] 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.

[0630] [Fourth Embodiment]

[0631] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0632] 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.

[0633] 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).

[0634] 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.

[0635] 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.

[0636] 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).

[0637] 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.

[0638] 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.

[0639] 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.

[0640] 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.

[0641] 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.

[0642] 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.

[0643] 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".

[0644] This invention provides a system that allows users to easily utilize the computing power of supercomputers. This system automates a series of processes, from selecting a computational model to verifying the results, by utilizing multiple AI agents. Specific embodiments of this system are described below.

[0645] First, users access the computing system through a terminal and input the purpose of the calculation and the dataset. This data can be used for a wide range of purposes, including scientific research, new drug development, and engineering analysis.

[0646] Based on this input data, the server launches a model selection agent. The model selection agent consults a database of available mathematical models and algorithms and automatically selects the model best suited to the user's purpose. The selected model is then presented to the user via the terminal.

[0647] Next, the server uses a parameter tuning agent to calculate the optimal parameters for the selected model. This parameter tuning is crucial for improving the accuracy and efficiency of the calculations, and the agent's automated estimation allows even users without specialized knowledge to start calculations under optimal conditions.

[0648] Subsequently, based on the computational model and parameters, the server activates a supercomputer conversion agent. This agent converts the user's input code and data into a format that can be efficiently executed on a supercomputer. This conversion process involves parallelization and memory optimization.

[0649] As a concrete example, consider molecular simulations used to predict drug efficacy in new drug development. The user simply inputs information about the molecule to be simulated, and the system automatically selects the optimal molecular model, sets appropriate temperature and pressure parameters, and converts the data into a format suitable for a supercomputer.

[0650] This allows users to fully utilize the computing power of a high-performance supercomputer without requiring specialized programming or simulation knowledge. Finally, the system can verify the calculation results and present them to the user in an easy-to-understand visual format. It can also provide feedback tailored to the user's objectives, enabling rapid incorporation into further research and development.

[0651] The following describes the processing flow.

[0652] Step 1:

[0653] The user accesses the system using a terminal and inputs the information and datasets necessary for the calculation. This includes specifying, for example, molecular structure information and the purpose of the simulation.

[0654] Step 2:

[0655] The server launches a model selection agent based on the input information. This agent searches the database for appropriate computational models and algorithms and presents the best option for the user's purpose.

[0656] Step 3:

[0657] The user reviews the presented model and, if necessary, enters additional conditions or requests via the terminal. This input allows the system to configure a more specific model to meet the user's needs.

[0658] Step 4:

[0659] The server uses a parameter tuning agent to set the optimal parameters for the selected model. This agent automatically calculates the parameters based on the model's characteristics and input data.

[0660] Step 5:

[0661] The server activates a supercomputer conversion agent and performs code conversion based on the model and parameters. This process optimizes the user's input code for supercomputers and converts it into a format that can be computed in parallel.

[0662] Step 6:

[0663] The server checks the available computing resources in the scheduling agent and determines the optimal timing for execution. This agent compares and allocates resources efficiently compared to other computing tasks.

[0664] Step 7:

[0665] The server initiates calculations on the supercomputer, and the simulation agent processes the data. The system ensures stability by saving the ongoing data as needed.

[0666] Step 8:

[0667] The server transfers the simulation results to the verification agent for consistency checks. This process verifies the accuracy of the results.

[0668] Step 9:

[0669] The device displays verified results to the user, presenting the data in an easy-to-understand visual format. The user can review the details and, if necessary, be instructed to take the next steps.

[0670] (Example 1)

[0671] 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".

[0672] In fields requiring complex calculations and simulations, a problem exists in that users without specialized knowledge find it difficult to fully utilize the capabilities of high-performance computers. Traditional methods require a specialized understanding of mathematical models, computational parameter selection, and code optimization, which is considered a high hurdle for users. As a result, there are many cases where high-performance computing resources are not effectively utilized.

[0673] 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.

