System

Abstract

A system is provided.SOLUTION: A system includes means for collecting historical data from a data source, means for analyzing and tagging the collected historical data, means for training an artificial intelligence model based on the tagged historical data, means for constructing a virtual environment using the trained artificial intelligence model, means for receiving an input from a user terminal and executing a simulation, and means for analyzing a simulation result and providing the simulation result to the user terminal.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] Traditional decision-making processes make it difficult to efficiently utilize past lessons and data, often resulting in uncertainty in strategic decisions and forecasts. Management and marketing professionals, in particular, face the challenge of lacking tools to quickly conduct simulations based on historical data and make highly accurate decisions. Furthermore, traditional systems are inadequate at processing large amounts of data and recreating pseudo-history, and there are many technical limitations to conducting realistic simulations. [Means for solving the problem]

[0005] The present invention solves the above-mentioned problems by providing a system that utilizes historical data to recreate historical events and people in a virtual environment. Specifically, the system includes means for collecting historical data from data sources, means for analyzing and tagging the collected data, means for training an AI model based on the tagged data, means for constructing a virtual environment using the trained AI model, means for accepting input from a user terminal and running a simulation, and means for analyzing and providing the simulation results to the user terminal. This provides management and marketing personnel with the materials they need to make quick and accurate decisions. Furthermore, the system includes a function for AI agents to interact with each other in the virtual environment during the simulation, and a function for scenario selection and parameter setting based on user interaction, enabling flexible and advanced simulations.

[0006] "Data Source" means the original source from which reliable historical data is obtained.

[0007] "Historical data" is data that includes information about past events, people, dates, places, etc.

[0008] "Collection" is the process of gathering the necessary historical data from multiple data sources.

[0009] "Analysis" is the process of processing and analyzing collected historical data to extract necessary information.

[0010] "Tagging" is the process of assigning keywords and attribute information to analyzed data.

[0011] An "artificial intelligence model" is a program that uses machine learning and deep learning techniques to learn from historical data and perform specific tasks.

[0012] "Training" is the learning process of using shaped data to improve the performance of an artificial intelligence model.

[0013] A "virtual environment" is a fictitious space or scenario recreated using computer technology.

[0014] A "user terminal" is a device used by a user, such as a PC, tablet, or smartphone.

[0015] "Simulation" is the process of running a set scenario in a virtual environment and observing the results.

[0016] "Analysis results" refer to data obtained through simulation and the results of analyzing that data.

[0017] An "artificial intelligence agent" is a virtual person or character that operates based on an artificial intelligence model.

[0018] "Interaction" refers to the mutual influence between artificial intelligence agents.

[0019] "User interaction" refers to the operations and inputs that a user makes to interact with a system.

[0020] A "scenario" is a setting or story that recreates a particular historical event or situation.

[0021] "Parameters" are numerical values ​​or variables used to set detailed conditions for a simulation. [Brief explanation of the drawings]

[0022] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 11] FIG. 3 is a sequence diagram showing a processing flow of the data processing system according to the first embodiment. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0023] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

[0024] First, the terms used in the following description will be explained.

[0025] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), and an APU (Accelerated Processing Unit).

[0026] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

[0027] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0028] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0029] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0030] [First embodiment]

[0031] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0032] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0033] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0034] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0035] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0036] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0037] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

[0038] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0039] 2, in the data processing device 12, a specific process is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0040] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0041] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with the specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0042] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0043] MODE FOR CARRYING OUT THE INVENTION

[0044] The present invention relates to a system for collecting and analyzing historical data and performing simulations based on the collected data, and the method for implementing the system will be described below.

[0045] 1. Data Collection

[0046] The server collects historical data from multiple reliable data sources, such as official government archives, historical documents, and databases, using APIs and web scraping techniques, and stores the collected data in a local database.

[0047] 2. Data formatting and analysis

[0048] The server cleanses the collected data, removing duplicates and missing data. It then analyzes the data using natural language processing (NLP) techniques to identify important events and people. Identified information is tagged with appropriate tags and the data is converted into a format suitable for training artificial intelligence models.

[0049] 3. Training the AI ​​model

[0050] The server uses the formatted data to train an artificial intelligence model. Specifically, it uses machine learning algorithms and deep learning techniques to learn the behavioral patterns of each historical event and person. The trained model's performance is evaluated, and parameters are optimized as needed.

[0051] 4. Building a virtual environment

[0052] The server uses the trained AI model to build a virtual environment ("History Sandbox"), a virtual space for recreating historical scenarios, designed in detail using 3D modeling tools. Trained AI agents are placed within this environment, interacting with each other to progress the simulation.

[0053] 5. User Interaction

[0054] Users access the "History Sandbox" using a terminal. They select a specific scenario from a list of scenarios and customize the simulation settings and parameters. For example, they can select the "Napoleonic Wars" scenario and set conditions such as the number of troops and weather.

[0055] 6. Running the simulation and providing the results

[0056] The server simulates a scenario based on the conditions set by the user. During this simulation, AI agents act based on their respective roles and interact with each other. After the simulation is complete, the server analyzes the results and extracts key events and performance data. The results are sent to the user's device, where they can view the results through detailed reports and graphs.

[0057] Specific examples

[0058] 1. World War II simulation

[0059] Users access the "History Sandbox" on their devices and select a World War II scenario. They set parameters such as the German army's advance speed and the Allied forces' reaction time. The server then runs the simulation and analyzes several strategic options. Simulation results, such as each country's strategic success rate and resource consumption, are provided to the user.

[0060] 2. Marketing strategy verification

[0061] Management simulates current market conditions based on historical marketing data. For example, they analyze data extracted from past successes and failures to train an AI model. They then use the trained model to simulate new product launch scenarios. As a result, product demand forecasts and competitor responses are analyzed, providing management with the information they need to make more accurate decisions.

[0062] In this way, by utilizing advanced simulation technology, the present invention makes it possible to predict the future based on historical data, becoming a powerful tool that enables users and companies to make quick and accurate decisions.

[0063] The processing flow will be explained below.

[0064] Step 1:

[0065] The server collects historical data from data sources, such as official archives, historical documents, and online databases, using APIs and web scraping techniques, and stores the collected data in a local database.

[0066] Step 2:

[0067] The server cleanses the collected data. During the cleansing process, duplicate data and missing data are removed to ensure data integrity. The cleansed data is then passed on to the next analysis step.

[0068] Step 3:

[0069] The server analyzes the data using natural language processing (NLP) techniques, such as segmenting the text data into words, tagging parts of speech, and extracting named entities to identify important events and people.

[0070] Step 4:

[0071] The server then tags the parsed data, for example, by adding appropriate tags based on specific eras, locations, or characters, and structuring the data.

[0072] Step 5:

[0073] The server uses the tagged data to train an artificial intelligence model, using machine learning algorithms and deep learning techniques to learn the behavioral patterns of each historical event and person.

[0074] Step 6:

[0075] The server evaluates the performance of the trained AI model, using metrics such as precision, recall, and F1 score, and optimizes the model parameters as needed.

[0076] Step 7:

[0077] The server uses trained artificial intelligence models to build a virtual environment (the "History Sandbox"), which is meticulously designed using 3D modeling tools and serves as a virtual space for recreating historical scenarios.

[0078] Step 8:

[0079] Users access the "History Sandbox" using their devices. They select a specific scenario from a list of scenarios and customize the simulation settings and parameters. For example, they can select the "Napoleonic Wars" scenario and set conditions such as the number of troops and weather.

[0080] Step 9:

[0081] The server simulates a scenario based on the conditions set by the user. AI agents interact with each other within the virtual environment, and the simulation progresses.

[0082] Step 10:

[0083] The server analyzes the simulation results and extracts key events and achievements, such as the outcome of a battle simulation and the resource consumption rate.

[0084] Step 11:

[0085] The server sends the simulation results to the user's device, where they can view the results through detailed reports and graphs, which can be used as a reference for decision-making.

[0086] Example 1

[0087] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0088] Conventional historical simulation systems require a great deal of time and effort to collect, format, and analyze reliable data, and they also have the problem of making it difficult for users to analyze the simulation results in detail.In addition, they lack the flexibility to allow users to customize the simulation content, making it difficult to make highly accurate predictions or analyze a variety of scenarios.

[0089] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0090] In this invention, the server includes means for collecting historical data from a data source, means for formatting and cleansing the collected historical data, means for tagging the cleansed historical data using natural language processing technology, means for training an artificial intelligence model based on the tagged historical data, means for constructing a virtual environment using the trained artificial intelligence model, means for accepting input from a user terminal and customizing simulation settings, means for executing a simulation based on the customized settings, and means for analyzing simulation results and providing them to the user terminal. This enables historical data to be collected and analyzed with high accuracy, allowing users to easily customize simulation content and perform detailed result analysis.

[0091] "Data sources" are sources of historical data and information, such as official government archives, historical documents, and online databases.

[0092] "Means of collection" refers to the methods and technologies used to obtain data using APIs or web scraping technology and store it in a local database on the server.

[0093] "Cleansing methods" refers to methods and techniques used to remove duplicate and missing data from collected data and create an accurate and consistent data set.

[0094] "Natural language processing technology" refers to technology that uses natural language processing (NLP) to analyze text data and identify important events and names of people.

[0095] "Tagging means" refers to the methods and techniques for assigning appropriate tags to analyzed data and organizing the data.

[0096] "Artificial intelligence model" refers to a model created using machine learning algorithms and deep learning techniques to learn from past data and understand patterns and features.

[0097] A "virtual environment" is a simulated space recreated using a trained artificial intelligence model, specifically a virtual space constructed using 3D modeling tools.

[0098] "Means for accepting input from a user terminal" refers to an interface or method for accepting operations such as simulation settings and scenario selection from a user via a terminal.

[0099] "Means for customizing simulation settings" refers to methods and technologies that allow users to change or set simulation conditions and parameters.

[0100] "Means for executing a simulation" refers to methods and techniques for progressing a simulation within a virtual environment based on set conditions.

[0101] "Means for analyzing simulation results" refers to methods and techniques for evaluating the results after the simulation is completed and extracting and analyzing key events, achievements, etc.

[0102] "Means for providing to user terminal" refers to the methods and technologies for displaying and transmitting the analyzed simulation results to the user's terminal so that the user can check and analyze the results.

[0103] The present invention relates to a system for collecting and analyzing historical data and performing simulations based on the collected data. A specific method for implementing the system will be described below.

[0104] The server collects historical data from multiple reliable data sources, including official government archives, historical documents, and online databases. The collected data is retrieved using APIs and web scraping techniques, such as Python's "BeautifulSoup" and "Scrapy."

[0105] The server then formats and cleanses the collected data, using Python's pandas and numpy libraries, to remove duplicates and missing data and create an accurate and consistent dataset.

[0106] The cleansed data is then analyzed using natural language processing (NLP) techniques to identify important events and people's names, using NLP libraries such as spaCy and NLTK, which then tag the data appropriately and convert it into a format suitable for training artificial intelligence models.

[0107] The server uses the formatted data to train an AI model using machine learning algorithms and deep learning techniques. For example, it uses deep learning frameworks such as "TENSORFLOW (registered trademark)" and "PyTorch." During the training process, the accuracy of the model is evaluated at each epoch and hyperparameters are adjusted as necessary. Once the training is complete, the model is stored in local storage or cloud storage.

[0108] The server then uses the trained AI model to build a virtual environment. This virtual environment, called a "virtual sandbox," is designed in detail using 3D modeling tools (e.g., Unity or Unreal Engine). Historical terrain, buildings, and characters are recreated in the virtual environment, and AI agents are placed in it. These agents behave based on the behavioral patterns learned by the trained AI model.

[0109] Users access the "virtual sandbox" using their devices. They access the system through a web browser or a dedicated app and select the historical scenario they want to recreate from a list of scenarios. For example, they can choose the "Napoleonic Wars" scenario and customize the number of troops, weather, and other conditions through the interface. This setting information is sent to the server.

[0110] The server simulates a scenario based on the conditions set by the user. During the simulation, multiple AI agents interact with each other. Once the simulation is complete, the server analyzes the results to extract key events and achievements. The analysis includes evaluation indicators of the simulation (success rate, resource consumption, etc.). The generated results are sent to the user's device, where the user can view and save the results through detailed reports and graphs.

[0111] Specific examples

[0112] 1. World War II simulation

[0113] Users access the "virtual sandbox" using their devices and select a World War II scenario. They set parameters such as the German army's advance speed and the Allied forces' reaction time. The server then runs the simulation and analyzes several strategic options. Simulation results, such as each country's strategic success rate and resource depletion, are provided to the user.

[0114] 2. Marketing strategy verification

[0115] Management simulates current market conditions based on historical marketing data. For example, they analyze data extracted from past successes and failures to train an AI model. They then use the trained model to simulate new product launch scenarios. As a result, product demand forecasts and competitor responses are analyzed, providing management with the information they need to make more accurate decisions.

[0116] Prompt Sentence Examples

[0117] "It simulates an early battle scenario from the German-Soviet War of 1941, assessing the speed of German advance and the Soviet defensive response."

[0118] This system collects and analyzes historical data with high accuracy, allowing users to easily customize simulation content and perform detailed analysis of results.

[0119] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0120] Step 1:

[0121] Data collection

[0122] The server collects historical data from multiple reliable data sources. Data sources include official government archives, historical documents, and online databases. The collection method uses APIs and web scraping techniques. For example, Python's "BeautifulSoup" or "Scrapy" is used to obtain data and store it in a local database in JSON format. The input is access information and acquisition conditions for the data source, and the output is the raw data stored in the local database.

[0123] Step 2:

[0124] Data Shaping and Cleansing

[0125] The server formats and cleanses the collected data. Specifically, it uses Python libraries such as "pandas" and "numpy." During cleansing, duplicate and missing data are removed to ensure data consistency. For example, missing values ​​are filled in and duplicate records are deleted. The input is the collected raw data, and the output is the formatted, cleansed data.

[0126] Step 3:

[0127] Data tagging and analysis

[0128] The server analyzes the cleansed data using natural language processing (NLP) techniques. Specifically, it uses NLP libraries such as "spaCy" and "NLTK" to identify important events and people's names. The identified information is then appropriately tagged. The input is the data that has been formatted and cleansed, and the output is the tagged analyzed data.

[0129] Step 4:

[0130] Training an AI model

[0131] The server uses the tagged data to train an artificial intelligence model. Specifically, it uses deep learning frameworks such as TensorFlow and PyTorch to run machine learning algorithms. The training process includes accuracy evaluation after each epoch and tuning of hyperparameters. The input is the tagged analysis data, and the output is a trained AI model.

[0132] Step 5:

[0133] Building a virtual environment

[0134] The server uses the trained AI model to build a virtual environment (virtual sandbox). Specifically, it designs it in detail using 3D modeling tools such as Unity or Unreal Engine. This environment recreates historical terrain, buildings, and characters, and AI agents are placed in it. The input is the trained AI model and the design information for the virtual environment, and the output is the virtual sandbox.

[0135] Step 6:

[0136] Accepting user interactions

[0137] Users access the virtual sandbox using their devices. They access the system through a web browser or a dedicated app and select the historical scenario they want to recreate from a list of scenarios. They then use the interface to customize conditions and parameters (e.g., number of troops, weather, etc.). The input is the user's selection and settings, and the output is the transmission of the settings to the server.

[0138] Step 7:

[0139] Running a simulation and analyzing the results

[0140] The server simulates a scenario based on the conditions set by the user. During the simulation, multiple AI agents interact with each other. When the simulation is complete, the server analyzes the results and extracts key events and achievements. Specifically, it analyzes the simulation's evaluation indicators (success rate, resource consumption, etc.). The input is the user settings and simulation result data, and the output is an analyzed simulation report.

[0141] Step 8:

[0142] Providing results

[0143] The server provides the analyzed simulation results to the user's terminal. The user can view and save the results through detailed reports and graphs. The input is the analyzed simulation report, and the output is the result display on the user's terminal.

[0144] (Application example 1)

[0145] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0146] Modern brick-and-mortar stores require effective customer service and optimized sales strategies. However, traditional methods do not fully utilize past sales data and customer information, making it difficult to make timely decisions. In addition, there are limited means of providing real-time sales forecasts and customer service information, making it difficult for store staff to respond immediately. This can lead to a decline in customer satisfaction and lost sales opportunities.

[0147] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0148] In this invention, the server includes means for collecting historical data from a data source, means for analyzing and tagging the collected historical data, means for training a generative AI model based on the tagged historical data, means for constructing a virtual environment using the trained generative AI model, means for accepting input from a user terminal and executing a simulation, means for providing information useful for customer service in a physical store in real time, and means for analyzing the simulation results and providing them to the user terminal, thereby enabling timely and effective customer service and optimization of sales strategies in physical stores.

[0149] "Data Source" refers to a reliable source or database from which historical data is collected.

[0150] "Historical data" refers to data that contains information about past events or phenomena.

[0151] "Tagging" is the process of adding relevant information to data to make it easier to identify.

[0152] A "generative AI model" is an artificial intelligence model that is trained based on collected and analyzed data.

[0153] "Virtual environment" refers to a virtual simulation environment built using a generative AI model.

[0154] A "user terminal" is a device (such as a smartphone or smart glasses) that a user uses to access the system and perform input and output.

[0155] "Simulation" is the process of virtually recreating real-world phenomena or scenarios.

[0156] A "physical store" is a store that exists physically and where customers can visit in person to purchase products.

[0157] "Customer care" refers to the process of providing service and support to customers.

[0158] 1. Data Collection

[0159] The server collects historical data from reliable data sources, such as official government archives, historical documents, and other databases, using APIs and web scraping techniques, and then stores the collected data in a local database.

[0160] 2. Data analysis and tagging

[0161] The server cleanses the collected historical data, removing missing and duplicate data, then analyzes it using natural language processing (NLP) techniques to identify important events and people, assigning appropriate tags to the identified information, and converting the data into a format suitable for training generative AI models.

[0162] 3. Training the AI ​​model

[0163] The server trains a generative AI model based on the formatted data, using machine learning algorithms and deep learning techniques. The trained model's performance is evaluated, and its parameters are optimized as needed.

[0164] 4. Building a virtual environment

[0165] The server uses the trained generative AI model to create a virtual environment, a virtual space for recreating historical scenarios, such as simulating a physical store using 3D modeling tools.

[0166] 5. User Interaction

[0167] Users access the virtual environment using a device (such as a smartphone or smart glasses). They select a specific scenario and customize the settings and parameters of the simulation. For example, they can set up a simulation to forecast sales based on past sales data.

[0168] 6. Simulation and real-time response

[0169] The server simulates scenarios based on the conditions set by the user. The simulation results are analyzed and displayed in real time on the store staff's smart glasses. This allows staff to take the optimal response based on the customer's past purchase history and sales forecasts.

[0170] Specific examples

[0171] Sales forecasting and product display optimization

[0172] Historical data is analyzed to visualize seasonal sales trends and customer purchasing patterns, and store staff can optimize product displays and inventory management based on sales forecast data obtained in real time through smart glasses.

[0173] Example: Proposing best-selling products according to the season

[0174] Every year before Christmas, the company analyzes which products are selling well and uses that data to make sales forecasts. For example, store staff can see through their smart glasses that "sales of this product increased by 50% during last year's Christmas season."

