system

Abstract

We provide the system. [Solution] Means for acquiring simulation data, Means for preprocessing the aforementioned simulation data, A method using an artificial intelligence model to analyze preprocessed data, A means for outputting the analysis results obtained from the aforementioned model in natural language, A means of visually displaying the analysis results to the user, 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, the method including steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a character of the chatbot, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance as a 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] In modern digital twin technology, in order for an expert to analyze the results of a simulation and apply them to actual applications, high-level expertise, a great deal of time, and costs are required. However, the number of experts is limited, and the resources therefor are also restricted. In such a situation, it is difficult to interpret the simulation results quickly and efficiently and apply them to business. The object of this invention is to provide a system that automates the analysis of simulation data and enables a user to directly obtain useful findings without going through an expert, thereby solving this problem.

Means for Solving the Problems

[0005] This invention provides a system that acquires simulation data, preprocesses it, analyzes it with an artificial intelligence model, outputs the results in natural language, and presents them visually to the user. This system also includes a function to acquire user feedback based on the analysis results and utilize it for training the artificial intelligence model, thereby improving the accuracy and validity of the analysis. Furthermore, it enables efficient decision-making by presenting the user with recommended actions for specific physical phenomena based on the insights gained from the analysis results.

[0006] "Simulation data" refers to a collection of digital information generated for analysis and prediction within a virtual environment related to a digital twin.

[0007] "Preprocessing" refers to the process of preparing data for analysis by performing tasks such as format conversion, noise reduction, and imputation of missing values ​​before data analysis is carried out.

[0008] An "artificial intelligence model" is a set of algorithms that use machine learning and deep learning to perform pattern recognition and prediction from input data.

[0009] "Means of outputting in natural language" refers to techniques for presenting analysis results in a human-readable format as text, and natural language processing technology is used for this purpose.

[0010] "Means of visual display" refers to methods of conveying analysis results to users visually through graphs, charts, and interfaces.

[0011] "User feedback" refers to information that users provide by evaluating or commenting on the information and recommendations offered by the system, and is used to further improve the system.

[0012] "Methods for retraining a model" refer to the process of improving an existing artificial intelligence model based on newly collected data and feedback, and adjusting the model's parameters to enhance its analytical accuracy.

[0013] "Recommended actions" refer to specific actions or measures suggested based on the analysis results, and are presented as solutions to problems faced by the user. [Brief explanation of the drawing]

[0014] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Figure 11] This is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] This is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] This is a sequence diagram showing the processing flow of the data processing system in Example 2, which incorporates an emotion engine. [Figure 14]It is a sequence diagram showing the processing flow of a data processing system in Application Example 2 when a sentiment engine is combined.

Embodiments for Carrying Out the Invention

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

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

[0017] In the following embodiments, a numbered processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Also, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), etc.

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

[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] The system of this invention automates the analysis of simulation data in a digital twin environment and provides users with useful insights. This system mainly consists of a server, terminals, and users.

[0036] The server collects and preprocesses simulation data. It receives image and numerical data from the digital twin system. This data is then processed through preprocessing steps such as noise reduction and formatting to make it ready for analysis.

[0037] Next, the server uses the pre-processed data to perform analysis using an artificial intelligence model. The AI ​​model extracts features from the input data and performs anomaly detection and prediction. This analysis generates results in a format that can be output in natural language.

[0038] Subsequently, the server uses natural language processing technology to summarize the analysis results into user-friendly text, generating insights. These insights include information to support important decision-making for the user.

[0039] The terminal receives analysis results and insights in natural language from the server and displays them visually through the user interface. This allows the user to quickly grasp the content of the analysis and decide on the necessary actions.

[0040] Users improve their work and take appropriate actions based on the analysis results displayed on their terminals. The feedback obtained during this process is then incorporated back into the system, and the server uses this feedback to retrain the artificial intelligence model. This improves the accuracy of the next analysis.

[0041] A concrete example is improving traffic flow management in smart cities. The server performs traffic flow simulations based on real-time data from traffic sensors, identifying the causes of congestion and proposing countermeasures. The terminal then presents the analysis results and proposed signal schedule improvements to the user, supporting them in making decisions to optimize urban traffic management. Successfully completing this process improves overall urban traffic efficiency and contributes to reducing congestion.

[0042] The following describes the processing flow.

[0043] Step 1:

[0044] The server receives image and numerical data based on simulations from the digital twin system. This data includes various parameters and environmental conditions of the phenomenon being studied.

[0045] Step 2:

[0046] The server performs preprocessing on the received image and numerical data, such as noise reduction and data loss imputation, to prepare it for analysis. This process improves the quality of the dataset and increases the reliability of the analysis results.

[0047] Step 3:

[0048] The server inputs pre-processed data into an artificial intelligence model for feature extraction and analysis. The AI ​​model uses deep learning to recognize patterns in the data, detect anomalies, and identify important indicators.

[0049] Step 4:

[0050] The server uses natural language processing technology to convert the analysis results obtained from the artificial intelligence model into text, generating insights in a format easily understandable to the user. These insights include predicted phenomena and recommended countermeasures.

[0051] Step 5:

[0052] The terminal receives insights transmitted from the server and displays them visually through the user interface. Users can use this information to quickly understand the situation and make decisions.

[0053] Step 6:

[0054] Based on the analysis results and insights obtained from their devices, users implement business-related actions and improvement measures. This allows users to increase operational efficiency and solve problems.

[0055] Step 7:

[0056] Users input feedback on the countermeasures they have taken and the results of those countermeasures into their terminals. The server collects this feedback and uses it to retrain the artificial intelligence model. This improves the accuracy of the analysis in the next run.

[0057] (Example 1)

[0058] 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."

[0059] In today's complex systems, there is a need to efficiently analyze large amounts of simulation data and provide information in a way that users can intuitively understand. Furthermore, there is a lack of systems that can improve the accuracy of data analysis by utilizing the feedback obtained, and this solution addresses that challenge.

[0060] 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.

[0061] In this invention, the server includes a mechanism for acquiring data, a mechanism for preprocessing the data, and a mechanism for using a machine learning model to analyze the preprocessed data. This makes it possible to efficiently process large amounts of data and to improve the accuracy of the analysis by reflecting feedback from users.

[0062] A "data acquisition mechanism" is a means of receiving digital information from an external source and converting it into a format usable within the system.

[0063] A "preprocessing mechanism" is a means of removing noise from acquired digital information and formatting it to make it easier to analyze.

[0064] A "mechanism that uses machine learning models" is a means of analyzing large amounts of digital information and utilizing algorithms to detect useful patterns and anomalies.

[0065] A "mechanism for outputting in natural language" is a means of generating and presenting analysis results in a form that is easy for users to understand.

[0066] A "visual display mechanism" is a means of displaying analyzed information in a way that users can intuitively understand.

[0067] A "mechanism for generating useful insights" is a means of constructing valuable information and insights to support users' decision-making based on analysis results.

[0068] A "feedback acquisition and retraining mechanism" is a means of collecting evaluations and reactions from users and updating the machine learning model based on them to improve its accuracy.

[0069] A "mechanism for suggesting recommended actions" is a means of showing users the optimal course of action derived from analyzed data and encouraging them to take action.

[0070] This invention is a system that automatically analyzes simulation data in a digital twin environment and provides users with useful insights. The main components of this system are a server, terminals, and users.

[0071] The server has a mechanism to automatically receive large amounts of data acquired from the digital twin system. For example, it collects real-time digital information via an API. This data includes image and numerical data, and is preprocessed in preparation for later analysis. At this stage, denoising and formatting are performed using the Python Pandas library.

[0072] Next, the server inputs the pre-processed data into a machine learning model, and the system performs anomaly detection and prediction. This machine learning model uses libraries such as TENSORFLOW® and PyTorch to extract features from the data and proceed with the analysis. The results obtained from the analysis are converted into natural language and provided in a format that is easy for the user to understand. For natural language processing, a generative AI model is employed to generate specific information, such as "The traffic congestion from 10 o'clock is due to construction, and a 15-minute delay is predicted."

[0073] The terminal receives analysis results sent from the server and displays them visually through a user interface. Technologies such as HTML and JavaScript are utilized, and a graphical user interface is designed to allow users to intuitively analyze the data.

[0074] Users improve and modify the system based on the analysis results displayed via their devices, providing useful feedback. This feedback is sent to the server and used to retrain the generated AI model. Through this process, the accuracy of the analysis improves, which is useful for subsequent data analyses.

[0075] A concrete example is traffic flow management in smart cities. The server analyzes real-time traffic sensor data and suggests causes of congestion and countermeasures. These analysis results are presented to users via terminals, supporting effective decision-making in urban traffic management.

[0076] An example of a prompt message that can be entered is, "Based on real-time data from traffic sensors, identify the causes of urban traffic congestion and propose effective improvement measures."

[0077] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0078] Step 1:

[0079] The server receives digital information from the digital twin system. The inputs are image and numerical data from the digital twin system, collected in real time via an API. The server stores this initial data internally, preparing it for subsequent processing.

[0080] Step 2:

[0081] The server preprocesses the received digital information. The main input is the raw data containing noise collected in Step 1. The server applies a denoising filter using the Python Pandas library to remove unwanted data. It also standardizes the data format and converts it into a structure that is easy to analyze. The preprocessing results in clean data, which is used in the next analysis step.

[0082] Step 3:

[0083] The server inputs pre-processed data into a machine learning model and performs data analysis. The input is clean, formatted data, which is then fed into a generative AI model using TensorFlow or PyTorch. The model extracts features from the data, performs calculations such as anomaly detection and prediction, and outputs the analysis results. For example, it can predict fluctuations in traffic flow during a specific time period.

[0084] Step 4:

[0085] The server generates a summary of the analyzed results using natural language processing technology. The input is the analysis results obtained in step 3, and based on this, a generation AI model is used to convert it into natural language text that is easy for the user to understand. The output provides information that supports the user's decision-making.

[0086] Step 5:

[0087] The terminal receives natural language analysis results sent from the server and displays them visually. The primary input is a designed natural language summary. The terminal uses HTML and JavaScript to place this information on a graphical user interface, making it easily accessible to the user.

[0088] Step 6:

[0089] Users utilize the analysis results presented via their terminals to improve their work and make decisions. Feedback input consists of the user's choices and judgments, which are sent back to the server. The server stores this feedback information and uses it to retrain the generated AI model. This is expected to improve the accuracy of subsequent data analyses.

[0090] (Application Example 1)

[0091] 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."

[0092] In current digital twin environments, there is a lack of means to effectively utilize real-time data to immediately present analysis results regarding specific physical phenomena and locations, enabling users to make rapid decisions. Furthermore, it is difficult to improve learning by effectively utilizing feedback loops based on analysis results.

[0093] 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.

[0094] In this invention, the server includes means for receiving information for simulation, means for preprocessing the simulation information, and means for using a learning algorithm to analyze the preprocessed information. This enables the rapid provision of analysis results based on real-time acquired data to the user, and also allows for automatic improvement of the learning algorithm through feedback.

[0095] "Information for simulation" refers to the data necessary to virtually reproduce physical phenomena and events in a digital twin environment.

[0096] "Preprocessing functions" refer to processing methods such as noise reduction and format conversion performed to convert raw data into an analyzable format.

[0097] A "learning algorithm" is a computational method used to extract features from input data and perform pattern recognition, prediction, and anomaly detection.

[0098] The "function to output in natural language format" is a technology that expresses analysis results and insights in a form that humans can easily understand.

[0099] "Devices provided to users" refers to interface devices that visually display analysis results and enable users to easily interpret the data.

[0100] "Specific location information" refers to a concrete location within physical space, and is an element that enables data analysis based on that location.

[0101] "Means for processing real-time information" refers to technologies that instantly analyze data obtained continuously over time and generate results.

[0102] This invention makes it possible to construct a traffic management system in a smart city environment. The server has the function of receiving and preprocessing information for simulation from traffic sensors. Specifically, it performs noise reduction and data formatting to prepare the data for analysis in real time. Python and the Requests library are used for this purpose.

[0103] Next, the server uses a learning algorithm based on the pre-processed information to perform anomaly detection and congestion prediction. The learning algorithm used here is implemented by a generative AI model. The detected anomaly data and prediction results are output in natural language format.

[0104] The server then sends the generated natural language analysis results to the terminal. The terminal functions as a device to provide the results to the user, displaying the data visually. This allows the user to quickly grasp the analysis results and assist in decision-making, such as selecting an appropriate route to avoid congestion.

