system

Abstract

Provide a system. A simulation system for practical training in new graduate training, comprising: A means of setting personas for specific executives; means for receiving user input and generating prompts based on said persona; means for sending a request to a generative artificial intelligence model using the prompt to generate a response; means for providing the generated response to a user; A system including:

Description

[Technical Field]

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

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

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

[0004] In training for new graduates, role-playing based on actual work scenarios is essential to increasing the effectiveness of practical training. However, traditional methods require specific personnel in positions of authority, such as department managers, to take time out to participate in the training, which places a significant burden on trainees and can lead to inconsistent training quality. Furthermore, trainees are often limited in the amount of time they have to practice right before the training begins, which can hinder their ability to fully prepare. This situation creates the challenge of ineffectively improving trainees' skills. [Means for solving the problem]

[0005] To address the above-mentioned issues, the present invention provides a simulation system for practical training in new graduate training. This system includes a means for setting a persona for a specific manager, a means for receiving user input and generating prompts based on the persona, a means for sending requests to a generative artificial intelligence model using the prompts to generate responses, and a means for providing the generated responses to the user. This allows trainees to engage in high-quality role-playing using the generative artificial intelligence without the participation of an actual manager, and allows for last-minute practice in advance. Furthermore, the generative artificial intelligence can maintain multiple personas corresponding to specific business scenarios and generate different prompts based on each persona, enabling practical training that can accommodate a wide variety of scenarios.

[0006] "New graduate training" is an early stage educational program that a company provides to newly hired employees, helping them acquire the knowledge and skills necessary for their jobs.

[0007] "Practical training" is not just theoretical learning, but training based on actual business scenarios, designed to equip participants with the skills to respond immediately to practical situations.

[0008] A "simulation system" is a system that artificially recreates specific situations or scenarios and allows training of actions and responses based on them.

[0009] A "person in a position" refers to an employee who has a specific role or responsibilities within a company, such as a department head or manager.

[0010] A "persona" is a virtual character that embodies the personality and behavioral characteristics of a specific person in a certain position, and is used in simulations.

[0011] "User" refers to the person who operates the system and enters data, which in this case mainly refers to new graduate trainees.

[0012] A "prompt" is text containing a question or instruction that is sent to a generative artificial intelligence model in response to user input.

[0013] A "generative artificial intelligence model" is a model that uses artificial intelligence technology to generate natural sentences like humans.

[0014] "Response" refers to the answer or reaction generated by a generative artificial intelligence model based on a prompt.

[0015] A "specific business scenario" refers to a simulation scenario that specifically assumes a specific business or situation.

[0016] "Training Session" means a series of activities or a period of time during which training is conducted with a specific purpose. [Brief explanation of the drawings]

[0017] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9]1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 11] FIG. 3 is a sequence diagram showing a processing flow of the data processing system according to the first embodiment. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0018] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

[0019] First, the terms used in the following description will be explained.

[0020] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), and an APU (Accelerated Processing Unit).

[0021] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

[0022] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0023] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0024] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0025] [First embodiment]

[0026] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0027] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0028] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0029] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0030] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0031] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0032] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

[0033] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0034] 2, in the data processing device 12, a specific process is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0035] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0036] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with the specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0037] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0038] This invention relates to a simulation system for providing effective practical training to new graduate trainees. The system sets the persona of a specific manager and uses a generative artificial intelligence model to generate appropriate responses based on user input, which are then provided to the user. This system allows trainees to role-play based on a variety of scenarios without the need for an actual manager.

[0039] Example of a system

[0040] server:

[0041] The server sets an OpenAI (registered trademark) API key and prepares to communicate with the generative artificial intelligence model (hereinafter referred to as the AI ​​model). As an initial setting, a persona of a specific person in a specific position is prepared, and the server is responsible for sending prompts to the AI ​​model based on this persona and obtaining responses.

[0042] Device:

[0043] The user's device acts as an interface to receive and send input from the user to the server. When the user provides input for a simulation scenario, such as seeking approval for a new business venture or preparing for an important meeting, the input is communicated to the server.

[0044] User:

[0045] The user, a new graduate trainee, uses the system to simulate interactions with a manager based on a simulation scenario. For example, the user reports the results of market research to a persona about launching a new business and requests approval for the project.

[0046] System Operation

[0047] 1. The server initializes an OpenAI API key and prepares it for communication with the AI ​​model, allowing it to generate responses based on a specific persona.

[0048] 2. The user inputs the following through the terminal: "After reporting on market research for a new business, we have confirmed that there is greater demand than expected. Would you please give us permission to proceed with this project?" The terminal then sends this input to the server.

[0049] 3. The server uses the persona "Manager: Manager interacting with subordinate seeking approval for launching a new business" and generates a prompt based on the user's input.

[0050] 4. The server sends a request based on this prompt to the AI ​​model, which analyzes the prompt and generates the most appropriate response.

[0051] 5. The server sends the response received from the AI ​​model to the device, for example, "These results are very good. Could you also provide a specific budget and timeline?"

[0052] 6. The terminal displays this response to the user, who can then confirm the response and continue the dialogue.

[0053] Specific examples

[0054] 1. User types, "I've reported on my market research for a new business and found that there is more demand than expected. Do I have permission to move forward with this project?"

[0055] 2. The server receives this input and generates a prompt based on the setting "Persona: Manager: Manager interacting with subordinate seeking approval for launching a new business."

[0056] 3. The server sends the generated prompt to the AI ​​model, which generates a response saying, "These results are very good. Can you also provide a specific budget and timeline?"

[0057] 4. The terminal displays this response to the user, who can then ask further questions or provide further explanations based on the response.

[0058] This system will reduce the burden on managers and other executives and allow trainees to practice in a variety of scenarios, which is expected to improve skills efficiently in a realistic environment.

[0059] The processing flow will be explained below.

[0060] Step 1:

[0061] The server sets up an OpenAI API key and prepares communication with the generative AI model, allowing the system to access the AI ​​model through the API.

[0062] Step 2:

[0063] To start the new graduate training simulation, the user inputs information based on the scenario into the terminal. For example, the user inputs a sentence such as, "After reporting on the market research for a new business, we have found that there is greater demand than expected. May I have your permission to proceed with this project?"

[0064] Step 3:

[0065] The terminal receives user input and transmits the input to the server.

[0066] Step 4:

[0067] The server uses the persona of a specific person (e.g., a manager) to generate a prompt based on user input. For example, the prompt is configured as "Persona: Manager: Manager interacting with subordinate seeking approval for launching a new business."

