system

Abstract

We provide the system. [Solution] A means of collecting data based on past risk cases and converting that data into a three-dimensional model, A means for generating a virtual reality simulation based on the three-dimensional model, A means for having a user run the virtual reality simulation and monitoring the user's behavior, A means for analyzing the monitoring results and providing feedback to the user, A system that includes this.

Description

Technical Field

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

Background Art

[0002] Patent Document 1 discloses a method for controlling a persona chatbot, which is performed by at least one processor and includes steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a character of the chatbot, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance as a response to the user utterance.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In conventional safety education using lectures and two-dimensional videos, there is a problem that it is difficult for the participants to feel the danger, and labor accident prevention and improvement of safety awareness have not been effectively achieved. In particular, it is difficult for the participants to recognize the danger as their own problem, and there is a problem that although the danger avoidance behavior in the actual site can be understood intellectually, it cannot be linked to a reflex action.

Means for Solving the Problems

[0005] This invention provides a means for collecting data based on past hazardous incidents and structuring the data into a three-dimensional model using artificial intelligence technology. It also includes means for generating a virtual reality simulation based on the three-dimensional model and providing a virtual environment that the user can experience. Furthermore, it includes means for the user to perform hazard avoidance actions through the virtual reality simulation, and for monitoring and evaluating those actions. In addition, the system is characterized by solving these problems by having means for analyzing the monitoring results, providing feedback to the user, and improving hazard recognition and avoidance actions.

[0006] "Past hazardous incidents" refer to records of important safety-related events that have occurred in the past in the work environment or in the course of operations, such as near misses, accidents, and injuries.

[0007] "Means of data collection" refers to the techniques and processes for systematically gathering information and materials necessary for a specific purpose.

[0008] "Artificial intelligence technology" refers to a collection of algorithms and programs that computer systems use to imitate or complement human intellectual behavior.

[0009] A "three-dimensional model" is a dataset or digital object that represents real-world objects and environments three-dimensionally in a three-dimensional space.

[0010] "Virtual reality simulation" is a technology or application that provides users with an immersive and interactive experience in a computer-generated three-dimensional environment.

[0011] "Means for monitoring user behavior" refers to technologies or devices for monitoring and recording actions and decisions taken by users within virtual reality.

[0012] "Means of providing feedback" refers to a process or technology that notifies users of areas for improvement and evaluations based on simulation results, thereby encouraging them to improve their behavior. [Brief explanation of the drawing]

[0013] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Figure 11] This is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] This is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] This is a sequence diagram showing the processing flow of the data processing system in Example 2, which incorporates an emotion engine. [Figure 14] This is a sequence diagram showing the processing flow of the data processing system in Application Example 2, which combines an emotion engine. [Modes for carrying out the invention]

[0014] Hereinafter, an example of an embodiment of a system according to the technology of the present disclosure will be described with reference to the accompanying drawings.

[0015] First, the terms used in the following description will be explained.

[0016] In the following embodiments, a labeled processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Also, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), and the like.

[0017] In the following embodiments, a labeled RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

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

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

[0020] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." That is, "A and / or B" means that it may be A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or."

[0021] [First Embodiment]

[0022] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0023] As shown in Figure 1, the data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0024] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0025] The smart device 14 comprises a computer 36, a reception device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The reception device 38, output device 40, and camera 42 are also connected to the bus 52.

[0026] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0027] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form perceptible to the user 20 (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0028] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

[0029] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0030] As shown in Figure 2, in the data processing device 12, specific processing is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" related to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0031] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0032] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with a specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0033] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0034] The system of this invention combines virtual reality technology and artificial intelligence technology to enable effective occupational safety education by utilizing data from past hazardous incidents. The server first collects data on past near misses and accident / injury cases that form the basis of safety education. This data includes reports, photographs, video footage, and text information related to the cases.

[0035] Next, the server analyzes the collected data and converts it into a three-dimensional model using artificial intelligence technology. This makes it possible to construct a virtual space that realistically reproduces the actual environment in three dimensions. This three-dimensional model will serve as the foundation for future simulations.

[0036] The server then designs a virtual reality simulation based on this three-dimensional model, recreating specific hazardous scenarios. The terminal then provides this virtual reality simulation to the user through a VR headset. The user can experience real-time interaction based on their own movements within the VR environment. For example, a simulation recreating a data center fire scenario could be considered. The user would experience the entire process from the outbreak of the fire to evacuation, learning appropriate actions.

[0037] The user's actions during the simulation are transmitted to the server via the terminal. The server monitors this action data and analyzes it using artificial intelligence. Specifically, it evaluates how the user attempted to avoid danger, including the speed and sequence of their actions. Based on this evaluation, the server provides feedback to the user, which is then used to improve future simulations and educational content.

[0038] In this way, the system of the present invention enables users to improve their risk awareness and acquire reflexive risk avoidance actions through practical training in a virtual environment.

[0039] The following describes the processing flow.

[0040] Step 1:

[0041] The server collects past near-miss and accident / injury case data necessary for safety training from a database. This data exists in various forms such as reports, photos, video footage, and text information, and the server converts it into a unified format.

[0042] Step 2:

[0043] The server analyzes the collected data and uses artificial intelligence technologies such as image recognition and natural language processing to convert the data into a three-dimensional model. The AI ​​understands the details of the accident from the text and identifies the environment and circumstances from the image data.

[0044] Step 3:

[0045] The server designs virtual reality simulation scenarios based on the generated 3D models. Here, specific hazardous scenarios are reproduced, and interaction and environmental elements are configured to ensure that users can have a immersive virtual experience.

[0046] Step 4:

[0047] The device confirms that the simulation is ready and prompts the user to put on the VR headset. Once the device confirms the user is ready, it starts the virtual reality simulation, and the user begins their experience in the virtual environment.

[0048] Step 5:

[0049] Users are prompted to perform real-world actions within the virtual reality environment, detect danger, and react appropriately. In this process, users are required to make decisions and take actions according to instructions within the virtual environment.

[0050] Step 6:

[0051] The device tracks the user's actions in real time during the simulation and sends that data to the server. This data includes detailed information such as the user's eye movements, speed, and direction of actions.

[0052] Step 7:

[0053] The server analyzes the behavioral data sent from the terminal and runs an algorithm to evaluate how effective the user's actions were in avoiding danger.

[0054] Step 8:

[0055] The server provides users with specific feedback based on the evaluation results. This feedback includes details about effective actions and areas that need improvement. Users can use this information to guide their responses in the next simulation.

[0056] (Example 1)

[0057] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0058] Traditional occupational safety training often focused solely on theoretical knowledge acquisition without providing participants with the opportunity to experience actual hazards. Furthermore, the training content was often uniform, failing to provide appropriate feedback tailored to each user's level of hazard awareness and avoidance behavior. Additionally, introducing new simulations presented significant challenges due to the considerable effort required.

[0059] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0060] In this invention, the server includes means for collecting information based on past hazard cases and structuring said information into a three-dimensional model using artificial intelligence technology; means for designing a virtual reality environment based on said three-dimensional model and generating specific hazard scenarios; and means for creating new prompt sentences using the generated AI model and preparing further simulation scenarios. This enables feedback based on individual user behavior and practical hazard awareness education.

[0061] "Past hazardous incidents" refers to specific information or events related to past near misses, accidents, or injuries in the work environment.

[0062] "Information gathering" refers to the act of extracting and collecting useful data from databases or other sources according to a specific purpose.

[0063] "Artificial intelligence technology" refers to technologies such as machine learning and data analysis in which computers mimic human intelligence and perform the necessary analyses to solve specific problems.

[0064] "Structuring into a three-dimensional model" refers to representing collected data in a three-dimensional virtual format and visually embodying it.

[0065] A "virtual reality environment" refers to a simulated three-dimensional space created using computer technology that users can experience.

[0066] A "specific danger scenario" refers to a concrete dangerous situation or case that is reproduced within the virtual reality environment, with the aim of allowing users to learn by dealing with it.

[0067] A "generative AI model" refers to a pre-trained artificial intelligence program used to generate new prompts or ideas from given data.

[0068] A "prompt message" refers to a document or phrase used as input to a generative AI model to obtain a specific output.

[0069] "Feedback" refers to providing evaluations and suggestions regarding user actions and results, and offering information for improvement.

[0070] This invention is a workplace safety education system that combines virtual reality and artificial intelligence technology. Its main components include a server, terminals, and users working together.

[0071] The server collects data on past risk incidents from an external database. Specifically, it uses Python and SQL to extract information such as reports, photos, and video footage. The collected data is then analyzed using artificial intelligence technology, extracting important information using tools like TENSORFLOW® and OpenCV, and generating a three-dimensional model. This model is then converted into a virtual reality environment using 3D modeling software (e.g., Blender, Unity).

[0072] The server then designs specific hazardous scenarios in the virtual reality environment based on the generated three-dimensional model. The designed simulations are programmed using C or JavaScript®, enabling the time progression of events and user interaction within the virtual space.

[0073] The terminal provides the user with simulation data transmitted from the server via a VR headset. Using a head-mounted display such as the Oculus Rift, the user can visually experience a virtual reality environment. The user can record their movements and actions within this environment in real time. A concrete example of a user experience is experiencing an evacuation scenario during a fire.

[0074] User actions are transmitted from the device to the server, where the server analyzes the data. Using machine learning algorithms, the server analyzes user behavior data to evaluate each user's risk avoidance ability and behavioral patterns. Based on the evaluated data, the server provides the user with feedback on areas for improvement.

[0075] Furthermore, it includes a function to create new prompts using a generative AI model, preparing a wider variety of simulation scenarios. For example, it is possible to input a prompt such as "Design a simulation of a safe evacuation scenario in the event of a fire in a data center" into the AI ​​model and generate a new scenario. This provides users with a simulation experience tailored to their needs and can continuously raise their safety awareness.

[0076] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0077] Step 1:

[0078] The server collects past incident data from an external database. It accepts database queries and API access as input, and outputs reports, photos, video footage, and related text data. Specifically, a Python script executes SQL queries, retrieves the necessary data, and saves it to a temporary file.

[0079] Step 2:

[0080] The server analyzes the collected data using artificial intelligence technology and generates a three-dimensional model. It receives the data collected in step 1 as input and performs natural language processing and image analysis. The output is three-dimensional model data for constructing a virtual reality environment. Specifically, a machine learning model using TensorFlow extracts risk elements from the report, OpenCV analyzes photos and videos, and converts the data into a format compatible with Blender.

[0081] Step 3:

[0082] The server designs a virtual reality simulation using the generated 3D model. It uses the 3D model data obtained in step 2 as input to assemble the simulation logic for the scenario. The output is a simulation program that can be reproduced in a virtual reality environment. Specifically, a script written in C defines event sequences in Unity, enabling user interaction.

[0083] Step 4:

[0084] The terminal receives simulation data from the server and provides the user with a virtual reality environment through a VR headset. It receives simulation program data from the server as input and presents an immersive virtual scene to the user visually and aurally as output. Specifically, VR equipment such as the Oculus Rift executes a simulation program running on Unity, updating the scene according to the user's movements.

[0085] Step 5:

[0086] Users interact with a simulation within a virtual reality environment, executing their own movements and choices. They receive visual, auditory, and haptic feedback from VR equipment as input, and simulate actions to avoid danger as output. Specifically, users use hand controllers to select menus, move, and respond to simulation events.

[0087] Step 6:

[0088] The terminal records the user's actions during simulation and sends them to the server. It takes user operation logs and motion data from sensors as input, and sends the combined action data to the server as output. Specifically, motion sensors monitor the user's position and posture, and store the data in a transmission buffer according to the communication protocol with the server.

[0089] Step 7:

[0090] The server analyzes user behavior data and generates feedback. It receives user behavior data sent from the terminal in step 6 as input and generates feedback content to provide to the user as output. Specifically, the server uses a machine learning algorithm to evaluate user behavior and automatically summarizes areas for improvement based on the results into text.

[0091] Step 8:

[0092] The server uses a generative AI model to create new prompts and prepare for the next simulation. It receives feedback and simulation evaluation results as input and generates prompts for a new simulation scenario as output. Specifically, the AI ​​model analyzes existing scenarios and user feedback data to generate detailed prompts for the next simulation.

[0093] (Application Example 1)

[0094] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0095] Traditional safety training in the workplace, such as lectures and simple simulations, faces the challenge of not adequately addressing real-world hazards. This results in insufficient development of employees' hazard awareness and ability to take appropriate immediate action, making it difficult to respond quickly when an actual accident occurs.

[0096] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0097] In this invention, the server includes means for collecting information based on past hazard cases and converting said information into a three-dimensional model, means for generating a virtual space simulation based on the three-dimensional model, and means for causing an operating entity to execute the virtual space simulation and monitoring the operating entity's activities. This makes it possible to reproduce specific hazard scenarios within industrial facilities in virtual reality, analyze the actions of the operating entity, and provide real-time feedback.

[0098] "Past dangerous incidents" refer to records of incidents that include information about accidents and disasters that have actually occurred.

[0099] "Information" refers to data such as reports, photographs, videos, and text related to hazardous incidents.

[0100] A "3D model" is a model reproduced in a three-dimensional virtual space constructed based on information.

[0101] A "virtual space simulation" is a simulation that recreates a virtual reality scenario that a user can experience, based on a three-dimensional model.

[0102] "Operating entity" refers to the user or participant experiencing the virtual space simulation.

[0103] "Monitoring activity" means observing and recording the actions of the controlling entity in real time.

[0104] "Providing a response" refers to the act of conveying appropriate guidance and information based on the actions of the manipulator.

[0105] A "specific hazard scenario within an industrial facility" is a scenario that reproduces specific hazardous situations that may occur within a factory or manufacturing facility in a virtual space.

[0106] "Analyzing behavior" is the process of analyzing the actions of the manipulator in detail and evaluating their effectiveness and appropriateness.

[0107] "Real-time feedback" refers to guidance and evaluation provided immediately in response to the actions of the user during a virtual space simulation.

[0108] The system used to realize this application generates virtual space simulations based on information about hazardous situations and allows users to experience them, thereby providing safety education.

[0109] The server first collects past incidents of risk, analyzes this information, and converts it into a three-dimensional model. Artificial intelligence technology is used for the analysis, specifically software such as TensorFlow. The 3D model is then constructed as a virtual space simulation in a development environment like Unity.