[0105] As a concrete example, a dedicated application is installed on the smartphones that users use daily, and traffic information is updated in real time. Users can choose an alternative route based on the traffic congestion information and shorten their commute time.

[0106] An example of a prompt message could be: "Recent traffic data analysis has detected abnormal traffic volume at a specific location. Do you want to check an alternative route?" Such prompt messages help users make informed decisions.

[0107] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0108] Step 1:

[0109] The server receives real-time simulation information from traffic sensors. The input is raw data from the sensors, and the output is this data itself. Specifically, the data is retrieved via an API and stored in the database in its unformatted state.

[0110] Step 2:

[0111] The server performs preprocessing on the received raw data. Specifically, it performs noise reduction and data formatting. The input here is the raw data, which is the output of step 1, and the output is analyzable data that has been noise-removed and formatted.

[0112] Step 3:

[0113] The server uses pre-processed data to perform analysis with a generated AI model. Specifically, it extracts features from the data and performs anomaly detection and traffic congestion prediction. The input is the data formatted in step 2, and the output is the analysis results, such as anomaly detection information and prediction results.

[0114] Step 4:

[0115] The server converts the generated analysis results into natural language format. Using natural language processing techniques, it transforms the results into a language that is easily understandable to humans. The input is the analysis result from step 3, and the output is a text format that can be presented to the user.

[0116] Step 5:

[0117] The server sends the parsing results, converted into natural language format, to the terminal. Specifically, it sends information to the user's terminal via data communication. The input is the text data that was output in step 4, and the output is the parsing result displayed visually on the terminal.

[0118] Step 6:

[0119] The user receives the analysis results visually presented on the terminal and makes a decision. Specifically, they read the prompt text and select the optimal route to avoid congested areas. The input is the visually displayed information that is the output in step 5, and the output is the decision-making action made by the user.

[0120] 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.

[0121] This invention provides a system that combines an emotion engine to improve the user experience in the analysis of digital twin simulation data. This system consists of a server, a terminal, and a user, and each element works organically to enable more effective utilization of the analysis results.

[0122] The server preprocesses image and numerical data acquired from digital twin simulations and analyzes them using an artificial intelligence model. During the analysis, it extracts data features and generates insights derived from them. These insights are output in natural language and provided to the user.

[0123] In addition, this system incorporates an emotion engine. The terminal senses the user's emotions, facial expressions, voice tone, etc., and sends this data to the emotion engine. The emotion engine analyzes this data to identify the user's current emotions and stress level.

[0124] Based on the information obtained from the emotion engine, the server adjusts how the analysis results are presented. For example, if the user is experiencing high stress, it selects an easy-to-use, low-load interface; conversely, if the user is relaxed, it presents detailed analysis results.

[0125] A concrete example is improving production efficiency in a manufacturing plant. The server acquires machine operation data and gains insights into operational efficiency and maintenance needs. Terminals acquire real-time emotional information from on-site workers via an emotion engine and feed it back to the server. As a result, the system makes suggestions and adjusts the interface to reduce the burden on workers, thereby improving productivity. This entire process increases operational efficiency and reduces worker satisfaction and burden.

[0126] The following describes the processing flow.

[0127] Step 1:

[0128] The server receives simulation image data and numerical data from the digital twin system. This allows it to collect basic information necessary for verifying and predicting phenomena in the virtual environment.

[0129] Step 2:

[0130] The server preprocesses the received data. Specifically, it performs noise reduction, imputation of missing values, and adjustment of the data format to prepare it for optimal analysis.

[0131] Step 3:

[0132] The server inputs pre-processed data into an artificial intelligence model, which extracts and analyzes the data's features. This allows for the detection of anomalies, the uncovering of unknown patterns, and the generation of insights that form the basis of inference.

[0133] Step 4:

[0134] The server uses natural language processing technology to convert the analysis results into text in a format that is easy for the user to understand, and generates it as knowledge.

[0135] Step 5:

[0136] The terminal receives insights transmitted from the server and displays them visually through the user interface. This allows the user to accurately grasp the information and make quick decisions.

[0137] Step 6:

[0138] The device collects emotional information by sensing the user's facial expressions and voice tone, and sends it to the emotion engine.

[0139] Step 7:

[0140] The emotion engine analyzes data sent from the device to identify the user's current emotional state. This information indicates the user's stress level, level of concentration, and other factors.

[0141] Step 8:

[0142] The server adjusts how the analysis results are presented based on information from the emotion engine. Specifically, it optimizes the complexity and amount of information in the display interface according to the user's emotional state.

[0143] Step 9:

[0144] Users can review analysis results and determine appropriate actions for their work through a customized interface presented on their device. This enables efficient decision-making tailored to the specific situation.

[0145] Step 10:

[0146] Users input feedback on their work actions and results into a terminal. The server receives this feedback and uses it to improve the artificial intelligence model and enhance the accuracy of the analysis.

[0147] (Example 2)

[0148] 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".

[0149] There is a need to provide the results of complex simulation data analysis in a format that is easy for users to understand. However, conventional technologies lack the ability to provide information that takes into account the user's emotional state, making the improvement of the user experience a challenge. Furthermore, it is also important to quickly reflect changing user feedback and improve the accuracy of the analysis information provided.

[0150] 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.

[0151] In this invention, the server includes means for acquiring information, means for preprocessing the information, and means for using an artificial intelligence model to analyze the preprocessed information. This enables the presentation of flexible analysis results that correspond to the user's emotional state and highly accurate data analysis that reflects user feedback.

[0152] "Means of acquiring information" refers to the function that a system uses to collect necessary data and information from external sources.

[0153] "Preprocessing means" refers to a function that performs data processing to prepare acquired information into a format suitable for analysis.

[0154] "Methods using artificial intelligence models" refer to the function of extracting patterns and insights from data by utilizing machine learning and statistical models in data analysis.

[0155] "Means of outputting in natural language" refers to a function that converts the analysis results into a language format that is easy for humans to understand and provides them.

[0156] "Means for detecting the user's emotional state" refers to a function that analyzes the user's physical reactions, such as facial expressions and voice, to understand their emotional state.

[0157] "Means for adjusting the presentation method of analysis results based on emotional state" refers to a function that appropriately changes the content and format of the displayed analysis results according to the detected emotions of the user.

[0158] "Means for visually displaying analysis results to the user" refers to a display function via a graphical user interface that provides the analyzed information to the user visually.

[0159] This invention is an advanced data analysis system that utilizes digital twin technology and aims to improve the user experience. The server first acquires image and numerical data generated in real time from the digital twin simulation. Advanced data cleaning software is used to perform preprocessing on this data, such as noise reduction and format conversion.

[0160] Next, the server utilizes a generative AI model to analyze this preprocessed data. This AI model is built on machine learning algorithms to extract features from the data and provide the necessary insights. The results are then translated into human-readable language using natural language processing software and presented to the user.

[0161] The device uses sensors such as cameras and microphones to detect the user's emotional state. The emotional data acquired by these sensors is sent to an emotion engine, which then provides the analysis results to a server. The server adjusts how the analysis results are displayed based on the user's emotions, selecting and displaying either simplified information or detailed analysis results as needed.

[0162] As a concrete example, consider optimizing machine operation in a manufacturing facility. In this case, the server collects operating data from the machines within the facility and analyzes their efficiency and maintenance needs. Simultaneously, terminals collect emotional information from on-site workers, feed it back to the server, and provide an interface that simplifies operations if the workers are feeling stressed.

[0163] An example of a prompt is the specific instruction, "Please describe data analysis and emotional state monitoring methods to improve factory productivity."

[0164] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0165] Step 1:

[0166] The server acquires image and numerical data from the digital twin simulation. This input data includes information about the machine's operating status and environment. The server stores this data in a database.

[0167] Step 2:

[0168] The server preprocesses the acquired data. This preprocessing includes denoising the data and imputing missing values. Specifically, it uses filtering algorithms to detect anomalous data and converts it into the correct format. This prepares the data for analysis.

[0169] Step 3:

[0170] The server feeds pre-processed data into a generating AI model for analysis. The model extracts features from the data and generates insights for improving machine efficiency and predicting failures. The output insights are presented as numerical information and statistical indicators.

[0171] Step 4:

[0172] The device uses a camera and microphone to detect the user's emotional state. This collects data on the user's facial expressions and changes in voice tone. This emotional data is sent to an emotion engine, which outputs information that evaluates the user's stress level and satisfaction level.

[0173] Step 5:

[0174] The server adjusts how the analysis results are displayed based on the emotional information sent from the emotion engine. It changes the level of detail of the information presented to the user according to their emotional state. For example, if high stress is detected, the information is simplified for easier understanding.

[0175] Step 6:

[0176] Users receive analysis results via a terminal. The terminal provides visual reports using a graphical interface. Users can use the information they obtain to improve their work and send feedback to the server.

[0177] (Application Example 2)

[0178] 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".

[0179] In modern manufacturing environments, complex data analysis and the effective utilization of its results are required. However, systems that provide uniform information without considering the user's emotional state can increase the psychological burden on workers and potentially decrease production efficiency. Furthermore, systems capable of flexibly presenting information according to the user's emotions and state are not sufficiently available, which is a barrier to efficient work execution on the factory floor.

[0180] 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.

[0181] In this invention, the server includes means for acquiring simulation data, means for preprocessing the simulation data, and means for using a machine learning model to analyze the preprocessed data. This makes it possible to present analysis results that take into account the user's emotional state and to adjust the interface based on those results.

[0182] "Simulation data" refers to data used to simulate physical phenomena and process states in a digital environment, and to virtually reproduce their behavior and results.

[0183] "Preprocessing" refers to processes such as data cleaning and format conversion performed to make simulation data easier to analyze.

[0184] A "machine learning model" is a set of algorithms used by computers to automatically learn specific tasks and identify patterns and rules.

[0185] "Outputting in natural language" means providing the analysis results as text in a language format that is easy for the user to understand.

[0186] "Emotional analysis" is the process of evaluating users' emotional state and psychological characteristics based on their facial expressions, tone of voice, and word choice.

[0187] "Display control" is a function that appropriately adjusts the content and format of the information presented visually according to the user's emotional state.

[0188] "Feedback" refers to information obtained from users, such as their reactions and evaluations, that is used to improve systems and processes.

[0189] "Recommended actions" refer to information that indicates the actions or strategies a user should take to achieve a desirable outcome in a particular situation.

[0190] The system for realizing this invention is based on the interaction of a server, a terminal, and a user. The server uses simulation data acquired from a digital twin environment to perform preprocessing and analysis using a machine learning model. The software used in this process is mainly Flask and TensorFlow, with Flask used for data collection and management, and TensorFlow used for model analysis of the data.

[0191] The analysis results are converted into text format in a language easily understood by the user, utilizing natural language generation technology. The device also plays a role in sensing the user's emotional state, collecting facial expression data and audio using the smartphone's camera and microphone. This information is analyzed by an emotion analysis engine to evaluate the user's psychological state.

[0192] Based on this emotional data, the server controls the display and automatically selects the optimal way to present information according to the user's state. For example, if the user is under high stress, simpler information will be displayed, while if they are relaxed, detailed analysis results will be shown.

[0193] As a concrete example, consider the monitoring of robotic arm operation in a factory. This system analyzes operational data in real time and reports on equipment efficiency and potential problems in natural language. Furthermore, it can provide operation guides to reduce workload based on the sentiment data of on-site workers.

[0194] An example of a prompt for a generative AI model is, "Optimize how information is displayed based on user sentiment data."

[0195] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0196] Step 1:

[0197] The server acquires simulation data from the digital twin environment. The input is parameter data of the physical environment, which is imported into the server. The output is a dataset for preprocessing. To prepare this dataset, the data format is checked and outliers are filtered.

[0198] Step 2:

[0199] The server performs preprocessing on the acquired data. The input is the acquired simulation data, and the output is data in a format suitable for analysis. Specifically, it performs noise reduction and data imputation.

[0200] Step 3:

[0201] The server inputs pre-processed data into a machine learning model and performs analysis. The input is formatted data, and the output is the raw data of the analysis results. For data processing, a feature extraction algorithm is used to identify important patterns in the data.

[0202] Step 4:

[0203] The server converts the analysis results into text output using natural language generation technology. The input is the raw data (numerical information) of the model, and the output is natural language text for the user. This operation involves using natural language processing algorithms to generate sentences that are easy for humans to understand.

[0204] Step 5:

[0205] The device captures the user's facial expressions and voice and performs emotion analysis. The input is raw data acquired from the smartphone's camera and microphone, and the output is metadata indicating the user's emotional state. In this process, the emotion analysis engine performs facial recognition and voice tone analysis.

