System

Abstract

System for analyzing simulation content input by user and visualizing result SOLUTION: A system comprising: means for inputting a simulation content from a user; means for analyzing the simulation content acquired from the inputting means; means for generating a 3D model based on the content analyzed by the analyzing means; means for executing a simulation using the 3D model generated by the generating means; and means for visualizing a result of the simulation executed by the executing means.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] Digital twin technology is effective for various simulations, but there is a problem in that its construction requires huge human and financial costs. Furthermore, specialized knowledge is required, making it difficult for only a limited number of experts to handle. For this reason, there is a demand for a platform that allows general users to easily use digital twin technology. [Means for solving the problem]

[0005] To solve the above-mentioned problems, the present invention provides the following means: a system including a means for inputting simulation content from a user, an analysis means for analyzing the input simulation content, a generation means for generating a 3D model based on the analysis results, an execution means for executing a simulation using the generated 3D model, and a visualization means for visualizing the results of the executed simulation. This system allows users to intuitively generate digital twins and perform simulations even without specialized knowledge. Furthermore, by utilizing the generative AI model, human and financial costs can be significantly reduced.

[0006] The "user input means" is a means by which the user can input the content that he or she wants to simulate.

[0007] The "analysis means" is a means for interpreting the simulation content input by the user and extracting the necessary objects and their interactions.

[0008] The "generation means" is a means for generating a 3D model of an object based on the content analyzed by the analysis means.

[0009] The "execution means" is a means for performing a simulation using the generated 3D model.

[0010] The "visualization means" is a means for visually displaying the simulation results to the user.

[0011] An "object" is a physical or conceptual phenomenon or element included in the simulation content.

[0012] "Interaction" refers to how objects affect each other in a simulation.

[0013] A "3D model" is digital data that represents the shape, movement, and physical characteristics of an object in three dimensions.

[0014] "Simulation" is the process of reproducing real-world phenomena and behaviors in a virtual environment.

[0015] A "generative AI model" is an artificial intelligence model that interprets user input and infers and generates the required 3D models and their interactions. [Brief explanation of the drawings]

[0016] [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

[0017] 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.

[0018] First, the terms used in the following description will be explained.

[0019] 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).

[0020] 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.

[0021] 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.

[0022] 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.

[0023] 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."

[0024] [First embodiment]

[0025] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0026] 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.

[0027] 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).

[0028] 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.

[0029] 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.

[0030] 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.

[0031] 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.

[0032] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0033] 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.

[0034] 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.

[0035] 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.

[0036] 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."

[0037] The present invention relates to a system that uses digital twin technology to automatically analyze simulation content entered by a user, generate the necessary 3D models, execute the simulation, and visualize the results. The specific system process for implementing the present invention and the processing between each step are as follows.

[0038] User Input Method

[0039] The user inputs the content they want to simulate into the terminal. The terminal receives the input from the user and prepares it to be sent to the server. For example, if the user inputs "simulation of a cat approaching a car," the content is sent to the server in text format.

[0040] Analysis means

[0041] The server passes the received user input to the generative AI model, which then analyzes the content. The generative AI model analyzes the input natural language text and extracts information about the objects (in this case, the cat and the car) required for the simulation, as well as their attributes and interactions.

[0042] generation means

[0043] The server then requests a generative AI model to create a 3D model based on the analyzed data. The generative AI model automatically generates a 3D model, taking into account the shape, movement, and physical characteristics of the object. At this stage, for example, a 3D model that mimics the shape and movement of a cat or a 3D model that expresses the movement of a car is generated.

[0044] Execution method

[0045] The generated 3D model is then passed to a simulation engine on the server, which simulates the interaction and movement of the objects. This process recreates the scene of how the cat and the car approach each other and, if necessary, avoid a collision.

[0046] Visualization means

[0047] When the simulation engine finishes the simulation, the results are sent from the server to the terminal, which displays the simulation results graphically. For example, the simulation result of a cat approaching a car is displayed to the user as a 3D animation.

[0048] Specific examples

[0049] Traffic simulation example

[0050] 1. User Input Method:

[0051] The user types "simulation of an intersection with four cars crossing."

[0052] The terminal sends this input to the server.

[0053] 2. Analysis method:

[0054] The server uses a generative AI model to analyze the content and extract the required objects (four cars) and their movements and interactions.

[0055] 3. Generation means:

[0056] The server generates 3D models of the four cars based on the analysis data.

[0057] 4. Implementation Method:

[0058] The server passes the generated 3D model to a simulation engine, which simulates the movement and interaction of cars at the intersection.

[0059] 5. Visualization means:

[0060] The server transmits the simulation results to the terminal, which displays the simulation results to the user.

[0061] As a result, by using the system of this invention, complex simulations can be performed automatically without specialist knowledge, and the results can be displayed in an easy-to-understand manner.The above-mentioned system has the advantage of enabling the generation of highly accurate digital twins while keeping human and financial costs down.

[0062] The processing flow will be explained below.

[0063] Step 1:

[0064] The user inputs the "content to be simulated" into the terminal. For example, they input "simulation of a cat approaching a car."

[0065] Step 2:

[0066] The terminal receives the user's input and sends it to the server.

[0067] Step 3:

[0068] The server passes the received user input to the generative AI model.

[0069] Step 4:

[0070] The generative AI model analyzes the text and extracts the objects needed for the simulation (in this case, the cat and the car), their attributes, and interactions. The analysis results include the names of the objects, their movement patterns, and interaction characteristics.

[0071] Step 5:

[0072] Based on the analysis results, the server requests the generative AI model to generate a 3D model, taking into account the shape, movement, and physical properties of the object.

[0073] Step 6:

[0074] A generative AI model generates a 3D model: for example, a 3D model of a cat includes the cat's shape and movement patterns, and a 3D model of a car includes the car's movement and physical properties.

[0075] Step 7:

[0076] The server passes the generated 3D model to the simulation engine.

[0077] Step 8:

[0078] The simulation engine uses the 3D model to run a simulation, simulating the cat's interaction with the car, its movements, collision avoidance, etc.

[0079] Step 9:

[0080] The server obtains the simulation results and sends them to the terminal.

[0081] Step 10:

[0082] The device receives the simulation results and displays them graphically to the user. For example, a scene of a cat approaching a car can be displayed as a 3D animation, allowing the user to visually confirm the detailed movement of the simulation results.

[0083] By following the above steps, the system can automatically generate a digital twin from user input, run a simulation, and visually display the results.

[0084] Example 1

[0085] 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."

[0086] Conventional simulation systems generally require users to have specialized knowledge to run a simulation, and require complex settings and manual work. Visualizing and analyzing the simulation results is also cumbersome and difficult to understand, which is an issue. These issues limit the use of simulation and increase the human and financial costs.

[0087] 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.

[0088] In this invention, the server includes an input means for inputting simulation content from a user, an analysis means for analyzing the simulation content acquired from the input means, a generation means for generating a three-dimensional model based on the content analyzed by the analysis means, an execution means for executing a simulation using the three-dimensional model generated by the generation means, and a visualization means for visualizing the results of the simulation executed by the execution means. This enables a user to execute a simulation without requiring specialized knowledge and to intuitively understand the results.

[0089] "User input means" refers to a device or interface that allows a user to input simulation content.

[0090] The "analysis means" is a device or program that has the function of analyzing the simulation content input by the user and extracting information on the necessary objects and their interactions.

[0091] The "generation means" is a device or program having the function of generating a three-dimensional model of an object based on the data analyzed by the analysis means.

[0092] The "execution means" is a device or program having the function of executing a simulation using the three-dimensional model generated by the generation means.

[0093] The "visualization means" is a device or program that graphically displays the results of the simulation executed by the execution means, allowing the user to visually confirm the results.

[0094] A "generative AI model" is an algorithm or program that analyzes the shape, movement, and physical properties of the object required for the simulation, and automatically generates a three-dimensional model based on the results.

[0095] A "prompt sentence" is text data used to pass the simulation content entered by the user to the analysis means or the generation AI model.

[0096] The present invention relates to a system that uses digital twin technology to automatically analyze simulation content entered by a user, generate the necessary three-dimensional models, execute the simulation, and visualize the results. The specific system configuration and processing between each step of the present invention are described below.

[0097] The system of the present invention comprises the following main means:

[0098] User Input Method

[0099] The user inputs the content they want to simulate into the terminal. The terminal receives the input from the user and sends the content in text format to the server. For example, if the user inputs "Simulation of a cat and a car approaching each other" into the text box, the content is sent to the server.

[0100] Analysis means

[0101] The server passes the received user input to the generative AI model, which analyzes the content. The generative AI model analyzes the input natural language text and extracts information about the objects required for the simulation (in this case, the cat and the car), as well as their attributes and interactions. Specifically, the generative AI model performs analysis using a prompt text. An example of a prompt text is "Simulation of a cat and a car approaching each other."

[0102] generation means

[0103] The server then requests a generative AI model to create a 3D model based on the analyzed data. The generative AI model automatically generates a 3D model, taking into account the shape, movement, and physical characteristics of the object. For example, a 3D model that mimics the shape and movement of a cat or a 3D model that expresses the movement of a car may be generated.

[0104] Execution method

[0105] The generated 3D model is then passed to a simulation engine on the server, which simulates the interaction and movement of the objects. This process recreates the scene of how the cat and the car approach each other and, if necessary, avoid a collision.

[0106] Visualization means

[0107] When the simulation engine finishes the simulation, the results are sent from the server to the terminal, which displays the simulation results graphically. For example, the simulation result of a cat approaching a car is displayed to the user as a 3D animation.

[0108] Specific examples

[0109] A specific example of traffic simulation is shown below.

[0110] Traffic simulation example

[0111] 1. User Input Method:

[0112] The user enters "Simulation of an intersection where four cars intersect" into the text box on the terminal and sends it from the terminal to the server.

[0113] 2. Analysis method:

[0114] The server receives the input and passes the prompt to the generative AI model, which parses the text "Simulation of an intersection with four cars" and extracts objects and their interactions.

[0115] 3. Generation means:

[0116] Based on the analyzed data, the server requests the AI ​​model to generate three-dimensional models of the four cars and obtains the generated three-dimensional models.

[0117] 4. Implementation Method:

[0118] The server passes the generated 3D model to a simulation engine, which simulates the movement and interaction of cars at the intersection.

[0119] 5. Visualization means:

[0120] The server sends the simulation results to the terminal, which displays the results to the user as a three-dimensional animation.

[0121] In this way, by using the system of this invention, users can automatically perform complex simulations without specialized knowledge and intuitively understand the results, making it possible to generate highly accurate digital twins while reducing human and financial costs.

[0122] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0123] Step 1: User Input

[0124] The user uses the input interface (e.g., text box) of the terminal to input the simulation content. Specifically, the user inputs a prompt sentence such as "Simulation of a cat approaching a car." The input prompt sentence is saved as text data in the terminal.

[0125] Input: Simulation content entered by the user (text format)

[0126] Output: Text data (simulation content)

[0127] Step 2: Prepare and send

[0128] The terminal generates data packets to transmit the stored text data to the server, and the packetized data is transmitted to the server over a network.

[0129] Input: Text data (simulation content)

[0130] Output: Data packet (including text data)

[0131] Step 3: Receiving data

[0132] The server receives the data packet sent from the terminal, acquires its contents, and saves them as text data.

[0133] Input: Data packet (contains text data)

[0134] Output: Text data (simulation content saved on the server)

[0135] Step 4: Analysis

[0136] The server passes the received text data to the generative AI model and requests it to analyze it. The generative AI model analyzes the prompt and extracts the objects (cat and car) and their attributes (size, movement, physical properties, etc.) required for the simulation.

[0137] Input: Text data (simulation content)

[0138] Output: Analysis results (objects and their attributes)

[0139] Step 5: Request for 3D model generation

[0140] The server then requests the generative AI model to generate a 3D model based on the analysis results. The generative AI model then generates a 3D model that takes into account the shape, movement, and physical properties of the specified object.

[0141] Input: Analysis results (objects and their attributes)

[0142] Output: 3D model data

[0143] Step 6: Run the simulation

[0144] The generated 3D model data is passed to the simulation engine on the server, where a simulation is run. The simulation engine reproduces how the cat and car approach each other, as well as collision and avoidance movements.

[0145] Input: 3D model data

[0146] Output: Simulation results

[0147] Step 7: Prepare and submit results

[0148] The server converts the simulation results obtained from the simulation engine into data packets and transmits them to the terminal.

[0149] Input: Simulation results

[0150] Output: Data packet (contains simulation results)

[0151] Step 8: Receive and view the results

[0152] The terminal receives the data packets sent from the server, analyzes their contents, and displays them graphically, allowing the user to visually confirm the simulation results as a three-dimensional animation.

[0153] Input: Data packet (contains simulation results)

[0154] Output: Graphical display (simulation results)

[0155] The above is a description of the specific processing flow of the system and each step.

[0156] (Application example 1)

[0157] 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."

[0158] Conventional simulation systems often require specialized knowledge and complex operations, requiring users to input simulation content, analyze that content, generate a 3D model, run the simulation, and visualize the results. In particular, in the development of autonomous vehicles, traffic scenario simulations are frequently required, but there are few ways to perform these simulations easily and quickly, which poses a challenge in reducing development efficiency.

[0159] 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.

[0160] In this invention, the server includes an input means for inputting simulation content from a user, an analysis means for analyzing the simulation content acquired from the input means, a generation means for generating a 3D model based on the content analyzed by the analysis means, and a generation AI model that enables input of a simulation scenario in natural language for operational testing and prediction of an autonomous vehicle. This makes it possible to easily and quickly perform operational testing and prediction of an autonomous vehicle based on the simulation scenario input by the user in natural language.

[0161] The "input means" is a means for a user to input simulation contents via a terminal.

[0162] The "analysis means" is a means for analyzing the simulation contents input by the user and extracting the objects and their attributes required for the scenario.

[0163] "Generation means" refers to a means for generating a 3D model based on the analyzed scenario.

[0164] The "execution means" is a means for executing a simulation using the generated 3D model.

[0165] The "visualization means" is a means for graphically displaying the simulation results and providing them to the user.

[0166] A "generative AI model" is an artificial intelligence model that analyzes the content of a simulation scenario entered in natural language, extracts the necessary information, and processes it.

[0167] This invention relates to a system that allows a user to input simulation content including a traffic scenario in natural language, generates a 3D model based on the content, executes the simulation, and visualizes the results. In this embodiment, the system is configured using the following means.

[0168] System configuration

[0169] 1. Input Method

[0170] Users can input the content they want to simulate in natural language using their smartphone.

[0171] For example, the user inputs "simulation of cars and pedestrians at an intersection."

[0172] 2. Analysis method

[0173] The input simulation content is sent to the server and analyzed by a generative AI model (e.g., OpenAI's GPT-4).

[0174] From the analyzed content, objects (vehicles, pedestrians) and their attributes (direction, speed, position) are extracted.

[0175] 3. Generation means

[0176] Based on the extracted data, the server generates a 3D model of the object using a 3D modeling tool (e.g., Unity).

[0177] The shape, movement, and physical properties of the object are taken into account to generate the data required for the simulation.

[0178] 4. Means of Implementation

[0179] The generated 3D model is passed to a simulation engine (e.g., Unity's PhysX) and the simulation is performed.

[0180] This simulation is used to test and predict the behavior of autonomous vehicles.

[0181] 5. Visualization means

[0182] The results of the executed simulation are sent from the server to the smartphone and visualized as a 3D animation.

[0183] Users can check the simulation results on their smartphones.

[0184] Hardware and software used

[0185] Hardware

[0186] Smartphone: A device where users can enter data and check the results.

[0187] Server: A computer device for implementing the analysis means, generation means, and execution means.

[0188] software

[0189] Generative AI models, such as OpenAI's GPT-4, are used to analyze a user's natural language input and understand the simulation content.

[0190] 3D modeling tools: for example, Unity, used to generate 3D models of objects based on the analyzed content.

[0191] Simulation engine: For example, Unity's PhysX. Runs the simulation using the generated 3D model.

[0192] Specific examples

[0193] The user types "simulation of cars and pedestrians at an intersection" into their smartphone. The input is sent to the server and analyzed by OpenAI's GPT-4. Based on the analysis results, 3D models of cars and pedestrians are generated using Unity. These 3D models are then passed to Unity's PhysX simulation engine, which runs the simulation. Finally, the simulation results are sent to the smartphone and visualized as a 3D animation.

[0194] Example prompts for generative AI models

[0195] "Analyze the following scenario: A simulation of a car and pedestrians at an intersection. The car moves to avoid a pedestrian entering the intersection."

[0196] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0197] Step 1:

[0198] The user inputs the simulation content in natural language using the smartphone's input means. Specifically, the user enters "Simulation of cars and pedestrians at an intersection" in the input field displayed on the smartphone screen and presses the send button. The input data is in character string format.

[0199] Step 2:

[0200] The terminal sends the simulation content entered by the user to the server. Specifically, it sends the input data to the server's analysis means using an HTTP request. The server receives the simulation content in the form of a character string.

[0201] Step 3:

[0202] The server's analysis means passes the received simulation content to a generative AI model (e.g., GPT-4) for analysis. Specifically, the analysis means passes the input data to the generative AI model as a prompt: "Analyze the following scenario: A simulation of a car and pedestrians at an intersection. The car moves to avoid pedestrians entering the intersection." The generative AI model analyzes this prompt and extracts the objects (cars, pedestrians) and their attributes (direction, speed, position). The analysis results are output in JSON format.

[0203] Step 4:

[0204] The server's generation means generates 3D models based on the analyzed data. Specifically, based on the analysis results (JSON format), it uses Unity's API to generate 3D models of vehicles and pedestrians. The generated 3D models include the shape, movement, and physical properties of the objects. The generated 3D models are saved in file formats (.fbx or .glb).

[0205] Step 5:

[0206] The server's execution means passes the generated 3D model to a simulation engine (for example, Unity's PhysX) to execute the simulation. Specifically, the file path of the generated 3D model is passed to the simulation engine as input, and the simulation is executed. The simulation engine reproduces the movements of cars and pedestrians and simulates their interaction. The simulation results are output in the form of a simulation log and 3D animation.

[0207] Step 6:

[0208] The server's visualization means sends the simulation results to the terminal, where they are visualized. Specifically, the simulation results (3D animation) are sent to the smartphone as an HTTP response. The smartphone plays the received 3D animation on its screen and displays the simulation results to the user. The user can then check the simulation results on the smartphone screen.

[0209] 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.

[0210] The present invention utilizes digital twin technology to automatically analyze simulation content entered by the user, generate the necessary 3D models, run the simulation, and visualize the results. By combining this with an emotion engine that recognizes the user's emotions, the system adds a function to dynamically adjust the simulation content. The specific system process for implementing the present invention and the processing between each step are as follows:

[0211] User Input Method

[0212] The user inputs the content they want to simulate into the terminal. The terminal receives the input from the user and prepares it to be sent to the server. For example, if the user inputs "simulation of a cat approaching a car," the content is sent to the server in text format.