[0110] The terminal plays the role of providing these simulations to the user. By wearing smart glasses or a head-mounted display, the user can experience dangerous scenarios in a virtual space. Devices such as the Oculus Quest 2 are being utilized.

[0111] When a user experiences a simulation, their activities are monitored in real time, and the server receives the data. This data is used to analyze the user's movements and behavioral patterns. Based on the analysis results, users are immediately provided with feedback, thus enhancing the effectiveness of safety education even during the simulation.

[0112] For example, if a user experiences a potentially dangerous situation in an industrial facility and takes inappropriate actions during that process, the system provides guidance to lead them to appropriate behavior. This feedback allows the user to learn safer behaviors.

[0113] An example of a prompt might be: "Propose a system that uses VR to recreate dangerous situations in a factory, analyzes participants' behavior with AI, and provides feedback on how to improve safety education."

[0114] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0115] Step 1:

[0116] The server collects information about risky incidents. This information includes reports, images, videos, and text. The collected information is stored in a database as input.

[0117] Step 2:

[0118] The server analyzes the information stored in the database. Using generative AI models and artificial intelligence technology, the analysis converts the collected information into a three-dimensional model. This data processing results in the output of the 3D model.

[0119] Step 3:

[0120] The server designs a virtual space simulation based on the generated 3D model and builds the simulation environment in the Unity development environment. It uses the 3D model as input and generates the virtual environment as output.

[0121] Step 4:

[0122] The device provides a virtual space simulation to the user through a device such as the Oculus Quest 2. The device allows the user to access the virtual space and obtain a virtual experience through sight and sound.

[0123] Step 5:

[0124] Users participate in virtual reality simulations and experience dangerous situations. Action data from the user during the experience is collected and transmitted to a server.

[0125] Step 6:

[0126] The server analyzes the received operational data from the user. This data is evaluated using an AI algorithm, and feedback is generated regarding safety and appropriateness of the actions.

[0127] Step 7:

[0128] The server provides real-time feedback to the user based on the analysis results. It identifies areas for improvement through data processing and encourages specific actions.

[0129] Step 8:

[0130] The server saves the simulation results and updates the data using a generative AI model to further optimize the educational content. This process improves the quality of subsequent simulations.

[0131] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0132] The present invention combines an emotion engine with a system that provides effective occupational safety education through virtual reality simulations using past hazard data to achieve a more precise educational experience. The server first collects past near-miss and accident / injury cases and converts them into two-dimensional and three-dimensional data formats. Artificial intelligence technology is applied to the collected data to generate a three-dimensional model.

[0133] Next, the server designs a virtual reality simulation based on this three-dimensional model, allowing the user to experience danger in a safe and realistic environment. The terminal provides this simulation to the user through a VR headset and assists the user in initiating interaction within the simulation. The user acts in various scenarios within this virtual environment and learns safe operations.

[0134] A distinctive feature of this invention is the incorporation of an emotion engine into the system. The emotion engine recognizes the user's emotional state through facial and voice analysis. The server takes in both the user's emotional and behavioral data and performs a comprehensive analysis. Based on this analysis, it dynamically adjusts the virtual reality simulation scenario to create a situation in which the user can learn more effectively. Furthermore, by providing the user with feedback tailored to their individual emotional state, it provides comprehensive guidance that includes not only immediate reactions but also psychological aspects.

[0135] For example, in a data center fire scenario, when a user genuinely feels in danger, the emotion engine can sense this and adjust guidance and advice to provide a greater sense of security. This allows users to integrate their emotions and actions and learn to more effectively desensitize risk avoidance behaviors. In this way, the system of the present invention enhances the user's ability to manage their own safety in the workplace by simultaneously improving both their emotional and behavioral aspects.

[0136] The following describes the processing flow.

[0137] Step 1:

[0138] The server collects data on past near misses, accidents, and malfunctions. This includes reports, photos, video footage, and text information. The collected data is converted into a standardized format for analysis.

[0139] Step 2:

[0140] The server uses artificial intelligence technology to convert the collected data into a three-dimensional model. The AI ​​then uses image recognition technology to convert 2D data into 3D information, preparing to recreate the details of the accident in three dimensions.

[0141] Step 3:

[0142] The server designs virtual reality simulation scenarios based on the generated three-dimensional models. This includes virtual environments to reproduce specific hazardous scenarios and the placement of dynamic elements that users can interact with.

[0143] Step 4:

[0144] The device allows the user to run a simulation through a VR headset. Through this experience in the virtual environment, the user is encouraged to perceive danger and take appropriate action.

[0145] Step 5:

[0146] When a user begins to act within virtual reality, the emotion engine analyzes the user's facial expressions and voice in real time to recognize the user's emotional state. This emotion data is sent to the server along with the behavioral data.

[0147] Step 6:

[0148] The server integrates emotional and behavioral data sent from the terminal to comprehensively analyze the user's risk avoidance behavior and emotional responses. Based on this analysis, it determines how to adjust the scenario and what kind of feedback to provide to the user.

[0149] Step 7:

[0150] The server provides feedback based on how the user felt and acted during the simulation. This feedback includes areas for improvement in the user's behavior and ways to manage emotions.

[0151] Step 8:

[0152] Users receive feedback, which they then use to improve their risk avoidance abilities in subsequent simulations, while also developing skills to control their own emotional responses.

[0153] (Example 2)

[0154] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0155] Traditional workplace safety education systems merely provide past hazardous incidents as information, failing to offer guidance tailored to the individual emotional states and behaviors of users. Furthermore, they lacked a dynamic learning environment that facilitated user behavioral improvement. Consequently, learning effectiveness was limited, and there were challenges in actually improving hazard avoidance abilities.

[0156] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0157] In this invention, the server includes means for collecting information based on past hazard cases and converting said information into a three-dimensional structure, means for generating a virtual reality environment based on said three-dimensional structure, and means for recognizing the user's emotional state and dynamically adjusting the virtual reality environment scenario based on said emotional state. This enables users to enjoy a learning experience tailored to their individual emotional state and improve their ability to avoid hazards more effectively.

[0158] "Means of information gathering" refers to the processes and techniques for collecting necessary information from documents and databases related to past incidents of danger.

[0159] "Means of converting into a three-dimensional structure" refers to methods and techniques for constructing collected information into a three-dimensional model that can be visually understood.

[0160] "Means for generating a virtual reality environment" refers to the processes and technologies for creating a simulated space that is reproduced on a computer based on a three-dimensional structure.

[0161] "Means of monitoring user reactions" refer to devices and technologies used to track and record the actions users take within a virtual reality environment.

[0162] A "means of providing improvement information" refers to a system that conveys appropriate feedback and advice to users based on their behavioral data.

[0163] "Means for recognizing a user's emotional state" refers to technologies that analyze a user's facial expressions and voice to determine their psychological state and emotions.

[0164] "Means for dynamically adjusting scenarios" refers to a technology that changes the scenario within virtual reality in real time according to the recognized emotional state of the user.

[0165] To implement this invention, the server first collects data on past hazardous incidents from safety reports and public accident databases. Based on this data, the server uses a common deep learning library, a machine learning framework, to convert it into two-dimensional and three-dimensional data formats. This allows the server to learn patterns and features in the collected data and build a visually reproducible model.

[0166] The server then designs a virtual reality simulation based on this generated three-dimensional model. This step utilizes virtual reality platforms such as Unity or Unreal Engine. The virtual reality environment is designed to be an intuitively interactive space for the user. Within this environment, the user can experience an immersive simulation through a VR headset or similar device. A concrete example is a scenario simulating a fire in a data center. In this scenario, the user is trained to identify and follow appropriate evacuation routes during a fire.

[0167] Furthermore, the server uses an emotion engine to analyze the user's facial expressions and voice to recognize their emotional state. Based on this recognition, it can dynamically adjust the virtual reality simulation scenario to provide the user with a personalized learning experience. For example, if the user is under high stress, the system will reduce the difficulty of the scenario and provide guidance that enhances their sense of security.

[0168] An example of a prompt is, "Create a scenario to learn safe behaviors while operating machinery in a factory." Based on this prompt, the generating AI model designs a specific simulation scenario and presents it in an actionable format. In this way, the system can provide users with effective safety education and effectively improve their ability to avoid hazards in the real world.

[0169] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0170] Step 1:

[0171] The server collects data on past hazard incidents. Industry-standard safety reports and historical accident databases are used as data input sources. This collected data is prepared for future analysis and model generation. The data includes not only text but also charts, graphs, and statistical information. The output is a structured dataset.

[0172] Step 2:

[0173] The server performs a two-dimensional to three-dimensional transformation using the collected data. The structured data obtained in Step 1 is used as input. The server utilizes a machine learning framework to analyze the data features and construct a three-dimensional model. Here, it finds correlations between data points and reorganizes them into a visualizeable form. The output is a dataset represented as a three-dimensional model.

[0174] Step 3:

[0175] The server constructs a virtual reality environment based on the generated 3D model. The 3D model obtained in step 2 is used as input. The server uses the virtual reality platform to design and provide interactive scenarios to the user. The program then redesigns the simulation based on this to reproduce specific hazardous situations. The output is the simulation environment experienced by the user.

[0176] Step 4:

[0177] The terminal provides the user with a virtual reality environment using a VR headset. The input is the simulation environment designed in step 3. The user puts on the VR device and begins acting in a virtual scenario that closely resembles reality. The terminal tracks the user's actions and movements and collects the results of the interaction. The output is user behavior data.

[0178] Step 5:

[0179] The server recognizes the user's emotional state and adjusts the virtual environment accordingly. It obtains input for analyzing the emotional state, along with user behavior data from the terminal. The server uses an emotion analysis algorithm to determine the user's stress level and interests, using these as indicators to adjust the virtual scenario. The program dynamically changes the simulation difficulty and scenario. The output is the adjusted learning environment.

[0180] Step 6:

[0181] The server provides feedback to the user. The input is the user's behavioral data and sentiment analysis results collected in step 4. Based on this, the server creates advice and feedback for improvement and communicates it to the user. This gives the user an opportunity to review their own behavior and learn effectively. The output is feedback provided to the user in text or audio format.

[0182] (Application Example 2)

[0183] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as a "server" and the smart device 14 as a "terminal".

[0184] Traditional occupational safety education systems use general virtual reality simulations to train and improve user behavior. However, they have the drawback of providing uniform instruction without considering the emotional state of individual users, making it difficult to deliver effective education tailored to the specific psychological state of each user. Furthermore, the lack of real-time scenario adjustments reduces the efficiency of training, making it difficult to improve actual hazard avoidance abilities.

[0185] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0186] In this invention, the server includes means for collecting data based on past hazard cases and converting said data into a three-dimensional model, means for generating a virtual reality simulation based on the three-dimensional model, means for analyzing the emotional state of the user running the virtual reality simulation, means for dynamically adjusting the scenario based on said emotional state, means for monitoring and comprehensively analyzing the user's behavior, and means for providing feedback. This makes it possible to provide effective and individualized occupational safety education to each user that takes their emotional state into account, and to promote the acquisition of hazard avoidance behaviors in an environment close to reality.

[0187] "Past hazardous incidents" refer to detailed records of accidents and near misses that have occurred in the past, and are data used to understand and avoid hazards in the workplace.

[0188] A "three-dimensional model" refers to a digital representation that reproduces real-world objects and situations in three dimensions, and is used for simulations in virtual spaces.

[0189] "Virtual reality simulation" refers to a technology in which users interact with a computer-generated virtual environment, and is used to simulate real-world situations.

[0190] "Emotional state" refers to the subjective psychological experience a user feels during an experience, and is inferred from data such as facial expressions and voice.

[0191] "Dynamic adjustment" refers to a process that makes changes in real time, meaning the system adapts based on user feedback to provide the optimal scenario.

[0192] "Monitoring" refers to the process of continuously observing and collecting data on user behavior and reactions.

[0193] "Feedback" refers to evaluation and guidance information provided to improve the user's learning efficiency, and is information that helps improve during the training process.

[0194] To implement this invention, the server first collects data on past hazardous incidents. This involves a process of collecting detailed data on near misses and accidents in the actual work environment using input devices such as cameras and sensors. The collected data is converted from a two-dimensional format to a three-dimensional format, and a more realistic model is created using three-dimensional modeling software such as Unity.

[0195] Next, the server uses artificial intelligence technology to analyze a three-dimensional model and generate a virtual reality simulation. This process utilizes machine learning frameworks such as TensorFlow to construct various scenarios that the user will experience. Within the simulation, the user immerses themselves in the virtual environment through a VR headset, safely learning about real-world dangerous situations.

[0196] Furthermore, to analyze the user's emotional state in real time, the server uses OpenCV to read facial expressions and infers the emotional state from the user's voice data. Based on this, the emotion engine dynamically adjusts the virtual reality scenario. If the user is in a high-stress state, the difficulty of the scenario is reduced or appropriate advice is provided; conversely, if the user is focused, training is performed in more complex situations.

[0197] A concrete example is an emergency situation in a factory environment where an oil leak causes a fire. If the user panics in this scenario, the emotion engine will sense this and immediately provide reassuring guidance. This practice allows the user to calmly learn how to respond.

[0198] An example of a prompt message might be, "In the event of a fire in the factory, analyze the operators' emotional responses and adaptive behaviors, and develop an appropriate scenario." This instructs the generative AI model on how to adjust the scenario in real time.

[0199] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0200] Step 1:

[0201] The server collects data on past incidents of risk. Specifically, it acquires two-dimensional data as input from devices such as cameras and sensors, and stores this information in a database. The collected data is used as foundational data for conversion into a three-dimensional model in the next step.

[0202] Step 2:

[0203] The server converts the collected two-dimensional data into a three-dimensional model. This conversion uses three-dimensional modeling software such as Unity, and the output is a three-dimensional model. The data is processed into a model with depth and three-dimensional structure. This creates a realistic environment that can be actually manipulated in a virtual reality simulation.

[0204] Step 3:

[0205] The server designs and builds virtual reality simulations based on the generated 3D models. The output is a virtual environment with various scenarios. Using a generation AI model, various conditions in each scenario are controlled, and realism is enhanced by including random elements. In this process, prompt statements are used as input to generate scenarios based on specific conditions.

[0206] Step 4:

[0207] The user enters the simulation using a VR headset. The user's experience begins, and they interact within the scenario, learning how to operate the system and take actions to avoid danger. The user's actions within VR are recorded as behavioral data for analysis in the next step.