[0068] Step 5:

[0069] The server sends the generated prompt to the AI ​​model, asking it to generate a response. The prompt includes the persona information and the specific question asked by the user.

[0070] Step 6:

[0071] The generative AI model generates an appropriate response based on the prompt, such as, "These results are very good. Can you also provide a specific budget and timeline?"

[0072] Step 7:

[0073] The server receives the response from the generative AI and converts it into a format that can be read by the user.

[0074] Step 8:

[0075] The server sends the converted response to the terminal, ready to display to the user.

[0076] Step 9:

[0077] The terminal displays the response received from the server to the user, for example, in the form "Manager: These results are very good. Could you also provide a specific budget proposal and timeline?"

[0078] Step 10:

[0079] The user can review the displayed responses and continue the simulation by entering new questions or information as needed. By repeating the process, the user can receive training tailored to real-world business scenarios.

[0080] Example 1

[0081] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0082] Traditional practical training for new graduates requires actual managers, which takes time and money, and places a burden on managers. Also, trainees have limited opportunities to practice in a variety of scenarios, which means the training is not as effective as it could be.

[0083] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0084] In this invention, the server includes means for setting a persona of a specific manager, means for receiving input from a user and transmitting the input from the terminal to the server, means for generating prompts based on the persona, means for using the generated prompts to send requests to a generative artificial intelligence model to generate responses, and means for transmitting the generated responses to the terminal and providing them to the user. This enables trainees to role-play based on a variety of scenarios without the need for an actual manager.

[0085] "New graduate training" is training given to new employees at a company to acquire the knowledge and skills necessary for their work.

[0086] A "simulation system" is a system that simulates and reproduces real-world situations to enable effective learning and training.

[0087] A "persona" is a fictional character created to represent a specific position or situation.

[0088] "User" refers to a person who uses the system and receives training.

[0089] "Input" refers to actions such as questions, requests, and information provided by a user to a system.

[0090] "Terminal" refers to the device used by a user to access the system.

[0091] A "server" refers to a system that receives input from a user and provides computing resources for processing.

[0092] A "prompt" refers to the act of writing a sentence containing instructions or questions to a generative artificial intelligence model to generate an appropriate response, or the sentence itself.

[0093] A "generative artificial intelligence model" refers to an algorithm or program that generates an optimal response based on a given input.

[0094] A "request" refers to a request made by a server to a generative artificial intelligence model to obtain or process information.

[0095] "Response" refers to the answer or result that a generative artificial intelligence model generates based on a request.

[0096] "Business scenario" refers to the content of a simulation created assuming a specific situation or case in business.

[0097] "Exit Condition" refers to a predefined condition for ending a training session.

[0098] This invention relates to a simulation system for providing effective practical training to new graduate trainees. This system creates a persona of a specific manager and uses a generative artificial intelligence model to generate appropriate responses based on user input, which are then provided to the user. This allows trainees to role-play based on a variety of scenarios without the need for an actual manager.

[0099] The server initializes the OpenAI API key and prepares to communicate with the AI ​​model. A specific role persona is prepared as the initial setting, and the server is responsible for sending prompts to the AI ​​model and obtaining responses based on this persona. The server runs on a cloud server such as AWS (registered trademark), GCP, or Azure (registered trademark), and is implemented using programming languages ​​such as Python and JavaScript (registered trademark).

[0100] A terminal is a device through which a user accesses the system, such as a PC, smartphone, or tablet. Operations on the terminal are performed through a web browser or a dedicated application (React, Vue.js, Flask, etc.). The terminal's role is to receive input from the user and send it to the server.

[0101] The user is a new graduate trainee who uses this system to simulate a dialogue with a manager based on a simulation scenario. For example, a scenario is imagined in which the user reports the results of market research to a persona about the launch of a new business and asks for approval for the project. The user inputs information through a terminal and receives responses from the server.

[0102] Specific examples

[0103] Here's an example of how it works:

[0104] 1. The user types into the terminal, "I have reported on the market research for a new business and found that there is more demand than expected. May I have permission to proceed with this project?"

[0105] 2. The device captures this input using JavaScript and sends it to the server using the axios library.

[0106] 3. The server receives this input and generates a prompt based on the persona: "Manager interacting with subordinate seeking approval for launching a new business."

[0107] 4. The server sends the generated prompt to the OpenAI API, where the AI ​​model analyzes the prompt and generates a response like, "These results are very good. Can you also provide a specific budget and timeline?"

[0108] 5. The server receives the response from the AI ​​model and sends it to the device as an HTTP response.

[0109] 6. The terminal displays the received response to the user, who can then ask further questions or continue the discussion based on the displayed response.

[0110] This system reduces the burden on managers and other executives and allows trainees to practice in a variety of scenarios, which is expected to improve skills efficiently in a realistic environment.

[0111] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0112] Step 1:

[0113] The server initializes the OpenAI API key, which prepares and configures the AI ​​model for communication. The server reads the API key and persona configuration from the config.json file and uses the Python requests library to prepare for communication with the OpenAI API. The data in the config.json file is used as input, and the AI ​​model is ready for communication as output.

[0114] Step 2:

[0115] The user types into the terminal, "After reporting on market research for a new business, we have found that there is more demand than expected. May I have permission to proceed with this project?" The input data is information based on the user's scenario. Specifically, it includes the action of entering text into an input form on a web browser. The terminal captures this input and sends it to the server as a POST request using the axios library. The input is the user's text input, and the output generates data that is sent to the server.

[0116] Step 3:

[0117] The server analyzes the input data received from the user and generates a prompt based on the persona. Specifically, the user's input data is stored in variables, and a prompt is created based on the persona set as "Manager: Manager conversing with subordinate seeking approval for launching a new business." As an example, prepare the following prompt: "Persona: Manager. Manager conversing with subordinate seeking approval for launching a new business. The subordinate reports the results of market research for the new business and requests permission to proceed with the project." The input is the user's text data, and the output is a prompt.

[0118] Step 4:

[0119] The server sends the generated prompt to the OpenAI API and receives a response from the AI ​​model. The server uses the requests.post method to send a request containing the prompt and receives the response generated by the AI ​​model. The input is the generated prompt, and the output is the response from the AI ​​model. For example, the response generated might be, "These results are very good. Could you also provide a specific budget and timeline?"

[0120] Step 5:

[0121] The server sends the response received from the AI ​​model to the terminal. The server analyzes the response returned from the AI ​​model and formats it in a format that is easy for the user to read. It then sends it to the terminal as an HTTP response. The response data from the AI ​​model is the input, and the formatted response data is sent to the terminal as the output.