[0206] Step 6:

[0207] The server dynamically adjusts the display form of the analysis results based on the sentiment analysis results. The input is the user's sentiment state data and previous analysis results, and the output is optimized UI content. At this stage, dynamic interface updates are performed using a UI framework.

[0208] Step 7:

[0209] The user takes the necessary actions based on the information provided. The input consists of displayed natural language result text and UI content. This step includes actions such as following guidelines and entering feedback into the device.

[0210] 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.

[0211] 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.

[0212] 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.

[0213] [Second Embodiment]

[0214] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0215] 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.

[0216] 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).

[0217] 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.

[0218] 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.

[0219] 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).

[0220] 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.

[0221] 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.

[0222] 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.

[0223] 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.

[0224] 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.

[0225] 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".

[0226] The system of this invention automates the analysis of simulation data in a digital twin environment and provides users with useful insights. This system mainly consists of a server, terminals, and users.

[0227] The server collects and preprocesses simulation data. It receives image and numerical data from the digital twin system. This data is then processed through preprocessing steps such as noise reduction and formatting to make it ready for analysis.

[0228] Next, the server uses the pre-processed data to perform analysis using an artificial intelligence model. The AI ​​model extracts features from the input data and performs anomaly detection and prediction. This analysis generates results in a format that can be output in natural language.

[0229] Subsequently, the server uses natural language processing technology to summarize the analysis results into user-friendly text, generating insights. These insights include information to support important decision-making for the user.

[0230] The terminal receives analysis results and insights in natural language from the server and displays them visually through the user interface. This allows the user to quickly grasp the content of the analysis and decide on the necessary actions.

[0231] Users improve their work and take appropriate actions based on the analysis results displayed on their terminals. The feedback obtained during this process is then incorporated back into the system, and the server uses this feedback to retrain the artificial intelligence model. This improves the accuracy of the next analysis.

[0232] A concrete example is improving traffic flow management in smart cities. The server performs traffic flow simulations based on real-time data from traffic sensors, identifying the causes of congestion and proposing countermeasures. The terminal then presents the analysis results and proposed signal schedule improvements to the user, supporting them in making decisions to optimize urban traffic management. Successfully completing this process improves overall urban traffic efficiency and contributes to reducing congestion.

[0233] The following describes the processing flow.

[0234] Step 1:

[0235] The server receives image and numerical data based on simulations from the digital twin system. This data includes various parameters and environmental conditions of the phenomenon being studied.

[0236] Step 2:

[0237] The server performs preprocessing on the received image and numerical data, such as noise reduction and data loss imputation, to prepare it for analysis. This process improves the quality of the dataset and increases the reliability of the analysis results.

[0238] Step 3:

[0239] The server inputs pre-processed data into an artificial intelligence model for feature extraction and analysis. The AI ​​model uses deep learning to recognize patterns in the data, detect anomalies, and identify important indicators.

[0240] Step 4:

[0241] The server uses natural language processing technology to convert the analysis results obtained from the artificial intelligence model into text, generating insights in a format easily understandable to the user. These insights include predicted phenomena and recommended countermeasures.

[0242] Step 5:

[0243] The terminal receives insights transmitted from the server and displays them visually through the user interface. Users can use this information to quickly understand the situation and make decisions.

[0244] Step 6:

[0245] Based on the analysis results and insights obtained from their devices, users implement business-related actions and improvement measures. This allows users to increase operational efficiency and solve problems.

[0246] Step 7:

[0247] Users input feedback on the countermeasures they have taken and the results of those countermeasures into their terminals. The server collects this feedback and uses it to retrain the artificial intelligence model. This improves the accuracy of the analysis in the next run.

[0248] (Example 1)

[0249] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0250] In today's complex systems, there is a need to efficiently analyze large amounts of simulation data and provide information in a way that users can intuitively understand. Furthermore, there is a lack of systems that can improve the accuracy of data analysis by utilizing the feedback obtained, and this solution addresses that challenge.

[0251] 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.

[0252] In this invention, the server includes a mechanism for acquiring data, a mechanism for preprocessing the data, and a mechanism for using a machine learning model to analyze the preprocessed data. This makes it possible to efficiently process large amounts of data and to improve the accuracy of the analysis by reflecting feedback from users.

[0253] A "data acquisition mechanism" is a means of receiving digital information from an external source and converting it into a format usable within the system.

[0254] A "preprocessing mechanism" is a means of removing noise from acquired digital information and formatting it to make it easier to analyze.

[0255] A "mechanism that uses machine learning models" is a means of analyzing large amounts of digital information and utilizing algorithms to detect useful patterns and anomalies.

[0256] A "mechanism for outputting in natural language" is a means of generating and presenting analysis results in a form that is easy for users to understand.

[0257] A "visual display mechanism" is a means of displaying analyzed information in a way that users can intuitively understand.

[0258] A "mechanism for generating useful insights" is a means of constructing valuable information and insights to support users' decision-making based on analysis results.

[0259] A "feedback acquisition and retraining mechanism" is a means of collecting evaluations and reactions from users and updating the machine learning model based on them to improve its accuracy.

[0260] A "mechanism for suggesting recommended actions" is a means of showing users the optimal course of action derived from analyzed data and encouraging them to take action.

[0261] This invention is a system that automatically analyzes simulation data in a digital twin environment and provides users with useful insights. The main components of this system are a server, terminals, and users.

[0262] The server has a mechanism to automatically receive large amounts of data acquired from the digital twin system. For example, it collects real-time digital information via an API. This data includes image and numerical data, and is preprocessed in preparation for later analysis. At this stage, denoising and formatting are performed using the Python Pandas library.

[0263] Next, the server inputs the pre-processed data into a machine learning model, and the system performs anomaly detection and prediction. This machine learning model uses libraries such as TensorFlow and PyTorch to extract features from the data and proceed with the analysis. The results obtained from the analysis are converted into natural language and provided in a format that is easy for the user to understand. For natural language processing, a generative AI model is employed to generate specific information, such as "the traffic congestion from 10 o'clock is due to construction, and a 15-minute delay is predicted."

[0264] The terminal receives analysis results sent from the server and displays them visually through a user interface. Technologies such as HTML and JavaScript are utilized, and a graphical user interface is designed to allow users to intuitively analyze the data.

[0265] Users improve and modify the system based on the analysis results displayed via their devices, providing useful feedback. This feedback is sent to the server and used to retrain the generated AI model. Through this process, the accuracy of the analysis improves, which is useful for subsequent data analyses.

[0266] A concrete example is traffic flow management in smart cities. The server analyzes real-time traffic sensor data and suggests causes of congestion and countermeasures. These analysis results are presented to users via terminals, supporting effective decision-making in urban traffic management.

[0267] An example of a prompt message that can be entered is, "Based on real-time data from traffic sensors, identify the causes of urban traffic congestion and propose effective improvement measures."

[0268] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0269] Step 1:

[0270] The server receives digital information from the digital twin system. The inputs are image and numerical data from the digital twin system, collected in real time via an API. The server stores this initial data internally, preparing it for subsequent processing.

[0271] Step 2:

[0272] The server preprocesses the received digital information. The main input is the raw data containing noise collected in Step 1. The server applies a denoising filter using the Python Pandas library to remove unwanted data. It also standardizes the data format and converts it into a structure that is easy to analyze. The preprocessing results in clean data, which is used in the next analysis step.

[0273] Step 3:

[0274] The server inputs pre-processed data into a machine learning model and performs data analysis. The input is clean, formatted data, which is then fed into a generative AI model using TensorFlow or PyTorch. The model extracts features from the data, performs calculations such as anomaly detection and prediction, and outputs the analysis results. For example, it can predict fluctuations in traffic flow during a specific time period.

[0275] Step 4:

[0276] The server generates a summary of the analyzed results using natural language processing technology. The input is the analysis results obtained in step 3, and based on this, a generation AI model is used to convert it into natural language text that is easy for the user to understand. The output provides information that supports the user's decision-making.

[0277] Step 5:

[0278] The terminal receives the analysis result in natural language sent from the server and visually displays it. The main input is the summary sentence of the designed natural language. The terminal uses HTML and JavaScript to place this information on the graphical user interface so that the user can easily access it.

[0279] Step 6:

[0280] The user utilizes the analysis result presented via the terminal to improve business operations and make decisions. The input as feedback is the content of the user's selection and judgment, and this is sent back to the server. The server accumulates this feedback information and uses it for the relearning of the generated AI model. As a result, an improvement in the accuracy of the next data analysis is expected.

[0281] (Application Example 1)

[0282] 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".

[0283] In the current digital twin environment, there is a lack of means to effectively utilize real-time data to immediately present analysis results regarding specific physical phenomena and positions, enabling users to make quick decisions. Also, it is difficult to effectively utilize the feedback loop based on the analysis results for improved learning.

[0284] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0285] In this invention, the server includes means for receiving information for simulation, means having a function for preprocessing the information for simulation, and means for using a learning algorithm to analyze the preprocessed information. Thereby, it becomes possible to quickly provide the user with analysis results based on real-time acquired data, and automatically improve the learning algorithm through feedback.

[0286] "The information for simulation" refers to the data necessary to virtually reproduce physical phenomena and events in a digital twin environment.

[0287] "The function of preprocessing" refers to processing means such as noise removal and format conversion that are performed to convert raw data into an analyzable form.

[0288] "The learning algorithm" is a computational method for extracting features from input data and performing pattern recognition, prediction, and anomaly detection.

[0289] "The function of outputting in natural language form" is a technology for expressing analysis results and insights as text that can be easily understood by people.

[0290] "The device for providing to users" refers to an interface device that visually displays analysis results and enables users to easily interpret data.

[0291] "Specific location information" refers to a specific location within the physical space and is an element that enables data analysis based on that location.

[0292] "The means for processing real-time information" refers to a technology for immediately analyzing data obtained continuously along a time series and generating results.

[0293] According to this invention, it is possible to construct a traffic management system in a smart city environment. The server receives information for simulation from traffic sensors and has a function of preprocessing. Specifically, it performs noise removal and data format shaping to prepare it in a state suitable for real-time information analysis. For this, Python and the Requests library are used.

[0294] Next, the server uses a learning algorithm based on the pre-processed information to perform anomaly detection and congestion prediction. The learning algorithm used here is implemented by a generative AI model. The detected anomaly data and prediction results are output in natural language format.

[0295] The server then sends the generated natural language analysis results to the terminal. The terminal functions as a device to provide the results to the user, displaying the data visually. This allows the user to quickly grasp the analysis results and assist in decision-making, such as selecting an appropriate route to avoid congestion.

[0296] As a concrete example, a dedicated application is installed on the smartphones that users use daily, and traffic information is updated in real time. Users can choose an alternative route based on the traffic congestion information and shorten their commute time.

[0297] An example of a prompt message could be: "Recent traffic data analysis has detected abnormal traffic volume at a specific location. Do you want to check an alternative route?" Such prompt messages help users make informed decisions.

[0298] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0299] Step 1:

[0300] The server receives real-time simulation information from traffic sensors. The input is raw data from the sensors, and the output is this data itself. Specifically, the data is retrieved via an API and stored in the database in its unformatted state.

[0301] Step 2:

[0302] The server performs preprocessing on the received raw data. Specifically, it performs noise removal and data format shaping. The input here is the raw data that is the output of Step 1, and the output is the analyzable data with noise removed and shaped.

[0303] Step 3:

[0304] The server analyzes the preprocessed data using a generated AI model. Specifically, it extracts features from the data and performs anomaly detection and congestion prediction. The input is the data shaped in Step 2, and the output is the analysis result, which is anomaly detection information and prediction results.

[0305] Step 4:

[0306] The server converts the generated analysis result into a natural language form. Using natural language processing technology, it makes the language easy for humans to understand. The input is the analysis result that is the output of Step 3, and the output is the sentence form that can be presented to the user.

[0307] Step 5:

[0308] The server sends the analysis result converted into a natural language form to the terminal. Specifically, it sends information to the user's terminal through data communication. The input is the text data that is the output of Step 4, and the output is the analysis result visually displayed on the terminal.

[0309] Step 6:

[0310] The user receives the analysis result visually presented on the terminal and makes a decision. Specifically, the user reads the prompt text and selects the optimal route to avoid congested areas. The input is the visual display information that is the output of Step 5, and the output is the decision-making action based on the user's selection.

[0311] 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.