[0674] In this invention, the server includes means for proposing an optimal mathematical model based on the purpose entered by the user, means for automatically adjusting parameters based on the selected mathematical model, and means for converting the input code into an optimized format executable on the computer. This allows the user to make full use of the capabilities of a high-performance computer without specialized knowledge.

[0675] A "mathematical model" is an abstract theoretical framework that expresses real-world phenomena using mathematical methods, making them analyzable through calculations and simulations.

[0676] A "parameter" is a variable in a mathematical model or algorithm that sets specific conditions or characteristics and affects the calculation results or the behavior of the simulation.

[0677] An "input code" is a program description that outlines the instructions to be given to a computer, and it represents a set of calculation procedures.

[0678] A "computer" is a physical or virtual machine used to process data and perform calculations and analyses, and generally includes a processor and memory.

[0679] "Optimization" is the process of adjusting available resources and conditions to the best possible state in order to improve the performance of a system or process.

[0680] A "user" is an entity that operates a system or software and utilizes its functions to achieve a specific purpose.

[0681] "Visualization" is a technique that presents information in an easily understandable way to users by representing calculation results and data in the form of graphs, diagrams, and other visual representations.

[0682] "Efficient" refers to a state in which the greatest results can be obtained with the fewest resources, or a method for achieving such a state.

[0683] This invention is a system for users to perform complex calculations using high-performance computers, and is designed to facilitate large-scale data processing and analysis by utilizing supercomputers. The central element of the system is multiple agents, each operated by a server, which cooperate to automate the selection of computational models, parameter adjustment, and code conversion.

[0684] Users access the interface using a terminal and input calculation objectives and required data into the system using prompt messages. It is recommended that these prompt messages clearly state specific needs. For example, by entering a prompt message such as "I would like to perform a simulation using the following molecular information for new drug development," the system will select the most suitable mathematical model for that purpose and prepare to begin the necessary calculations.

[0685] The server uses configured software to analyze the input data and select the most suitable mathematical model from the database to meet the user's requirements. This process is streamlined by utilizing generative AI models, ensuring highly accurate selection by referencing similar past cases and the latest algorithms.

[0686] Parameter tuning for the selected mathematical model is performed by a dedicated agent on the server, automatically making the necessary configuration changes to maximize computational accuracy and efficiency. This allows users to continue calculations under optimized conditions without requiring any manual adjustments.

[0687] Furthermore, the server converts the user-provided input code, preparing it for execution on a supercomputer. This conversion process includes parallelization and optimization of memory usage, enabling rapid computation even for large datasets.

[0688] This invention enables users to utilize a high-performance computing environment without specialized knowledge, thereby saving considerable time and effort while obtaining accurate and rapid simulation results.

[0689] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0690] Step 1:

[0691] The user accesses the computing system using a terminal and inputs specific calculation objectives and data through prompts. The input data includes, for example, molecular information necessary for new drug development. Based on this information, the user requests a calculation task from the system. The user's input is sent to the server, and processing begins.

[0692] Step 2:

[0693] The server analyzes the received input data and selects the optimal mathematical model using a generated AI model. During this process, the server refers to an internal model database and automatically selects the model best suited to the user's computational objectives. The selected mathematical model, resulting from the data analysis, is then output.

[0694] Step 3:

[0695] The server activates a parameter tuning agent based on the selected mathematical model. The agent automatically calculates appropriate parameters according to the input data and model requirements. For example, in molecular simulations, temperature and pressure parameters are set. This tuning ensures the model achieves maximum accuracy and performance. The tuned parameters are then output for the next process.

[0696] Step 4:

[0697] The server activates a supercomputer conversion agent based on parameters and mathematical models. This agent converts the input code into a format that can run efficiently on a supercomputer. This process involves parallelization and memory optimization of the code. The converted executable code is output, ready for execution on the supercomputer.