[0213] Analysis means

[0214] The server passes the received user input to the generative AI model, which then analyzes the content. The generative AI model analyzes the input natural language text and extracts information about the objects (in this case, the cat and the car) required for the simulation, as well as their attributes and interactions.

[0215] generation means

[0216] The server then requests the generative AI model to generate a 3D model based on the analyzed data. The generative AI model automatically generates a 3D model, taking into account the shape, movement, and physical properties of the object. At this stage, for example, a 3D model that mimics the shape and movement of a cat or a 3D model that expresses the movement of a car is generated.

[0217] Execution method

[0218] The generated 3D model is then passed to a simulation engine on the server, which simulates the interaction and movement of the objects. This process recreates the scene of how the cat and the car approach each other and, if necessary, avoid a collision.

[0219] Visualization means

[0220] When the simulation engine finishes the simulation, the results are sent from the server to the terminal, which displays the simulation results graphically. For example, the simulation result of a cat approaching a car is displayed to the user as a 3D animation.

[0221] Emotion Engine

[0222] The emotion engine installed on the server analyzes the user's facial expressions and voice and recognizes the user's emotions. To do this, the device uses sensor devices such as a camera and microphone to acquire the user's facial expression data and voice data, and sends it to the server.

[0223] Adjustment means

[0224] The server adjusts the simulation content based on the user's emotions recognized by the emotion engine. For example, if the user shows surprise or fear, the server will slow down the simulation speed or change the content to make it easier for the user to understand.

[0225] Specific examples

[0226] Traffic simulation example

[0227] 1. User Input Method:

[0228] The user types "simulation of an intersection with four cars crossing."

[0229] The terminal sends this input to the server.

[0230] 2. Analysis method:

[0231] The server uses a generative AI model to analyze the content and extract the required objects (four cars) and their movements and interactions.

[0232] 3. Generation means:

[0233] The server generates 3D models of the four cars based on the analysis data.

[0234] 4. Implementation Method:

[0235] The server passes the generated 3D model to a simulation engine, which simulates the movement and interaction of cars at the intersection.

[0236] 5. Emotion Engine:

[0237] The server analyzes the user's emotions using an emotion engine and detects, for example, whether the user is nervous.

[0238] 6. Adjustment means:

[0239] To ease the user's tension, the server makes adjustments such as slowing down the simulation speed slightly.

[0240] 7. Visualization means:

[0241] The server transmits the adjusted simulation results to the terminal, and the terminal displays the simulation results to the user.

[0242] This allows the simulation content to be dynamically adjusted in response to the user's emotions, making it possible to provide a more user-friendly and intuitive simulation environment.The above-mentioned system is characterized by its high-precision generation and simulation of digital twins while keeping human and financial costs down, and by its ability to provide a high level of interactivity in response to the user's emotions.

[0243] The processing flow will be explained below.

[0244] Step 1:

[0245] The user inputs the "content to be simulated" into the terminal. For example, they input "simulation of a cat approaching a car."

[0246] Step 2:

[0247] The terminal receives the user's input and sends it to the server.

[0248] Step 3:

[0249] The server passes the received user input to the generative AI model.

[0250] Step 4:

[0251] The generative AI model analyzes the text and extracts the objects needed for the simulation (in this case, the cat and the car), their attributes, and interactions. The analysis results include the names of the objects, their movement patterns, and interaction characteristics.

[0252] Step 5:

[0253] Based on the analysis results, the server requests the generative AI model to generate a 3D model, taking into account the shape, movement, and physical properties of the object.

[0254] Step 6:

[0255] A generative AI model generates a 3D model: for example, a 3D model of a cat includes the cat's shape and movement patterns, and a 3D model of a car includes the car's movement and physical properties.

[0256] Step 7:

[0257] The server passes the generated 3D model to the simulation engine.

[0258] Step 8:

[0259] The simulation engine uses the 3D model to run a simulation, simulating the cat's interaction with the car, its movements, collision avoidance, etc.

[0260] Step 9:

[0261] The server obtains the simulation results and sends them to the terminal.

[0262] Step 10:

[0263] The device receives the simulation results and displays them graphically to the user. For example, a scene of a cat approaching a car can be displayed as a 3D animation, allowing the user to visually confirm the detailed movement of the simulation results.

[0264] Step 11:

[0265] The device's built-in camera and microphone are used to record the user's facial expressions and voice, and this data is sent to the server.

[0266] Step 12:

[0267] The server passes the received facial expression and voice data to the emotion engine, which analyzes this data and recognizes the user's emotions. For example, it can detect whether the user is surprised or nervous.

[0268] Step 13:

[0269] The server adjusts the simulation content based on the analysis results of the emotion engine. For example, if the user is surprised, it will slow down the simulation speed or simplify the content.

[0270] Step 14:

[0271] The server sends the adjusted simulation results back to the simulation engine for re-execution.

[0272] Step 15:

[0273] The simulation engine executes the adjusted simulation and sends the results back to the server.

[0274] Step 16:

[0275] The server sends the new simulation results to the terminal, which then displays them to the user. For example, the terminal reconfirms the user's reaction based on the adjusted simulation results and makes additional adjustments as necessary.

[0276] This allows the simulation content to be dynamically adjusted in response to the user's emotions, making it possible to provide a more user-friendly and intuitive simulation environment.The above-mentioned system is characterized by its high-precision generation and simulation of digital twins while keeping human and financial costs down, and by its ability to provide a high level of interactivity in response to the user's emotions.

[0277] Example 2

[0278] 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."

[0279] Conventional simulation systems execute simulations based on user input, but do not dynamically adjust to account for the user's emotional state, resulting in a limited user experience. Furthermore, it can be difficult to understand and interact with the simulation results, requiring intuitive operation and feedback.

[0280] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes an input means for inputting simulation content from a user, an analysis means for analyzing the simulation content acquired from the input means, a generation means for generating a 3D model based on the content analyzed by the analysis means, an execution means for executing a simulation using the 3D model generated by the generation means, a visualization means for visualizing the results of the simulation executed by the execution means, an emotion recognition means for recognizing the user's emotion, and an adjustment means for dynamically adjusting the simulation content based on the user's emotion recognized by the emotion recognition means. This improves the user experience and enables a more intuitive and interactive simulation.

[0281] The "input means" is a means for the user to input the simulation contents.

[0282] The "analysis means" is a means for analyzing the simulation content acquired from the input means.

[0283] The "generation means" is a means for generating a 3D model based on the content analyzed by the analysis means.

[0284] The "execution means" is a means for executing a simulation using the 3D model generated by the generation means.

[0285] The "visualization means" is a means for visualizing the results of the simulation executed by the execution means.

[0286] The "emotion recognition means" is a means for recognizing the user's emotions.

[0287] The "adjustment means" is a means for dynamically adjusting the simulation content based on the user's emotion recognized by the emotion recognition means.

[0288] This invention combines a system that allows users to input simulation content, analyzes that content, generates a 3D model, runs the simulation, and visualizes the results with an emotion engine that recognizes the user's emotions. This system improves the user experience and enables intuitive, interactive simulation.

[0289] 1. User Input Method

[0290] The user inputs the simulation content into the terminal. The terminal includes input devices such as a keyboard, mouse, and touch screen. This input content is saved in text format. For example, the user inputs "Simulation of a cat approaching a car."

[0291] 2. Sending Input

[0292] The terminal formats the user's input as text data and sends it to the server over the network, which can be the Internet or a local network. The input data is sent to the server in text format.

[0293] 3. Analysis method

[0294] The server receives the text data and passes it to the generative AI model, which uses natural language processing techniques to analyze the input text. Through this analysis, it extracts information about the objects (e.g., cats and cars) required for the simulation, as well as their attributes and interactions.

[0295] 4. 3D model generation method

[0296] Based on the analyzed information, the server requests a generative AI model to generate a 3D model. The generative AI model creates the 3D model taking into account the shape, movement, and physical characteristics. For example, a 3D model of a cat and a car is automatically generated and its movement is set.

[0297] 5. Simulation execution method

[0298] The generated 3D model is then passed to a simulation engine on the server, which simulates its interactions with other objects and physical movements, such as how a cat approaches a car and how it avoids collisions.

[0299] 6. Visualization means

[0300] The server sends the simulation results to the terminal. The terminal receives the simulation results and displays them to the user using a graphical display engine. For example, the simulation results can be shown to the user in real time as 3D animation.

[0301] 7. Emotion recognition means

[0302] The server is equipped with an emotion recognition engine and analyzes the user's emotions in real time through sensor devices such as cameras and microphones connected to the device, identifying emotions from the user's facial expressions and tone of voice, for example.

[0303] 8. Adjustment means

[0304] The server dynamically adjusts the simulation content based on the user's emotions recognized by the emotion recognition engine. For example, if the user expresses surprise or fear, it will slow down the simulation speed. The results of these adjustments are then sent back to the device and provided as feedback to the user.

[0305] Specific examples

[0306] Prompt Sentence Examples

[0307] The user inputs "simulation of an intersection where four cars intersect." The device sends this input to the server, which analyzes the content using a generative AI model and extracts the required objects (four cars) and their movements and interactions. The server generates 3D models of the four cars based on the analysis data, then passes them to the simulation engine, which simulates the movement of the cars at the intersection. The results are sent to the device, which displays the simulation results. The device also analyzes the user's emotions and dynamically adjusts the simulation content according to the results.

[0308] This allows for a simulation that responds to the user's emotions, making it possible to provide an intuitive and user-friendly simulation environment.

[0309] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0310] Step 1: User Input

[0311] The user inputs the simulation details into the terminal. Input devices include a keyboard, mouse, and touch screen. Specifically, the user inputs "Simulation of a cat approaching a car." The input data is saved in text format on the terminal. The next process is initiated based on the input data.

[0312] Step 2: Sending Input

[0313] The terminal sends the saved input data to the server via the network. The text data is formatted and sent to the server using the HTTP protocol, etc. Once the data arrives at the server, the next analysis step begins.

[0314] Step 3: Parsing the input

[0315] The server passes the text data received via the network to the generative AI model. The generative AI model performs text analysis using a natural language processing algorithm. Specifically, it extracts the necessary objects (e.g., "cat" and "car") and their interactions from the input text. The extracted results are the objects and their attribute data.

[0316] Step 4: 3D model generation

[0317] Based on the analysis results, the server requests the generative AI model to generate a 3D model. The generative AI model generates the 3D model by taking into account the shape, movement, and physical properties of the extracted object. For example, a 3D model of a cat is generated along with its movement, and a 3D model of a car is also generated according to its movement. The generated 3D model is then returned to the server.

[0318] Step 5: Run the simulation

[0319] The server inputs the generated 3D models into a simulation engine and runs the simulation. It simulates the interactions between the 3D models and their physical movements. For example, it simulates how a cat approaches a car and avoids a collision. The output of the simulation is generated as simulation data.

[0320] Step 6: Visualize the simulation results

[0321] The server sends the generated simulation data to the terminal. The terminal receives the simulation data and displays it to the user using a graphics display engine. For example, the simulation may be displayed as a 3D animation so that the user can check its details. As a result, a simulation video is displayed on the terminal.

[0322] Step 7: Recognizing User Emotions

[0323] The server analyzes the user's emotions using an emotion recognition engine. It captures facial expressions and voice in real time through sensor devices such as cameras and microphones connected to the device, and generates emotion data. For example, it can determine whether the user is expressing surprise.

[0324] Step 8: Adjust the simulation

[0325] The server dynamically adjusts the simulation content based on the emotional data analyzed by the emotion recognition engine. For example, if the user expresses surprise or fear, the server may adjust the speed of the simulation, such as slowing it down. The adjustment results are generated as new simulation data and resent to the device. The device then redisplays the adjusted simulation to the user.

[0326] Through the above steps, the processing of the entire system is completed, and optimized simulation results are provided to the user.

[0327] (Application example 2)

[0328] 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."

[0329] Current simulation systems can perform simulations by analyzing user input, generating 3D models, and visualizing the results. However, they lack the ability to dynamically adjust the simulation content according to the user's emotional state, which results in a lack of realism and interactivity to deepen the user's understanding. In particular, simulations of autonomous vehicles require appropriate speed adjustments and scenario changes according to the user's emotions.

[0330] The specific processing by the specific 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: input means for inputting simulation content from a user; analysis means for analyzing the simulation content acquired from the input means; generation means for generating a 3D model based on the content analyzed by the analysis means; execution means for executing a simulation using the 3D model generated by the generation means; visualization means for visualizing the results of the simulation executed by the execution means; an emotion engine for recognizing the emotional state of the user; and adjustment means for dynamically adjusting the simulation content based on the user's emotional state recognized by the emotion engine. This makes it possible to dynamically change the simulation content in accordance with the user's emotional state, providing a more intuitive and user-friendly simulation environment.

[0331] "User input means" refers to means by which a user inputs simulation content into a terminal.

[0332] The "analysis means" is a means for analyzing the simulation contents input by the user and extracting the objects required for the simulation, as well as their attributes and interactions.

[0333] The "generation means" is a means for automatically generating a 3D model based on the data obtained by the analysis means.

[0334] The "execution means" is a means for executing a simulation using the 3D model generated by the generation means.

[0335] The "visualization means" is a means for graphically displaying the results of the simulation executed by the execution means.

[0336] The "emotion engine" is an engine that analyzes the user's facial expression data and voice data to recognize the user's emotional state.

[0337] The "adjustment means" is a means for dynamically adjusting the simulation content based on the emotional state of the user recognized by the emotion engine.

[0338] 1. Overall system configuration:

[0339] This system consists of multiple components: a server, a terminal, and a user. The terminal provides an input means for the user to input simulation content. The server has an analysis means for analyzing the input content, a generation means for generating a 3D model based on the analysis results, an execution means for executing a simulation using the generated 3D model, a visualization means for visualizing the results of the executed simulation, an emotion engine for recognizing the user's emotional state, and an adjustment means for dynamically adjusting the simulation content based on the user's emotional state.

[0340] 2. Hardware and software configuration:

[0341] Hardware:

[0342] Smart glasses: Equipped with an input means for accepting user input, a data acquisition means for emotion recognition using a camera and microphone, and a display function for showing simulation results.

[0343] software:

[0344] EmotionRecognizer (emotion recognition library): An engine that analyzes the user's emotional state from their facial expressions and voice.

[0345] Simulation Engine: Software that runs simulations using 3D models.

[0346] ModelGenerator (3D model generation library): A library for generating 3D models for simulation.

[0347] 3. Processing Description:

[0348] User input means:

[0349] Using the smart glasses, users input the simulation content, for example, specifying a scenario such as "the behavior of an autonomous vehicle at an urban intersection."

[0350] Analysis method:

[0351] The server analyzes the scenario entered by the user and extracts the necessary objects (e.g., cars, intersections, traffic lights, etc.) and their attributes and interactions. This analysis is performed using a generative AI model.

[0352] Generation means:

[0353] Based on the analyzed data, the 3D model generation library (ModelGenerator) automatically generates a 3D model of the object, for example, a 3D model that mimics the shape and movement of a car.

[0354] To do this:

[0355] The generated 3D model is passed to a simulation engine, which simulates the scenario (e.g., the movement of a car at an intersection).

[0356] Visualization means:

[0357] The simulation results executed by the simulation engine are sent from the server to the terminal and displayed on the smart glasses display.

[0358] Emotion Engine:

[0359] The smart glasses use a built-in camera and microphone to capture and acquire the user's facial expression and voice data. EmotionRecognizer analyzes this data and recognizes the user's emotional state.

[0360] Adjustment means:

[0361] The emotion engine dynamically adjusts the simulation content based on the user's emotional state (e.g., surprise, fear) recognized by the emotion engine. For example, if the user shows surprise or fear, the simulation speed is slowed down.

[0362] 4. Example:

[0363] When a user inputs "self-driving car movement at an urban intersection," the generative AI model generates 3D models of the required objects (cars, intersections, traffic lights, etc.).

[0364] The simulation engine simulates the autonomous vehicle's movement through the intersection and displays the results on the smart glasses' display.

[0365] While the user is watching the simulation, the emotion engine analyzes the user's emotional state, and if it detects expressions of surprise or fear, it makes adjustments such as slowing down the speed of the simulation.

[0366] 5. Example prompt:

[0367] "Simulate the behavior of an autonomous vehicle at an urban intersection. Generate the necessary 3D models (buildings, traffic lights, vehicles, pedestrians, etc.) in the scenario to recreate how the vehicle will behave in a specific situation."

[0368] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0369] Step 1:

[0370] The user inputs the simulation content using smart glasses.

[0371] Input: The user enters the scenario: "Autonomous vehicle behavior at an urban intersection."

[0372] How it works: Accepts user voice and text input through the UI of the smart glasses.

[0373] Output: Simulation content (text format).

[0374] Step 2:

[0375] The terminal sends user input to the server, which parses it.

[0376] Input: User input (movement of an autonomous vehicle at an urban intersection).

[0377] How it works: The device sends input data to the server, which then uses a generative AI model to analyze the content, specifically extracting objects (cars, intersections, traffic lights, etc.).

[0378] Output: Analysis results (objects, their attributes and interactions).

[0379] Step 3:

[0380] The server generates a 3D model based on the analysis results.

[0381] Input: Analysis results (objects and their attributes and interactions).

[0382] How it works: The server uses the ModelGenerator library to generate 3D models of the extracted objects (cars, intersections, traffic lights, etc.).

[0383] Output: The generated 3D model.

[0384] Step 4:

[0385] The server runs a simulation using the generated 3D model.

[0386] Input: A generated 3D model.

[0387] How it works: The server runs a simulation using SimulationEngine to recreate a scenario (the movement of an autonomous vehicle at an urban intersection).

[0388] Output: Simulation results.

[0389] Step 5:

[0390] The server sends the simulation results to the terminal, which then visualizes them.

[0391] Input: Simulation results.

[0392] How it works: The server sends the simulation results to the device, which then displays a 3D animation of the simulation on the smart glasses display.

[0393] Output: Visualized simulation results.

[0394] Step 6:

[0395] The camera and microphone are used to recognize the user's emotional state through an emotion engine.

[0396] Input: User's facial expression data and voice data.

[0397] How it works: The smart glasses' camera and microphone are used to capture the user's facial expressions and voice, and the EmotionRecognizer library is used to analyze their emotional state.

[0398] Output: The user's emotional state (e.g., surprise, fear).

[0399] Step 7:

[0400] The server dynamically adjusts the simulation content based on the user's emotional state.

[0401] Input: User's emotional state (e.g., surprise, fear).

[0402] Operation: Depending on the emotional state, the server sends instructions to the simulation engine and makes adjustments such as slowing down the simulation speed.