[0312] This invention provides a system that combines an emotion engine to improve the user experience in the analysis of digital twin simulation data. This system consists of a server, a terminal, and a user, and each element works organically to enable more effective utilization of the analysis results.

[0313] The server preprocesses image and numerical data acquired from digital twin simulations and analyzes them using an artificial intelligence model. During the analysis, it extracts data features and generates insights derived from them. These insights are output in natural language and provided to the user.

[0314] In addition, this system incorporates an emotion engine. The terminal senses the user's emotions, facial expressions, voice tone, etc., and sends this data to the emotion engine. The emotion engine analyzes this data to identify the user's current emotions and stress level.

[0315] Based on the information obtained from the emotion engine, the server adjusts how the analysis results are presented. For example, if the user is experiencing high stress, it selects an easy-to-use, low-load interface; conversely, if the user is relaxed, it presents detailed analysis results.

[0316] A concrete example is improving production efficiency in a manufacturing plant. The server acquires machine operation data and gains insights into operational efficiency and maintenance needs. Terminals acquire real-time emotional information from on-site workers via an emotion engine and feed it back to the server. As a result, the system makes suggestions and adjusts the interface to reduce the burden on workers, thereby improving productivity. This entire process increases operational efficiency and reduces worker satisfaction and burden.

[0317] The following describes the processing flow.

[0318] Step 1:

[0319] The server receives simulation image data and numerical data from the digital twin system. This allows it to collect basic information necessary for verifying and predicting phenomena in the virtual environment.

[0320] Step 2:

[0321] The server preprocesses the received data. Specifically, it performs noise reduction, imputation of missing values, and adjustment of the data format to prepare it for optimal analysis.

[0322] Step 3:

[0323] The server inputs pre-processed data into an artificial intelligence model, which extracts and analyzes the data's features. This allows for the detection of anomalies, the uncovering of unknown patterns, and the generation of insights that form the basis of inference.

[0324] Step 4:

[0325] The server uses natural language processing technology to convert the analysis results into text in a format that is easy for the user to understand, and generates it as knowledge.

[0326] Step 5:

[0327] The terminal receives insights transmitted from the server and displays them visually through the user interface. This allows the user to accurately grasp the information and make quick decisions.

[0328] Step 6:

[0329] The device collects emotional information by sensing the user's facial expressions and voice tone, and sends it to the emotion engine.

[0330] Step 7:

[0331] The emotion engine analyzes data sent from the device to identify the user's current emotional state. This information indicates the user's stress level, level of concentration, and other factors.

[0332] Step 8:

[0333] The server adjusts how the analysis results are presented based on information from the emotion engine. Specifically, it optimizes the complexity and amount of information in the display interface according to the user's emotional state.

[0334] Step 9:

[0335] Users can review analysis results and determine appropriate actions for their work through a customized interface presented on their device. This enables efficient decision-making tailored to the specific situation.

[0336] Step 10:

[0337] Users input feedback on their work actions and results into a terminal. The server receives this feedback and uses it to improve the artificial intelligence model and enhance the accuracy of the analysis.

[0338] (Example 2)

[0339] 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".

[0340] There is a need to provide the results of complex simulation data analysis in a format that is easy for users to understand. However, conventional technologies lack the ability to provide information that takes into account the user's emotional state, making the improvement of the user experience a challenge. Furthermore, it is also important to quickly reflect changing user feedback and improve the accuracy of the analysis information provided.

[0341] 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.

[0342] In this invention, the server includes means for acquiring information, means for preprocessing the information, and means for using an artificial intelligence model to analyze the preprocessed information. This enables the presentation of flexible analysis results that correspond to the user's emotional state and highly accurate data analysis that reflects user feedback.

[0343] "Means of acquiring information" refers to the function that a system uses to collect necessary data and information from external sources.

[0344] "Preprocessing means" refers to a function that performs data processing to prepare acquired information into a format suitable for analysis.

[0345] "Methods using artificial intelligence models" refer to the function of extracting patterns and insights from data by utilizing machine learning and statistical models in data analysis.

[0346] "Means of outputting in natural language" refers to a function that converts the analysis results into a language format that is easy for humans to understand and provides them.

[0347] "Means for detecting the user's emotional state" refers to a function that analyzes the user's physical reactions, such as facial expressions and voice, to understand their emotional state.

[0348] "Means for adjusting the presentation method of analysis results based on emotional state" refers to a function that appropriately changes the content and format of the displayed analysis results according to the detected emotions of the user.

[0349] "Means for visually displaying analysis results to the user" refers to a display function via a graphical user interface that provides the analyzed information to the user visually.

[0350] This invention is an advanced data analysis system that utilizes digital twin technology and aims to improve the user experience. The server first acquires image and numerical data generated in real time from the digital twin simulation. Advanced data cleaning software is used to perform preprocessing on this data, such as noise reduction and format conversion.

[0351] Next, the server utilizes a generative AI model to analyze this preprocessed data. This AI model is built on machine learning algorithms to extract features from the data and provide the necessary insights. The results are then translated into human-readable language using natural language processing software and presented to the user.

[0352] The device uses sensors such as cameras and microphones to detect the user's emotional state. The emotional data acquired by these sensors is sent to an emotion engine, which then provides the analysis results to a server. The server adjusts how the analysis results are displayed based on the user's emotions, selecting and displaying either simplified information or detailed analysis results as needed.

[0353] As a concrete example, consider optimizing machine operation in a manufacturing facility. In this case, the server collects operating data from the machines within the facility and analyzes their efficiency and maintenance needs. Simultaneously, terminals collect emotional information from on-site workers, feed it back to the server, and provide an interface that simplifies operations if the workers are feeling stressed.

[0354] An example of a prompt is the specific instruction, "Please describe data analysis and emotional state monitoring methods to improve factory productivity."

[0355] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0356] Step 1:

[0357] The server acquires image and numerical data from the digital twin simulation. This input data includes information about the machine's operating status and environment. The server stores this data in a database.

[0358] Step 2:

[0359] The server preprocesses the acquired data. This preprocessing includes denoising the data and imputing missing values. Specifically, it uses filtering algorithms to detect anomalous data and converts it into the correct format. This prepares the data for analysis.

[0360] Step 3:

[0361] The server feeds pre-processed data into a generating AI model for analysis. The model extracts features from the data and generates insights for improving machine efficiency and predicting failures. The output insights are presented as numerical information and statistical indicators.

[0362] Step 4:

[0363] The device uses a camera and microphone to detect the user's emotional state. This collects data on the user's facial expressions and changes in voice tone. This emotional data is sent to an emotion engine, which outputs information that evaluates the user's stress level and satisfaction level.

[0364] Step 5:

[0365] The server adjusts how the analysis results are displayed based on the emotional information sent from the emotion engine. It changes the level of detail of the information presented to the user according to their emotional state. For example, if high stress is detected, the information is simplified for easier understanding.

[0366] Step 6:

[0367] Users receive analysis results via a terminal. The terminal provides visual reports using a graphical interface. Users can use the information they obtain to improve their work and send feedback to the server.

[0368] (Application Example 2)

[0369] 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."

[0370] In modern manufacturing environments, complex data analysis and the effective utilization of its results are required. However, systems that provide uniform information without considering the user's emotional state can increase the psychological burden on workers and potentially decrease production efficiency. Furthermore, systems capable of flexibly presenting information according to the user's emotions and state are not sufficiently available, which is a barrier to efficient work execution on the factory floor.

[0371] 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.

[0372] In this invention, the server includes means for acquiring simulation data, means for preprocessing the simulation data, and means for using a machine learning model to analyze the preprocessed data. This makes it possible to present analysis results that take into account the user's emotional state and to adjust the interface based on those results.

[0373] "Simulation data" refers to data used to simulate physical phenomena and process states in a digital environment, and to virtually reproduce their behavior and results.

[0374] "Preprocessing" refers to processes such as data cleaning and format conversion performed to make simulation data easier to analyze.

[0375] A "machine learning model" is a set of algorithms used by computers to automatically learn specific tasks and identify patterns and rules.

[0376] "Outputting in natural language" means providing the analysis results as text in a language format that is easy for the user to understand.

[0377] "Emotional analysis" is the process of evaluating users' emotional state and psychological characteristics based on their facial expressions, tone of voice, and word choice.

[0378] "Display control" is a function that appropriately adjusts the content and format of the information presented visually according to the user's emotional state.

[0379] "Feedback" refers to information obtained from users, such as their reactions and evaluations, that is used to improve systems and processes.

[0380] "Recommended actions" refer to information that indicates the actions or strategies a user should take to achieve a desirable outcome in a particular situation.

[0381] The system for realizing this invention is based on the interaction of a server, a terminal, and a user. The server uses simulation data acquired from a digital twin environment to perform preprocessing and analysis using a machine learning model. The software used in this process is mainly Flask and TensorFlow, with Flask used for data collection and management, and TensorFlow used for model analysis of the data.

[0382] The analysis results are converted into text format in a language easily understood by the user, utilizing natural language generation technology. The device also plays a role in sensing the user's emotional state, collecting facial expression data and audio using the smartphone's camera and microphone. This information is analyzed by an emotion analysis engine to evaluate the user's psychological state.

[0383] Based on this emotional data, the server controls the display and automatically selects the optimal way to present information according to the user's state. For example, if the user is under high stress, simpler information will be displayed, while if they are relaxed, detailed analysis results will be shown.

[0384] As a concrete example, consider the monitoring of robotic arm operation in a factory. This system analyzes operational data in real time and reports on equipment efficiency and potential problems in natural language. Furthermore, it can provide operation guides to reduce workload based on the sentiment data of on-site workers.

[0385] An example of a prompt for a generative AI model is, "Optimize how information is displayed based on user sentiment data."

[0386] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0387] Step 1:

[0388] The server acquires simulation data from the digital twin environment. The input is parameter data of the physical environment, which is imported into the server. The output is a dataset for preprocessing. To prepare this dataset, the data format is checked and outliers are filtered.

[0389] Step 2:

[0390] The server performs preprocessing on the acquired data. The input is the acquired simulation data, and the output is data in a format suitable for analysis. Specifically, it performs noise reduction and data imputation.

[0391] Step 3:

[0392] The server inputs pre-processed data into a machine learning model and performs analysis. The input is formatted data, and the output is the raw data of the analysis results. For data processing, a feature extraction algorithm is used to identify important patterns in the data.

[0393] Step 4:

[0394] The server converts the analysis results into text output using natural language generation technology. The input is the raw data (numerical information) of the model, and the output is natural language text for the user. This operation involves using natural language processing algorithms to generate sentences that are easy for humans to understand.

[0395] Step 5:

[0396] The device captures the user's facial expressions and voice and performs emotion analysis. The input is raw data acquired from the smartphone's camera and microphone, and the output is metadata indicating the user's emotional state. In this process, the emotion analysis engine performs facial recognition and voice tone analysis.

[0397] Step 6:

[0398] The server dynamically adjusts the display form of the analysis results based on the sentiment analysis results. The input is the user's sentiment state data and previous analysis results, and the output is optimized UI content. At this stage, dynamic interface updates are performed using a UI framework.

[0399] Step 7:

[0400] The user takes the necessary actions based on the information provided. The input consists of displayed natural language result text and UI content. This step includes actions such as following guidelines and entering feedback into the device.

[0401] 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.

[0402] 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.

[0403] 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.

[0404] [Third Embodiment]

[0405] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0406] 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.

[0407] 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).

[0408] 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.

[0409] 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.

[0410] 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).

[0411] 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.

[0412] 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.

[0413] 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.

[0414] 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.

[0415] 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.

[0416] 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".

[0417] The system of this invention automates the analysis of simulation data in a digital twin environment and provides users with useful insights. This system mainly consists of a server, terminals, and users.

[0418] The server collects and preprocesses simulation data. It receives image and numerical data from the digital twin system. This data is then processed through preprocessing steps such as noise reduction and formatting to make it ready for analysis.

[0419] Next, the server uses the pre-processed data to perform analysis using an artificial intelligence model. The AI ​​model extracts features from the input data and performs anomaly detection and prediction. This analysis generates results in a format that can be output in natural language.

[0420] Subsequently, the server uses natural language processing technology to summarize the analysis results into user-friendly text, generating insights. These insights include information to support important decision-making for the user.

[0421] The terminal receives analysis results and insights in natural language from the server and displays them visually through the user interface. This allows the user to quickly grasp the content of the analysis and decide on the necessary actions.

[0422] Users improve their work and take appropriate actions based on the analysis results displayed on their terminals. The feedback obtained during this process is then incorporated back into the system, and the server uses this feedback to retrain the artificial intelligence model. This improves the accuracy of the next analysis.