[0175] Prompt Sentence Examples

[0176] Use historical sales data when forecasting next month's sales. The data should be in the following format and take into account seasonality and trends:

[0177] Features: Date, Season, Historical Sales

[0178] Response variable: future sales

[0179] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0180] Step 1: Data collection

[0181] The server retrieves data from official government archives and historical databases using APIs and web scraping techniques, and stores historical documents and archived data in a local database. The input is information from the data source, and the output is raw data stored in the local database.

[0182] Step 2: Data analysis and cleansing

[0183] The server cleanses the collected data, removing duplicates and missing data. It uses natural language processing (NLP) to analyze the data, identify and tag important events and people. The input is raw data stored in a local database, and the output is cleaned, analyzed data.

[0184] Step 3: Training the generative AI model

[0185] The server uses the cleansed and tagged data to train a generative AI model. It then uses machine learning algorithms and deep learning techniques to optimize the trained model. The input is the cleaned and analyzed data, and the output is a trained generative AI model.

[0186] Step 4: Building the virtual environment

[0187] The server uses the trained generative AI model to create a virtual environment that can recreate historical scenarios or virtual situations within a physical store. The input is the generative AI model, and the output is the virtual environment and scenario data.

[0188] Step 5: Accepting User Input and Setting Up the Simulation

[0189] Users access the virtual environment through their terminals, select specific scenarios, and customize the settings and parameters of the simulation. The input is the user's settings and selections, and the output is the simulation configuration data.

[0190] Step 6: Run the simulation

[0191] The server runs a simulation based on the conditions set by the user. AI agents interact with each other as the simulation progresses within the virtual environment. The input is the simulation setting data, and the output is the simulation result data.

[0192] Step 7: Result analysis and real-time display

[0193] The server analyzes the simulation results and extracts key events and achievements. The analysis results are displayed in real time on smart glasses or devices. The input is the simulation result data, and the output is the analysis results and their display.

[0194] Example operation

[0195] For example, if a user wants to predict sales for the Christmas season, a simulation is performed based on sales data from past Christmas seasons, and the resulting information, such as "Sales of this product increased by 50% during last year's Christmas season," is displayed on the smart glasses.

[0196] Prompt Sentence Examples

[0197] Use historical sales data when forecasting next month's sales. The data should be in the following format and take into account seasonality and trends:

[0198] Features: Date, Season, Historical Sales

[0199] Response variable: future sales

[0200] Furthermore, an emotion engine that estimates the user's emotion may be combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0201] MODE FOR CARRYING OUT THE INVENTION

[0202] The present invention relates to a system incorporating an emotion engine that recognizes a user's emotions, and the implementation method thereof will be described below.

[0203] 1. Data Collection

[0204] The server collects historical data from multiple reliable data sources, such as official archives, historical documents, and online databases, using APIs and web scraping techniques, and stores the collected data in a local database.

[0205] 2. Data formatting and analysis

[0206] The server cleanses the collected data, removing duplicates and missing data. It then analyzes the data using natural language processing (NLP) techniques to identify important events and people. Identified information is tagged with appropriate tags and the data is converted into a format suitable for training artificial intelligence models.

[0207] 3. Training the AI ​​model

[0208] The server uses the formatted data to train an artificial intelligence model. Specifically, it uses machine learning algorithms and deep learning techniques to learn the behavioral patterns of each historical event and person. The trained model's performance is evaluated, and parameters are optimized as needed.

[0209] 4. Building a virtual environment

[0210] The server uses the trained AI model to build a virtual environment ("History Sandbox"), a virtual space for recreating historical scenarios, designed in detail using 3D modeling tools. Trained AI agents are placed within this environment, interacting with each other to progress the simulation.

[0211] 5. User Interaction

[0212] Users access the "History Sandbox" using their devices. They select a specific scenario from a list of scenarios and customize the simulation settings and parameters. For example, they can select the "Napoleonic Wars" scenario and set conditions such as the number of troops and weather.

[0213] 6. Running the simulation and providing the results

[0214] The server simulates a scenario based on the conditions set by the user. During this simulation, AI agents act based on their respective roles and interact with each other. After the simulation is complete, the server analyzes the results and extracts key events and performance data. The results are sent to the user's device, where they can view the results through detailed reports and graphs.

[0215] 7. Implementing the Emotion Engine

[0216] The device is equipped with an emotion engine that recognizes the user's emotions in real time and has the ability to analyze emotional data from the user's facial expressions and voice.

[0217] 8. Emotion-based simulation adjustment

[0218] The server receives the user's emotional data analyzed by the emotion engine and adjusts the simulation accordingly. For example, if the user is excited, the simulation results will be displayed in detail, but if the user is stressed, the results will be displayed in a concise summary.

[0219] 9. Emotion-Based Recommendations

[0220] The device provides recommended scenarios and parameter settings based on the user's emotional state. For example, if the user is relaxed, it will recommend a high-difficulty scenario or complex conditions, while if the user is tense, it will recommend an easy scenario.

[0221] Specific examples

[0222] 1. Emotion-based strategic game simulation

[0223] Users access the "History Sandbox" on their devices and select a medieval strategy game scenario. The emotion engine analyzes the user's facial expressions to detect whether they are enjoying the game. The server uses this information to display detailed simulation results and offer a variety of tactical options.

[0224] 2. Emotional feedback simulation of marketing strategies

[0225] Management uses the emotion engine when simulating marketing strategy scenarios. It analyzes the voice data obtained from the device to detect how the user feels about the presentation. The server uses this information to adjust the content of the presentation and provides the final results to management.

[0226] In this way, combining emotion engines enables flexible simulation and interaction according to the user's emotional state. By using emotion data, the present invention can provide a more personalized experience and improve user satisfaction.

[0227] The processing flow will be explained below.

[0228] Step 1:

[0229] The server collects historical data from data sources, such as official archives, historical documents, and online databases, using APIs and web scraping techniques, and stores the data in a local database.

[0230] Step 2:

[0231] The server cleanses the collected data, removing duplicates and missing data to ensure the data is complete and consistent.

[0232] Step 3:

[0233] The server analyzes the data using natural language processing (NLP) techniques, specifically segmenting the text data into words, tagging parts of speech, extracting named entities, and identifying important events and people.

[0234] Step 4:

[0235] The server tags the parsed data, for example, by adding appropriate tags based on specific eras, locations, or characters, and structuring the data.

[0236] Step 5:

[0237] The server uses the tagged data to train an artificial intelligence model, using machine learning algorithms and deep learning techniques to learn the behavioral patterns of each historical event and person.

[0238] Step 6:

[0239] The server evaluates the performance of the trained AI model, using precision, recall, and F1 score as evaluation metrics, and optimizes the model parameters as needed.

[0240] Step 7:

[0241] The server uses trained artificial intelligence models to build virtual environments ("History Sandbox"), which are then detailed using 3D modeling tools to create virtual spaces for recreating historical scenarios.

[0242] Step 8:

[0243] Users access the "History Sandbox" using a device, where they can select a specific scenario from a list of scenarios and customize the simulation settings and parameters. For example, they can select the "Napoleonic Wars" scenario and set the number of troops and weather conditions.

[0244] Step 9:

[0245] The device's emotion engine recognizes the user's emotions in real time by analyzing the user's facial expressions and voice data to detect their emotional state.

[0246] Step 10:

[0247] The server receives the user's emotional data sent from the emotion engine and analyzes the user's emotional state, such as whether they are excited or relaxed.

[0248] Step 11:

[0249] The server adjusts the simulation based on the emotional data, for example, displaying detailed simulation results if the user is excited, or summarizing the results if the user is stressed.

[0250] Step 12:

[0251] The server simulates a scenario based on the conditions set by the user. AI agents interact with each other within the virtual environment, driving the simulation forward.

[0252] Step 13:

[0253] The server analyzes the simulation results and extracts key events and achievements, such as the outcome of a battle simulation and the resource consumption rate.

[0254] Step 14:

[0255] The server sends the simulation results to the user's device, where the user can view the results through detailed reports and graphs to help guide decision-making.

[0256] Step 15:

[0257] The device provides recommended scenarios and parameter settings based on the user's emotional state: for example, if the user is relaxed, it recommends a more difficult scenario, and if the user is nervous, it recommends an easier scenario.

[0258] Example 2

[0259] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0260] Conventional historical simulation systems have the problem of only providing uniform results and operation methods without considering the user's emotions. This often results in a lack of consistency in the user's experience, leading to low satisfaction. The present invention aims to provide a more personalized experience by analyzing the user's emotions in real time and dynamically adjusting the simulation based on the results.

[0261] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0262] In this invention, the server includes means for collecting historical data from a data source, means for analyzing and tagging the collected historical data, means for training an artificial intelligence model based on the tagged historical data, means for constructing a virtual environment using the trained artificial intelligence model, means for accepting input from a user terminal and executing a simulation, means for analyzing user emotion data, means for adjusting the simulation based on the analyzed emotion data, means for providing recommended scenario and parameter settings based on the analyzed emotion data, and means for analyzing the simulation results and providing them to the user terminal, thereby enabling a flexible and personalized simulation experience that corresponds to the user's emotions.

[0263] "Data Source" means a source for collecting historical data used to provide reliable information.

[0264] "Historical data" is data that contains detailed information about events, people, places, etc. that occurred in the past.

[0265] "Tagging" is the process of assigning specific labels or keywords to data to make it easier to classify and search.

[0266] An "artificial intelligence model" is a program that uses algorithms and computational tools to learn from large amounts of data and perform specific tasks.

[0267] A "virtual environment" is an artificial space generated by computer simulation that mimics the real world.

[0268] A "user terminal" is a device such as a computer or smartphone that a user uses to perform operations or input data.

[0269] "Emotion data" is data that indicates the emotional state of the user, analyzed from facial expressions, voice, and the like.

[0270] "Simulation" is a computational process that recreates real-world events or processes in a virtual environment.

[0271] "Recommended settings" are optimal scenarios and parameter settings suggested by the system based on the user's feelings and situation.

[0272] "Analysis" is the process of examining information in detail to understand meaning and patterns.

[0273] MODE FOR CARRYING OUT THE INVENTION

[0274] The present invention relates to a system that recognizes a user's emotions and dynamically adjusts a simulation based on the emotions. The following describes how the system can be implemented.

[0275] The server first collects historical data from data sources. Data collection is performed using APIs and web scraping techniques to gather the necessary data from official archives, historical documents, online databases, etc. The collected data is then stored in a local database. Specifically, Python's BeautifulSoup and Scrapy are used.

[0276] The server then cleanses the collected data, removing duplicates and missing data. It then uses Natural Language Processing (NLP) techniques to analyze the data and identify important events and people. This stage involves data preprocessing using the Pandas library and text tagging using NLTK or spaCy. The tagged data is then converted into a format suitable for training artificial intelligence models.

[0277] The server then uses the formatted data to train an artificial intelligence model, using TensorFlow or PyTorch to apply machine learning algorithms and deep learning techniques to learn the behavioral patterns of each historical event and person. The trained model is then evaluated and optimized.

[0278] Using the trained AI model, the server builds a virtual environment called the "History Sandbox," which is meticulously designed using Unity or Unreal Engine and populated with AI agents. These agents interact with each other to advance the simulation.

[0279] Users can access the "History Sandbox" using their devices. They select a specific scenario from a list of scenarios and customize the simulation settings and parameters. For example, they can select the "Napoleonic Wars" scenario and set conditions such as the number of troops and weather. The user interface is provided via a web browser or a dedicated app.

[0280] During the simulation, the server advances the simulation based on the user's input conditions. To collect user emotion data, the device is equipped with an emotion engine that analyzes the user's emotions in real time using a camera and microphone. This analysis is performed using OpenCV or Azure® Cognitive Services.

[0281] Based on the analyzed emotional data, the server dynamically adjusts the simulation. For example, if the user is excited, it displays detailed results and offers many tactical options. On the other hand, if the user is stressed, it displays concise results. It also recommends appropriate scenarios and parameter settings based on the emotional data. For example, if the user is relaxed, it recommends more difficult scenarios and more complex conditions.

[0282] Here are some examples of specific prompts:

[0283] "Write a Python program that recommends settings for a strategy game scenario based on the user's emotional data. Specifically, implement logic to display detailed simulation results if the user is having fun, and a concise summary of the results if the user is stressed."

[0284] The above is an embodiment of the present invention, which makes it possible to provide a flexible and personalized simulation experience that responds to the user's emotions.

[0285] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0286] Step 1:

[0287] The server collects historical data from multiple reliable data sources. It receives API endpoints and website URLs as input, and stores the collected data in a local database as output. Specifically, the server uses Python's BeautifulSoup and Scrapy to retrieve data via APIs and perform web scraping.

[0288] Step 2:

[0289] The server cleanses the collected data. As input, it takes the raw data stored in the local database and as output, it obtains cleansed data from which duplicates and missing data have been removed. Specifically, the server preprocesses the data using the Pandas library.

[0290] Step 3:

[0291] The server parses the cleansed data and identifies important events and people. It takes the cleansed data as input and the tagged data as output. Specifically, the server uses NLTK or spaCy to parse the text data and assigns appropriate tags to each data point.

[0292] Step 4:

[0293] The server uses the tagged data to train an artificial intelligence model. It takes the tagged data as input and produces a trained AI model as output. Specifically, the server uses TensorFlow or PyTorch to build and train machine learning algorithms and deep learning models.

[0294] Step 5:

[0295] The server uses the trained AI model to build a virtual environment called the "History Sandbox." The trained AI model is taken as input, and the virtual environment is generated as output. Specifically, the server uses Unity or Unreal Engine to perform 3D modeling and place AI agents.

[0296] Step 6:

[0297] The user accesses the "History Sandbox" using a terminal and sets the scenario and parameters. As input, a list of scenarios and configurable parameters is obtained, and as output, the scenario selected by the user and customized parameters are obtained. In concrete terms, the user accesses the server using a web browser or a dedicated app and operates the interface.

[0298] Step 7:

[0299] The server runs the simulation based on the user's settings. It takes the user's selected scenario and customized parameters as input and generates the simulation results as output. The specific behavior is that AI agents act while influencing each other in the virtual space.

[0300] Step 8:

[0301] The device uses a camera and microphone to collect user emotional data. The input is the user's facial expressions and voice, and the output is analyzed emotional data. Specifically, the device performs real-time emotional analysis using OpenCV or Azure Cognitive Services.

[0302] Step 9:

[0303] The server adjusts the simulation based on the analyzed emotional data. It takes the user's emotional data as input and generates adjusted simulation results as output. Specifically, it displays detailed results if the user is excited, and summarizes the results briefly if the user is stressed.

[0304] Step 10:

[0305] The device provides recommended scenarios and parameter settings based on the analyzed emotional data. It receives emotional data as input and provides recommended scenarios and parameters as output. Specifically, it recommends a high-difficulty scenario if the user is relaxed, and an easy scenario if the user is tense.

[0306] The above is the specific processing flow of this system.

[0307] (Application example 2)

[0308] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0309] Conventional content delivery systems provide content without considering the user's emotional state, resulting in insufficient personalization of user interactions and difficulty in improving user satisfaction. Furthermore, the lack of technology to dynamically adjust content based on the user's emotions in real time makes it difficult to provide services that meet individual needs.

[0310] The identification processing by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting information data from a data source, means for analyzing and tagging the collected information data, means for training an artificial intelligence model based on the tagged information data, means for constructing a virtual environment using the trained artificial intelligence model, means for accepting input from a user terminal and executing a simulation, means for analyzing the simulation results and providing them to the user terminal, means for collecting user emotion data and analyzing it with an emotion engine, and means for dynamically adjusting the simulation and content based on the emotion data. This enables personalized content delivery based on the user's emotional state, which is expected to improve user satisfaction.

[0311] "Data sources" are the various information sources that the system uses to gather information.

[0312] "Information Data" means historical, statistical, or other type of data obtained from a data source.

[0313] "Analysis" is the process of processing collected information data and extracting specific meanings and patterns.

[0314] "Tagging" is the process of adding metadata and identifying information to analyzed data.

[0315] An "artificial intelligence model" is a computational model that learns from data and makes predictions and distinctions.

[0316] "Training" is the learning process of providing an artificial intelligence model with the necessary data to improve the accuracy of its predictions and identification.

[0317] A "virtual environment" is a simulated environment generated by a computer program with which humans can interact.

[0318] A "user terminal" is a device (e.g., smartphone, PC, tablet, etc.) that a user uses to perform operations or input data.

[0319] "Simulation" is a technology that reproduces real-world phenomena and processes on a computer and performs analysis and predictions.

[0320] "Emotion data" is information about emotions obtained from the user's facial expressions, voice, etc.

[0321] An "emotion engine" is an algorithm or program that analyzes collected emotion data and identifies the user's emotional state.

[0322] "Dynamic adjustment" refers to the process of changing in response to real-time conditions.

[0323] The present invention relates to a system for recognizing user emotions and dynamically adjusting content delivery based on the emotion data. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS ... will be described in detail below.

[0324] System Overview

[0325] The system consists of a server, a user terminal, and an emotion engine. The server performs processes such as data collection and analysis, training of artificial intelligence models, and construction of virtual environments. The user terminal serves as the user's interface, collecting emotion data and displaying simulation results. The emotion engine analyzes the user's emotions and provides feedback to the system.

[0326] Hardware and software used

[0327] Hardware: Smartphones, smart glasses, head-mounted displays

[0328] Software: OpenCV (facial expression analysis), Google® Cloud Speech-to-Text (voice analysis), TensorFlow and Keras (AI model training), Unity and Unreal Engine (virtual environment construction), AWS® or Google Cloud Platform (server)

[0329] Program Overview

[0330] The server collects, analyzes, and tags information data from data sources. It then uses the tagged data to train an artificial intelligence model and uses this model to build a virtual environment. The user device collects the user's emotion data through a camera and microphone and analyzes the data through an emotion engine. Based on the data analyzed by the emotion engine, the server dynamically adjusts the simulation and provides the results to the user device.

[0331] Specific examples

[0332] For example, while a user is watching a drama series, the system uses the smartphone's camera and microphone to collect the user's facial expressions and voice in real time. The collected data is analyzed using OpenCV and Google Cloud Speech-to-Text, and the emotional engine identifies the user's emotional state. Based on the identified emotional state, the server dynamically adjusts the viewing content and even suggests related content recommendations. This process allows users to seamlessly enjoy content that matches their emotions.

[0333] Prompt Sentence Examples

[0334] "Recommend what content to watch next based on user sentiment data and viewing history."

[0335] As a result, a system built on the basis of the present invention realizes personalized content delivery to increase user engagement.

[0336] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0337] Step 1:

[0338] The server collects information data from data sources. Specifically, it retrieves data from databases and online repositories using APIs and web scraping techniques. The input is information data from external data sources, and the output is the collected information data.

[0339] Step 2:

[0340] The server analyzes and tags the collected information data. Specifically, it performs data cleansing to remove duplicate and missing data. It then uses NLP technology to extract important information and assign appropriate tags. The input is the collected information data, and the output is the analyzed and tagged data.

[0341] Step 3:

[0342] The server uses the tagged data to train an AI model. Specifically, it uses TensorFlow and Keras to feed the data and apply machine learning algorithms to train the model. The input is the parsed and tagged data, and the output is the trained AI model.

