system

Abstract

We provide the system. [Solution] A means of selecting a model based on user input, A means of adjusting parameters based on the selected model, Means for converting the adjusted model and parameters into a format suitable for a supercomputer, A means of managing the computing schedule based on the usage status of the supercomputer, Means for running simulations on a supercomputer, A means of verifying and providing simulation results to users, A system that includes this.

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, including steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a chatbot character, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance in response to the user utterance.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] Calculations and simulations using high-performance supercomputers require specific expertise and are difficult for general users to utilize. Furthermore, efficient use of computing resources and complex processes such as model selection and parameter adjustment are required, which pose problems in that they require a lot of time and effort. The present invention aims to solve these problems and enable anyone to easily utilize supercomputers.

Means for Solving the Problems

[0005] This invention provides a means for selecting the optimal model based on the application input by the user. Furthermore, it includes means for automatically adjusting the parameters corresponding to the selected model and converting them into a format executable on a supercomputer. It also provides means for efficient scheduling based on the utilization status of computing resources. In this way, it provides a system that includes means for efficiently executing simulations on a supercomputer and verifying and visualizing the results, thereby solving the aforementioned problems.

[0006] A "user" is the entity that operates the system, selecting computational models and adjusting parameters.

[0007] "Model selection" is the process of presenting and selecting the optimal computational model based on user input.

[0008] "Parameter tuning" is the process of setting input variables and conditions for a selected model to optimize it for the desired purpose.

[0009] A "supercomputer" is a computer with large-scale and high-performance computing capabilities, capable of efficiently processing large amounts of calculations.

[0010] "Conversion" is the process of preparing the adjusted model and parameters into a format that can be executed on a supercomputer.

[0011] "Schedule management" is the process of planning the execution of calculations in order to efficiently allocate the resources of a supercomputer.

[0012] "Simulation execution" is the process of performing calculations on a supercomputer based on a set model and parameters, and generating results.

[0013] "Verification" is the process of analyzing the results of a simulation and confirming whether they are appropriate to the established criteria. [Brief explanation of the drawing]

[0014] [Figure 1] It 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] Shows an emotion map to which a plurality of emotions are mapped. [Figure 10] 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

[0015] Hereinafter, an example of an embodiment of the system according to the technology of the present disclosure will be described with reference to the accompanying drawings.

[0016] First, the terms used in the following description will be explained.

[0017] In the following embodiments, a labeled 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.

[0018] In the following embodiments, a labeled RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0019] In the following embodiments, a labeled 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, and the like.

[0020] In the following embodiments, the signed communication interface (I / F) is an interface that includes a communication processor and an antenna, etc. The communication interface manages communication between multiple computers. Examples of communication standards applicable to the communication interface include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0021] 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."

[0022] [First Embodiment]

[0023] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0024] 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.

[0025] 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).

[0026] 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.

[0027] 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.

[0028] 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.

[0029] 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.

[0030] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0031] 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.

[0032] 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.

[0033] 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.

[0034] 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".

[0035] This invention relates to a platform that allows users to easily perform complex calculations and simulations using high-performance supercomputers. This platform enhances efficiency by assisting with the selection of computational models, parameter tuning, conversion to supercomputers, scheduling, simulation execution, and verification through multiple AI agents.

[0036] System Overview

[0037] 1. Model selection process:

[0038] The user accesses the platform through their device and enters the project objective. Based on this input, the server selects an appropriate computational model from its database. After being presented with options, the user can choose the model that best suits their needs.

[0039] 2. Parameter adjustment process:

[0040] The server automatically sets the necessary initial parameters based on the selected model. This includes the user entering specific initial conditions and constraints into the terminal, which the server then takes into account when performing optimization.

[0041] 3. Supercomputer conversion process:

[0042] The server converts the tuned model and parameters into program code that can be processed by the supercomputer. During this process, parallel processing optimizations are performed to maximize computation speed.

[0043] 4. Schedule management process:

[0044] The server analyzes the supercomputer's usage and automatically reserves appropriate computing time. This allows users to optimally set the timing for starting calculations.

[0045] 5. Simulation execution process:

[0046] The calculation starts automatically at the scheduled time. The supercomputer executes the parallelized code and generates the results.

[0047] 6. Verification Process:

[0048] The generated simulation results are sent to a server and analyzed by a verification agent. These verification results are then visually presented to the user via a terminal, allowing the user to review the results.

[0049] Specific example

[0050] For example, if a user wants to simulate the thermal behavior of a new material, they input the material's properties into the platform. The server selects an appropriate physical model and proposes it to the user. Based on the selected model, necessary parameters (such as thermal conductivity) are adjusted, and calculations begin on the supercomputer. After the calculation, the results are verified and reported to the user via a terminal.

[0051] Through the above process, the present invention provides an environment in which even non-expert users can efficiently perform advanced calculations.

[0052] The following describes the processing flow.

[0053] Step 1:

[0054] Users access the platform from their terminals and input the project's objectives and requirements. As users input basic information about the simulation target, the server prepares to select the optimal computational model based on that information.

[0055] Step 2:

[0056] The server analyzes user input and extracts suitable computational model candidates from its internal database. The user selects the most suitable model from the list of candidates presented by the server. The selection process is interactive, and the server adjusts the information in real time based on user feedback.

[0057] Step 3:

[0058] The terminal prompts the user to make the necessary parameter adjustments based on the selected model. The user inputs detailed parameters (e.g., range, precision settings, etc.), and the server receives this information, runs an automatic optimization engine, and generates the optimal parameter set.

[0059] Step 4:

[0060] The server collects the tuned model and parameters and converts them into a format executable on the supercomputer. At this stage, optimizations are performed for code parallelization and efficient distributed processing. The converted code is stored by the server, ready for subsequent processing.

[0061] Step 5:

[0062] The server checks the status of the supercomputer currently in use and determines the time when computing resources can be used most efficiently. It automatically reserves available computing time and notifies the user of the result, informing them when to start computing.

[0063] Step 6:

[0064] When the scheduled time arrives, the server sends an instruction to the supercomputer to start the simulation. The supercomputer performs calculations using parallelized code and generates results. Throughout this process, the server monitors the progress and responds promptly if any problems arise.

[0065] Step 7:

[0066] The calculation results generated by the supercomputer are returned to the server. The server passes these results to a verification agent, which checks whether the results meet the target conditions. After verification is complete, the results are visualized and provided to the user via a terminal for final confirmation.

[0067] The detailed processes at each step are crucial elements for enhancing the efficiency and usability of this system, and are useful in research and development and industrial applications.

[0068] (Example 1)

[0069] 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."

[0070] Modern advanced computations and simulations require specialized knowledge and complex settings, making them difficult for non-experts to use. Furthermore, efficiently utilizing high-performance computing devices such as supercomputers is not easy, and optimization of resource utilization is also required.

[0071] 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.

[0072] In this invention, the server includes means for inputting a target via an information processing device and selecting an appropriate computation model; means for optimizing numerical information based on initial conditions and constraints using the selected computation model; and means for converting the optimized computation model and numerical information into a format executable by a high-performance computer. This makes it possible to efficiently perform advanced calculations even without specialized knowledge.

[0073] An "information processing device" is a terminal that receives user input and supports data processing and the selection of calculation models.

[0074] "Purpose" refers to information that indicates the specific results or project goals that the user wants to achieve.

[0075] A "computational model" is a set of computational methods and algorithms selected according to the input objective.

[0076] "Initial conditions" are numerical values ​​or settings specified as prerequisites for executing the computational model.

[0077] A "constraint" is a set of values ​​that indicate the limitations or restrictions that must be followed when executing an computational model.

[0078] "Numerical information" refers to the data set generated from the initial conditions and constraints in a computational model.

[0079] A "high-performance computing device" is a computer with high computational power to support the processing of large amounts of data and parallel computing.

[0080] "Computational processing" is the process by which a computing device uses input numerical information to perform calculations based on models and algorithms.

[0081] "Calculation results" refer to the output or data generated by a high-performance computing device after it has completed its calculation process.

[0082] This invention provides a system that allows users to easily perform advanced calculations using an information processing device, a server, and a high-performance computing device. The user begins by accessing the information processing device via a terminal and inputting their objective. Based on the input objective, the server selects an appropriate calculation model and sets initial and constraint conditions based on that model.

[0083] The server converts the selected computational model and numerical information into a format executable by high-performance computing devices. The hardware used here is a supercomputer with high computational power. The converted data is optimized for parallel processing, enabling high-speed calculations.

[0084] For example, when a user simulates the thermal behavior of a new material, they input the material's properties into the platform using a terminal. The server then selects an appropriate physical model based on this information and presents it to the user. This process provides an environment where users can perform complex simulations even without specialized knowledge.

[0085] A concrete example of a prompt message would be, "I would like to input the thermal conductivity and specific heat of a new material and perform a thermal behavior simulation." In this way, the present invention connects the user's intent with high-performance computing capabilities, enabling applications in a wide range of fields.

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

[0087] Step 1:

[0088] The user accesses the system using a terminal and inputs the project objectives into the information processing device. Specifically, the user inputs the content and conditions they want to simulate in text format. This input is sent to the server and stored as basic data for use in the next step.

[0089] Step 2:

[0090] Based on the project objectives received by the server, it searches its internal database to extract candidate computational models. The server then uses an AI algorithm to select the most relevant model from this input data. This process allows the user to view a list of selectable computational models on their device.

[0091] Step 3:

[0092] The user selects the most appropriate computational model from the candidates presented by the server on their terminal. The selected model is verified on the server, and initial conditions and constraints related to each model are set. This information is stored by the server for use in the next step.

[0093] Step 4:

[0094] Based on the initial conditions and constraints entered by the user, the server optimizes numerical information. Specifically, it uses AI to automatically calculate the initial parameters best suited to the user's objective. These optimized parameters are then prepared for processing on a supercomputer.

[0095] Step 5:

[0096] The server converts the optimized computational model and parameters into a format executable by high-performance computing devices. During this process, the server optimizes parallel processing to maximize computation time efficiency. The converted data is then prepared for transfer to the supercomputer.

[0097] Step 6:

[0098] The server analyzes the usage and load of high-performance computing devices and reserves the optimal computing time. This process is performed automatically by the server's scheduling system, and users can check the start time of the calculation on their terminal.

[0099] Step 7:

[0100] According to the reserved time slot, the supercomputer begins executing the parallelized model. The high-performance computing device rapidly processes the data and generates the calculation results.

[0101] Step 8:

[0102] The server receives the calculation results sent from the supercomputer and evaluates the integrity and validity of the data. The server uses AI to verify the results and sends this verified data back to the terminal.

[0103] Step 9:

[0104] The user receives visual data provided by the server via their terminal and checks the results. This allows the user to properly analyze the results of the calculations and use them as input for the next stage of the project.

[0105] (Application Example 1)

[0106] 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."

[0107] Controlling robots and optimizing manufacturing processes in factories requires advanced technology and specialized knowledge, making it difficult for typical end-users to easily perform these tasks. Furthermore, efficient complex calculations and simulations using high-performance computing devices require resource management and systematic scheduling. Therefore, there is a need to provide an operational environment that is easily accessible even to non-professional users.

[0108] 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.

[0109] In this invention, the server includes means for selecting a computational model based on user input, means for converting the adjusted computational model and initial parameters into a format suitable for a high-performance computing device, and means for managing the computation schedule and efficiently allocating the resources of the high-performance computing device. This enables end users to efficiently perform tasks such as optimizing the operation of factory robot arms using a high-performance computing device without requiring specialized knowledge.

[0110] "User input" refers to the act of a user providing the conditions and parameters necessary for a calculation model or simulation via a terminal.

[0111] "Means for selecting a computational model" refers to a method for identifying the most suitable computational model based on the provided conditions.

[0112] "Means for adjusting initial parameters" refers to methods for setting necessary initial values ​​and constraints for a selected computational model and optimizing it.

[0113] "Means of converting to a format suitable for high-performance computing devices" refers to a method of converting the adjusted model and parameters into a code format that can be processed by a high-performance computer.

[0114] "Means of managing computation schedules" refers to a method of investigating the available time and resources of high-performance computing devices and creating a schedule that enables efficient computation execution.

[0115] "Means for efficiently allocating resources of high-performance computing devices" refers to a method of allocation that uses computing resources without waste and optimizes processing time and load.

[0116] "Means of providing an operable interface" refers to a method that allows users to intuitively manipulate and visualize calculation and simulation results in an understandable format.

[0117] The system of this invention is designed to enable users to efficiently perform complex simulations on a high-performance computing device using a terminal. A specific embodiment is described below.

[0118] The server first receives input from the user and selects a computational model from the database based on that input. For the selected model, it automatically adjusts the parameters based on the initial parameters and constraints further set by the user. At this stage, the software used includes optimization algorithms to rapidly process the data.