[0208] Step 5:

[0209] The server analyzes user behavior data, facial expressions, and voice data obtained through VR simulation. The input data is analyzed in real time using AI technology (TensorFlow) to infer the user's emotional state. This process outputs numerical data representing the user's psychological state, such as stress levels and concentration levels.

[0210] Step 6:

[0211] The server dynamically adjusts the simulation scenario based on the user's emotional state. The input to this process is the quantified emotional data from the previous step; the server adjusts the output by easing the scenario when emotions are heightened and increasing the difficulty when emotions are calm. This provides a learning experience optimized for each individual user.

[0212] Step 7:

[0213] The server generates and provides feedback to the user based on the final analysis of user behavior and emotions. It analyzes user performance and areas for improvement from the input data, providing specific and effective guidance as output. The feedback includes points to focus on in the next training session and guidelines for further learning.

[0214] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0215] Data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0216] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart device 14.

[0217] [Second Embodiment]

[0218] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0219] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0220] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0221] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0222] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0223] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0224] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0225] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0226] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0227] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0228] In the smart glasses 214, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0229] Next, the identification processing performed by the identification processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0230] The system of this invention combines virtual reality technology and artificial intelligence technology to enable effective occupational safety education by utilizing data from past hazardous incidents. The server first collects data on past near misses and accident / injury cases that form the basis of safety education. This data includes reports, photographs, video footage, and text information related to the cases.

[0231] Next, the server analyzes the collected data and converts it into a three-dimensional model using artificial intelligence technology. This makes it possible to construct a virtual space that realistically reproduces the actual environment in three dimensions. This three-dimensional model will serve as the foundation for future simulations.

[0232] The server then designs a virtual reality simulation based on this three-dimensional model, recreating specific hazardous scenarios. The terminal then provides this virtual reality simulation to the user through a VR headset. The user can experience real-time interaction based on their own movements within the VR environment. For example, a simulation recreating a data center fire scenario could be considered. The user would experience the entire process from the outbreak of the fire to evacuation, learning appropriate actions.

[0233] The user's actions during the simulation are transmitted to the server via the terminal. The server monitors this action data and analyzes it using artificial intelligence. Specifically, it evaluates how the user attempted to avoid danger, including the speed and sequence of their actions. Based on this evaluation, the server provides feedback to the user, which is then used to improve future simulations and educational content.

[0234] In this way, the system of the present invention enables users to improve their risk awareness and acquire reflexive risk avoidance actions through practical training in a virtual environment.

[0235] The following describes the processing flow.

[0236] Step 1:

[0237] The server collects data from a database of past near misses and accident / injury incidents necessary for safety training. This data exists in various formats, such as reports, photos, video footage, and text information, and the server converts it into a unified format.

[0238] Step 2:

[0239] The server analyzes the collected data and uses artificial intelligence technologies such as image recognition and natural language processing to convert the data into a three-dimensional model. The AI ​​understands the details of the accident from the text and identifies the environment and circumstances from the image data.

[0240] Step 3:

[0241] The server designs virtual reality simulation scenarios based on the generated 3D models. Here, specific hazardous scenarios are reproduced, and interaction and environmental elements are configured to ensure that users can have a realistic virtual experience.

[0242] Step 4:

[0243] The device confirms that the simulation is ready and prompts the user to put on the VR headset. Once the device confirms the user is ready, it starts the virtual reality simulation, and the user begins their experience in the virtual environment.

[0244] Step 5:

[0245] Users are prompted to perform real-world actions within the virtual reality environment, detect danger, and react appropriately. In this process, users are required to make decisions and take actions according to instructions within the virtual environment.

[0246] Step 6:

[0247] The device tracks the user's actions in real time during the simulation and sends that data to the server. This data includes detailed information such as the user's eye movements, speed, and direction of actions.

[0248] Step 7:

[0249] The server analyzes the behavioral data sent from the terminal and runs an algorithm to evaluate how effective the user's actions were in avoiding danger.

[0250] Step 8:

[0251] The server provides users with specific feedback based on the evaluation results. This feedback includes details about effective actions and areas that need improvement. Users can use this information to guide their responses in the next simulation.

[0252] (Example 1)

[0253] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0254] Traditional occupational safety training often focused solely on theoretical knowledge acquisition without providing participants with the opportunity to experience actual hazards. Furthermore, the training content was often uniform, failing to provide appropriate feedback tailored to each user's level of hazard awareness and avoidance behavior. Additionally, introducing new simulations presented significant challenges due to the considerable effort required.

[0255] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0256] In this invention, the server includes means for collecting information based on past hazard cases and structuring said information into a three-dimensional model using artificial intelligence technology; means for designing a virtual reality environment based on said three-dimensional model and generating specific hazard scenarios; and means for creating new prompt sentences using the generated AI model and preparing further simulation scenarios. This enables feedback based on individual user behavior and practical hazard awareness education.

[0257] "Past hazardous incidents" refers to specific information or events related to past near misses, accidents, or injuries in the work environment.

[0258] "Information gathering" refers to the act of extracting and collecting useful data from databases or other sources according to a specific purpose.

[0259] "Artificial intelligence technology" refers to technologies such as machine learning and data analysis in which computers mimic human intelligence and perform the necessary analyses to solve specific problems.

[0260] "Structuring into a three-dimensional model" refers to representing collected data in a three-dimensional virtual format and visually embodying it.

[0261] A "virtual reality environment" refers to a simulated three-dimensional space created using computer technology that users can experience.

[0262] A "specific danger scenario" refers to a concrete dangerous situation or case that is reproduced within the virtual reality environment, with the aim of allowing users to learn by dealing with it.

[0263] A "generative AI model" refers to a pre-trained artificial intelligence program used to generate new prompts or ideas from given data.

[0264] A "prompt message" refers to a document or phrase used as input to a generative AI model to obtain a specific output.

[0265] "Feedback" refers to providing evaluations and suggestions regarding user actions and results, and offering information for improvement.

[0266] This invention is a workplace safety education system that combines virtual reality and artificial intelligence technology. Its main components include a server, terminals, and users working together.

[0267] The server collects data on past risk incidents from an external database. Specifically, it uses Python and SQL to extract information such as reports, photos, and video footage. The collected data is then analyzed using artificial intelligence technology, extracting important information using TensorFlow and OpenCV, and generating a three-dimensional model. This model is then converted into a virtual reality environment using 3D modeling software (e.g., Blender, Unity).

[0268] The server then designs specific hazardous scenarios in the virtual reality environment based on the generated 3D model. The designed simulations are programmed using C or JavaScript, enabling the time progression of events and user interaction within the virtual space.

[0269] The terminal provides the user with simulation data transmitted from the server via a VR headset. Using a head-mounted display such as the Oculus Rift, the user can visually experience a virtual reality environment. The user can record their movements and actions within this environment in real time. A concrete example of a user experience is experiencing an evacuation scenario during a fire.

[0270] User actions are transmitted from the device to the server, where the server analyzes the data. Using machine learning algorithms, the server analyzes user behavior data to evaluate each user's risk avoidance ability and behavioral patterns. Based on the evaluated data, the server provides the user with feedback on areas for improvement.

[0271] Furthermore, it includes a function to create new prompts using a generative AI model, preparing a wider variety of simulation scenarios. For example, it is possible to input a prompt such as "Design a simulation of a safe evacuation scenario in the event of a fire in a data center" into the AI ​​model and generate a new scenario. This provides users with a simulation experience tailored to their needs and can continuously raise their safety awareness.

[0272] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0273] Step 1:

[0274] The server collects past incident data from an external database. It accepts database queries and API access as input, and outputs reports, photos, video footage, and related text data. Specifically, a Python script executes SQL queries, retrieves the necessary data, and saves it to a temporary file.

[0275] Step 2:

[0276] The server analyzes the collected data using artificial intelligence technology and generates a three-dimensional model. It receives the data collected in step 1 as input and performs natural language processing and image analysis. The output is three-dimensional model data for constructing a virtual reality environment. Specifically, a machine learning model using TensorFlow extracts risk elements from the report, OpenCV analyzes photos and videos, and converts the data into a format compatible with Blender.

[0277] Step 3:

[0278] The server designs a virtual reality simulation using the generated 3D model. It uses the 3D model data obtained in step 2 as input to assemble the simulation logic for the scenario. The output is a simulation program that can be reproduced in a virtual reality environment. Specifically, a script written in C defines event sequences in Unity, enabling user interaction.

[0279] Step 4:

[0280] The terminal receives simulation data from the server and provides a virtual reality environment to the user through a VR headset. As input, it receives simulation program data from the server, and as output, it visually and auditorily presents a virtual scene where the user can immerse themselves. As a specific operation, a VR device such as the Oculus Rift executes a simulation program operating on Unity and updates the scene according to the user's movement.

[0281] Step 5:

[0282] The user operates the simulation within the virtual reality environment and executes their movements and selections. As input, it receives visual, auditory, and tactile feedback from the VR device, and as output, it simulates actions for danger avoidance. As a specific operation, the user uses a hand controller to make menu selections and movement operations and responds to simulation events.

[0283] Step 6:

[0284] The terminal records the user's actions during the simulation and sends them to the server. As input, it obtains the user's operation log and movement data from the sensor, and as output, it summarizes and sends the action data to the server. As a specific operation, a motion sensor monitors the user's position and posture and stores the data in a transmission buffer according to the communication protocol with the server.

[0285] Step 7:

[0286] The server analyzes the data of the user's actions and generates feedback. As input, it receives the user action data sent from the terminal in Step 6, and as output, it creates the content of the feedback to be provided to the user. As a specific operation, the server evaluates the user's actions using a machine learning algorithm and automatically summarizes the improvement points based on the results into text.

[0287] Step 8:

[0288] The server uses a generative AI model to create new prompts and prepare for the next simulation. It receives feedback and simulation evaluation results as input and generates prompts for a new simulation scenario as output. Specifically, the AI ​​model analyzes existing scenarios and user feedback data to generate detailed prompts for the next simulation.

[0289] (Application Example 1)

[0290] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0291] Traditional safety training in the workplace, such as lectures and simple simulations, faces the challenge of not adequately addressing real-world hazards. This results in insufficient development of employees' hazard awareness and ability to take appropriate immediate action, making it difficult to respond quickly when an actual accident occurs.

[0292] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0293] In this invention, the server includes means for collecting information based on past hazard cases and converting said information into a three-dimensional model, means for generating a virtual space simulation based on the three-dimensional model, and means for causing an operating entity to execute the virtual space simulation and monitoring the operating entity's activities. This makes it possible to reproduce specific hazard scenarios within industrial facilities in virtual reality, analyze the actions of the operating entity, and provide real-time feedback.

[0294] "Past dangerous incidents" refer to records of incidents that include information about accidents and disasters that have actually occurred.

[0295] "Information" refers to data such as reports, photographs, videos, and text related to hazardous incidents.

[0296] A "3D model" is a model reproduced in a three-dimensional virtual space constructed based on information.

[0297] A "virtual space simulation" is a simulation that recreates a virtual reality scenario that a user can experience, based on a three-dimensional model.

[0298] "Operating entity" refers to the user or participant experiencing the virtual space simulation.

[0299] "Monitoring activities" means observing and recording the actions of the controlling entity in real time.

[0300] "Providing a response" refers to the act of conveying appropriate guidance or information based on the actions of the manipulator.

[0301] A "specific hazard scenario within an industrial facility" is a scenario that reproduces specific hazardous situations that may occur within a factory or manufacturing facility in a virtual space.

[0302] "Analyzing behavior" is the process of analyzing the actions of the manipulator in detail and evaluating their effectiveness and appropriateness.

[0303] "Real-time feedback" refers to guidance and evaluation provided immediately in response to the actions of the user during a virtual space simulation.

[0304] The system used to realize this application generates virtual space simulations based on information about hazardous situations and allows users to experience them, thereby providing safety education.

[0305] The server first collects past dangerous cases, analyzes the information, and converts it into a three-dimensional solid model. For the analysis, artificial intelligence technology is used, specifically software such as TensorFlow. The solid model is constructed as a virtual space simulation in a development environment like Unity.

[0306] The terminal plays a role in providing these simulations to the operator. By the operator wearing smart glasses or a head-mounted display, it becomes possible to experience dangerous scenarios in the virtual space. Devices such as the Oculus Quest 2 are utilized.

[0307] When the user experiences the simulation, their activities are monitored in real-time, and the server receives the data. The received data is used to analyze the user's motion and behavior patterns. Based on the analysis results, immediate feedback is provided to the user, so that the effect of safety education can be enhanced even during the simulation.

[0308] For example, if the user experiences a dangerous situation that may occur in an industrial facility and takes inappropriate actions during the process, the system provides guidance to lead to appropriate actions. Through this feedback, the user can learn safe behaviors.

[0309] An example of the prompt text is something like "Propose a system that reproduces dangerous situations in a factory in VR, analyzes the actions of participants with AI, and provides feedback on how to improve safety education."

[0310] The flow of the specific process in Application Example 1 will be described using FIG. 12.

[0311] Step 1:

[0312] The server collects information about risky incidents. This information includes reports, images, videos, and text. The collected information is stored in a database as input.

[0313] Step 2:

[0314] The server analyzes the information stored in the database. Using generative AI models and artificial intelligence technology, the analysis converts the collected information into a three-dimensional model. This data processing results in the output of the 3D model.

[0315] Step 3:

[0316] The server designs a virtual space simulation based on the generated 3D model and builds the simulation environment in the Unity development environment. It uses the 3D model as input and generates the virtual environment as output.

[0317] Step 4:

[0318] The device provides a virtual space simulation to the user through a device such as the Oculus Quest 2. The device allows the user to access the virtual space and obtain a virtual experience through sight and sound.

[0319] Step 5:

[0320] Users participate in virtual reality simulations and experience dangerous situations. Action data from the user during the experience is collected and transmitted to a server.

[0321] Step 6:

[0322] The server analyzes the received operational data from the user. This data is evaluated using an AI algorithm, and feedback is generated regarding safety and appropriateness of the actions.

[0323] Step 7:

[0324] The server provides real-time feedback to the user based on the analysis results. It identifies areas for improvement through data processing and encourages specific actions.

[0325] Step 8:

[0326] The server saves the simulation results and updates the data using a generative AI model to further optimize the educational content. This process improves the quality of subsequent simulations.