[0343] Step 4:

[0344] The server uses a trained AI model to build a virtual environment. Specifically, it uses Unity or Unreal Engine for 3D modeling and designs the virtual space in detail. The input is the trained AI model, and the output is the constructed virtual environment.

[0345] Step 5:

[0346] The device uses a camera and microphone to collect the user's emotional data in real time. The collected data is analyzed by an emotion engine to identify the user's emotional state. The input is the user's facial and voice data, and the output is the analyzed emotional data.

[0347] Step 6:

[0348] The server receives the user's emotional data analyzed by the emotion engine, runs the simulation, and dynamically adjusts the results. This includes displaying the simulation results in detail and recommending the next content to watch according to the user's emotions. The input is the analyzed emotional data and the virtual environment, and the output is the dynamically adjusted simulation results.

[0349] Step 7:

[0350] The terminal provides the user with the simulation results and content recommendations received from the server, providing visual and auditory feedback to help the user decide on their next action. The input is the dynamically adjusted simulation results, and the output is feedback to the user.

[0351] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0352] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0353] In the above embodiment, an example in which the specific process is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0354] [Second embodiment]

[0355] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0356] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0357] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0358] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0359] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0360] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0361] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0362] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0363] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0364] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0365] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0366] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal."

[0367] MODE FOR CARRYING OUT THE INVENTION

[0368] The present invention relates to a system for collecting and analyzing historical data and performing simulations based on the collected data, and the method for implementing the system will be described below.

[0369] 1. Data Collection

[0370] The server collects historical data from multiple reliable data sources, such as official government archives, historical documents, and databases, using APIs and web scraping techniques, and stores the collected data in a local database.

[0371] 2. Data formatting and analysis

[0372] The server cleanses the collected data, removing duplicates and missing data. It then analyzes the data using natural language processing (NLP) techniques to identify important events and people. Identified information is tagged with appropriate tags and the data is converted into a format suitable for training artificial intelligence models.

[0373] 3. Training the AI ​​model

[0374] The server uses the formatted data to train an artificial intelligence model. Specifically, it uses machine learning algorithms and deep learning techniques to learn the behavioral patterns of each historical event and person. The trained model's performance is evaluated, and parameters are optimized as needed.

[0375] 4. Building a virtual environment

[0376] The server uses the trained AI model to build a virtual environment ("History Sandbox"), a virtual space for recreating historical scenarios, designed in detail using 3D modeling tools. Trained AI agents are placed within this environment, interacting with each other to progress the simulation.

[0377] 5. User Interaction

[0378] Users access the "History Sandbox" using a terminal. They select a specific scenario from a list of scenarios and customize the simulation settings and parameters. For example, they can select the "Napoleonic Wars" scenario and set conditions such as the number of troops and weather.

[0379] 6. Running the simulation and providing the results

[0380] The server simulates a scenario based on the conditions set by the user. During this simulation, AI agents act based on their respective roles and interact with each other. After the simulation is complete, the server analyzes the results and extracts key events and performance data. The results are sent to the user's device, where they can view the results through detailed reports and graphs.

[0381] Specific examples

[0382] 1. World War II simulation

[0383] Users access the "History Sandbox" on their devices and select a World War II scenario. They set parameters such as the German army's advance speed and the Allied forces' reaction time. The server then runs the simulation and analyzes several strategic options. Simulation results, such as each country's strategic success rate and resource consumption, are provided to the user.

[0384] 2. Marketing strategy verification

[0385] Management simulates current market conditions based on historical marketing data. For example, they analyze data extracted from past successes and failures to train an AI model. They then use the trained model to simulate new product launch scenarios. As a result, product demand forecasts and competitor responses are analyzed, providing management with the information they need to make more accurate decisions.

[0386] In this way, by utilizing advanced simulation technology, the present invention makes it possible to predict the future based on historical data, becoming a powerful tool that enables users and companies to make quick and accurate decisions.

[0387] The processing flow will be explained below.

[0388] Step 1:

[0389] The server collects historical data from data sources, such as official archives, historical documents, and online databases, using APIs and web scraping techniques, and stores the collected data in a local database.

[0390] Step 2:

[0391] The server cleanses the collected data. During the cleansing process, duplicate data and missing data are removed to ensure data integrity. The cleansed data is then passed on to the next analysis step.

[0392] Step 3:

[0393] The server analyzes the data using natural language processing (NLP) techniques, such as segmenting the text data into words, tagging parts of speech, and extracting named entities to identify important events and people.

[0394] Step 4:

[0395] The server then tags the parsed data, for example, by adding appropriate tags based on specific eras, locations, or characters, and structuring the data.

[0396] Step 5:

[0397] The server uses the tagged data to train an artificial intelligence model, using machine learning algorithms and deep learning techniques to learn the behavioral patterns of each historical event and person.

[0398] Step 6:

[0399] The server evaluates the performance of the trained AI model, using metrics such as precision, recall, and F1 score, and optimizes the model parameters as needed.

[0400] Step 7:

[0401] The server uses trained artificial intelligence models to build a virtual environment (the "History Sandbox"), which is meticulously designed using 3D modeling tools and serves as a virtual space for recreating historical scenarios.

[0402] Step 8:

[0403] Users access the "History Sandbox" using their devices. They select a specific scenario from a list of scenarios and customize the simulation settings and parameters. For example, they can select the "Napoleonic Wars" scenario and set conditions such as the number of troops and weather.

[0404] Step 9:

[0405] The server simulates a scenario based on the conditions set by the user. AI agents interact with each other within the virtual environment, and the simulation progresses.

[0406] Step 10:

[0407] The server analyzes the simulation results and extracts key events and achievements, such as the outcome of a battle simulation and the resource consumption rate.

[0408] Step 11:

[0409] The server sends the simulation results to the user's device, where they can view the results through detailed reports and graphs, which can be used as a reference for decision-making.

[0410] Example 1

[0411] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0412] Conventional historical simulation systems require a great deal of time and effort to collect, format, and analyze reliable data, and they also have the problem of making it difficult for users to analyze the simulation results in detail.In addition, they lack the flexibility to allow users to customize the simulation content, making it difficult to make highly accurate predictions or analyze a variety of scenarios.

[0413] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0414] In this invention, the server includes means for collecting historical data from a data source, means for formatting and cleansing the collected historical data, means for tagging the cleansed historical data using natural language processing technology, means for training an artificial intelligence model based on the tagged historical data, means for constructing a virtual environment using the trained artificial intelligence model, means for accepting input from a user terminal and customizing simulation settings, means for executing a simulation based on the customized settings, and means for analyzing simulation results and providing them to the user terminal. This enables historical data to be collected and analyzed with high accuracy, allowing users to easily customize simulation content and perform detailed result analysis.

[0415] "Data sources" are sources of historical data and information, such as official government archives, historical documents, and online databases.

[0416] "Means of collection" refers to the methods and technologies used to obtain data using APIs or web scraping technology and store it in a local database on the server.

[0417] "Cleansing methods" refers to methods and techniques used to remove duplicate and missing data from collected data and create an accurate and consistent data set.

[0418] "Natural language processing technology" refers to technology that uses natural language processing (NLP) to analyze text data and identify important events and names of people.

[0419] "Tagging means" refers to the methods and techniques for assigning appropriate tags to analyzed data and organizing the data.

[0420] "Artificial intelligence model" refers to a model created using machine learning algorithms and deep learning techniques to learn from past data and understand patterns and features.

[0421] A "virtual environment" is a simulated space recreated using a trained artificial intelligence model, specifically a virtual space constructed using 3D modeling tools.

[0422] "Means for accepting input from a user terminal" refers to an interface or method for accepting operations such as simulation settings and scenario selection from a user via a terminal.

[0423] "Means for customizing simulation settings" refers to methods and technologies that allow users to change or set simulation conditions and parameters.

[0424] "Means for executing a simulation" refers to methods and techniques for progressing a simulation within a virtual environment based on set conditions.

[0425] "Means for analyzing simulation results" refers to methods and techniques for evaluating the results after the simulation is completed and extracting and analyzing key events, achievements, etc.

[0426] "Means for providing to user terminal" refers to the methods and technologies for displaying and transmitting the analyzed simulation results to the user's terminal so that the user can check and analyze the results.

[0427] The present invention relates to a system for collecting and analyzing historical data and performing simulations based on the collected data. A specific method for implementing the system will be described below.

[0428] The server collects historical data from multiple reliable data sources, including official government archives, historical documents, and online databases. The collected data is retrieved using APIs and web scraping techniques, such as Python's "BeautifulSoup" and "Scrapy."

[0429] The server then formats and cleanses the collected data, using Python's pandas and numpy libraries, to remove duplicates and missing data and create an accurate and consistent dataset.

[0430] The cleansed data is then analyzed using natural language processing (NLP) techniques to identify important events and people's names, using NLP libraries such as spaCy and NLTK, which then tag the data appropriately and convert it into a format suitable for training artificial intelligence models.

[0431] The server uses the formatted data to train an AI model using machine learning algorithms and deep learning techniques, such as deep learning frameworks like TensorFlow and PyTorch. During the training process, the accuracy of the model is evaluated after each epoch and hyperparameters are adjusted as needed. Once the model is fully trained, it is stored in local or cloud storage.

[0432] The server then uses the trained AI model to build a virtual environment. This virtual environment, called a "virtual sandbox," is designed in detail using 3D modeling tools (e.g., Unity or Unreal Engine). Historical terrain, buildings, and characters are recreated in the virtual environment, and AI agents are placed in it. These agents behave based on the behavioral patterns learned by the trained AI model.

[0433] Users access the "virtual sandbox" using their devices. They access the system through a web browser or a dedicated app and select the historical scenario they want to recreate from a list of scenarios. For example, they can choose the "Napoleonic Wars" scenario and customize the number of troops, weather, and other conditions through the interface. This setting information is sent to the server.

[0434] The server simulates a scenario based on the conditions set by the user. During the simulation, multiple AI agents interact with each other. Once the simulation is complete, the server analyzes the results to extract key events and achievements. The analysis includes evaluation indicators of the simulation (success rate, resource consumption, etc.). The generated results are sent to the user's device, where the user can view and save the results through detailed reports and graphs.

[0435] Specific examples

[0436] 1. World War II simulation

[0437] Users access the "virtual sandbox" using their devices and select a World War II scenario. They set parameters such as the German army's advance speed and the Allied forces' reaction time. The server then runs the simulation and analyzes several strategic options. Simulation results, such as each country's strategic success rate and resource depletion, are provided to the user.

[0438] 2. Marketing strategy verification

[0439] Management simulates current market conditions based on historical marketing data. For example, they analyze data extracted from past successes and failures to train an AI model. They then use the trained model to simulate new product launch scenarios. As a result, product demand forecasts and competitor responses are analyzed, providing management with the information they need to make more accurate decisions.

[0440] Prompt Sentence Examples

[0441] "It simulates an early battle scenario from the German-Soviet War of 1941, assessing the speed of German advance and the Soviet defensive response."

[0442] This system collects and analyzes historical data with high accuracy, allowing users to easily customize simulation content and perform detailed analysis of results.

[0443] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0444] Step 1:

[0445] Data collection

[0446] The server collects historical data from multiple reliable data sources. Data sources include official government archives, historical documents, and online databases. The collection method uses APIs and web scraping techniques. For example, Python's "BeautifulSoup" or "Scrapy" is used to obtain data and store it in a local database in JSON format. The input is access information and acquisition conditions for the data source, and the output is the raw data stored in the local database.

[0447] Step 2:

[0448] Data Shaping and Cleansing

[0449] The server formats and cleanses the collected data. Specifically, it uses Python libraries such as "pandas" and "numpy." During cleansing, duplicate and missing data are removed to ensure data consistency. For example, missing values ​​are filled in and duplicate records are deleted. The input is the collected raw data, and the output is the formatted, cleansed data.

[0450] Step 3:

[0451] Data tagging and analysis

[0452] The server analyzes the cleansed data using natural language processing (NLP) techniques. Specifically, it uses NLP libraries such as "spaCy" and "NLTK" to identify important events and people's names. The identified information is then appropriately tagged. The input is the data that has been formatted and cleansed, and the output is the tagged analyzed data.

[0453] Step 4:

[0454] Training an AI model

[0455] The server uses the tagged data to train an artificial intelligence model. Specifically, it uses deep learning frameworks such as TensorFlow and PyTorch to run machine learning algorithms. The training process includes accuracy evaluation after each epoch and tuning of hyperparameters. The input is the tagged analysis data, and the output is a trained AI model.

[0456] Step 5:

[0457] Building a virtual environment

[0458] The server uses the trained AI model to build a virtual environment (virtual sandbox). Specifically, it designs it in detail using 3D modeling tools such as Unity or Unreal Engine. This environment recreates historical terrain, buildings, and characters, and AI agents are placed in it. The input is the trained AI model and the design information for the virtual environment, and the output is the virtual sandbox.

[0459] Step 6:

[0460] Accepting user interactions

[0461] Users access the virtual sandbox using their devices. They access the system through a web browser or a dedicated app and select the historical scenario they want to recreate from a list of scenarios. They then use the interface to customize conditions and parameters (e.g., number of troops, weather, etc.). The input is the user's selection and settings, and the output is the transmission of the settings to the server.

[0462] Step 7:

[0463] Running a simulation and analyzing the results

[0464] The server simulates a scenario based on the conditions set by the user. During the simulation, multiple AI agents interact with each other. When the simulation is complete, the server analyzes the results and extracts key events and achievements. Specifically, it analyzes the simulation's evaluation indicators (success rate, resource consumption, etc.). The input is the user settings and simulation result data, and the output is an analyzed simulation report.

[0465] Step 8:

[0466] Providing results

[0467] The server provides the analyzed simulation results to the user's terminal. The user can view and save the results through detailed reports and graphs. The input is the analyzed simulation report, and the output is the result display on the user's terminal.

[0468] (Application example 1)

[0469] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0470] Modern brick-and-mortar stores require effective customer service and optimized sales strategies. However, traditional methods do not fully utilize past sales data and customer information, making it difficult to make timely decisions. In addition, there are limited means of providing real-time sales forecasts and customer service information, making it difficult for store staff to respond immediately. This can lead to a decline in customer satisfaction and lost sales opportunities.

[0471] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0472] In this invention, the server includes means for collecting historical data from a data source, means for analyzing and tagging the collected historical data, means for training a generative AI model based on the tagged historical data, means for constructing a virtual environment using the trained generative AI model, means for accepting input from a user terminal and executing a simulation, means for providing information useful for customer service in a physical store in real time, and means for analyzing the simulation results and providing them to the user terminal, thereby enabling timely and effective customer service and optimization of sales strategies in physical stores.

[0473] "Data Source" refers to a reliable source or database from which historical data is collected.

[0474] "Historical data" refers to data that contains information about past events or phenomena.

[0475] "Tagging" is the process of adding relevant information to data to make it easier to identify.

[0476] A "generative AI model" is an artificial intelligence model that is trained based on collected and analyzed data.

[0477] "Virtual environment" refers to a virtual simulation environment built using a generative AI model.

[0478] A "user terminal" is a device (such as a smartphone or smart glasses) that a user uses to access the system and perform input and output.

[0479] "Simulation" is the process of virtually recreating real-world phenomena or scenarios.

[0480] A "physical store" is a store that exists physically and where customers can visit in person to purchase products.

[0481] "Customer care" refers to the process of providing service and support to customers.

[0482] 1. Data Collection

[0483] The server collects historical data from reliable data sources, such as official government archives, historical documents, and other databases, using APIs and web scraping techniques, and then stores the collected data in a local database.

[0484] 2. Data analysis and tagging

[0485] The server cleanses the collected historical data, removing missing and duplicate data, then analyzes it using natural language processing (NLP) techniques to identify important events and people, assigning appropriate tags to the identified information, and converting the data into a format suitable for training generative AI models.

[0486] 3. Training the AI ​​model

[0487] The server trains a generative AI model based on the formatted data, using machine learning algorithms and deep learning techniques. The trained model's performance is evaluated, and its parameters are optimized as needed.

[0488] 4. Building a virtual environment

[0489] The server uses the trained generative AI model to create a virtual environment, a virtual space for recreating historical scenarios, such as simulating a physical store using 3D modeling tools.

[0490] 5. User Interaction

[0491] Users access the virtual environment using a device (such as a smartphone or smart glasses). They select a specific scenario and customize the settings and parameters of the simulation. For example, they can set up a simulation to forecast sales based on past sales data.

[0492] 6. Simulation and real-time response

[0493] The server simulates scenarios based on the conditions set by the user. The simulation results are analyzed and displayed in real time on the store staff's smart glasses. This allows staff to take the optimal response based on the customer's past purchase history and sales forecasts.

[0494] Specific examples

[0495] Sales forecasting and product display optimization

[0496] Historical data is analyzed to visualize seasonal sales trends and customer purchasing patterns, and store staff can optimize product displays and inventory management based on sales forecast data obtained in real time through smart glasses.

[0497] Example: Proposing best-selling products according to the season

[0498] Every year before Christmas, the company analyzes which products are selling well and uses that data to make sales forecasts. For example, store staff can see through their smart glasses that "sales of this product increased by 50% during last year's Christmas season."

[0499] Prompt Sentence Examples

[0500] Use historical sales data when forecasting next month's sales. The data should be in the following format and take into account seasonality and trends:

[0501] Features: Date, Season, Historical Sales

[0502] Response variable: future sales

[0503] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0504] Step 1: Data collection

[0505] The server retrieves data from official government archives and historical databases using APIs and web scraping techniques, and stores historical documents and archived data in a local database. The input is information from the data source, and the output is raw data stored in the local database.

[0506] Step 2: Data analysis and cleansing

[0507] The server cleanses the collected data, removing duplicates and missing data. It uses natural language processing (NLP) to analyze the data, identify and tag important events and people. The input is raw data stored in a local database, and the output is cleaned, analyzed data.

[0508] Step 3: Training the generative AI model

[0509] The server uses the cleansed and tagged data to train a generative AI model. It then uses machine learning algorithms and deep learning techniques to optimize the trained model. The input is the cleaned and analyzed data, and the output is a trained generative AI model.

[0510] Step 4: Building the virtual environment

[0511] The server uses the trained generative AI model to create a virtual environment that can recreate historical scenarios or virtual situations within a physical store. The input is the generative AI model, and the output is the virtual environment and scenario data.

[0512] Step 5: Accepting User Input and Setting Up the Simulation

[0513] Users access the virtual environment through their terminals, select specific scenarios, and customize the settings and parameters of the simulation. The input is the user's settings and selections, and the output is the simulation configuration data.

[0514] Step 6: Run the simulation

[0515] The server runs a simulation based on the conditions set by the user. AI agents interact with each other as the simulation progresses within the virtual environment. The input is the simulation setting data, and the output is the simulation result data.

[0516] Step 7: Result analysis and real-time display

[0517] The server analyzes the simulation results and extracts key events and achievements. The analysis results are displayed in real time on smart glasses or devices. The input is the simulation result data, and the output is the analysis results and their display.

[0518] Example operation

[0519] For example, if a user wants to predict sales for the Christmas season, a simulation is performed based on sales data from past Christmas seasons, and the resulting information, such as "Sales of this product increased by 50% during last year's Christmas season," is displayed on the smart glasses.