[0122] Step 6:

[0123] The device receives the response from the server and displays it to the user. The device uses JavaScript to receive the response from the server and updates the HTML DOM. The displayed response is "These results are very good. Can you also provide a specific budget and timeline?", and the user can continue the dialogue based on this information. The input is the response data from the server, and the output is the response displayed to the user.

[0124] (Application example 1)

[0125] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0126] While practical training is important for new graduates, conducting real-time training in dialogue with managers and operating factory robots consumes a lot of time and resources. Furthermore, it places a heavy burden on managers, potentially reducing efficiency and resulting in inconsistent training quality. Furthermore, there is a high risk of mistakes when operating factory robots, so a method is needed to enable employees to acquire sufficient skills through simulation before undergoing actual training.

[0127] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0128] In this invention, the server includes a means for setting a persona for a specific manager, a means for receiving user input and generating a prompt based on the persona, a means for sending a request to a generative artificial intelligence model using the prompt to generate a response, a means for providing the generated response to the user, and a means for simulating a specific scenario for factory robot operation training and responding to user operations. This reduces the burden on managers during new graduate training, provides effective practical training, and enables users to safely and practically acquire factory robot operation skills. Furthermore, by supporting a variety of scenarios, the quality and efficiency of training can be improved.

[0129] A "job title persona" is a character that mimics the behavior and thoughts of a person with a specific job title, and is a setting used to simulate human interaction during training for new graduates.

[0130] "User input" refers to information provided in text or voice format, such as instructions or questions given by the trainee to the simulation system through the training terminal.

[0131] A "prompt" is input data sent to a generative artificial intelligence model. It is generated based on user input and persona settings and serves as a guide for the AI ​​to generate a response.

[0132] A "generative artificial intelligence model" is an algorithm or system that learns from large amounts of data and performs advanced text generation in response to input, and is a technology used to generate responses appropriate to user input.

[0133] A "response" is a text message or instruction that is created by a generative artificial intelligence model in response to user input and provided to the user.

[0134] A "factory robot" is a mechanical device used to automate manufacturing operations and is capable of performing a variety of tasks, but requires training to operate it.

[0135] "Operation training" is training to learn how to operate factory robots effectively and safely, and is an educational process to improve actual operating skills through simulation.

[0136] "Simulation" is a virtual training method that mimics real-life situations and work environments, and is a learning technique used to acquire practical skills while minimizing risk.

[0137] This invention is an example of a simulation system for effectively conducting practical training in new graduate training. In particular, a system applicable to training in the operation of factory robots will be described.

[0138] System Overview

[0139] The system consists of a server, a user terminal, and a generative artificial intelligence model.

[0140] Server: Holds OpenAI API keys and configuration information, communicates with AI models, sets personas, generates prompts, and manages user input.

[0141] User terminal: A device used by new operators to input data, typically a tablet or smart glasses.

[0142] Generative artificial intelligence model: An AI model with large-scale text generation capabilities that generates appropriate responses based on user input.

[0143] Basic system operation

[0144] 1. The user starts up the terminal and logs in. A training scenario for operating a factory robot is presented.

[0145] 2. The user enters a specific instruction or question.

[0146] 3. The server receives the user's input and generates a prompt based on the persona.

[0147] 4. The server sends the generated prompt to the AI ​​model.

[0148] 5. The AI ​​model parses the prompt and generates an appropriate response.

[0149] 6. The server receives the generated response and sends it to the user terminal.

[0150] 7. The user confirms the response and continues or asks an additional question or takes an action.

[0151] Program processing and hardware / software configuration

[0152] Hardware: User devices such as tablets and smart glasses, and cloud-based servers.

[0153] Software: Web server using Flask, AI model communication using OpenAI API.

[0154] The server first initializes the OpenAI API key and generates a prompt based on the persona. When the user enters input, the server generates a prompt based on the input and sends it to the AI ​​model. The AI ​​model then analyzes the prompt and generates the optimal response.

[0155] Specific examples

[0156] Examples of prompts:

[0157] User Input: "My robot arm suddenly stopped working. What should I do?"

[0158] Generated prompt:

[0159] "Senior Operator's Manual: Provides operating and troubleshooting instructions.\n\nNew Operator: The robot arm suddenly stopped working. What should I do?\n\nSenior Operator:"

[0160] Generated response:

[0161] "First, make sure your arm's power cable is properly connected. If that's OK, try resetting the software. Here's how to do it..."

[0162] In this way, by using a server and a generative artificial intelligence model, a system is provided that allows new graduate trainees to safely and efficiently learn factory robot operation techniques in a realistic environment.

[0163] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0164] Step 1:

[0165] The user starts up the terminal and logs in. The input is the user ID and password, and the output is a message that the user has successfully logged in to the system. This allows the user to access the training scenario.

[0166] Step 2:

[0167] The server receives login information and authenticates the user. The input is the user ID and password, and the output is the authentication result. If authentication is successful, the user is presented with a specific scenario.

[0168] Step 3:

[0169] The user inputs specific operation instructions and questions based on the factory robot operation training scenario. The inputs are operation instructions and questions, and the outputs are requests to the server.

[0170] Step 4:

[0171] The server receives input from the user and generates a prompt based on the persona. The input is the user's operation instructions or questions, and the output is a prompt. The server generates a prompt based on the persona's configuration information, and uses this prompt in the next step.

[0172] Step 5:

[0173] The server sends the generated prompt to the AI ​​model. The input is the prompt and the output is the response from the AI ​​model. Based on this prompt, the AI ​​model performs data analysis to generate an appropriate response.

[0174] Step 6:

[0175] The AI ​​model analyzes the prompt and generates the optimal response. The input is the prompt and the output is the generated response. The AI ​​model's internal algorithm is used to derive the appropriate response to the user's input.

[0176] Step 7:

[0177] The server receives the generated response and sends it to the user's device. The input is the response from the AI ​​model, and the output is a text message that is presented to the user, allowing the user to see the generated response.

[0178] Step 8:

[0179] The user confirms the presented response and, if necessary, continues or asks an additional question. The input is the user's new operation instruction or question, and the output is another request to the server. This cycle allows for continuous training.

[0180] Furthermore, an emotion engine that estimates the user's emotion may be combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0181] This invention combines a simulation system for effective practical training for new graduate trainees with an emotion engine that recognizes the user's emotions. This system allows trainees to have an emotionally rich interactive experience through role-playing based on real business scenarios.