[0403] Output: Adjusted simulation results.

[0404] 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.

[0405] 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.

[0406] 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.

[0407] [Second embodiment]

[0408] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0409] 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.

[0410] 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).

[0411] 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.

[0412] 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.

[0413] 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).

[0414] 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.

[0415] 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.

[0416] 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.

[0417] 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.

[0418] 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.

[0419] 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."

[0420] The present invention relates to a system that uses digital twin technology to automatically analyze simulation content entered by a user, generate the necessary 3D models, execute the simulation, and visualize the results. The specific system process for implementing the present invention and the processing between each step are as follows.

[0421] User Input Method

[0422] The user inputs the content they want to simulate into the terminal. The terminal receives the input from the user and prepares it to be sent to the server. For example, if the user inputs "simulation of a cat approaching a car," the content is sent to the server in text format.

[0423] Analysis means

[0424] The server passes the received user input to the generative AI model, which then analyzes the content. The generative AI model analyzes the input natural language text and extracts information about the objects (in this case, the cat and the car) required for the simulation, as well as their attributes and interactions.

[0425] generation means

[0426] The server then requests a generative AI model to create a 3D model based on the analyzed data. The generative AI model automatically generates a 3D model, taking into account the shape, movement, and physical characteristics of the object. At this stage, for example, a 3D model that mimics the shape and movement of a cat or a 3D model that expresses the movement of a car is generated.

[0427] Execution method

[0428] The generated 3D model is then passed to a simulation engine on the server, which simulates the interaction and movement of the objects. This process recreates the scene of how the cat and the car approach each other and, if necessary, avoid a collision.

[0429] Visualization means

[0430] When the simulation engine finishes the simulation, the results are sent from the server to the terminal, which displays the simulation results graphically. For example, the simulation result of a cat approaching a car is displayed to the user as a 3D animation.

[0431] Specific examples

[0432] Traffic simulation example

[0433] 1. User Input Method:

[0434] The user types "simulation of an intersection with four cars crossing."

[0435] The terminal sends this input to the server.

[0436] 2. Analysis method:

[0437] The server uses a generative AI model to analyze the content and extract the required objects (four cars) and their movements and interactions.

[0438] 3. Generation means:

[0439] The server generates 3D models of the four cars based on the analysis data.

[0440] 4. Implementation Method:

[0441] The server passes the generated 3D model to a simulation engine, which simulates the movement and interaction of cars at the intersection.

[0442] 5. Visualization means:

[0443] The server transmits the simulation results to the terminal, which displays the simulation results to the user.

[0444] As a result, by using the system of this invention, complex simulations can be performed automatically without specialist knowledge, and the results can be displayed in an easy-to-understand manner.The above-mentioned system has the advantage of enabling the generation of highly accurate digital twins while keeping human and financial costs down.

[0445] The processing flow will be explained below.

[0446] Step 1:

[0447] The user inputs the "content to be simulated" into the terminal. For example, they input "simulation of a cat approaching a car."

[0448] Step 2:

[0449] The terminal receives the user's input and sends it to the server.

[0450] Step 3:

[0451] The server passes the received user input to the generative AI model.

[0452] Step 4:

[0453] The generative AI model analyzes the text and extracts the objects needed for the simulation (in this case, the cat and the car), their attributes, and interactions. The analysis results include the names of the objects, their movement patterns, and interaction characteristics.

[0454] Step 5:

[0455] Based on the analysis results, the server requests the generative AI model to generate a 3D model, taking into account the shape, movement, and physical properties of the object.

[0456] Step 6:

[0457] A generative AI model generates a 3D model: for example, a 3D model of a cat includes the cat's shape and movement patterns, and a 3D model of a car includes the car's movement and physical properties.

[0458] Step 7:

[0459] The server passes the generated 3D model to the simulation engine.

[0460] Step 8:

[0461] The simulation engine uses the 3D model to run a simulation, simulating the cat's interaction with the car, its movements, collision avoidance, etc.

[0462] Step 9:

[0463] The server obtains the simulation results and sends them to the terminal.

[0464] Step 10:

[0465] The device receives the simulation results and displays them graphically to the user. For example, a scene of a cat approaching a car can be displayed as a 3D animation, allowing the user to visually confirm the detailed movement of the simulation results.

[0466] By following the above steps, the system can automatically generate a digital twin from user input, run a simulation, and visually display the results.

[0467] Example 1

[0468] 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."

[0469] Conventional simulation systems generally require users to have specialized knowledge to run a simulation, and require complex settings and manual work. Visualizing and analyzing the simulation results is also cumbersome and difficult to understand, which is an issue. These issues limit the use of simulation and increase the human and financial costs.

[0470] 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.

[0471] In this invention, the server includes an input means for inputting simulation content from a user, an analysis means for analyzing the simulation content acquired from the input means, a generation means for generating a three-dimensional model based on the content analyzed by the analysis means, an execution means for executing a simulation using the three-dimensional model generated by the generation means, and a visualization means for visualizing the results of the simulation executed by the execution means. This enables a user to execute a simulation without requiring specialized knowledge and to intuitively understand the results.

[0472] "User input means" refers to a device or interface that allows a user to input simulation content.

[0473] The "analysis means" is a device or program that has the function of analyzing the simulation content input by the user and extracting information on the necessary objects and their interactions.

[0474] The "generation means" is a device or program having the function of generating a three-dimensional model of an object based on the data analyzed by the analysis means.

[0475] The "execution means" is a device or program having the function of executing a simulation using the three-dimensional model generated by the generation means.

[0476] The "visualization means" is a device or program that graphically displays the results of the simulation executed by the execution means, allowing the user to visually confirm the results.

[0477] A "generative AI model" is an algorithm or program that analyzes the shape, movement, and physical properties of the object required for the simulation, and automatically generates a three-dimensional model based on the results.

[0478] A "prompt sentence" is text data used to pass the simulation content entered by the user to the analysis means or the generation AI model.

[0479] The present invention relates to a system that uses digital twin technology to automatically analyze simulation content entered by a user, generate the necessary three-dimensional models, execute the simulation, and visualize the results. The specific system configuration and processing between each step of the present invention are described below.

[0480] The system of the present invention comprises the following main means:

[0481] User Input Method

[0482] The user inputs the content they want to simulate into the terminal. The terminal receives the input from the user and sends the content in text format to the server. For example, if the user inputs "Simulation of a cat and a car approaching each other" into the text box, the content is sent to the server.

[0483] Analysis means

[0484] The server passes the received user input to the generative AI model, which analyzes the content. The generative AI model analyzes the input natural language text and extracts information about the objects required for the simulation (in this case, the cat and the car), as well as their attributes and interactions. Specifically, the generative AI model performs analysis using a prompt text. An example of a prompt text is "Simulation of a cat and a car approaching each other."

[0485] generation means

[0486] The server then requests a generative AI model to create a 3D model based on the analyzed data. The generative AI model automatically generates a 3D model, taking into account the shape, movement, and physical characteristics of the object. For example, a 3D model that mimics the shape and movement of a cat or a 3D model that expresses the movement of a car may be generated.

[0487] Execution method

[0488] The generated 3D model is then passed to a simulation engine on the server, which simulates the interaction and movement of the objects. This process recreates the scene of how the cat and the car approach each other and, if necessary, avoid a collision.

[0489] Visualization means

[0490] When the simulation engine finishes the simulation, the results are sent from the server to the terminal, which displays the simulation results graphically. For example, the simulation result of a cat approaching a car is displayed to the user as a 3D animation.

[0491] Specific examples

[0492] A specific example of traffic simulation is shown below.

[0493] Traffic simulation example

[0494] 1. User Input Method:

[0495] The user enters "Simulation of an intersection where four cars intersect" into the text box on the terminal and sends it from the terminal to the server.

[0496] 2. Analysis method:

[0497] The server receives the input and passes the prompt to the generative AI model, which parses the text "Simulation of an intersection with four cars" and extracts objects and their interactions.

[0498] 3. Generation means:

[0499] Based on the analyzed data, the server requests the AI ​​model to generate three-dimensional models of the four cars and obtains the generated three-dimensional models.

[0500] 4. Implementation Method:

[0501] The server passes the generated 3D model to a simulation engine, which simulates the movement and interaction of cars at the intersection.

[0502] 5. Visualization means:

[0503] The server sends the simulation results to the terminal, which displays the results to the user as a three-dimensional animation.

[0504] In this way, by using the system of this invention, users can automatically perform complex simulations without specialized knowledge and intuitively understand the results, making it possible to generate highly accurate digital twins while reducing human and financial costs.

[0505] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0506] Step 1: User Input

[0507] The user uses the input interface (e.g., text box) of the terminal to input the simulation content. Specifically, the user inputs a prompt sentence such as "Simulation of a cat approaching a car." The input prompt sentence is saved as text data in the terminal.

[0508] Input: Simulation content entered by the user (text format)

[0509] Output: Text data (simulation content)

[0510] Step 2: Prepare and send

[0511] The terminal generates data packets to transmit the stored text data to the server, and the packetized data is transmitted to the server over a network.

[0512] Input: Text data (simulation content)

[0513] Output: Data packet (including text data)

[0514] Step 3: Receiving data

[0515] The server receives the data packet sent from the terminal, acquires its contents, and saves them as text data.

[0516] Input: Data packet (contains text data)

[0517] Output: Text data (simulation content saved on the server)

[0518] Step 4: Analysis

[0519] The server passes the received text data to the generative AI model and requests it to analyze it. The generative AI model analyzes the prompt and extracts the objects (cat and car) and their attributes (size, movement, physical properties, etc.) required for the simulation.

[0520] Input: Text data (simulation content)

[0521] Output: Analysis results (objects and their attributes)

[0522] Step 5: Request for 3D model generation

[0523] The server then requests the generative AI model to generate a 3D model based on the analysis results. The generative AI model then generates a 3D model that takes into account the shape, movement, and physical properties of the specified object.

[0524] Input: Analysis results (objects and their attributes)

[0525] Output: 3D model data

[0526] Step 6: Run the simulation

[0527] The generated 3D model data is passed to the simulation engine on the server, where a simulation is run. The simulation engine reproduces how the cat and car approach each other, as well as collision and avoidance movements.

[0528] Input: 3D model data

[0529] Output: Simulation results

[0530] Step 7: Prepare and submit results

[0531] The server converts the simulation results obtained from the simulation engine into data packets and transmits them to the terminal.

[0532] Input: Simulation results

[0533] Output: Data packet (contains simulation results)

[0534] Step 8: Receive and view the results

[0535] The terminal receives the data packets sent from the server, analyzes their contents, and displays them graphically, allowing the user to visually confirm the simulation results as a three-dimensional animation.

[0536] Input: Data packet (contains simulation results)

[0537] Output: Graphical display (simulation results)

[0538] The above is a description of the specific processing flow of the system and each step.

[0539] (Application example 1)

[0540] 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."

[0541] Conventional simulation systems often require specialized knowledge and complex operations, requiring users to input simulation content, analyze that content, generate a 3D model, run the simulation, and visualize the results. In particular, in the development of autonomous vehicles, traffic scenario simulations are frequently required, but there are few ways to perform these simulations easily and quickly, which poses a challenge in reducing development efficiency.

[0542] 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.

[0543] In this invention, the server includes an input means for inputting simulation content from a user, an analysis means for analyzing the simulation content acquired from the input means, a generation means for generating a 3D model based on the content analyzed by the analysis means, and a generation AI model that enables input of a simulation scenario in natural language for operational testing and prediction of an autonomous vehicle. This makes it possible to easily and quickly perform operational testing and prediction of an autonomous vehicle based on the simulation scenario input by the user in natural language.

[0544] The "input means" is a means for a user to input simulation contents via a terminal.

[0545] The "analysis means" is a means for analyzing the simulation contents input by the user and extracting the objects and their attributes required for the scenario.

[0546] "Generation means" refers to a means for generating a 3D model based on the analyzed scenario.

[0547] The "execution means" is a means for executing a simulation using the generated 3D model.

[0548] The "visualization means" is a means for graphically displaying the simulation results and providing them to the user.

[0549] A "generative AI model" is an artificial intelligence model that analyzes the content of a simulation scenario entered in natural language, extracts the necessary information, and processes it.

[0550] This invention relates to a system that allows a user to input simulation content including a traffic scenario in natural language, generates a 3D model based on the content, executes the simulation, and visualizes the results. In this embodiment, the system is configured using the following means.

[0551] System configuration

[0552] 1. Input Method

[0553] Users can input the content they want to simulate in natural language using their smartphone.

[0554] For example, the user inputs "simulation of cars and pedestrians at an intersection."

[0555] 2. Analysis method

[0556] The input simulation content is sent to the server and analyzed by a generative AI model (e.g., OpenAI's GPT-4).

[0557] From the analyzed content, objects (vehicles, pedestrians) and their attributes (direction, speed, position) are extracted.

[0558] 3. Generation means

[0559] Based on the extracted data, the server generates a 3D model of the object using a 3D modeling tool (e.g., Unity).

[0560] The shape, movement, and physical properties of the object are taken into account to generate the data required for the simulation.

[0561] 4. Means of Implementation

[0562] The generated 3D model is passed to a simulation engine (e.g., Unity's PhysX) and the simulation is performed.

[0563] This simulation is used to test and predict the behavior of autonomous vehicles.

[0564] 5. Visualization means

[0565] The results of the executed simulation are sent from the server to the smartphone and visualized as a 3D animation.

[0566] Users can check the simulation results on their smartphones.

[0567] Hardware and software used

[0568] Hardware

[0569] Smartphone: A device where users can enter data and check the results.

[0570] Server: A computer device for implementing the analysis means, generation means, and execution means.

[0571] software

[0572] Generative AI models, such as OpenAI's GPT-4, are used to analyze a user's natural language input and understand the simulation content.

[0573] 3D modeling tools: for example, Unity, used to generate 3D models of objects based on the analyzed content.

[0574] Simulation engine: For example, Unity's PhysX. Runs the simulation using the generated 3D model.

[0575] Specific examples

[0576] The user types "simulation of cars and pedestrians at an intersection" into their smartphone. The input is sent to the server and analyzed by OpenAI's GPT-4. Based on the analysis results, 3D models of cars and pedestrians are generated using Unity. These 3D models are then passed to Unity's PhysX simulation engine, which runs the simulation. Finally, the simulation results are sent to the smartphone and visualized as a 3D animation.

[0577] Example prompts for generative AI models

[0578] "Analyze the following scenario: A simulation of a car and pedestrians at an intersection. The car moves to avoid a pedestrian entering the intersection."

[0579] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0580] Step 1:

[0581] The user inputs the simulation content in natural language using the smartphone's input means. Specifically, the user enters "Simulation of cars and pedestrians at an intersection" in the input field displayed on the smartphone screen and presses the send button. The input data is in character string format.

[0582] Step 2:

[0583] The terminal sends the simulation content entered by the user to the server. Specifically, it sends the input data to the server's analysis means using an HTTP request. The server receives the simulation content in the form of a character string.

[0584] Step 3:

[0585] The server's analysis means passes the received simulation content to a generative AI model (e.g., GPT-4) for analysis. Specifically, the analysis means passes the input data to the generative AI model as a prompt: "Analyze the following scenario: A simulation of a car and pedestrians at an intersection. The car moves to avoid pedestrians entering the intersection." The generative AI model analyzes this prompt and extracts the objects (cars, pedestrians) and their attributes (direction, speed, position). The analysis results are output in JSON format.

[0586] Step 4:

[0587] The server's generation means generates 3D models based on the analyzed data. Specifically, based on the analysis results (JSON format), it uses Unity's API to generate 3D models of vehicles and pedestrians. The generated 3D models include the shape, movement, and physical properties of the objects. The generated 3D models are saved in file formats (.fbx or .glb).

[0588] Step 5:

[0589] The server's execution means passes the generated 3D model to a simulation engine (for example, Unity's PhysX) to execute the simulation. Specifically, the file path of the generated 3D model is passed to the simulation engine as input, and the simulation is executed. The simulation engine reproduces the movements of cars and pedestrians and simulates their interaction. The simulation results are output in the form of a simulation log and 3D animation.

[0590] Step 6:

[0591] The server's visualization means sends the simulation results to the terminal, where they are visualized. Specifically, the simulation results (3D animation) are sent to the smartphone as an HTTP response. The smartphone plays the received 3D animation on its screen and displays the simulation results to the user. The user can then check the simulation results on the smartphone screen.

[0592] 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.

[0593] The present invention utilizes digital twin technology to automatically analyze simulation content entered by the user, generate the necessary 3D models, run the simulation, and visualize the results. By combining this with an emotion engine that recognizes the user's emotions, the system adds a function to dynamically adjust the simulation content. The specific system process for implementing the present invention and the processing between each step are as follows:

[0594] User Input Method

[0595] The user inputs the content they want to simulate into the terminal. The terminal receives the input from the user and prepares it to be sent to the server. For example, if the user inputs "simulation of a cat approaching a car," the content is sent to the server in text format.

[0596] Analysis means

[0597] The server passes the received user input to the generative AI model, which then analyzes the content. The generative AI model analyzes the input natural language text and extracts information about the objects (in this case, the cat and the car) required for the simulation, as well as their attributes and interactions.

[0598] generation means

[0599] The server then requests the generative AI model to generate a 3D model based on the analyzed data. The generative AI model automatically generates a 3D model, taking into account the shape, movement, and physical properties of the object. At this stage, for example, a 3D model that mimics the shape and movement of a cat or a 3D model that expresses the movement of a car is generated.

[0600] Execution method

[0601] The generated 3D model is then passed to a simulation engine on the server, which simulates the interaction and movement of the objects. This process recreates the scene of how the cat and the car approach each other and, if necessary, avoid a collision.

[0602] Visualization means

[0603] When the simulation engine finishes the simulation, the results are sent from the server to the terminal, which displays the simulation results graphically. For example, the simulation result of a cat approaching a car is displayed to the user as a 3D animation.

[0604] Emotion Engine

[0605] The emotion engine installed on the server analyzes the user's facial expressions and voice and recognizes the user's emotions. To do this, the device uses sensor devices such as a camera and microphone to acquire the user's facial expression data and voice data, and sends it to the server.

[0606] Adjustment means

[0607] The server adjusts the simulation content based on the user's emotions recognized by the emotion engine. For example, if the user shows surprise or fear, the server will slow down the simulation speed or change the content to make it easier for the user to understand.

[0608] Specific examples

[0609] Traffic simulation example

[0610] 1. User Input Method:

[0611] The user types "simulation of an intersection with four cars crossing."

[0612] The terminal sends this input to the server.

[0613] 2. Analysis method:

[0614] The server uses a generative AI model to analyze the content and extract the required objects (four cars) and their movements and interactions.

[0615] 3. Generation means:

[0616] The server generates 3D models of the four cars based on the analysis data.