[0520] Prompt Sentence Examples

[0521] Use historical sales data when forecasting next month's sales. The data should be in the following format and take into account seasonality and trends:

[0522] Features: Date, Season, Historical Sales

[0523] Response variable: future sales

[0524] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0525] MODE FOR CARRYING OUT THE INVENTION

[0526] The present invention relates to a system incorporating an emotion engine that recognizes a user's emotions, and the implementation method thereof will be described below.

[0527] 1. Data Collection

[0528] The server collects historical data from multiple reliable data sources, such as official archives, historical documents, and online databases, using APIs and web scraping techniques, and stores the collected data in a local database.

[0529] 2. Data formatting and analysis

[0530] The server cleanses the collected data, removing duplicates and missing data. It then analyzes the data using natural language processing (NLP) techniques to identify important events and people. Identified information is tagged with appropriate tags and the data is converted into a format suitable for training artificial intelligence models.

[0531] 3. Training the AI ​​model

[0532] The server uses the formatted data to train an artificial intelligence model. Specifically, it uses machine learning algorithms and deep learning techniques to learn the behavioral patterns of each historical event and person. The trained model's performance is evaluated, and parameters are optimized as needed.

[0533] 4. Building a virtual environment

[0534] The server uses the trained AI model to build a virtual environment ("History Sandbox"), a virtual space for recreating historical scenarios, designed in detail using 3D modeling tools. Trained AI agents are placed within this environment, interacting with each other to progress the simulation.

[0535] 5. User Interaction

[0536] Users access the "History Sandbox" using their devices. They select a specific scenario from a list of scenarios and customize the simulation settings and parameters. For example, they can select the "Napoleonic Wars" scenario and set conditions such as the number of troops and weather.

[0537] 6. Running the simulation and providing the results

[0538] The server simulates a scenario based on the conditions set by the user. During this simulation, AI agents act based on their respective roles and interact with each other. After the simulation is complete, the server analyzes the results and extracts key events and performance data. The results are sent to the user's device, where they can view the results through detailed reports and graphs.

[0539] 7. Implementing the Emotion Engine

[0540] The device is equipped with an emotion engine that recognizes the user's emotions in real time and has the ability to analyze emotional data from the user's facial expressions and voice.

[0541] 8. Emotion-based simulation adjustment

[0542] The server receives the user's emotional data analyzed by the emotion engine and adjusts the simulation accordingly. For example, if the user is excited, the simulation results will be displayed in detail, but if the user is stressed, the results will be displayed in a concise summary.

[0543] 9. Emotion-Based Recommendations

[0544] The device provides recommended scenarios and parameter settings based on the user's emotional state. For example, if the user is relaxed, it will recommend a high-difficulty scenario or complex conditions, while if the user is tense, it will recommend an easy scenario.

[0545] Specific examples

[0546] 1. Emotion-based strategic game simulation

[0547] Users access the "History Sandbox" on their devices and select a medieval strategy game scenario. The emotion engine analyzes the user's facial expressions to detect whether they are enjoying the game. The server uses this information to display detailed simulation results and offer a variety of tactical options.

[0548] 2. Emotional feedback simulation of marketing strategies

[0549] Management uses the emotion engine when simulating marketing strategy scenarios. It analyzes the voice data obtained from the device to detect how the user feels about the presentation. The server uses this information to adjust the content of the presentation and provides the final results to management.

[0550] In this way, combining emotion engines enables flexible simulation and interaction according to the user's emotional state. By using emotion data, the present invention can provide a more personalized experience and improve user satisfaction.

[0551] The processing flow will be explained below.

[0552] Step 1:

[0553] The server collects historical data from data sources, such as official archives, historical documents, and online databases, using APIs and web scraping techniques, and stores the data in a local database.

[0554] Step 2:

[0555] The server cleanses the collected data, removing duplicates and missing data to ensure the data is complete and consistent.

[0556] Step 3:

[0557] The server analyzes the data using natural language processing (NLP) techniques, specifically segmenting the text data into words, tagging parts of speech, extracting named entities, and identifying important events and people.

[0558] Step 4:

[0559] The server tags the parsed data, for example, by adding appropriate tags based on specific eras, locations, or characters, and structuring the data.

[0560] Step 5:

[0561] The server uses the tagged data to train an artificial intelligence model, using machine learning algorithms and deep learning techniques to learn the behavioral patterns of each historical event and person.

[0562] Step 6:

[0563] The server evaluates the performance of the trained AI model, using precision, recall, and F1 score as evaluation metrics, and optimizes the model parameters as needed.

[0564] Step 7:

[0565] The server uses trained artificial intelligence models to build virtual environments ("History Sandbox"), which are then detailed using 3D modeling tools to create virtual spaces for recreating historical scenarios.

[0566] Step 8:

[0567] Users access the "History Sandbox" using a device, where they can select a specific scenario from a list of scenarios and customize the simulation settings and parameters. For example, they can select the "Napoleonic Wars" scenario and set the number of troops and weather conditions.

[0568] Step 9:

[0569] The device's emotion engine recognizes the user's emotions in real time by analyzing the user's facial expressions and voice data to detect their emotional state.

[0570] Step 10:

[0571] The server receives the user's emotional data sent from the emotion engine and analyzes the user's emotional state, such as whether they are excited or relaxed.

[0572] Step 11:

[0573] The server adjusts the simulation based on the emotional data, for example, displaying detailed simulation results if the user is excited, or summarizing the results if the user is stressed.

[0574] Step 12:

[0575] The server simulates a scenario based on the conditions set by the user. AI agents interact with each other within the virtual environment, driving the simulation forward.

[0576] Step 13:

[0577] The server analyzes the simulation results and extracts key events and achievements, such as the outcome of a battle simulation and the resource consumption rate.

[0578] Step 14:

[0579] The server sends the simulation results to the user's device, where the user can view the results through detailed reports and graphs to help guide decision-making.

[0580] Step 15:

[0581] The device provides recommended scenarios and parameter settings based on the user's emotional state: for example, if the user is relaxed, it recommends a more difficult scenario, and if the user is nervous, it recommends an easier scenario.

[0582] Example 2

[0583] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0584] Conventional historical simulation systems have the problem of only providing uniform results and operation methods without considering the user's emotions. This often results in a lack of consistency in the user's experience, leading to low satisfaction. The present invention aims to provide a more personalized experience by analyzing the user's emotions in real time and dynamically adjusting the simulation based on the results.

[0585] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0586] In this invention, the server includes means for collecting historical data from a data source, means for analyzing and tagging the collected historical data, means for training an artificial intelligence model based on the tagged historical data, means for constructing a virtual environment using the trained artificial intelligence model, means for accepting input from a user terminal and executing a simulation, means for analyzing user emotion data, means for adjusting the simulation based on the analyzed emotion data, means for providing recommended scenario and parameter settings based on the analyzed emotion data, and means for analyzing the simulation results and providing them to the user terminal, thereby enabling a flexible and personalized simulation experience that corresponds to the user's emotions.

[0587] "Data Source" means a source for collecting historical data used to provide reliable information.

[0588] "Historical data" is data that contains detailed information about events, people, places, etc. that occurred in the past.

[0589] "Tagging" is the process of assigning specific labels or keywords to data to make it easier to classify and search.

[0590] An "artificial intelligence model" is a program that uses algorithms and computational tools to learn from large amounts of data and perform specific tasks.

[0591] A "virtual environment" is an artificial space generated by computer simulation that mimics the real world.

[0592] A "user terminal" is a device such as a computer or smartphone that a user uses to perform operations or input data.

[0593] "Emotion data" is data that indicates the emotional state of the user, analyzed from facial expressions, voice, and the like.

[0594] "Simulation" is a computational process that recreates real-world events or processes in a virtual environment.

[0595] "Recommended settings" are optimal scenarios and parameter settings suggested by the system based on the user's feelings and situation.

[0596] "Analysis" is the process of examining information in detail to understand meaning and patterns.

[0597] MODE FOR CARRYING OUT THE INVENTION

[0598] The present invention relates to a system that recognizes a user's emotions and dynamically adjusts a simulation based on the emotions. The following describes how the system can be implemented.

[0599] The server first collects historical data from data sources. Data collection is performed using APIs and web scraping techniques to gather the necessary data from official archives, historical documents, online databases, etc. The collected data is then stored in a local database. Specifically, Python's BeautifulSoup and Scrapy are used.

[0600] The server then cleanses the collected data, removing duplicates and missing data. It then uses Natural Language Processing (NLP) techniques to analyze the data and identify important events and people. This stage involves data preprocessing using the Pandas library and text tagging using NLTK or spaCy. The tagged data is then converted into a format suitable for training artificial intelligence models.

[0601] The server then uses the formatted data to train an artificial intelligence model, using TensorFlow or PyTorch to apply machine learning algorithms and deep learning techniques to learn the behavioral patterns of each historical event and person. The trained model is then evaluated and optimized.

[0602] Using the trained AI model, the server builds a virtual environment called the "History Sandbox," which is meticulously designed using Unity or Unreal Engine and populated with AI agents. These agents interact with each other to advance the simulation.

[0603] Users can access the "History Sandbox" using their devices. They select a specific scenario from a list of scenarios and customize the simulation settings and parameters. For example, they can select the "Napoleonic Wars" scenario and set conditions such as the number of troops and weather. The user interface is provided via a web browser or a dedicated app.

[0604] During the simulation, the server advances the simulation based on the user's input conditions. To collect user emotion data, the device is equipped with an emotion engine that uses the camera and microphone to analyze the user's emotions in real time. This analysis is performed using OpenCV or Azure Cognitive Services.

[0605] Based on the analyzed emotional data, the server dynamically adjusts the simulation. For example, if the user is excited, it displays detailed results and offers many tactical options. On the other hand, if the user is stressed, it displays concise results. It also recommends appropriate scenarios and parameter settings based on the emotional data. For example, if the user is relaxed, it recommends more difficult scenarios and more complex conditions.

[0606] Here are some examples of specific prompts:

[0607] "Write a Python program that recommends settings for a strategy game scenario based on the user's emotional data. Specifically, implement logic to display detailed simulation results if the user is having fun, and a concise summary of the results if the user is stressed."

[0608] The above is an embodiment of the present invention, which makes it possible to provide a flexible and personalized simulation experience that responds to the user's emotions.

[0609] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0610] Step 1:

[0611] The server collects historical data from multiple reliable data sources. It receives API endpoints and website URLs as input, and stores the collected data in a local database as output. Specifically, the server uses Python's BeautifulSoup and Scrapy to retrieve data via APIs and perform web scraping.

[0612] Step 2:

[0613] The server cleanses the collected data. As input, it takes the raw data stored in the local database and as output, it obtains cleansed data from which duplicates and missing data have been removed. Specifically, the server preprocesses the data using the Pandas library.

[0614] Step 3:

[0615] The server parses the cleansed data and identifies important events and people. It takes the cleansed data as input and the tagged data as output. Specifically, the server uses NLTK or spaCy to parse the text data and assigns appropriate tags to each data point.

[0616] Step 4:

[0617] The server uses the tagged data to train an artificial intelligence model. It takes the tagged data as input and produces a trained AI model as output. Specifically, the server uses TensorFlow or PyTorch to build and train machine learning algorithms and deep learning models.

[0618] Step 5:

[0619] The server uses the trained AI model to build a virtual environment called the "History Sandbox." The trained AI model is taken as input, and the virtual environment is generated as output. Specifically, the server uses Unity or Unreal Engine to perform 3D modeling and place AI agents.

[0620] Step 6:

[0621] The user accesses the "History Sandbox" using a terminal and sets the scenario and parameters. As input, a list of scenarios and configurable parameters is obtained, and as output, the scenario selected by the user and customized parameters are obtained. In concrete terms, the user accesses the server using a web browser or a dedicated app and operates the interface.

[0622] Step 7:

[0623] The server runs the simulation based on the user's settings. It takes the user's selected scenario and customized parameters as input and generates the simulation results as output. The specific behavior is that AI agents act while influencing each other in the virtual space.

[0624] Step 8:

[0625] The device uses a camera and microphone to collect user emotional data. The input is the user's facial expressions and voice, and the output is analyzed emotional data. Specifically, the device performs real-time emotional analysis using OpenCV or Azure Cognitive Services.

[0626] Step 9:

[0627] The server adjusts the simulation based on the analyzed emotional data. It takes the user's emotional data as input and generates adjusted simulation results as output. Specifically, it displays detailed results if the user is excited, and summarizes the results briefly if the user is stressed.

[0628] Step 10:

[0629] The device provides recommended scenarios and parameter settings based on the analyzed emotional data. It receives emotional data as input and provides recommended scenarios and parameters as output. Specifically, it recommends a high-difficulty scenario if the user is relaxed, and an easy scenario if the user is tense.

[0630] The above is the specific processing flow of this system.

[0631] (Application example 2)

[0632] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0633] Conventional content delivery systems provide content without considering the user's emotional state, resulting in insufficient personalization of user interactions and difficulty in improving user satisfaction. Furthermore, the lack of technology to dynamically adjust content based on the user's emotions in real time makes it difficult to provide services that meet individual needs.

[0634] The identification processing by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting information data from a data source, means for analyzing and tagging the collected information data, means for training an artificial intelligence model based on the tagged information data, means for constructing a virtual environment using the trained artificial intelligence model, means for accepting input from a user terminal and executing a simulation, means for analyzing the simulation results and providing them to the user terminal, means for collecting user emotion data and analyzing it with an emotion engine, and means for dynamically adjusting the simulation and content based on the emotion data. This enables personalized content delivery based on the user's emotional state, which is expected to improve user satisfaction.

[0635] "Data sources" are the various information sources that the system uses to gather information.

[0636] "Information Data" means historical, statistical, or other type of data obtained from a data source.

[0637] "Analysis" is the process of processing collected information data and extracting specific meanings and patterns.

[0638] "Tagging" is the process of adding metadata and identifying information to analyzed data.

[0639] An "artificial intelligence model" is a computational model that learns from data and makes predictions and distinctions.

[0640] "Training" is the learning process of providing an artificial intelligence model with the necessary data to improve the accuracy of its predictions and identification.

[0641] A "virtual environment" is a simulated environment generated by a computer program with which humans can interact.

[0642] A "user terminal" is a device (e.g., smartphone, PC, tablet, etc.) that a user uses to perform operations or input data.

[0643] "Simulation" is a technology that reproduces real-world phenomena and processes on a computer and performs analysis and predictions.

[0644] "Emotion data" is information about emotions obtained from the user's facial expressions, voice, etc.

[0645] An "emotion engine" is an algorithm or program that analyzes collected emotion data and identifies the user's emotional state.

[0646] "Dynamic adjustment" refers to the process of changing in response to real-time conditions.

[0647] The present invention relates to a system for recognizing user emotions and dynamically adjusting content delivery based on the emotion data. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS ... will be described in detail below.

[0648] System Overview

[0649] The system consists of a server, a user terminal, and an emotion engine. The server performs processes such as data collection and analysis, training of artificial intelligence models, and construction of virtual environments. The user terminal serves as the user's interface, collecting emotion data and displaying simulation results. The emotion engine analyzes the user's emotions and provides feedback to the system.

[0650] Hardware and software used

[0651] Hardware: Smartphones, smart glasses, head-mounted displays

[0652] Software: OpenCV (facial expression analysis), Google Cloud Speech-to-Text (voice analysis), TensorFlow and Keras (AI model training), Unity and Unreal Engine (virtual environment creation), AWS or Google Cloud Platform (server)

[0653] Program Overview

[0654] The server collects, analyzes, and tags information data from data sources. It then uses the tagged data to train an artificial intelligence model and uses this model to build a virtual environment. The user device collects the user's emotion data through a camera and microphone and analyzes the data through an emotion engine. Based on the data analyzed by the emotion engine, the server dynamically adjusts the simulation and provides the results to the user device.

[0655] Specific examples

[0656] For example, while a user is watching a drama series, the system uses the smartphone's camera and microphone to collect the user's facial expressions and voice in real time. The collected data is analyzed using OpenCV and Google Cloud Speech-to-Text, and the emotional engine identifies the user's emotional state. Based on the identified emotional state, the server dynamically adjusts the viewing content and even suggests related content recommendations. This process allows users to seamlessly enjoy content that matches their emotions.

[0657] Prompt Sentence Examples

[0658] "Recommend what content to watch next based on user sentiment data and viewing history."

[0659] As a result, a system built on the basis of the present invention realizes personalized content delivery to increase user engagement.

[0660] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0661] Step 1:

[0662] The server collects information data from data sources. Specifically, it retrieves data from databases and online repositories using APIs and web scraping techniques. The input is information data from external data sources, and the output is the collected information data.

[0663] Step 2:

[0664] The server analyzes and tags the collected information data. Specifically, it performs data cleansing to remove duplicate and missing data. It then uses NLP technology to extract important information and assign appropriate tags. The input is the collected information data, and the output is the analyzed and tagged data.

[0665] Step 3:

[0666] The server uses the tagged data to train an AI model. Specifically, it uses TensorFlow and Keras to feed the data and apply machine learning algorithms to train the model. The input is the parsed and tagged data, and the output is the trained AI model.

[0667] Step 4:

[0668] The server uses a trained AI model to build a virtual environment. Specifically, it uses Unity or Unreal Engine for 3D modeling and designs the virtual space in detail. The input is the trained AI model, and the output is the constructed virtual environment.

[0669] Step 5:

[0670] The device uses a camera and microphone to collect the user's emotional data in real time. The collected data is analyzed by an emotion engine to identify the user's emotional state. The input is the user's facial and voice data, and the output is the analyzed emotional data.

[0671] Step 6:

[0672] The server receives the user's emotional data analyzed by the emotion engine, runs the simulation, and dynamically adjusts the results. This includes displaying the simulation results in detail and recommending the next content to watch according to the user's emotions. The input is the analyzed emotional data and the virtual environment, and the output is the dynamically adjusted simulation results.

[0673] Step 7:

[0674] The terminal provides the user with the simulation results and content recommendations received from the server, providing visual and auditory feedback to help the user decide on their next action. The input is the dynamically adjusted simulation results, and the output is feedback to the user.

[0675] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0676] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0677] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the smart glasses 214.

[0678] [Third embodiment]

[0679] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0680] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0681] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0682] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0683] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0684] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0685] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0686] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0687] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0688] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0689] In the headset type terminal 314, a reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0690] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the headset type terminal 314 will be referred to as the "terminal."

[0691] MODE FOR CARRYING OUT THE INVENTION

[0692] The present invention relates to a system for collecting and analyzing historical data and performing simulations based on the collected data, and the method for implementing the system will be described below.

[0693] 1. Data Collection

[0694] The server collects historical data from multiple reliable data sources, such as official government archives, historical documents, and databases, using APIs and web scraping techniques, and stores the collected data in a local database.

[0695] 2. Data formatting and analysis

[0696] The server cleanses the collected data, removing duplicates and missing data. It then analyzes the data using natural language processing (NLP) techniques to identify important events and people. Identified information is tagged with appropriate tags and the data is converted into a format suitable for training artificial intelligence models.

[0697] 3. Training the AI ​​model

[0698] The server uses the formatted data to train an artificial intelligence model. Specifically, it uses machine learning algorithms and deep learning techniques to learn the behavioral patterns of each historical event and person. The trained model's performance is evaluated, and parameters are optimized as needed.