[0119] The server translates the adjusted computational model and parameters into code that can be executed on high-performance computing devices such as supercomputers. This translation process involves constructing the code with particularly high-speed parallel processing in mind.

[0120] The terminal provides users with a visually user-friendly interface and displays simulation results in real time. A concrete example of the results is the simulation of robot arm movements that contribute to factory efficiency. This simulation provides the optimal movement pattern by taking into account the characteristics of the parts being handled and the balance of the movement speed.

[0121] When using a generative AI model, the following example prompts apply:

[0122] "I would like to perform an operation simulation to optimize the robot arm. Please provide the current operating time, error, and constraints, and perform a simulation to achieve maximum efficiency."

[0123] This allows users to obtain optimal results by leveraging the advantages of high-performance computing devices, even without advanced expertise.

[0124] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0125] Step 1:

[0126] The user logs into the system using a terminal and starts the project. In this step, the user inputs the operating conditions and constraints of the robot arm they want to simulate. The entered data reflects the user's intentions and goals, and this serves as the basis for processing in the next step.

[0127] Step 2:

[0128] The server receives input data from the user, analyzes it, and selects the optimal computational model from the database. This selection process utilizes generative AI models to quickly identify the model best suited to the user's needs. The selected model is then returned to the server as output.

[0129] Step 3:

[0130] The server optimizes the initial parameters for the selected computational model. Here, it considers the operating conditions and constraints provided by the user and adjusts the initial parameters accordingly. Specifically, it receives the parameter range and constraints as input, applies an optimization algorithm, and outputs the optimal initial parameters.

[0131] Step 4:

[0132] The server converts the tuned model and parameters into a format suitable for high-performance computing devices. Code optimization is performed here to maximize the use of parallel processing. At this stage, the tuned model is received as input, and highly efficient executable code is generated.

[0133] Step 5:

[0134] The server monitors the operational status of the high-performance computing units and prepares to run simulations at the most appropriate schedule. The input here is the latest resource status of the computing units, and based on this information, the optimal timing for starting calculations is output.

[0135] Step 6:

[0136] A high-performance computing unit performs calculations at scheduled times and generates simulation results. The output simulation results include detailed analysis based on user-defined conditions.

[0137] Step 7:

[0138] The server receives the generated simulation results and performs verification and evaluation. This process uses verification algorithms to assess the reliability and validity of the results. The input is the simulation data, and the output is the evaluated results report.

[0139] Step 8:

[0140] Finally, the server sends the evaluation results to the terminal and provides them to the user in a visualized format. A user interface is used here to clearly display the results. The input is the evaluated result data, and the output is user-friendly visual information.

[0141] 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.

[0142] This invention is a system that enhances the user experience when users perform advanced calculations and simulations using a supercomputer by combining it with an emotion engine. This system utilizes emotion recognition technology to dynamically adjust the interface and feedback according to the user's emotional state, thereby increasing work efficiency and comfort.

[0143] System Overview

[0144] 1. Emotion recognition process:

[0145] The emotion engine uses the camera and sensors on the device to analyze the user's facial expressions and behavior in real time. Based on this data, the server identifies the user's emotional state and prepares that information for use throughout the system.

[0146] 2. Interface adjustment process:

[0147] The server receives feedback from the emotion engine and, if it determines that the user is experiencing stress, changes the interface to be more intuitive and easier to use. This includes simpler navigation and highlighted operation guides.

[0148] 3. Optimizing the simulation process:

[0149] The server modifies the simulation's progression based on the user's emotional state. For example, if the user is showing signs of anxiety, the server simplifies the process and presents the progress in an easy-to-understand manner to increase the user's sense of security.

[0150] 4. Feedback process:

[0151] After the results are generated, the server customizes the feedback based on the sentiment analysis results from the sentiment engine. This feedback is delivered to the user via the device, providing appropriate advice and suggestions for improvement.

[0152] Specific example

[0153] For example, suppose a user is performing a complex aircraft performance simulation and the emotion engine detects a decrease in the user's concentration. In this situation, the server simplifies the simulation screen and hides unnecessary information, allowing the user to focus only on the target parameters.

[0154] Thus, by integrating an emotion engine, the present invention provides a system that enhances the user experience by realizing high-performance computational support that is attuned to the user's emotions.

[0155] The following describes the processing flow.

[0156] Step 1:

[0157] The user operates a terminal to access the system and input the project's objectives and data. This input completes the initial setup, and the server prepares to search for candidate computational models.

[0158] Step 2:

[0159] The device uses its built-in camera and microphone to record the user's facial expressions and voice intonation in real time. The emotion engine analyzes this recorded data to identify the user's current emotional state. The server receives this information and prepares to adjust the interface and processes.

[0160] Step 3:

[0161] The server selects candidate computational models from the database based on user input and sends a list of candidates to the terminal. The user reviews this list on the terminal and selects the most suitable model. After selection, the server provides further feedback and processing advice.

[0162] Step 4:

[0163] Based on information from the emotion engine, the server provides an interface optimized for the user's emotional state. If the user shows signs of frustration, the server highlights the operation guide or simplifies the operation procedure to make it easier to understand.

[0164] Step 5:

[0165] Once the user selects a model and inputs the necessary data into the terminal, the server automatically adjusts the parameters and converts the code into a format that can be processed by a supercomputer. Optimizations such as parallel processing are also performed at this stage.

[0166] Step 6:

[0167] The server optimizes the simulation's progress in real time based on emotional data. For users exhibiting impatience, it provides reassurance by displaying detailed processing status and clearly showing the progress.

[0168] Step 7:

[0169] After the supercomputer runs the simulation and generates results, the server verifies the results and forms feedback. The verification takes into account the analysis results of the emotion engine, and the most relevant detailed information and improvements are provided to the user through the terminal.

[0170] Through these steps, the present invention provides a support environment for performing advanced calculations and simulations while taking into consideration the user's emotions.

[0171] (Example 2)

[0172] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0173] Modern high-performance computing systems require improved efficiency and user comfort when performing complex calculations. However, conventional systems proceed with calculations in a uniform manner regardless of the user's emotional state, lacking care, especially in situations where users feel stressed or anxious, and failing to provide an optimal user experience.

[0174] 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.

[0175] In this invention, the server includes means for analyzing the user's emotional state, means for dynamically changing user information based on the user's emotions, and means for optimizing computational processing according to the user's emotional state. This makes it possible to provide management and feedback that is sensitive to the user's emotions, thereby improving computational efficiency and user experience.

[0176] A "computational model" is a set of algorithms or mathematical formulas constructed to achieve a specific computational objective.

[0177] "Numerical elements" refer to the parameters and variables in a computational model, and are values ​​that affect the calculation results.

[0178] "High-performance computing systems" refer to supercomputers and cluster computers designed to process large-scale calculations quickly and efficiently.

[0179] "Computational work" refers to the entire series of computational processes performed using a computational model.

[0180] "Emotion recognition technology" is a technology that analyzes a user's emotional state from their facial expressions, voice, and behavior.

[0181] "Dynamically changing user information" means adjusting the interface and output information in real time according to the user's emotional state.

[0182] "Efficient resource allocation" means allocating limited resources, such as computing resources and time, in a way that makes the most effective use of them.

[0183] The embodiments for carrying out the present invention will be described in detail below.

[0184] The user first uses a terminal to operate a high-performance computing system. This terminal has built-in cameras and sensors to capture the user's facial expressions and movements. The data acquired from these devices is input into the emotion recognition system in real time.

[0185] The server receives data sent from the terminal and analyzes the user's emotional state using a generative AI model. This model utilizes facial recognition software and voice analysis algorithms to identify emotions such as stress and joy. Once the emotional state is identified, the server dynamically adjusts the user interface based on that information. For example, if the user is showing signs of stress, the server simplifies navigation to make it more intuitive and highlights important information.

[0186] Furthermore, the server optimizes the progress of calculations while taking into account the user's emotional state. Specifically, if the server determines that the user is in a state of impatience, it simplifies the calculation process and supports the user by visually displaying intermediate results.

[0187] Once the calculation results are generated, the server customizes the feedback based on the emotion recognition results, providing advice and a roadmap to the next steps tailored to the user's state. The device receives this feedback and displays it appropriately to the user.

[0188] A concrete example is when a user is performing a weather forecast simulation; the system evaluates the user's emotional state and optimizes the display of information as needed to facilitate the process.

[0189] An example of a prompt message is, "How can we use emotion recognition to provide efficient support when a user runs a simulation?" Such a framework allows users to utilize high-performance computing systems more comfortably.

[0190] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0191] Step 1:

[0192] The device collects the user's facial expressions and movements using cameras and sensors. This input data includes facial image data and audio data. The device then preprocesses this data, removing data noise and converting it into a format suitable for analysis. A clean dataset is generated as output.

[0193] Step 2:

[0194] The server receives a pre-processed dataset sent from the terminal. The server inputs this data into a generating AI model, which analyzes the user's emotional state in real time. The data calculations performed here output the user's emotional state in the form of "stress" or "decreased concentration."

[0195] Step 3:

[0196] The server dynamically adjusts the user interface based on the analysis of the user's emotional state. Specifically, the server can reorganize the interface, transforming it into a simpler, more user-friendly interface. For example, if stress is detected, the system highlights important items and eliminates complex slide menus. The resulting output is the adjusted interface settings.

[0197] Step 4:

[0198] The server optimizes calculations based on the user's emotional state. This process simplifies calculation steps and redesigns how intermediate results are presented, particularly for users exhibiting anxiety. The output consists of user-friendly intermediate results.

[0199] Step 5:

[0200] The terminal presents the user with feedback information received from the server. This includes advice that takes emotional state into account and guidance on the next steps. The terminal displays this information in an optimized interface to support the user's actions. The final output is personalized feedback information for the user.

[0201] (Application Example 2)

[0202] 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".

[0203] Conventional calculation and simulation systems often fail to consider the user's emotional state, making it difficult to improve the user experience. Furthermore, complex interfaces can cause user stress and reduce work efficiency. There is a need for systems that address these challenges and enhance both user comfort and efficiency.

[0204] 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.

[0205] In this invention, the server includes means for detecting an emotional state and providing an appropriate interface, means for dynamically changing the operation panel based on the emotional state, and means for verifying and providing simulation results to the user. This enables automatic adjustment of the interface according to the user's emotional state, thereby reducing user stress and improving work efficiency.

[0206] A "user" refers to a person who uses the system to perform calculations or simulations.

[0207] A "model" refers to a set of hypotheses or designs used for calculations or simulations selected by the user.

[0208] "Parameters" refer to numerical values ​​or variables used to adjust the behavior of a model.

[0209] "Large-scale computing equipment" refers to devices such as supercomputers that are used to process large amounts of data and perform advanced calculations.

[0210] A "calculation schedule" refers to a plan for managing the order and timing of calculations.

[0211] "Emotional state" refers to the user's mental state or mood, and the information detected by the emotion engine.

[0212] "Interface" refers to the screen or operating environment that a user uses to interact with a system.

[0213] The term "control panel" refers to a part of the interface that allows users to operate various functions of a system.

[0214] "Simulation results" refers to calculation results and analysis data obtained by large-scale computing devices.

[0215] This invention is a system that utilizes emotion recognition technology to dynamically adjust the system's interface and functions according to the user's emotional state, thereby improving the user experience when using large-scale computing devices. This system is realized through the roles of the server, terminal, and user.

[0216] The server uses an emotion recognition engine to analyze the user's emotional state in real time. It acquires the user's facial expressions and actions from cameras and sensors and identifies their emotional state based on this information. Based on this information, it adjusts the interface and control panel according to the user's emotional state. If the user is feeling stressed, the server simplifies the control panel and changes the interface to display only the most important information.

[0217] The terminal is responsible for sending and receiving emotional state data between the user and the server, and displaying the simulation results. Users can interact with the system through the terminal and receive customized feedback tailored to their emotional state.

[0218] For example, if the system detects that a user is showing signs of fatigue while operating a robot in a factory, it will simplify the interface and reduce visual strain. Another example of a prompt to input into the generating AI model is, "How would you modify the interface if the user is experiencing stress?" This makes it possible to provide an experience that is sensitive to the user's emotions.

[0219] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0220] Step 1:

[0221] The server acquires user facial expression data from the terminal's camera and sensors. The input is the user's real-time video. The server processes this video data and uses facial recognition technology to extract the user's facial features. Based on this, it makes an initial judgment about the user's emotional state.

[0222] Step 2:

[0223] The server uses an emotion recognition engine to analyze the user's emotional state from extracted facial features. The input for this step is facial features, and the output is the user's emotional state (e.g., concentration, fatigue, stress). Data analysis techniques are used to classify specific facial patterns into emotional categories.

[0224] Step 3:

[0225] The server dynamically adjusts the interface based on the analysis results. The input is the emotional state obtained in the previous step, and the output is the modified user interface. When the user is stressed, the server hides visually complex elements and highlights only important information.