[0182] Example of a system

[0183] server:

[0184] The server sets an OpenAI API key and prepares to communicate with the generative artificial intelligence model (hereafter referred to as the AI ​​model).It also has an emotion engine that recognizes the user's emotions and reflects them in responses.

[0185] Device:

[0186] The device used by the user acts as an interface to receive input from the user and send it to the server. When the user provides input for a simulation scenario, such as requesting approval for a new business or preparing for an important meeting, this input is transmitted to the server via the emotion engine.

[0187] User:

[0188] The user, a new graduate trainee, uses the system to simulate interactions with a manager based on a simulation scenario. For example, the user reports the results of market research to a persona about launching a new business and requests approval for the project.

[0189] System Operation

[0190] 1. The server initializes the OpenAI API key and prepares to communicate with the AI ​​model. The emotion engine is also initialized at the same time. This allows the system to access the AI ​​model through the API and process the user's emotion information.

[0191] 2. The user inputs the following through the device: "After reporting on market research for a new business, we have found that there is greater demand than expected. Would you please give us permission to proceed with this project?" The device then sends this input to the emotion engine.

[0192] 3. The emotion engine analyzes user input and extracts emotional states. For example, text analysis can recognize emotions such as "excitement" or "fear."

[0193] 4. The device sends the user input, including the emotion recognition results, to the server.

[0194] 5. The server generates prompts that reflect the emotion recognition results using the persona of a specific person in a certain position (e.g., a manager). For example, in addition to the setting of "Persona: Manager: Manager interacting with a subordinate seeking approval for the launch of a new business," the server configures the prompts by taking into account the user's "excitement" state.

[0195] 6. The server sends the generated prompt to the AI ​​model, asking it to generate a response. The prompt includes the persona information, the specific question from the user, and the emotion recognition results.

[0196] 7. The generative AI model generates an appropriate response based on the prompt, such as "These results are very good. Can you also provide a specific budget and timeline?", and adapts the tone and expression to reflect the user's level of excitement.

[0197] 8. The server receives the response from the generative AI and converts it into a format that can be read by the user.

[0198] 9. The server sends the converted response to the terminal, ready to display to the user.

[0199] 10. The device displays the response received from the server to the user, for example, "Manager: These results are very good. Could you also provide a specific budget and timeline?", reflecting the user's sentiment.

[0200] Specific examples

[0201] 1. User types, "I've reported on my market research for a new business and found that there is more demand than expected. Do I have permission to move forward with this project?"

[0202] 2. The emotion engine analyzes this input and recognizes the user's "excited" state.

[0203] 3. The server receives this and generates a prompt based on the setting "Persona: Manager: Manager interacting with subordinate seeking approval for launching a new business." The prompt reflects the emotion of "excitement."

[0204] 4. Based on the prompt, the generative AI model generates a response like, "These results are very good. Can you also provide a specific budget and timeline?"

[0205] 5. The device displays this response to the user: "Manager: These results are very good. Can you also provide a specific budget and timeline?"

[0206] This system reduces the burden on managers and other executives, and allows trainees to practice in a variety of scenarios. The introduction of an emotion engine allows users to enjoy a more realistic dialogue experience, improving their skills in an environment that is closer to the real work environment.

[0207] The processing flow will be explained below.

[0208] Step 1:

[0209] The server sets the OpenAI API key and prepares for communication with the generative AI model. It also initializes the emotion engine and prepares for emotion analysis.

[0210] Step 2:

[0211] The user inputs information to start the simulation through the terminal. For example, the user might input, "After reporting on the market research for a new business, we have found that there is greater demand than expected. May I have your permission to proceed with this project?"

[0212] Step 3:

[0213] The device receives user input and first sends it to the emotion engine, which analyzes the user's input text and recognizes the user's emotional state (e.g., "excited" or "tense").

[0214] Step 4:

[0215] The emotion engine returns the analysis results to the terminal and sends the input, including the user's emotional state, to the server.

[0216] Step 5:

[0217] The server uses the persona of a specific person (e.g., a manager) to generate prompts based on user input. For example, in addition to the setting "Persona: Manager: Manager interacting with subordinate seeking approval for launching a new business," the server configures the prompt taking into account the user's "excitement" state.

[0218] Step 6:

[0219] The server sends the generated prompt and emotion recognition results to the AI ​​model, asking it to generate a response. The prompt includes persona information, a specific question from the user, and the emotion recognition results.

[0220] Step 7:

[0221] The generative AI model generates an appropriate response based on the prompt, such as "These results are very good. Can you also provide a specific budget and timeline?", reflecting the user's level of excitement in tone and expression.

[0222] Step 8:

[0223] The server receives the response from the generative AI and converts it into a format that can be read by the user.

[0224] Step 9:

[0225] The server sends the converted response to the terminal, ready to display to the user.

[0226] Step 10:

[0227] The terminal displays the response received from the server to the user, for example, "Manager: These results are very good. Could you also provide a specific budget proposal and timeline?", reflecting the user's feelings.

[0228] Step 11:

[0229] The user can review the displayed responses and continue the simulation by entering new questions or information as needed. By repeating this process, the user can receive advanced training that is tailored to real-world business scenarios.

[0230] Example 2

[0231] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0232] Conventional practical training systems for new graduates are unable to generate responses that take into account the user's emotions, making it difficult to provide the emotionally rich dialogue experience required in actual business scenarios. In addition, the simple persona settings of executives lack the precision required to obtain a realistic dialogue experience, limiting the effectiveness of the training.

[0233] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for receiving a user's input and analyzing the emotional state through an emotion engine, means for setting a persona of a specific manager, means for generating a prompt based on the persona taking the emotional state into consideration, means for sending a request to a generative AI model using the prompt to generate a response, and means for providing the generated response to the user. This enables a realistic dialogue experience that takes the user's emotions into consideration, allowing trainees to receive effective training in an environment that is close to actual work.

[0234] The "means for receiving user input and analyzing the emotional state through an emotion engine" is a device or program for receiving text entered by a user into a terminal and transmitting it to an emotion engine to extract emotional information.

[0235] A "means for setting the persona of a specific manager" is a device or program for specifically setting the personality and position of a manager used in practical training during new graduate training.

[0236] The "means for generating a prompt based on the persona while taking into account the emotional state" is a device or program that creates a prompt that reflects the user's emotional state based on set persona information.