[0698] Step 5:

[0699] The server sends the prepared executable code to the supercomputer and starts the calculation. The server monitors the progress of the calculation and manages resources as needed. Once the calculation is complete, the results are returned to the server.

[0700] Step 6:

[0701] The server analyzes the calculation results and verifies their accuracy through a results verification agent. The analysis results are then visualized and presented to the user via a terminal. The user reviews the results based on the provided visual information and provides feedback as needed. This feedback is then incorporated into the system's next processing cycle.

[0702] (Application Example 1)

[0703] 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".

[0704] The challenge lies in performing real-time analysis of complex traffic and energy consumption data in urban environments to enable efficient and appropriate responses. Conventional systems require enormous computing power, making it difficult to select appropriate models and set parameters without specialized knowledge, thus hindering real-time analysis. This results in problems such as the inability to respond quickly to sudden traffic congestion or peak energy consumption.

[0705] 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.

[0706] In this invention, the server includes means for proposing an optimal computational model, means for collecting and analyzing traffic information and energy consumption information within the urban environment, and means for providing the analysis results to the user via a terminal. This enables real-time analysis of complex urban environment data and supports efficient infrastructure operation.

[0707] "The primary method for proposing the optimal computational model" refers to a technology that automatically presents the best computational model for problem solving using an algorithm that selects an appropriate mathematical model based on the user's input information.

[0708] "A second method for setting parameters based on the proposed computational model" refers to an automated estimation technique for setting optimal parameters for the selected model and improving the accuracy and efficiency of the calculations.

[0709] "A third method for converting specified computational code into a format executable on high-performance computing devices" refers to a technology that performs conversion, including parallelization and memory management, in order to efficiently execute input code or data on high-performance computing devices.

[0710] The "fourth means of systematically managing resource usage" refers to management techniques for efficiently allocating computing resources and performing necessary calculations while maintaining optimal performance.

[0711] The "fifth method of performing analysis on a high-performance computing device" is a technique that uses the converted code to perform data analysis on a device with advanced computing capabilities.

[0712] The "sixth method for verifying the consistency of analysis results" refers to verification techniques for confirming that the obtained analysis results are accurate and consistent.

[0713] The "seventh method for collecting and analyzing traffic and energy consumption information within urban environments" refers to a technology that monitors traffic and energy usage in cities, analyzes this information, and derives patterns.

[0714] The "eighth method of providing analysis results to users via a terminal" is a technology that visually organizes the analyzed information in an easy-to-understand manner and provides it to users via their terminals.

[0715] In the system implementing this invention, the server first receives urban environment-related data entered by the user. This data includes traffic information and energy consumption information. Based on this input data, the server executes a program to select the optimal mathematical model. In this process, cloud AI platforms such as Azure Machine Learning and Amazon SageMaker are used to select the mathematical model.

[0716] After selecting a mathematical model, the server optimizes the parameters on the cloud platform and converts the code for execution on a supercomputer. This conversion process optimizes parallel processing and memory management, generating code that runs efficiently on high-performance computing devices.

[0717] Furthermore, the server uses the generated analysis algorithms to predict traffic congestion and detect peak energy consumption in real time. These results are then presented to the user's device in an easily understandable visual format. The device displays the analysis results in the form of charts and graphs, providing a convenient interface for everyday use.

[0718] A concrete example would be a scenario where a server monitors road congestion in a city and suggests the most suitable alternative route to the user. It could also suggest the best time to use air conditioning on hot days. Through such systems, we aim to improve the efficiency and comfort of urban life.

[0719] An example of a prompt to input into a generative AI model might be: "Using one week's worth of urban traffic data and weather forecasts, predict traffic congestion for the coming weekend."

[0720] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0721] Step 1:

[0722] Users input urban environmental data, such as traffic information and energy consumption data, into the server via their terminals. This data forms the basis for the analysis process across the entire system. The server receives this data and stores it in a database.