[0699] 4. Building a virtual environment

[0700] The server uses the trained AI model to build a virtual environment ("History Sandbox"), a virtual space for recreating historical scenarios, designed in detail using 3D modeling tools. Trained AI agents are placed within this environment, interacting with each other to progress the simulation.

[0701] 5. User Interaction

[0702] Users access the "History Sandbox" using a terminal. They select a specific scenario from a list of scenarios and customize the simulation settings and parameters. For example, they can select the "Napoleonic Wars" scenario and set conditions such as the number of troops and weather.

[0703] 6. Running the simulation and providing the results

[0704] The server simulates a scenario based on the conditions set by the user. During this simulation, AI agents act based on their respective roles and interact with each other. After the simulation is complete, the server analyzes the results and extracts key events and performance data. The results are sent to the user's device, where they can view the results through detailed reports and graphs.

[0705] Specific examples

[0706] 1. World War II simulation

[0707] Users access the "History Sandbox" on their devices and select a World War II scenario. They set parameters such as the German army's advance speed and the Allied forces' reaction time. The server then runs the simulation and analyzes several strategic options. Simulation results, such as each country's strategic success rate and resource consumption, are provided to the user.

[0708] 2. Marketing strategy verification

[0709] Management simulates current market conditions based on historical marketing data. For example, they analyze data extracted from past successes and failures to train an AI model. They then use the trained model to simulate new product launch scenarios. As a result, product demand forecasts and competitor responses are analyzed, providing management with the information they need to make more accurate decisions.

[0710] In this way, by utilizing advanced simulation technology, the present invention makes it possible to predict the future based on historical data, becoming a powerful tool that enables users and companies to make quick and accurate decisions.

[0711] The processing flow will be explained below.

[0712] Step 1:

[0713] The server collects historical data from data sources, such as official archives, historical documents, and online databases, using APIs and web scraping techniques, and stores the collected data in a local database.

[0714] Step 2:

[0715] The server cleanses the collected data. During the cleansing process, duplicate data and missing data are removed to ensure data integrity. The cleansed data is then passed on to the next analysis step.

[0716] Step 3:

[0717] The server analyzes the data using natural language processing (NLP) techniques, such as segmenting the text data into words, tagging parts of speech, and extracting named entities to identify important events and people.

[0718] Step 4:

[0719] The server then tags the parsed data, for example, by adding appropriate tags based on specific eras, locations, or characters, and structuring the data.

[0720] Step 5:

[0721] The server uses the tagged data to train an artificial intelligence model, using machine learning algorithms and deep learning techniques to learn the behavioral patterns of each historical event and person.

[0722] Step 6:

[0723] The server evaluates the performance of the trained AI model, using metrics such as precision, recall, and F1 score, and optimizes the model parameters as needed.

[0724] Step 7:

[0725] The server uses trained artificial intelligence models to build a virtual environment (the "History Sandbox"), which is meticulously designed using 3D modeling tools and serves as a virtual space for recreating historical scenarios.

[0726] Step 8:

[0727] Users access the "History Sandbox" using their devices. They select a specific scenario from a list of scenarios and customize the simulation settings and parameters. For example, they can select the "Napoleonic Wars" scenario and set conditions such as the number of troops and weather.

[0728] Step 9:

[0729] The server simulates a scenario based on the conditions set by the user. AI agents interact with each other within the virtual environment, and the simulation progresses.

[0730] Step 10:

[0731] The server analyzes the simulation results and extracts key events and achievements, such as the outcome of a battle simulation and the resource consumption rate.

[0732] Step 11:

[0733] The server sends the simulation results to the user's device, where they can view the results through detailed reports and graphs, which can be used as a reference for decision-making.

[0734] Example 1

[0735] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0736] Conventional historical simulation systems require a great deal of time and effort to collect, format, and analyze reliable data, and they also have the problem of making it difficult for users to analyze the simulation results in detail.In addition, they lack the flexibility to allow users to customize the simulation content, making it difficult to make highly accurate predictions or analyze a variety of scenarios.

[0737] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0738] In this invention, the server includes means for collecting historical data from a data source, means for formatting and cleansing the collected historical data, means for tagging the cleansed historical data using natural language processing technology, means for training an artificial intelligence model based on the tagged historical data, means for constructing a virtual environment using the trained artificial intelligence model, means for accepting input from a user terminal and customizing simulation settings, means for executing a simulation based on the customized settings, and means for analyzing simulation results and providing them to the user terminal. This enables historical data to be collected and analyzed with high accuracy, allowing users to easily customize simulation content and perform detailed result analysis.

[0739] "Data sources" are sources of historical data and information, such as official government archives, historical documents, and online databases.

[0740] "Means of collection" refers to the methods and technologies used to obtain data using APIs or web scraping technology and store it in a local database on the server.

[0741] "Cleansing methods" refers to methods and techniques used to remove duplicate and missing data from collected data and create an accurate and consistent data set.

[0742] "Natural language processing technology" refers to technology that uses natural language processing (NLP) to analyze text data and identify important events and names of people.

[0743] "Tagging means" refers to the methods and techniques for assigning appropriate tags to analyzed data and organizing the data.

[0744] "Artificial intelligence model" refers to a model created using machine learning algorithms and deep learning techniques to learn from past data and understand patterns and features.

[0745] A "virtual environment" is a simulated space recreated using a trained artificial intelligence model, specifically a virtual space constructed using 3D modeling tools.

[0746] "Means for accepting input from a user terminal" refers to an interface or method for accepting operations such as simulation settings and scenario selection from a user via a terminal.

[0747] "Means for customizing simulation settings" refers to methods and technologies that allow users to change or set simulation conditions and parameters.

[0748] "Means for executing a simulation" refers to methods and techniques for progressing a simulation within a virtual environment based on set conditions.

[0749] "Means for analyzing simulation results" refers to methods and techniques for evaluating the results after the simulation is completed and extracting and analyzing key events, achievements, etc.

[0750] "Means for providing to user terminal" refers to the methods and technologies for displaying and transmitting the analyzed simulation results to the user's terminal so that the user can check and analyze the results.

[0751] The present invention relates to a system for collecting and analyzing historical data and performing simulations based on the collected data. A specific method for implementing the system will be described below.

[0752] The server collects historical data from multiple reliable data sources, including official government archives, historical documents, and online databases. The collected data is retrieved using APIs and web scraping techniques, such as Python's "BeautifulSoup" and "Scrapy."

[0753] The server then formats and cleanses the collected data, using Python's pandas and numpy libraries, to remove duplicates and missing data and create an accurate and consistent dataset.

[0754] The cleansed data is then analyzed using natural language processing (NLP) techniques to identify important events and people's names, using NLP libraries such as spaCy and NLTK, which then tag the data appropriately and convert it into a format suitable for training artificial intelligence models.

[0755] The server uses the formatted data to train an AI model using machine learning algorithms and deep learning techniques, such as deep learning frameworks like TensorFlow and PyTorch. During the training process, the accuracy of the model is evaluated after each epoch and hyperparameters are adjusted as needed. Once the model is fully trained, it is stored in local or cloud storage.

[0756] The server then uses the trained AI model to build a virtual environment. This virtual environment, called a "virtual sandbox," is designed in detail using 3D modeling tools (e.g., Unity or Unreal Engine). Historical terrain, buildings, and characters are recreated in the virtual environment, and AI agents are placed in it. These agents behave based on the behavioral patterns learned by the trained AI model.

[0757] Users access the "virtual sandbox" using their devices. They access the system through a web browser or a dedicated app and select the historical scenario they want to recreate from a list of scenarios. For example, they can choose the "Napoleonic Wars" scenario and customize the number of troops, weather, and other conditions through the interface. This setting information is sent to the server.

[0758] The server simulates a scenario based on the conditions set by the user. During the simulation, multiple AI agents interact with each other. Once the simulation is complete, the server analyzes the results to extract key events and achievements. The analysis includes evaluation indicators of the simulation (success rate, resource consumption, etc.). The generated results are sent to the user's device, where the user can view and save the results through detailed reports and graphs.

[0759] Specific examples

[0760] 1. World War II simulation

[0761] Users access the "virtual sandbox" using their devices and select a World War II scenario. They set parameters such as the German army's advance speed and the Allied forces' reaction time. The server then runs the simulation and analyzes several strategic options. Simulation results, such as each country's strategic success rate and resource depletion, are provided to the user.

[0762] 2. Marketing strategy verification

[0763] Management simulates current market conditions based on historical marketing data. For example, they analyze data extracted from past successes and failures to train an AI model. They then use the trained model to simulate new product launch scenarios. As a result, product demand forecasts and competitor responses are analyzed, providing management with the information they need to make more accurate decisions.

[0764] Prompt Sentence Examples

[0765] "It simulates an early battle scenario from the German-Soviet War of 1941, assessing the speed of German advance and the Soviet defensive response."

[0766] This system collects and analyzes historical data with high accuracy, allowing users to easily customize simulation content and perform detailed analysis of results.

[0767] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0768] Step 1:

[0769] Data collection

[0770] The server collects historical data from multiple reliable data sources. Data sources include official government archives, historical documents, and online databases. The collection method uses APIs and web scraping techniques. For example, Python's "BeautifulSoup" or "Scrapy" is used to obtain data and store it in a local database in JSON format. The input is access information and acquisition conditions for the data source, and the output is the raw data stored in the local database.

[0771] Step 2:

[0772] Data Shaping and Cleansing

[0773] The server formats and cleanses the collected data. Specifically, it uses Python libraries such as "pandas" and "numpy." During cleansing, duplicate and missing data are removed to ensure data consistency. For example, missing values ​​are filled in and duplicate records are deleted. The input is the collected raw data, and the output is the formatted, cleansed data.

[0774] Step 3:

[0775] Data tagging and analysis

[0776] The server analyzes the cleansed data using natural language processing (NLP) techniques. Specifically, it uses NLP libraries such as "spaCy" and "NLTK" to identify important events and people's names. The identified information is then appropriately tagged. The input is the data that has been formatted and cleansed, and the output is the tagged analyzed data.

[0777] Step 4:

[0778] Training an AI model

[0779] The server uses the tagged data to train an artificial intelligence model. Specifically, it uses deep learning frameworks such as TensorFlow and PyTorch to run machine learning algorithms. The training process includes accuracy evaluation after each epoch and tuning of hyperparameters. The input is the tagged analysis data, and the output is a trained AI model.

[0780] Step 5:

[0781] Building a virtual environment

[0782] The server uses the trained AI model to build a virtual environment (virtual sandbox). Specifically, it designs it in detail using 3D modeling tools such as Unity or Unreal Engine. This environment recreates historical terrain, buildings, and characters, and AI agents are placed in it. The input is the trained AI model and the design information for the virtual environment, and the output is the virtual sandbox.

[0783] Step 6:

[0784] Accepting user interactions

[0785] Users access the virtual sandbox using their devices. They access the system through a web browser or a dedicated app and select the historical scenario they want to recreate from a list of scenarios. They then use the interface to customize conditions and parameters (e.g., number of troops, weather, etc.). The input is the user's selection and settings, and the output is the transmission of the settings to the server.

[0786] Step 7:

[0787] Running a simulation and analyzing the results

[0788] The server simulates a scenario based on the conditions set by the user. During the simulation, multiple AI agents interact with each other. When the simulation is complete, the server analyzes the results and extracts key events and achievements. Specifically, it analyzes the simulation's evaluation indicators (success rate, resource consumption, etc.). The input is the user settings and simulation result data, and the output is an analyzed simulation report.

[0789] Step 8:

[0790] Providing results

[0791] The server provides the analyzed simulation results to the user's terminal. The user can view and save the results through detailed reports and graphs. The input is the analyzed simulation report, and the output is the result display on the user's terminal.

[0792] (Application example 1)

[0793] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0794] Modern brick-and-mortar stores require effective customer service and optimized sales strategies. However, traditional methods do not fully utilize past sales data and customer information, making it difficult to make timely decisions. In addition, there are limited means of providing real-time sales forecasts and customer service information, making it difficult for store staff to respond immediately. This can lead to a decline in customer satisfaction and lost sales opportunities.

[0795] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0796] In this invention, the server includes means for collecting historical data from a data source, means for analyzing and tagging the collected historical data, means for training a generative AI model based on the tagged historical data, means for constructing a virtual environment using the trained generative AI model, means for accepting input from a user terminal and executing a simulation, means for providing information useful for customer service in a physical store in real time, and means for analyzing the simulation results and providing them to the user terminal, thereby enabling timely and effective customer service and optimization of sales strategies in physical stores.

[0797] "Data Source" refers to a reliable source or database from which historical data is collected.

[0798] "Historical data" refers to data that contains information about past events or phenomena.

[0799] "Tagging" is the process of adding relevant information to data to make it easier to identify.

[0800] A "generative AI model" is an artificial intelligence model that is trained based on collected and analyzed data.

[0801] "Virtual environment" refers to a virtual simulation environment built using a generative AI model.

[0802] A "user terminal" is a device (such as a smartphone or smart glasses) that a user uses to access the system and perform input and output.

[0803] "Simulation" is the process of virtually recreating real-world phenomena or scenarios.

[0804] A "physical store" is a store that exists physically and where customers can visit in person to purchase products.

[0805] "Customer care" refers to the process of providing service and support to customers.

[0806] 1. Data Collection

[0807] The server collects historical data from reliable data sources, such as official government archives, historical documents, and other databases, using APIs and web scraping techniques, and then stores the collected data in a local database.

[0808] 2. Data analysis and tagging

[0809] The server cleanses the collected historical data, removing missing and duplicate data, then analyzes it using natural language processing (NLP) techniques to identify important events and people, assigning appropriate tags to the identified information, and converting the data into a format suitable for training generative AI models.

[0810] 3. Training the AI ​​model

[0811] The server trains a generative AI model based on the formatted data, using machine learning algorithms and deep learning techniques. The trained model's performance is evaluated, and its parameters are optimized as needed.

[0812] 4. Building a virtual environment

[0813] The server uses the trained generative AI model to create a virtual environment, a virtual space for recreating historical scenarios, such as simulating a physical store using 3D modeling tools.

[0814] 5. User Interaction

[0815] Users access the virtual environment using a device (such as a smartphone or smart glasses). They select a specific scenario and customize the settings and parameters of the simulation. For example, they can set up a simulation to forecast sales based on past sales data.

[0816] 6. Simulation and real-time response

[0817] The server simulates scenarios based on the conditions set by the user. The simulation results are analyzed and displayed in real time on the store staff's smart glasses. This allows staff to take the optimal response based on the customer's past purchase history and sales forecasts.

[0818] Specific examples

[0819] Sales forecasting and product display optimization

[0820] Historical data is analyzed to visualize seasonal sales trends and customer purchasing patterns, and store staff can optimize product displays and inventory management based on sales forecast data obtained in real time through smart glasses.

[0821] Example: Proposing best-selling products according to the season

[0822] Every year before Christmas, the company analyzes which products are selling well and uses that data to make sales forecasts. For example, store staff can see through their smart glasses that "sales of this product increased by 50% during last year's Christmas season."

[0823] Prompt Sentence Examples

[0824] Use historical sales data when forecasting next month's sales. The data should be in the following format and take into account seasonality and trends:

[0825] Features: Date, Season, Historical Sales

[0826] Response variable: future sales

[0827] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0828] Step 1: Data collection

[0829] The server retrieves data from official government archives and historical databases using APIs and web scraping techniques, and stores historical documents and archived data in a local database. The input is information from the data source, and the output is raw data stored in the local database.

[0830] Step 2: Data analysis and cleansing

[0831] The server cleanses the collected data, removing duplicates and missing data. It uses natural language processing (NLP) to analyze the data, identify and tag important events and people. The input is raw data stored in a local database, and the output is cleaned, analyzed data.

[0832] Step 3: Training the generative AI model

[0833] The server uses the cleansed and tagged data to train a generative AI model. It then uses machine learning algorithms and deep learning techniques to optimize the trained model. The input is the cleaned and analyzed data, and the output is a trained generative AI model.

[0834] Step 4: Building the virtual environment

[0835] The server uses the trained generative AI model to create a virtual environment that can recreate historical scenarios or virtual situations within a physical store. The input is the generative AI model, and the output is the virtual environment and scenario data.

[0836] Step 5: Accepting User Input and Setting Up the Simulation

[0837] Users access the virtual environment through their terminals, select specific scenarios, and customize the settings and parameters of the simulation. The input is the user's settings and selections, and the output is the simulation configuration data.

[0838] Step 6: Run the simulation

[0839] The server runs a simulation based on the conditions set by the user. AI agents interact with each other as the simulation progresses within the virtual environment. The input is the simulation setting data, and the output is the simulation result data.

[0840] Step 7: Result analysis and real-time display

[0841] The server analyzes the simulation results and extracts key events and achievements. The analysis results are displayed in real time on smart glasses or devices. The input is the simulation result data, and the output is the analysis results and their display.

[0842] Example operation

[0843] For example, if a user wants to predict sales for the Christmas season, a simulation is performed based on sales data from past Christmas seasons, and the resulting information, such as "Sales of this product increased by 50% during last year's Christmas season," is displayed on the smart glasses.

[0844] Prompt Sentence Examples

[0845] Use historical sales data when forecasting next month's sales. The data should be in the following format and take into account seasonality and trends:

[0846] Features: Date, Season, Historical Sales

[0847] Response variable: future sales

[0848] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0849] MODE FOR CARRYING OUT THE INVENTION

[0850] The present invention relates to a system incorporating an emotion engine that recognizes a user's emotions, and the implementation method thereof will be described below.

[0851] 1. Data Collection

[0852] The server collects historical data from multiple reliable data sources, such as official archives, historical documents, and online databases, using APIs and web scraping techniques, and stores the collected data in a local database.

[0853] 2. Data formatting and analysis

[0854] The server cleanses the collected data, removing duplicates and missing data. It then analyzes the data using natural language processing (NLP) techniques to identify important events and people. Identified information is tagged with appropriate tags and the data is converted into a format suitable for training artificial intelligence models.

[0855] 3. Training the AI ​​model

[0856] The server uses the formatted data to train an artificial intelligence model. Specifically, it uses machine learning algorithms and deep learning techniques to learn the behavioral patterns of each historical event and person. The trained model's performance is evaluated, and parameters are optimized as needed.

[0857] 4. Building a virtual environment

[0858] The server uses the trained AI model to build a virtual environment ("History Sandbox"), a virtual space for recreating historical scenarios, designed in detail using 3D modeling tools. Trained AI agents are placed within this environment, interacting with each other to progress the simulation.

[0859] 5. User Interaction

[0860] Users access the "History Sandbox" using their devices. They select a specific scenario from a list of scenarios and customize the simulation settings and parameters. For example, they can select the "Napoleonic Wars" scenario and set conditions such as the number of troops and weather.

[0861] 6. Running the simulation and providing the results

[0862] The server simulates a scenario based on the conditions set by the user. During this simulation, AI agents act based on their respective roles and interact with each other. After the simulation is complete, the server analyzes the results and extracts key events and performance data. The results are sent to the user's device, where they can view the results through detailed reports and graphs.

[0863] 7. Implementing the Emotion Engine

[0864] The device is equipped with an emotion engine that recognizes the user's emotions in real time and has the ability to analyze emotional data from the user's facial expressions and voice.