[0237] "Means for sending a request to a generative artificial intelligence model using the prompt and generating a response" refers to a device or program that sends the generated prompt to an AI model and generates a response in response.

[0238] The "means for providing the generated response to the user" refers to a device or program that converts the generated response into a format that can be confirmed by the user and displays it through a terminal.

[0239] A "generative artificial intelligence model" is a type of artificial intelligence that generates human-like responses based on user-provided prompts.

[0240] A "persona" is a virtual character that defines the personality, position, and role of a specific person or character.

[0241] An "emotion engine" is software or algorithm that analyzes a user's text input and extracts the emotions contained therein.

[0242] This invention combines an emotion engine that recognizes user emotions in a simulation system for practical training for new graduate trainees. The system is designed to enable users to have an emotionally rich dialogue experience based on business scenarios through persona setting for executives, prompt generation, and a generative AI model.

[0243] Hardware and software used

[0244] The following hardware and software are used to implement this system.

[0245] Server: A server with high-performance computing power

[0246] Terminal: A computer or mobile device for receiving user input.

[0247] Emotion engine: Software that recognizes emotions through text analysis (e.g., "Microsoft® Azure Sentiment Analysis" or "IBM Watson® Tone Analyzer")

[0248] Generative artificial intelligence model: An AI model that performs natural language processing (e.g., "OpenAI GPT-3 (registered trademark)")

[0249] Communication interface: API communication via the internet

[0250] Overall system flow

[0251] 1. The server first sets the OpenAI API key and prepares to communicate with the AI ​​model. It also initializes the emotion engine, which completes preparations for API communication and emotion analysis.

[0252] 2. The user inputs scenario information into the terminal and sends it. For example, the user might input a sentence like, "After reporting on market research for a new business, we have found that there is greater demand than expected. May I have your permission to proceed with this project?"

[0253] 3. The device sends the input data from the user to the emotion engine, allowing the emotion engine to analyze the data.

[0254] 4. The emotion engine analyzes the user's input and extracts the emotional state (e.g., "excited," "fear," etc.). The analysis result is encoded and sent back to the device.

[0255] 5. The device sends the user's input, including the emotion recognition results, to the server.

[0256] 6. The server generates a prompt using the persona of the specified manager and the user's emotion recognition results. For example, it generates a prompt with the content "Persona: Manager, interacting with subordinate seeking approval for launching a new business."

[0257] 7. The server sends the generated prompt to the AI ​​model, asking it to generate a response.

[0258] 8. The generative AI model generates an appropriate response based on the prompt and sends it back to the server, for example, "These results are very good. Can you also provide a specific budget and timeline?"

[0259] 9. The server converts the received response into a user-readable format and sends it to the terminal.

[0260] 10. The terminal displays the response from the server to the user, for example, "Manager: These results are very good. Could you also provide a specific budget and timeline?"

[0261] Specific examples

[0262] For example, a new graduate trainee might input, "I reported on the market research for a new business and found that there is greater demand than expected. Can I have your permission to proceed with this project?" This input is analyzed through an emotion engine, which recognizes the "excited" state. The server then generates a prompt based on the setting "Persona: Manager interacting with subordinate seeking approval for launching a new business." The generative AI model then generates an appropriate response, such as, "These results are very good. Could you also provide a specific budget proposal and timeline?" This response is finally displayed on the user's device, providing the new graduate with a realistic dialogue experience.

[0263] By using this system in this way, new graduate trainees can practice in a variety of scenarios, reducing the burden on specific managers while allowing trainees to improve their skills through emotionally rich dialogue.

[0264] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0265] Step 1:

[0266] The server initializes the OpenAI API key and prepares to communicate with the AI ​​model. The emotion engine is also initialized at the same time, allowing the system to access the AI ​​model through the API and process the user's emotion information.

[0267] Specific operation: Enter the OpenAI API key in the server's configuration file and call the initialization method of the emotion engine (e.g., "Microsoft Azure Sentiment Analysis" or "IBM Watson Tone Analyzer").

[0268] Input: Basic configuration information to boot the system

[0269] Output: API communication and emotion engine initialization complete

[0270] Step 2:

[0271] The user inputs scenario information through the terminal and clicks the send button on the terminal. For example, the user can input a sentence such as, "After reporting on market research for a new business, we have found that there is greater demand than expected. May I have your permission to proceed with this project?"

[0272] Specific behavior: The user enters text into the input field on the terminal and clicks the send button.

[0273] Input: Text entered by the user

[0274] Output: Send button click event on the device

[0275] Step 3:

[0276] The device sends input data from the user to the emotion engine, which uses the data for emotion analysis.

[0277] Specific operation: An HTTP request is generated on the terminal side and the user's input text is sent to the emotion engine's API endpoint.

[0278] Input: User-entered text

[0279] Output: Text data sent to the emotion engine API

[0280] Step 4:

[0281] The emotion engine analyzes the user's input and extracts the emotional state (e.g., "excited," "fear," etc.), which is then encoded and sent back to the device.

[0282] What it does: Analyzes text using the sentiment engine API and generates a sentiment score.

[0283] Input: Text data sent to the emotion engine

[0284] Output: Emotion score (user's emotional state)

[0285] Step 5:

[0286] The device sends the user's input, including the emotion recognition results, to the server, which then receives the necessary information to generate prompts.

[0287] Specific operation: The device sends the data received from the emotion engine to the server's API endpoint.

[0288] Input: Sentiment score and user input text

[0289] Output: HTTP request to the server

[0290] Step 6:

[0291] The server generates a prompt using the persona of a specific manager and the emotion recognition results from the user, for example, "Persona: Manager, interacting with subordinate seeking approval for launching a new business."

[0292] Specific operation: A script on the server combines the persona information template and emotion recognition results to generate prompt text.

[0293] Input: Persona information, emotion recognition results, user input text

[0294] Output: The generated prompt text

[0295] Step 7:

[0296] The server sends the generated prompt to the AI ​​model, asking it to generate a response.

[0297] Specific operation: The server generates an HTTP request and sends prompt data to the OpenAI API.

[0298] Input: Generated prompt text

[0299] Output: The request sent to the OpenAI API

[0300] Step 8:

[0301] The generative AI model generates an appropriate response based on the prompt and sends it back to the server, for example, "These results are very good. Can you also provide a specific budget and timeline?"

[0302] What it does: The generative AI model analyzes the prompt and generates response text based on an algorithm.

[0303] Input: The prompt text sent to the AI ​​model

[0304] Output: The generated response text

[0305] Step 9:

[0306] The server converts the response from the AI ​​model into a user-readable format and sends it to the device.