[0327] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0328] The present invention combines an emotion engine with a system that provides effective occupational safety education through virtual reality simulations using past hazard data to achieve a more precise educational experience. The server first collects past near-miss and accident / injury cases and converts them into two-dimensional and three-dimensional data formats. Artificial intelligence technology is applied to the collected data to generate a three-dimensional model.

[0329] Next, the server designs a virtual reality simulation based on this three-dimensional model, allowing the user to experience danger in a safe and realistic environment. The terminal provides this simulation to the user through a VR headset and assists the user in initiating interaction within the simulation. The user acts in various scenarios within this virtual environment and learns safe operations.

[0330] A distinctive feature of this invention is the incorporation of an emotion engine into the system. The emotion engine recognizes the user's emotional state through facial and voice analysis. The server takes in both the user's emotional and behavioral data and performs a comprehensive analysis. Based on this analysis, it dynamically adjusts the virtual reality simulation scenario to create a situation in which the user can learn more effectively. Furthermore, by providing the user with feedback tailored to their individual emotional state, it provides comprehensive guidance that includes not only immediate reactions but also psychological aspects.

[0331] For example, in a data center fire scenario, when a user genuinely feels in danger, the emotion engine can sense this and adjust guidance and advice to provide a greater sense of security. This allows users to integrate their emotions and actions and learn to more effectively desensitize risk avoidance behaviors. In this way, the system of the present invention enhances the user's ability to manage their own safety in the workplace by simultaneously improving both their emotional and behavioral aspects.

[0332] The following describes the processing flow.

[0333] Step 1:

[0334] The server collects data on past near misses, accidents, and malfunctions. This includes reports, photos, video footage, and text information. The collected data is converted into a standardized format for analysis.

[0335] Step 2:

[0336] The server uses artificial intelligence technology to convert the collected data into a three-dimensional model. The AI ​​uses image recognition technology to convert 2D data into 3D information, preparing to recreate the details of the accident in three dimensions.

[0337] Step 3:

[0338] The server designs virtual reality simulation scenarios based on the generated three-dimensional models. This includes virtual environments to reproduce specific hazardous scenarios and the placement of dynamic elements that users can interact with.

[0339] Step 4:

[0340] The device allows the user to run a simulation through a VR headset. Through this experience in the virtual environment, the user is encouraged to perceive danger and take appropriate action.

[0341] Step 5:

[0342] When a user begins to act within virtual reality, the emotion engine analyzes the user's facial expressions and voice in real time to recognize the user's emotional state. This emotion data is sent to the server along with the behavioral data.

[0343] Step 6:

[0344] The server integrates emotional and behavioral data sent from the terminal to comprehensively analyze the user's risk avoidance behavior and emotional responses. Based on this analysis, it determines how to adjust the scenario and what kind of feedback to provide to the user.

[0345] Step 7:

[0346] The server provides feedback based on how the user felt and acted during the simulation. This feedback includes areas for improvement in the user's behavior and ways to manage emotions.

[0347] Step 8:

[0348] Users receive feedback, which they then use to improve their risk avoidance abilities in subsequent simulations, while also developing skills to control their own emotional responses.

[0349] (Example 2)

[0350] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0351] Traditional workplace safety education systems merely provide past hazardous incidents as information, failing to offer guidance tailored to the individual emotional states and behaviors of users. Furthermore, they lacked a dynamic learning environment that facilitated user behavioral improvement. Consequently, learning effectiveness was limited, and there were challenges in actually improving hazard avoidance abilities.

[0352] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0353] In this invention, the server includes means for collecting information based on past hazard cases and converting said information into a three-dimensional structure, means for generating a virtual reality environment based on said three-dimensional structure, and means for recognizing the user's emotional state and dynamically adjusting the virtual reality environment scenario based on said emotional state. This enables users to enjoy a learning experience tailored to their individual emotional state and improve their ability to avoid hazards more effectively.

[0354] "Means of information gathering" refers to the processes and techniques for collecting necessary information from documents and databases related to past incidents of danger.

[0355] "Means of converting into a three-dimensional structure" refers to methods and techniques for constructing collected information into a three-dimensional model that can be visually understood.

[0356] "Means for generating a virtual reality environment" refers to the processes and technologies for creating a simulated space that is reproduced on a computer based on a three-dimensional structure.

[0357] "Means of monitoring user responses" refer to devices and technologies used to track and record the actions users take within a virtual reality environment.

[0358] A "means of providing improvement information" refers to a system that uses user behavior data to convey appropriate feedback and advice to users.

[0359] "Means for recognizing a user's emotional state" refers to technologies that analyze a user's facial expressions and voice to determine their psychological state and emotions.

[0360] "Methods for dynamically adjusting scenarios" refer to technologies that change the scenario within virtual reality in real time according to the recognized emotional state of the user.

[0361] To implement this invention, the server first collects data on past hazardous incidents from safety reports and public accident databases. Based on this data, the server uses a common deep learning library, a machine learning framework, to convert it into two-dimensional and three-dimensional data formats. This allows the server to learn patterns and features in the collected data and build a visually reproducible model.

[0362] The server then designs a virtual reality simulation based on this generated three-dimensional model. This step utilizes virtual reality platforms such as Unity or Unreal Engine. The virtual reality environment is designed to be an intuitively interactive space for the user. Within this environment, the user can experience an immersive simulation through a VR headset or similar device. A concrete example is a scenario simulating a fire in a data center. In this scenario, the user is trained to identify and follow appropriate evacuation routes during a fire.

[0363] Furthermore, the server uses an emotion engine to analyze the user's facial expressions and voice to recognize their emotional state. Based on this recognition, it can dynamically adjust the virtual reality simulation scenario to provide the user with a personalized learning experience. For example, if the user is under high stress, the system will reduce the difficulty of the scenario and provide guidance that enhances their sense of security.

[0364] An example of a prompt is, "Create a scenario to learn safe behaviors while operating machinery in a factory." Based on this prompt, the generating AI model designs a specific simulation scenario and presents it in an actionable format. In this way, the system can provide users with effective safety education and effectively improve their ability to avoid hazards in the real world.

[0365] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0366] Step 1:

[0367] The server collects data on past hazard incidents. Industry-standard safety reports and historical accident databases are used as data input sources. This collected data is prepared for future analysis and model generation. The data includes not only text but also charts, graphs, and statistical information. The output is a structured dataset.

[0368] Step 2:

[0369] The server performs a two-dimensional to three-dimensional transformation using the collected data. The structured data obtained in Step 1 is used as input. The server utilizes a machine learning framework to analyze the data features and construct a three-dimensional model. Here, it finds correlations between data points and reorganizes them into a visualizeable form. The output is a dataset represented as a three-dimensional model.

[0370] Step 3:

[0371] The server constructs a virtual reality environment based on the generated 3D model. The 3D model obtained in step 2 is used as input. The server uses the virtual reality platform to design and provide interactive scenarios to the user. The program then redesigns the simulation based on this to reproduce specific hazardous situations. The output is the simulation environment experienced by the user.

[0372] Step 4:

[0373] The terminal provides the user with a virtual reality environment using a VR headset. The input is the simulation environment designed in step 3. The user puts on the VR device and begins acting in a virtual scenario that closely resembles reality. The terminal tracks the user's actions and movements and collects the results of the interaction. The output is user behavior data.

[0374] Step 5:

[0375] The server recognizes the user's emotional state and adjusts the virtual environment accordingly. It obtains input for analyzing the emotional state, along with user behavior data from the terminal. The server uses an emotion analysis algorithm to determine the user's stress level and interests, using these as indicators to adjust the virtual scenario. The program dynamically changes the simulation difficulty and scenario. The output is the adjusted learning environment.

[0376] Step 6:

[0377] The server provides feedback to the user. The input is the user's behavioral data and sentiment analysis results collected in step 4. Based on this, the server creates advice and feedback for improvement and communicates it to the user. This gives the user an opportunity to review their own behavior and learn effectively. The output is feedback provided to the user in text or audio format.

[0378] (Application Example 2)

[0379] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0380] Traditional occupational safety education systems use general virtual reality simulations to train and improve user behavior. However, they have the drawback of providing uniform instruction without considering the emotional state of individual users, making it difficult to deliver effective education tailored to the specific psychological state of each user. Furthermore, the lack of real-time scenario adjustments reduces the efficiency of training, making it difficult to improve actual hazard avoidance abilities.

[0381] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0382] In this invention, the server includes means for collecting data based on past hazard cases and converting said data into a three-dimensional model, means for generating a virtual reality simulation based on the three-dimensional model, means for analyzing the emotional state of the user running the virtual reality simulation, means for dynamically adjusting the scenario based on said emotional state, means for monitoring and comprehensively analyzing the user's behavior, and means for providing feedback. This makes it possible to provide effective and individualized occupational safety education to each user that takes their emotional state into account, and to promote the acquisition of hazard avoidance behaviors in an environment close to reality.

[0383] "Past hazardous incidents" refer to detailed records of accidents and near misses that have occurred in the past, and are data used to understand and avoid hazards in the workplace.

[0384] A "three-dimensional model" refers to a digital representation that reproduces real-world objects and situations in three dimensions, and is used for simulations in virtual spaces.

[0385] "Virtual reality simulation" refers to a technology in which users interact with a computer-generated virtual environment, and is used to simulate real-world situations.

[0386] "Emotional state" refers to the subjective psychological experience a user feels during an experience, and is inferred from data such as facial expressions and voice.

[0387] "Dynamic adjustment" refers to a process of making changes in real time, meaning the system adapts based on user feedback to provide the optimal scenario.

[0388] "Monitoring" refers to the process of continuously observing and collecting data on user behavior and reactions.

[0389] "Feedback" refers to evaluation and guidance information provided to improve the user's learning efficiency, and is information that helps improve during the training process.

[0390] To implement this invention, the server first collects data on past hazardous incidents. This involves a process of collecting detailed data on near misses and accidents in the actual work environment using input devices such as cameras and sensors. The collected data is converted from a two-dimensional format to a three-dimensional format, and a more realistic model is created using three-dimensional modeling software such as Unity.

[0391] Next, the server uses artificial intelligence technology to analyze a three-dimensional model and generate a virtual reality simulation. This process utilizes machine learning frameworks such as TensorFlow to construct various scenarios that the user will experience. Within the simulation, the user immerses themselves in the virtual environment through a VR headset, safely learning about real-world dangerous situations.

[0392] Furthermore, to analyze the user's emotional state in real time, the server uses OpenCV to read facial expressions and infers the emotional state from the user's voice data. Based on this, the emotion engine dynamically adjusts the virtual reality scenario. If the user is in a high-stress state, the difficulty of the scenario is reduced or appropriate advice is provided; conversely, if the user is focused, training is performed in more complex situations.

[0393] A concrete example is an emergency situation in a factory environment where an oil leak causes a fire. If the user panics in this scenario, the emotional engine will sense this and immediately provide reassuring guidance. This practice allows the user to calmly learn how to respond.

[0394] An example of a prompt message might be, "In the event of a fire in the factory, analyze the operators' emotional responses and adaptive behaviors, and develop an appropriate scenario." This instructs the generative AI model on how to adjust the scenario in real time.

[0395] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0396] Step 1:

[0397] The server collects data on past hazardous incidents. Specifically, it acquires two-dimensional data as input from devices such as cameras and sensors, and stores this information in a database. The collected data is used as foundational data for conversion into a three-dimensional model in the next step.

[0398] Step 2:

[0399] The server converts the collected two-dimensional data into a three-dimensional model. This conversion uses three-dimensional modeling software such as Unity, and the output is a three-dimensional model. The data is processed into a model with depth and three-dimensional structure. This creates a realistic environment that can be actually manipulated in a virtual reality simulation.

[0400] Step 3:

[0401] The server designs and builds virtual reality simulations based on the generated 3D models. The output is a virtual environment with various scenarios. Using a generation AI model, various conditions in each scenario are controlled, and realism is enhanced by including random elements. In this process, prompt statements are used as input to generate scenarios based on specific conditions.

[0402] Step 4:

[0403] The user enters the simulation using a VR headset. The user's experience begins, and they interact within the scenario, learning how to operate the system and take actions to avoid danger. The user's actions within VR are recorded as behavioral data for analysis in the next step.

[0404] Step 5:

[0405] The server analyzes user behavior data, facial expressions, and voice data obtained through VR simulation. The input data is analyzed in real time using AI technology (TensorFlow) to infer the user's emotional state. This process outputs numerical data representing the user's psychological state, such as stress levels and concentration levels.

[0406] Step 6:

[0407] The server dynamically adjusts the simulation scenario based on the user's emotional state. The input to this process is the quantified emotional data from the previous step; the server adjusts the output by easing the scenario when emotions are heightened and increasing the difficulty when emotions are calm. This provides a learning experience optimized for each individual user.

[0408] Step 7:

[0409] The server generates and provides feedback to the user based on the final analysis of user behavior and emotions. It analyzes user performance and areas for improvement from the input data, providing specific and effective guidance as output. The feedback includes points to focus on in the next training session and guidelines for further learning.

[0410] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0411] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet Search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0412] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart glasses 214.

[0413] [Third Embodiment]

[0414] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0415] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0416] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0417] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0418] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0419] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0420] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0421] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0422] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0423] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0424] In the headset terminal 314, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0425] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the headset terminal 314 will be referred to as the "terminal".

[0426] The system of this invention combines virtual reality technology and artificial intelligence technology to enable effective occupational safety education by utilizing data from past hazardous incidents. The server first collects data on past near misses and accident / injury cases that form the basis of safety education. This data includes reports, photographs, video footage, and text information related to the cases.

[0427] Next, the server analyzes the collected data and converts it into a three-dimensional model using artificial intelligence technology. This makes it possible to construct a virtual space that realistically reproduces the actual environment in three dimensions. This three-dimensional model will serve as the foundation for future simulations.

[0428] The server then designs a virtual reality simulation based on this three-dimensional model, recreating specific hazardous scenarios. The terminal then provides this virtual reality simulation to the user through a VR headset. The user can experience real-time interaction based on their own movements within the VR environment. For example, a simulation recreating a data center fire scenario could be considered. The user would experience the entire process from the outbreak of the fire to evacuation, learning appropriate actions.