[0226] Step 4:

[0227] The terminal presents the user with a pre-configured interface received from the server. At this stage, the interface display is optimized to the user's needs. The input is the interface data received from the server, and the output is its visual representation. The terminal renders the interface in a way that allows the user to operate it intuitively.

[0228] Step 5:

[0229] Users manipulate and verify simulation results using a tailored interface. User input is the response to the operation, and output is feedback and data viewing corresponding to that response. Users efficiently take actions to achieve their goals.

[0230] 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.

[0231] 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.

[0232] 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.

[0233] [Second Embodiment]

[0234] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0235] 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.

[0236] 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).

[0237] 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.

[0238] 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.

[0239] 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).

[0240] 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.

[0241] 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.

[0242] 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.

[0243] 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.

[0244] 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.

[0245] 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".

[0246] This invention relates to a platform that allows users to easily perform complex calculations and simulations using high-performance supercomputers. This platform enhances efficiency by assisting with the selection of computational models, parameter tuning, conversion to supercomputers, scheduling, simulation execution, and verification through multiple AI agents.

[0247] System Overview

[0248] 1. Model selection process:

[0249] The user accesses the platform through their device and enters the project objective. Based on this input, the server selects an appropriate computational model from its database. After being presented with options, the user can choose the model that best suits their needs.

[0250] 2. Parameter adjustment process:

[0251] The server automatically sets the necessary initial parameters based on the selected model. This includes the user entering specific initial conditions and constraints into the terminal, which the server then takes into account when performing optimization.

[0252] 3. Supercomputer conversion process:

[0253] The server converts the tuned model and parameters into program code that can be processed by the supercomputer. During this process, parallel processing optimizations are performed to maximize computation speed.

[0254] 4. Schedule management process:

[0255] The server analyzes the supercomputer's usage and automatically reserves appropriate computing time. This allows users to optimally set the timing for starting calculations.

[0256] 5. Simulation execution process:

[0257] The calculation starts automatically at the scheduled time. The supercomputer executes the parallelized code and generates the results.

[0258] 6. Verification Process:

[0259] The generated simulation results are sent to a server and analyzed by a verification agent. These verification results are then visually presented to the user via a terminal, allowing the user to review the results.

[0260] Specific example

[0261] For example, if a user wants to simulate the thermal behavior of a new material, they input the material's properties into the platform. The server selects an appropriate physical model and proposes it to the user. Based on the selected model, necessary parameters (such as thermal conductivity) are adjusted, and calculations begin on the supercomputer. After the calculation, the results are verified and reported to the user via a terminal.

[0262] Through the above process, the present invention provides an environment in which even non-expert users can efficiently perform advanced calculations.

[0263] The following describes the processing flow.

[0264] Step 1:

[0265] Users access the platform from their terminals and input the project's objectives and requirements. As users input basic information about the simulation target, the server prepares to select the optimal computational model based on that information.

[0266] Step 2:

[0267] The server analyzes user input and extracts suitable computational model candidates from its internal database. The user selects the most suitable model from the list of candidates presented by the server. The selection process is interactive, and the server adjusts the information in real time based on user feedback.

[0268] Step 3:

[0269] The terminal prompts the user to make the necessary parameter adjustments based on the selected model. The user inputs detailed parameters (e.g., range, precision settings, etc.), and the server receives this information, runs an automatic optimization engine, and generates the optimal parameter set.

[0270] Step 4:

[0271] The server collects the tuned model and parameters and converts them into a format executable on the supercomputer. At this stage, optimizations are performed for code parallelization and efficient distributed processing. The converted code is stored by the server, ready for subsequent processing.

[0272] Step 5:

[0273] The server checks the status of the supercomputer currently in use and determines the time when computing resources can be used most efficiently. It automatically reserves available computing time and notifies the user of the result, informing them when to start computing.

[0274] Step 6:

[0275] When the scheduled time arrives, the server sends an instruction to the supercomputer to start the simulation. The supercomputer performs calculations using parallelized code and generates results. Throughout this process, the server monitors the progress and responds promptly if any problems arise.

[0276] Step 7:

[0277] The calculation results generated by the supercomputer are returned to the server. The server passes these results to a verification agent, which checks whether the results meet the target conditions. After verification is complete, the results are visualized and provided to the user via a terminal for final confirmation.

[0278] The detailed processes at each step are crucial elements for enhancing the efficiency and usability of this system, and are useful in research and development and industrial applications.

[0279] (Example 1)

[0280] Next, Example 1 will be described. In the following description, the data processing device 12 is referred to as a "server", and the smart glasses 214 are referred to as a "terminal".

[0281] Modern advanced computations and simulations require specialized knowledge and complex settings, presenting a challenge for non-experts in terms of difficulty of use. Additionally, it is not easy to efficiently use high-performance computing devices such as supercomputers, and optimization of utilized resources is also demanded.

[0282] The specific processing by the specific processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0283] In this invention, the server includes means for inputting a purpose via an information processing device and selecting an appropriate computation model, means for optimizing numerical information based on initial conditions and constraint conditions using the selected computation model, and means for converting the optimized computation model and numerical information into a form executable by a high-performance computing device. Thereby, it becomes possible to efficiently perform advanced computations without specialized knowledge.

[0284] The "information processing device" is a terminal that receives user input and supports data processing and selection of a computation model.

[0285] The "purpose" is information indicating a specific result that the user wishes to achieve or the goal of a project.

[0286] The "computation model" is a set of calculation methods and algorithms selected according to the input purpose.

[0287] The "initial conditions" are numerical values and setting values specified as prerequisite conditions required for the execution of the computation model.

[0288] The "constraint conditions" are specified values indicating restrictions and bindings to be observed in the execution of the computation model.

[0289] "Numerical information" refers to the data set generated from the initial conditions and constraints in a computational model.

[0290] A "high-performance computing device" is a computer with high computational power to support the processing of large amounts of data and parallel computing.

[0291] "Computational processing" is the process by which a computing device uses input numerical information to perform calculations based on models and algorithms.

[0292] "Calculation results" refer to the output or data generated by a high-performance computing device after it has completed its calculation process.

[0293] This invention provides a system that allows users to easily perform advanced calculations using an information processing device, a server, and a high-performance computing device. The user begins by accessing the information processing device via a terminal and inputting their objective. Based on the input objective, the server selects an appropriate calculation model and sets initial and constraint conditions based on that model.

[0294] The server converts the selected computational model and numerical information into a format executable by high-performance computing devices. The hardware used here is a supercomputer with high computational power. The converted data is optimized for parallel processing, enabling high-speed calculations.

[0295] For example, when a user simulates the thermal behavior of a new material, they input the material's properties into the platform using a terminal. The server then selects an appropriate physical model based on this information and presents it to the user. This process provides an environment where users can perform complex simulations even without specialized knowledge.

[0296] A concrete example of a prompt message would be, "I would like to input the thermal conductivity and specific heat of a new material and perform a thermal behavior simulation." In this way, the present invention connects the user's intent with high-performance computing capabilities, enabling applications in a wide range of fields.

[0297] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0298] Step 1:

[0299] The user accesses the system using a terminal and inputs the project objectives into the information processing device. Specifically, the user inputs the content and conditions they want to simulate in text format. This input is sent to the server and stored as basic data for use in the next step.

[0300] Step 2:

[0301] Based on the project objectives received by the server, it searches its internal database to extract candidate computational models. The server then uses an AI algorithm to select the most relevant model from this input data. This process allows the user to view a list of selectable computational models on their device.

[0302] Step 3:

[0303] The user selects the most appropriate computational model from the candidates presented by the server on their terminal. The selected model is verified on the server, and initial conditions and constraints related to each model are set. This information is stored by the server for use in the next step.

[0304] Step 4:

[0305] Based on the initial conditions and constraints entered by the user, the server optimizes numerical information. Specifically, it uses AI to automatically calculate the initial parameters best suited to the user's objective. These optimized parameters are then prepared for processing on a supercomputer.

[0306] Step 5:

[0307] The server converts the optimized operation model and parameters into a form executable on a high-performance computing device. At this time, the server optimizes parallel processing to maximize the efficiency of the calculation time. The converted data is prepared for transfer to a supercomputer.

[0308] Step 6:

[0309] The server analyzes the usage status and load of the high-performance computing device and reserves the optimal calculation time. This process is automatically performed by the server's schedule management, and the user can check the start time of the calculation on the terminal.

[0310] Step 7:

[0311] According to the reserved time, the supercomputer starts executing the parallelized model. The high-performance computing device advances the process quickly and generates the calculation results.

[0312] Step 8:

[0313] The server receives the calculation results sent from the supercomputer and evaluates the data integrity and validity. The server verifies the results using AI and sends this verified data back to the terminal.

[0314] Step 9:

[0315] The user receives the visual data provided by the server through the terminal and checks the results. Thereby, the user can appropriately analyze the results of the arithmetic processing and use them as input for the next stage of the project.

[0316] (Application Example 1)

[0317] Next, Application Example 1 will be described. In the following description, the data processing device 12 is referred to as the "server", and the smart glasses 214 are referred to as the "terminal".

[0318] Controlling robots and optimizing manufacturing processes in factories requires advanced technology and specialized knowledge, making it difficult for typical end-users to easily perform these tasks. Furthermore, efficient complex calculations and simulations using high-performance computing devices require resource management and systematic scheduling. Therefore, there is a need to provide an operational environment that is easily accessible even to non-professional users.

[0319] 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.

[0320] In this invention, the server includes means for selecting a computational model based on user input, means for converting the adjusted computational model and initial parameters into a format suitable for a high-performance computing device, and means for managing the computation schedule and efficiently allocating the resources of the high-performance computing device. This enables end users to efficiently perform tasks such as optimizing the operation of factory robot arms using a high-performance computing device without requiring specialized knowledge.

[0321] "User input" refers to the act of a user providing the conditions and parameters necessary for a calculation model or simulation via a terminal.

[0322] "Means for selecting a computational model" refers to a method for identifying the most suitable computational model based on the provided conditions.

[0323] "Means for adjusting initial parameters" refers to methods for setting necessary initial values ​​and constraints for a selected computational model and optimizing it.

[0324] "Means of converting to a format suitable for high-performance computing devices" refers to a method of converting the adjusted model and parameters into a code format that can be processed by a high-performance computer.

[0325] "Means of managing computation schedules" refers to a method of investigating the available time and resources of high-performance computing devices and creating a schedule that enables efficient computation execution.

[0326] "Means for efficiently allocating resources of high-performance computing devices" refers to a method of allocation that uses computing resources without waste and optimizes processing time and load.

[0327] "Means of providing an operable interface" refers to a method that allows users to intuitively manipulate and visualize calculation and simulation results in an understandable format.

[0328] The system of this invention is designed to enable users to efficiently perform complex simulations on a high-performance computing device using a terminal. A specific embodiment is described below.

[0329] The server first receives input from the user and selects a computational model from the database based on that input. For the selected model, it automatically adjusts the parameters based on the initial parameters and constraints further set by the user. At this stage, the software used includes optimization algorithms to rapidly process the data.

[0330] The server translates the adjusted computational model and parameters into code that can be executed on high-performance computing devices such as supercomputers. This translation process involves constructing the code with particularly high-speed parallel processing in mind.

[0331] The terminal provides users with a visually user-friendly interface and displays simulation results in real time. A concrete example of the results is the simulation of robot arm movements that contribute to factory efficiency. This simulation provides the optimal movement pattern by taking into account the characteristics of the parts being handled and the balance of the movement speed.

[0332] When using a generative AI model, the following example prompts apply:

[0333] "I would like to perform an operation simulation to optimize the robot arm. Please provide the current operating time, error, and constraints, and perform a simulation to achieve maximum efficiency."

[0334] This allows users to obtain optimal results by leveraging the advantages of high-performance computing devices, even without advanced expertise.

[0335] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0336] Step 1:

[0337] The user logs into the system using a terminal and starts the project. In this step, the user inputs the operating conditions and constraints of the robot arm they want to simulate. The entered data reflects the user's intentions and goals, and this serves as the basis for processing in the next step.

[0338] Step 2:

[0339] The server receives input data from the user, analyzes it, and selects the optimal computational model from the database. This selection process utilizes generative AI models to quickly identify the model best suited to the user's needs. The selected model is then returned to the server as output.

[0340] Step 3:

[0341] The server optimizes the initial parameters for the selected computational model. Here, it considers the operating conditions and constraints provided by the user and adjusts the initial parameters accordingly. Specifically, it receives the parameter range and constraints as input, applies an optimization algorithm, and outputs the optimal initial parameters.

[0342] Step 4:

[0343] The server converts the tuned model and parameters into a format suitable for high-performance computing devices. Code optimization is performed here to maximize the use of parallel processing. At this stage, the tuned model is received as input, and highly efficient executable code is generated.