[0423] A concrete example is improving traffic flow management in smart cities. The server performs traffic flow simulations based on real-time data from traffic sensors, identifying the causes of congestion and proposing countermeasures. The terminal then presents the analysis results and proposed signal schedule improvements to the user, supporting them in making decisions to optimize urban traffic management. Successfully completing this process improves overall urban traffic efficiency and contributes to reducing congestion.

[0424] The following describes the processing flow.

[0425] Step 1:

[0426] The server receives image and numerical data based on simulations from the digital twin system. This data includes various parameters and environmental conditions of the phenomenon being studied.

[0427] Step 2:

[0428] The server performs preprocessing on the received image and numerical data, such as noise reduction and data loss imputation, to prepare it for analysis. This process improves the quality of the dataset and increases the reliability of the analysis results.

[0429] Step 3:

[0430] The server inputs pre-processed data into an artificial intelligence model for feature extraction and analysis. The AI ​​model uses deep learning to recognize patterns in the data, detect anomalies, and identify important indicators.

[0431] Step 4:

[0432] The server uses natural language processing technology to convert the analysis results obtained from the artificial intelligence model into text, generating insights in a format easily understandable to the user. These insights include predicted phenomena and recommended countermeasures.

[0433] Step 5:

[0434] The terminal receives insights transmitted from the server and displays them visually through the user interface. Users can use this information to quickly understand the situation and make decisions.

[0435] Step 6:

[0436] Based on the analysis results and insights obtained from their devices, users implement business-related actions and improvement measures. This allows users to increase operational efficiency and solve problems.

[0437] Step 7:

[0438] Users input feedback on the countermeasures they have taken and the results of those countermeasures into their terminals. The server collects this feedback and uses it to retrain the artificial intelligence model. This improves the accuracy of the analysis in the next run.

[0439] (Example 1)

[0440] 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."

[0441] In today's complex systems, there is a need to efficiently analyze large amounts of simulation data and provide information in a way that users can intuitively understand. Furthermore, there is a lack of systems that can improve the accuracy of data analysis by utilizing the feedback obtained, and this solution addresses that challenge.

[0442] 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.

[0443] In this invention, the server includes a mechanism for acquiring data, a mechanism for preprocessing the data, and a mechanism for using a machine learning model to analyze the preprocessed data. This makes it possible to efficiently process large amounts of data and to improve the accuracy of the analysis by reflecting feedback from users.

[0444] A "data acquisition mechanism" is a means of receiving digital information from an external source and converting it into a format usable within the system.

[0445] A "preprocessing mechanism" is a means of removing noise from acquired digital information and formatting it to make it easier to analyze.

[0446] A "mechanism that uses machine learning models" is a means of analyzing large amounts of digital information and utilizing algorithms to detect useful patterns and anomalies.

[0447] A "mechanism for outputting in natural language" is a means of generating and presenting analysis results in a form that is easy for users to understand.

[0448] A "visual display mechanism" is a means of displaying analyzed information in a way that users can intuitively understand.

[0449] A "mechanism for generating useful insights" is a means of constructing valuable information and insights to support users' decision-making based on analysis results.

[0450] A "feedback acquisition and retraining mechanism" is a means of collecting evaluations and reactions from users and updating the machine learning model based on them to improve its accuracy.

[0451] A "mechanism for suggesting recommended actions" is a means of showing users the optimal course of action derived from analyzed data and encouraging them to take action.

[0452] This invention is a system that automatically analyzes simulation data in a digital twin environment and provides users with useful insights. The main components of this system are a server, terminals, and users.

[0453] The server has a mechanism to automatically receive large amounts of data acquired from the digital twin system. For example, it collects real-time digital information via an API. This data includes image and numerical data, and is preprocessed in preparation for later analysis. At this stage, denoising and formatting are performed using the Python Pandas library.

[0454] Next, the server inputs the pre-processed data into a machine learning model, and the system performs anomaly detection and prediction. This machine learning model uses libraries such as TensorFlow and PyTorch to extract features from the data and proceed with the analysis. The results obtained from the analysis are converted into natural language and provided in a format that is easy for the user to understand. For natural language processing, a generative AI model is employed to generate specific information, such as "the traffic congestion from 10 o'clock is due to construction, and a 15-minute delay is predicted."

[0455] The terminal receives analysis results sent from the server and displays them visually through a user interface. Technologies such as HTML and JavaScript are utilized, and a graphical user interface is designed to allow users to intuitively analyze the data.

[0456] Users improve and modify the system based on the analysis results displayed via their devices, providing useful feedback. This feedback is sent to the server and used to retrain the generated AI model. Through this process, the accuracy of the analysis improves, which is useful for subsequent data analyses.

[0457] A concrete example is traffic flow management in smart cities. The server analyzes real-time traffic sensor data and suggests causes of congestion and countermeasures. These analysis results are presented to users via terminals, supporting effective decision-making in urban traffic management.

[0458] An example of a prompt message that can be entered is, "Based on real-time data from traffic sensors, identify the causes of urban traffic congestion and propose effective improvement measures."

[0459] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0460] Step 1:

[0461] The server receives digital information from the digital twin system. The inputs are image and numerical data from the digital twin system, collected in real time via an API. The server stores this initial data internally, preparing it for subsequent processing.

[0462] Step 2:

[0463] The server preprocesses the received digital information. The main input is the raw data containing noise collected in Step 1. The server applies a denoising filter using the Python Pandas library to remove unwanted data. It also standardizes the data format and converts it into a structure that is easy to analyze. The preprocessing results in clean data, which is used in the next analysis step.

[0464] Step 3:

[0465] The server inputs pre-processed data into a machine learning model and performs data analysis. The input is clean, formatted data, which is then fed into a generative AI model using TensorFlow or PyTorch. The model extracts features from the data, performs calculations such as anomaly detection and prediction, and outputs the analysis results. For example, it can predict fluctuations in traffic flow during a specific time period.

[0466] Step 4:

[0467] The server generates a summary of the analyzed results using natural language processing technology. The input is the analysis results obtained in step 3, and based on this, a generation AI model is used to convert it into natural language text that is easy for the user to understand. The output provides information that supports the user's decision-making.

[0468] Step 5:

[0469] The terminal receives natural language analysis results sent from the server and displays them visually. The primary input is a designed natural language summary. The terminal uses HTML and JavaScript to place this information on a graphical user interface, making it easily accessible to the user.

[0470] Step 6:

[0471] Users utilize the analysis results presented via their terminals to improve their work and make decisions. Feedback input consists of the user's choices and judgments, which are sent back to the server. The server stores this feedback information and uses it to retrain the generated AI model. This is expected to improve the accuracy of subsequent data analyses.

[0472] (Application Example 1)

[0473] 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."

[0474] In current digital twin environments, there is a lack of means to effectively utilize real-time data to immediately present analysis results regarding specific physical phenomena and locations, enabling users to make rapid decisions. Furthermore, it is difficult to improve learning by effectively utilizing feedback loops based on analysis results.

[0475] 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.

[0476] In this invention, the server includes means for receiving information for simulation, means for preprocessing the simulation information, and means for using a learning algorithm to analyze the preprocessed information. This enables the rapid provision of analysis results based on real-time acquired data to the user, and also allows for automatic improvement of the learning algorithm through feedback.

[0477] "Information for simulation" refers to the data necessary to virtually reproduce physical phenomena and events in a digital twin environment.

[0478] "Preprocessing functions" refer to processing methods such as noise reduction and format conversion performed to convert raw data into an analyzable format.

[0479] A "learning algorithm" is a computational method used to extract features from input data and perform pattern recognition, prediction, and anomaly detection.

[0480] The "function to output in natural language format" is a technology that expresses analysis results and insights in a form that humans can easily understand.

[0481] "Devices provided to users" refers to interface devices that visually display analysis results and enable users to easily interpret the data.

[0482] "Specific location information" refers to a concrete location within physical space, and is an element that enables data analysis based on that location.

[0483] "Means for processing real-time information" refers to technologies that instantly analyze data obtained continuously over time and generate results.

[0484] This invention makes it possible to construct a traffic management system in a smart city environment. The server has the function of receiving and preprocessing information for simulation from traffic sensors. Specifically, it performs noise reduction and data formatting to prepare the data for analysis in real time. Python and the Requests library are used for this purpose.

[0485] Next, the server uses a learning algorithm based on the pre-processed information to perform anomaly detection and congestion prediction. The learning algorithm used here is implemented by a generative AI model. The detected anomaly data and prediction results are output in natural language format.

[0486] The server then sends the generated natural language analysis results to the terminal. The terminal functions as a device to provide the results to the user, displaying the data visually. This allows the user to quickly grasp the analysis results and assist in decision-making, such as selecting an appropriate route to avoid congestion.

[0487] As a concrete example, a dedicated application is installed on the smartphones that users use daily, and traffic information is updated in real time. Users can choose an alternative route based on the traffic congestion information and shorten their commute time.

[0488] An example of a prompt message could be: "Recent traffic data analysis has detected abnormal traffic volume at a specific location. Do you want to check an alternative route?" Such prompt messages help users make informed decisions.

[0489] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0490] Step 1:

[0491] The server receives real-time simulation information from traffic sensors. The input is raw data from the sensors, and the output is this data itself. Specifically, the data is retrieved via an API and stored in the database in its unformatted state.

[0492] Step 2:

[0493] The server performs preprocessing on the received raw data. Specifically, it performs noise reduction and data formatting. The input here is the raw data, which is the output of step 1, and the output is analyzable data that has been noise-removed and formatted.

[0494] Step 3:

[0495] The server uses pre-processed data to perform analysis with a generated AI model. Specifically, it extracts features from the data and performs anomaly detection and traffic congestion prediction. The input is the data formatted in step 2, and the output is the analysis results, such as anomaly detection information and prediction results.

[0496] Step 4:

[0497] The server converts the generated analysis results into natural language format. Using natural language processing techniques, it transforms the results into a language that is easily understandable to humans. The input is the analysis result from step 3, and the output is a text format that can be presented to the user.

[0498] Step 5:

[0499] The server sends the parsing results, converted into natural language format, to the terminal. Specifically, it sends information to the user's terminal via data communication. The input is the text data that was output in step 4, and the output is the parsing result displayed visually on the terminal.

[0500] Step 6:

[0501] The user receives the analysis results visually presented on the terminal and makes a decision. Specifically, they read the prompt text and select the optimal route to avoid congested areas. The input is the visually displayed information that is the output in step 5, and the output is the decision-making action made by the user.

[0502] 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.

[0503] This invention provides a system that combines an emotion engine to improve the user experience in the analysis of digital twin simulation data. This system consists of a server, a terminal, and a user, and each element works organically to enable more effective utilization of the analysis results.

[0504] The server preprocesses image and numerical data acquired from digital twin simulations and analyzes them using an artificial intelligence model. During the analysis, it extracts data features and generates insights derived from them. These insights are output in natural language and provided to the user.

[0505] In addition, this system incorporates an emotion engine. The terminal senses the user's emotions, facial expressions, voice tone, etc., and sends this data to the emotion engine. The emotion engine analyzes this data to identify the user's current emotions and stress level.

[0506] Based on the information obtained from the emotion engine, the server adjusts how the analysis results are presented. For example, if the user is experiencing high stress, it selects an easy-to-use, low-load interface; conversely, if the user is relaxed, it presents detailed analysis results.

[0507] A concrete example is improving production efficiency in a manufacturing plant. The server acquires machine operation data and gains insights into operational efficiency and maintenance needs. Terminals acquire real-time emotional information from on-site workers via an emotion engine and feed it back to the server. As a result, the system makes suggestions and adjusts the interface to reduce the burden on workers, thereby improving productivity. This entire process increases operational efficiency and reduces worker satisfaction and burden.

[0508] The following describes the processing flow.

[0509] Step 1:

[0510] The server receives simulation image data and numerical data from the digital twin system. This allows it to collect basic information necessary for verifying and predicting phenomena in the virtual environment.

[0511] Step 2:

[0512] The server preprocesses the received data. Specifically, it performs noise reduction, imputation of missing values, and adjustment of the data format to prepare it for optimal analysis.

[0513] Step 3:

[0514] The server inputs pre-processed data into an artificial intelligence model, which extracts and analyzes the data's features. This allows for the detection of anomalies, the uncovering of unknown patterns, and the generation of insights that form the basis of inference.

[0515] Step 4:

[0516] The server uses natural language processing technology to convert the analysis results into text in a format that is easy for the user to understand, and generates it as knowledge.