[0617] 4. Implementation Method:

[0618] The server passes the generated 3D model to a simulation engine, which simulates the movement and interaction of cars at the intersection.

[0619] 5. Emotion Engine:

[0620] The server analyzes the user's emotions using an emotion engine and detects, for example, whether the user is nervous.

[0621] 6. Adjustment means:

[0622] To ease the user's tension, the server makes adjustments such as slowing down the simulation speed slightly.

[0623] 7. Visualization means:

[0624] The server transmits the adjusted simulation results to the terminal, and the terminal displays the simulation results to the user.

[0625] This allows the simulation content to be dynamically adjusted in response to the user's emotions, making it possible to provide a more user-friendly and intuitive simulation environment.The above-mentioned system is characterized by its high-precision generation and simulation of digital twins while keeping human and financial costs down, and by its ability to provide a high level of interactivity in response to the user's emotions.

[0626] The processing flow will be explained below.

[0627] Step 1:

[0628] The user inputs the "content to be simulated" into the terminal. For example, they input "simulation of a cat approaching a car."

[0629] Step 2:

[0630] The terminal receives the user's input and sends it to the server.

[0631] Step 3:

[0632] The server passes the received user input to the generative AI model.

[0633] Step 4:

[0634] The generative AI model analyzes the text and extracts the objects needed for the simulation (in this case, the cat and the car), their attributes, and interactions. The analysis results include the names of the objects, their movement patterns, and interaction characteristics.

[0635] Step 5:

[0636] Based on the analysis results, the server requests the generative AI model to generate a 3D model, taking into account the shape, movement, and physical properties of the object.

[0637] Step 6:

[0638] A generative AI model generates a 3D model: for example, a 3D model of a cat includes the cat's shape and movement patterns, and a 3D model of a car includes the car's movement and physical properties.

[0639] Step 7:

[0640] The server passes the generated 3D model to the simulation engine.

[0641] Step 8:

[0642] The simulation engine uses the 3D model to run a simulation, simulating the cat's interaction with the car, its movements, collision avoidance, etc.

[0643] Step 9:

[0644] The server obtains the simulation results and sends them to the terminal.

[0645] Step 10:

[0646] The device receives the simulation results and displays them graphically to the user. For example, a scene of a cat approaching a car can be displayed as a 3D animation, allowing the user to visually confirm the detailed movement of the simulation results.

[0647] Step 11:

[0648] The device's built-in camera and microphone are used to record the user's facial expressions and voice, and this data is sent to the server.

[0649] Step 12:

[0650] The server passes the received facial expression and voice data to the emotion engine, which analyzes this data and recognizes the user's emotions. For example, it can detect whether the user is surprised or nervous.

[0651] Step 13:

[0652] The server adjusts the simulation content based on the analysis results of the emotion engine. For example, if the user is surprised, it will slow down the simulation speed or simplify the content.

[0653] Step 14:

[0654] The server sends the adjusted simulation results back to the simulation engine for re-execution.

[0655] Step 15:

[0656] The simulation engine executes the adjusted simulation and sends the results back to the server.

[0657] Step 16:

[0658] The server sends the new simulation results to the terminal, which then displays them to the user. For example, the terminal reconfirms the user's reaction based on the adjusted simulation results and makes additional adjustments as necessary.

[0659] This allows the simulation content to be dynamically adjusted in response to the user's emotions, making it possible to provide a more user-friendly and intuitive simulation environment.The above-mentioned system is characterized by its high-precision generation and simulation of digital twins while keeping human and financial costs down, and by its ability to provide a high level of interactivity in response to the user's emotions.

[0660] Example 2

[0661] 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."

[0662] Conventional simulation systems execute simulations based on user input, but do not dynamically adjust to account for the user's emotional state, resulting in a limited user experience. Furthermore, it can be difficult to understand and interact with the simulation results, requiring intuitive operation and feedback.

[0663] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes an input means for inputting simulation content from a user, an analysis means for analyzing the simulation content acquired from the input means, a generation means for generating a 3D model based on the content analyzed by the analysis means, an execution means for executing a simulation using the 3D model generated by the generation means, a visualization means for visualizing the results of the simulation executed by the execution means, an emotion recognition means for recognizing the user's emotion, and an adjustment means for dynamically adjusting the simulation content based on the user's emotion recognized by the emotion recognition means. This improves the user experience and enables a more intuitive and interactive simulation.

[0664] The "input means" is a means for the user to input the simulation contents.

[0665] The "analysis means" is a means for analyzing the simulation content acquired from the input means.

[0666] The "generation means" is a means for generating a 3D model based on the content analyzed by the analysis means.

[0667] The "execution means" is a means for executing a simulation using the 3D model generated by the generation means.

[0668] The "visualization means" is a means for visualizing the results of the simulation executed by the execution means.

[0669] The "emotion recognition means" is a means for recognizing the user's emotions.

[0670] The "adjustment means" is a means for dynamically adjusting the simulation content based on the user's emotion recognized by the emotion recognition means.

[0671] This invention combines a system that allows users to input simulation content, analyzes that content, generates a 3D model, runs the simulation, and visualizes the results with an emotion engine that recognizes the user's emotions. This system improves the user experience and enables intuitive, interactive simulation.

[0672] 1. User Input Method

[0673] The user inputs the simulation content into the terminal. The terminal includes input devices such as a keyboard, mouse, and touch screen. This input content is saved in text format. For example, the user inputs "Simulation of a cat approaching a car."

[0674] 2. Sending Input

[0675] The terminal formats the user's input as text data and sends it to the server over the network, which can be the Internet or a local network. The input data is sent to the server in text format.

[0676] 3. Analysis method

[0677] The server receives the text data and passes it to the generative AI model, which uses natural language processing techniques to analyze the input text. Through this analysis, it extracts information about the objects (e.g., cats and cars) required for the simulation, as well as their attributes and interactions.

[0678] 4. 3D model generation method

[0679] Based on the analyzed information, the server requests a generative AI model to generate a 3D model. The generative AI model creates the 3D model taking into account the shape, movement, and physical characteristics. For example, a 3D model of a cat and a car is automatically generated and its movement is set.

[0680] 5. Simulation execution method

[0681] The generated 3D model is then passed to a simulation engine on the server, which simulates its interactions with other objects and physical movements, such as how a cat approaches a car and how it avoids collisions.

[0682] 6. Visualization means

[0683] The server sends the simulation results to the terminal. The terminal receives the simulation results and displays them to the user using a graphical display engine. For example, the simulation results can be shown to the user in real time as 3D animation.

[0684] 7. Emotion recognition means

[0685] The server is equipped with an emotion recognition engine and analyzes the user's emotions in real time through sensor devices such as cameras and microphones connected to the device, identifying emotions from the user's facial expressions and tone of voice, for example.

[0686] 8. Adjustment means

[0687] The server dynamically adjusts the simulation content based on the user's emotions recognized by the emotion recognition engine. For example, if the user expresses surprise or fear, it will slow down the simulation speed. The results of these adjustments are then sent back to the device and provided as feedback to the user.

[0688] Specific examples

[0689] Prompt Sentence Examples

[0690] The user inputs "simulation of an intersection where four cars intersect." The device sends this input to the server, which analyzes the content using a generative AI model and extracts the required objects (four cars) and their movements and interactions. The server generates 3D models of the four cars based on the analysis data, then passes them to the simulation engine, which simulates the movement of the cars at the intersection. The results are sent to the device, which displays the simulation results. The device also analyzes the user's emotions and dynamically adjusts the simulation content according to the results.

[0691] This allows for a simulation that responds to the user's emotions, making it possible to provide an intuitive and user-friendly simulation environment.

[0692] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0693] Step 1: User Input

[0694] The user inputs the simulation details into the terminal. Input devices include a keyboard, mouse, and touch screen. Specifically, the user inputs "Simulation of a cat approaching a car." The input data is saved in text format on the terminal. The next process is initiated based on the input data.

[0695] Step 2: Sending Input

[0696] The terminal sends the saved input data to the server via the network. The text data is formatted and sent to the server using the HTTP protocol, etc. Once the data arrives at the server, the next analysis step begins.

[0697] Step 3: Parsing the input

[0698] The server passes the text data received via the network to the generative AI model. The generative AI model performs text analysis using a natural language processing algorithm. Specifically, it extracts the necessary objects (e.g., "cat" and "car") and their interactions from the input text. The extracted results are the objects and their attribute data.

[0699] Step 4: 3D model generation

[0700] Based on the analysis results, the server requests the generative AI model to generate a 3D model. The generative AI model generates the 3D model by taking into account the shape, movement, and physical properties of the extracted object. For example, a 3D model of a cat is generated along with its movement, and a 3D model of a car is also generated according to its movement. The generated 3D model is then returned to the server.

[0701] Step 5: Run the simulation

[0702] The server inputs the generated 3D models into a simulation engine and runs the simulation. It simulates the interactions between the 3D models and their physical movements. For example, it simulates how a cat approaches a car and avoids a collision. The output of the simulation is generated as simulation data.

[0703] Step 6: Visualize the simulation results

[0704] The server sends the generated simulation data to the terminal. The terminal receives the simulation data and displays it to the user using a graphics display engine. For example, the simulation may be displayed as a 3D animation so that the user can check its details. As a result, a simulation video is displayed on the terminal.

[0705] Step 7: Recognizing User Emotions

[0706] The server analyzes the user's emotions using an emotion recognition engine. It captures facial expressions and voice in real time through sensor devices such as cameras and microphones connected to the device, and generates emotion data. For example, it can determine whether the user is expressing surprise.

[0707] Step 8: Adjust the simulation

[0708] The server dynamically adjusts the simulation content based on the emotional data analyzed by the emotion recognition engine. For example, if the user expresses surprise or fear, the server may adjust the speed of the simulation, such as slowing it down. The adjustment results are generated as new simulation data and resent to the device. The device then redisplays the adjusted simulation to the user.

[0709] Through the above steps, the processing of the entire system is completed, and optimized simulation results are provided to the user.

[0710] (Application example 2)

[0711] 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."

[0712] Current simulation systems can perform simulations by analyzing user input, generating 3D models, and visualizing the results. However, they lack the ability to dynamically adjust the simulation content according to the user's emotional state, which results in a lack of realism and interactivity to deepen the user's understanding. In particular, simulations of autonomous vehicles require appropriate speed adjustments and scenario changes according to the user's emotions.

[0713] The specific processing by the specific 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: input means for inputting simulation content from a user; analysis means for analyzing the simulation content acquired from the input means; generation means for generating a 3D model based on the content analyzed by the analysis means; execution means for executing a simulation using the 3D model generated by the generation means; visualization means for visualizing the results of the simulation executed by the execution means; an emotion engine for recognizing the emotional state of the user; and adjustment means for dynamically adjusting the simulation content based on the user's emotional state recognized by the emotion engine. This makes it possible to dynamically change the simulation content in accordance with the user's emotional state, providing a more intuitive and user-friendly simulation environment.

[0714] "User input means" refers to means by which a user inputs simulation content into a terminal.

[0715] The "analysis means" is a means for analyzing the simulation contents input by the user and extracting the objects required for the simulation, as well as their attributes and interactions.

[0716] The "generation means" is a means for automatically generating a 3D model based on the data obtained by the analysis means.

[0717] The "execution means" is a means for executing a simulation using the 3D model generated by the generation means.

[0718] The "visualization means" is a means for graphically displaying the results of the simulation executed by the execution means.

[0719] The "emotion engine" is an engine that analyzes the user's facial expression data and voice data to recognize the user's emotional state.

[0720] The "adjustment means" is a means for dynamically adjusting the simulation content based on the emotional state of the user recognized by the emotion engine.

[0721] 1. Overall system configuration:

[0722] This system consists of multiple components: a server, a terminal, and a user. The terminal provides an input means for the user to input simulation content. The server has an analysis means for analyzing the input content, a generation means for generating a 3D model based on the analysis results, an execution means for executing a simulation using the generated 3D model, a visualization means for visualizing the results of the executed simulation, an emotion engine for recognizing the user's emotional state, and an adjustment means for dynamically adjusting the simulation content based on the user's emotional state.

[0723] 2. Hardware and software configuration:

[0724] Hardware:

[0725] Smart glasses: Equipped with an input means for accepting user input, a data acquisition means for emotion recognition using a camera and microphone, and a display function for showing simulation results.

[0726] software:

[0727] EmotionRecognizer (emotion recognition library): An engine that analyzes the user's emotional state from their facial expressions and voice.

[0728] Simulation Engine: Software that runs simulations using 3D models.

[0729] ModelGenerator (3D model generation library): A library for generating 3D models for simulation.

[0730] 3. Processing Description:

[0731] User input means:

[0732] Using the smart glasses, users input the simulation content, for example, specifying a scenario such as "the behavior of an autonomous vehicle at an urban intersection."

[0733] Analysis method:

[0734] The server analyzes the scenario entered by the user and extracts the necessary objects (e.g., cars, intersections, traffic lights, etc.) and their attributes and interactions. This analysis is performed using a generative AI model.

[0735] Generation means:

[0736] Based on the analyzed data, the 3D model generation library (ModelGenerator) automatically generates a 3D model of the object, for example, a 3D model that mimics the shape and movement of a car.

[0737] To do this:

[0738] The generated 3D model is passed to a simulation engine, which simulates the scenario (e.g., the movement of a car at an intersection).

[0739] Visualization means:

[0740] The simulation results executed by the simulation engine are sent from the server to the terminal and displayed on the smart glasses display.

[0741] Emotion Engine:

[0742] The smart glasses use a built-in camera and microphone to capture and acquire the user's facial expression and voice data. EmotionRecognizer analyzes this data and recognizes the user's emotional state.

[0743] Adjustment means:

[0744] The emotion engine dynamically adjusts the simulation content based on the user's emotional state (e.g., surprise, fear) recognized by the emotion engine. For example, if the user shows surprise or fear, the simulation speed is slowed down.

[0745] 4. Example:

[0746] When a user inputs "self-driving car movement at an urban intersection," the generative AI model generates 3D models of the required objects (cars, intersections, traffic lights, etc.).

[0747] The simulation engine simulates the autonomous vehicle's movement through the intersection and displays the results on the smart glasses' display.

[0748] While the user is watching the simulation, the emotion engine analyzes the user's emotional state, and if it detects expressions of surprise or fear, it makes adjustments such as slowing down the speed of the simulation.

[0749] 5. Example prompt:

[0750] "Simulate the behavior of an autonomous vehicle at an urban intersection. Generate the necessary 3D models (buildings, traffic lights, vehicles, pedestrians, etc.) in the scenario to recreate how the vehicle will behave in a specific situation."

[0751] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0752] Step 1:

[0753] The user inputs the simulation content using smart glasses.

[0754] Input: The user enters the scenario: "Autonomous vehicle behavior at an urban intersection."

[0755] How it works: Accepts user voice and text input through the UI of the smart glasses.

[0756] Output: Simulation content (text format).

[0757] Step 2:

[0758] The terminal sends user input to the server, which parses it.

[0759] Input: User input (movement of an autonomous vehicle at an urban intersection).

[0760] How it works: The device sends input data to the server, which then uses a generative AI model to analyze the content, specifically extracting objects (cars, intersections, traffic lights, etc.).

[0761] Output: Analysis results (objects, their attributes and interactions).

[0762] Step 3:

[0763] The server generates a 3D model based on the analysis results.

[0764] Input: Analysis results (objects and their attributes and interactions).

[0765] How it works: The server uses the ModelGenerator library to generate 3D models of the extracted objects (cars, intersections, traffic lights, etc.).

[0766] Output: The generated 3D model.

[0767] Step 4:

[0768] The server runs a simulation using the generated 3D model.

[0769] Input: A generated 3D model.

[0770] How it works: The server runs a simulation using SimulationEngine to recreate a scenario (the movement of an autonomous vehicle at an urban intersection).

[0771] Output: Simulation results.

[0772] Step 5:

[0773] The server sends the simulation results to the terminal, which then visualizes them.

[0774] Input: Simulation results.

[0775] How it works: The server sends the simulation results to the device, which then displays a 3D animation of the simulation on the smart glasses display.

[0776] Output: Visualized simulation results.

[0777] Step 6:

[0778] The camera and microphone are used to recognize the user's emotional state through an emotion engine.

[0779] Input: User's facial expression data and voice data.

[0780] How it works: The smart glasses' camera and microphone are used to capture the user's facial expressions and voice, and the EmotionRecognizer library is used to analyze their emotional state.

[0781] Output: The user's emotional state (e.g., surprise, fear).

[0782] Step 7:

[0783] The server dynamically adjusts the simulation content based on the user's emotional state.

[0784] Input: User's emotional state (e.g., surprise, fear).

[0785] Operation: Depending on the emotional state, the server sends instructions to the simulation engine and makes adjustments such as slowing down the simulation speed.

[0786] Output: Adjusted simulation results.

[0787] 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.

[0788] 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.

[0789] 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.

[0790] [Third embodiment]

[0791] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0792] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0793] 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).

[0794] 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.

[0795] 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.

[0796] 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).

[0797] 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.

[0798] 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.

[0799] 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.

[0800] 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.

[0801] 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.

[0802] 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."

[0803] The present invention relates to a system that uses digital twin technology to automatically analyze simulation content entered by a user, generate the necessary 3D models, execute the simulation, and visualize the results. The specific system process for implementing the present invention and the processing between each step are as follows.

[0804] User Input Method

[0805] The user inputs the content they want to simulate into the terminal. The terminal receives the input from the user and prepares it to be sent to the server. For example, if the user inputs "simulation of a cat approaching a car," the content is sent to the server in text format.

[0806] Analysis means

[0807] The server passes the received user input to the generative AI model, which then analyzes the content. The generative AI model analyzes the input natural language text and extracts information about the objects (in this case, the cat and the car) required for the simulation, as well as their attributes and interactions.

[0808] generation means

[0809] The server then requests a generative AI model to create a 3D model based on the analyzed data. The generative AI model automatically generates a 3D model, taking into account the shape, movement, and physical characteristics of the object. At this stage, for example, a 3D model that mimics the shape and movement of a cat or a 3D model that expresses the movement of a car is generated.

[0810] Execution method

[0811] The generated 3D model is then passed to a simulation engine on the server, which simulates the interaction and movement of the objects. This process recreates the scene of how the cat and the car approach each other and, if necessary, avoid a collision.

[0812] Visualization means

[0813] When the simulation engine finishes the simulation, the results are sent from the server to the terminal, which displays the simulation results graphically. For example, the simulation result of a cat approaching a car is displayed to the user as a 3D animation.

[0814] Specific examples

[0815] Traffic simulation example

[0816] 1. User Input Method:

[0817] The user types "simulation of an intersection with four cars crossing."

[0818] The terminal sends this input to the server.

[0819] 2. Analysis method:

[0820] The server uses a generative AI model to analyze the content and extract the required objects (four cars) and their movements and interactions.