[0344] Step 5:

[0345] The server monitors the operational status of the high-performance computing units and prepares to run simulations at the most appropriate schedule. The input here is the latest resource status of the computing units, and based on this information, the optimal timing for starting calculations is output.

[0346] Step 6:

[0347] A high-performance computing unit performs calculations at scheduled times and generates simulation results. The output simulation results include detailed analysis based on user-defined conditions.

[0348] Step 7:

[0349] The server receives the generated simulation results and performs verification and evaluation. This process uses verification algorithms to assess the reliability and validity of the results. The input is the simulation data, and the output is the evaluated results report.

[0350] Step 8:

[0351] Finally, the server sends the evaluation results to the terminal and provides them to the user in a visualized format. A user interface is used here to clearly display the results. The input is the evaluated result data, and the output is user-friendly visual information.

[0352] 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.

[0353] This invention is a system that enhances the user experience when users perform advanced calculations and simulations using a supercomputer by combining it with an emotion engine. This system utilizes emotion recognition technology to dynamically adjust the interface and feedback according to the user's emotional state, thereby increasing work efficiency and comfort.

[0354] System Overview

[0355] 1. Emotion recognition process:

[0356] The emotion engine uses the camera and sensors on the device to analyze the user's facial expressions and behavior in real time. Based on this data, the server identifies the user's emotional state and prepares that information for use throughout the system.

[0357] 2. Interface adjustment process:

[0358] The server receives feedback from the emotion engine and, if it determines that the user is experiencing stress, changes the interface to be more intuitive and easier to use. This includes simpler navigation and highlighted operation guides.

[0359] 3. Optimizing the simulation process:

[0360] The server modifies the simulation's progression based on the user's emotional state. For example, if the user is showing signs of anxiety, the server simplifies the process and presents the progress in an easy-to-understand manner to increase the user's sense of security.

[0361] 4. Feedback process:

[0362] After the results are generated, the server customizes the feedback based on the sentiment analysis results from the sentiment engine. This feedback is delivered to the user via the device, providing appropriate advice and suggestions for improvement.

[0363] Specific example

[0364] For example, suppose a user is performing a complex aircraft performance simulation and the emotion engine detects a decrease in the user's concentration. In this situation, the server simplifies the simulation screen and hides unnecessary information, allowing the user to focus only on the target parameters.

[0365] Thus, by integrating an emotion engine, the present invention provides a system that enhances the user experience by realizing high-performance computational support that is attuned to the user's emotions.

[0366] The following describes the processing flow.

[0367] Step 1:

[0368] The user operates a terminal to access the system and input the project's objectives and data. This input completes the initial setup, and the server prepares to search for candidate computational models.

[0369] Step 2:

[0370] The device uses its built-in camera and microphone to record the user's facial expressions and voice intonation in real time. The emotion engine analyzes this recorded data to identify the user's current emotional state. The server receives this information and prepares to adjust the interface and processes.

[0371] Step 3:

[0372] The server selects candidate computational models from the database based on user input and sends a list of candidates to the terminal. The user reviews this list on the terminal and selects the most suitable model. After selection, the server provides further feedback and processing advice.

[0373] Step 4:

[0374] Based on information from the emotion engine, the server provides an interface optimized for the user's emotional state. If the user shows signs of frustration, the server highlights the operation guide or simplifies the operation procedure to make it easier to understand.

[0375] Step 5:

[0376] Once the user selects a model and inputs the necessary data into the terminal, the server automatically adjusts the parameters and converts the code into a format that can be processed by a supercomputer. Optimizations such as parallel processing are also performed at this stage.

[0377] Step 6:

[0378] The server optimizes the simulation's progress in real time based on emotional data. For users exhibiting impatience, it provides reassurance by displaying detailed processing status and clearly showing the progress.

[0379] Step 7:

[0380] After the supercomputer runs the simulation and generates results, the server verifies the results and forms feedback. The verification takes into account the analysis results of the emotion engine, and the most relevant detailed information and improvements are provided to the user through the terminal.

[0381] Through these steps, the present invention provides a support environment for performing advanced calculations and simulations while taking into consideration the user's emotions.

[0382] (Example 2)

[0383] 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".

[0384] Modern high-performance computing systems require improved efficiency and user comfort when performing complex calculations. However, conventional systems proceed with calculations in a uniform manner regardless of the user's emotional state, lacking care, especially in situations where users feel stressed or anxious, and failing to provide an optimal user experience.

[0385] 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.

[0386] In this invention, the server includes means for analyzing the user's emotional state, means for dynamically changing user information based on the user's emotions, and means for optimizing computational processing according to the user's emotional state. This makes it possible to provide management and feedback that is sensitive to the user's emotions, thereby improving computational efficiency and user experience.

[0387] A "computational model" is a set of algorithms or mathematical formulas constructed to achieve a specific computational objective.

[0388] "Numerical elements" refer to the parameters and variables in a computational model, and are values ​​that affect the calculation results.

[0389] "High-performance computing systems" refer to supercomputers and cluster computers designed to process large-scale calculations quickly and efficiently.

[0390] "Computational work" refers to the entire series of computational processes performed using a computational model.

[0391] "Emotion recognition technology" is a technology that analyzes a user's emotional state from their facial expressions, voice, and behavior.

[0392] "Dynamically changing user information" means adjusting the interface and output information in real time according to the user's emotional state.

[0393] "Efficient resource allocation" means allocating limited resources, such as computing resources and time, in a way that makes the most effective use of them.

[0394] The embodiments for carrying out the present invention will be described in detail below.

[0395] The user first uses a terminal to operate a high-performance computing system. This terminal has built-in cameras and sensors to capture the user's facial expressions and movements. The data acquired from these devices is input into the emotion recognition system in real time.

[0396] The server receives data sent from the terminal and analyzes the user's emotional state using a generative AI model. This model utilizes facial recognition software and voice analysis algorithms to identify emotions such as stress and joy. Once the emotional state is identified, the server dynamically adjusts the user interface based on that information. For example, if the user is showing signs of stress, the server simplifies navigation to make it more intuitive and highlights important information.

[0397] Furthermore, the server optimizes the progress of calculations while taking into account the user's emotional state. Specifically, if the server determines that the user is in a state of impatience, it simplifies the calculation process and supports the user by visually displaying intermediate results.

[0398] Once the calculation results are generated, the server customizes the feedback based on the emotion recognition results, providing advice and a roadmap to the next steps tailored to the user's state. The device receives this feedback and displays it appropriately to the user.

[0399] A concrete example is when a user is performing a weather forecast simulation; the system evaluates the user's emotional state and optimizes the display of information as needed to facilitate the process.

[0400] An example of a prompt message is, "How can we use emotion recognition to provide efficient support when a user runs a simulation?" Such a framework allows users to utilize high-performance computing systems more comfortably.

[0401] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0402] Step 1:

[0403] The device collects the user's facial expressions and movements using cameras and sensors. This input data includes facial image data and audio data. The device then preprocesses this data, removing data noise and converting it into a format suitable for analysis. A clean dataset is generated as output.

[0404] Step 2:

[0405] The server receives a pre-processed dataset sent from the terminal. The server inputs this data into a generating AI model, which analyzes the user's emotional state in real time. The data calculations performed here output the user's emotional state in the form of "stress" or "decreased concentration."

[0406] Step 3:

[0407] The server dynamically adjusts the user interface based on the analysis of the user's emotional state. Specifically, the server can reorganize the interface, transforming it into a simpler, more user-friendly interface. For example, if stress is detected, the system highlights important items and eliminates complex slide menus. The resulting output is the adjusted interface settings.

[0408] Step 4:

[0409] The server optimizes calculations based on the user's emotional state. This process simplifies calculation steps and redesigns how intermediate results are presented, particularly for users exhibiting anxiety. The output consists of user-friendly intermediate results.

[0410] Step 5:

[0411] The terminal presents the user with feedback information received from the server. This includes advice that takes emotional state into account and guidance on the next steps. The terminal displays this information in an optimized interface to support the user's actions. The final output is personalized feedback information for the user.

[0412] (Application Example 2)

[0413] 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."

[0414] Conventional calculation and simulation systems often fail to consider the user's emotional state, making it difficult to improve the user experience. Furthermore, complex interfaces can cause user stress and reduce work efficiency. There is a need for systems that address these challenges and enhance both user comfort and efficiency.

[0415] 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.

[0416] In this invention, the server includes means for detecting an emotional state and providing an appropriate interface, means for dynamically changing the operation panel based on the emotional state, and means for verifying and providing simulation results to the user. This enables automatic adjustment of the interface according to the user's emotional state, thereby reducing user stress and improving work efficiency.

[0417] A "user" refers to a person who uses the system to perform calculations or simulations.

[0418] A "model" refers to a set of hypotheses or designs used for calculations or simulations selected by the user.

[0419] "Parameters" refer to numerical values ​​or variables used to adjust the behavior of a model.

[0420] "Large-scale computing equipment" refers to devices such as supercomputers that are used to process large amounts of data and perform advanced calculations.

[0421] A "calculation schedule" refers to a plan for managing the order and timing of calculations.

[0422] "Emotional state" refers to the user's mental state or mood, and the information detected by the emotion engine.

[0423] "Interface" refers to the screen or operating environment that a user uses to interact with a system.

[0424] The term "control panel" refers to a part of the interface that allows users to operate various functions of a system.

[0425] "Simulation results" refers to calculation results and analysis data obtained by large-scale computing devices.

[0426] This invention is a system that utilizes emotion recognition technology to dynamically adjust the system's interface and functions according to the user's emotional state, thereby improving the user experience when using large-scale computing devices. This system is realized through the roles of the server, terminal, and user.

[0427] The server uses an emotion recognition engine to analyze the user's emotional state in real time. It acquires the user's facial expressions and actions from cameras and sensors and identifies their emotional state based on this information. Based on this information, it adjusts the interface and control panel according to the user's emotional state. If the user is feeling stressed, the server simplifies the control panel and changes the interface to display only the most important information.

[0428] The terminal is responsible for sending and receiving emotional state data between the user and the server, and displaying the simulation results. Users can interact with the system through the terminal and receive customized feedback tailored to their emotional state.

[0429] For example, if the system detects that a user is showing signs of fatigue while operating a robot in a factory, it will simplify the interface and reduce visual strain. Another example of a prompt to input into the generating AI model is, "How would you modify the interface if the user is experiencing stress?" This makes it possible to provide an experience that is sensitive to the user's emotions.

[0430] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0431] Step 1:

[0432] The server acquires user facial expression data from the terminal's camera and sensors. The input is the user's real-time video. The server processes this video data and uses facial recognition technology to extract the user's facial features. Based on this, it makes an initial judgment about the user's emotional state.

[0433] Step 2:

[0434] The server uses an emotion recognition engine to analyze the user's emotional state from extracted facial features. The input for this step is facial features, and the output is the user's emotional state (e.g., concentration, fatigue, stress). Data analysis techniques are used to classify specific facial patterns into emotional categories.

[0435] Step 3:

[0436] The server dynamically adjusts the interface based on the analysis results. The input is the emotional state obtained in the previous step, and the output is the modified user interface. When the user is stressed, the server hides visually complex elements and highlights only important information.

[0437] Step 4:

[0438] The terminal presents the user with a pre-configured interface received from the server. At this stage, the interface display is optimized to the user's needs. The input is the interface data received from the server, and the output is its visual representation. The terminal renders the interface in a way that allows the user to operate it intuitively.

[0439] Step 5:

[0440] Users manipulate and verify simulation results using a tailored interface. User input is the response to the operation, and output is feedback and data viewing corresponding to that response. Users efficiently take actions to achieve their goals.

[0441] 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.

[0442] 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.

[0443] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart glasses 214.

[0444] [Third Embodiment]

[0445] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0446] 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.

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

[0448] The 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.

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

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

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

[0452] Figure 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.

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

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

[0455] In the 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.

[0456] 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".

[0457] This invention relates to a platform that allows users to easily perform complex calculations and simulations using high-performance supercomputers. This platform enhances efficiency by assisting with the selection of computational models, parameter tuning, conversion to supercomputers, scheduling, simulation execution, and verification through multiple AI agents.

[0458] System Overview

[0459] 1. Model selection process:

[0460] The user accesses the platform through their device and enters the project objective. Based on this input, the server selects an appropriate computational model from its database. After being presented with options, the user can choose the model that best suits their needs.

[0461] 2. Parameter adjustment process:

[0462] The server automatically sets the necessary initial parameters based on the selected model. This includes the user entering specific initial conditions and constraints into the terminal, which the server then takes into account when performing optimization.

[0463] 3. Supercomputer conversion process:

[0464] The server converts the tuned model and parameters into program code that can be processed by the supercomputer. During this process, parallel processing optimizations are performed to maximize computation speed.