[0865] 8. Emotion-based simulation adjustment

[0866] The server receives the user's emotional data analyzed by the emotion engine and adjusts the simulation accordingly. For example, if the user is excited, the simulation results will be displayed in detail, but if the user is stressed, the results will be displayed in a concise summary.

[0867] 9. Emotion-Based Recommendations

[0868] The device provides recommended scenarios and parameter settings based on the user's emotional state. For example, if the user is relaxed, it will recommend a high-difficulty scenario or complex conditions, while if the user is tense, it will recommend an easy scenario.

[0869] Specific examples

[0870] 1. Emotion-based strategic game simulation

[0871] Users access the "History Sandbox" on their devices and select a medieval strategy game scenario. The emotion engine analyzes the user's facial expressions to detect whether they are enjoying the game. The server uses this information to display detailed simulation results and offer a variety of tactical options.

[0872] 2. Emotional feedback simulation of marketing strategies

[0873] Management uses the emotion engine when simulating marketing strategy scenarios. It analyzes the voice data obtained from the device to detect how the user feels about the presentation. The server uses this information to adjust the content of the presentation and provides the final results to management.

[0874] In this way, combining emotion engines enables flexible simulation and interaction according to the user's emotional state. By using emotion data, the present invention can provide a more personalized experience and improve user satisfaction.

[0875] The processing flow will be explained below.

[0876] Step 1:

[0877] The server collects historical data from data sources, such as official archives, historical documents, and online databases, using APIs and web scraping techniques, and stores the data in a local database.

[0878] Step 2:

[0879] The server cleanses the collected data, removing duplicates and missing data to ensure the data is complete and consistent.

[0880] Step 3:

[0881] The server analyzes the data using natural language processing (NLP) techniques, specifically segmenting the text data into words, tagging parts of speech, extracting named entities, and identifying important events and people.

[0882] Step 4:

[0883] The server tags the parsed data, for example, by adding appropriate tags based on specific eras, locations, or characters, and structuring the data.

[0884] Step 5:

[0885] The server uses the tagged data to train an artificial intelligence model, using machine learning algorithms and deep learning techniques to learn the behavioral patterns of each historical event and person.

[0886] Step 6:

[0887] The server evaluates the performance of the trained AI model, using precision, recall, and F1 score as evaluation metrics, and optimizes the model parameters as needed.

[0888] Step 7:

[0889] The server uses trained artificial intelligence models to build virtual environments ("History Sandbox"), which are then detailed using 3D modeling tools to create virtual spaces for recreating historical scenarios.

[0890] Step 8:

[0891] Users access the "History Sandbox" using a device, where they can select a specific scenario from a list of scenarios and customize the simulation settings and parameters. For example, they can select the "Napoleonic Wars" scenario and set the number of troops and weather conditions.

[0892] Step 9:

[0893] The device's emotion engine recognizes the user's emotions in real time by analyzing the user's facial expressions and voice data to detect their emotional state.

[0894] Step 10:

[0895] The server receives the user's emotional data sent from the emotion engine and analyzes the user's emotional state, such as whether they are excited or relaxed.

[0896] Step 11:

[0897] The server adjusts the simulation based on the emotional data, for example, displaying detailed simulation results if the user is excited, or summarizing the results if the user is stressed.

[0898] Step 12:

[0899] The server simulates a scenario based on the conditions set by the user. AI agents interact with each other within the virtual environment, driving the simulation forward.

[0900] Step 13:

[0901] The server analyzes the simulation results and extracts key events and achievements, such as the outcome of a battle simulation and the resource consumption rate.

[0902] Step 14:

[0903] The server sends the simulation results to the user's device, where the user can view the results through detailed reports and graphs to help guide decision-making.

[0904] Step 15:

[0905] The device provides recommended scenarios and parameter settings based on the user's emotional state: for example, if the user is relaxed, it recommends a more difficult scenario, and if the user is nervous, it recommends an easier scenario.

[0906] Example 2

[0907] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0908] Conventional historical simulation systems have the problem of only providing uniform results and operation methods without considering the user's emotions. This often results in a lack of consistency in the user's experience, leading to low satisfaction. The present invention aims to provide a more personalized experience by analyzing the user's emotions in real time and dynamically adjusting the simulation based on the results.

[0909] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0910] In this invention, the server includes means for collecting historical data from a data source, means for analyzing and tagging the collected historical data, means for training an artificial intelligence model based on the tagged historical data, means for constructing a virtual environment using the trained artificial intelligence model, means for accepting input from a user terminal and executing a simulation, means for analyzing user emotion data, means for adjusting the simulation based on the analyzed emotion data, means for providing recommended scenario and parameter settings based on the analyzed emotion data, and means for analyzing the simulation results and providing them to the user terminal, thereby enabling a flexible and personalized simulation experience that corresponds to the user's emotions.

[0911] "Data Source" means a source for collecting historical data used to provide reliable information.

[0912] "Historical data" is data that contains detailed information about events, people, places, etc. that occurred in the past.

[0913] "Tagging" is the process of assigning specific labels or keywords to data to make it easier to classify and search.

[0914] An "artificial intelligence model" is a program that uses algorithms and computational tools to learn from large amounts of data and perform specific tasks.

[0915] A "virtual environment" is an artificial space generated by computer simulation that mimics the real world.

[0916] A "user terminal" is a device such as a computer or smartphone that a user uses to perform operations or input data.

[0917] "Emotion data" is data that indicates the emotional state of the user, analyzed from facial expressions, voice, and the like.

[0918] "Simulation" is a computational process that recreates real-world events or processes in a virtual environment.

[0919] "Recommended settings" are optimal scenarios and parameter settings suggested by the system based on the user's feelings and situation.

[0920] "Analysis" is the process of examining information in detail to understand meaning and patterns.

[0921] MODE FOR CARRYING OUT THE INVENTION

[0922] The present invention relates to a system that recognizes a user's emotions and dynamically adjusts a simulation based on the emotions. The following describes how the system can be implemented.

[0923] The server first collects historical data from data sources. Data collection is performed using APIs and web scraping techniques to gather the necessary data from official archives, historical documents, online databases, etc. The collected data is then stored in a local database. Specifically, Python's BeautifulSoup and Scrapy are used.

[0924] The server then cleanses the collected data, removing duplicates and missing data. It then uses Natural Language Processing (NLP) techniques to analyze the data and identify important events and people. This stage involves data preprocessing using the Pandas library and text tagging using NLTK or spaCy. The tagged data is then converted into a format suitable for training artificial intelligence models.

[0925] The server then uses the formatted data to train an artificial intelligence model, using TensorFlow or PyTorch to apply machine learning algorithms and deep learning techniques to learn the behavioral patterns of each historical event and person. The trained model is then evaluated and optimized.

[0926] Using the trained AI model, the server builds a virtual environment called the "History Sandbox," which is meticulously designed using Unity or Unreal Engine and populated with AI agents. These agents interact with each other to advance the simulation.

[0927] Users can access the "History Sandbox" using their devices. They select a specific scenario from a list of scenarios and customize the simulation settings and parameters. For example, they can select the "Napoleonic Wars" scenario and set conditions such as the number of troops and weather. The user interface is provided via a web browser or a dedicated app.

[0928] During the simulation, the server advances the simulation based on the user's input conditions. To collect user emotion data, the device is equipped with an emotion engine that uses the camera and microphone to analyze the user's emotions in real time. This analysis is performed using OpenCV or Azure Cognitive Services.

[0929] Based on the analyzed emotional data, the server dynamically adjusts the simulation. For example, if the user is excited, it displays detailed results and offers many tactical options. On the other hand, if the user is stressed, it displays concise results. It also recommends appropriate scenarios and parameter settings based on the emotional data. For example, if the user is relaxed, it recommends more difficult scenarios and more complex conditions.

[0930] Here are some examples of specific prompts:

[0931] "Write a Python program that recommends settings for a strategy game scenario based on the user's emotional data. Specifically, implement logic to display detailed simulation results if the user is having fun, and a concise summary of the results if the user is stressed."

[0932] The above is an embodiment of the present invention, which makes it possible to provide a flexible and personalized simulation experience that responds to the user's emotions.

[0933] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0934] Step 1:

[0935] The server collects historical data from multiple reliable data sources. It receives API endpoints and website URLs as input, and stores the collected data in a local database as output. Specifically, the server uses Python's BeautifulSoup and Scrapy to retrieve data via APIs and perform web scraping.

[0936] Step 2:

[0937] The server cleanses the collected data. As input, it takes the raw data stored in the local database and as output, it obtains cleansed data from which duplicates and missing data have been removed. Specifically, the server preprocesses the data using the Pandas library.

[0938] Step 3:

[0939] The server parses the cleansed data and identifies important events and people. It takes the cleansed data as input and the tagged data as output. Specifically, the server uses NLTK or spaCy to parse the text data and assigns appropriate tags to each data point.

[0940] Step 4:

[0941] The server uses the tagged data to train an artificial intelligence model. It takes the tagged data as input and produces a trained AI model as output. Specifically, the server uses TensorFlow or PyTorch to build and train machine learning algorithms and deep learning models.

[0942] Step 5:

[0943] The server uses the trained AI model to build a virtual environment called the "History Sandbox." The trained AI model is taken as input, and the virtual environment is generated as output. Specifically, the server uses Unity or Unreal Engine to perform 3D modeling and place AI agents.

[0944] Step 6:

[0945] The user accesses the "History Sandbox" using a terminal and sets the scenario and parameters. As input, a list of scenarios and configurable parameters is obtained, and as output, the scenario selected by the user and customized parameters are obtained. In concrete terms, the user accesses the server using a web browser or a dedicated app and operates the interface.

[0946] Step 7:

[0947] The server runs the simulation based on the user's settings. It takes the user's selected scenario and customized parameters as input and generates the simulation results as output. The specific behavior is that AI agents act while influencing each other in the virtual space.

[0948] Step 8:

[0949] The device uses a camera and microphone to collect user emotional data. The input is the user's facial expressions and voice, and the output is analyzed emotional data. Specifically, the device performs real-time emotional analysis using OpenCV or Azure Cognitive Services.

[0950] Step 9:

[0951] The server adjusts the simulation based on the analyzed emotional data. It takes the user's emotional data as input and generates adjusted simulation results as output. Specifically, it displays detailed results if the user is excited, and summarizes the results briefly if the user is stressed.

[0952] Step 10:

[0953] The device provides recommended scenarios and parameter settings based on the analyzed emotional data. It receives emotional data as input and provides recommended scenarios and parameters as output. Specifically, it recommends a high-difficulty scenario if the user is relaxed, and an easy scenario if the user is tense.

[0954] The above is the specific processing flow of this system.

[0955] (Application example 2)

[0956] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0957] Conventional content delivery systems provide content without considering the user's emotional state, resulting in insufficient personalization of user interactions and difficulty in improving user satisfaction. Furthermore, the lack of technology to dynamically adjust content based on the user's emotions in real time makes it difficult to provide services that meet individual needs.

[0958] The identification processing by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting information data from a data source, means for analyzing and tagging the collected information data, means for training an artificial intelligence model based on the tagged information data, means for constructing a virtual environment using the trained artificial intelligence model, means for accepting input from a user terminal and executing a simulation, means for analyzing the simulation results and providing them to the user terminal, means for collecting user emotion data and analyzing it with an emotion engine, and means for dynamically adjusting the simulation and content based on the emotion data. This enables personalized content delivery based on the user's emotional state, which is expected to improve user satisfaction.

[0959] "Data sources" are the various information sources that the system uses to gather information.

[0960] "Information Data" means historical, statistical, or other type of data obtained from a data source.

[0961] "Analysis" is the process of processing collected information data and extracting specific meanings and patterns.

[0962] "Tagging" is the process of adding metadata and identifying information to analyzed data.

[0963] An "artificial intelligence model" is a computational model that learns from data and makes predictions and distinctions.

[0964] "Training" is the learning process of providing an artificial intelligence model with the necessary data to improve the accuracy of its predictions and identification.

[0965] A "virtual environment" is a simulated environment generated by a computer program with which humans can interact.

[0966] A "user terminal" is a device (e.g., smartphone, PC, tablet, etc.) that a user uses to perform operations or input data.

[0967] "Simulation" is a technology that reproduces real-world phenomena and processes on a computer and performs analysis and predictions.

[0968] "Emotion data" is information about emotions obtained from the user's facial expressions, voice, etc.

[0969] An "emotion engine" is an algorithm or program that analyzes collected emotion data and identifies the user's emotional state.

[0970] "Dynamic adjustment" refers to the process of changing in response to real-time conditions.

[0971] The present invention relates to a system for recognizing user emotions and dynamically adjusting content delivery based on the emotion data. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS ... will be described in detail below.

[0972] System Overview

[0973] The system consists of a server, a user terminal, and an emotion engine. The server performs processes such as data collection and analysis, training of artificial intelligence models, and construction of virtual environments. The user terminal serves as the user's interface, collecting emotion data and displaying simulation results. The emotion engine analyzes the user's emotions and provides feedback to the system.

[0974] Hardware and software used

[0975] Hardware: Smartphones, smart glasses, head-mounted displays

[0976] Software: OpenCV (facial expression analysis), Google Cloud Speech-to-Text (voice analysis), TensorFlow and Keras (AI model training), Unity and Unreal Engine (virtual environment creation), AWS or Google Cloud Platform (server)

[0977] Program Overview

[0978] The server collects, analyzes, and tags information data from data sources. It then uses the tagged data to train an artificial intelligence model and uses this model to build a virtual environment. The user device collects the user's emotion data through a camera and microphone and analyzes the data through an emotion engine. Based on the data analyzed by the emotion engine, the server dynamically adjusts the simulation and provides the results to the user device.

[0979] Specific examples

[0980] For example, while a user is watching a drama series, the system uses the smartphone's camera and microphone to collect the user's facial expressions and voice in real time. The collected data is analyzed using OpenCV and Google Cloud Speech-to-Text, and the emotional engine identifies the user's emotional state. Based on the identified emotional state, the server dynamically adjusts the viewing content and even suggests related content recommendations. This process allows users to seamlessly enjoy content that matches their emotions.

[0981] Prompt Sentence Examples

[0982] "Recommend what content to watch next based on user sentiment data and viewing history."

[0983] As a result, a system built on the basis of the present invention realizes personalized content delivery to increase user engagement.

[0984] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0985] Step 1:

[0986] The server collects information data from data sources. Specifically, it retrieves data from databases and online repositories using APIs and web scraping techniques. The input is information data from external data sources, and the output is the collected information data.

[0987] Step 2:

[0988] The server analyzes and tags the collected information data. Specifically, it performs data cleansing to remove duplicate and missing data. It then uses NLP technology to extract important information and assign appropriate tags. The input is the collected information data, and the output is the analyzed and tagged data.

[0989] Step 3:

[0990] The server uses the tagged data to train an AI model. Specifically, it uses TensorFlow and Keras to feed the data and apply machine learning algorithms to train the model. The input is the parsed and tagged data, and the output is the trained AI model.

[0991] Step 4:

[0992] The server uses a trained AI model to build a virtual environment. Specifically, it uses Unity or Unreal Engine for 3D modeling and designs the virtual space in detail. The input is the trained AI model, and the output is the constructed virtual environment.

[0993] Step 5:

[0994] The device uses a camera and microphone to collect the user's emotional data in real time. The collected data is analyzed by an emotion engine to identify the user's emotional state. The input is the user's facial and voice data, and the output is the analyzed emotional data.

[0995] Step 6:

[0996] The server receives the user's emotional data analyzed by the emotion engine, runs the simulation, and dynamically adjusts the results. This includes displaying the simulation results in detail and recommending the next content to watch according to the user's emotions. The input is the analyzed emotional data and the virtual environment, and the output is the dynamically adjusted simulation results.

[0997] Step 7:

[0998] The terminal provides the user with the simulation results and content recommendations received from the server, providing visual and auditory feedback to help the user decide on their next action. The input is the dynamically adjusted simulation results, and the output is feedback to the user.

[0999] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[1000] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1001] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314.

[1002] [Fourth embodiment]

[1003] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1004] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[1005] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1006] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[1007] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[1008] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[1009] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1010] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[1011] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1012] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[1013] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1014] In the robot 414, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1015] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1016] MODE FOR CARRYING OUT THE INVENTION

[1017] The present invention relates to a system for collecting and analyzing historical data and performing simulations based on the collected data, and the method for implementing the system will be described below.

[1018] 1. Data Collection

[1019] The server collects historical data from multiple reliable data sources, such as official government archives, historical documents, and databases, using APIs and web scraping techniques, and stores the collected data in a local database.

[1020] 2. Data formatting and analysis

[1021] The server cleanses the collected data, removing duplicates and missing data. It then analyzes the data using natural language processing (NLP) techniques to identify important events and people. Identified information is tagged with appropriate tags and the data is converted into a format suitable for training artificial intelligence models.

[1022] 3. Training the AI ​​model

[1023] The server uses the formatted data to train an artificial intelligence model. Specifically, it uses machine learning algorithms and deep learning techniques to learn the behavioral patterns of each historical event and person. The trained model's performance is evaluated, and parameters are optimized as needed.

[1024] 4. Building a virtual environment

[1025] The server uses the trained AI model to build a virtual environment ("History Sandbox"), a virtual space for recreating historical scenarios, designed in detail using 3D modeling tools. Trained AI agents are placed within this environment, interacting with each other to progress the simulation.

[1026] 5. User Interaction

[1027] Users access the "History Sandbox" using a terminal. They select a specific scenario from a list of scenarios and customize the simulation settings and parameters. For example, they can select the "Napoleonic Wars" scenario and set conditions such as the number of troops and weather.

[1028] 6. Running the simulation and providing the results

[1029] The server simulates a scenario based on the conditions set by the user. During this simulation, AI agents act based on their respective roles and interact with each other. After the simulation is complete, the server analyzes the results and extracts key events and performance data. The results are sent to the user's device, where they can view the results through detailed reports and graphs.

[1030] Specific examples

[1031] 1. World War II simulation

[1032] Users access the "History Sandbox" on their devices and select a World War II scenario. They set parameters such as the German army's advance speed and the Allied forces' reaction time. The server then runs the simulation and analyzes several strategic options. Simulation results, such as each country's strategic success rate and resource consumption, are provided to the user.

[1033] 2. Marketing strategy verification

[1034] Management simulates current market conditions based on historical marketing data. For example, they analyze data extracted from past successes and failures to train an AI model. They then use the trained model to simulate new product launch scenarios. As a result, product demand forecasts and competitor responses are analyzed, providing management with the information they need to make more accurate decisions.

[1035] In this way, by utilizing advanced simulation technology, the present invention makes it possible to predict the future based on historical data, becoming a powerful tool that enables users and companies to make quick and accurate decisions.

[1036] The processing flow will be explained below.

[1037] Step 1:

[1038] The server collects historical data from data sources, such as official archives, historical documents, and online databases, using APIs and web scraping techniques, and stores the collected data in a local database.

[1039] Step 2:

[1040] The server cleanses the collected data. During the cleansing process, duplicate data and missing data are removed to ensure data integrity. The cleansed data is then passed on to the next analysis step.