[0821] 3. Generation means:

[0822] The server generates 3D models of the four cars based on the analysis data.

[0823] 4. Implementation Method:

[0824] The server passes the generated 3D model to a simulation engine, which simulates the movement and interaction of cars at the intersection.

[0825] 5. Visualization means:

[0826] The server transmits the simulation results to the terminal, which displays the simulation results to the user.

[0827] As a result, by using the system of this invention, complex simulations can be performed automatically without specialist knowledge, and the results can be displayed in an easy-to-understand manner.The above-mentioned system has the advantage of enabling the generation of highly accurate digital twins while keeping human and financial costs down.

[0828] The processing flow will be explained below.

[0829] Step 1:

[0830] The user inputs the "content to be simulated" into the terminal. For example, they input "simulation of a cat approaching a car."

[0831] Step 2:

[0832] The terminal receives the user's input and sends it to the server.

[0833] Step 3:

[0834] The server passes the received user input to the generative AI model.

[0835] Step 4:

[0836] The generative AI model analyzes the text and extracts the objects needed for the simulation (in this case, the cat and the car), their attributes, and interactions. The analysis results include the names of the objects, their movement patterns, and interaction characteristics.

[0837] Step 5:

[0838] Based on the analysis results, the server requests the generative AI model to generate a 3D model, taking into account the shape, movement, and physical properties of the object.

[0839] Step 6:

[0840] A generative AI model generates a 3D model: for example, a 3D model of a cat includes the cat's shape and movement patterns, and a 3D model of a car includes the car's movement and physical properties.

[0841] Step 7:

[0842] The server passes the generated 3D model to the simulation engine.

[0843] Step 8:

[0844] The simulation engine uses the 3D model to run a simulation, simulating the cat's interaction with the car, its movements, collision avoidance, etc.

[0845] Step 9:

[0846] The server obtains the simulation results and sends them to the terminal.

[0847] Step 10:

[0848] The device receives the simulation results and displays them graphically to the user. For example, a scene of a cat approaching a car can be displayed as a 3D animation, allowing the user to visually confirm the detailed movement of the simulation results.

[0849] By following the above steps, the system can automatically generate a digital twin from user input, run a simulation, and visually display the results.

[0850] Example 1

[0851] 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."

[0852] Conventional simulation systems generally require users to have specialized knowledge to run a simulation, and require complex settings and manual work. Visualizing and analyzing the simulation results is also cumbersome and difficult to understand, which is an issue. These issues limit the use of simulation and increase the human and financial costs.

[0853] 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.

[0854] In this invention, the server includes an input means for inputting simulation content from a user, an analysis means for analyzing the simulation content acquired from the input means, a generation means for generating a three-dimensional model based on the content analyzed by the analysis means, an execution means for executing a simulation using the three-dimensional model generated by the generation means, and a visualization means for visualizing the results of the simulation executed by the execution means. This enables a user to execute a simulation without requiring specialized knowledge and to intuitively understand the results.

[0855] "User input means" refers to a device or interface that allows a user to input simulation content.

[0856] The "analysis means" is a device or program that has the function of analyzing the simulation content input by the user and extracting information on the necessary objects and their interactions.

[0857] The "generation means" is a device or program having the function of generating a three-dimensional model of an object based on the data analyzed by the analysis means.

[0858] The "execution means" is a device or program having the function of executing a simulation using the three-dimensional model generated by the generation means.

[0859] The "visualization means" is a device or program that graphically displays the results of the simulation executed by the execution means, allowing the user to visually confirm the results.

[0860] A "generative AI model" is an algorithm or program that analyzes the shape, movement, and physical properties of the object required for the simulation, and automatically generates a three-dimensional model based on the results.

[0861] A "prompt sentence" is text data used to pass the simulation content entered by the user to the analysis means or the generation AI model.

[0862] The present invention relates to a system that uses digital twin technology to automatically analyze simulation content entered by a user, generate the necessary three-dimensional models, execute the simulation, and visualize the results. The specific system configuration and processing between each step of the present invention are described below.

[0863] The system of the present invention comprises the following main means:

[0864] User Input Method

[0865] The user inputs the content they want to simulate into the terminal. The terminal receives the input from the user and sends the content in text format to the server. For example, if the user inputs "Simulation of a cat and a car approaching each other" into the text box, the content is sent to the server.

[0866] Analysis means

[0867] The server passes the received user input to the generative AI model, which analyzes the content. The generative AI model analyzes the input natural language text and extracts information about the objects required for the simulation (in this case, the cat and the car), as well as their attributes and interactions. Specifically, the generative AI model performs analysis using a prompt text. An example of a prompt text is "Simulation of a cat and a car approaching each other."

[0868] generation means

[0869] The server then requests a generative AI model to create a 3D model based on the analyzed data. The generative AI model automatically generates a 3D model, taking into account the shape, movement, and physical characteristics of the object. For example, a 3D model that mimics the shape and movement of a cat or a 3D model that expresses the movement of a car may be generated.

[0870] Execution method

[0871] The generated 3D model is then passed to a simulation engine on the server, which simulates the interaction and movement of the objects. This process recreates the scene of how the cat and the car approach each other and, if necessary, avoid a collision.

[0872] Visualization means

[0873] When the simulation engine finishes the simulation, the results are sent from the server to the terminal, which displays the simulation results graphically. For example, the simulation result of a cat approaching a car is displayed to the user as a 3D animation.

[0874] Specific examples

[0875] A specific example of traffic simulation is shown below.

[0876] Traffic simulation example

[0877] 1. User Input Method:

[0878] The user enters "Simulation of an intersection where four cars intersect" into the text box on the terminal and sends it from the terminal to the server.

[0879] 2. Analysis method:

[0880] The server receives the input and passes the prompt to the generative AI model, which parses the text "Simulation of an intersection with four cars" and extracts objects and their interactions.

[0881] 3. Generation means:

[0882] Based on the analyzed data, the server requests the AI ​​model to generate three-dimensional models of the four cars and obtains the generated three-dimensional models.

[0883] 4. Implementation Method:

[0884] The server passes the generated 3D model to a simulation engine, which simulates the movement and interaction of cars at the intersection.

[0885] 5. Visualization means:

[0886] The server sends the simulation results to the terminal, which displays the results to the user as a three-dimensional animation.

[0887] In this way, by using the system of this invention, users can automatically perform complex simulations without specialized knowledge and intuitively understand the results, making it possible to generate highly accurate digital twins while reducing human and financial costs.

[0888] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0889] Step 1: User Input

[0890] The user uses the input interface (e.g., text box) of the terminal to input the simulation content. Specifically, the user inputs a prompt sentence such as "Simulation of a cat approaching a car." The input prompt sentence is saved as text data in the terminal.

[0891] Input: Simulation content entered by the user (text format)

[0892] Output: Text data (simulation content)

[0893] Step 2: Prepare and send

[0894] The terminal generates data packets to transmit the stored text data to the server, and the packetized data is transmitted to the server over a network.

[0895] Input: Text data (simulation content)

[0896] Output: Data packet (including text data)

[0897] Step 3: Receiving data

[0898] The server receives the data packet sent from the terminal, acquires its contents, and saves them as text data.

[0899] Input: Data packet (contains text data)

[0900] Output: Text data (simulation content saved on the server)

[0901] Step 4: Analysis

[0902] The server passes the received text data to the generative AI model and requests it to analyze it. The generative AI model analyzes the prompt and extracts the objects (cat and car) and their attributes (size, movement, physical properties, etc.) required for the simulation.

[0903] Input: Text data (simulation content)

[0904] Output: Analysis results (objects and their attributes)

[0905] Step 5: Request for 3D model generation

[0906] The server then requests the generative AI model to generate a 3D model based on the analysis results. The generative AI model then generates a 3D model that takes into account the shape, movement, and physical properties of the specified object.

[0907] Input: Analysis results (objects and their attributes)

[0908] Output: 3D model data

[0909] Step 6: Run the simulation

[0910] The generated 3D model data is passed to the simulation engine on the server, where a simulation is run. The simulation engine reproduces how the cat and car approach each other, as well as collision and avoidance movements.

[0911] Input: 3D model data

[0912] Output: Simulation results

[0913] Step 7: Prepare and submit results

[0914] The server converts the simulation results obtained from the simulation engine into data packets and transmits them to the terminal.

[0915] Input: Simulation results

[0916] Output: Data packet (contains simulation results)

[0917] Step 8: Receive and view the results

[0918] The terminal receives the data packets sent from the server, analyzes their contents, and displays them graphically, allowing the user to visually confirm the simulation results as a three-dimensional animation.

[0919] Input: Data packet (contains simulation results)

[0920] Output: Graphical display (simulation results)

[0921] The above is a description of the specific processing flow of the system and each step.

[0922] (Application example 1)

[0923] 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."

[0924] Conventional simulation systems often require specialized knowledge and complex operations, requiring users to input simulation content, analyze that content, generate a 3D model, run the simulation, and visualize the results. In particular, in the development of autonomous vehicles, traffic scenario simulations are frequently required, but there are few ways to perform these simulations easily and quickly, which poses a challenge in reducing development efficiency.

[0925] 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.

[0926] In this invention, the server includes an input means for inputting simulation content from a user, an analysis means for analyzing the simulation content acquired from the input means, a generation means for generating a 3D model based on the content analyzed by the analysis means, and a generation AI model that enables input of a simulation scenario in natural language for operational testing and prediction of an autonomous vehicle. This makes it possible to easily and quickly perform operational testing and prediction of an autonomous vehicle based on the simulation scenario input by the user in natural language.

[0927] The "input means" is a means for a user to input simulation contents via a terminal.

[0928] The "analysis means" is a means for analyzing the simulation contents input by the user and extracting the objects and their attributes required for the scenario.

[0929] "Generation means" refers to a means for generating a 3D model based on the analyzed scenario.

[0930] The "execution means" is a means for executing a simulation using the generated 3D model.

[0931] The "visualization means" is a means for graphically displaying the simulation results and providing them to the user.

[0932] A "generative AI model" is an artificial intelligence model that analyzes the content of a simulation scenario entered in natural language, extracts the necessary information, and processes it.

[0933] This invention relates to a system that allows a user to input simulation content including a traffic scenario in natural language, generates a 3D model based on the content, executes the simulation, and visualizes the results. In this embodiment, the system is configured using the following means.

[0934] System configuration

[0935] 1. Input Method

[0936] Users can input the content they want to simulate in natural language using their smartphone.

[0937] For example, the user inputs "simulation of cars and pedestrians at an intersection."

[0938] 2. Analysis method

[0939] The input simulation content is sent to the server and analyzed by a generative AI model (e.g., OpenAI's GPT-4).

[0940] From the analyzed content, objects (vehicles, pedestrians) and their attributes (direction, speed, position) are extracted.

[0941] 3. Generation means

[0942] Based on the extracted data, the server generates a 3D model of the object using a 3D modeling tool (e.g., Unity).

[0943] The shape, movement, and physical properties of the object are taken into account to generate the data required for the simulation.

[0944] 4. Means of Implementation

[0945] The generated 3D model is passed to a simulation engine (e.g., Unity's PhysX) and the simulation is performed.

[0946] This simulation is used to test and predict the behavior of autonomous vehicles.

[0947] 5. Visualization means

[0948] The results of the executed simulation are sent from the server to the smartphone and visualized as a 3D animation.

[0949] Users can check the simulation results on their smartphones.

[0950] Hardware and software used

[0951] Hardware

[0952] Smartphone: A device where users can enter data and check the results.

[0953] Server: A computer device for implementing the analysis means, generation means, and execution means.

[0954] software

[0955] Generative AI models, such as OpenAI's GPT-4, are used to analyze a user's natural language input and understand the simulation content.

[0956] 3D modeling tools: for example, Unity, used to generate 3D models of objects based on the analyzed content.

[0957] Simulation engine: For example, Unity's PhysX. Runs the simulation using the generated 3D model.

[0958] Specific examples

[0959] The user types "simulation of cars and pedestrians at an intersection" into their smartphone. The input is sent to the server and analyzed by OpenAI's GPT-4. Based on the analysis results, 3D models of cars and pedestrians are generated using Unity. These 3D models are then passed to Unity's PhysX simulation engine, which runs the simulation. Finally, the simulation results are sent to the smartphone and visualized as a 3D animation.

[0960] Example prompts for generative AI models

[0961] "Analyze the following scenario: A simulation of a car and pedestrians at an intersection. The car moves to avoid a pedestrian entering the intersection."

[0962] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0963] Step 1:

[0964] The user inputs the simulation content in natural language using the smartphone's input means. Specifically, the user enters "Simulation of cars and pedestrians at an intersection" in the input field displayed on the smartphone screen and presses the send button. The input data is in character string format.

[0965] Step 2:

[0966] The terminal sends the simulation content entered by the user to the server. Specifically, it sends the input data to the server's analysis means using an HTTP request. The server receives the simulation content in the form of a character string.

[0967] Step 3:

[0968] The server's analysis means passes the received simulation content to a generative AI model (e.g., GPT-4) for analysis. Specifically, the analysis means passes the input data to the generative AI model as a prompt: "Analyze the following scenario: A simulation of a car and pedestrians at an intersection. The car moves to avoid pedestrians entering the intersection." The generative AI model analyzes this prompt and extracts the objects (cars, pedestrians) and their attributes (direction, speed, position). The analysis results are output in JSON format.

[0969] Step 4:

[0970] The server's generation means generates 3D models based on the analyzed data. Specifically, based on the analysis results (JSON format), it uses Unity's API to generate 3D models of vehicles and pedestrians. The generated 3D models include the shape, movement, and physical properties of the objects. The generated 3D models are saved in file formats (.fbx or .glb).

[0971] Step 5:

[0972] The server's execution means passes the generated 3D model to a simulation engine (for example, Unity's PhysX) to execute the simulation. Specifically, the file path of the generated 3D model is passed to the simulation engine as input, and the simulation is executed. The simulation engine reproduces the movements of cars and pedestrians and simulates their interaction. The simulation results are output in the form of a simulation log and 3D animation.

[0973] Step 6:

[0974] The server's visualization means sends the simulation results to the terminal, where they are visualized. Specifically, the simulation results (3D animation) are sent to the smartphone as an HTTP response. The smartphone plays the received 3D animation on its screen and displays the simulation results to the user. The user can then check the simulation results on the smartphone screen.

[0975] 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.

[0976] The present invention utilizes digital twin technology to automatically analyze simulation content entered by the user, generate the necessary 3D models, run the simulation, and visualize the results. By combining this with an emotion engine that recognizes the user's emotions, the system adds a function to dynamically adjust the simulation content. The specific system process for implementing the present invention and the processing between each step are as follows:

[0977] User Input Method

[0978] The user inputs the content they want to simulate into the terminal. The terminal receives the input from the user and prepares it to be sent to the server. For example, if the user inputs "simulation of a cat approaching a car," the content is sent to the server in text format.

[0979] Analysis means

[0980] The server passes the received user input to the generative AI model, which then analyzes the content. The generative AI model analyzes the input natural language text and extracts information about the objects (in this case, the cat and the car) required for the simulation, as well as their attributes and interactions.

[0981] generation means

[0982] The server then requests the generative AI model to generate a 3D model based on the analyzed data. The generative AI model automatically generates a 3D model, taking into account the shape, movement, and physical properties of the object. At this stage, for example, a 3D model that mimics the shape and movement of a cat or a 3D model that expresses the movement of a car is generated.

[0983] Execution method

[0984] The generated 3D model is then passed to a simulation engine on the server, which simulates the interaction and movement of the objects. This process recreates the scene of how the cat and the car approach each other and, if necessary, avoid a collision.

[0985] Visualization means

[0986] When the simulation engine finishes the simulation, the results are sent from the server to the terminal, which displays the simulation results graphically. For example, the simulation result of a cat approaching a car is displayed to the user as a 3D animation.

[0987] Emotion Engine

[0988] The emotion engine installed on the server analyzes the user's facial expressions and voice and recognizes the user's emotions. To do this, the device uses sensor devices such as a camera and microphone to acquire the user's facial expression data and voice data, and sends it to the server.

[0989] Adjustment means

[0990] The server adjusts the simulation content based on the user's emotions recognized by the emotion engine. For example, if the user shows surprise or fear, the server will slow down the simulation speed or change the content to make it easier for the user to understand.

[0991] Specific examples

[0992] Traffic simulation example

[0993] 1. User Input Method:

[0994] The user types "simulation of an intersection with four cars crossing."

[0995] The terminal sends this input to the server.

[0996] 2. Analysis method:

[0997] The server uses a generative AI model to analyze the content and extract the required objects (four cars) and their movements and interactions.

[0998] 3. Generation means:

[0999] The server generates 3D models of the four cars based on the analysis data.

[1000] 4. Implementation Method:

[1001] The server passes the generated 3D model to a simulation engine, which simulates the movement and interaction of cars at the intersection.

[1002] 5. Emotion Engine:

[1003] The server analyzes the user's emotions using an emotion engine and detects, for example, whether the user is nervous.

[1004] 6. Adjustment means:

[1005] To ease the user's tension, the server makes adjustments such as slowing down the simulation speed slightly.

[1006] 7. Visualization means:

[1007] The server transmits the adjusted simulation results to the terminal, and the terminal displays the simulation results to the user.

[1008] This allows the simulation content to be dynamically adjusted in response to the user's emotions, making it possible to provide a more user-friendly and intuitive simulation environment.The above-mentioned system is characterized by its high-precision generation and simulation of digital twins while keeping human and financial costs down, and by its ability to provide a high level of interactivity in response to the user's emotions.

[1009] The processing flow will be explained below.

[1010] Step 1:

[1011] The user inputs the "content to be simulated" into the terminal. For example, they input "simulation of a cat approaching a car."

[1012] Step 2:

[1013] The terminal receives the user's input and sends it to the server.

[1014] Step 3:

[1015] The server passes the received user input to the generative AI model.

[1016] Step 4:

[1017] The generative AI model analyzes the text and extracts the objects needed for the simulation (in this case, the cat and the car), their attributes, and interactions. The analysis results include the names of the objects, their movement patterns, and interaction characteristics.

[1018] Step 5:

[1019] Based on the analysis results, the server requests the generative AI model to generate a 3D model, taking into account the shape, movement, and physical properties of the object.

[1020] Step 6:

[1021] A generative AI model generates a 3D model: for example, a 3D model of a cat includes the cat's shape and movement patterns, and a 3D model of a car includes the car's movement and physical properties.

[1022] Step 7:

[1023] The server passes the generated 3D model to the simulation engine.

[1024] Step 8:

[1025] The simulation engine uses the 3D model to run a simulation, simulating the cat's interaction with the car, its movements, collision avoidance, etc.

[1026] Step 9:

[1027] The server obtains the simulation results and sends them to the terminal.