[0429] The user's actions during the simulation are transmitted to the server via the terminal. The server monitors this action data and analyzes it using artificial intelligence. Specifically, it evaluates how the user attempted to avoid danger, including the speed and sequence of their actions. Based on this evaluation, the server provides feedback to the user, which is then used to improve future simulations and educational content.

[0430] In this way, the system of the present invention enables users to improve their risk awareness and acquire reflexive risk avoidance actions through practical training in a virtual environment.

[0431] The following describes the processing flow.

[0432] Step 1:

[0433] The server collects data from a database of past near misses and accident / injury incidents necessary for safety training. This data exists in various formats, such as reports, photos, video footage, and text information, and the server converts it into a unified format.

[0434] Step 2:

[0435] The server analyzes the collected data and uses artificial intelligence technologies such as image recognition and natural language processing to convert the data into a three-dimensional model. The AI ​​understands the details of the accident from the text and identifies the environment and circumstances from the image data.

[0436] Step 3:

[0437] The server designs virtual reality simulation scenarios based on the generated 3D models. Here, specific hazardous scenarios are reproduced, and interaction and environmental elements are configured to ensure that users can have a realistic virtual experience.

[0438] Step 4:

[0439] The device confirms that the simulation is ready and prompts the user to put on the VR headset. Once the device confirms the user is ready, it starts the virtual reality simulation, and the user begins their experience in the virtual environment.

[0440] Step 5:

[0441] Users are prompted to perform real-world actions within the virtual reality environment, detect danger, and react appropriately. In this process, users are required to make decisions and take actions according to instructions within the virtual environment.

[0442] Step 6:

[0443] The device tracks the user's actions in real time during the simulation and sends that data to the server. This data includes detailed information such as the user's eye movements, speed, and direction of actions.

[0444] Step 7:

[0445] The server analyzes the behavioral data sent from the terminal and runs an algorithm to evaluate how effective the user's actions were in avoiding danger.

[0446] Step 8:

[0447] The server provides users with specific feedback based on the evaluation results. This feedback includes details about effective actions and areas that need improvement. Users can use this information to guide their responses in the next simulation.

[0448] (Example 1)

[0449] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0450] Traditional occupational safety training often focused solely on theoretical knowledge acquisition without providing participants with the opportunity to experience actual hazards. Furthermore, the training content was often uniform, failing to provide appropriate feedback tailored to each user's level of hazard awareness and avoidance behavior. Additionally, introducing new simulations presented significant challenges due to the considerable effort required.

[0451] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0452] In this invention, the server includes means for collecting information based on past hazard cases and structuring said information into a three-dimensional model using artificial intelligence technology; means for designing a virtual reality environment based on said three-dimensional model and generating specific hazard scenarios; and means for creating new prompt sentences using the generated AI model and preparing further simulation scenarios. This enables feedback based on individual user behavior and practical hazard awareness education.

[0453] "Past hazardous incidents" refers to specific information or events related to past near misses, accidents, or injuries in the work environment.

[0454] "Information gathering" refers to the act of extracting and collecting useful data from databases or other sources according to a specific purpose.

[0455] "Artificial intelligence technology" refers to technologies such as machine learning and data analysis in which computers mimic human intelligence and perform the necessary analyses to solve specific problems.

[0456] "Structuring into a three-dimensional model" refers to representing collected data in a three-dimensional virtual format and visually embodying it.

[0457] A "virtual reality environment" refers to a simulated three-dimensional space created using computer technology that users can experience.

[0458] A "specific danger scenario" refers to a concrete dangerous situation or case that is reproduced within the virtual reality environment, with the aim of allowing users to learn by dealing with it.

[0459] A "generative AI model" refers to a pre-trained artificial intelligence program used to generate new prompts or ideas from given data.

[0460] A "prompt message" refers to a document or phrase used as input to a generative AI model to obtain a specific output.

[0461] "Feedback" refers to providing evaluations and suggestions regarding user actions and results, and offering information for improvement.

[0462] This invention is a workplace safety education system that combines virtual reality and artificial intelligence technology. Its main components include a server, terminals, and users working together.

[0463] The server collects data on past risk incidents from an external database. Specifically, it uses Python and SQL to extract information such as reports, photos, and video footage. The collected data is then analyzed using artificial intelligence technology, extracting important information using TensorFlow and OpenCV, and generating a three-dimensional model. This model is then converted into a virtual reality environment using 3D modeling software (e.g., Blender, Unity).

[0464] The server then designs specific hazardous scenarios in the virtual reality environment based on the generated 3D model. The designed simulations are programmed using C or JavaScript, enabling the time progression of events and user interaction within the virtual space.

[0465] The terminal provides the user with simulation data transmitted from the server via a VR headset. Using a head-mounted display such as the Oculus Rift, the user can visually experience a virtual reality environment. The user can record their movements and actions within this environment in real time. A concrete example of a user experience is experiencing an evacuation scenario during a fire.

[0466] User actions are transmitted from the device to the server, where the server analyzes the data. Using machine learning algorithms, the server analyzes user behavior data to evaluate each user's risk avoidance ability and behavioral patterns. Based on the evaluated data, the server provides the user with feedback on areas for improvement.

[0467] Furthermore, it includes a function to create new prompts using a generative AI model, preparing a wider variety of simulation scenarios. For example, it is possible to input a prompt such as "Design a simulation of a safe evacuation scenario in the event of a fire in a data center" into the AI ​​model and generate a new scenario. This provides users with a simulation experience tailored to their needs and can continuously raise their safety awareness.

[0468] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0469] Step 1:

[0470] The server collects past incident data from an external database. It accepts database queries and API access as input, and outputs reports, photos, video footage, and related text data. Specifically, a Python script executes SQL queries, retrieves the necessary data, and saves it to a temporary file.

[0471] Step 2:

[0472] The server analyzes the collected data using artificial intelligence technology and generates a three-dimensional model. It receives the data collected in step 1 as input and performs natural language processing and image analysis. The output is three-dimensional model data for constructing a virtual reality environment. Specifically, a machine learning model using TensorFlow extracts risk elements from the report, OpenCV analyzes photos and videos, and converts the data into a format compatible with Blender.

[0473] Step 3:

[0474] The server designs a virtual reality simulation using the generated 3D model. It uses the 3D model data obtained in step 2 as input to assemble the simulation logic for the scenario. The output is a simulation program that can be reproduced in a virtual reality environment. Specifically, a script written in C defines event sequences in Unity, enabling user interaction.

[0475] Step 4:

[0476] The terminal receives simulation data from the server and provides the user with a virtual reality environment through a VR headset. It receives simulation program data from the server as input and presents an immersive virtual scene to the user visually and aurally as output. Specifically, VR equipment such as the Oculus Rift executes a simulation program running on Unity, updating the scene according to the user's movements.

[0477] Step 5:

[0478] Users interact with a simulation within a virtual reality environment, executing their own movements and choices. They receive visual, auditory, and haptic feedback from VR equipment as input, and simulate actions to avoid danger as output. Specifically, users use hand controllers to select menus, move, and respond to simulation events.

[0479] Step 6:

[0480] The terminal records the user's actions during simulation and sends them to the server. It takes user operation logs and motion data from sensors as input, and sends the combined action data to the server as output. Specifically, motion sensors monitor the user's position and posture, and store the data in a transmission buffer according to the communication protocol with the server.

[0481] Step 7:

[0482] The server analyzes user behavior data and generates feedback. It receives user behavior data sent from the terminal in step 6 as input and generates feedback content to provide to the user as output. Specifically, the server uses a machine learning algorithm to evaluate user behavior and automatically summarizes areas for improvement based on the results into text.

[0483] Step 8:

[0484] The server uses a generative AI model to create new prompts and prepare for the next simulation. It receives feedback and simulation evaluation results as input and generates prompts for a new simulation scenario as output. Specifically, the AI ​​model analyzes existing scenarios and user feedback data to generate detailed prompts for the next simulation.

[0485] (Application Example 1)

[0486] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0487] Traditional safety training in the workplace, such as lectures and simple simulations, faces the challenge of not adequately addressing real-world hazards. This results in insufficient development of employees' hazard awareness and ability to take appropriate immediate action, making it difficult to respond quickly when an actual accident occurs.

[0488] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0489] In this invention, the server includes means for collecting information based on past hazard cases and converting said information into a three-dimensional model, means for generating a virtual space simulation based on the three-dimensional model, and means for causing an operating entity to execute the virtual space simulation and monitoring the operating entity's activities. This makes it possible to reproduce specific hazard scenarios within industrial facilities in virtual reality, analyze the actions of the operating entity, and provide real-time feedback.

[0490] "Past dangerous incidents" refer to records of incidents that include information about accidents and disasters that have actually occurred.

[0491] "Information" refers to data such as reports, photographs, videos, and text related to hazardous incidents.

[0492] A "3D model" is a model reproduced in a three-dimensional virtual space constructed based on information.

[0493] A "virtual space simulation" is a simulation that recreates a virtual reality scenario that a user can experience, based on a three-dimensional model.

[0494] "Operating entity" refers to the user or participant experiencing the virtual space simulation.

[0495] "Monitoring activities" means observing and recording the actions of the controlling entity in real time.

[0496] "Providing a response" refers to the act of conveying appropriate guidance or information based on the actions of the manipulator.

[0497] A "specific hazard scenario within an industrial facility" is a scenario that reproduces specific hazardous situations that may occur within a factory or manufacturing facility in a virtual space.

[0498] "Analyzing behavior" is the process of analyzing the actions of the manipulator in detail and evaluating their effectiveness and appropriateness.

[0499] "Real-time feedback" refers to guidance and evaluation provided immediately in response to the actions of the user during a virtual space simulation.

[0500] The system used to realize this application generates virtual space simulations based on information about hazardous situations and allows users to experience them, thereby providing safety education.

[0501] The server first collects past incidents of risk, analyzes this information, and converts it into a three-dimensional model. Artificial intelligence technology is used for the analysis, specifically software such as TensorFlow. The 3D model is then constructed as a virtual space simulation in a development environment like Unity.

[0502] The terminal plays the role of providing these simulations to the user. By wearing smart glasses or a head-mounted display, the user can experience dangerous scenarios in a virtual space. Devices such as the Oculus Quest 2 are being utilized.

[0503] When a user experiences a simulation, their activities are monitored in real time, and the server receives the data. This data is used to analyze the user's movements and behavioral patterns. Based on the analysis results, users are immediately provided with feedback, thus enhancing the effectiveness of safety education even during the simulation.

[0504] For example, if a user experiences a potentially dangerous situation in an industrial facility and takes inappropriate actions during that process, the system provides guidance to lead them to appropriate behavior. This feedback allows the user to learn safer behaviors.

[0505] An example of a prompt might be: "Propose a system that uses VR to recreate dangerous situations in a factory, analyzes participants' behavior with AI, and provides feedback on how to improve safety education."

[0506] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0507] Step 1:

[0508] The server collects information about risky incidents. This information includes reports, images, videos, and text. The collected information is stored in a database as input.

[0509] Step 2:

[0510] The server analyzes the information stored in the database. Using generative AI models and artificial intelligence technology, the analysis converts the collected information into a three-dimensional model. This data processing results in the output of the 3D model.

[0511] Step 3:

[0512] The server designs a virtual space simulation based on the generated 3D model and builds the simulation environment in the Unity development environment. It uses the 3D model as input and generates the virtual environment as output.

[0513] Step 4:

[0514] The device provides a virtual space simulation to the user through a device such as the Oculus Quest 2. The device allows the user to access the virtual space and obtain a virtual experience through sight and sound.

[0515] Step 5:

[0516] Users participate in virtual reality simulations and experience dangerous situations. Action data from the user during the experience is collected and transmitted to a server.

[0517] Step 6:

[0518] The server analyzes the received operational data from the user. This data is evaluated using an AI algorithm, and feedback is generated regarding safety and appropriateness of the actions.

[0519] Step 7:

[0520] The server provides real-time feedback to the user based on the analysis results. It identifies areas for improvement through data processing and encourages specific actions.

[0521] Step 8:

[0522] The server saves the simulation results and updates the data using a generative AI model to further optimize the educational content. This process improves the quality of subsequent simulations.

[0523] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0524] The present invention combines an emotion engine with a system that provides effective occupational safety education through virtual reality simulations using past hazard data to achieve a more precise educational experience. The server first collects past near-miss and accident / injury cases and converts them into two-dimensional and three-dimensional data formats. Artificial intelligence technology is applied to the collected data to generate a three-dimensional model.

[0525] Next, the server designs a virtual reality simulation based on this three-dimensional model, allowing the user to experience danger in a safe and realistic environment. The terminal provides this simulation to the user through a VR headset and assists the user in initiating interaction within the simulation. The user acts in various scenarios within this virtual environment and learns safe operations.

[0526] A distinctive feature of this invention is the incorporation of an emotion engine into the system. The emotion engine recognizes the user's emotional state through facial and voice analysis. The server takes in both the user's emotional and behavioral data and performs a comprehensive analysis. Based on this analysis, it dynamically adjusts the virtual reality simulation scenario to create a situation in which the user can learn more effectively. Furthermore, by providing the user with feedback tailored to their individual emotional state, it provides comprehensive guidance that includes not only immediate reactions but also psychological aspects.

[0527] For example, in a data center fire scenario, when a user genuinely feels in danger, the emotion engine can sense this and adjust guidance and advice to provide a greater sense of security. This allows users to integrate their emotions and actions and learn to more effectively desensitize risk avoidance behaviors. In this way, the system of the present invention enhances the user's ability to manage their own safety in the workplace by simultaneously improving both their emotional and behavioral aspects.

[0528] The following describes the processing flow.

[0529] Step 1:

[0530] The server collects data on past near misses, accidents, and malfunctions. This includes reports, photos, video footage, and text information. The collected data is converted into a standardized format for analysis.

[0531] Step 2:

[0532] The server uses artificial intelligence technology to convert the collected data into a three-dimensional model. The AI ​​uses image recognition technology to convert 2D data into 3D information, preparing to recreate the details of the accident in three dimensions.

[0533] Step 3:

[0534] The server designs virtual reality simulation scenarios based on the generated three-dimensional models. This includes virtual environments to reproduce specific hazardous scenarios and the placement of dynamic elements that users can interact with.

[0535] Step 4:

[0536] The device allows the user to run a simulation through a VR headset. Through this experience in the virtual environment, the user is encouraged to perceive danger and take appropriate action.