[0465] 4. Schedule management process:

[0466] The server analyzes the supercomputer's usage and automatically reserves appropriate computing time. This allows users to optimally set the timing for starting calculations.

[0467] 5. Simulation execution process:

[0468] The calculation starts automatically at the scheduled time. The supercomputer executes the parallelized code and generates the results.

[0469] 6. Verification Process:

[0470] The generated simulation results are sent to a server and analyzed by a verification agent. These verification results are then visually presented to the user via a terminal, allowing the user to review the results.

[0471] Specific example

[0472] For example, if a user wants to simulate the thermal behavior of a new material, they input the material's properties into the platform. The server selects an appropriate physical model and proposes it to the user. Based on the selected model, necessary parameters (such as thermal conductivity) are adjusted, and calculations begin on the supercomputer. After the calculation, the results are verified and reported to the user via a terminal.

[0473] Through the above process, the present invention provides an environment in which even non-expert users can efficiently perform advanced calculations.

[0474] The following describes the processing flow.

[0475] Step 1:

[0476] Users access the platform from their terminals and input the project's objectives and requirements. As users input basic information about the simulation target, the server prepares to select the optimal computational model based on that information.

[0477] Step 2:

[0478] The server analyzes user input and extracts suitable computational model candidates from its internal database. The user selects the most suitable model from the list of candidates presented by the server. The selection process is interactive, and the server adjusts the information in real time based on user feedback.

[0479] Step 3:

[0480] The terminal prompts the user to make the necessary parameter adjustments based on the selected model. The user inputs detailed parameters (e.g., range, precision settings, etc.), and the server receives this information, runs an automatic optimization engine, and generates the optimal parameter set.

[0481] Step 4:

[0482] The server collects the tuned model and parameters and converts them into a format executable on the supercomputer. At this stage, optimizations are performed for code parallelization and efficient distributed processing. The converted code is stored by the server, ready for subsequent processing.

[0483] Step 5:

[0484] The server checks the status of the supercomputer currently in use and determines the time when computing resources can be used most efficiently. It automatically reserves available computing time and notifies the user of the result, informing them when to start computing.

[0485] Step 6:

[0486] When the scheduled time arrives, the server sends an instruction to the supercomputer to start the simulation. The supercomputer performs calculations using parallelized code and generates results. Throughout this process, the server monitors the progress and responds promptly if any problems arise.

[0487] Step 7:

[0488] The calculation results generated by the supercomputer are returned to the server. The server passes these results to a verification agent, which checks whether the results meet the target conditions. After verification is complete, the results are visualized and provided to the user via a terminal for final confirmation.

[0489] The detailed processes at each step are crucial elements for enhancing the efficiency and usability of this system, and are useful in research and development and industrial applications.

[0490] (Example 1)

[0491] 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."

[0492] Modern advanced computations and simulations require specialized knowledge and complex settings, making them difficult for non-experts to use. Furthermore, efficiently utilizing high-performance computing devices such as supercomputers is not easy, and optimization of resource utilization is also required.

[0493] 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.

[0494] In this invention, the server includes means for inputting a target via an information processing device and selecting an appropriate computation model; means for optimizing numerical information based on initial conditions and constraints using the selected computation model; and means for converting the optimized computation model and numerical information into a format executable by a high-performance computer. This makes it possible to efficiently perform advanced calculations even without specialized knowledge.

[0495] An "information processing device" is a terminal that receives user input and supports data processing and the selection of calculation models.

[0496] "Purpose" refers to information that indicates the specific results or project goals that the user wants to achieve.

[0497] A "computational model" is a set of computational methods and algorithms selected according to the input objective.

[0498] "Initial conditions" are numerical values ​​or settings specified as prerequisites for executing the computational model.

[0499] A "constraint" is a set of values ​​that indicate the limitations or restrictions that must be followed when executing an computational model.

[0500] "Numerical information" refers to the data set generated from the initial conditions and constraints in a computational model.

[0501] A "high-performance computing device" is a computer with high computational power to support the processing of large amounts of data and parallel computing.

[0502] "Computational processing" is the process by which a computing device uses input numerical information to perform calculations based on models and algorithms.

[0503] "Calculation results" refer to the output or data generated by a high-performance computing device after it has completed its calculation process.

[0504] This invention provides a system that allows users to easily perform advanced calculations using an information processing device, a server, and a high-performance computing device. The user begins by accessing the information processing device via a terminal and inputting their objective. Based on the input objective, the server selects an appropriate calculation model and sets initial and constraint conditions based on that model.

[0505] The server converts the selected computational model and numerical information into a format executable by high-performance computing devices. The hardware used here is a supercomputer with high computational power. The converted data is optimized for parallel processing, enabling high-speed calculations.

[0506] For example, when a user simulates the thermal behavior of a new material, they input the material's properties into the platform using a terminal. The server then selects an appropriate physical model based on this information and presents it to the user. This process provides an environment where users can perform complex simulations even without specialized knowledge.

[0507] A concrete example of a prompt message would be, "I would like to input the thermal conductivity and specific heat of a new material and perform a thermal behavior simulation." In this way, the present invention connects the user's intent with high-performance computing capabilities, enabling applications in a wide range of fields.

[0508] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0509] Step 1:

[0510] The user accesses the system using a terminal and inputs the project objectives into the information processing device. Specifically, the user inputs the content and conditions they want to simulate in text format. This input is sent to the server and stored as basic data for use in the next step.

[0511] Step 2:

[0512] Based on the project objectives received by the server, it searches its internal database to extract candidate computational models. The server then uses an AI algorithm to select the most relevant model from this input data. This process allows the user to view a list of selectable computational models on their device.

[0513] Step 3:

[0514] The user selects the most appropriate computational model from the candidates presented by the server on their terminal. The selected model is verified on the server, and initial conditions and constraints related to each model are set. This information is stored by the server for use in the next step.

[0515] Step 4:

[0516] Based on the initial conditions and constraints entered by the user, the server optimizes numerical information. Specifically, it uses AI to automatically calculate the initial parameters best suited to the user's objective. These optimized parameters are then prepared for processing on a supercomputer.

[0517] Step 5:

[0518] The server converts the optimized computational model and parameters into a format executable by high-performance computing devices. During this process, the server optimizes parallel processing to maximize computation time efficiency. The converted data is then prepared for transfer to the supercomputer.

[0519] Step 6:

[0520] The server analyzes the usage and load of high-performance computing devices and reserves the optimal computing time. This process is performed automatically by the server's scheduling system, and users can check the start time of the calculation on their terminal.

[0521] Step 7:

[0522] According to the reserved time slot, the supercomputer begins executing the parallelized model. The high-performance computing device rapidly processes the data and generates the calculation results.

[0523] Step 8:

[0524] The server receives the calculation results sent from the supercomputer and evaluates the integrity and validity of the data. The server uses AI to verify the results and sends this verified data back to the terminal.

[0525] Step 9:

[0526] The user receives visual data provided by the server via their terminal and checks the results. This allows the user to properly analyze the results of the calculations and use them as input for the next stage of the project.

[0527] (Application Example 1)

[0528] 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."

[0529] Controlling robots and optimizing manufacturing processes in factories requires advanced technology and specialized knowledge, making it difficult for typical end-users to easily perform these tasks. Furthermore, efficient complex calculations and simulations using high-performance computing devices require resource management and systematic scheduling. Therefore, there is a need to provide an operational environment that is easily accessible even to non-professional users.

[0530] 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.

[0531] In this invention, the server includes means for selecting a computational model based on user input, means for converting the adjusted computational model and initial parameters into a format suitable for a high-performance computing device, and means for managing the computation schedule and efficiently allocating the resources of the high-performance computing device. This enables end users to efficiently perform tasks such as optimizing the operation of factory robot arms using a high-performance computing device without requiring specialized knowledge.

[0532] "User input" refers to the act of a user providing the conditions and parameters necessary for a calculation model or simulation via a terminal.

[0533] "Means for selecting a computational model" refers to a method for identifying the most suitable computational model based on the provided conditions.

[0534] "Means for adjusting initial parameters" refers to methods for setting necessary initial values ​​and constraints for a selected computational model and optimizing it.

[0535] "Means of converting to a format suitable for high-performance computing devices" refers to a method of converting the adjusted model and parameters into a code format that can be processed by a high-performance computer.

[0536] "Means of managing computation schedules" refers to a method of investigating the available time and resources of high-performance computing devices and creating a schedule that enables efficient computation execution.

[0537] "Means for efficiently allocating resources of high-performance computing devices" refers to a method of allocation that uses computing resources without waste and optimizes processing time and load.

[0538] "Means of providing an operable interface" refers to a method that allows users to intuitively manipulate and visualize calculation and simulation results in an understandable format.

[0539] The system of this invention is designed to enable users to efficiently perform complex simulations on a high-performance computing device using a terminal. A specific embodiment is described below.

[0540] The server first receives input from the user and selects a computational model from the database based on that input. For the selected model, it automatically adjusts the parameters based on the initial parameters and constraints further set by the user. At this stage, the software used includes optimization algorithms to rapidly process the data.

[0541] The server translates the adjusted computational model and parameters into code that can be executed on high-performance computing devices such as supercomputers. This translation process involves constructing the code with particularly high-speed parallel processing in mind.

[0542] The terminal provides users with a visually user-friendly interface and displays simulation results in real time. A concrete example of the results is the simulation of robot arm movements that contribute to factory efficiency. This simulation provides the optimal movement pattern by taking into account the characteristics of the parts being handled and the balance of the movement speed.

[0543] When using a generative AI model, the following example prompts apply:

[0544] "I would like to perform an operation simulation to optimize the robot arm. Please provide the current operating time, error, and constraints, and perform a simulation to achieve maximum efficiency."

[0545] This allows users to obtain optimal results by leveraging the advantages of high-performance computing devices, even without advanced expertise.

[0546] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0547] Step 1:

[0548] The user logs into the system using a terminal and starts the project. In this step, the user inputs the operating conditions and constraints of the robot arm they want to simulate. The entered data reflects the user's intentions and goals, and this serves as the basis for processing in the next step.

[0549] Step 2:

[0550] The server receives input data from the user, analyzes it, and selects the optimal computational model from the database. This selection process utilizes generative AI models to quickly identify the model best suited to the user's needs. The selected model is then returned to the server as output.

[0551] Step 3:

[0552] The server optimizes the initial parameters for the selected computational model. Here, it considers the operating conditions and constraints provided by the user and adjusts the initial parameters accordingly. Specifically, it receives the parameter range and constraints as input, applies an optimization algorithm, and outputs the optimal initial parameters.

[0553] Step 4:

[0554] The server converts the tuned model and parameters into a format suitable for high-performance computing devices. Code optimization is performed here to maximize the use of parallel processing. At this stage, the tuned model is received as input, and highly efficient executable code is generated.

[0555] Step 5:

[0556] The server monitors the operational status of the high-performance computing units and prepares to run simulations at the most appropriate schedule. The input here is the latest resource status of the computing units, and based on this information, the optimal timing for starting calculations is output.

[0557] Step 6:

[0558] A high-performance computing unit performs calculations at scheduled times and generates simulation results. The output simulation results include detailed analysis based on user-defined conditions.

[0559] Step 7:

[0560] The server receives the generated simulation results and performs verification and evaluation. This process uses verification algorithms to assess the reliability and validity of the results. The input is the simulation data, and the output is the evaluated results report.

[0561] Step 8:

[0562] Finally, the server sends the evaluation results to the terminal and provides them to the user in a visualized format. A user interface is used here to clearly display the results. The input is the evaluated result data, and the output is user-friendly visual information.

[0563] 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.

[0564] This invention is a system that enhances the user experience when users perform advanced calculations and simulations using a supercomputer by combining it with an emotion engine. This system utilizes emotion recognition technology to dynamically adjust the interface and feedback according to the user's emotional state, thereby increasing work efficiency and comfort.

[0565] System Overview

[0566] 1. Emotion recognition process:

[0567] The emotion engine uses the camera and sensors on the device to analyze the user's facial expressions and behavior in real time. Based on this data, the server identifies the user's emotional state and prepares that information for use throughout the system.

[0568] 2. Interface adjustment process:

[0569] The server receives feedback from the emotion engine and, if it determines that the user is experiencing stress, changes the interface to be more intuitive and easier to use. This includes simpler navigation and highlighted operation guides.

[0570] 3. Optimizing the simulation process:

[0571] The server modifies the simulation's progression based on the user's emotional state. For example, if the user is showing signs of anxiety, the server simplifies the process and presents the progress in an easy-to-understand manner to increase the user's sense of security.

[0572] 4. Feedback process:

[0573] After the results are generated, the server customizes the feedback based on the sentiment analysis results from the sentiment engine. This feedback is delivered to the user via the device, providing appropriate advice and suggestions for improvement.