[1028] Step 10:

[1029] The device receives the simulation results and displays them graphically to the user. For example, a scene of a cat approaching a car can be displayed as a 3D animation, allowing the user to visually confirm the detailed movement of the simulation results.

[1030] Step 11:

[1031] The device's built-in camera and microphone are used to record the user's facial expressions and voice, and this data is sent to the server.

[1032] Step 12:

[1033] The server passes the received facial expression and voice data to the emotion engine, which analyzes this data and recognizes the user's emotions. For example, it can detect whether the user is surprised or nervous.

[1034] Step 13:

[1035] The server adjusts the simulation content based on the analysis results of the emotion engine. For example, if the user is surprised, it will slow down the simulation speed or simplify the content.

[1036] Step 14:

[1037] The server sends the adjusted simulation results back to the simulation engine for re-execution.

[1038] Step 15:

[1039] The simulation engine executes the adjusted simulation and sends the results back to the server.

[1040] Step 16:

[1041] The server sends the new simulation results to the terminal, which then displays them to the user. For example, the terminal reconfirms the user's reaction based on the adjusted simulation results and makes additional adjustments as necessary.

[1042] This allows the simulation content to be dynamically adjusted in response to the user's emotions, making it possible to provide a more user-friendly and intuitive simulation environment.The above-mentioned system is characterized by its high-precision generation and simulation of digital twins while keeping human and financial costs down, and by its ability to provide a high level of interactivity in response to the user's emotions.

[1043] Example 2

[1044] 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."

[1045] Conventional simulation systems execute simulations based on user input, but do not dynamically adjust to account for the user's emotional state, resulting in a limited user experience. Furthermore, it can be difficult to understand and interact with the simulation results, requiring intuitive operation and feedback.

[1046] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes an input means for inputting simulation content from a user, an analysis means for analyzing the simulation content acquired from the input means, a generation means for generating a 3D model based on the content analyzed by the analysis means, an execution means for executing a simulation using the 3D model generated by the generation means, a visualization means for visualizing the results of the simulation executed by the execution means, an emotion recognition means for recognizing the user's emotion, and an adjustment means for dynamically adjusting the simulation content based on the user's emotion recognized by the emotion recognition means. This improves the user experience and enables a more intuitive and interactive simulation.

[1047] The "input means" is a means for the user to input the simulation contents.

[1048] The "analysis means" is a means for analyzing the simulation content acquired from the input means.

[1049] The "generation means" is a means for generating a 3D model based on the content analyzed by the analysis means.

[1050] The "execution means" is a means for executing a simulation using the 3D model generated by the generation means.

[1051] The "visualization means" is a means for visualizing the results of the simulation executed by the execution means.

[1052] The "emotion recognition means" is a means for recognizing the user's emotions.

[1053] The "adjustment means" is a means for dynamically adjusting the simulation content based on the user's emotion recognized by the emotion recognition means.

[1054] This invention combines a system that allows users to input simulation content, analyzes that content, generates a 3D model, runs the simulation, and visualizes the results with an emotion engine that recognizes the user's emotions. This system improves the user experience and enables intuitive, interactive simulation.

[1055] 1. User Input Method

[1056] The user inputs the simulation content into the terminal. The terminal includes input devices such as a keyboard, mouse, and touch screen. This input content is saved in text format. For example, the user inputs "Simulation of a cat approaching a car."

[1057] 2. Sending Input

[1058] The terminal formats the user's input as text data and sends it to the server over the network, which can be the Internet or a local network. The input data is sent to the server in text format.

[1059] 3. Analysis method

[1060] The server receives the text data and passes it to the generative AI model, which uses natural language processing techniques to analyze the input text. Through this analysis, it extracts information about the objects (e.g., cats and cars) required for the simulation, as well as their attributes and interactions.

[1061] 4. 3D model generation method

[1062] Based on the analyzed information, the server requests a generative AI model to generate a 3D model. The generative AI model creates the 3D model taking into account the shape, movement, and physical characteristics. For example, a 3D model of a cat and a car is automatically generated and its movement is set.

[1063] 5. Simulation execution method

[1064] The generated 3D model is then passed to a simulation engine on the server, which simulates its interactions with other objects and physical movements, such as how a cat approaches a car and how it avoids collisions.

[1065] 6. Visualization means

[1066] The server sends the simulation results to the terminal. The terminal receives the simulation results and displays them to the user using a graphical display engine. For example, the simulation results can be shown to the user in real time as 3D animation.

[1067] 7. Emotion recognition means

[1068] The server is equipped with an emotion recognition engine and analyzes the user's emotions in real time through sensor devices such as cameras and microphones connected to the device, identifying emotions from the user's facial expressions and tone of voice, for example.

[1069] 8. Adjustment means

[1070] The server dynamically adjusts the simulation content based on the user's emotions recognized by the emotion recognition engine. For example, if the user expresses surprise or fear, it will slow down the simulation speed. The results of these adjustments are then sent back to the device and provided as feedback to the user.

[1071] Specific examples

[1072] Prompt Sentence Examples

[1073] The user inputs "simulation of an intersection where four cars intersect." The device sends this input to the server, which analyzes the content using a generative AI model and extracts the required objects (four cars) and their movements and interactions. The server generates 3D models of the four cars based on the analysis data, then passes them to the simulation engine, which simulates the movement of the cars at the intersection. The results are sent to the device, which displays the simulation results. The device also analyzes the user's emotions and dynamically adjusts the simulation content according to the results.

[1074] This allows for a simulation that responds to the user's emotions, making it possible to provide an intuitive and user-friendly simulation environment.

[1075] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1076] Step 1: User Input

[1077] The user inputs the simulation details into the terminal. Input devices include a keyboard, mouse, and touch screen. Specifically, the user inputs "Simulation of a cat approaching a car." The input data is saved in text format on the terminal. The next process is initiated based on the input data.

[1078] Step 2: Sending Input

[1079] The terminal sends the saved input data to the server via the network. The text data is formatted and sent to the server using the HTTP protocol, etc. Once the data arrives at the server, the next analysis step begins.

[1080] Step 3: Parsing the input

[1081] The server passes the text data received via the network to the generative AI model. The generative AI model performs text analysis using a natural language processing algorithm. Specifically, it extracts the necessary objects (e.g., "cat" and "car") and their interactions from the input text. The extracted results are the objects and their attribute data.

[1082] Step 4: 3D model generation

[1083] Based on the analysis results, the server requests the generative AI model to generate a 3D model. The generative AI model generates the 3D model by taking into account the shape, movement, and physical properties of the extracted object. For example, a 3D model of a cat is generated along with its movement, and a 3D model of a car is also generated according to its movement. The generated 3D model is then returned to the server.

[1084] Step 5: Run the simulation

[1085] The server inputs the generated 3D models into a simulation engine and runs the simulation. It simulates the interactions between the 3D models and their physical movements. For example, it simulates how a cat approaches a car and avoids a collision. The output of the simulation is generated as simulation data.

[1086] Step 6: Visualize the simulation results

[1087] The server sends the generated simulation data to the terminal. The terminal receives the simulation data and displays it to the user using a graphics display engine. For example, the simulation may be displayed as a 3D animation so that the user can check its details. As a result, a simulation video is displayed on the terminal.

[1088] Step 7: Recognizing User Emotions

[1089] The server analyzes the user's emotions using an emotion recognition engine. It captures facial expressions and voice in real time through sensor devices such as cameras and microphones connected to the device, and generates emotion data. For example, it can determine whether the user is expressing surprise.

[1090] Step 8: Adjust the simulation

[1091] The server dynamically adjusts the simulation content based on the emotional data analyzed by the emotion recognition engine. For example, if the user expresses surprise or fear, the server may adjust the speed of the simulation, such as slowing it down. The adjustment results are generated as new simulation data and resent to the device. The device then redisplays the adjusted simulation to the user.

[1092] Through the above steps, the processing of the entire system is completed, and optimized simulation results are provided to the user.

[1093] (Application example 2)

[1094] 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."

[1095] Current simulation systems can perform simulations by analyzing user input, generating 3D models, and visualizing the results. However, they lack the ability to dynamically adjust the simulation content according to the user's emotional state, which results in a lack of realism and interactivity to deepen the user's understanding. In particular, simulations of autonomous vehicles require appropriate speed adjustments and scenario changes according to the user's emotions.

[1096] The specific processing by the specific 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: input means for inputting simulation content from a user; analysis means for analyzing the simulation content acquired from the input means; generation means for generating a 3D model based on the content analyzed by the analysis means; execution means for executing a simulation using the 3D model generated by the generation means; visualization means for visualizing the results of the simulation executed by the execution means; an emotion engine for recognizing the emotional state of the user; and adjustment means for dynamically adjusting the simulation content based on the user's emotional state recognized by the emotion engine. This makes it possible to dynamically change the simulation content in accordance with the user's emotional state, providing a more intuitive and user-friendly simulation environment.

[1097] "User input means" refers to means by which a user inputs simulation content into a terminal.

[1098] The "analysis means" is a means for analyzing the simulation contents input by the user and extracting the objects required for the simulation, as well as their attributes and interactions.

[1099] The "generation means" is a means for automatically generating a 3D model based on the data obtained by the analysis means.

[1100] The "execution means" is a means for executing a simulation using the 3D model generated by the generation means.

[1101] The "visualization means" is a means for graphically displaying the results of the simulation executed by the execution means.

[1102] The "emotion engine" is an engine that analyzes the user's facial expression data and voice data to recognize the user's emotional state.

[1103] The "adjustment means" is a means for dynamically adjusting the simulation content based on the emotional state of the user recognized by the emotion engine.

[1104] 1. Overall system configuration:

[1105] This system consists of multiple components: a server, a terminal, and a user. The terminal provides an input means for the user to input simulation content. The server has an analysis means for analyzing the input content, a generation means for generating a 3D model based on the analysis results, an execution means for executing a simulation using the generated 3D model, a visualization means for visualizing the results of the executed simulation, an emotion engine for recognizing the user's emotional state, and an adjustment means for dynamically adjusting the simulation content based on the user's emotional state.

[1106] 2. Hardware and software configuration:

[1107] Hardware:

[1108] Smart glasses: Equipped with an input means for accepting user input, a data acquisition means for emotion recognition using a camera and microphone, and a display function for showing simulation results.

[1109] software:

[1110] EmotionRecognizer (emotion recognition library): An engine that analyzes the user's emotional state from their facial expressions and voice.

[1111] Simulation Engine: Software that runs simulations using 3D models.

[1112] ModelGenerator (3D model generation library): A library for generating 3D models for simulation.

[1113] 3. Processing Description:

[1114] User input means:

[1115] Using the smart glasses, users input the simulation content, for example, specifying a scenario such as "the behavior of an autonomous vehicle at an urban intersection."

[1116] Analysis method:

[1117] The server analyzes the scenario entered by the user and extracts the necessary objects (e.g., cars, intersections, traffic lights, etc.) and their attributes and interactions. This analysis is performed using a generative AI model.

[1118] Generation means:

[1119] Based on the analyzed data, the 3D model generation library (ModelGenerator) automatically generates a 3D model of the object, for example, a 3D model that mimics the shape and movement of a car.

[1120] To do this:

[1121] The generated 3D model is passed to a simulation engine, which simulates the scenario (e.g., the movement of a car at an intersection).

[1122] Visualization means:

[1123] The simulation results executed by the simulation engine are sent from the server to the terminal and displayed on the smart glasses display.

[1124] Emotion Engine:

[1125] The smart glasses use a built-in camera and microphone to capture and acquire the user's facial expression and voice data. EmotionRecognizer analyzes this data and recognizes the user's emotional state.

[1126] Adjustment means:

[1127] The emotion engine dynamically adjusts the simulation content based on the user's emotional state (e.g., surprise, fear) recognized by the emotion engine. For example, if the user shows surprise or fear, the simulation speed is slowed down.

[1128] 4. Example:

[1129] When a user inputs "self-driving car movement at an urban intersection," the generative AI model generates 3D models of the required objects (cars, intersections, traffic lights, etc.).

[1130] The simulation engine simulates the autonomous vehicle's movement through the intersection and displays the results on the smart glasses' display.

[1131] While the user is watching the simulation, the emotion engine analyzes the user's emotional state, and if it detects expressions of surprise or fear, it makes adjustments such as slowing down the speed of the simulation.

[1132] 5. Example prompt:

[1133] "Simulate the behavior of an autonomous vehicle at an urban intersection. Generate the necessary 3D models (buildings, traffic lights, vehicles, pedestrians, etc.) in the scenario to recreate how the vehicle will behave in a specific situation."

[1134] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1135] Step 1:

[1136] The user inputs the simulation content using smart glasses.

[1137] Input: The user enters the scenario: "Autonomous vehicle behavior at an urban intersection."

[1138] How it works: Accepts user voice and text input through the UI of the smart glasses.

[1139] Output: Simulation content (text format).

[1140] Step 2:

[1141] The terminal sends user input to the server, which parses it.

[1142] Input: User input (movement of an autonomous vehicle at an urban intersection).

[1143] How it works: The device sends input data to the server, which then uses a generative AI model to analyze the content, specifically extracting objects (cars, intersections, traffic lights, etc.).

[1144] Output: Analysis results (objects, their attributes and interactions).

[1145] Step 3:

[1146] The server generates a 3D model based on the analysis results.

[1147] Input: Analysis results (objects and their attributes and interactions).

[1148] How it works: The server uses the ModelGenerator library to generate 3D models of the extracted objects (cars, intersections, traffic lights, etc.).

[1149] Output: The generated 3D model.

[1150] Step 4:

[1151] The server runs a simulation using the generated 3D model.

[1152] Input: A generated 3D model.

[1153] How it works: The server runs a simulation using SimulationEngine to recreate a scenario (the movement of an autonomous vehicle at an urban intersection).

[1154] Output: Simulation results.

[1155] Step 5:

[1156] The server sends the simulation results to the terminal, which then visualizes them.

[1157] Input: Simulation results.

[1158] How it works: The server sends the simulation results to the device, which then displays a 3D animation of the simulation on the smart glasses display.

[1159] Output: Visualized simulation results.

[1160] Step 6:

[1161] The camera and microphone are used to recognize the user's emotional state through an emotion engine.

[1162] Input: User's facial expression data and voice data.

[1163] How it works: The smart glasses' camera and microphone are used to capture the user's facial expressions and voice, and the EmotionRecognizer library is used to analyze their emotional state.

[1164] Output: The user's emotional state (e.g., surprise, fear).

[1165] Step 7:

[1166] The server dynamically adjusts the simulation content based on the user's emotional state.

[1167] Input: User's emotional state (e.g., surprise, fear).

[1168] Operation: Depending on the emotional state, the server sends instructions to the simulation engine and makes adjustments such as slowing down the simulation speed.

[1169] Output: Adjusted simulation results.

[1170] 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.

[1171] 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.

[1172] 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.

[1173] [Fourth embodiment]

[1174] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1175] 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.

[1176] 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).

[1177] 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.

[1178] 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.

[1179] 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).

[1180] 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.

[1181] 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.

[1182] 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.

[1183] 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.

[1184] 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.

[1185] 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.

[1186] 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."

[1187] The present invention relates to a system that uses digital twin technology to automatically analyze simulation content entered by a user, generate the necessary 3D models, execute the simulation, and visualize the results. The specific system process for implementing the present invention and the processing between each step are as follows.

[1188] User Input Method

[1189] The user inputs the content they want to simulate into the terminal. The terminal receives the input from the user and prepares it to be sent to the server. For example, if the user inputs "simulation of a cat approaching a car," the content is sent to the server in text format.

[1190] Analysis means

[1191] The server passes the received user input to the generative AI model, which then analyzes the content. The generative AI model analyzes the input natural language text and extracts information about the objects (in this case, the cat and the car) required for the simulation, as well as their attributes and interactions.

[1192] generation means

[1193] The server then requests a generative AI model to create a 3D model based on the analyzed data. The generative AI model automatically generates a 3D model, taking into account the shape, movement, and physical characteristics of the object. At this stage, for example, a 3D model that mimics the shape and movement of a cat or a 3D model that expresses the movement of a car is generated.

[1194] Execution method

[1195] The generated 3D model is then passed to a simulation engine on the server, which simulates the interaction and movement of the objects. This process recreates the scene of how the cat and the car approach each other and, if necessary, avoid a collision.

[1196] Visualization means

[1197] When the simulation engine finishes the simulation, the results are sent from the server to the terminal, which displays the simulation results graphically. For example, the simulation result of a cat approaching a car is displayed to the user as a 3D animation.

[1198] Specific examples

[1199] Traffic simulation example

[1200] 1. User Input Method:

[1201] The user types "simulation of an intersection with four cars crossing."

[1202] The terminal sends this input to the server.

[1203] 2. Analysis method:

[1204] The server uses a generative AI model to analyze the content and extract the required objects (four cars) and their movements and interactions.

[1205] 3. Generation means:

[1206] The server generates 3D models of the four cars based on the analysis data.

[1207] 4. Implementation Method:

[1208] The server passes the generated 3D model to a simulation engine, which simulates the movement and interaction of cars at the intersection.

[1209] 5. Visualization means:

[1210] The server transmits the simulation results to the terminal, which displays the simulation results to the user.

[1211] As a result, by using the system of this invention, complex simulations can be performed automatically without specialist knowledge, and the results can be displayed in an easy-to-understand manner.The above-mentioned system has the advantage of enabling the generation of highly accurate digital twins while keeping human and financial costs down.

[1212] The processing flow will be explained below.

[1213] Step 1:

[1214] The user inputs the "content to be simulated" into the terminal. For example, they input "simulation of a cat approaching a car."

[1215] Step 2:

[1216] The terminal receives the user's input and sends it to the server.

[1217] Step 3:

[1218] The server passes the received user input to the generative AI model.

[1219] Step 4:

[1220] The generative AI model analyzes the text and extracts the objects needed for the simulation (in this case, the cat and the car), their attributes, and interactions. The analysis results include the names of the objects, their movement patterns, and interaction characteristics.

[1221] Step 5:

[1222] Based on the analysis results, the server requests the generative AI model to generate a 3D model, taking into account the shape, movement, and physical properties of the object.

[1223] Step 6:

[1224] A generative AI model generates a 3D model: for example, a 3D model of a cat includes the cat's shape and movement patterns, and a 3D model of a car includes the car's movement and physical properties.

[1225] Step 7:

[1226] The server passes the generated 3D model to the simulation engine.

[1227] Step 8:

[1228] The simulation engine uses the 3D model to run a simulation, simulating the cat's interaction with the car, its movements, collision avoidance, etc.

[1229] Step 9:

[1230] The server obtains the simulation results and sends them to the terminal.

[1231] Step 10:

[1232] The device receives the simulation results and displays them graphically to the user. For example, a scene of a cat approaching a car can be displayed as a 3D animation, allowing the user to visually confirm the detailed movement of the simulation results.