[0517] Step 5:

[0518] The terminal receives insights transmitted from the server and displays them visually through the user interface. This allows the user to accurately grasp the information and make quick decisions.

[0519] Step 6:

[0520] The device collects emotional information by sensing the user's facial expressions and voice tone, and sends it to the emotion engine.

[0521] Step 7:

[0522] The emotion engine analyzes data sent from the device to identify the user's current emotional state. This information indicates the user's stress level, level of concentration, and other factors.

[0523] Step 8:

[0524] The server adjusts how the analysis results are presented based on information from the emotion engine. Specifically, it optimizes the complexity and amount of information in the display interface according to the user's emotional state.

[0525] Step 9:

[0526] Users can review analysis results and determine appropriate actions for their work through a customized interface presented on their device. This enables efficient decision-making tailored to the specific situation.

[0527] Step 10:

[0528] Users input feedback on their work actions and results into a terminal. The server receives this feedback and uses it to improve the artificial intelligence model and enhance the accuracy of the analysis.

[0529] (Example 2)

[0530] 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."

[0531] There is a need to provide the results of complex simulation data analysis in a format that is easy for users to understand. However, conventional technologies lack the ability to provide information that takes into account the user's emotional state, making the improvement of the user experience a challenge. Furthermore, it is also important to quickly reflect changing user feedback and improve the accuracy of the analysis information provided.

[0532] 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.

[0533] In this invention, the server includes means for acquiring information, means for preprocessing the information, and means for using an artificial intelligence model to analyze the preprocessed information. This enables the presentation of flexible analysis results that correspond to the user's emotional state and highly accurate data analysis that reflects user feedback.

[0534] "Means of acquiring information" refers to the function that a system uses to collect necessary data and information from external sources.

[0535] "Preprocessing means" refers to a function that performs data processing to prepare acquired information into a format suitable for analysis.

[0536] "Methods using artificial intelligence models" refer to the function of extracting patterns and insights from data by utilizing machine learning and statistical models in data analysis.

[0537] "Means of outputting in natural language" refers to a function that converts the analysis results into a language format that is easy for humans to understand and provides them.

[0538] "Means for detecting the user's emotional state" refers to a function that analyzes the user's physical reactions, such as facial expressions and voice, to understand their emotional state.

[0539] "Means for adjusting the presentation method of analysis results based on emotional state" refers to a function that appropriately changes the content and format of the displayed analysis results according to the detected emotions of the user.

[0540] "Means for visually displaying analysis results to the user" refers to a display function via a graphical user interface that provides the analyzed information to the user visually.

[0541] This invention is an advanced data analysis system that utilizes digital twin technology and aims to improve the user experience. The server first acquires image and numerical data generated in real time from the digital twin simulation. Advanced data cleaning software is used to perform preprocessing on this data, such as noise reduction and format conversion.

[0542] Next, the server utilizes a generative AI model to analyze this preprocessed data. This AI model is built on machine learning algorithms to extract features from the data and provide the necessary insights. The results are then translated into human-readable language using natural language processing software and presented to the user.

[0543] The device uses sensors such as cameras and microphones to detect the user's emotional state. The emotional data acquired by these sensors is sent to an emotion engine, which then provides the analysis results to a server. The server adjusts how the analysis results are displayed based on the user's emotions, selecting and displaying either simplified information or detailed analysis results as needed.

[0544] As a concrete example, consider optimizing machine operation in a manufacturing facility. In this case, the server collects operating data from the machines within the facility and analyzes their efficiency and maintenance needs. Simultaneously, terminals collect emotional information from on-site workers, feed it back to the server, and provide an interface that simplifies operations if the workers are feeling stressed.

[0545] An example of a prompt is the specific instruction, "Please describe data analysis and emotional state monitoring methods to improve factory productivity."

[0546] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0547] Step 1:

[0548] The server acquires image and numerical data from the digital twin simulation. This input data includes information about the machine's operating status and environment. The server stores this data in a database.

[0549] Step 2:

[0550] The server preprocesses the acquired data. This preprocessing includes denoising the data and imputing missing values. Specifically, it uses filtering algorithms to detect anomalous data and converts it into the correct format. This prepares the data for analysis.

[0551] Step 3:

[0552] The server feeds pre-processed data into a generating AI model for analysis. The model extracts features from the data and generates insights for improving machine efficiency and predicting failures. The output insights are presented as numerical information and statistical indicators.

[0553] Step 4:

[0554] The device uses a camera and microphone to detect the user's emotional state. This collects data on the user's facial expressions and changes in voice tone. This emotional data is sent to an emotion engine, which outputs information that evaluates the user's stress level and satisfaction level.

[0555] Step 5:

[0556] The server adjusts how the analysis results are displayed based on the emotional information sent from the emotion engine. It changes the level of detail of the information presented to the user according to their emotional state. For example, if high stress is detected, the information is simplified for easier understanding.

[0557] Step 6:

[0558] Users receive analysis results via a terminal. The terminal provides visual reports using a graphical interface. Users can use the information they obtain to improve their work and send feedback to the server.

[0559] (Application Example 2)

[0560] 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."

[0561] In modern manufacturing environments, complex data analysis and the effective utilization of its results are required. However, systems that provide uniform information without considering the user's emotional state can increase the psychological burden on workers and potentially decrease production efficiency. Furthermore, systems capable of flexibly presenting information according to the user's emotions and state are not sufficiently available, which is a barrier to efficient work execution on the factory floor.

[0562] 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.

[0563] In this invention, the server includes means for acquiring simulation data, means for preprocessing the simulation data, and means for using a machine learning model to analyze the preprocessed data. This makes it possible to present analysis results that take into account the user's emotional state and to adjust the interface based on those results.

[0564] "Simulation data" refers to data used to simulate physical phenomena and process states in a digital environment, and to virtually reproduce their behavior and results.

[0565] "Preprocessing" refers to processes such as data cleaning and format conversion performed to make simulation data easier to analyze.

[0566] A "machine learning model" is a set of algorithms used by computers to automatically learn specific tasks and identify patterns and rules.

[0567] "Outputting in natural language" means providing the analysis results as text in a language format that is easy for the user to understand.

[0568] "Emotional analysis" is the process of evaluating users' emotional state and psychological characteristics based on their facial expressions, tone of voice, and word choice.

[0569] "Display control" is a function that appropriately adjusts the content and format of the information presented visually according to the user's emotional state.

[0570] "Feedback" refers to information obtained from users, such as their reactions and evaluations, that is used to improve systems and processes.

[0571] "Recommended actions" refer to information that indicates the actions or strategies a user should take to achieve a desirable outcome in a particular situation.

[0572] The system for realizing this invention is based on the interaction of a server, a terminal, and a user. The server uses simulation data acquired from a digital twin environment to perform preprocessing and analysis using a machine learning model. The software used in this process is mainly Flask and TensorFlow, with Flask used for data collection and management, and TensorFlow used for model analysis of the data.

[0573] The analysis results are converted into text format in a language easily understood by the user, utilizing natural language generation technology. The device also plays a role in sensing the user's emotional state, collecting facial expression data and audio using the smartphone's camera and microphone. This information is analyzed by an emotion analysis engine to evaluate the user's psychological state.

[0574] Based on this emotional data, the server controls the display and automatically selects the optimal way to present information according to the user's state. For example, if the user is under high stress, simpler information will be displayed, while if they are relaxed, detailed analysis results will be shown.

[0575] As a concrete example, consider the monitoring of robotic arm operation in a factory. This system analyzes operational data in real time and reports on equipment efficiency and potential problems in natural language. Furthermore, it can provide operation guides to reduce workload based on the sentiment data of on-site workers.

[0576] An example of a prompt for a generative AI model is, "Optimize how information is displayed based on user sentiment data."

[0577] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0578] Step 1:

[0579] The server acquires simulation data from the digital twin environment. The input is parameter data of the physical environment, which is imported into the server. The output is a dataset for preprocessing. To prepare this dataset, the data format is checked and outliers are filtered.

[0580] Step 2:

[0581] The server performs preprocessing on the acquired data. The input is the acquired simulation data, and the output is data in a format suitable for analysis. Specifically, it performs noise reduction and data imputation.

[0582] Step 3:

[0583] The server inputs pre-processed data into a machine learning model and performs analysis. The input is formatted data, and the output is the raw data of the analysis results. For data processing, a feature extraction algorithm is used to identify important patterns in the data.

[0584] Step 4:

[0585] The server converts the analysis results into text output using natural language generation technology. The input is the raw data (numerical information) of the model, and the output is natural language text for the user. This operation involves using natural language processing algorithms to generate sentences that are easy for humans to understand.

[0586] Step 5:

[0587] The device captures the user's facial expressions and voice and performs emotion analysis. The input is raw data acquired from the smartphone's camera and microphone, and the output is metadata indicating the user's emotional state. In this process, the emotion analysis engine performs facial recognition and voice tone analysis.

[0588] Step 6:

[0589] The server dynamically adjusts the display form of the analysis results based on the sentiment analysis results. The input is the user's sentiment state data and previous analysis results, and the output is optimized UI content. At this stage, dynamic interface updates are performed using a UI framework.

[0590] Step 7:

[0591] The user takes the necessary actions based on the information provided. The input consists of displayed natural language result text and UI content. This step includes actions such as following guidelines and entering feedback into the device.

[0592] 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.

[0593] 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.

[0594] 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.

[0595] [Fourth Embodiment]

[0596] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0597] 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.

[0598] 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).

[0599] 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.

[0600] 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.

[0601] 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).

[0602] 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.

[0603] 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.

[0604] 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.

[0605] 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.

[0606] 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.

[0607] 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.

[0608] 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".

[0609] The system of this invention automates the analysis of simulation data in a digital twin environment and provides users with useful insights. This system mainly consists of a server, terminals, and users.

[0610] The server collects and preprocesses simulation data. It receives image and numerical data from the digital twin system. This data is then processed through preprocessing steps such as noise reduction and formatting to make it ready for analysis.

[0611] Next, the server uses the pre-processed data to perform analysis using an artificial intelligence model. The AI ​​model extracts features from the input data and performs anomaly detection and prediction. This analysis generates results in a format that can be output in natural language.

[0612] Subsequently, the server uses natural language processing technology to summarize the analysis results into user-friendly text, generating insights. These insights include information to support important decision-making for the user.

[0613] The terminal receives analysis results and insights in natural language from the server and displays them visually through the user interface. This allows the user to quickly grasp the content of the analysis and decide on the necessary actions.

[0614] Users improve their work and take appropriate actions based on the analysis results displayed on their terminals. The feedback obtained during this process is then incorporated back into the system, and the server uses this feedback to retrain the artificial intelligence model. This improves the accuracy of the next analysis.

[0615] A concrete example is improving traffic flow management in smart cities. The server performs traffic flow simulations based on real-time data from traffic sensors, identifying the causes of congestion and proposing countermeasures. The terminal then presents the analysis results and proposed signal schedule improvements to the user, supporting them in making decisions to optimize urban traffic management. Successfully completing this process improves overall urban traffic efficiency and contributes to reducing congestion.

[0616] The following describes the processing flow.

[0617] Step 1:

[0618] The server receives image and numerical data based on simulations from the digital twin system. This data includes various parameters and environmental conditions of the phenomenon being studied.

[0619] Step 2:

[0620] The server performs preprocessing on the received image and numerical data, such as noise reduction and data loss imputation, to prepare it for analysis. This process improves the quality of the dataset and increases the reliability of the analysis results.

[0621] Step 3:

[0622] The server inputs pre-processed data into an artificial intelligence model for feature extraction and analysis. The AI ​​model uses deep learning to recognize patterns in the data, detect anomalies, and identify important indicators.

[0623] Step 4:

[0624] The server uses natural language processing technology to convert the analysis results obtained from the artificial intelligence model into text, generating insights in a format easily understandable to the user. These insights include predicted phenomena and recommended countermeasures.

[0625] Step 5:

[0626] The terminal receives insights transmitted from the server and displays them visually through the user interface. Users can use this information to quickly understand the situation and make decisions.

[0627] Step 6:

[0628] Based on the analysis results and insights obtained from their devices, users implement business-related actions and improvement measures. This allows users to increase operational efficiency and solve problems.

[0629] Step 7:

[0630] Users input feedback on the countermeasures they have taken and the results of those countermeasures into their terminals. The server collects this feedback and uses it to retrain the artificial intelligence model. This improves the accuracy of the analysis in the next run.

[0631] (Example 1)

[0632] 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".