[0537] Step 5:

[0538] When a user begins to act within virtual reality, the emotion engine analyzes the user's facial expressions and voice in real time to recognize the user's emotional state. This emotion data is sent to the server along with the behavioral data.

[0539] Step 6:

[0540] The server integrates emotional and behavioral data sent from the terminal to comprehensively analyze the user's risk avoidance behavior and emotional responses. Based on this analysis, it determines how to adjust the scenario and what kind of feedback to provide to the user.

[0541] Step 7:

[0542] The server provides feedback based on how the user felt and acted during the simulation. This feedback includes areas for improvement in the user's behavior and ways to manage emotions.

[0543] Step 8:

[0544] Users receive feedback, which they then use to improve their risk avoidance abilities in subsequent simulations, while also developing skills to control their own emotional responses.

[0545] (Example 2)

[0546] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0547] Traditional workplace safety education systems merely provide past hazardous incidents as information, failing to offer guidance tailored to the individual emotional states and behaviors of users. Furthermore, they lacked a dynamic learning environment that facilitated user behavioral improvement. Consequently, learning effectiveness was limited, and there were challenges in actually improving hazard avoidance abilities.

[0548] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0549] In this invention, the server includes means for collecting information based on past hazard cases and converting said information into a three-dimensional structure, means for generating a virtual reality environment based on said three-dimensional structure, and means for recognizing the user's emotional state and dynamically adjusting the virtual reality environment scenario based on said emotional state. This enables users to enjoy a learning experience tailored to their individual emotional state and improve their ability to avoid hazards more effectively.

[0550] "Means of information gathering" refers to the processes and techniques for collecting necessary information from documents and databases related to past incidents of danger.

[0551] "Means of converting into a three-dimensional structure" refers to methods and techniques for constructing collected information into a three-dimensional model that can be visually understood.

[0552] "Means for generating a virtual reality environment" refers to the processes and technologies for creating a simulated space that is reproduced on a computer based on a three-dimensional structure.

[0553] "Means of monitoring user responses" refer to devices and technologies used to track and record the actions users take within a virtual reality environment.

[0554] A "means of providing improvement information" refers to a system that uses user behavior data to convey appropriate feedback and advice to users.

[0555] "Means for recognizing a user's emotional state" refers to technologies that analyze a user's facial expressions and voice to determine their psychological state and emotions.

[0556] "Methods for dynamically adjusting scenarios" refer to technologies that change the scenario within virtual reality in real time according to the recognized emotional state of the user.

[0557] To implement this invention, the server first collects data on past hazardous incidents from safety reports and public accident databases. Based on this data, the server uses a common deep learning library, a machine learning framework, to convert it into two-dimensional and three-dimensional data formats. This allows the server to learn patterns and features in the collected data and build a visually reproducible model.

[0558] The server then designs a virtual reality simulation based on this generated three-dimensional model. This step utilizes virtual reality platforms such as Unity or Unreal Engine. The virtual reality environment is designed to be an intuitively interactive space for the user. Within this environment, the user can experience an immersive simulation through a VR headset or similar device. A concrete example is a scenario simulating a fire in a data center. In this scenario, the user is trained to identify and follow appropriate evacuation routes during a fire.

[0559] Furthermore, the server uses an emotion engine to analyze the user's facial expressions and voice to recognize their emotional state. Based on this recognition, it can dynamically adjust the virtual reality simulation scenario to provide the user with a personalized learning experience. For example, if the user is under high stress, the system will reduce the difficulty of the scenario and provide guidance that enhances their sense of security.

[0560] An example of a prompt is, "Create a scenario to learn safe behaviors while operating machinery in a factory." Based on this prompt, the generating AI model designs a specific simulation scenario and presents it in an actionable format. In this way, the system can provide users with effective safety education and effectively improve their ability to avoid hazards in the real world.

[0561] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0562] Step 1:

[0563] The server collects data on past hazard incidents. Industry-standard safety reports and historical accident databases are used as data input sources. This collected data is prepared for future analysis and model generation. The data includes not only text but also charts, graphs, and statistical information. The output is a structured dataset.

[0564] Step 2:

[0565] The server performs a two-dimensional to three-dimensional transformation using the collected data. The structured data obtained in Step 1 is used as input. The server utilizes a machine learning framework to analyze the data features and construct a three-dimensional model. Here, it finds correlations between data points and reorganizes them into a visualizeable form. The output is a dataset represented as a three-dimensional model.

[0566] Step 3:

[0567] The server constructs a virtual reality environment based on the generated 3D model. The 3D model obtained in step 2 is used as input. The server uses the virtual reality platform to design and provide interactive scenarios to the user. The program then redesigns the simulation based on this to reproduce specific hazardous situations. The output is the simulation environment experienced by the user.

[0568] Step 4:

[0569] The terminal provides the user with a virtual reality environment using a VR headset. The input is the simulation environment designed in step 3. The user puts on the VR device and begins acting in a virtual scenario that closely resembles reality. The terminal tracks the user's actions and movements and collects the results of the interaction. The output is user behavior data.

[0570] Step 5:

[0571] The server recognizes the user's emotional state and adjusts the virtual environment accordingly. It obtains input for analyzing the emotional state, along with user behavior data from the terminal. The server uses an emotion analysis algorithm to determine the user's stress level and interests, using these as indicators to adjust the virtual scenario. The program dynamically changes the simulation difficulty and scenario. The output is the adjusted learning environment.

[0572] Step 6:

[0573] The server provides feedback to the user. The input is the user's behavioral data and sentiment analysis results collected in step 4. Based on this, the server creates advice and feedback for improvement and communicates it to the user. This gives the user an opportunity to review their own behavior and learn effectively. The output is feedback provided to the user in text or audio format.

[0574] (Application Example 2)

[0575] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0576] Traditional occupational safety education systems use general virtual reality simulations to train and improve user behavior. However, they have the drawback of providing uniform instruction without considering the emotional state of individual users, making it difficult to deliver effective education tailored to the specific psychological state of each user. Furthermore, the lack of real-time scenario adjustments reduces the efficiency of training, making it difficult to improve actual hazard avoidance abilities.

[0577] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0578] In this invention, the server includes means for collecting data based on past hazard cases and converting said data into a three-dimensional model, means for generating a virtual reality simulation based on the three-dimensional model, means for analyzing the emotional state of the user running the virtual reality simulation, means for dynamically adjusting the scenario based on said emotional state, means for monitoring and comprehensively analyzing the user's behavior, and means for providing feedback. This makes it possible to provide effective and individualized occupational safety education to each user that takes their emotional state into account, and to promote the acquisition of hazard avoidance behaviors in an environment close to reality.

[0579] "Past hazardous incidents" refer to detailed records of accidents and near misses that have occurred in the past, and are data used to understand and avoid hazards in the workplace.

[0580] A "three-dimensional model" refers to a digital representation that reproduces real-world objects and situations in three dimensions, and is used for simulations in virtual spaces.

[0581] "Virtual reality simulation" refers to a technology in which users interact with a computer-generated virtual environment, and is used to simulate real-world situations.

[0582] "Emotional state" refers to the subjective psychological experience a user feels during an experience, and is inferred from data such as facial expressions and voice.

[0583] "Dynamic adjustment" refers to a process of making changes in real time, meaning the system adapts based on user feedback to provide the optimal scenario.

[0584] "Monitoring" refers to the process of continuously observing and collecting data on user behavior and reactions.

[0585] "Feedback" refers to evaluation and guidance information provided to improve the user's learning efficiency, and is information that helps improve during the training process.

[0586] To implement this invention, the server first collects data on past hazardous incidents. This involves a process of collecting detailed data on near misses and accidents in the actual work environment using input devices such as cameras and sensors. The collected data is converted from a two-dimensional format to a three-dimensional format, and a more realistic model is created using three-dimensional modeling software such as Unity.

[0587] Next, the server uses artificial intelligence technology to analyze a three-dimensional model and generate a virtual reality simulation. This process utilizes machine learning frameworks such as TensorFlow to construct various scenarios that the user will experience. Within the simulation, the user immerses themselves in the virtual environment through a VR headset, safely learning about real-world dangerous situations.

[0588] Furthermore, to analyze the user's emotional state in real time, the server uses OpenCV to read facial expressions and infers the emotional state from the user's voice data. Based on this, the emotion engine dynamically adjusts the virtual reality scenario. If the user is in a high-stress state, the difficulty of the scenario is reduced or appropriate advice is provided; conversely, if the user is focused, training is performed in more complex situations.

[0589] A concrete example is an emergency situation in a factory environment where an oil leak causes a fire. If the user panics in this scenario, the emotional engine will sense this and immediately provide reassuring guidance. This practice allows the user to calmly learn how to respond.

[0590] An example of a prompt message might be, "In the event of a fire in the factory, analyze the operators' emotional responses and adaptive behaviors, and develop an appropriate scenario." This instructs the generative AI model on how to adjust the scenario in real time.

[0591] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0592] Step 1:

[0593] The server collects data on past hazardous incidents. Specifically, it acquires two-dimensional data as input from devices such as cameras and sensors, and stores this information in a database. The collected data is used as foundational data for conversion into a three-dimensional model in the next step.

[0594] Step 2:

[0595] The server converts the collected two-dimensional data into a three-dimensional model. This conversion uses three-dimensional modeling software such as Unity, and the output is a three-dimensional model. The data is processed into a model with depth and three-dimensional structure. This creates a realistic environment that can be actually manipulated in a virtual reality simulation.

[0596] Step 3:

[0597] The server designs and builds virtual reality simulations based on the generated 3D models. The output is a virtual environment with various scenarios. Using a generation AI model, various conditions in each scenario are controlled, and realism is enhanced by including random elements. In this process, prompt statements are used as input to generate scenarios based on specific conditions.

[0598] Step 4:

[0599] The user enters the simulation using a VR headset. The user's experience begins, and they interact within the scenario, learning how to operate the system and take actions to avoid danger. The user's actions within VR are recorded as behavioral data for analysis in the next step.

[0600] Step 5:

[0601] The server analyzes user behavior data, facial expressions, and voice data obtained through VR simulation. The input data is analyzed in real time using AI technology (TensorFlow) to infer the user's emotional state. This process outputs numerical data representing the user's psychological state, such as stress levels and concentration levels.

[0602] Step 6:

[0603] The server dynamically adjusts the simulation scenario based on the user's emotional state. The input to this process is the quantified emotional data from the previous step; the server adjusts the output by easing the scenario when emotions are heightened and increasing the difficulty when emotions are calm. This provides a learning experience optimized for each individual user.

[0604] Step 7:

[0605] The server generates and provides feedback to the user based on the final analysis of user behavior and emotions. It analyzes user performance and areas for improvement from the input data, providing specific and effective guidance as output. The feedback includes points to focus on in the next training session and guidelines for further learning.

[0606] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0607] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet Search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0608] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and specific processing may also be performed by the headset terminal 314.

[0609] [Fourth Embodiment]

[0610] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0611] As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0612] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0613] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0614] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0615] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0616] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0617] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. Furthermore, the robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0618] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0619] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0620] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0621] In robot 414, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0622] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0623] The system of this invention combines virtual reality technology and artificial intelligence technology to enable effective occupational safety education by utilizing data from past hazardous incidents. The server first collects data on past near misses and accident / injury cases that form the basis of safety education. This data includes reports, photographs, video footage, and text information related to the cases.

[0624] Next, the server analyzes the collected data and converts it into a three-dimensional model using artificial intelligence technology. This makes it possible to construct a virtual space that realistically reproduces the actual environment in three dimensions. This three-dimensional model will serve as the foundation for future simulations.

[0625] The server then designs a virtual reality simulation based on this three-dimensional model, recreating specific hazardous scenarios. The terminal then provides this virtual reality simulation to the user through a VR headset. The user can experience real-time interaction based on their own movements within the VR environment. For example, a simulation recreating a data center fire scenario could be considered. The user would experience the entire process from the outbreak of the fire to evacuation, learning appropriate actions.

[0626] The user's actions during the simulation are transmitted to the server via the terminal. The server monitors this action data and analyzes it using artificial intelligence. Specifically, it evaluates how the user attempted to avoid danger, including the speed and sequence of their actions. Based on this evaluation, the server provides feedback to the user, which is then used to improve future simulations and educational content.

[0627] In this way, the system of the present invention enables users to improve their risk awareness and acquire reflexive risk avoidance actions through practical training in a virtual environment.

[0628] The following describes the processing flow.

[0629] Step 1:

[0630] The server collects data from a database of past near misses and accident / injury incidents necessary for safety training. This data exists in various formats, such as reports, photos, video footage, and text information, and the server converts it into a unified format.

[0631] Step 2:

[0632] The server analyzes the collected data and uses artificial intelligence technologies such as image recognition and natural language processing to convert the data into a three-dimensional model. The AI ​​understands the details of the accident from the text and identifies the environment and circumstances from the image data.

[0633] Step 3:

[0634] The server designs virtual reality simulation scenarios based on the generated 3D models. Here, specific hazardous scenarios are reproduced, and interaction and environmental elements are configured to ensure that users can have a realistic virtual experience.

[0635] Step 4:

[0636] The device confirms that the simulation is ready and prompts the user to put on the VR headset. Once the device confirms the user is ready, it starts the virtual reality simulation, and the user begins their experience in the virtual environment.

[0637] Step 5:

[0638] Users are prompted to perform real-world actions within the virtual reality environment, detect danger, and react appropriately. In this process, users are required to make decisions and take actions according to instructions within the virtual environment.

[0639] Step 6:

[0640] The device tracks the user's actions in real time during the simulation and sends that data to the server. This data includes detailed information such as the user's eye movements, speed, and direction of actions.

[0641] Step 7:

[0642] The server analyzes the behavioral data sent from the terminal and runs an algorithm to evaluate how effective the user's actions were in avoiding danger.

[0643] Step 8:

[0644] The server provides users with specific feedback based on the evaluation results. This feedback includes details about effective actions and areas that need improvement. Users can use this information to guide their responses in the next simulation.

[0645] (Example 1)

[0646] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0647] Traditional occupational safety training often focused solely on theoretical knowledge acquisition without providing participants with the opportunity to experience actual hazards. Furthermore, the training content was often uniform, failing to provide appropriate feedback tailored to each user's level of hazard awareness and avoidance behavior. Additionally, introducing new simulations presented significant challenges due to the considerable effort required.