[0723] Step 2:

[0724] The server sends the received data to a cloud AI platform, which selects the optimal mathematical model. In this process, the generated AI model chooses algorithms suitable for traffic congestion prediction and energy consumption analysis. This enables the selection of the optimal model according to the user's requirements. The input is urban environment data, and the output is the selected mathematical model.

[0725] Step 3:

[0726] The server sets the model parameters based on the selected mathematical model. In this step, it receives the selected model data as input and calculates the optimized parameters. This output is saved for use in the next analysis step. This is done efficiently by utilizing the automated optimization function of the cloud AI platform.

[0727] Step 4:

[0728] The server uses the constructed mathematical model and parameters to convert the user-specified computation code into a format executable on a high-performance computer. The input consists of the mathematical model, parameters, and computation code, while the output is the converted code that can be executed on the computer. The conversion is performed with parallel processing optimization in mind.

[0729] Step 5:

[0730] Using the converted code, the server performs analysis on a high-performance computing device. Here, the data for analysis is real-time urban environmental information, and the output consists of prediction results and analysis results.

[0731] Step 6:

[0732] The server verifies the consistency of the obtained analysis results. This involves a process that uses data validation algorithms to ensure the accuracy and consistency of the results. The input to this step is the analysis results, and the output is the validated data.

[0733] Step 7:

[0734] Finally, the server sends the verified analysis results to the user's terminal. The terminal displays these results visually, providing information in an easy-to-understand format for the user. Examples of analysis results provided include traffic congestion predictions and power consumption advice.

[0735] 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.

[0736] This invention provides a system that enables a wide range of users to utilize the computing power of supercomputers, and is particularly characterized by its combination with an emotion engine that recognizes user emotions and optimizes the system's behavior based on that emotion information. This system utilizes multiple AI agents and the emotion engine to perform tasks from selecting a computational model to verifying the results. The following describes a specific embodiment of this system.

[0737] First, the user accesses the system via a terminal and registers the calculation project they wish to run. During this process, the emotion engine recognizes the user's emotional state by analyzing their facial expressions and voice tone. This emotional information is then used to adjust the overall operation of the system.

[0738] The server activates a model selection agent based on data received from the user. The emotion engine reflects the user's expectations and stress levels and selects a computational model appropriate to the user's emotions. This process allows for adjustments, such as selecting a more robust model if the user is feeling anxious.

[0739] Next, the server uses a parameter tuning agent to set the optimal parameters for the selected model. Based on the information from the emotion engine, the visualization and presentation methods are also adjusted to support the user's intuitive understanding.

[0740] Subsequently, the supercomputer conversion agent operates, transforming the given model and parameters into a format that can be efficiently executed on a supercomputer. Even during this conversion process, the emotion engine flexibly modifies the conversion method according to user requests.

[0741] As a concrete example, consider a case where a user performs a predictive simulation for a new product. If the emotion engine determines that the user's level of tension is high, the system will select a conservative model that reduces risk in the model selection process and operate in a way that presents the calculation results in a stable manner.

[0742] Finally, after the simulation is complete, the server checks the results using a consistency verification agent. The terminal then displays the results in a visually easy-to-understand format, providing further insights by adding explanations that are sensitive to the user's emotions.

[0743] In this way, by combining it with an emotion engine, we can provide a user experience different from conventional systems and support the effective use of computation.

[0744] The following describes the processing flow.

[0745] Step 1:

[0746] Users access the system using a terminal and input information about the calculation project they wish to undertake. Along with the calculation data, they provide facial expressions and voice tone via camera and microphone.

[0747] Step 2:

[0748] The device sends the collected user emotion data to an emotion engine, which analyzes the user's emotional state. The emotion engine determines whether the user is stressed, relaxed, or otherwise.

[0749] Step 3:

[0750] Based on information from the emotion engine, the server activates a model selection agent to select a computational model appropriate to the user's emotions. For example, if the user is feeling anxious, it will prioritize suggesting a model that emphasizes reliability.