[1233] By following the above steps, the system can automatically generate a digital twin from user input, run a simulation, and visually display the results.

[1234] Example 1

[1235] 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."

[1236] Conventional simulation systems generally require users to have specialized knowledge to run a simulation, and require complex settings and manual work. Visualizing and analyzing the simulation results is also cumbersome and difficult to understand, which is an issue. These issues limit the use of simulation and increase the human and financial costs.

[1237] 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.

[1238] In this invention, the server includes an input means for inputting simulation content from a user, an analysis means for analyzing the simulation content acquired from the input means, a generation means for generating a three-dimensional model based on the content analyzed by the analysis means, an execution means for executing a simulation using the three-dimensional model generated by the generation means, and a visualization means for visualizing the results of the simulation executed by the execution means. This enables a user to execute a simulation without requiring specialized knowledge and to intuitively understand the results.

[1239] "User input means" refers to a device or interface that allows a user to input simulation content.

[1240] The "analysis means" is a device or program that has the function of analyzing the simulation content input by the user and extracting information on the necessary objects and their interactions.

[1241] The "generation means" is a device or program having the function of generating a three-dimensional model of an object based on the data analyzed by the analysis means.

[1242] The "execution means" is a device or program having the function of executing a simulation using the three-dimensional model generated by the generation means.

[1243] The "visualization means" is a device or program that graphically displays the results of the simulation executed by the execution means, allowing the user to visually confirm the results.

[1244] A "generative AI model" is an algorithm or program that analyzes the shape, movement, and physical properties of the object required for the simulation, and automatically generates a three-dimensional model based on the results.

[1245] A "prompt sentence" is text data used to pass the simulation content entered by the user to the analysis means or the generation AI model.

[1246] The present invention relates to a system that uses digital twin technology to automatically analyze simulation content entered by a user, generate the necessary three-dimensional models, execute the simulation, and visualize the results. The specific system configuration and processing between each step of the present invention are described below.

[1247] The system of the present invention comprises the following main means:

[1248] User Input Method

[1249] The user inputs the content they want to simulate into the terminal. The terminal receives the input from the user and sends the content in text format to the server. For example, if the user inputs "Simulation of a cat and a car approaching each other" into the text box, the content is sent to the server.

[1250] Analysis means

[1251] The server passes the received user input to the generative AI model, which analyzes the content. The generative AI model analyzes the input natural language text and extracts information about the objects required for the simulation (in this case, the cat and the car), as well as their attributes and interactions. Specifically, the generative AI model performs analysis using a prompt text. An example of a prompt text is "Simulation of a cat and a car approaching each other."

[1252] generation means

[1253] The server then requests a generative AI model to create a 3D model based on the analyzed data. The generative AI model automatically generates a 3D model, taking into account the shape, movement, and physical characteristics of the object. For example, a 3D model that mimics the shape and movement of a cat or a 3D model that expresses the movement of a car may be generated.

[1254] Execution method

[1255] The generated 3D model is then passed to a simulation engine on the server, which simulates the interaction and movement of the objects. This process recreates the scene of how the cat and the car approach each other and, if necessary, avoid a collision.

[1256] Visualization means

[1257] When the simulation engine finishes the simulation, the results are sent from the server to the terminal, which displays the simulation results graphically. For example, the simulation result of a cat approaching a car is displayed to the user as a 3D animation.

[1258] Specific examples

[1259] A specific example of traffic simulation is shown below.

[1260] Traffic simulation example

[1261] 1. User Input Method:

[1262] The user enters "Simulation of an intersection where four cars intersect" into the text box on the terminal and sends it from the terminal to the server.

[1263] 2. Analysis method:

[1264] The server receives the input and passes the prompt to the generative AI model, which parses the text "Simulation of an intersection with four cars" and extracts objects and their interactions.

[1265] 3. Generation means:

[1266] Based on the analyzed data, the server requests the AI ​​model to generate three-dimensional models of the four cars and obtains the generated three-dimensional models.

[1267] 4. Implementation Method:

[1268] The server passes the generated 3D model to a simulation engine, which simulates the movement and interaction of cars at the intersection.

[1269] 5. Visualization means:

[1270] The server sends the simulation results to the terminal, which displays the results to the user as a three-dimensional animation.

[1271] In this way, by using the system of this invention, users can automatically perform complex simulations without specialized knowledge and intuitively understand the results, making it possible to generate highly accurate digital twins while reducing human and financial costs.

[1272] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1273] Step 1: User Input

[1274] The user uses the input interface (e.g., text box) of the terminal to input the simulation content. Specifically, the user inputs a prompt sentence such as "Simulation of a cat approaching a car." The input prompt sentence is saved as text data in the terminal.

[1275] Input: Simulation content entered by the user (text format)

[1276] Output: Text data (simulation content)

[1277] Step 2: Prepare and send

[1278] The terminal generates data packets to transmit the stored text data to the server, and the packetized data is transmitted to the server over a network.

[1279] Input: Text data (simulation content)

[1280] Output: Data packet (including text data)

[1281] Step 3: Receiving data

[1282] The server receives the data packet sent from the terminal, acquires its contents, and saves them as text data.

[1283] Input: Data packet (contains text data)

[1284] Output: Text data (simulation content saved on the server)

[1285] Step 4: Analysis

[1286] The server passes the received text data to the generative AI model and requests it to analyze it. The generative AI model analyzes the prompt and extracts the objects (cat and car) and their attributes (size, movement, physical properties, etc.) required for the simulation.

[1287] Input: Text data (simulation content)

[1288] Output: Analysis results (objects and their attributes)

[1289] Step 5: Request for 3D model generation

[1290] The server then requests the generative AI model to generate a 3D model based on the analysis results. The generative AI model then generates a 3D model that takes into account the shape, movement, and physical properties of the specified object.

[1291] Input: Analysis results (objects and their attributes)

[1292] Output: 3D model data

[1293] Step 6: Run the simulation

[1294] The generated 3D model data is passed to the simulation engine on the server, where a simulation is run. The simulation engine reproduces how the cat and car approach each other, as well as collision and avoidance movements.

[1295] Input: 3D model data

[1296] Output: Simulation results

[1297] Step 7: Prepare and submit results

[1298] The server converts the simulation results obtained from the simulation engine into data packets and transmits them to the terminal.

[1299] Input: Simulation results

[1300] Output: Data packet (contains simulation results)

[1301] Step 8: Receive and view the results

[1302] The terminal receives the data packets sent from the server, analyzes their contents, and displays them graphically, allowing the user to visually confirm the simulation results as a three-dimensional animation.

[1303] Input: Data packet (contains simulation results)

[1304] Output: Graphical display (simulation results)

[1305] The above is a description of the specific processing flow of the system and each step.

[1306] (Application example 1)

[1307] 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."

[1308] Conventional simulation systems often require specialized knowledge and complex operations, requiring users to input simulation content, analyze that content, generate a 3D model, run the simulation, and visualize the results. In particular, in the development of autonomous vehicles, traffic scenario simulations are frequently required, but there are few ways to perform these simulations easily and quickly, which poses a challenge in reducing development efficiency.

[1309] 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.

[1310] In this invention, the server includes an input means for inputting simulation content from a user, an analysis means for analyzing the simulation content acquired from the input means, a generation means for generating a 3D model based on the content analyzed by the analysis means, and a generation AI model that enables input of a simulation scenario in natural language for operational testing and prediction of an autonomous vehicle. This makes it possible to easily and quickly perform operational testing and prediction of an autonomous vehicle based on the simulation scenario input by the user in natural language.

[1311] The "input means" is a means for a user to input simulation contents via a terminal.

[1312] The "analysis means" is a means for analyzing the simulation contents input by the user and extracting the objects and their attributes required for the scenario.

[1313] "Generation means" refers to a means for generating a 3D model based on the analyzed scenario.

[1314] The "execution means" is a means for executing a simulation using the generated 3D model.

[1315] The "visualization means" is a means for graphically displaying the simulation results and providing them to the user.

[1316] A "generative AI model" is an artificial intelligence model that analyzes the content of a simulation scenario entered in natural language, extracts the necessary information, and processes it.

[1317] This invention relates to a system that allows a user to input simulation content including a traffic scenario in natural language, generates a 3D model based on the content, executes the simulation, and visualizes the results. In this embodiment, the system is configured using the following means.

[1318] System configuration

[1319] 1. Input Method

[1320] Users can input the content they want to simulate in natural language using their smartphone.

[1321] For example, the user inputs "simulation of cars and pedestrians at an intersection."

[1322] 2. Analysis method

[1323] The input simulation content is sent to the server and analyzed by a generative AI model (e.g., OpenAI's GPT-4).

[1324] From the analyzed content, objects (vehicles, pedestrians) and their attributes (direction, speed, position) are extracted.

[1325] 3. Generation means

[1326] Based on the extracted data, the server generates a 3D model of the object using a 3D modeling tool (e.g., Unity).

[1327] The shape, movement, and physical properties of the object are taken into account to generate the data required for the simulation.

[1328] 4. Means of Implementation

[1329] The generated 3D model is passed to a simulation engine (e.g., Unity's PhysX) and the simulation is performed.

[1330] This simulation is used to test and predict the behavior of autonomous vehicles.

[1331] 5. Visualization means

[1332] The results of the executed simulation are sent from the server to the smartphone and visualized as a 3D animation.

[1333] Users can check the simulation results on their smartphones.

[1334] Hardware and software used

[1335] Hardware

[1336] Smartphone: A device where users can enter data and check the results.

[1337] Server: A computer device for implementing the analysis means, generation means, and execution means.

[1338] software

[1339] Generative AI models, such as OpenAI's GPT-4, are used to analyze a user's natural language input and understand the simulation content.

[1340] 3D modeling tools: for example, Unity, used to generate 3D models of objects based on the analyzed content.

[1341] Simulation engine: For example, Unity's PhysX. Runs the simulation using the generated 3D model.

[1342] Specific examples

[1343] The user types "simulation of cars and pedestrians at an intersection" into their smartphone. The input is sent to the server and analyzed by OpenAI's GPT-4. Based on the analysis results, 3D models of cars and pedestrians are generated using Unity. These 3D models are then passed to Unity's PhysX simulation engine, which runs the simulation. Finally, the simulation results are sent to the smartphone and visualized as a 3D animation.

[1344] Example prompts for generative AI models

[1345] "Analyze the following scenario: A simulation of a car and pedestrians at an intersection. The car moves to avoid a pedestrian entering the intersection."

[1346] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1347] Step 1:

[1348] The user inputs the simulation content in natural language using the smartphone's input means. Specifically, the user enters "Simulation of cars and pedestrians at an intersection" in the input field displayed on the smartphone screen and presses the send button. The input data is in character string format.

[1349] Step 2:

[1350] The terminal sends the simulation content entered by the user to the server. Specifically, it sends the input data to the server's analysis means using an HTTP request. The server receives the simulation content in the form of a character string.

[1351] Step 3:

[1352] The server's analysis means passes the received simulation content to a generative AI model (e.g., GPT-4) for analysis. Specifically, the analysis means passes the input data to the generative AI model as a prompt: "Analyze the following scenario: A simulation of a car and pedestrians at an intersection. The car moves to avoid pedestrians entering the intersection." The generative AI model analyzes this prompt and extracts the objects (cars, pedestrians) and their attributes (direction, speed, position). The analysis results are output in JSON format.

[1353] Step 4:

[1354] The server's generation means generates 3D models based on the analyzed data. Specifically, based on the analysis results (JSON format), it uses Unity's API to generate 3D models of vehicles and pedestrians. The generated 3D models include the shape, movement, and physical properties of the objects. The generated 3D models are saved in file formats (.fbx or .glb).

[1355] Step 5:

[1356] The server's execution means passes the generated 3D model to a simulation engine (for example, Unity's PhysX) to execute the simulation. Specifically, the file path of the generated 3D model is passed to the simulation engine as input, and the simulation is executed. The simulation engine reproduces the movements of cars and pedestrians and simulates their interaction. The simulation results are output in the form of a simulation log and 3D animation.

[1357] Step 6:

[1358] The server's visualization means sends the simulation results to the terminal, where they are visualized. Specifically, the simulation results (3D animation) are sent to the smartphone as an HTTP response. The smartphone plays the received 3D animation on its screen and displays the simulation results to the user. The user can then check the simulation results on the smartphone screen.

[1359] 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.

[1360] The present invention utilizes digital twin technology to automatically analyze simulation content entered by the user, generate the necessary 3D models, run the simulation, and visualize the results. By combining this with an emotion engine that recognizes the user's emotions, the system adds a function to dynamically adjust the simulation content. The specific system process for implementing the present invention and the processing between each step are as follows:

[1361] User Input Method

[1362] The user inputs the content they want to simulate into the terminal. The terminal receives the input from the user and prepares it to be sent to the server. For example, if the user inputs "simulation of a cat approaching a car," the content is sent to the server in text format.

[1363] Analysis means

[1364] The server passes the received user input to the generative AI model, which then analyzes the content. The generative AI model analyzes the input natural language text and extracts information about the objects (in this case, the cat and the car) required for the simulation, as well as their attributes and interactions.

[1365] generation means

[1366] The server then requests the generative AI model to generate a 3D model based on the analyzed data. The generative AI model automatically generates a 3D model, taking into account the shape, movement, and physical properties of the object. At this stage, for example, a 3D model that mimics the shape and movement of a cat or a 3D model that expresses the movement of a car is generated.

[1367] Execution method

[1368] The generated 3D model is then passed to a simulation engine on the server, which simulates the interaction and movement of the objects. This process recreates the scene of how the cat and the car approach each other and, if necessary, avoid a collision.

[1369] Visualization means

[1370] When the simulation engine finishes the simulation, the results are sent from the server to the terminal, which displays the simulation results graphically. For example, the simulation result of a cat approaching a car is displayed to the user as a 3D animation.

[1371] Emotion Engine

[1372] The emotion engine installed on the server analyzes the user's facial expressions and voice and recognizes the user's emotions. To do this, the device uses sensor devices such as a camera and microphone to acquire the user's facial expression data and voice data, and sends it to the server.

[1373] Adjustment means

[1374] The server adjusts the simulation content based on the user's emotions recognized by the emotion engine. For example, if the user shows surprise or fear, the server will slow down the simulation speed or change the content to make it easier for the user to understand.

[1375] Specific examples

[1376] Traffic simulation example

[1377] 1. User Input Method:

[1378] The user types "simulation of an intersection with four cars crossing."

[1379] The terminal sends this input to the server.

[1380] 2. Analysis method:

[1381] The server uses a generative AI model to analyze the content and extract the required objects (four cars) and their movements and interactions.

[1382] 3. Generation means:

[1383] The server generates 3D models of the four cars based on the analysis data.

[1384] 4. Implementation Method:

[1385] The server passes the generated 3D model to a simulation engine, which simulates the movement and interaction of cars at the intersection.

[1386] 5. Emotion Engine:

[1387] The server analyzes the user's emotions using an emotion engine and detects, for example, whether the user is nervous.

[1388] 6. Adjustment means:

[1389] To ease the user's tension, the server makes adjustments such as slowing down the simulation speed slightly.

[1390] 7. Visualization means:

[1391] The server transmits the adjusted simulation results to the terminal, and the terminal displays the simulation results to the user.

[1392] This allows the simulation content to be dynamically adjusted in response to the user's emotions, making it possible to provide a more user-friendly and intuitive simulation environment.The above-mentioned system is characterized by its high-precision generation and simulation of digital twins while keeping human and financial costs down, and by its ability to provide a high level of interactivity in response to the user's emotions.

[1393] The processing flow will be explained below.

[1394] Step 1:

[1395] The user inputs the "content to be simulated" into the terminal. For example, they input "simulation of a cat approaching a car."

[1396] Step 2:

[1397] The terminal receives the user's input and sends it to the server.

[1398] Step 3:

[1399] The server passes the received user input to the generative AI model.

[1400] Step 4:

[1401] The generative AI model analyzes the text and extracts the objects needed for the simulation (in this case, the cat and the car), their attributes, and interactions. The analysis results include the names of the objects, their movement patterns, and interaction characteristics.

[1402] Step 5:

[1403] Based on the analysis results, the server requests the generative AI model to generate a 3D model, taking into account the shape, movement, and physical properties of the object.

[1404] Step 6:

[1405] A generative AI model generates a 3D model: for example, a 3D model of a cat includes the cat's shape and movement patterns, and a 3D model of a car includes the car's movement and physical properties.

[1406] Step 7:

[1407] The server passes the generated 3D model to the simulation engine.

[1408] Step 8:

[1409] The simulation engine uses the 3D model to run a simulation, simulating the cat's interaction with the car, its movements, collision avoidance, etc.

[1410] Step 9:

[1411] The server obtains the simulation results and sends them to the terminal.

[1412] Step 10:

[1413] The device receives the simulation results and displays them graphically to the user. For example, a scene of a cat approaching a car can be displayed as a 3D animation, allowing the user to visually confirm the detailed movement of the simulation results.

[1414] Step 11:

[1415] The device's built-in camera and microphone are used to record the user's facial expressions and voice, and this data is sent to the server.

[1416] Step 12:

[1417] The server passes the received facial expression and voice data to the emotion engine, which analyzes this data and recognizes the user's emotions. For example, it can detect whether the user is surprised or nervous.

[1418] Step 13:

[1419] The server adjusts the simulation content based on the analysis results of the emotion engine. For example, if the user is surprised, it will slow down the simulation speed or simplify the content.

[1420] Step 14:

[1421] The server sends the adjusted simulation results back to the simulation engine for re-execution.

[1422] Step 15:

[1423] The simulation engine executes the adjusted simulation and sends the results back to the server.

[1424] Step 16:

[1425] The server sends the new simulation results to the terminal, which then displays them to the user. For example, the terminal reconfirms the user's reaction based on the adjusted simulation results and makes additional adjustments as necessary.

[1426] This allows the simulation content to be dynamically adjusted in response to the user's emotions, making it possible to provide a more user-friendly and intuitive simulation environment.The above-mentioned system is characterized by its high-precision generation and simulation of digital twins while keeping human and financial costs down, and by its ability to provide a high level of interactivity in response to the user's emotions.

[1427] Example 2

[1428] 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."

[1429] Conventional simulation systems execute simulations based on user input, but do not dynamically adjust to account for the user's emotional state, resulting in a limited user experience. Furthermore, it can be difficult to understand and interact with the simulation results, requiring intuitive operation and feedback.

[1430] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes an input means for inputting simulation content from a user, an analysis means for analyzing the simulation content acquired from the input means, a generation means for generating a 3D model based on the content analyzed by the analysis means, an execution means for executing a simulation using the 3D model generated by the generation means, a visualization means for visualizing the results of the simulation executed by the execution means, an emotion recognition means for recognizing the user's emotion, and an adjustment means for dynamically adjusting the simulation content based on the user's emotion recognized by the emotion recognition means. This improves the user experience and enables a more intuitive and interactive simulation.