[0648] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0649] In this invention, the server includes means for collecting information based on past hazard cases and structuring said information into a three-dimensional model using artificial intelligence technology; means for designing a virtual reality environment based on said three-dimensional model and generating specific hazard scenarios; and means for creating new prompt sentences using the generated AI model and preparing further simulation scenarios. This enables feedback based on individual user behavior and practical hazard awareness education.

[0650] "Past hazardous incidents" refers to specific information or events related to past near misses, accidents, or injuries in the work environment.

[0651] "Information gathering" refers to the act of extracting and collecting useful data from databases or other sources according to a specific purpose.

[0652] "Artificial intelligence technology" refers to technologies such as machine learning and data analysis in which computers mimic human intelligence and perform the necessary analyses to solve specific problems.

[0653] "Structuring into a three-dimensional model" refers to representing collected data in a three-dimensional virtual format and visually embodying it.

[0654] A "virtual reality environment" refers to a simulated three-dimensional space created using computer technology that users can experience.

[0655] A "specific danger scenario" refers to a concrete dangerous situation or case that is reproduced within the virtual reality environment, with the aim of allowing users to learn by dealing with it.

[0656] A "generative AI model" refers to a pre-trained artificial intelligence program used to generate new prompts or ideas from given data.

[0657] A "prompt message" refers to a document or phrase used as input to a generative AI model to obtain a specific output.

[0658] "Feedback" refers to providing evaluations and suggestions regarding user actions and results, and offering information for improvement.

[0659] This invention is a workplace safety education system that combines virtual reality and artificial intelligence technology. Its main components include a server, terminals, and users working together.

[0660] The server collects data on past risk incidents from an external database. Specifically, it uses Python and SQL to extract information such as reports, photos, and video footage. The collected data is then analyzed using artificial intelligence technology, extracting important information using TensorFlow and OpenCV, and generating a three-dimensional model. This model is then converted into a virtual reality environment using 3D modeling software (e.g., Blender, Unity).

[0661] The server then designs specific hazardous scenarios in the virtual reality environment based on the generated 3D model. The designed simulations are programmed using C or JavaScript, enabling the time progression of events and user interaction within the virtual space.

[0662] The terminal provides the user with simulation data transmitted from the server via a VR headset. Using a head-mounted display such as the Oculus Rift, the user can visually experience a virtual reality environment. The user can record their movements and actions within this environment in real time. A concrete example of a user experience is experiencing an evacuation scenario during a fire.

[0663] User actions are transmitted from the device to the server, where the server analyzes the data. Using machine learning algorithms, the server analyzes user behavior data to evaluate each user's risk avoidance ability and behavioral patterns. Based on the evaluated data, the server provides the user with feedback on areas for improvement.

[0664] Furthermore, it includes a function to create new prompts using a generative AI model, preparing a wider variety of simulation scenarios. For example, it is possible to input a prompt such as "Design a simulation of a safe evacuation scenario in the event of a fire in a data center" into the AI ​​model and generate a new scenario. This provides users with a simulation experience tailored to their needs and can continuously raise their safety awareness.

[0665] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0666] Step 1:

[0667] The server collects past incident data from an external database. It accepts database queries and API access as input, and outputs reports, photos, video footage, and related text data. Specifically, a Python script executes SQL queries, retrieves the necessary data, and saves it to a temporary file.

[0668] Step 2:

[0669] The server analyzes the collected data using artificial intelligence technology and generates a three-dimensional model. It receives the data collected in step 1 as input and performs natural language processing and image analysis. The output is three-dimensional model data for constructing a virtual reality environment. Specifically, a machine learning model using TensorFlow extracts risk elements from the report, OpenCV analyzes photos and videos, and converts the data into a format compatible with Blender.

[0670] Step 3:

[0671] The server designs a virtual reality simulation using the generated 3D model. It uses the 3D model data obtained in step 2 as input to assemble the simulation logic for the scenario. The output is a simulation program that can be reproduced in a virtual reality environment. Specifically, a script written in C defines event sequences in Unity, enabling user interaction.

[0672] Step 4:

[0673] The terminal receives simulation data from the server and provides the user with a virtual reality environment through a VR headset. It receives simulation program data from the server as input and presents an immersive virtual scene to the user visually and aurally as output. Specifically, VR equipment such as the Oculus Rift executes a simulation program running on Unity, updating the scene according to the user's movements.

[0674] Step 5:

[0675] Users interact with a simulation within a virtual reality environment, executing their own movements and choices. They receive visual, auditory, and haptic feedback from VR equipment as input, and simulate actions to avoid danger as output. Specifically, users use hand controllers to select menus, move, and respond to simulation events.

[0676] Step 6:

[0677] The terminal records the user's actions during simulation and sends them to the server. It takes user operation logs and motion data from sensors as input, and sends the combined action data to the server as output. Specifically, motion sensors monitor the user's position and posture, and store the data in a transmission buffer according to the communication protocol with the server.

[0678] Step 7:

[0679] The server analyzes user behavior data and generates feedback. It receives user behavior data sent from the terminal in step 6 as input and generates feedback content to provide to the user as output. Specifically, the server uses a machine learning algorithm to evaluate user behavior and automatically summarizes areas for improvement based on the results into text.

[0680] Step 8:

[0681] The server uses a generative AI model to create new prompts and prepare for the next simulation. It receives feedback and simulation evaluation results as input and generates prompts for a new simulation scenario as output. Specifically, the AI ​​model analyzes existing scenarios and user feedback data to generate detailed prompts for the next simulation.

[0682] (Application Example 1)

[0683] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0684] Traditional safety training in the workplace, such as lectures and simple simulations, faces the challenge of not adequately addressing real-world hazards. This results in insufficient development of employees' hazard awareness and ability to take appropriate immediate action, making it difficult to respond quickly when an actual accident occurs.

[0685] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0686] In this invention, the server includes means for collecting information based on past hazard cases and converting said information into a three-dimensional model, means for generating a virtual space simulation based on the three-dimensional model, and means for causing an operating entity to execute the virtual space simulation and monitoring the operating entity's activities. This makes it possible to reproduce specific hazard scenarios within industrial facilities in virtual reality, analyze the actions of the operating entity, and provide real-time feedback.

[0687] "Past dangerous incidents" refer to records of incidents that include information about accidents and disasters that have actually occurred.

[0688] "Information" refers to data such as reports, photographs, videos, and text related to hazardous incidents.

[0689] A "3D model" is a model reproduced in a three-dimensional virtual space constructed based on information.

[0690] A "virtual space simulation" is a simulation that recreates a virtual reality scenario that a user can experience, based on a three-dimensional model.

[0691] "Operating entity" refers to the user or participant experiencing the virtual space simulation.

[0692] "Monitoring activities" means observing and recording the actions of the controlling entity in real time.

[0693] "Providing a response" refers to the act of conveying appropriate guidance or information based on the actions of the manipulator.

[0694] A "specific hazard scenario within an industrial facility" is a scenario that reproduces specific hazardous situations that may occur within a factory or manufacturing facility in a virtual space.

[0695] "Analyzing behavior" is the process of analyzing the actions of the manipulator in detail and evaluating their effectiveness and appropriateness.

[0696] "Real-time feedback" refers to guidance and evaluation provided immediately in response to the actions of the user during a virtual space simulation.

[0697] The system used to realize this application generates virtual space simulations based on information about hazardous situations and allows users to experience them, thereby providing safety education.

[0698] The server first collects past incidents of risk, analyzes this information, and converts it into a three-dimensional model. Artificial intelligence technology is used for the analysis, specifically software such as TensorFlow. The 3D model is then constructed as a virtual space simulation in a development environment like Unity.

[0699] The terminal plays the role of providing these simulations to the user. By wearing smart glasses or a head-mounted display, the user can experience dangerous scenarios in a virtual space. Devices such as the Oculus Quest 2 are being utilized.

[0700] When a user experiences a simulation, their activities are monitored in real time, and the server receives the data. This data is used to analyze the user's movements and behavioral patterns. Based on the analysis results, users are immediately provided with feedback, thus enhancing the effectiveness of safety education even during the simulation.

[0701] For example, if a user experiences a potentially dangerous situation in an industrial facility and takes inappropriate actions during that process, the system provides guidance to lead them to appropriate behavior. This feedback allows the user to learn safer behaviors.

[0702] An example of a prompt might be: "Propose a system that uses VR to recreate dangerous situations in a factory, analyzes participants' behavior with AI, and provides feedback on how to improve safety education."

[0703] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0704] Step 1:

[0705] The server collects information about risky incidents. This information includes reports, images, videos, and text. The collected information is stored in a database as input.

[0706] Step 2:

[0707] The server analyzes the information stored in the database. Using generative AI models and artificial intelligence technology, the analysis converts the collected information into a three-dimensional model. This data processing results in the output of the 3D model.

[0708] Step 3:

[0709] The server designs a virtual space simulation based on the generated 3D model and builds the simulation environment in the Unity development environment. It uses the 3D model as input and generates the virtual environment as output.

[0710] Step 4:

[0711] The device provides a virtual space simulation to the user through a device such as the Oculus Quest 2. The device allows the user to access the virtual space and obtain a virtual experience through sight and sound.

[0712] Step 5:

[0713] Users participate in virtual reality simulations and experience dangerous situations. Action data from the user during the experience is collected and transmitted to a server.

[0714] Step 6:

[0715] The server analyzes the received operational data from the user. This data is evaluated using an AI algorithm, and feedback is generated regarding safety and appropriateness of the actions.

[0716] Step 7:

[0717] The server provides real-time feedback to the user based on the analysis results. It identifies areas for improvement through data processing and encourages specific actions.

[0718] Step 8:

[0719] The server saves the simulation results and updates the data using a generative AI model to further optimize the educational content. This process improves the quality of subsequent simulations.

[0720] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0721] The present invention combines an emotion engine with a system that provides effective occupational safety education through virtual reality simulations using past hazard data to achieve a more precise educational experience. The server first collects past near-miss and accident / injury cases and converts them into two-dimensional and three-dimensional data formats. Artificial intelligence technology is applied to the collected data to generate a three-dimensional model.

[0722] Next, the server designs a virtual reality simulation based on this three-dimensional model, allowing the user to experience danger in a safe and realistic environment. The terminal provides this simulation to the user through a VR headset and assists the user in initiating interaction within the simulation. The user acts in various scenarios within this virtual environment and learns safe operations.

[0723] A distinctive feature of this invention is the incorporation of an emotion engine into the system. The emotion engine recognizes the user's emotional state through facial and voice analysis. The server takes in both the user's emotional and behavioral data and performs a comprehensive analysis. Based on this analysis, it dynamically adjusts the virtual reality simulation scenario to create a situation in which the user can learn more effectively. Furthermore, by providing the user with feedback tailored to their individual emotional state, it provides comprehensive guidance that includes not only immediate reactions but also psychological aspects.

[0724] For example, in a data center fire scenario, when a user genuinely feels in danger, the emotion engine can sense this and adjust guidance and advice to provide a greater sense of security. This allows users to integrate their emotions and actions and learn to more effectively desensitize risk avoidance behaviors. In this way, the system of the present invention enhances the user's ability to manage their own safety in the workplace by simultaneously improving both their emotional and behavioral aspects.

[0725] The following describes the processing flow.

[0726] Step 1:

[0727] The server collects data on past near misses, accidents, and malfunctions. This includes reports, photos, video footage, and text information. The collected data is converted into a standardized format for analysis.

[0728] Step 2:

[0729] The server uses artificial intelligence technology to convert the collected data into a three-dimensional model. The AI ​​uses image recognition technology to convert 2D data into 3D information, preparing to recreate the details of the accident in three dimensions.

[0730] Step 3:

[0731] The server designs virtual reality simulation scenarios based on the generated three-dimensional models. This includes virtual environments to reproduce specific hazardous scenarios and the placement of dynamic elements that users can interact with.

[0732] Step 4:

[0733] The device allows the user to run a simulation through a VR headset. Through this experience in the virtual environment, the user is encouraged to perceive danger and take appropriate action.

[0734] Step 5:

[0735] When a user begins to act within virtual reality, the emotion engine analyzes the user's facial expressions and voice in real time to recognize the user's emotional state. This emotion data is sent to the server along with the behavioral data.

[0736] Step 6:

[0737] The server integrates emotional and behavioral data sent from the terminal to comprehensively analyze the user's risk avoidance behavior and emotional responses. Based on this analysis, it determines how to adjust the scenario and what kind of feedback to provide to the user.

[0738] Step 7:

[0739] The server provides feedback based on how the user felt and acted during the simulation. This feedback includes areas for improvement in the user's behavior and ways to manage emotions.

[0740] Step 8:

[0741] Users receive feedback, which they then use to improve their risk avoidance abilities in subsequent simulations, while also developing skills to control their own emotional responses.

[0742] (Example 2)

[0743] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0744] Traditional workplace safety education systems merely provide past hazardous incidents as information, failing to offer guidance tailored to the individual emotional states and behaviors of users. Furthermore, they lacked a dynamic learning environment that facilitated user behavioral improvement. Consequently, learning effectiveness was limited, and there were challenges in actually improving hazard avoidance abilities.

[0745] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0746] In this invention, the server includes means for collecting information based on past hazard cases and converting said information into a three-dimensional structure, means for generating a virtual reality environment based on said three-dimensional structure, and means for recognizing the user's emotional state and dynamically adjusting the virtual reality environment scenario based on said emotional state. This enables users to enjoy a learning experience tailored to their individual emotional state and improve their ability to avoid hazards more effectively.

[0747] "Means of information gathering" refers to the processes and techniques for collecting necessary information from documents and databases related to past incidents of danger.

[0748] "Means of converting into a three-dimensional structure" refers to methods and techniques for constructing collected information into a three-dimensional model that can be visually understood.

[0749] "Means for generating a virtual reality environment" refers to the processes and technologies for creating a simulated space that is reproduced on a computer based on a three-dimensional structure.

[0750] "Means of monitoring user responses" refer to devices and technologies used to track and record the actions users take within a virtual reality environment.

[0751] A "means of providing improvement information" refers to a system that uses user behavior data to convey appropriate feedback and advice to users.

[0752] "Means for recognizing a user's emotional state" refers to technologies that analyze a user's facial expressions and voice to determine their psychological state and emotions.