[0751] Step 4:

[0752] Users review the proposed model and input modifications or additional conditions as needed. This feedback is also interpreted by the emotion engine, leading to further adjustments.

[0753] Step 5:

[0754] The server uses a parameter tuning agent to set parameters for the selected model. Based on instructions from the emotion engine, the settings are configured in a way that is intuitively easy for the user to understand.

[0755] Step 6:

[0756] The server activates the supercomputer transformation agent, which converts the parameterized model into code for execution on a supercomputer. During the transformation process, it adjusts the flexibility and efficiency of the transformation based on information from the emotion engine.

[0757] Step 7:

[0758] The server uses a scheduling agent to optimize the timing and resources of calculations and to create an execution plan. It can also leverage sentiment data to adjust priorities.

[0759] Step 8:

[0760] The server starts the simulation on the supercomputer and performs the computational tasks. Data in progress is periodically saved to ensure the stability of the computation.

[0761] Step 9:

[0762] After the simulation is complete, the server verifies the consistency of the results with a validation agent and prepares to provide reliable results.

[0763] Step 10:

[0764] The device visually presents the verified results to the user, adding explanations based on the sentiment engine's judgment. This makes it easier for the user to understand the results and decide on the next action.

[0765] (Example 2)

[0766] 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".

[0767] There is a problem in that it is difficult for ordinary users to intuitively utilize high-performance computers such as supercomputers, and it is also difficult to effectively understand the results. Furthermore, conventional systems do not take into account the user's psychological state, so the operation and display of results may not match the user's expectations or understanding.

[0768] 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.

[0769] In this invention, the server includes means for analyzing the user's emotional state and adjusting the operation of the entire system, means for selecting an appropriate computational model using an emotion engine based on the analyzed emotional information, and means for setting optimal parameters for the selected computational model. As a result, the appropriate computational model and parameters are automatically selected and applied according to the user's emotional state, enabling a more user-friendly and effective understanding of the computational results.

[0770] "User emotional state" refers to the psychological or emotional state of the user as recognized by the system from the user's facial expressions, voice tone, etc.

[0771] An "emotion engine" refers to a technology that analyzes the user's emotional state and uses that information to optimize the overall operation of the system.

[0772] A "computational model" refers to a set of procedures or algorithms prepared to perform a specific computational task.

[0773] "Parameter setting" refers to the process of determining the specific numerical values ​​and settings used in the calculation model.

[0774] A "supercomputer" refers to a high-performance computer capable of performing large-scale and complex calculations at high speed.

[0775] "Visually displaying" refers to presenting information on a screen in a graphical format in order to help users understand the information.

[0776] A "consistency verification agent" refers to an automated software process used to check whether calculation results are accurate.

[0777] A "generative AI model" refers to a set of algorithms that are generated using artificial intelligence technology and perform specific information processing or data analysis.

[0778] The system in this invention is designed around the user, terminal, and server, and is intended to recognize the user's emotional state and use that to efficiently carry out computational projects.

[0779] Users access the system using a terminal to carry out computational projects. The terminal is equipped with a camera and microphone, which capture the user's facial expressions and voice tone. This data is sent to a server for later analysis by an emotion engine.

[0780] The server receives this data and uses a generative AI model to analyze the user's emotional state. For example, if the system recognizes that the user is feeling anxious, this emotional information is reflected in the selection of a computational model, ensuring that a robust model is chosen. The emotion engine plays a crucial role in this process, optimizing the overall system operation.

[0781] The selected computational model has its optimal parameters set using a parameter tuning agent. This model is then transformed by a supercomputer conversion agent into a format suitable for execution on a supercomputer. A supercomputer is a high-performance computer capable of processing large-scale and complex calculations at high speed.

[0782] The device displays the final calculation results in a visually easy-to-understand format for the user. Based on information obtained from the emotion engine, explanations are added to the results to make them easier for the user to understand. This allows the user to intuitively grasp the results and use them to aid in decision-making.