[0633] In today's complex systems, there is a need to efficiently analyze large amounts of simulation data and provide information in a way that users can intuitively understand. Furthermore, there is a lack of systems that can improve the accuracy of data analysis by utilizing the feedback obtained, and this solution addresses that challenge.

[0634] 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.

[0635] In this invention, the server includes a mechanism for acquiring data, a mechanism for preprocessing the data, and a mechanism for using a machine learning model to analyze the preprocessed data. This makes it possible to efficiently process large amounts of data and to improve the accuracy of the analysis by reflecting feedback from users.

[0636] A "data acquisition mechanism" is a means of receiving digital information from an external source and converting it into a format usable within the system.

[0637] A "preprocessing mechanism" is a means of removing noise from acquired digital information and formatting it to make it easier to analyze.

[0638] A "mechanism that uses machine learning models" is a means of analyzing large amounts of digital information and utilizing algorithms to detect useful patterns and anomalies.

[0639] A "mechanism for outputting in natural language" is a means of generating and presenting analysis results in a form that is easy for users to understand.

[0640] A "visual display mechanism" is a means of displaying analyzed information in a way that users can intuitively understand.

[0641] A "mechanism for generating useful insights" is a means of constructing valuable information and insights to support users' decision-making based on analysis results.

[0642] A "feedback acquisition and retraining mechanism" is a means of collecting evaluations and reactions from users and updating the machine learning model based on them to improve its accuracy.

[0643] A "mechanism for suggesting recommended actions" is a means of showing users the optimal course of action derived from analyzed data and encouraging them to take action.

[0644] This invention is a system that automatically analyzes simulation data in a digital twin environment and provides users with useful insights. The main components of this system are a server, terminals, and users.

[0645] The server has a mechanism to automatically receive large amounts of data acquired from the digital twin system. For example, it collects real-time digital information via an API. This data includes image and numerical data, and is preprocessed in preparation for later analysis. At this stage, denoising and formatting are performed using the Python Pandas library.

[0646] Next, the server inputs the pre-processed data into a machine learning model, and the system performs anomaly detection and prediction. This machine learning model uses libraries such as TensorFlow and PyTorch to extract features from the data and proceed with the analysis. The results obtained from the analysis are converted into natural language and provided in a format that is easy for the user to understand. For natural language processing, a generative AI model is employed to generate specific information, such as "the traffic congestion from 10 o'clock is due to construction, and a 15-minute delay is predicted."

[0647] The terminal receives analysis results sent from the server and displays them visually through a user interface. Technologies such as HTML and JavaScript are utilized, and a graphical user interface is designed to allow users to intuitively analyze the data.

[0648] Users improve and modify the system based on the analysis results displayed via their devices, providing useful feedback. This feedback is sent to the server and used to retrain the generated AI model. Through this process, the accuracy of the analysis improves, which is useful for subsequent data analyses.

[0649] A concrete example is traffic flow management in smart cities. The server analyzes real-time traffic sensor data and suggests causes of congestion and countermeasures. These analysis results are presented to users via terminals, supporting effective decision-making in urban traffic management.

[0650] An example of a prompt message that can be entered is, "Based on real-time data from traffic sensors, identify the causes of urban traffic congestion and propose effective improvement measures."

[0651] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0652] Step 1:

[0653] The server receives digital information from the digital twin system. The inputs are image and numerical data from the digital twin system, collected in real time via an API. The server stores this initial data internally, preparing it for subsequent processing.

[0654] Step 2:

[0655] The server preprocesses the received digital information. The main input is the raw data containing noise collected in Step 1. The server applies a denoising filter using the Python Pandas library to remove unwanted data. It also standardizes the data format and converts it into a structure that is easy to analyze. The preprocessing results in clean data, which is used in the next analysis step.

[0656] Step 3:

[0657] The server inputs pre-processed data into a machine learning model and performs data analysis. The input is clean, formatted data, which is then fed into a generative AI model using TensorFlow or PyTorch. The model extracts features from the data, performs calculations such as anomaly detection and prediction, and outputs the analysis results. For example, it can predict fluctuations in traffic flow during a specific time period.

[0658] Step 4:

[0659] The server generates a summary of the analyzed results using natural language processing technology. The input is the analysis results obtained in step 3, and based on this, a generation AI model is used to convert it into natural language text that is easy for the user to understand. The output provides information that supports the user's decision-making.

[0660] Step 5:

[0661] The terminal receives natural language analysis results sent from the server and displays them visually. The primary input is a designed natural language summary. The terminal uses HTML and JavaScript to place this information on a graphical user interface, making it easily accessible to the user.

[0662] Step 6:

[0663] Users utilize the analysis results presented via their terminals to improve their work and make decisions. Feedback input consists of the user's choices and judgments, which are sent back to the server. The server stores this feedback information and uses it to retrain the generated AI model. This is expected to improve the accuracy of subsequent data analyses.

[0664] (Application Example 1)

[0665] 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".

[0666] In current digital twin environments, there is a lack of means to effectively utilize real-time data to immediately present analysis results regarding specific physical phenomena and locations, enabling users to make rapid decisions. Furthermore, it is difficult to improve learning by effectively utilizing feedback loops based on analysis results.

[0667] 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.

[0668] In this invention, the server includes means for receiving information for simulation, means for preprocessing the simulation information, and means for using a learning algorithm to analyze the preprocessed information. This enables the rapid provision of analysis results based on real-time acquired data to the user, and also allows for automatic improvement of the learning algorithm through feedback.

[0669] "Information for simulation" refers to the data necessary to virtually reproduce physical phenomena and events in a digital twin environment.

[0670] "Preprocessing functions" refer to processing methods such as noise reduction and format conversion performed to convert raw data into an analyzable format.

[0671] A "learning algorithm" is a computational method used to extract features from input data and perform pattern recognition, prediction, and anomaly detection.

[0672] The "function to output in natural language format" is a technology that expresses analysis results and insights in a form that humans can easily understand.

[0673] "Devices provided to users" refers to interface devices that visually display analysis results and enable users to easily interpret the data.

[0674] "Specific location information" refers to a concrete location within physical space, and is an element that enables data analysis based on that location.

[0675] "Means for processing real-time information" refers to technologies that instantly analyze data obtained continuously over time and generate results.

[0676] This invention makes it possible to construct a traffic management system in a smart city environment. The server has the function of receiving and preprocessing information for simulation from traffic sensors. Specifically, it performs noise reduction and data formatting to prepare the data for analysis in real time. Python and the Requests library are used for this purpose.

[0677] Next, the server uses a learning algorithm based on the pre-processed information to perform anomaly detection and congestion prediction. The learning algorithm used here is implemented by a generative AI model. The detected anomaly data and prediction results are output in natural language format.

[0678] The server then sends the generated natural language analysis results to the terminal. The terminal functions as a device to provide the results to the user, displaying the data visually. This allows the user to quickly grasp the analysis results and assist in decision-making, such as selecting an appropriate route to avoid congestion.

[0679] As a concrete example, a dedicated application is installed on the smartphones that users use daily, and traffic information is updated in real time. Users can choose an alternative route based on the traffic congestion information and shorten their commute time.

[0680] An example of a prompt message could be: "Recent traffic data analysis has detected abnormal traffic volume at a specific location. Do you want to check an alternative route?" Such prompt messages help users make informed decisions.

[0681] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0682] Step 1:

[0683] The server receives real-time simulation information from traffic sensors. The input is raw data from the sensors, and the output is this data itself. Specifically, the data is retrieved via an API and stored in the database in its unformatted state.

[0684] Step 2:

[0685] The server performs preprocessing on the received raw data. Specifically, it performs noise reduction and data formatting. The input here is the raw data, which is the output of step 1, and the output is analyzable data that has been noise-removed and formatted.

[0686] Step 3:

[0687] The server uses pre-processed data to perform analysis with a generated AI model. Specifically, it extracts features from the data and performs anomaly detection and traffic congestion prediction. The input is the data formatted in step 2, and the output is the analysis results, such as anomaly detection information and prediction results.

[0688] Step 4:

[0689] The server converts the generated analysis results into natural language format. Using natural language processing techniques, it transforms the results into a language that is easily understandable to humans. The input is the analysis result from step 3, and the output is a text format that can be presented to the user.

[0690] Step 5:

[0691] The server sends the parsing results, converted into natural language format, to the terminal. Specifically, it sends information to the user's terminal via data communication. The input is the text data that was output in step 4, and the output is the parsing result displayed visually on the terminal.

[0692] Step 6:

[0693] The user receives the analysis results visually presented on the terminal and makes a decision. Specifically, they read the prompt text and select the optimal route to avoid congested areas. The input is the visually displayed information that is the output in step 5, and the output is the decision-making action made by the user.

[0694] 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.

[0695] This invention provides a system that combines an emotion engine to improve the user experience in the analysis of digital twin simulation data. This system consists of a server, a terminal, and a user, and each element works organically to enable more effective utilization of the analysis results.

[0696] The server preprocesses image and numerical data acquired from digital twin simulations and analyzes them using an artificial intelligence model. During the analysis, it extracts data features and generates insights derived from them. These insights are output in natural language and provided to the user.

[0697] In addition, this system incorporates an emotion engine. The terminal senses the user's emotions, facial expressions, voice tone, etc., and sends this data to the emotion engine. The emotion engine analyzes this data to identify the user's current emotions and stress level.

[0698] Based on the information obtained from the emotion engine, the server adjusts how the analysis results are presented. For example, if the user is experiencing high stress, it selects an easy-to-use, low-load interface; conversely, if the user is relaxed, it presents detailed analysis results.

[0699] A concrete example is improving production efficiency in a manufacturing plant. The server acquires machine operation data and gains insights into operational efficiency and maintenance needs. Terminals acquire real-time emotional information from on-site workers via an emotion engine and feed it back to the server. As a result, the system makes suggestions and adjusts the interface to reduce the burden on workers, thereby improving productivity. This entire process increases operational efficiency and reduces worker satisfaction and burden.

[0700] The following describes the processing flow.

[0701] Step 1:

[0702] The server receives simulation image data and numerical data from the digital twin system. This allows it to collect basic information necessary for verifying and predicting phenomena in the virtual environment.

[0703] Step 2:

[0704] The server preprocesses the received data. Specifically, it performs noise reduction, imputation of missing values, and adjustment of the data format to prepare it for optimal analysis.

[0705] Step 3:

[0706] The server inputs pre-processed data into an artificial intelligence model, which extracts and analyzes the data's features. This allows for the detection of anomalies, the uncovering of unknown patterns, and the generation of insights that form the basis of inference.

[0707] Step 4:

[0708] The server uses natural language processing technology to convert the analysis results into text in a format that is easy for the user to understand, and generates it as knowledge.

[0709] Step 5:

[0710] The terminal receives insights transmitted from the server and displays them visually through the user interface. This allows the user to accurately grasp the information and make quick decisions.

[0711] Step 6:

[0712] The device collects emotional information by sensing the user's facial expressions and voice tone, and sends it to the emotion engine.

[0713] Step 7:

[0714] The emotion engine analyzes data sent from the device to identify the user's current emotional state. This information indicates the user's stress level, level of concentration, and other factors.

[0715] Step 8:

[0716] The server adjusts how the analysis results are presented based on information from the emotion engine. Specifically, it optimizes the complexity and amount of information in the display interface according to the user's emotional state.

[0717] Step 9:

[0718] Users can review analysis results and determine appropriate actions for their work through a customized interface presented on their device. This enables efficient decision-making tailored to the specific situation.

[0719] Step 10:

[0720] Users input feedback on their work actions and results into a terminal. The server receives this feedback and uses it to improve the artificial intelligence model and enhance the accuracy of the analysis.

[0721] (Example 2)

[0722] 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".

[0723] There is a need to provide the results of complex simulation data analysis in a format that is easy for users to understand. However, conventional technologies lack the ability to provide information that takes into account the user's emotional state, making the improvement of the user experience a challenge. Furthermore, it is also important to quickly reflect changing user feedback and improve the accuracy of the analysis information provided.

[0724] 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.

[0725] In this invention, the server includes means for acquiring information, means for preprocessing the information, and means for using an artificial intelligence model to analyze the preprocessed information. This enables the presentation of flexible analysis results that correspond to the user's emotional state and highly accurate data analysis that reflects user feedback.

[0726] "Means of acquiring information" refers to the function that a system uses to collect necessary data and information from external sources.

[0727] "Preprocessing means" refers to a function that performs data processing to prepare acquired information into a format suitable for analysis.