[0753] "Methods for dynamically adjusting scenarios" refer to technologies that change the scenario within virtual reality in real time according to the recognized emotional state of the user.

[0754] To implement this invention, the server first collects data on past hazardous incidents from safety reports and public accident databases. Based on this data, the server uses a common deep learning library, a machine learning framework, to convert it into two-dimensional and three-dimensional data formats. This allows the server to learn patterns and features in the collected data and build a visually reproducible model.

[0755] The server then designs a virtual reality simulation based on this generated three-dimensional model. This step utilizes virtual reality platforms such as Unity or Unreal Engine. The virtual reality environment is designed to be an intuitively interactive space for the user. Within this environment, the user can experience an immersive simulation through a VR headset or similar device. A concrete example is a scenario simulating a fire in a data center. In this scenario, the user is trained to identify and follow appropriate evacuation routes during a fire.

[0756] Furthermore, the server uses an emotion engine to analyze the user's facial expressions and voice to recognize their emotional state. Based on this recognition, it can dynamically adjust the virtual reality simulation scenario to provide the user with a personalized learning experience. For example, if the user is under high stress, the system will reduce the difficulty of the scenario and provide guidance that enhances their sense of security.

[0757] An example of a prompt is, "Create a scenario to learn safe behaviors while operating machinery in a factory." Based on this prompt, the generating AI model designs a specific simulation scenario and presents it in an actionable format. In this way, the system can provide users with effective safety education and effectively improve their ability to avoid hazards in the real world.

[0758] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0759] Step 1:

[0760] The server collects data on past hazard incidents. Industry-standard safety reports and historical accident databases are used as data input sources. This collected data is prepared for future analysis and model generation. The data includes not only text but also charts, graphs, and statistical information. The output is a structured dataset.

[0761] Step 2:

[0762] The server performs a two-dimensional to three-dimensional transformation using the collected data. The structured data obtained in Step 1 is used as input. The server utilizes a machine learning framework to analyze the data features and construct a three-dimensional model. Here, it finds correlations between data points and reorganizes them into a visualizeable form. The output is a dataset represented as a three-dimensional model.

[0763] Step 3:

[0764] The server constructs a virtual reality environment based on the generated 3D model. The 3D model obtained in step 2 is used as input. The server uses the virtual reality platform to design and provide interactive scenarios to the user. The program then redesigns the simulation based on this to reproduce specific hazardous situations. The output is the simulation environment experienced by the user.

[0765] Step 4:

[0766] The terminal provides the user with a virtual reality environment using a VR headset. The input is the simulation environment designed in step 3. The user puts on the VR device and begins acting in a virtual scenario that closely resembles reality. The terminal tracks the user's actions and movements and collects the results of the interaction. The output is user behavior data.

[0767] Step 5:

[0768] The server recognizes the user's emotional state and adjusts the virtual environment accordingly. It obtains input for analyzing the emotional state, along with user behavior data from the terminal. The server uses an emotion analysis algorithm to determine the user's stress level and interests, using these as indicators to adjust the virtual scenario. The program dynamically changes the simulation difficulty and scenario. The output is the adjusted learning environment.

[0769] Step 6:

[0770] The server provides feedback to the user. The input is the user's behavioral data and sentiment analysis results collected in step 4. Based on this, the server creates advice and feedback for improvement and communicates it to the user. This gives the user an opportunity to review their own behavior and learn effectively. The output is feedback provided to the user in text or audio format.

[0771] (Application Example 2)

[0772] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0773] Traditional occupational safety education systems use general virtual reality simulations to train and improve user behavior. However, they have the drawback of providing uniform instruction without considering the emotional state of individual users, making it difficult to deliver effective education tailored to the specific psychological state of each user. Furthermore, the lack of real-time scenario adjustments reduces the efficiency of training, making it difficult to improve actual hazard avoidance abilities.

[0774] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0775] In this invention, the server includes means for collecting data based on past hazard cases and converting said data into a three-dimensional model, means for generating a virtual reality simulation based on the three-dimensional model, means for analyzing the emotional state of the user running the virtual reality simulation, means for dynamically adjusting the scenario based on said emotional state, means for monitoring and comprehensively analyzing the user's behavior, and means for providing feedback. This makes it possible to provide effective and individualized occupational safety education to each user that takes their emotional state into account, and to promote the acquisition of hazard avoidance behaviors in an environment close to reality.

[0776] "Past hazardous incidents" refer to detailed records of accidents and near misses that have occurred in the past, and are data used to understand and avoid hazards in the workplace.

[0777] A "three-dimensional model" refers to a digital representation that reproduces real-world objects and situations in three dimensions, and is used for simulations in virtual spaces.

[0778] "Virtual reality simulation" refers to a technology in which users interact with a computer-generated virtual environment, and is used to simulate real-world situations.

[0779] "Emotional state" refers to the subjective psychological experience a user feels during an experience, and is inferred from data such as facial expressions and voice.

[0780] "Dynamic adjustment" refers to a process of making changes in real time, meaning the system adapts based on user feedback to provide the optimal scenario.

[0781] "Monitoring" refers to the process of continuously observing and collecting data on user behavior and reactions.

[0782] "Feedback" refers to evaluation and guidance information provided to improve the user's learning efficiency, and is information that helps improve during the training process.

[0783] To implement this invention, the server first collects data on past hazardous incidents. This involves a process of collecting detailed data on near misses and accidents in the actual work environment using input devices such as cameras and sensors. The collected data is converted from a two-dimensional format to a three-dimensional format, and a more realistic model is created using three-dimensional modeling software such as Unity.

[0784] Next, the server uses artificial intelligence technology to analyze a three-dimensional model and generate a virtual reality simulation. This process utilizes machine learning frameworks such as TensorFlow to construct various scenarios that the user will experience. Within the simulation, the user immerses themselves in the virtual environment through a VR headset, safely learning about real-world dangerous situations.

[0785] Furthermore, to analyze the user's emotional state in real time, the server uses OpenCV to read facial expressions and infers the emotional state from the user's voice data. Based on this, the emotion engine dynamically adjusts the virtual reality scenario. If the user is in a high-stress state, the difficulty of the scenario is reduced or appropriate advice is provided; conversely, if the user is focused, training is performed in more complex situations.

[0786] A concrete example is an emergency situation in a factory environment where an oil leak causes a fire. If the user panics in this scenario, the emotional engine will sense this and immediately provide reassuring guidance. This practice allows the user to calmly learn how to respond.

[0787] An example of a prompt message might be, "In the event of a fire in the factory, analyze the operators' emotional responses and adaptive behaviors, and develop an appropriate scenario." This instructs the generative AI model on how to adjust the scenario in real time.

[0788] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0789] Step 1:

[0790] The server collects data on past hazardous incidents. Specifically, it acquires two-dimensional data as input from devices such as cameras and sensors, and stores this information in a database. The collected data is used as foundational data for conversion into a three-dimensional model in the next step.

[0791] Step 2:

[0792] The server converts the collected two-dimensional data into a three-dimensional model. This conversion uses three-dimensional modeling software such as Unity, and the output is a three-dimensional model. The data is processed into a model with depth and three-dimensional structure. This creates a realistic environment that can be actually manipulated in a virtual reality simulation.

[0793] Step 3:

[0794] The server designs and builds virtual reality simulations based on the generated 3D models. The output is a virtual environment with various scenarios. Using a generation AI model, various conditions in each scenario are controlled, and realism is enhanced by including random elements. In this process, prompt statements are used as input to generate scenarios based on specific conditions.

[0795] Step 4:

[0796] The user enters the simulation using a VR headset. The user's experience begins, and they interact within the scenario, learning how to operate the system and take actions to avoid danger. The user's actions within VR are recorded as behavioral data for analysis in the next step.

[0797] Step 5:

[0798] The server analyzes user behavior data, facial expressions, and voice data obtained through VR simulation. The input data is analyzed in real time using AI technology (TensorFlow) to infer the user's emotional state. This process outputs numerical data representing the user's psychological state, such as stress levels and concentration levels.

[0799] Step 6:

[0800] The server dynamically adjusts the simulation scenario based on the user's emotional state. The input to this process is the quantified emotional data from the previous step; the server adjusts the output by easing the scenario when emotions are heightened and increasing the difficulty when emotions are calm. This provides a learning experience optimized for each individual user.

[0801] Step 7:

[0802] The server generates and provides feedback to the user based on the final analysis of user behavior and emotions. It analyzes user performance and areas for improvement from the input data, providing specific and effective guidance as output. The feedback includes points to focus on in the next training session and guidelines for further learning.

[0803] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0804] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet Search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0805] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[0806] Furthermore, the emotion identification model 59, acting as an emotion engine, may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0807] Figure 9 shows an emotion map 400 in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0808] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0809] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0810] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, motorcycles, etc., emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0811] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0812] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0813] The above description primarily focuses on the functions of the data processing device 12 in relation to this disclosure. However, the system related to this disclosure is not necessarily implemented on a server. The system related to this disclosure may be implemented as a general information processing system. This disclosure may be implemented, for example, as a software program that runs on a personal computer or as an application that runs on a smartphone. The method related to this disclosure may be provided to users in SaaS (Software as a Service) format.

[0814] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing of the specific process may be performed by multiple computers, including computer 22. For example, a data generation model 58 may be provided in an external device of the data processing device 12, and the external device may generate data according to the input data.

[0815] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0816] 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.

[0817] Furthermore, it is not necessary to store the entirety of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0818] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0819] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0820] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0821] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0822] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and the like that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0823] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted as being incorporated by reference.

[0824] The following is further disclosed regarding the embodiments described above.

[0825] (Claim 1)

[0826] A means of collecting data based on past risk cases and converting that data into a three-dimensional model,

[0827] A means for generating a virtual reality simulation based on the three-dimensional model,

[0828] A means for having a user run the virtual reality simulation and monitoring the user's behavior,

[0829] A means for analyzing the monitoring results and providing feedback to the user,

[0830] A system that includes this.

[0831] (Claim 2)

[0832] The system according to claim 1, comprising means for evaluating a user's risk avoidance behavior within a virtual reality simulation and providing guidance for improvement.

[0833] (Claim 3)

[0834] The system according to claim 1, comprising means for analyzing collected data using artificial intelligence technology and structuring it into a three-dimensional model.

[0835] "Example 1"

[0836] (Claim 1)

[0837] A means of collecting information based on past risk cases and structuring that information into a three-dimensional model using artificial intelligence technology,

[0838] A means for designing a virtual reality environment based on the three-dimensional model and generating specific risk scenarios,

[0839] A means for allowing a user to experience the virtual reality environment and recording the user's actions in real time,

[0840] A means for analyzing the behavioral information and providing improvement information to the user based on the results,

[0841] A means of creating new prompt sentences using a generative AI model and preparing further simulation scenarios,

[0842] A system that includes this.

[0843] (Claim 2)

[0844] The system according to claim 1, comprising means for evaluating a user's ability to avoid danger in a virtual reality environment and providing guidance for learning based on the analysis results.

[0845] (Claim 3)

[0846] The system according to claim 1, comprising means for analyzing user behavior information using data processing technology and generating feedback content.

[0847] "Application Example 1"

[0848] (Claim 1)

[0849] A means of collecting information based on past risk cases and converting that information into a three-dimensional model,

[0850] A means for generating a virtual space simulation based on the three-dimensional model,

[0851] A means of having a virtual space simulation run by an operating entity and monitoring the operating entity's activities,

[0852] A means for analyzing the monitoring results and providing a response to the operating entity,

[0853] A means of analyzing the activities of the operator, evaluating the safety of those activities, and suggesting areas for improvement,

[0854] A system that includes this.

[0855] (Claim 2)

[0856] The system according to claim 1, comprising means for recreating specific hazard scenarios within an industrial facility in virtual reality, analyzing the actions of the operator, and providing real-time feedback.

[0857] (Claim 3)

[0858] The system according to claim 1, comprising means for capturing the movements of an operating entity in a virtual reality environment and analyzing them using artificial intelligence technology.

[0859] "Example 2 of combining an emotion engine"

[0860] (Claim 1)

[0861] A means of collecting information based on past dangerous incidents and converting that information into a three-dimensional structure,

[0862] A means for generating a virtual reality environment based on the three-dimensional structure,

[0863] A means for having a user run the virtual reality environment and monitoring the user's reactions,

[0864] A means for analyzing the monitoring results and providing improvement information to the user,

[0865] A means for recognizing the user's emotional state and dynamically adjusting the virtual reality environment scenario based on that emotional state,

[0866] A system that includes this.

[0867] (Claim 2)

[0868] The system according to claim 1, comprising means for evaluating and guiding a user's risk avoidance behavior within a virtual reality environment.

[0869] (Claim 3)

[0870] The system according to claim 1, comprising means for analyzing collected information using machine learning technology and converting it into a three-dimensional structure.

[0871] "Application example 2 of combining emotional engines"

[0872] (Claim 1)

[0873] A means of collecting data based on past risk cases and converting that data into a three-dimensional model,

[0874] A means for generating a virtual reality simulation based on the three-dimensional model,

[0875] A means of analyzing the emotional state of users running virtual reality simulations,

[0876] A means for dynamically adjusting the scenario based on the emotional state,

[0877] A means for having a user run the virtual reality simulation, monitoring the user's behavior, and comprehensively analyzing it,

[0878] A means for providing feedback to the user based on the monitoring results and sentiment analysis results,

[0879] A system that includes this.

[0880] (Claim 2)

[0881] The system according to claim 1, comprising means for evaluating the user's risk avoidance behavior within a virtual reality simulation and providing individualized guidance for improvement according to the user's emotions.

[0882] (Claim 3)

[0883] The system according to claim 1, comprising means for analyzing collected data using artificial intelligence technology and structuring it into a three-dimensional model, and means for analyzing the emotional state in real time. [Explanation of Symbols]

[0884] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. A means of collecting data based on past risk cases and converting that data into a three-dimensional model, A means for generating a virtual reality simulation based on the three-dimensional model, A means for having a user run the virtual reality simulation and monitoring the user's behavior, A means for analyzing the monitoring results and providing feedback to the user, A system that includes this.

2. The system according to claim 1, comprising means for evaluating a user's risk avoidance behavior within a virtual reality simulation and providing guidance for improvement.

3. The system according to claim 1, comprising means for analyzing collected data using artificial intelligence technology and structuring it into a three-dimensional model.

Images