[1431] The "input means" is a means for the user to input the simulation contents.

[1432] The "analysis means" is a means for analyzing the simulation content acquired from the input means.

[1433] The "generation means" is a means for generating a 3D model based on the content analyzed by the analysis means.

[1434] The "execution means" is a means for executing a simulation using the 3D model generated by the generation means.

[1435] The "visualization means" is a means for visualizing the results of the simulation executed by the execution means.

[1436] The "emotion recognition means" is a means for recognizing the user's emotions.

[1437] The "adjustment means" is a means for dynamically adjusting the simulation content based on the user's emotion recognized by the emotion recognition means.

[1438] This invention combines a system that allows users to input simulation content, analyzes that content, generates a 3D model, runs the simulation, and visualizes the results with an emotion engine that recognizes the user's emotions. This system improves the user experience and enables intuitive, interactive simulation.

[1439] 1. User Input Method

[1440] The user inputs the simulation content into the terminal. The terminal includes input devices such as a keyboard, mouse, and touch screen. This input content is saved in text format. For example, the user inputs "Simulation of a cat approaching a car."

[1441] 2. Sending Input

[1442] The terminal formats the user's input as text data and sends it to the server over the network, which can be the Internet or a local network. The input data is sent to the server in text format.

[1443] 3. Analysis method

[1444] The server receives the text data and passes it to the generative AI model, which uses natural language processing techniques to analyze the input text. Through this analysis, it extracts information about the objects (e.g., cats and cars) required for the simulation, as well as their attributes and interactions.

[1445] 4. 3D model generation method

[1446] Based on the analyzed information, the server requests a generative AI model to generate a 3D model. The generative AI model creates the 3D model taking into account the shape, movement, and physical characteristics. For example, a 3D model of a cat and a car is automatically generated and its movement is set.

[1447] 5. Simulation execution method

[1448] The generated 3D model is then passed to a simulation engine on the server, which simulates its interactions with other objects and physical movements, such as how a cat approaches a car and how it avoids collisions.

[1449] 6. Visualization means

[1450] The server sends the simulation results to the terminal. The terminal receives the simulation results and displays them to the user using a graphical display engine. For example, the simulation results can be shown to the user in real time as 3D animation.

[1451] 7. Emotion recognition means

[1452] The server is equipped with an emotion recognition engine and analyzes the user's emotions in real time through sensor devices such as cameras and microphones connected to the device, identifying emotions from the user's facial expressions and tone of voice, for example.

[1453] 8. Adjustment means

[1454] The server dynamically adjusts the simulation content based on the user's emotions recognized by the emotion recognition engine. For example, if the user expresses surprise or fear, it will slow down the simulation speed. The results of these adjustments are then sent back to the device and provided as feedback to the user.

[1455] Specific examples

[1456] Prompt Sentence Examples

[1457] The user inputs "simulation of an intersection where four cars intersect." The device sends this input to the server, which analyzes the content using a generative AI model and extracts the required objects (four cars) and their movements and interactions. The server generates 3D models of the four cars based on the analysis data, then passes them to the simulation engine, which simulates the movement of the cars at the intersection. The results are sent to the device, which displays the simulation results. The device also analyzes the user's emotions and dynamically adjusts the simulation content according to the results.

[1458] This allows for a simulation that responds to the user's emotions, making it possible to provide an intuitive and user-friendly simulation environment.

[1459] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1460] Step 1: User Input

[1461] The user inputs the simulation details into the terminal. Input devices include a keyboard, mouse, and touch screen. Specifically, the user inputs "Simulation of a cat approaching a car." The input data is saved in text format on the terminal. The next process is initiated based on the input data.

[1462] Step 2: Sending Input

[1463] The terminal sends the saved input data to the server via the network. The text data is formatted and sent to the server using the HTTP protocol, etc. Once the data arrives at the server, the next analysis step begins.

[1464] Step 3: Parsing the input

[1465] The server passes the text data received via the network to the generative AI model. The generative AI model performs text analysis using a natural language processing algorithm. Specifically, it extracts the necessary objects (e.g., "cat" and "car") and their interactions from the input text. The extracted results are the objects and their attribute data.

[1466] Step 4: 3D model generation

[1467] Based on the analysis results, the server requests the generative AI model to generate a 3D model. The generative AI model generates the 3D model by taking into account the shape, movement, and physical properties of the extracted object. For example, a 3D model of a cat is generated along with its movement, and a 3D model of a car is also generated according to its movement. The generated 3D model is then returned to the server.

[1468] Step 5: Run the simulation

[1469] The server inputs the generated 3D models into a simulation engine and runs the simulation. It simulates the interactions between the 3D models and their physical movements. For example, it simulates how a cat approaches a car and avoids a collision. The output of the simulation is generated as simulation data.

[1470] Step 6: Visualize the simulation results

[1471] The server sends the generated simulation data to the terminal. The terminal receives the simulation data and displays it to the user using a graphics display engine. For example, the simulation may be displayed as a 3D animation so that the user can check its details. As a result, a simulation video is displayed on the terminal.

[1472] Step 7: Recognizing User Emotions

[1473] The server analyzes the user's emotions using an emotion recognition engine. It captures facial expressions and voice in real time through sensor devices such as cameras and microphones connected to the device, and generates emotion data. For example, it can determine whether the user is expressing surprise.

[1474] Step 8: Adjust the simulation

[1475] The server dynamically adjusts the simulation content based on the emotional data analyzed by the emotion recognition engine. For example, if the user expresses surprise or fear, the server may adjust the speed of the simulation, such as slowing it down. The adjustment results are generated as new simulation data and resent to the device. The device then redisplays the adjusted simulation to the user.

[1476] Through the above steps, the processing of the entire system is completed, and optimized simulation results are provided to the user.

[1477] (Application example 2)

[1478] 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."

[1479] Current simulation systems can perform simulations by analyzing user input, generating 3D models, and visualizing the results. However, they lack the ability to dynamically adjust the simulation content according to the user's emotional state, which results in a lack of realism and interactivity to deepen the user's understanding. In particular, simulations of autonomous vehicles require appropriate speed adjustments and scenario changes according to the user's emotions.

[1480] The specific processing by the specific 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: input means for inputting simulation content from a user; analysis means for analyzing the simulation content acquired from the input means; generation means for generating a 3D model based on the content analyzed by the analysis means; execution means for executing a simulation using the 3D model generated by the generation means; visualization means for visualizing the results of the simulation executed by the execution means; an emotion engine for recognizing the emotional state of the user; and adjustment means for dynamically adjusting the simulation content based on the user's emotional state recognized by the emotion engine. This makes it possible to dynamically change the simulation content in accordance with the user's emotional state, providing a more intuitive and user-friendly simulation environment.

[1481] "User input means" refers to means by which a user inputs simulation content into a terminal.

[1482] The "analysis means" is a means for analyzing the simulation contents input by the user and extracting the objects required for the simulation, as well as their attributes and interactions.

[1483] The "generation means" is a means for automatically generating a 3D model based on the data obtained by the analysis means.

[1484] The "execution means" is a means for executing a simulation using the 3D model generated by the generation means.

[1485] The "visualization means" is a means for graphically displaying the results of the simulation executed by the execution means.

[1486] The "emotion engine" is an engine that analyzes the user's facial expression data and voice data to recognize the user's emotional state.

[1487] The "adjustment means" is a means for dynamically adjusting the simulation content based on the emotional state of the user recognized by the emotion engine.

[1488] 1. Overall system configuration:

[1489] This system consists of multiple components: a server, a terminal, and a user. The terminal provides an input means for the user to input simulation content. The server has an analysis means for analyzing the input content, a generation means for generating a 3D model based on the analysis results, an execution means for executing a simulation using the generated 3D model, a visualization means for visualizing the results of the executed simulation, an emotion engine for recognizing the user's emotional state, and an adjustment means for dynamically adjusting the simulation content based on the user's emotional state.

[1490] 2. Hardware and software configuration:

[1491] Hardware:

[1492] Smart glasses: Equipped with an input means for accepting user input, a data acquisition means for emotion recognition using a camera and microphone, and a display function for showing simulation results.

[1493] software:

[1494] EmotionRecognizer (emotion recognition library): An engine that analyzes the user's emotional state from their facial expressions and voice.

[1495] Simulation Engine: Software that runs simulations using 3D models.

[1496] ModelGenerator (3D model generation library): A library for generating 3D models for simulation.

[1497] 3. Processing Description:

[1498] User input means:

[1499] Using the smart glasses, users input the simulation content, for example, specifying a scenario such as "the behavior of an autonomous vehicle at an urban intersection."

[1500] Analysis method:

[1501] The server analyzes the scenario entered by the user and extracts the necessary objects (e.g., cars, intersections, traffic lights, etc.) and their attributes and interactions. This analysis is performed using a generative AI model.

[1502] Generation means:

[1503] Based on the analyzed data, the 3D model generation library (ModelGenerator) automatically generates a 3D model of the object, for example, a 3D model that mimics the shape and movement of a car.

[1504] To do this:

[1505] The generated 3D model is passed to a simulation engine, which simulates the scenario (e.g., the movement of a car at an intersection).

[1506] Visualization means:

[1507] The simulation results executed by the simulation engine are sent from the server to the terminal and displayed on the smart glasses display.

[1508] Emotion Engine:

[1509] The smart glasses use a built-in camera and microphone to capture and acquire the user's facial expression and voice data. EmotionRecognizer analyzes this data and recognizes the user's emotional state.

[1510] Adjustment means:

[1511] The emotion engine dynamically adjusts the simulation content based on the user's emotional state (e.g., surprise, fear) recognized by the emotion engine. For example, if the user shows surprise or fear, the simulation speed is slowed down.

[1512] 4. Example:

[1513] When a user inputs "self-driving car movement at an urban intersection," the generative AI model generates 3D models of the required objects (cars, intersections, traffic lights, etc.).

[1514] The simulation engine simulates the autonomous vehicle's movement through the intersection and displays the results on the smart glasses' display.

[1515] While the user is watching the simulation, the emotion engine analyzes the user's emotional state, and if it detects expressions of surprise or fear, it makes adjustments such as slowing down the speed of the simulation.

[1516] 5. Example prompt:

[1517] "Simulate the behavior of an autonomous vehicle at an urban intersection. Generate the necessary 3D models (buildings, traffic lights, vehicles, pedestrians, etc.) in the scenario to recreate how the vehicle will behave in a specific situation."

[1518] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1519] Step 1:

[1520] The user inputs the simulation content using smart glasses.

[1521] Input: The user enters the scenario: "Autonomous vehicle behavior at an urban intersection."

[1522] How it works: Accepts user voice and text input through the UI of the smart glasses.

[1523] Output: Simulation content (text format).

[1524] Step 2:

[1525] The terminal sends user input to the server, which parses it.

[1526] Input: User input (movement of an autonomous vehicle at an urban intersection).

[1527] How it works: The device sends input data to the server, which then uses a generative AI model to analyze the content, specifically extracting objects (cars, intersections, traffic lights, etc.).

[1528] Output: Analysis results (objects, their attributes and interactions).

[1529] Step 3:

[1530] The server generates a 3D model based on the analysis results.

[1531] Input: Analysis results (objects and their attributes and interactions).

[1532] How it works: The server uses the ModelGenerator library to generate 3D models of the extracted objects (cars, intersections, traffic lights, etc.).

[1533] Output: The generated 3D model.

[1534] Step 4:

[1535] The server runs a simulation using the generated 3D model.

[1536] Input: A generated 3D model.

[1537] How it works: The server runs a simulation using SimulationEngine to recreate a scenario (the movement of an autonomous vehicle at an urban intersection).

[1538] Output: Simulation results.

[1539] Step 5:

[1540] The server sends the simulation results to the terminal, which then visualizes them.

[1541] Input: Simulation results.

[1542] How it works: The server sends the simulation results to the device, which then displays a 3D animation of the simulation on the smart glasses display.

[1543] Output: Visualized simulation results.

[1544] Step 6:

[1545] The camera and microphone are used to recognize the user's emotional state through an emotion engine.

[1546] Input: User's facial expression data and voice data.

[1547] How it works: The smart glasses' camera and microphone are used to capture the user's facial expressions and voice, and the EmotionRecognizer library is used to analyze their emotional state.

[1548] Output: The user's emotional state (e.g., surprise, fear).

[1549] Step 7:

[1550] The server dynamically adjusts the simulation content based on the user's emotional state.

[1551] Input: User's emotional state (e.g., surprise, fear).

[1552] Operation: Depending on the emotional state, the server sends instructions to the simulation engine and makes adjustments such as slowing down the simulation speed.

[1553] Output: Adjusted simulation results.

[1554] 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.

[1555] 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.

[1556] 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 robot 414.

[1557] 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.

[1558] 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.

[1559] 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.

[1560] 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).

[1561] 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.

[1562] 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."

[1563] 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.

[1564] 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).

[1565] 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.

[1566] 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.

[1567] 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.

[1568] 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.

[1569] 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.

[1570] 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.

[1571] 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.

[1572] 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.

[1573] 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.

[1574] 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.

[1575] The following is further disclosed regarding the above embodiment.

[1576] (Claim 1)

[1577] A means for inputting simulation content from a user;

[1578] analysis means for analyzing the simulation content acquired from the input means;

[1579] a generation means for generating a 3D model based on the content analyzed by the analysis means;

[1580] an execution means for executing a simulation using the 3D model generated by the generation means;

[1581] visualization means for visualizing the results of the simulation executed by the execution means;

[1582] A system including:

[1583] (Claim 2)

[1584] 2. The system according to claim 1, wherein said analyzing means includes analyzing an object and its interaction from a simulation content input by a user.

[1585] (Claim 3)

[1586] The system according to claim 1 , wherein the generating means includes a generating means for generating a 3D model based on the results of the analysis by the analyzing means, taking into account the shape, movement, and physical properties of the object.

[1587] (Claim 4)

[1588] 2. The system of claim 1, wherein the execution means includes execution means for simulating interactions and movements using the generated 3D model, and further optimizing collision avoidance.

[1589] (Claim 5)

[1590] 2. The system of claim 1, wherein the visualization means includes visualization means for graphically displaying simulation results to a user.

[1591] "Example 1"

[1592] (Claim 1)

[1593] an input means for inputting the simulation contents from a user;

[1594] analysis means for analyzing the simulation content acquired from the input means;

[1595] a generation means for generating a three-dimensional model based on the content analyzed by the analysis means;

[1596] an execution means for executing a simulation using the three-dimensional model generated by the generation means;

[1597] visualization means for visualizing the results of the simulation executed by the execution means;

[1598] A system including:

[1599] (Claim 2)

[1600] 2. The system of claim 1, wherein the analyzing means includes analyzing means for analyzing objects and their interactions from user-input simulation content using a generative AI model.

[1601] (Claim 3)

[1602] 2. The system according to claim 1, wherein the generating means includes generating means for generating a three-dimensional model based on the results of the analysis by the analyzing means, taking into account the shape, movement, and physical properties of the object.

[1603] "Application Example 1"

[1604] (Claim 1)

[1605] an input means for inputting the simulation contents from a user;

[1606] analysis means for analyzing the simulation content acquired from the input means;

[1607] a generation means for generating a 3D model based on the content analyzed by the analysis means;

[1608] an execution means for executing a simulation using the 3D model generated by the generation means;

[1609] visualization means for visualizing the results of the simulation executed by the execution means;

[1610] This includes a generative AI model that allows users to input simulation scenarios in natural language for testing and predicting autonomous vehicle behavior.

[1611] A system including:

[1612] (Claim 2)

[1613] 2. The system of claim 1, wherein the analysis means includes analysis means for analyzing objects and their interactions from simulation content input by a user and adapting to a traffic scenario.

[1614] (Claim 3)

[1615] The system according to claim 1, wherein the generating means includes a generating means for generating a 3D model based on the results of the analysis by the analyzing means, taking into account the shape, movement, and physical properties of the object, and simulating a traffic scenario.

[1616] "Example 2: Combining Emotion Engines"

[1617] (Claim 1)

[1618] an input means for inputting the simulation contents from a user;

[1619] analysis means for analyzing the simulation content acquired from the input means;

[1620] a generation means for generating a 3D model based on the content analyzed by the analysis means;

[1621] an execution means for executing a simulation using the 3D model generated by the generation means;

[1622] visualization means for visualizing the results of the simulation executed by the execution means;

[1623] emotion recognition means for recognizing an emotion of a user;

[1624] an adjustment means for dynamically adjusting the simulation content based on the user's emotion recognized by the emotion recognition means;

[1625] A system including:

[1626] (Claim 2)

[1627] 2. The system according to claim 1, wherein said analyzing means includes analyzing an object and its interaction from a simulation content input by a user.

[1628] (Claim 3)

[1629] The system according to claim 1 , wherein the generating means includes a generating means for generating a 3D model based on the results of the analysis by the analyzing means, taking into account the shape, movement, and physical properties of the object.

[1630] "Application example 2 when combining emotion engines"

[1631] (Claim 1)

[1632] A means for inputting simulation content from a user;

[1633] analysis means for analyzing the simulation content acquired from the input means;

[1634] a generation means for generating a 3D model based on the content analyzed by the analysis means;

[1635] an execution means for executing a simulation using the 3D model generated by the generation means;

[1636] visualization means for visualizing the results of the simulation executed by the execution means;

[1637] an emotion engine that recognizes the user's emotional state;

[1638] an adjusting means for dynamically adjusting the simulation content based on the emotional state of the user recognized by the emotion engine;

[1639] A system including:

[1640] (Claim 2)

[1641] 2. The system according to claim 1, wherein said analyzing means includes analyzing an object and its interaction from a simulation content input by a user.

[1642] (Claim 3)

[1643] The system according to claim 1 , wherein the generating means includes a generating means for generating a 3D model based on the results of the analysis by the analyzing means, taking into account the shape, movement, and physical properties of the object. [Explanation of symbols]

[1644] 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 for inputting simulation content from a user; analysis means for analyzing the simulation content acquired from the input means; a generation means for generating a 3D model based on the content analyzed by the analysis means; an execution means for executing a simulation using the 3D model generated by the generation means; visualization means for visualizing the results of the simulation executed by the execution means; A system including:

2. 2. The system according to claim 1, wherein said analyzing means includes analyzing means for analyzing objects and their interactions from simulation content input by a user.

3. The system according to claim 1 , wherein the generating means includes a generating means for generating a 3D model based on the results of the analysis by the analyzing means, taking into account the shape, movement, and physical properties of the object.

4. The system of claim 1 , wherein the execution means includes execution means for simulating interactions and movements using the generated 3D model, and further optimizing collision avoidance.

5. The system according to claim 1 , wherein the visualization means includes visualization means for displaying the simulation results graphically to a user.

Images