[0728] "Methods using artificial intelligence models" refer to the function of extracting patterns and insights from data by utilizing machine learning and statistical models in data analysis.

[0729] "Means of outputting in natural language" refers to a function that converts the analysis results into a language format that is easy for humans to understand and provides them.

[0730] "Means for detecting the user's emotional state" refers to a function that analyzes the user's physical reactions, such as facial expressions and voice, to understand their emotional state.

[0731] "Means for adjusting the presentation method of analysis results based on emotional state" refers to a function that appropriately changes the content and format of the displayed analysis results according to the detected emotions of the user.

[0732] "Means for visually displaying analysis results to the user" refers to a display function via a graphical user interface that provides the analyzed information to the user visually.

[0733] This invention is an advanced data analysis system that utilizes digital twin technology and aims to improve the user experience. The server first acquires image and numerical data generated in real time from the digital twin simulation. Advanced data cleaning software is used to perform preprocessing on this data, such as noise reduction and format conversion.

[0734] Next, the server utilizes a generative AI model to analyze this preprocessed data. This AI model is built on machine learning algorithms to extract features from the data and provide the necessary insights. The results are then translated into human-readable language using natural language processing software and presented to the user.

[0735] The device uses sensors such as cameras and microphones to detect the user's emotional state. The emotional data acquired by these sensors is sent to an emotion engine, which then provides the analysis results to a server. The server adjusts how the analysis results are displayed based on the user's emotions, selecting and displaying either simplified information or detailed analysis results as needed.

[0736] As a concrete example, consider optimizing machine operation in a manufacturing facility. In this case, the server collects operating data from the machines within the facility and analyzes their efficiency and maintenance needs. Simultaneously, terminals collect emotional information from on-site workers, feed it back to the server, and provide an interface that simplifies operations if the workers are feeling stressed.

[0737] An example of a prompt is the specific instruction, "Please describe data analysis and emotional state monitoring methods to improve factory productivity."

[0738] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0739] Step 1:

[0740] The server acquires image and numerical data from the digital twin simulation. This input data includes information about the machine's operating status and environment. The server stores this data in a database.

[0741] Step 2:

[0742] The server preprocesses the acquired data. This preprocessing includes denoising the data and imputing missing values. Specifically, it uses filtering algorithms to detect anomalous data and converts it into the correct format. This prepares the data for analysis.

[0743] Step 3:

[0744] The server feeds pre-processed data into a generating AI model for analysis. The model extracts features from the data and generates insights for improving machine efficiency and predicting failures. The output insights are presented as numerical information and statistical indicators.

[0745] Step 4:

[0746] The device uses a camera and microphone to detect the user's emotional state. This collects data on the user's facial expressions and changes in voice tone. This emotional data is sent to an emotion engine, which outputs information that evaluates the user's stress level and satisfaction level.

[0747] Step 5:

[0748] The server adjusts how the analysis results are displayed based on the emotional information sent from the emotion engine. It changes the level of detail of the information presented to the user according to their emotional state. For example, if high stress is detected, the information is simplified for easier understanding.

[0749] Step 6:

[0750] Users receive analysis results via a terminal. The terminal provides visual reports using a graphical interface. Users can use the information they obtain to improve their work and send feedback to the server.

[0751] (Application Example 2)

[0752] 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".

[0753] In modern manufacturing environments, complex data analysis and the effective utilization of its results are required. However, systems that provide uniform information without considering the user's emotional state can increase the psychological burden on workers and potentially decrease production efficiency. Furthermore, systems capable of flexibly presenting information according to the user's emotions and state are not sufficiently available, which is a barrier to efficient work execution on the factory floor.

[0754] 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.

[0755] In this invention, the server includes means for acquiring simulation data, means for preprocessing the simulation data, and means for using a machine learning model to analyze the preprocessed data. This makes it possible to present analysis results that take into account the user's emotional state and to adjust the interface based on those results.

[0756] "Simulation data" refers to data used to simulate physical phenomena and process states in a digital environment, and to virtually reproduce their behavior and results.

[0757] "Preprocessing" refers to processes such as data cleaning and format conversion performed to make simulation data easier to analyze.

[0758] A "machine learning model" is a set of algorithms used by computers to automatically learn specific tasks and identify patterns and rules.

[0759] "Outputting in natural language" means providing the analysis results as text in a language format that is easy for the user to understand.

[0760] "Emotional analysis" is the process of evaluating users' emotional state and psychological characteristics based on their facial expressions, tone of voice, and word choice.

[0761] "Display control" is a function that appropriately adjusts the content and format of the information presented visually according to the user's emotional state.

[0762] "Feedback" refers to information obtained from users, such as their reactions and evaluations, that is used to improve systems and processes.

[0763] "Recommended actions" refer to information that indicates the actions or strategies a user should take to achieve a desirable outcome in a particular situation.

[0764] The system for realizing this invention is based on the interaction of a server, a terminal, and a user. The server uses simulation data acquired from a digital twin environment to perform preprocessing and analysis using a machine learning model. The software used in this process is mainly Flask and TensorFlow, with Flask used for data collection and management, and TensorFlow used for model analysis of the data.

[0765] The analysis results are converted into text format in a language easily understood by the user, utilizing natural language generation technology. The device also plays a role in sensing the user's emotional state, collecting facial expression data and audio using the smartphone's camera and microphone. This information is analyzed by an emotion analysis engine to evaluate the user's psychological state.

[0766] Based on this emotional data, the server controls the display and automatically selects the optimal way to present information according to the user's state. For example, if the user is under high stress, simpler information will be displayed, while if they are relaxed, detailed analysis results will be shown.

[0767] As a concrete example, consider the monitoring of robotic arm operation in a factory. This system analyzes operational data in real time and reports on equipment efficiency and potential problems in natural language. Furthermore, it can provide operation guides to reduce workload based on the sentiment data of on-site workers.

[0768] An example of a prompt for a generative AI model is, "Optimize how information is displayed based on user sentiment data."

[0769] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0770] Step 1:

[0771] The server acquires simulation data from the digital twin environment. The input is parameter data of the physical environment, which is imported into the server. The output is a dataset for preprocessing. To prepare this dataset, the data format is checked and outliers are filtered.

[0772] Step 2:

[0773] The server performs preprocessing on the acquired data. The input is the acquired simulation data, and the output is data in a format suitable for analysis. Specifically, it performs noise reduction and data imputation.

[0774] Step 3:

[0775] The server inputs pre-processed data into a machine learning model and performs analysis. The input is formatted data, and the output is the raw data of the analysis results. For data processing, a feature extraction algorithm is used to identify important patterns in the data.

[0776] Step 4:

[0777] The server converts the analysis results into text output using natural language generation technology. The input is the raw data (numerical information) of the model, and the output is natural language text for the user. This operation involves using natural language processing algorithms to generate sentences that are easy for humans to understand.

[0778] Step 5:

[0779] The device captures the user's facial expressions and voice and performs emotion analysis. The input is raw data acquired from the smartphone's camera and microphone, and the output is metadata indicating the user's emotional state. In this process, the emotion analysis engine performs facial recognition and voice tone analysis.

[0780] Step 6:

[0781] The server dynamically adjusts the display form of the analysis results based on the sentiment analysis results. The input is the user's sentiment state data and previous analysis results, and the output is optimized UI content. At this stage, dynamic interface updates are performed using a UI framework.

[0782] Step 7:

[0783] The user takes the necessary actions based on the information provided. The input consists of displayed natural language result text and UI content. This step includes actions such as following guidelines and entering feedback into the device.

[0784] 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.

[0785] 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.

[0786] 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.

[0787] 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.

[0788] 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.

[0789] 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.

[0790] 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.

[0791] 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.

[0792] 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."

[0793] 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.

[0794] 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.

[0795] 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.

[0796] 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.

[0797] 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.

[0798] 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.

[0799] 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.

[0800] 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.

[0801] 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.

[0802] 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.

[0803] 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.

[0804] 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.

[0805] The following is further disclosed regarding the embodiments described above.

[0806] (Claim 1)

[0807] Means for acquiring simulation data,

[0808] Means for preprocessing the aforementioned simulation data,

[0809] A method using an artificial intelligence model to analyze preprocessed data,

[0810] A means for outputting the analysis results obtained from the aforementioned model in natural language,

[0811] A means of visually displaying the analysis results to the user,

[0812] A system that includes this.

[0813] (Claim 2)

[0814] The system according to claim 1, further comprising means for obtaining user feedback based on the analysis results and for retraining the artificial intelligence model.

[0815] (Claim 3)

[0816] The system according to claim 1, further comprising means for suggesting recommended actions for a specific physical phenomenon based on insights obtained from the aforementioned analysis results.

[0817] "Example 1"

[0818] (Claim 1)

[0819] A mechanism for acquiring data,

[0820] A mechanism for preprocessing the aforementioned data,

[0821] A mechanism that uses machine learning models to analyze preprocessed data,

[0822] A mechanism for outputting the analysis results obtained from the aforementioned model in natural language,

[0823] A mechanism to visually display the analysis results to the user,

[0824] A mechanism that summarizes analysis results and generates useful insights to support user decision-making,

[0825] A system that includes this.

[0826] (Claim 2)

[0827] The system according to claim 1, further comprising a mechanism for obtaining user feedback based on the aforementioned analysis results and for retraining the machine learning model.

[0828] (Claim 3)

[0829] The system according to claim 1, further comprising a mechanism that presents recommended actions for a specific physical phenomenon based on the insights obtained from the aforementioned analysis results.

[0830] "Application Example 1"

[0831] (Claim 1)

[0832] A means for receiving information for simulation,

[0833] Means having a function for preprocessing the aforementioned simulation information,

[0834] A means of using a learning algorithm to analyze preprocessed information,

[0835] A means having a function to output the analysis results obtained from the aforementioned algorithm in natural language format,

[0836] Means including a device for visually providing analysis results to the user,

[0837] A means of processing real-time information based on specific location information,

[0838] A system that includes this.

[0839] (Claim 2)

[0840] The system according to claim 1, further comprising a function to obtain input information from the user based on the analysis results and to cause the learning algorithm to perform continuous learning.

[0841] (Claim 3)

[0842] The system according to claim 1, further comprising means for providing recommendations for specific activity phenomena based on insights obtained from the aforementioned analysis results.

[0843] "Example 2 of combining an emotion engine"

[0844] (Claim 1)

[0845] Means of obtaining information,

[0846] Means for preprocessing the aforementioned information,

[0847] A method using an artificial intelligence model to analyze pre-processed information,

[0848] A means for outputting the analysis results obtained from the aforementioned model in natural language,

[0849] A means of detecting the user's emotional state,

[0850] Means for adjusting the method of presenting the analysis results based on the aforementioned emotional state,

[0851] A means of visually displaying the analysis results to the user,

[0852] A system that includes this.

[0853] (Claim 2)

[0854] The system according to claim 1, further comprising means for obtaining user feedback based on the analysis results and for retraining the artificial intelligence model.

[0855] (Claim 3)

[0856] The system according to claim 1, further comprising means for suggesting recommended actions for a specific physical phenomenon based on insights obtained from the aforementioned analysis results.

[0857] "Application example 2 when combining with an emotional engine"

[0858] (Claim 1)

[0859] Means for acquiring simulation data,

[0860] Means for preprocessing the aforementioned simulation data,

[0861] A method using a machine learning model to analyze preprocessed data,

[0862] A means for outputting the analysis results obtained from the aforementioned model in natural language,

[0863] A means for sensing and analyzing the emotional state of a user,

[0864] A display control means that adjusts the method of presenting the analysis results based on the aforementioned emotional state,

[0865] A system that includes this.

[0866] (Claim 2)

[0867] The system according to claim 1, further comprising means for obtaining user feedback based on the analysis results and retraining the machine learning model.

[0868] (Claim 3)

[0869] The system according to claim 1, further comprising means for suggesting recommended actions for a specific physical phenomenon based on the analysis results and information obtained from the emotion analysis means. [Explanation of symbols]

[0870] 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. Means for acquiring simulation data, Means for preprocessing the aforementioned simulation data, A method using an artificial intelligence model to analyze preprocessed data, A means for outputting the analysis results obtained from the aforementioned model in natural language, A means of visually displaying the analysis results to the user, A system that includes this.

2. The system according to claim 1, further comprising means for obtaining user feedback based on the analysis results and for retraining the artificial intelligence model.

3. The system according to claim 1, further comprising means for suggesting recommended actions for a specific physical phenomenon based on insights obtained from the aforementioned analysis results.

Images