[0783] A concrete example is a market forecast simulation for a new product. An example of a prompt message might be, "Perform a market forecast simulation for the new product and select a method for presenting the results based on user sentiment."

[0784] This system aims to make the execution of computational projects more flexible and user-friendly by taking user emotions into consideration.

[0785] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0786] Step 1:

[0787] Users register their calculation projects with the system using a terminal. They enter details of the project they want to run and upload the necessary data. This information includes the calculation type, purpose, and associated datasets. Once this information is sent to the server, the project is initially configured.

[0788] Step 2:

[0789] The device collects the user's facial expressions and voice tone using its camera and microphone. This data is used as input to infer the user's emotional state. The device then transfers this information to a server for preprocessing of emotion analysis.

[0790] Step 3:

[0791] The server inputs the received facial expression and voice data into a generating AI model. This model analyzes the user's emotional state, specifically identifying emotions such as joy, surprise, and anxiety. The output provides the type and intensity of the emotion. This result is used to select a subsequent computational model.

[0792] Step 4:

[0793] The server selects an appropriate computational model by referencing the emotion engine. The user's emotional state significantly influences this selection process. For example, if the user is showing anxiety, a robust model will be chosen to ensure stable results. The results of this model selection are reflected in the parameter tuning in the next step.

[0794] Step 5:

[0795] The server sets parameters for the selected computational model. Based on the input from the emotion engine, the parameters are adjusted to produce results that are easy to understand intuitively. The adjusted parameters are output as the specific execution specifications for the model.

[0796] Step 6:

[0797] On the server, the adjusted model and parameters are converted into a format executable by the supercomputer. A supercomputer conversion agent handles this conversion, optimizing parallel processing. The converted code is generated as the final output and sent to the supercomputer.

[0798] Step 7:

[0799] The server initiates computation on the supercomputer. Once the computation is complete, the resulting data is generated. This data is checked by an integrity verification agent to ensure its accuracy and reliability.

[0800] Step 8:

[0801] The terminal receives the calculation results sent from the server. The system selects a method to visually display the results based on the user's emotional state. An explanatory visualization is provided, allowing the user to intuitively understand the results and gain insights for analysis.

[0802] (Application Example 2)

[0803] 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".

[0804] In modern urban environments, residents and administrators are required to make appropriate decisions using vast amounts of data. However, conventional systems have provided uniform information and decision-making support without considering the user's emotional state, which can lead to stress and confusion. This invention aims to recognize the user's emotions, adjust the computational structure and information presentation based on those emotions, and provide the user with a more personalized experience.

[0805] 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.

[0806] In this invention, the server includes means for presenting an optimal computational structure, means for converting a specified computational code into a format executable by a high-speed computer, and means for recognizing the user's emotional state and optimizing the presentation of the computational structure and results based on that state. This enables the provision of customized information according to each user's emotional state.

[0807] An "optimal computational structure" is a theoretical framework for selecting the computational model or algorithm that best suits the user's specific needs and objectives.

[0808] "Condition setting" is a procedure for controlling the accuracy and efficiency of calculations by setting initial values ​​and ranges of variation for each element in the calculation structure.

[0809] A "high-speed computer" is a computer system that can process vast amounts of data and perform complex calculations quickly.

[0810] "Systematic management of resource use" refers to management techniques that optimize the use of computing power, memory, and other resources necessary for computation, thereby enabling efficient and effective computation.

[0811] A "simulated experiment" is a computational method used to virtually reproduce real-world events and predict their behavior and results.

[0812] "Recognizing emotional state" is a technology that analyzes information such as a user's facial expressions and voice tone to determine their psychological state.

[0813] "Optimizing information presentation" means adjusting the way calculation results and data are displayed and their content according to the user's emotional state, providing information in a way that is easy for the user to understand and beneficial to them.

[0814] In this embodiment of the invention, an application system for use by residents and city administrators is constructed based on data from a smart city environment. The server selects the optimal computational structure based on the user's emotional state and efficiently processes the relevant information. In this process, a high-speed computer is essential for computation execution and data processing.