[0307] Specific operation: The server script converts the response text from the AI ​​into HTML or JSON format and sends it to the terminal.

[0308] Input: Response text from the AI ​​model

[0309] Output: Formatted text data sent to the terminal

[0310] Step 10:

[0311] The terminal receives the response from the server and displays it to the user, for example, "Manager: These results are very good. Could you also provide a specific budget and timeline?"

[0312] Specific behavior: Renders text to the display area on the device's web page or application UI.

[0313] Input: Preformatted text data from the server

[0314] Output: The response text that is displayed to the user

[0315] (Application example 2)

[0316] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0317] When new graduates receive practical training based on actual work scenarios, they are required to be provided with a realistic dialogue experience that reflects emotions. However, conventional simulation systems lack the ability to recognize emotions and reflect them in responses, which means they are unable to provide sufficient dialogue scenarios for trainees. In addition, because the scenarios are fixed, it is difficult for trainees to effectively acquire skills that can be applied to actual work.

[0318] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0319] In this invention, the server includes means for setting a virtual personality of a specific manager, means for receiving user input and generating a prompt based on the virtual personality, means for sending a request to a generative AI model using the prompt and generating a response, means for using an emotion engine to recognize the user's emotions and reflect them in the response, and means for providing the generated response to the user. This allows trainees to receive practical training in realistic dialogue scenarios that reflect emotions.

[0320] "New graduate training" is the initial training that companies and organizations provide to newly hired employees.

[0321] "Practical training" refers to training based on real-world work scenarios, where trainees acquire the skills necessary for their jobs through hands-on experience.

[0322] A "simulation system" is a system that uses a virtual environment to reproduce actual business scenarios and provide training to users.

[0323] The "virtual personality of a specific executive" refers to the character or persona of an executive set up to interact with the user within the simulation.

[0324] A "prompting sentence" is a question or instruction sentence generated based on the user's input, and is linguistic content used to progress the simulation.

[0325] A "generative AI model" is an AI system that generates natural language based on given prompts and instructions.

[0326] An "emotion engine" is a technical means for analyzing a user's input, recognizing their emotional state, and reflecting that state in the system's responses.

[0327] A "response" is a reply or reaction generated by the system in response to input from the user, and reflects the analysis results of the emotion engine.

[0328] A "work scenario" is a simulation scenario that specifically recreates situations or problems that trainees may encounter in a particular work environment.

[0329] The system for carrying out the present invention is a simulation system for effectively carrying out practical training in new graduate training. A specific embodiment of this system will be described below.

[0330] 1. Hardware Configuration

[0331] It requires a server and a terminal. The server has the computing resources to run the generative AI model and emotion engine. The terminal is a device (e.g., PC, tablet, smartphone) that receives input from the user.

[0332] 2. Software Configuration

[0333] Install the following software components on the server:

[0334] Generative artificial intelligence model: Uses OpenAI's API.

[0335] Emotion engine: A library for analyzing user input and recognizing its emotional state. For example, the emotion_recognition module.

[0336] 3. Data processing and calculation

[0337] The server communicates with the generative artificial intelligence model using the OpenAI API key to receive queries from users.

[0338] The emotion engine analyzes the user's input text and recognizes emotional states such as excitement or anxiety.

[0339] The recognized emotion is incorporated into the prompt sentence for the generative AI model along with the user input. For example, the prompt sentence for the virtual personality mentioned above includes the information "User emotion: excitement."

[0340] The server sends a request to the generative artificial intelligence model using the generated prompt sentence and obtains a response.

[0341] 4. Specific Examples

[0342] For example, consider a new graduate training scenario in a factory. If the user types, "The machine has stopped working. What should I do?", the emotion engine recognizes the user's "anxious" state. The server generates a prompt sentence like this:

[0343] Example of a text prompt:

[0344] Persona: Factory Robot: A robot interacting with a new trainee. User Emotion: Anxiety. User Input: My machine has stopped working. What should I do?

[0345] When this prompt is sent to a generative artificial intelligence model, an example response it generates is, "Please stay calm, new trainee. First, check the machine's control panel to see if there are any error messages. If the problem persists, please contact your technician."

[0346] This allows trainees to receive practical training in realistic dialogue scenarios that reflect emotions. The system simulates various work scenarios that trainees will encounter in real life and provides responses that include emotional reactions, providing a more realistic learning experience.

[0347] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0348] Step 1:

[0349] The user inputs an inquiry about the new graduate training scenario through a terminal. The input information is imported into the terminal as text information.

[0350] Input: User text input (e.g., "My machine has stopped working. What should I do?")

[0351] Output: Data containing text information

[0352] Step 2:

[0353] The device sends text information to the server, which receives it and transfers it to the emotion engine.

[0354] Input: Text information (e.g., "My machine has stopped working. What should I do?")

[0355] Output: Text information sent to the emotion engine

[0356] Step 3:

[0357] The server uses an emotion engine to analyze the user's text input and recognize their emotional state. For example, the server obtains the emotion "anxiety" as the analysis result.

[0358] Input: Text information (user query)

[0359] Output: Perceived emotional state (e.g., "anxiety")

[0360] Step 4:

[0361] The server generates a prompt sentence that includes the user's emotional state, combines the virtual personality and the user's query, and prepares to send it to the generative AI model.

[0362] Input: Text information (user query) and emotional state

[0363] Output: Prompt statement (e.g., "Persona: Factory robot: A robot interacting with a new trainee. User emotion: Anxiety. User input: My machine has stopped working. What should I do?")

[0364] Step 5:

[0365] The server sends a prompt to the generative AI model, requesting it to generate a response. The generative AI model generates an appropriate response based on the prompt.

[0366] Input: prompt statement

[0367] Output: The generated response (e.g., "Please stay calm, new trainee. First, check the machine's control panel and see if there are any error messages. If the problem persists, please contact your technician.")

[0368] Step 6:

[0369] The generated response is received by the server and converted into a user-friendly format, for example, sent to the terminal in text format.

[0370] Input: The generated response

[0371] Output: Response data in a format that can be displayed to the user (e.g., "Please stay calm, new trainee. First, check the machine's control panel and see if there are any error messages. If the problem persists, please contact your technician.")

[0372] Step 7:

[0373] The terminal displays the responses received from the server to the user, allowing the user to have an appropriate interactive experience in the simulation scenario.

[0374] Input: Response data sent from the server

[0375] Output: The response message that is displayed to the user (e.g., "Please stay calm, new trainee. First, check the machine's control panel and see if there are any error messages. If the problem persists, please contact your technician.")