[1041] Step 3:

[1042] The server analyzes the data using natural language processing (NLP) techniques, such as segmenting the text data into words, tagging parts of speech, and extracting named entities to identify important events and people.

[1043] Step 4:

[1044] The server then tags the parsed data, for example, by adding appropriate tags based on specific eras, locations, or characters, and structuring the data.

[1045] Step 5:

[1046] The server uses the tagged data to train an artificial intelligence model, using machine learning algorithms and deep learning techniques to learn the behavioral patterns of each historical event and person.

[1047] Step 6:

[1048] The server evaluates the performance of the trained AI model, using metrics such as precision, recall, and F1 score, and optimizes the model parameters as needed.

[1049] Step 7:

[1050] The server uses trained artificial intelligence models to build a virtual environment (the "History Sandbox"), which is meticulously designed using 3D modeling tools and serves as a virtual space for recreating historical scenarios.

[1051] Step 8:

[1052] Users access the "History Sandbox" using their devices. They select a specific scenario from a list of scenarios and customize the simulation settings and parameters. For example, they can select the "Napoleonic Wars" scenario and set conditions such as the number of troops and weather.

[1053] Step 9:

[1054] The server simulates a scenario based on the conditions set by the user. AI agents interact with each other within the virtual environment, and the simulation progresses.

[1055] Step 10:

[1056] The server analyzes the simulation results and extracts key events and achievements, such as the outcome of a battle simulation and the resource consumption rate.

[1057] Step 11:

[1058] The server sends the simulation results to the user's device, where they can view the results through detailed reports and graphs, which can be used as a reference for decision-making.

[1059] Example 1

[1060] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1061] Conventional historical simulation systems require a great deal of time and effort to collect, format, and analyze reliable data, and they also have the problem of making it difficult for users to analyze the simulation results in detail.In addition, they lack the flexibility to allow users to customize the simulation content, making it difficult to make highly accurate predictions or analyze a variety of scenarios.

[1062] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1063] In this invention, the server includes means for collecting historical data from a data source, means for formatting and cleansing the collected historical data, means for tagging the cleansed historical data using natural language processing technology, means for training an artificial intelligence model based on the tagged historical data, means for constructing a virtual environment using the trained artificial intelligence model, means for accepting input from a user terminal and customizing simulation settings, means for executing a simulation based on the customized settings, and means for analyzing simulation results and providing them to the user terminal. This enables historical data to be collected and analyzed with high accuracy, allowing users to easily customize simulation content and perform detailed result analysis.

[1064] "Data sources" are sources of historical data and information, such as official government archives, historical documents, and online databases.

[1065] "Means of collection" refers to the methods and technologies used to obtain data using APIs or web scraping technology and store it in a local database on the server.

[1066] "Cleansing methods" refers to methods and techniques used to remove duplicate and missing data from collected data and create an accurate and consistent data set.

[1067] "Natural language processing technology" refers to technology that uses natural language processing (NLP) to analyze text data and identify important events and names of people.

[1068] "Tagging means" refers to the methods and techniques for assigning appropriate tags to analyzed data and organizing the data.

[1069] "Artificial intelligence model" refers to a model created using machine learning algorithms and deep learning techniques to learn from past data and understand patterns and features.

[1070] A "virtual environment" is a simulated space recreated using a trained artificial intelligence model, specifically a virtual space constructed using 3D modeling tools.

[1071] "Means for accepting input from a user terminal" refers to an interface or method for accepting operations such as simulation settings and scenario selection from a user via a terminal.

[1072] "Means for customizing simulation settings" refers to methods and technologies that allow users to change or set simulation conditions and parameters.

[1073] "Means for executing a simulation" refers to methods and techniques for progressing a simulation within a virtual environment based on set conditions.

[1074] "Means for analyzing simulation results" refers to methods and techniques for evaluating the results after the simulation is completed and extracting and analyzing key events, achievements, etc.

[1075] "Means for providing to user terminal" refers to the methods and technologies for displaying and transmitting the analyzed simulation results to the user's terminal so that the user can check and analyze the results.

[1076] The present invention relates to a system for collecting and analyzing historical data and performing simulations based on the collected data. A specific method for implementing the system will be described below.

[1077] The server collects historical data from multiple reliable data sources, including official government archives, historical documents, and online databases. The collected data is retrieved using APIs and web scraping techniques, such as Python's "BeautifulSoup" and "Scrapy."

[1078] The server then formats and cleanses the collected data, using Python's pandas and numpy libraries, to remove duplicates and missing data and create an accurate and consistent dataset.

[1079] The cleansed data is then analyzed using natural language processing (NLP) techniques to identify important events and people's names, using NLP libraries such as spaCy and NLTK, which then tag the data appropriately and convert it into a format suitable for training artificial intelligence models.

[1080] The server uses the formatted data to train an AI model using machine learning algorithms and deep learning techniques, such as deep learning frameworks like TensorFlow and PyTorch. During the training process, the accuracy of the model is evaluated after each epoch and hyperparameters are adjusted as needed. Once the model is fully trained, it is stored in local or cloud storage.

[1081] The server then uses the trained AI model to build a virtual environment. This virtual environment, called a "virtual sandbox," is designed in detail using 3D modeling tools (e.g., Unity or Unreal Engine). Historical terrain, buildings, and characters are recreated in the virtual environment, and AI agents are placed in it. These agents behave based on the behavioral patterns learned by the trained AI model.

[1082] Users access the "virtual sandbox" using their devices. They access the system through a web browser or a dedicated app and select the historical scenario they want to recreate from a list of scenarios. For example, they can choose the "Napoleonic Wars" scenario and customize the number of troops, weather, and other conditions through the interface. This setting information is sent to the server.

[1083] The server simulates a scenario based on the conditions set by the user. During the simulation, multiple AI agents interact with each other. Once the simulation is complete, the server analyzes the results to extract key events and achievements. The analysis includes evaluation indicators of the simulation (success rate, resource consumption, etc.). The generated results are sent to the user's device, where the user can view and save the results through detailed reports and graphs.

[1084] Specific examples

[1085] 1. World War II simulation

[1086] Users access the "virtual sandbox" using their devices and select a World War II scenario. They set parameters such as the German army's advance speed and the Allied forces' reaction time. The server then runs the simulation and analyzes several strategic options. Simulation results, such as each country's strategic success rate and resource depletion, are provided to the user.

[1087] 2. Marketing strategy verification

[1088] Management simulates current market conditions based on historical marketing data. For example, they analyze data extracted from past successes and failures to train an AI model. They then use the trained model to simulate new product launch scenarios. As a result, product demand forecasts and competitor responses are analyzed, providing management with the information they need to make more accurate decisions.

[1089] Prompt Sentence Examples

[1090] "It simulates an early battle scenario from the German-Soviet War of 1941, assessing the speed of German advance and the Soviet defensive response."

[1091] This system collects and analyzes historical data with high accuracy, allowing users to easily customize simulation content and perform detailed analysis of results.

[1092] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1093] Step 1:

[1094] Data collection

[1095] The server collects historical data from multiple reliable data sources. Data sources include official government archives, historical documents, and online databases. The collection method uses APIs and web scraping techniques. For example, Python's "BeautifulSoup" or "Scrapy" is used to obtain data and store it in a local database in JSON format. The input is access information and acquisition conditions for the data source, and the output is the raw data stored in the local database.

[1096] Step 2:

[1097] Data Shaping and Cleansing

[1098] The server formats and cleanses the collected data. Specifically, it uses Python libraries such as "pandas" and "numpy." During cleansing, duplicate and missing data are removed to ensure data consistency. For example, missing values ​​are filled in and duplicate records are deleted. The input is the collected raw data, and the output is the formatted, cleansed data.

[1099] Step 3:

[1100] Data tagging and analysis

[1101] The server analyzes the cleansed data using natural language processing (NLP) techniques. Specifically, it uses NLP libraries such as "spaCy" and "NLTK" to identify important events and people's names. The identified information is then appropriately tagged. The input is the data that has been formatted and cleansed, and the output is the tagged analyzed data.

[1102] Step 4:

[1103] Training an AI model

[1104] The server uses the tagged data to train an artificial intelligence model. Specifically, it uses deep learning frameworks such as TensorFlow and PyTorch to run machine learning algorithms. The training process includes accuracy evaluation after each epoch and tuning of hyperparameters. The input is the tagged analysis data, and the output is a trained AI model.

[1105] Step 5:

[1106] Building a virtual environment

[1107] The server uses the trained AI model to build a virtual environment (virtual sandbox). Specifically, it designs it in detail using 3D modeling tools such as Unity or Unreal Engine. This environment recreates historical terrain, buildings, and characters, and AI agents are placed in it. The input is the trained AI model and the design information for the virtual environment, and the output is the virtual sandbox.

[1108] Step 6:

[1109] Accepting user interactions

[1110] Users access the virtual sandbox using their devices. They access the system through a web browser or a dedicated app and select the historical scenario they want to recreate from a list of scenarios. They then use the interface to customize conditions and parameters (e.g., number of troops, weather, etc.). The input is the user's selection and settings, and the output is the transmission of the settings to the server.

[1111] Step 7:

[1112] Running a simulation and analyzing the results

[1113] The server simulates a scenario based on the conditions set by the user. During the simulation, multiple AI agents interact with each other. When the simulation is complete, the server analyzes the results and extracts key events and achievements. Specifically, it analyzes the simulation's evaluation indicators (success rate, resource consumption, etc.). The input is the user settings and simulation result data, and the output is an analyzed simulation report.

[1114] Step 8:

[1115] Providing results

[1116] The server provides the analyzed simulation results to the user's terminal. The user can view and save the results through detailed reports and graphs. The input is the analyzed simulation report, and the output is the result display on the user's terminal.

[1117] (Application example 1)

[1118] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1119] Modern brick-and-mortar stores require effective customer service and optimized sales strategies. However, traditional methods do not fully utilize past sales data and customer information, making it difficult to make timely decisions. In addition, there are limited means of providing real-time sales forecasts and customer service information, making it difficult for store staff to respond immediately. This can lead to a decline in customer satisfaction and lost sales opportunities.

[1120] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1121] In this invention, the server includes means for collecting historical data from a data source, means for analyzing and tagging the collected historical data, means for training a generative AI model based on the tagged historical data, means for constructing a virtual environment using the trained generative AI model, means for accepting input from a user terminal and executing a simulation, means for providing information useful for customer service in a physical store in real time, and means for analyzing the simulation results and providing them to the user terminal, thereby enabling timely and effective customer service and optimization of sales strategies in physical stores.

[1122] "Data Source" refers to a reliable source or database from which historical data is collected.

[1123] "Historical data" refers to data that contains information about past events or phenomena.

[1124] "Tagging" is the process of adding relevant information to data to make it easier to identify.

[1125] A "generative AI model" is an artificial intelligence model that is trained based on collected and analyzed data.

[1126] "Virtual environment" refers to a virtual simulation environment built using a generative AI model.

[1127] A "user terminal" is a device (such as a smartphone or smart glasses) that a user uses to access the system and perform input and output.

[1128] "Simulation" is the process of virtually recreating real-world phenomena or scenarios.

[1129] A "physical store" is a store that exists physically and where customers can visit in person to purchase products.

[1130] "Customer care" refers to the process of providing service and support to customers.

[1131] 1. Data Collection

[1132] The server collects historical data from reliable data sources, such as official government archives, historical documents, and other databases, using APIs and web scraping techniques, and then stores the collected data in a local database.

[1133] 2. Data analysis and tagging

[1134] The server cleanses the collected historical data, removing missing and duplicate data, then analyzes it using natural language processing (NLP) techniques to identify important events and people, assigning appropriate tags to the identified information, and converting the data into a format suitable for training generative AI models.

[1135] 3. Training the AI ​​model

[1136] The server trains a generative AI model based on the formatted data, using machine learning algorithms and deep learning techniques. The trained model's performance is evaluated, and its parameters are optimized as needed.

[1137] 4. Building a virtual environment

[1138] The server uses the trained generative AI model to create a virtual environment, a virtual space for recreating historical scenarios, such as simulating a physical store using 3D modeling tools.

[1139] 5. User Interaction

[1140] Users access the virtual environment using a device (such as a smartphone or smart glasses). They select a specific scenario and customize the settings and parameters of the simulation. For example, they can set up a simulation to forecast sales based on past sales data.

[1141] 6. Simulation and real-time response

[1142] The server simulates scenarios based on the conditions set by the user. The simulation results are analyzed and displayed in real time on the store staff's smart glasses. This allows staff to take the optimal response based on the customer's past purchase history and sales forecasts.

[1143] Specific examples

[1144] Sales forecasting and product display optimization

[1145] Historical data is analyzed to visualize seasonal sales trends and customer purchasing patterns, and store staff can optimize product displays and inventory management based on sales forecast data obtained in real time through smart glasses.

[1146] Example: Proposing best-selling products according to the season

[1147] Every year before Christmas, the company analyzes which products are selling well and uses that data to make sales forecasts. For example, store staff can see through their smart glasses that "sales of this product increased by 50% during last year's Christmas season."

[1148] Prompt Sentence Examples

[1149] Use historical sales data when forecasting next month's sales. The data should be in the following format and take into account seasonality and trends:

[1150] Features: Date, Season, Historical Sales

[1151] Response variable: future sales

[1152] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1153] Step 1: Data collection

[1154] The server retrieves data from official government archives and historical databases using APIs and web scraping techniques, and stores historical documents and archived data in a local database. The input is information from the data source, and the output is raw data stored in the local database.

[1155] Step 2: Data analysis and cleansing

[1156] The server cleanses the collected data, removing duplicates and missing data. It uses natural language processing (NLP) to analyze the data, identify and tag important events and people. The input is raw data stored in a local database, and the output is cleaned, analyzed data.

[1157] Step 3: Training the generative AI model

[1158] The server uses the cleansed and tagged data to train a generative AI model. It then uses machine learning algorithms and deep learning techniques to optimize the trained model. The input is the cleaned and analyzed data, and the output is a trained generative AI model.

[1159] Step 4: Building the virtual environment

[1160] The server uses the trained generative AI model to create a virtual environment that can recreate historical scenarios or virtual situations within a physical store. The input is the generative AI model, and the output is the virtual environment and scenario data.

[1161] Step 5: Accepting User Input and Setting Up the Simulation

[1162] Users access the virtual environment through their terminals, select specific scenarios, and customize the settings and parameters of the simulation. The input is the user's settings and selections, and the output is the simulation configuration data.

[1163] Step 6: Run the simulation

[1164] The server runs a simulation based on the conditions set by the user. AI agents interact with each other as the simulation progresses within the virtual environment. The input is the simulation setting data, and the output is the simulation result data.

[1165] Step 7: Result analysis and real-time display

[1166] The server analyzes the simulation results and extracts key events and achievements. The analysis results are displayed in real time on smart glasses or devices. The input is the simulation result data, and the output is the analysis results and their display.

[1167] Example operation

[1168] For example, if a user wants to predict sales for the Christmas season, a simulation is performed based on sales data from past Christmas seasons, and the resulting information, such as "Sales of this product increased by 50% during last year's Christmas season," is displayed on the smart glasses.

[1169] Prompt Sentence Examples

[1170] Use historical sales data when forecasting next month's sales. The data should be in the following format and take into account seasonality and trends:

[1171] Features: Date, Season, Historical Sales

[1172] Response variable: future sales

[1173] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1174] MODE FOR CARRYING OUT THE INVENTION

[1175] The present invention relates to a system incorporating an emotion engine that recognizes a user's emotions, and the implementation method thereof will be described below.

[1176] 1. Data Collection

[1177] The server collects historical data from multiple reliable data sources, such as official archives, historical documents, and online databases, using APIs and web scraping techniques, and stores the collected data in a local database.

[1178] 2. Data formatting and analysis

[1179] The server cleanses the collected data, removing duplicates and missing data. It then analyzes the data using natural language processing (NLP) techniques to identify important events and people. Identified information is tagged with appropriate tags and the data is converted into a format suitable for training artificial intelligence models.

[1180] 3. Training the AI ​​model

[1181] The server uses the formatted data to train an artificial intelligence model. Specifically, it uses machine learning algorithms and deep learning techniques to learn the behavioral patterns of each historical event and person. The trained model's performance is evaluated, and parameters are optimized as needed.

[1182] 4. Building a virtual environment

[1183] The server uses the trained AI model to build a virtual environment ("History Sandbox"), a virtual space for recreating historical scenarios, designed in detail using 3D modeling tools. Trained AI agents are placed within this environment, interacting with each other to progress the simulation.

[1184] 5. User Interaction

[1185] Users access the "History Sandbox" using their devices. They select a specific scenario from a list of scenarios and customize the simulation settings and parameters. For example, they can select the "Napoleonic Wars" scenario and set conditions such as the number of troops and weather.

[1186] 6. Running the simulation and providing the results

[1187] The server simulates a scenario based on the conditions set by the user. During this simulation, AI agents act based on their respective roles and interact with each other. After the simulation is complete, the server analyzes the results and extracts key events and performance data. The results are sent to the user's device, where they can view the results through detailed reports and graphs.

[1188] 7. Implementing the Emotion Engine

[1189] The device is equipped with an emotion engine that recognizes the user's emotions in real time and has the ability to analyze emotional data from the user's facial expressions and voice.

[1190] 8. Emotion-based simulation adjustment

[1191] The server receives the user's emotional data analyzed by the emotion engine and adjusts the simulation accordingly. For example, if the user is excited, the simulation results will be displayed in detail, but if the user is stressed, the results will be displayed in a concise summary.

[1192] 9. Emotion-Based Recommendations

[1193] The device provides recommended scenarios and parameter settings based on the user's emotional state. For example, if the user is relaxed, it will recommend a high-difficulty scenario or complex conditions, while if the user is tense, it will recommend an easy scenario.

[1194] Specific examples

[1195] 1. Emotion-based strategic game simulation

[1196] Users access the "History Sandbox" on their devices and select a medieval strategy game scenario. The emotion engine analyzes the user's facial expressions to detect whether they are enjoying the game. The server uses this information to display detailed simulation results and offer a variety of tactical options.

[1197] 2. Emotional feedback simulation of marketing strategies

[1198] Management uses the emotion engine when simulating marketing strategy scenarios. It analyzes the voice data obtained from the device to detect how the user feels about the presentation. The server uses this information to adjust the content of the presentation and provides the final results to management.

[1199] In this way, combining emotion engines enables flexible simulation and interaction according to the user's emotional state. By using emotion data, the present invention can provide a more personalized experience and improve user satisfaction.

[1200] The processing flow will be explained below.

[1201] Step 1:

[1202] The server collects historical data from data sources, such as official archives, historical documents, and online databases, using APIs and web scraping techniques, and stores the data in a local database.

[1203] Step 2:

[1204] The server cleanses the collected data, removing duplicates and missing data to ensure the data is complete and consistent.

[1205] Step 3:

[1206] The server analyzes the data using natural language processing (NLP) techniques, specifically segmenting the text data into words, tagging parts of speech, extracting named entities, and identifying important events and people.

[1207] Step 4:

[1208] The server tags the parsed data, for example, by adding appropriate tags based on specific eras, locations, or characters, and structuring the data.

[1209] Step 5:

[1210] The server uses the tagged data to train an artificial intelligence model, using machine learning algorithms and deep learning techniques to learn the behavioral patterns of each historical event and person.