[0574] Specific example

[0575] For example, suppose a user is performing a complex aircraft performance simulation and the emotion engine detects a decrease in the user's concentration. In this situation, the server simplifies the simulation screen and hides unnecessary information, allowing the user to focus only on the target parameters.

[0576] Thus, by integrating an emotion engine, the present invention provides a system that enhances the user experience by realizing high-performance computational support that is attuned to the user's emotions.

[0577] The following describes the processing flow.

[0578] Step 1:

[0579] The user operates a terminal to access the system and input the project's objectives and data. This input completes the initial setup, and the server prepares to search for candidate computational models.

[0580] Step 2:

[0581] The device uses its built-in camera and microphone to record the user's facial expressions and voice intonation in real time. The emotion engine analyzes this recorded data to identify the user's current emotional state. The server receives this information and prepares to adjust the interface and processes.

[0582] Step 3:

[0583] The server selects candidate computational models from the database based on user input and sends a list of candidates to the terminal. The user reviews this list on the terminal and selects the most suitable model. After selection, the server provides further feedback and processing advice.

[0584] Step 4:

[0585] Based on information from the emotion engine, the server provides an interface optimized for the user's emotional state. If the user shows signs of frustration, the server highlights the operation guide or simplifies the operation procedure to make it easier to understand.

[0586] Step 5:

[0587] Once the user selects a model and inputs the necessary data into the terminal, the server automatically adjusts the parameters and converts the code into a format that can be processed by a supercomputer. Optimizations such as parallel processing are also performed at this stage.

[0588] Step 6:

[0589] The server optimizes the simulation's progress in real time based on emotional data. For users exhibiting impatience, it provides reassurance by displaying detailed processing status and clearly showing the progress.

[0590] Step 7:

[0591] After the supercomputer runs the simulation and generates results, the server verifies the results and forms feedback. The verification takes into account the analysis results of the emotion engine, and the most relevant detailed information and improvements are provided to the user through the terminal.

[0592] Through these steps, the present invention provides a support environment for performing advanced calculations and simulations while taking into consideration the user's emotions.

[0593] (Example 2)

[0594] 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."

[0595] Modern high-performance computing systems require improved efficiency and user comfort when performing complex calculations. However, conventional systems proceed with calculations in a uniform manner regardless of the user's emotional state, lacking care, especially in situations where users feel stressed or anxious, and failing to provide an optimal user experience.

[0596] 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.

[0597] In this invention, the server includes means for analyzing the user's emotional state, means for dynamically changing user information based on the user's emotions, and means for optimizing computational processing according to the user's emotional state. This makes it possible to provide management and feedback that is sensitive to the user's emotions, thereby improving computational efficiency and user experience.

[0598] A "computational model" is a set of algorithms or mathematical formulas constructed to achieve a specific computational objective.

[0599] "Numerical elements" refer to the parameters and variables in a computational model, and are values ​​that affect the calculation results.

[0600] "High-performance computing systems" refer to supercomputers and cluster computers designed to process large-scale calculations quickly and efficiently.

[0601] "Computational work" refers to the entire series of computational processes performed using a computational model.

[0602] "Emotion recognition technology" is a technology that analyzes a user's emotional state from their facial expressions, voice, and behavior.

[0603] "Dynamically changing user information" means adjusting the interface and output information in real time according to the user's emotional state.

[0604] "Efficient resource allocation" means allocating limited resources, such as computing resources and time, in a way that makes the most effective use of them.

[0605] The embodiments for carrying out the present invention will be described in detail below.

[0606] The user first uses a terminal to operate a high-performance computing system. This terminal has built-in cameras and sensors to capture the user's facial expressions and movements. The data acquired from these devices is input into the emotion recognition system in real time.

[0607] The server receives data sent from the terminal and analyzes the user's emotional state using a generative AI model. This model utilizes facial recognition software and voice analysis algorithms to identify emotions such as stress and joy. Once the emotional state is identified, the server dynamically adjusts the user interface based on that information. For example, if the user is showing signs of stress, the server simplifies navigation to make it more intuitive and highlights important information.

[0608] Furthermore, the server optimizes the progress of calculations while taking into account the user's emotional state. Specifically, if the server determines that the user is in a state of impatience, it simplifies the calculation process and supports the user by visually displaying intermediate results.

[0609] Once the calculation results are generated, the server customizes the feedback based on the emotion recognition results, providing advice and a roadmap to the next steps tailored to the user's state. The device receives this feedback and displays it appropriately to the user.

[0610] A concrete example is when a user is performing a weather forecast simulation; the system evaluates the user's emotional state and optimizes the display of information as needed to facilitate the process.

[0611] An example of a prompt message is, "How can we use emotion recognition to provide efficient support when a user runs a simulation?" Such a framework allows users to utilize high-performance computing systems more comfortably.

[0612] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0613] Step 1:

[0614] The device collects the user's facial expressions and movements using cameras and sensors. This input data includes facial image data and audio data. The device then preprocesses this data, removing data noise and converting it into a format suitable for analysis. A clean dataset is generated as output.

[0615] Step 2:

[0616] The server receives a pre-processed dataset sent from the terminal. The server inputs this data into a generating AI model, which analyzes the user's emotional state in real time. The data calculations performed here output the user's emotional state in the form of "stress" or "decreased concentration."

[0617] Step 3:

[0618] The server dynamically adjusts the user interface based on the analysis of the user's emotional state. Specifically, the server can reorganize the interface, transforming it into a simpler, more user-friendly interface. For example, if stress is detected, the system highlights important items and eliminates complex slide menus. The resulting output is the adjusted interface settings.

[0619] Step 4:

[0620] The server optimizes calculations based on the user's emotional state. This process simplifies calculation steps and redesigns how intermediate results are presented, particularly for users exhibiting anxiety. The output consists of user-friendly intermediate results.

[0621] Step 5:

[0622] The terminal presents the user with feedback information received from the server. This includes advice that takes emotional state into account and guidance on the next steps. The terminal displays this information in an optimized interface to support the user's actions. The final output is personalized feedback information for the user.

[0623] (Application Example 2)

[0624] 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."

[0625] Conventional calculation and simulation systems often fail to consider the user's emotional state, making it difficult to improve the user experience. Furthermore, complex interfaces can cause user stress and reduce work efficiency. There is a need for systems that address these challenges and enhance both user comfort and efficiency.

[0626] 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.

[0627] In this invention, the server includes means for detecting an emotional state and providing an appropriate interface, means for dynamically changing the operation panel based on the emotional state, and means for verifying and providing simulation results to the user. This enables automatic adjustment of the interface according to the user's emotional state, thereby reducing user stress and improving work efficiency.

[0628] A "user" refers to a person who uses the system to perform calculations or simulations.

[0629] A "model" refers to a set of hypotheses or designs used for calculations or simulations selected by the user.

[0630] "Parameters" refer to numerical values ​​or variables used to adjust the behavior of a model.

[0631] "Large-scale computing equipment" refers to devices such as supercomputers that are used to process large amounts of data and perform advanced calculations.

[0632] A "calculation schedule" refers to a plan for managing the order and timing of calculations.

[0633] "Emotional state" refers to the user's mental state or mood, and the information detected by the emotion engine.

[0634] "Interface" refers to the screen or operating environment that a user uses to interact with a system.

[0635] The term "control panel" refers to a part of the interface that allows users to operate various functions of a system.

[0636] "Simulation results" refers to calculation results and analysis data obtained by large-scale computing devices.

[0637] This invention is a system that utilizes emotion recognition technology to dynamically adjust the system's interface and functions according to the user's emotional state, thereby improving the user experience when using large-scale computing devices. This system is realized through the roles of the server, terminal, and user.

[0638] The server uses an emotion recognition engine to analyze the user's emotional state in real time. It acquires the user's facial expressions and actions from cameras and sensors and identifies their emotional state based on this information. Based on this information, it adjusts the interface and control panel according to the user's emotional state. If the user is feeling stressed, the server simplifies the control panel and changes the interface to display only the most important information.

[0639] The terminal is responsible for sending and receiving emotional state data between the user and the server, and displaying the simulation results. Users can interact with the system through the terminal and receive customized feedback tailored to their emotional state.

[0640] For example, if the system detects that a user is showing signs of fatigue while operating a robot in a factory, it will simplify the interface and reduce visual strain. Another example of a prompt to input into the generating AI model is, "How would you modify the interface if the user is experiencing stress?" This makes it possible to provide an experience that is sensitive to the user's emotions.

[0641] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0642] Step 1:

[0643] The server acquires user facial expression data from the terminal's camera and sensors. The input is the user's real-time video. The server processes this video data and uses facial recognition technology to extract the user's facial features. Based on this, it makes an initial judgment about the user's emotional state.

[0644] Step 2:

[0645] The server uses an emotion recognition engine to analyze the user's emotional state from extracted facial features. The input for this step is facial features, and the output is the user's emotional state (e.g., concentration, fatigue, stress). Data analysis techniques are used to classify specific facial patterns into emotional categories.

[0646] Step 3:

[0647] The server dynamically adjusts the interface based on the analysis results. The input is the emotional state obtained in the previous step, and the output is the modified user interface. When the user is stressed, the server hides visually complex elements and highlights only important information.

[0648] Step 4:

[0649] The terminal presents the user with a pre-configured interface received from the server. At this stage, the interface display is optimized to the user's needs. The input is the interface data received from the server, and the output is its visual representation. The terminal renders the interface in a way that allows the user to operate it intuitively.

[0650] Step 5:

[0651] Users manipulate and verify simulation results using a tailored interface. User input is the response to the operation, and output is feedback and data viewing corresponding to that response. Users efficiently take actions to achieve their goals.

[0652] 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.

[0653] 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.

[0654] 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.

[0655] [Fourth Embodiment]

[0656] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0657] 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.

[0658] 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).

[0659] 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.

[0660] 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.

[0661] 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).

[0662] 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.

[0663] 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.

[0664] 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.

[0665] 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.

[0666] 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.

[0667] 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.

[0668] 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".

[0669] This invention relates to a platform that allows users to easily perform complex calculations and simulations using high-performance supercomputers. This platform enhances efficiency by assisting with the selection of computational models, parameter tuning, conversion to supercomputers, scheduling, simulation execution, and verification through multiple AI agents.

[0670] System Overview

[0671] 1. Model selection process:

[0672] The user accesses the platform through their device and enters the project objective. Based on this input, the server selects an appropriate computational model from its database. After being presented with options, the user can choose the model that best suits their needs.

[0673] 2. Parameter adjustment process:

[0674] The server automatically sets the necessary initial parameters based on the selected model. This includes the user entering specific initial conditions and constraints into the terminal, which the server then takes into account when performing optimization.

[0675] 3. Supercomputer conversion process:

[0676] The server converts the tuned model and parameters into program code that can be processed by the supercomputer. During this process, parallel processing optimizations are performed to maximize computation speed.

[0677] 4. Schedule management process:

[0678] The server analyzes the supercomputer's usage and automatically reserves appropriate computing time. This allows users to optimally set the timing for starting calculations.

[0679] 5. Simulation execution process:

[0680] The calculation starts automatically at the scheduled time. The supercomputer executes the parallelized code and generates the results.

[0681] 6. Verification Process:

[0682] The generated simulation results are sent to a server and analyzed by a verification agent. These verification results are then visually presented to the user via a terminal, allowing the user to review the results.

[0683] Specific example

[0684] For example, if a user wants to simulate the thermal behavior of a new material, they input the material's properties into the platform. The server selects an appropriate physical model and proposes it to the user. Based on the selected model, necessary parameters (such as thermal conductivity) are adjusted, and calculations begin on the supercomputer. After the calculation, the results are verified and reported to the user via a terminal.

[0685] Through the above process, the present invention provides an environment in which even non-expert users can efficiently perform advanced calculations.

[0686] The following describes the processing flow.

[0687] Step 1:

[0688] Users access the platform from their terminals and input the project's objectives and requirements. As users input basic information about the simulation target, the server prepares to select the optimal computational model based on that information.

[0689] Step 2:

[0690] The server analyzes user input and extracts suitable computational model candidates from its internal database. The user selects the most suitable model from the list of candidates presented by the server. The selection process is interactive, and the server adjusts the information in real time based on user feedback.

[0691] Step 3:

[0692] The terminal prompts the user to make the necessary parameter adjustments based on the selected model. The user inputs detailed parameters (e.g., range, precision settings, etc.), and the server receives this information, runs an automatic optimization engine, and generates the optimal parameter set.

[0693] Step 4:

[0694] The server collects the tuned model and parameters and converts them into a format executable on the supercomputer. At this stage, optimizations are performed for code parallelization and efficient distributed processing. The converted code is stored by the server, ready for subsequent processing.

[0695] Step 5:

[0696] The server checks the status of the supercomputer currently in use and determines the time when computing resources can be used most efficiently. It automatically reserves available computing time and notifies the user of the result, informing them when to start computing.