[0376] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0377] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0378] In the above embodiment, an example in which the specific process is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0379] [Second embodiment]

[0380] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0381] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0382] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0383] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0384] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0385] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0386] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0387] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0388] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0389] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0390] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0391] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal."

[0392] This invention relates to a simulation system for providing effective practical training to new graduate trainees. The system sets the persona of a specific manager and uses a generative artificial intelligence model to generate appropriate responses based on user input, which are then provided to the user. This system allows trainees to role-play based on a variety of scenarios without the need for an actual manager.

[0393] Example of a system

[0394] server:

[0395] The server sets an OpenAI API key and prepares to communicate with the generative artificial intelligence model (hereafter referred to as the AI ​​model). By default, a persona of a specific role is prepared, and the server is responsible for sending prompts to the AI ​​model and obtaining responses based on this persona.

[0396] Device:

[0397] The user's device acts as an interface to receive and send input from the user to the server. When the user provides input for a simulation scenario, such as seeking approval for a new business venture or preparing for an important meeting, the input is communicated to the server.

[0398] User:

[0399] The user, a new graduate trainee, uses the system to simulate interactions with a manager based on a simulation scenario. For example, the user reports the results of market research to a persona about launching a new business and requests approval for the project.

[0400] System Operation

[0401] 1. The server initializes an OpenAI API key and prepares it for communication with the AI ​​model, allowing it to generate responses based on a specific persona.

[0402] 2. The user inputs the following through the terminal: "After reporting on market research for a new business, we have confirmed that there is greater demand than expected. Would you please give us permission to proceed with this project?" The terminal then sends this input to the server.

[0403] 3. The server uses the persona "Manager: Manager interacting with subordinate seeking approval for launching a new business" and generates a prompt based on the user's input.

[0404] 4. The server sends a request based on this prompt to the AI ​​model, which analyzes the prompt and generates the most appropriate response.

[0405] 5. The server sends the response received from the AI ​​model to the device, for example, "These results are very good. Could you also provide a specific budget and timeline?"

[0406] 6. The terminal displays this response to the user, who can then confirm the response and continue the dialogue.

[0407] Specific examples

[0408] 1. User types, "I've reported on my market research for a new business and found that there is more demand than expected. Do I have permission to move forward with this project?"

[0409] 2. The server receives this input and generates a prompt based on the setting "Persona: Manager: Manager interacting with subordinate seeking approval for launching a new business."

[0410] 3. The server sends the generated prompt to the AI ​​model, which generates a response saying, "These results are very good. Can you also provide a specific budget and timeline?"

[0411] 4. The terminal displays this response to the user, who can then ask further questions or provide further explanations based on the response.

[0412] This system will reduce the burden on managers and other executives and allow trainees to practice in a variety of scenarios, which is expected to improve skills efficiently in a realistic environment.

[0413] The processing flow will be explained below.

[0414] Step 1:

[0415] The server sets up an OpenAI API key and prepares communication with the generative AI model, allowing the system to access the AI ​​model through the API.

[0416] Step 2:

[0417] To start the new graduate training simulation, the user inputs information based on the scenario into the terminal. For example, the user inputs a sentence such as, "After reporting on the market research for a new business, we have found that there is greater demand than expected. May I have your permission to proceed with this project?"

[0418] Step 3:

[0419] The terminal receives user input and transmits the input to the server.

[0420] Step 4:

[0421] The server uses the persona of a specific person (e.g., a manager) to generate a prompt based on user input. For example, the prompt is configured as "Persona: Manager: Manager interacting with subordinate seeking approval for launching a new business."

[0422] Step 5:

[0423] The server sends the generated prompt to the AI ​​model, asking it to generate a response. The prompt includes the persona information and the specific question asked by the user.

[0424] Step 6:

[0425] The generative AI model generates an appropriate response based on the prompt, such as, "These results are very good. Can you also provide a specific budget and timeline?"

[0426] Step 7:

[0427] The server receives the response from the generative AI and converts it into a format that can be read by the user.

[0428] Step 8:

[0429] The server sends the converted response to the terminal, ready to display to the user.

[0430] Step 9:

[0431] The terminal displays the response received from the server to the user, for example, in the form "Manager: These results are very good. Could you also provide a specific budget proposal and timeline?"

[0432] Step 10:

[0433] The user can review the displayed responses and continue the simulation by entering new questions or information as needed. By repeating the process, the user can receive training tailored to real-world business scenarios.

[0434] Example 1

[0435] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0436] Traditional practical training for new graduates requires actual managers, which takes time and money, and places a burden on managers. Also, trainees have limited opportunities to practice in a variety of scenarios, which means the training is not as effective as it could be.

[0437] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0438] In this invention, the server includes means for setting a persona of a specific manager, means for receiving input from a user and transmitting the input from the terminal to the server, means for generating prompts based on the persona, means for using the generated prompts to send requests to a generative artificial intelligence model to generate responses, and means for transmitting the generated responses to the terminal and providing them to the user. This enables trainees to role-play based on a variety of scenarios without the need for an actual manager.

[0439] "New graduate training" is training given to new employees at a company to acquire the knowledge and skills necessary for their work.

[0440] A "simulation system" is a system that simulates and reproduces real-world situations to enable effective learning and training.

[0441] A "persona" is a fictional character created to represent a specific position or situation.

[0442] "User" refers to a person who uses the system and receives training.

[0443] "Input" refers to actions such as questions, requests, and information provided by a user to a system.

[0444] "Terminal" refers to the device used by a user to access the system.

[0445] A "server" refers to a system that receives input from a user and provides computing resources for processing.

[0446] A "prompt" refers to the act of writing a sentence containing instructions or questions to a generative artificial intelligence model to generate an appropriate response, or the sentence itself.

[0447] A "generative artificial intelligence model" refers to an algorithm or program that generates an optimal response based on a given input.

[0448] A "request" refers to a request made by a server to a generative artificial intelligence model to obtain or process information.

[0449] "Response" refers to the answer or result that a generative artificial intelligence model generates based on a request.

[0450] "Business scenario" refers to the content of a simulation created assuming a specific situation or case in business.

[0451] "Exit Condition" refers to a predefined condition for ending a training session.

[0452] This invention relates to a simulation system for providing effective practical training to new graduate trainees. This system creates a persona of a specific manager and uses a generative artificial intelligence model to generate appropriate responses based on user input, which are then provided to the user. This allows trainees to role-play based on a variety of scenarios without the need for an actual manager.