[1211] Step 6:

[1212] The server evaluates the performance of the trained AI model, using precision, recall, and F1 score as evaluation metrics, and optimizes the model parameters as needed.

[1213] Step 7:

[1214] The server uses trained artificial intelligence models to build virtual environments ("History Sandbox"), which are then detailed using 3D modeling tools to create virtual spaces for recreating historical scenarios.

[1215] Step 8:

[1216] Users access the "History Sandbox" using a device, where they can select a specific scenario from a list of scenarios and customize the simulation settings and parameters. For example, they can select the "Napoleonic Wars" scenario and set the number of troops and weather conditions.

[1217] Step 9:

[1218] The device's emotion engine recognizes the user's emotions in real time by analyzing the user's facial expressions and voice data to detect their emotional state.

[1219] Step 10:

[1220] The server receives the user's emotional data sent from the emotion engine and analyzes the user's emotional state, such as whether they are excited or relaxed.

[1221] Step 11:

[1222] The server adjusts the simulation based on the emotional data, for example, displaying detailed simulation results if the user is excited, or summarizing the results if the user is stressed.

[1223] Step 12:

[1224] The server simulates a scenario based on the conditions set by the user. AI agents interact with each other within the virtual environment, driving the simulation forward.

[1225] Step 13:

[1226] The server analyzes the simulation results and extracts key events and achievements, such as the outcome of a battle simulation and the resource consumption rate.

[1227] Step 14:

[1228] The server sends the simulation results to the user's device, where the user can view the results through detailed reports and graphs to help guide decision-making.

[1229] Step 15:

[1230] The device provides recommended scenarios and parameter settings based on the user's emotional state: for example, if the user is relaxed, it recommends a more difficult scenario, and if the user is nervous, it recommends an easier scenario.

[1231] Example 2

[1232] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1233] Conventional historical simulation systems have the problem of only providing uniform results and operation methods without considering the user's emotions. This often results in a lack of consistency in the user's experience, leading to low satisfaction. The present invention aims to provide a more personalized experience by analyzing the user's emotions in real time and dynamically adjusting the simulation based on the results.

[1234] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1235] In this invention, the server includes means for collecting historical data from a data source, means for analyzing and tagging the collected historical data, means for training an artificial intelligence model based on the tagged historical data, means for constructing a virtual environment using the trained artificial intelligence model, means for accepting input from a user terminal and executing a simulation, means for analyzing user emotion data, means for adjusting the simulation based on the analyzed emotion data, means for providing recommended scenario and parameter settings based on the analyzed emotion data, and means for analyzing the simulation results and providing them to the user terminal, thereby enabling a flexible and personalized simulation experience that corresponds to the user's emotions.

[1236] "Data Source" means a source for collecting historical data used to provide reliable information.

[1237] "Historical data" is data that contains detailed information about events, people, places, etc. that occurred in the past.

[1238] "Tagging" is the process of assigning specific labels or keywords to data to make it easier to classify and search.

[1239] An "artificial intelligence model" is a program that uses algorithms and computational tools to learn from large amounts of data and perform specific tasks.

[1240] A "virtual environment" is an artificial space generated by computer simulation that mimics the real world.

[1241] A "user terminal" is a device such as a computer or smartphone that a user uses to perform operations or input data.

[1242] "Emotion data" is data that indicates the emotional state of the user, analyzed from facial expressions, voice, and the like.

[1243] "Simulation" is a computational process that recreates real-world events or processes in a virtual environment.

[1244] "Recommended settings" are optimal scenarios and parameter settings suggested by the system based on the user's feelings and situation.

[1245] "Analysis" is the process of examining information in detail to understand meaning and patterns.

[1246] MODE FOR CARRYING OUT THE INVENTION

[1247] The present invention relates to a system that recognizes a user's emotions and dynamically adjusts a simulation based on the emotions. The following describes how the system can be implemented.

[1248] The server first collects historical data from data sources. Data collection is performed using APIs and web scraping techniques to gather the necessary data from official archives, historical documents, online databases, etc. The collected data is then stored in a local database. Specifically, Python's BeautifulSoup and Scrapy are used.

[1249] The server then cleanses the collected data, removing duplicates and missing data. It then uses Natural Language Processing (NLP) techniques to analyze the data and identify important events and people. This stage involves data preprocessing using the Pandas library and text tagging using NLTK or spaCy. The tagged data is then converted into a format suitable for training artificial intelligence models.

[1250] The server then uses the formatted data to train an artificial intelligence model, using TensorFlow or PyTorch to apply machine learning algorithms and deep learning techniques to learn the behavioral patterns of each historical event and person. The trained model is then evaluated and optimized.

[1251] Using the trained AI model, the server builds a virtual environment called the "History Sandbox," which is meticulously designed using Unity or Unreal Engine and populated with AI agents. These agents interact with each other to advance the simulation.

[1252] Users can access the "History Sandbox" using their devices. They select a specific scenario from a list of scenarios and customize the simulation settings and parameters. For example, they can select the "Napoleonic Wars" scenario and set conditions such as the number of troops and weather. The user interface is provided via a web browser or a dedicated app.

[1253] During the simulation, the server advances the simulation based on the user's input conditions. To collect user emotion data, the device is equipped with an emotion engine that uses the camera and microphone to analyze the user's emotions in real time. This analysis is performed using OpenCV or Azure Cognitive Services.

[1254] Based on the analyzed emotional data, the server dynamically adjusts the simulation. For example, if the user is excited, it displays detailed results and offers many tactical options. On the other hand, if the user is stressed, it displays concise results. It also recommends appropriate scenarios and parameter settings based on the emotional data. For example, if the user is relaxed, it recommends more difficult scenarios and more complex conditions.

[1255] Here are some examples of specific prompts:

[1256] "Write a Python program that recommends settings for a strategy game scenario based on the user's emotional data. Specifically, implement logic to display detailed simulation results if the user is having fun, and a concise summary of the results if the user is stressed."

[1257] The above is an embodiment of the present invention, which makes it possible to provide a flexible and personalized simulation experience that responds to the user's emotions.

[1258] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1259] Step 1:

[1260] The server collects historical data from multiple reliable data sources. It receives API endpoints and website URLs as input, and stores the collected data in a local database as output. Specifically, the server uses Python's BeautifulSoup and Scrapy to retrieve data via APIs and perform web scraping.

[1261] Step 2:

[1262] The server cleanses the collected data. As input, it takes the raw data stored in the local database and as output, it obtains cleansed data from which duplicates and missing data have been removed. Specifically, the server preprocesses the data using the Pandas library.

[1263] Step 3:

[1264] The server parses the cleansed data and identifies important events and people. It takes the cleansed data as input and the tagged data as output. Specifically, the server uses NLTK or spaCy to parse the text data and assigns appropriate tags to each data point.

[1265] Step 4:

[1266] The server uses the tagged data to train an artificial intelligence model. It takes the tagged data as input and produces a trained AI model as output. Specifically, the server uses TensorFlow or PyTorch to build and train machine learning algorithms and deep learning models.

[1267] Step 5:

[1268] The server uses the trained AI model to build a virtual environment called the "History Sandbox." The trained AI model is taken as input, and the virtual environment is generated as output. Specifically, the server uses Unity or Unreal Engine to perform 3D modeling and place AI agents.

[1269] Step 6:

[1270] The user accesses the "History Sandbox" using a terminal and sets the scenario and parameters. As input, a list of scenarios and configurable parameters is obtained, and as output, the scenario selected by the user and customized parameters are obtained. In concrete terms, the user accesses the server using a web browser or a dedicated app and operates the interface.

[1271] Step 7:

[1272] The server runs the simulation based on the user's settings. It takes the user's selected scenario and customized parameters as input and generates the simulation results as output. The specific behavior is that AI agents act while influencing each other in the virtual space.

[1273] Step 8:

[1274] The device uses a camera and microphone to collect user emotional data. The input is the user's facial expressions and voice, and the output is analyzed emotional data. Specifically, the device performs real-time emotional analysis using OpenCV or Azure Cognitive Services.

[1275] Step 9:

[1276] The server adjusts the simulation based on the analyzed emotional data. It takes the user's emotional data as input and generates adjusted simulation results as output. Specifically, it displays detailed results if the user is excited, and summarizes the results briefly if the user is stressed.

[1277] Step 10:

[1278] The device provides recommended scenarios and parameter settings based on the analyzed emotional data. It receives emotional data as input and provides recommended scenarios and parameters as output. Specifically, it recommends a high-difficulty scenario if the user is relaxed, and an easy scenario if the user is tense.

[1279] The above is the specific processing flow of this system.

[1280] (Application example 2)

[1281] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1282] Conventional content delivery systems provide content without considering the user's emotional state, resulting in insufficient personalization of user interactions and difficulty in improving user satisfaction. Furthermore, the lack of technology to dynamically adjust content based on the user's emotions in real time makes it difficult to provide services that meet individual needs.

[1283] The identification processing by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting information data from a data source, means for analyzing and tagging the collected information data, means for training an artificial intelligence model based on the tagged information data, means for constructing a virtual environment using the trained artificial intelligence model, means for accepting input from a user terminal and executing a simulation, means for analyzing the simulation results and providing them to the user terminal, means for collecting user emotion data and analyzing it with an emotion engine, and means for dynamically adjusting the simulation and content based on the emotion data. This enables personalized content delivery based on the user's emotional state, which is expected to improve user satisfaction.

[1284] "Data sources" are the various information sources that the system uses to gather information.

[1285] "Information Data" means historical, statistical, or other type of data obtained from a data source.

[1286] "Analysis" is the process of processing collected information data and extracting specific meanings and patterns.

[1287] "Tagging" is the process of adding metadata and identifying information to analyzed data.

[1288] An "artificial intelligence model" is a computational model that learns from data and makes predictions and distinctions.

[1289] "Training" is the learning process of providing an artificial intelligence model with the necessary data to improve the accuracy of its predictions and identification.

[1290] A "virtual environment" is a simulated environment generated by a computer program with which humans can interact.

[1291] A "user terminal" is a device (e.g., smartphone, PC, tablet, etc.) that a user uses to perform operations or input data.

[1292] "Simulation" is a technology that reproduces real-world phenomena and processes on a computer and performs analysis and predictions.

[1293] "Emotion data" is information about emotions obtained from the user's facial expressions, voice, etc.

[1294] An "emotion engine" is an algorithm or program that analyzes collected emotion data and identifies the user's emotional state.

[1295] "Dynamic adjustment" refers to the process of changing in response to real-time conditions.

[1296] The present invention relates to a system for recognizing user emotions and dynamically adjusting content delivery based on the emotion data. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS ... will be described in detail below.

[1297] System Overview

[1298] The system consists of a server, a user terminal, and an emotion engine. The server performs processes such as data collection and analysis, training of artificial intelligence models, and construction of virtual environments. The user terminal serves as the user's interface, collecting emotion data and displaying simulation results. The emotion engine analyzes the user's emotions and provides feedback to the system.

[1299] Hardware and software used

[1300] Hardware: Smartphones, smart glasses, head-mounted displays

[1301] Software: OpenCV (facial expression analysis), Google Cloud Speech-to-Text (voice analysis), TensorFlow and Keras (AI model training), Unity and Unreal Engine (virtual environment creation), AWS or Google Cloud Platform (server)

[1302] Program Overview

[1303] The server collects, analyzes, and tags information data from data sources. It then uses the tagged data to train an artificial intelligence model and uses this model to build a virtual environment. The user device collects the user's emotion data through a camera and microphone and analyzes the data through an emotion engine. Based on the data analyzed by the emotion engine, the server dynamically adjusts the simulation and provides the results to the user device.

[1304] Specific examples

[1305] For example, while a user is watching a drama series, the system uses the smartphone's camera and microphone to collect the user's facial expressions and voice in real time. The collected data is analyzed using OpenCV and Google Cloud Speech-to-Text, and the emotional engine identifies the user's emotional state. Based on the identified emotional state, the server dynamically adjusts the viewing content and even suggests related content recommendations. This process allows users to seamlessly enjoy content that matches their emotions.

[1306] Prompt Sentence Examples

[1307] "Recommend what content to watch next based on user sentiment data and viewing history."

[1308] As a result, a system built on the basis of the present invention realizes personalized content delivery to increase user engagement.

[1309] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1310] Step 1:

[1311] The server collects information data from data sources. Specifically, it retrieves data from databases and online repositories using APIs and web scraping techniques. The input is information data from external data sources, and the output is the collected information data.

[1312] Step 2:

[1313] The server analyzes and tags the collected information data. Specifically, it performs data cleansing to remove duplicate and missing data. It then uses NLP technology to extract important information and assign appropriate tags. The input is the collected information data, and the output is the analyzed and tagged data.

[1314] Step 3:

[1315] The server uses the tagged data to train an AI model. Specifically, it uses TensorFlow and Keras to feed the data and apply machine learning algorithms to train the model. The input is the parsed and tagged data, and the output is the trained AI model.

[1316] Step 4:

[1317] The server uses a trained AI model to build a virtual environment. Specifically, it uses Unity or Unreal Engine for 3D modeling and designs the virtual space in detail. The input is the trained AI model, and the output is the constructed virtual environment.

[1318] Step 5:

[1319] The device uses a camera and microphone to collect the user's emotional data in real time. The collected data is analyzed by an emotion engine to identify the user's emotional state. The input is the user's facial and voice data, and the output is the analyzed emotional data.

[1320] Step 6:

[1321] The server receives the user's emotional data analyzed by the emotion engine, runs the simulation, and dynamically adjusts the results. This includes displaying the simulation results in detail and recommending the next content to watch according to the user's emotions. The input is the analyzed emotional data and the virtual environment, and the output is the dynamically adjusted simulation results.

[1322] Step 7:

[1323] The terminal provides the user with the simulation results and content recommendations received from the server, providing visual and auditory feedback to help the user decide on their next action. The input is the dynamically adjusted simulation results, and the output is feedback to the user.

[1324] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[1325] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1326] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1327] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1328] FIG. 9 is a diagram illustrating an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1329] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[1330] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[1331] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[1332] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs 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 a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[1333] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[1334] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[1335] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[1336] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[1337] 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.

[1338] It is not necessary to store all 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 all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[1339] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[1340] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with 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). Also, the hardware resource that executes the specific processing may be a single processor.

[1341] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[1342] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[1343] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[1344] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[1345] The following is further disclosed regarding the above embodiment.

[1346] (Claim 1)

[1347] a means of collecting historical data from data sources;

[1348] a means for analyzing and tagging the collected historical data;

[1349] A means of training an artificial intelligence model based on the tagged historical data; and

[1350] a means for constructing a virtual environment using the trained artificial intelligence model; and

[1351] means for receiving input from a user terminal and executing a simulation;

[1352] means for analyzing the simulation results and providing them to a user terminal;

[1353] A system including:

[1354] (Claim 2)

[1355] 10. The system of claim 1, further comprising means for allowing artificial intelligence agents located within the virtual environment to interact with each other as the simulation progresses.

[1356] (Claim 3)

[1357] 10. The system of claim 1, further comprising means for enabling scenario selection and parameter setting based on user interaction.

[1358] "Example 1"

[1359] (Claim 1)

[1360] a means of collecting historical data from data sources;

[1361] A means of formatting and cleansing the collected historical data;

[1362] a means for tagging the cleansed historical data using natural language processing techniques;

[1363] A means of training an artificial intelligence model on the tagged historical data; and

[1364] a means for constructing a virtual environment using the trained artificial intelligence model; and

[1365] a means for accepting input from a user terminal and customizing simulation settings;

[1366] means for running a simulation based on the customized settings;

[1367] means for analyzing the simulation results and providing them to a user terminal;

[1368] A system including:

[1369] (Claim 2)

[1370] 10. The system of claim 1, further comprising means for allowing artificial intelligence agents located within the virtual environment to interact with each other as the simulation progresses.

[1371] (Claim 3)

[1372] 10. The system of claim 1, further comprising means for enabling scenario selection and parameter setting based on user interaction.

[1373] "Application Example 1"

[1374] (Claim 1)

[1375] a means of collecting historical data from data sources;

[1376] A means of analyzing and tagging the collected historical data;

[1377] A means to train a generative AI model based on tagged historical data; and

[1378] a means for constructing a virtual environment using the trained generative AI model; and

[1379] means for receiving input from a user terminal and executing a simulation;

[1380] A means to provide real-time information useful for customer service in physical stores,

[1381] means for analyzing the simulation results and providing them to a user terminal;

[1382] A system including:

[1383] (Claim 2)

[1384] 10. The system of claim 1, further comprising: means for AI agents located within the virtual environment to interact with each other as the simulation progresses; and means for providing sales forecast information in real time via the smart glasses.

[1385] (Claim 3)

[1386] 10. The system of claim 1, further comprising means for enabling scenario selection and parameter setting based on user interaction.

[1387] "Example 2: Combining Emotion Engines"

[1388] (Claim 1)

[1389] a means of collecting historical data from data sources;

[1390] a means for analyzing and tagging the collected historical data;

[1391] A means of training an artificial intelligence model based on the tagged historical data; and

[1392] a means for constructing a virtual environment using the trained artificial intelligence model; and

[1393] means for receiving input from a user terminal and executing a simulation;

[1394] means for analyzing user emotion data;

[1395] means for adjusting the simulation based on the analyzed emotion data;

[1396] a means for providing recommended scenarios and parameter settings based on the analyzed emotion data; and

[1397] means for analyzing the simulation results and providing them to a user terminal;

[1398] A system including:

[1399] (Claim 2)

[1400] 10. The system of claim 1, further comprising means for allowing artificial intelligence agents located within the virtual environment to interact with each other as the simulation progresses.

[1401] (Claim 3)

[1402] 10. The system of claim 1, further comprising means for enabling scenario selection and parameter setting based on user interaction.

[1403] "Application example 2 when combining emotion engines"

[1404] (Claim 1)

[1405] a means for collecting information data from a data source;

[1406] a means for analyzing and tagging the collected information data;

[1407] a means for training an artificial intelligence model based on the tagged information data; and

[1408] a means for constructing a virtual environment using the trained artificial intelligence model; and

[1409] means for receiving input from a user terminal and executing a simulation;

[1410] means for analyzing the simulation results and providing them to a user terminal;

[1411] A means for collecting user emotion data and analyzing it with an emotion engine;

[1412] means for dynamically adjusting the simulation and content based on the emotional data;

[1413] A system including:

[1414] (Claim 2)

[1415] 10. The system of claim 1, further comprising means for allowing artificial intelligence agents located within the virtual environment to interact with each other as the simulation progresses.

[1416] (Claim 3)

[1417] 10. The system of claim 1, further comprising means for enabling scenario selection and parameter setting based on user interaction. [Explanation of symbols]

[1418] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. a means of collecting historical data from data sources; a means for analyzing and tagging the collected historical data; A means of training an artificial intelligence model based on the tagged historical data; and a means for constructing a virtual environment using the trained artificial intelligence model; and means for receiving input from a user terminal and executing a simulation; means for analyzing the simulation results and providing them to a user terminal; A system including:

2. 2. The system according to claim 1, further comprising means for allowing artificial intelligence agents located within the virtual environment to interact with each other as the simulation progresses.

3. The system of claim 1 , further comprising means for allowing scenario selection and parameter setting based on user interaction.

Images