[0697] Step 6:

[0698] When the scheduled time arrives, the server sends an instruction to the supercomputer to start the simulation. The supercomputer performs calculations using parallelized code and generates results. Throughout this process, the server monitors the progress and responds promptly if any problems arise.

[0699] Step 7:

[0700] The calculation results generated by the supercomputer are returned to the server. The server passes these results to a verification agent, which checks whether the results meet the target conditions. After verification is complete, the results are visualized and provided to the user via a terminal for final confirmation.

[0701] The detailed processes at each step are crucial elements for enhancing the efficiency and usability of this system, and are useful in research and development and industrial applications.

[0702] (Example 1)

[0703] 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".

[0704] Modern advanced computations and simulations require specialized knowledge and complex settings, making them difficult for non-experts to use. Furthermore, efficiently utilizing high-performance computing devices such as supercomputers is not easy, and optimization of resource utilization is also required.

[0705] 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.

[0706] In this invention, the server includes means for inputting a target via an information processing device and selecting an appropriate computation model; means for optimizing numerical information based on initial conditions and constraints using the selected computation model; and means for converting the optimized computation model and numerical information into a format executable by a high-performance computer. This makes it possible to efficiently perform advanced calculations even without specialized knowledge.

[0707] An "information processing device" is a terminal that receives user input and supports data processing and the selection of calculation models.

[0708] "Purpose" refers to information that indicates the specific results or project goals that the user wants to achieve.

[0709] A "computational model" is a set of computational methods and algorithms selected according to the input objective.

[0710] "Initial conditions" are numerical values ​​or settings specified as prerequisites for executing the computational model.

[0711] A "constraint" is a set of values ​​that indicate the limitations or restrictions that must be followed when executing an computational model.

[0712] "Numerical information" refers to the data set generated from the initial conditions and constraints in a computational model.

[0713] A "high-performance computing device" is a computer with high computational power to support the processing of large amounts of data and parallel computing.

[0714] "Computational processing" is the process by which a computing device uses input numerical information to perform calculations based on models and algorithms.

[0715] "Calculation results" refer to the output or data generated by a high-performance computing device after it has completed its calculation process.

[0716] This invention provides a system that allows users to easily perform advanced calculations using an information processing device, a server, and a high-performance computing device. The user begins by accessing the information processing device via a terminal and inputting their objective. Based on the input objective, the server selects an appropriate calculation model and sets initial and constraint conditions based on that model.

[0717] The server converts the selected computational model and numerical information into a format executable by high-performance computing devices. The hardware used here is a supercomputer with high computational power. The converted data is optimized for parallel processing, enabling high-speed calculations.

[0718] For example, when a user simulates the thermal behavior of a new material, they input the material's properties into the platform using a terminal. The server then selects an appropriate physical model based on this information and presents it to the user. This process provides an environment where users can perform complex simulations even without specialized knowledge.

[0719] A concrete example of a prompt message would be, "I would like to input the thermal conductivity and specific heat of a new material and perform a thermal behavior simulation." In this way, the present invention connects the user's intent with high-performance computing capabilities, enabling applications in a wide range of fields.

[0720] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0721] Step 1:

[0722] The user accesses the system using a terminal and inputs the project objectives into the information processing device. Specifically, the user inputs the content and conditions they want to simulate in text format. This input is sent to the server and stored as basic data for use in the next step.

[0723] Step 2:

[0724] Based on the project objectives received by the server, it searches its internal database to extract candidate computational models. The server then uses an AI algorithm to select the most relevant model from this input data. This process allows the user to view a list of selectable computational models on their device.

[0725] Step 3:

[0726] The user selects the most appropriate computational model from the candidates presented by the server on their terminal. The selected model is verified on the server, and initial conditions and constraints related to each model are set. This information is stored by the server for use in the next step.

[0727] Step 4:

[0728] Based on the initial conditions and constraints entered by the user, the server optimizes numerical information. Specifically, it uses AI to automatically calculate the initial parameters best suited to the user's objective. These optimized parameters are then prepared for processing on a supercomputer.

[0729] Step 5:

[0730] The server converts the optimized computational model and parameters into a format executable by high-performance computing devices. During this process, the server optimizes parallel processing to maximize computation time efficiency. The converted data is then prepared for transfer to the supercomputer.

[0731] Step 6:

[0732] The server analyzes the usage and load of high-performance computing devices and reserves the optimal computing time. This process is performed automatically by the server's scheduling system, and users can check the start time of the calculation on their terminal.

[0733] Step 7:

[0734] According to the reserved time slot, the supercomputer begins executing the parallelized model. The high-performance computing device rapidly processes the data and generates the calculation results.

[0735] Step 8:

[0736] The server receives the calculation results sent from the supercomputer and evaluates the integrity and validity of the data. The server uses AI to verify the results and sends this verified data back to the terminal.

[0737] Step 9:

[0738] The user receives visual data provided by the server via their terminal and checks the results. This allows the user to properly analyze the results of the calculations and use them as input for the next stage of the project.

[0739] (Application Example 1)

[0740] 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".

[0741] Controlling robots and optimizing manufacturing processes in factories requires advanced technology and specialized knowledge, making it difficult for typical end-users to easily perform these tasks. Furthermore, efficient complex calculations and simulations using high-performance computing devices require resource management and systematic scheduling. Therefore, there is a need to provide an operational environment that is easily accessible even to non-professional users.

[0742] 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.

[0743] In this invention, the server includes means for selecting a computational model based on user input, means for converting the adjusted computational model and initial parameters into a format suitable for a high-performance computing device, and means for managing the computation schedule and efficiently allocating the resources of the high-performance computing device. This enables end users to efficiently perform tasks such as optimizing the operation of factory robot arms using a high-performance computing device without requiring specialized knowledge.

[0744] "User input" refers to the act of a user providing the conditions and parameters necessary for a calculation model or simulation via a terminal.

[0745] "Means for selecting a computational model" refers to a method for identifying the most suitable computational model based on the provided conditions.

[0746] "Means for adjusting initial parameters" refers to methods for setting necessary initial values ​​and constraints for a selected computational model and optimizing it.

[0747] "Means of converting to a format suitable for high-performance computing devices" refers to a method of converting the adjusted model and parameters into a code format that can be processed by a high-performance computer.

[0748] "Means of managing computation schedules" refers to a method of investigating the available time and resources of high-performance computing devices and creating a schedule that enables efficient computation execution.

[0749] "Means for efficiently allocating resources of high-performance computing devices" refers to a method of allocation that uses computing resources without waste and optimizes processing time and load.

[0750] "Means of providing an operable interface" refers to a method that allows users to intuitively manipulate and visualize calculation and simulation results in an understandable format.

[0751] The system of this invention is designed to enable users to efficiently perform complex simulations on a high-performance computing device using a terminal. A specific embodiment is described below.

[0752] The server first receives input from the user and selects a computational model from the database based on that input. For the selected model, it automatically adjusts the parameters based on the initial parameters and constraints further set by the user. At this stage, the software used includes optimization algorithms to rapidly process the data.

[0753] The server translates the adjusted computational model and parameters into code that can be executed on high-performance computing devices such as supercomputers. This translation process involves constructing the code with particularly high-speed parallel processing in mind.

[0754] The terminal provides users with a visually user-friendly interface and displays simulation results in real time. A concrete example of the results is the simulation of robot arm movements that contribute to factory efficiency. This simulation provides the optimal movement pattern by taking into account the characteristics of the parts being handled and the balance of the movement speed.

[0755] When using a generative AI model, the following example prompts apply:

[0756] "I would like to perform an operation simulation to optimize the robot arm. Please provide the current operating time, error, and constraints, and perform a simulation to achieve maximum efficiency."

[0757] This allows users to obtain optimal results by leveraging the advantages of high-performance computing devices, even without advanced expertise.

[0758] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0759] Step 1:

[0760] The user logs into the system using a terminal and starts the project. In this step, the user inputs the operating conditions and constraints of the robot arm they want to simulate. The entered data reflects the user's intentions and goals, and this serves as the basis for processing in the next step.

[0761] Step 2:

[0762] The server receives input data from the user, analyzes it, and selects the optimal computational model from the database. This selection process utilizes generative AI models to quickly identify the model best suited to the user's needs. The selected model is then returned to the server as output.

[0763] Step 3:

[0764] The server optimizes the initial parameters for the selected computational model. Here, it considers the operating conditions and constraints provided by the user and adjusts the initial parameters accordingly. Specifically, it receives the parameter range and constraints as input, applies an optimization algorithm, and outputs the optimal initial parameters.

[0765] Step 4:

[0766] The server converts the tuned model and parameters into a format suitable for high-performance computing devices. Code optimization is performed here to maximize the use of parallel processing. At this stage, the tuned model is received as input, and highly efficient executable code is generated.

[0767] Step 5:

[0768] The server monitors the operational status of the high-performance computing units and prepares to run simulations at the most appropriate schedule. The input here is the latest resource status of the computing units, and based on this information, the optimal timing for starting calculations is output.

[0769] Step 6:

[0770] A high-performance computing unit performs calculations at scheduled times and generates simulation results. The output simulation results include detailed analysis based on user-defined conditions.

[0771] Step 7:

[0772] The server receives the generated simulation results and performs verification and evaluation. This process uses verification algorithms to assess the reliability and validity of the results. The input is the simulation data, and the output is the evaluated results report.

[0773] Step 8:

[0774] Finally, the server sends the evaluation results to the terminal and provides them to the user in a visualized format. A user interface is used here to clearly display the results. The input is the evaluated result data, and the output is user-friendly visual information.

[0775] 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.

[0776] This invention is a system that enhances the user experience when users perform advanced calculations and simulations using a supercomputer by combining it with an emotion engine. This system utilizes emotion recognition technology to dynamically adjust the interface and feedback according to the user's emotional state, thereby increasing work efficiency and comfort.

[0777] System Overview

[0778] 1. Emotion recognition process:

[0779] The emotion engine uses the camera and sensors on the device to analyze the user's facial expressions and behavior in real time. Based on this data, the server identifies the user's emotional state and prepares that information for use throughout the system.

[0780] 2. Interface adjustment process:

[0781] The server receives feedback from the emotion engine and, if it determines that the user is experiencing stress, changes the interface to be more intuitive and easier to use. This includes simpler navigation and highlighted operation guides.

[0782] 3. Optimizing the simulation process:

[0783] The server modifies the simulation's progression based on the user's emotional state. For example, if the user is showing signs of anxiety, the server simplifies the process and presents the progress in an easy-to-understand manner to increase the user's sense of security.

[0784] 4. Feedback process:

[0785] After the results are generated, the server customizes the feedback based on the sentiment analysis results from the sentiment engine. This feedback is delivered to the user via the device, providing appropriate advice and suggestions for improvement.

[0786] Specific example

[0787] For example, suppose a user is performing a complex aircraft performance simulation and the emotion engine detects a decrease in the user's concentration. In this situation, the server simplifies the simulation screen and hides unnecessary information, allowing the user to focus only on the target parameters.

[0788] Thus, by integrating an emotion engine, the present invention provides a system that enhances the user experience by realizing high-performance computational support that is attuned to the user's emotions.

[0789] The following describes the processing flow.

[0790] Step 1:

[0791] The user operates a terminal to access the system and input the project's objectives and data. This input completes the initial setup, and the server prepares to search for candidate computational models.

[0792] Step 2:

[0793] The device uses its built-in camera and microphone to record the user's facial expressions and voice intonation in real time. The emotion engine analyzes this recorded data to identify the user's current emotional state. The server receives this information and prepares to adjust the interface and processes.

[0794] Step 3:

[0795] The server selects candidate computational models from the database based on user input and sends a list of candidates to the terminal. The user reviews this list on the terminal and selects the most suitable model. After selection, the server provides further feedback and processing advice.

[0796] Step 4:

[0797] Based on information from the emotion engine, the server provides an interface optimized for the user's emotional state. If the user shows signs of frustration, the server highlights the operation guide or simplifies the operation procedure to make it easier to understand.

[0798] Step 5:

[0799] Once the user selects a model and inputs the necessary data into the terminal, the server automatically adjusts the parameters and converts the code into a format that can be processed by a supercomputer. Optimizations such as parallel processing are also performed at this stage.

[0800] Step 6:

[0801] The server optimizes the simulation's progress in real time based on emotional data. For users exhibiting impatience, it provides reassurance by displaying detailed processing status and clearly showing the progress.

[0802] Step 7:

[0803] After the supercomputer runs the simulation and generates results, the server verifies the results and forms feedback. The verification takes into account the analysis results of the emotion engine, and the most relevant detailed information and improvements are provided to the user through the terminal.

[0804] Through these steps, the present invention provides a support environment for performing advanced calculations and simulations while taking into consideration the user's emotions.

[0805] (Example 2)

[0806] 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".