[0815] The server performs simulation experiments using a high-speed computer and sends the results to the user's terminal. During this process, it recognizes the user's emotional state and optimizes the information presentation. For example, if the user is experiencing stress regarding traffic information or public services, it provides reassuring route recommendations and service information. The terminal then presents the data visually in a way that is easy for the user to understand.

[0816] Specifically, the hardware will consist of high-speed computers equipped with multi-core processors, and user terminals will include smartphones and smart glasses. For software, emotion recognition will utilize Microsoft Azure's Face API and voice tone analysis capabilities.

[0817] An example of a prompt message might be, "Please tell me how to suggest an optimized commute route when a user is experiencing stress." Based on this, the system provides information tailored to the user's needs. It can intuitively present a variety of options to users aiming to shorten their commute time or improve comfort.

[0818] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0819] Step 1:

[0820] The server receives initial input data and sentiment information from the user's terminal. The input data includes questions and requirements related to transportation and public services. The sentiment engine analyzes the user's facial expressions and voice to determine their emotional state and adds the results to the data. The output is a dataset containing the emotional states for selecting the necessary computational structure.

[0821] Step 2:

[0822] The server uses a dataset containing emotional states to select the optimal computational structure. This process analyzes the data using a generative AI model and configures a computational structure tailored to the user's needs. The output is the selected computational model and its initial configuration parameters.

[0823] Step 3:

[0824] The server uses the computation model and initial parameters to generate computation code for the high-speed computer. Here, transformations are performed to optimize parallel processing. The output is code in a format executable on the high-speed computer.

[0825] Step 4:

[0826] The server sends code to a high-speed computer to perform the necessary simulations and data processing. The calculation results are returned to the server and output as simulation data.

[0827] Step 5:

[0828] The server analyzes the simulation results and optimizes them while taking the user's emotional state into consideration. Here, the focus is on presenting information in a way that reassures the user, for example, by offering flexible transportation route options. The output is data that can be presented in a way that minimizes user stress.

[0829] Step 6:

[0830] The terminal visually presents information based on optimized data received from the server. Users can review the presented data and route suggestions and make selections as appropriate. The output is easy to understand and visualized, better meeting the user's needs.

[0831] 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.

[0832] 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.

[0833] 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 robot 414.

[0834] 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.

[0835] 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.

[0836] 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.

[0837] 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.

[0838] 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.

[0839] 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."

[0840] 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.

[0841] 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.

[0842] 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.

[0843] 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.

[0844] 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.

[0845] 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.

[0846] 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.

[0847] 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.

[0848] 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.

[0849] 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.

[0850] 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.

[0851] 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.

[0852] The following is further disclosed regarding the embodiments described above.

[0853] (Claim 1)

[0854] The first method for proposing the optimal computational model,

[0855] A second method for setting parameters based on the proposed computational model,

[0856] A third means of converting a specified computation code into a format executable by a supercomputer,

[0857] A fourth method for systematically managing resource usage,

[0858] A fifth method for running simulations on a supercomputer,

[0859] A sixth method for verifying the consistency of the simulation results,

[0860] A system that includes this.

[0861] (Claim 2)

[0862] The system according to claim 1, wherein the first means uses an algorithm that selects a mathematical model based on input data received from a user.

[0863] (Claim 3)

[0864] The system according to claim 1, wherein the third means includes a transformation algorithm for optimizing the parallelization of the code.

[0865] "Example 1"

[0866] (Claim 1)

[0867] A means of proposing the optimal mathematical model based on the objective entered by the user,

[0868] A means for automatically adjusting parameters based on a selected mathematical model,

[0869] A means for converting an input code into an optimized format that can be executed on a computer,

[0870] Means for formulating a plan for efficiently managing computing resources,

[0871] Means for performing computational tasks on a high-performance computer,

[0872] A means of verifying the calculation results and presenting them to the user in a visualized format,

[0873] A system that includes this.