[0807] Modern high-performance computing systems require improved efficiency and user comfort when performing complex calculations. However, conventional systems proceed with calculations in a uniform manner regardless of the user's emotional state, lacking care, especially in situations where users feel stressed or anxious, and failing to provide an optimal user experience.

[0808] 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.

[0809] In this invention, the server includes means for analyzing the user's emotional state, means for dynamically changing user information based on the user's emotions, and means for optimizing computational processing according to the user's emotional state. This makes it possible to provide management and feedback that is sensitive to the user's emotions, thereby improving computational efficiency and user experience.

[0810] A "computational model" is a set of algorithms or mathematical formulas constructed to achieve a specific computational objective.

[0811] "Numerical elements" refer to the parameters and variables in a computational model, and are values ​​that affect the calculation results.

[0812] "High-performance computing systems" refer to supercomputers and cluster computers designed to process large-scale calculations quickly and efficiently.

[0813] "Computational work" refers to the entire series of computational processes performed using a computational model.

[0814] "Emotion recognition technology" is a technology that analyzes a user's emotional state from their facial expressions, voice, and behavior.

[0815] "Dynamically changing user information" means adjusting the interface and output information in real time according to the user's emotional state.

[0816] "Efficient resource allocation" means allocating limited resources, such as computing resources and time, in a way that makes the most effective use of them.

[0817] The embodiments for carrying out the present invention will be described in detail below.

[0818] The user first uses a terminal to operate a high-performance computing system. This terminal has built-in cameras and sensors to capture the user's facial expressions and movements. The data acquired from these devices is input into the emotion recognition system in real time.

[0819] The server receives data sent from the terminal and analyzes the user's emotional state using a generative AI model. This model utilizes facial recognition software and voice analysis algorithms to identify emotions such as stress and joy. Once the emotional state is identified, the server dynamically adjusts the user interface based on that information. For example, if the user is showing signs of stress, the server simplifies navigation to make it more intuitive and highlights important information.

[0820] Furthermore, the server optimizes the progress of calculations while taking into account the user's emotional state. Specifically, if the server determines that the user is in a state of impatience, it simplifies the calculation process and supports the user by visually displaying intermediate results.

[0821] Once the calculation results are generated, the server customizes the feedback based on the emotion recognition results, providing advice and a roadmap to the next steps tailored to the user's state. The device receives this feedback and displays it appropriately to the user.

[0822] A concrete example is when a user is performing a weather forecast simulation; the system evaluates the user's emotional state and optimizes the display of information as needed to facilitate the process.

[0823] An example of a prompt message is, "How can we use emotion recognition to provide efficient support when a user runs a simulation?" Such a framework allows users to utilize high-performance computing systems more comfortably.

[0824] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0825] Step 1:

[0826] The device collects the user's facial expressions and movements using cameras and sensors. This input data includes facial image data and audio data. The device then preprocesses this data, removing data noise and converting it into a format suitable for analysis. A clean dataset is generated as output.

[0827] Step 2:

[0828] The server receives a pre-processed dataset sent from the terminal. The server inputs this data into a generating AI model, which analyzes the user's emotional state in real time. The data calculations performed here output the user's emotional state in the form of "stress" or "decreased concentration."

[0829] Step 3:

[0830] The server dynamically adjusts the user interface based on the analysis of the user's emotional state. Specifically, the server can reorganize the interface, transforming it into a simpler, more user-friendly interface. For example, if stress is detected, the system highlights important items and eliminates complex slide menus. The resulting output is the adjusted interface settings.

[0831] Step 4:

[0832] The server optimizes calculations based on the user's emotional state. This process simplifies calculation steps and redesigns how intermediate results are presented, particularly for users exhibiting anxiety. The output consists of user-friendly intermediate results.

[0833] Step 5:

[0834] The terminal presents the user with feedback information received from the server. This includes advice that takes emotional state into account and guidance on the next steps. The terminal displays this information in an optimized interface to support the user's actions. The final output is personalized feedback information for the user.

[0835] (Application Example 2)

[0836] 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".

[0837] Conventional calculation and simulation systems often fail to consider the user's emotional state, making it difficult to improve the user experience. Furthermore, complex interfaces can cause user stress and reduce work efficiency. There is a need for systems that address these challenges and enhance both user comfort and efficiency.

[0838] 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.

[0839] In this invention, the server includes means for detecting an emotional state and providing an appropriate interface, means for dynamically changing the operation panel based on the emotional state, and means for verifying and providing simulation results to the user. This enables automatic adjustment of the interface according to the user's emotional state, thereby reducing user stress and improving work efficiency.

[0840] A "user" refers to a person who uses the system to perform calculations or simulations.

[0841] A "model" refers to a set of hypotheses or designs used for calculations or simulations selected by the user.

[0842] "Parameters" refer to numerical values ​​or variables used to adjust the behavior of a model.

[0843] "Large-scale computing equipment" refers to devices such as supercomputers that are used to process large amounts of data and perform advanced calculations.

[0844] A "calculation schedule" refers to a plan for managing the order and timing of calculations.

[0845] "Emotional state" refers to the user's mental state or mood, and the information detected by the emotion engine.

[0846] "Interface" refers to the screen or operating environment that a user uses to interact with a system.

[0847] The term "control panel" refers to a part of the interface that allows users to operate various functions of a system.

[0848] "Simulation results" refers to calculation results and analysis data obtained by large-scale computing devices.

[0849] This invention is a system that utilizes emotion recognition technology to dynamically adjust the system's interface and functions according to the user's emotional state, thereby improving the user experience when using large-scale computing devices. This system is realized through the roles of the server, terminal, and user.

[0850] The server uses an emotion recognition engine to analyze the user's emotional state in real time. It acquires the user's facial expressions and actions from cameras and sensors and identifies their emotional state based on this information. Based on this information, it adjusts the interface and control panel according to the user's emotional state. If the user is feeling stressed, the server simplifies the control panel and changes the interface to display only the most important information.

[0851] The terminal is responsible for sending and receiving emotional state data between the user and the server, and displaying the simulation results. Users can interact with the system through the terminal and receive customized feedback tailored to their emotional state.

[0852] For example, if the system detects that a user is showing signs of fatigue while operating a robot in a factory, it will simplify the interface and reduce visual strain. Another example of a prompt to input into the generating AI model is, "How would you modify the interface if the user is experiencing stress?" This makes it possible to provide an experience that is sensitive to the user's emotions.

[0853] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0854] Step 1:

[0855] The server acquires user facial expression data from the terminal's camera and sensors. The input is the user's real-time video. The server processes this video data and uses facial recognition technology to extract the user's facial features. Based on this, it makes an initial judgment about the user's emotional state.

[0856] Step 2:

[0857] The server uses an emotion recognition engine to analyze the user's emotional state from extracted facial features. The input for this step is facial features, and the output is the user's emotional state (e.g., concentration, fatigue, stress). Data analysis techniques are used to classify specific facial patterns into emotional categories.

[0858] Step 3:

[0859] The server dynamically adjusts the interface based on the analysis results. The input is the emotional state obtained in the previous step, and the output is the modified user interface. When the user is stressed, the server hides visually complex elements and highlights only important information.

[0860] Step 4:

[0861] The terminal presents the user with a pre-configured interface received from the server. At this stage, the interface display is optimized to the user's needs. The input is the interface data received from the server, and the output is its visual representation. The terminal renders the interface in a way that allows the user to operate it intuitively.

[0862] Step 5:

[0863] Users manipulate and verify simulation results using a tailored interface. User input is the response to the operation, and output is feedback and data viewing corresponding to that response. Users efficiently take actions to achieve their goals.

[0864] 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.

[0865] 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.

[0866] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[0867] 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.

[0868] 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.

[0869] 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.

[0870] 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.

[0871] 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.

[0872] 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."

[0873] 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.

[0874] 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.

[0875] 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.

[0876] 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.

[0877] 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.

[0878] 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.

[0879] 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.

[0880] 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.

[0881] 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.

[0882] 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.

[0883] 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.

[0884] 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.

[0885] The following is further disclosed regarding the embodiments described above.

[0886] (Claim 1)

[0887] A means of selecting a model based on user input,

[0888] A means of adjusting parameters based on the selected model,

[0889] Means for converting the adjusted model and parameters into a format suitable for a supercomputer,

[0890] A means of managing the computing schedule based on the usage status of the supercomputer,

[0891] Means for running simulations on a supercomputer,

[0892] A means of verifying and providing simulation results to users,

[0893] A system that includes this.

[0894] (Claim 2)

[0895] The system according to claim 1, further comprising means for optimizing parameters in accordance with the user's goals.

[0896] (Claim 3)

[0897] The system according to claim 1, further comprising means for enabling efficient allocation of resources in managing calculation schedules.

[0898] "Example 1"

[0899] (Claim 1)

[0900] A means for inputting a target via an information processing device and selecting an appropriate computational model,

[0901] The selected computational model provides means for optimizing numerical information based on initial conditions and constraints,

[0902] A means for converting an optimized computational model and numerical information into a format executable by a high-performance computer,

[0903] A means for analyzing the usage status and load of a high-performance computing device and automatically reserving the optimal computing time,

[0904] A means for performing calculation processing and generating calculation results in a high-performance computing device,

[0905] A means of evaluating the generated calculation results and providing them to the user visually,

[0906] A system that includes this.

[0907] (Claim 2)

[0908] The system according to claim 1, further comprising means for automatically performing data adjustments to suit the user's purpose in optimizing numerical information.

[0909] (Claim 3)

[0910] The system according to claim 1, further comprising means for performing analysis to maximize the effective use of resources in the reservation of computation time.

[0911] "Application Example 1"

[0912] (Claim 1)

[0913] A means for selecting a calculation model based on user input,

[0914] A means for adjusting initial parameters based on the selected computational model,

[0915] Means for converting the adjusted computational model and initial parameters into a format suitable for a high-performance computing device,

[0916] A means for managing the calculation schedule based on the operating status of the high-performance computing device,

[0917] A means of performing complex simulations on a high-performance computing device,

[0918] A means for evaluating the simulation results and providing them to the user via a display device,

[0919] A means of providing an interface that visualizes and manipulates calculation results,

[0920] A system that includes this.

[0921] (Claim 2)

[0922] The system according to claim 1, further comprising means for optimizing the operation of a machine device based on user-defined operating conditions in parameter adjustment.

[0923] (Claim 3)

[0924] The system according to claim 1, further comprising means for efficiently allocating the resources of a high-performance computing device in managing the calculation schedule.

[0925] "Example 2 of combining an emotion engine"

[0926] (Claim 1)

[0927] A means of selecting a calculation model based on user input,

[0928] Means for adjusting numerical elements based on the selected calculation model,

[0929] Means for converting the adjusted computational model and numerical elements into a format suitable for a high-performance computing system,

[0930] A means of managing computational tasks based on the usage status of high-performance computing systems,

[0931] Means for performing computational processing in a high-performance computing system,

[0932] A means of verifying the calculation results and providing them to the user,

[0933] A means of analyzing a user's emotional state using emotion recognition technology,

[0934] A means of dynamically changing user information based on the user's emotional state,

[0935] A means for optimizing the progress of calculation processing based on the user's emotional state,

[0936] A system that includes this.

[0937] (Claim 2)

[0938] The system according to claim 1, further comprising means for optimizing the calculation process in accordance with the user's goals when adjusting numerical elements.

[0939] (Claim 3)

[0940] The system according to claim 1, further comprising means for enabling the efficient allocation of resources in managing computational tasks.

[0941] "Application example 2 when combining with an emotional engine"

[0942] (Claim 1)

[0943] A means of selecting a model based on user input,

[0944] A means of adjusting parameters based on the selected model,

[0945] Means for converting the adjusted model and parameters into a format suitable for large-scale computing devices,

[0946] A means for managing calculation schedules based on the usage status of large-scale computing devices,

[0947] Means for performing simulations on a large-scale computing device,

[0948] A means for detecting emotional states and providing an appropriate interface,

[0949] A means for dynamically changing the control panel based on emotional state,

[0950] A means of verifying and providing simulation results to users,

[0951] A system that includes this.

[0952] (Claim 2)

[0953] The system according to claim 1, further comprising means for optimizing parameters in accordance with the user's goals.

[0954] (Claim 3)

[0955] The system according to claim 1, further comprising means for enabling efficient allocation of resources in managing calculation schedules. [Explanation of symbols]

[0956] 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. A means of selecting a model based on user input, A means of adjusting parameters based on the selected model, Means for converting the adjusted model and parameters into a format suitable for a supercomputer, A means of managing the computing schedule based on the usage status of the supercomputer, Means for running simulations on a supercomputer, A means of verifying and providing simulation results to users, A system that includes this.

2. The system according to claim 1, further comprising means for optimizing parameters in accordance with the user's goals.

3. The system according to claim 1, further comprising means for enabling efficient allocation of resources in managing calculation schedules.

Images