[0874] (Claim 2)

[0875] The system according to claim 1, comprising an algorithm for analyzing user input data in order to select the optimal mathematical model.

[0876] (Claim 3)

[0877] The system according to claim 1, comprising a conversion method for optimizing parallel processing of input codes.

[0878] "Application Example 1"

[0879] (Claim 1)

[0880] The first method for proposing the optimal computational model,

[0881] A second method for setting parameters based on the proposed computational model,

[0882] A third means of converting a specified computation code into a format executable by a high-performance computing device,

[0883] A fourth method for systematically managing resource usage,

[0884] A fifth method for performing analysis on a high-performance computing device,

[0885] A sixth method for verifying the consistency of the analysis results,

[0886] A seventh method for collecting and analyzing traffic information and energy consumption information within urban environments,

[0887] The eighth method is to provide the analysis results to the user via a terminal,

[0888] A system that includes this.

[0889] (Claim 2)

[0890] The system according to claim 1, wherein the first means is an algorithm that selects a mathematical model based on input information received from a user.

[0891] (Claim 3)

[0892] The system according to claim 1, wherein a third means includes a transformation algorithm for optimizing the parallelization of code, and efficiently processes urban environment data.

[0893] "Example 2 of combining an emotion engine"

[0894] (Claim 1)

[0895] A first method for analyzing the user's emotional state and adjusting the overall system operation,

[0896] A second method involves using an emotion engine to select an appropriate computational model based on the analyzed emotion information,

[0897] A third method for setting optimal parameters for the selected computational model,

[0898] A fourth method for transforming computational models for use with supercomputers in order to efficiently perform computational tasks,

[0899] A fifth method for performing computational processing on a supercomputer,

[0900] A sixth method for verifying the calculation results using a consistency verification agent,

[0901] A seventh method involves visually displaying results and providing explanations in a way that takes user emotions into consideration,

[0902] A system that includes this.

[0903] (Claim 2)

[0904] The system according to claim 1, wherein the second means is an algorithm that selects a computational model by taking into account the user's emotional information using an emotion engine.

[0905] (Claim 3)

[0906] The system according to claim 1, wherein the fourth means includes a program conversion algorithm for optimizing processing efficiency on a supercomputer.

[0907] "Application example 2 when combining with an emotional engine"

[0908] (Claim 1)

[0909] A first means of presenting the optimal computational structure,

[0910] A second means of setting conditions based on the presented calculation structure,

[0911] A third means for converting a specified computation code into a format executable by a high-speed computer,

[0912] A fourth means of systematically managing resource use,

[0913] A fifth method for conducting simulated experiments on a high-speed computer,

[0914] A sixth method for verifying the consistency of the results of the simulated experiment,

[0915] A seventh means of recognizing the user's emotional state and optimizing the computational structure and result presentation based on that,

[0916] A system that includes this.

[0917] (Claim 2)

[0918] The system according to claim 1, wherein the first means is a procedure for selecting a mathematical construct based on input information received from a user.

[0919] (Claim 3)

[0920] The system according to claim 1, wherein a third means includes a transformation procedure for optimizing the parallel processing of the code. [Explanation of Symbols]

[0921] 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. The first method for proposing the optimal computational model, A second method for setting parameters based on the proposed computational model, A third means of converting a specified computation code into a format executable by a high-performance computing device, A fourth method for systematically managing resource usage, A fifth method for performing analysis on a high-performance computing device, A sixth method for verifying the consistency of the analysis results, A seventh method for collecting and analyzing traffic information and energy consumption information within urban environments, The eighth method is to provide the analysis results to the user via a terminal, A system that includes this.

2. The system according to claim 1, wherein the first means is an algorithm that selects a mathematical model based on input information received from a user.

3. The system according to claim 1, wherein a third means includes a transformation algorithm for optimizing the parallelization of code and efficiently processes urban environment data.

Images