[0453] The server initializes the OpenAI API key and prepares to communicate with the AI ​​model. A specific role persona is prepared as the initial setting, and the server is responsible for sending prompts to the AI ​​model and obtaining responses based on this persona. The server runs on a cloud server such as AWS, GCP, or Azure, and is implemented using programming languages ​​such as Python and JavaScript.

[0454] A terminal is a device through which a user accesses the system, such as a PC, smartphone, or tablet. Operations on the terminal are performed through a web browser or a dedicated application (React, Vue.js, Flask, etc.). The terminal's role is to receive input from the user and send it to the server.

[0455] The user is a new graduate trainee who uses this system to simulate a dialogue with a manager based on a simulation scenario. For example, a scenario is imagined in which the user reports the results of market research to a persona about the launch of a new business and asks for approval for the project. The user inputs information through a terminal and receives responses from the server.

[0456] Specific examples

[0457] Here's an example of how it works:

[0458] 1. The user types into the terminal, "I have reported on the market research for a new business and found that there is more demand than expected. May I have permission to proceed with this project?"

[0459] 2. The device captures this input using JavaScript and sends it to the server using the axios library.

[0460] 3. The server receives this input and generates a prompt based on the persona: "Manager interacting with subordinate seeking approval for launching a new business."

[0461] 4. The server sends the generated prompt to the OpenAI API, where the AI ​​model analyzes the prompt and generates a response like, "These results are very good. Can you also provide a specific budget and timeline?"

[0462] 5. The server receives the response from the AI ​​model and sends it to the device as an HTTP response.

[0463] 6. The terminal displays the received response to the user, who can then ask further questions or continue the discussion based on the displayed response.

[0464] This system reduces the burden on managers and other executives and allows trainees to practice in a variety of scenarios, which is expected to improve skills efficiently in a realistic environment.

[0465] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0466] Step 1:

[0467] The server initializes the OpenAI API key, which prepares and configures the AI ​​model for communication. The server reads the API key and persona configuration from the config.json file and uses the Python requests library to prepare for communication with the OpenAI API. The data in the config.json file is used as input, and the AI ​​model is ready for communication as output.

[0468] Step 2:

[0469] The user types into the terminal, "After reporting on market research for a new business, we have found that there is more demand than expected. May I have permission to proceed with this project?" The input data is information based on the user's scenario. Specifically, it includes the action of entering text into an input form on a web browser. The terminal captures this input and sends it to the server as a POST request using the axios library. The input is the user's text input, and the output generates data that is sent to the server.

[0470] Step 3:

[0471] The server analyzes the input data received from the user and generates a prompt based on the persona. Specifically, the user's input data is stored in variables, and a prompt is created based on the persona set as "Manager: Manager conversing with subordinate seeking approval for launching a new business." As an example, prepare the following prompt: "Persona: Manager. Manager conversing with subordinate seeking approval for launching a new business. The subordinate reports the results of market research for the new business and requests permission to proceed with the project." The input is the user's text data, and the output is a prompt.

[0472] Step 4:

[0473] The server sends the generated prompt to the OpenAI API and receives a response from the AI ​​model. The server uses the requests.post method to send a request containing the prompt and receives the response generated by the AI ​​model. The input is the generated prompt, and the output is the response from the AI ​​model. For example, the response generated might be, "These results are very good. Could you also provide a specific budget and timeline?"

[0474] Step 5:

[0475] The server sends the response received from the AI ​​model to the terminal. The server analyzes the response returned from the AI ​​model and formats it in a format that is easy for the user to read. It then sends it to the terminal as an HTTP response. The response data from the AI ​​model is the input, and the formatted response data is sent to the terminal as the output.

[0476] Step 6:

[0477] The device receives the response from the server and displays it to the user. The device uses JavaScript to receive the response from the server and updates the HTML DOM. The displayed response is "These results are very good. Can you also provide a specific budget and timeline?", and the user can continue the dialogue based on this information. The input is the response data from the server, and the output is the response displayed to the user.

[0478] (Application example 1)

[0479] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0480] While practical training is important for new graduates, conducting real-time training in dialogue with managers and operating factory robots consumes a lot of time and resources. Furthermore, it places a heavy burden on managers, potentially reducing efficiency and resulting in inconsistent training quality. Furthermore, there is a high risk of mistakes when operating factory robots, so a method is needed to enable employees to acquire sufficient skills through simulation before undergoing actual training.

[0481] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0482] In this invention, the server includes a means for setting a persona for a specific manager, a means for receiving user input and generating a prompt based on the persona, a means for sending a request to a generative artificial intelligence model using the prompt to generate a response, a means for providing the generated response to the user, and a means for simulating a specific scenario for factory robot operation training and responding to user operations. This reduces the burden on managers during new graduate training, provides effective practical training, and enables users to safely and practically acquire factory robot operation skills. Furthermore, by supporting a variety of scenarios, the quality and efficiency of training can be improved.

[0483] A "job title persona" is a character that mimics the behavior and thoughts of a person with a specific job title, and is a setting used to simulate human interaction during training for new graduates.

[0484] "User input" refers to information provided in text or voice format, such as instructions or questions given by the trainee to the simulation system through the training terminal.

[0485] A "prompt" is input data sent to a generative artificial intelligence model. It is generated based on user input and persona settings and serves as a guide for the AI ​​to generate a response.

[0486] A "generative artificial intelligence model" is an algorithm or system that learns from large amounts of data and performs advanced text generation in response to input, and is a technology used to generate responses appropriate to user input.

[0487] A "response" is a text message or instruction that is created by a generative artificial intelligence model in response to user input and provided to the user.

[0488] A "factory robot" is a mechanical device used to automate manufacturing operations and is capable of performing a variety of tasks, but requires training to operate it.

[0489] "Operation training" is training to learn how to operate factory robots effectively and safely, and is an educational process to improve actual operating skills through simulation.

[0490] "Simulation" is a virtual training method that mimics real-life situations and work environments, and is a learning technique used to acquire practical skills while minimizing risk.

[0491] This invention is an example of a simulation system for effectively conducting practical training in new graduate training. In particular, a system applicable to training in the operation of factory robots will be described.

[0492] System Overview

[0493] The system consists of a server, a user terminal, and a generative artificial intelligence model.

[0494] Server: Holds OpenAI API keys and configuration information, communicates with AI models, sets personas, generates prompts, and manages user input.

[0495] User terminal: A device used by new operators to input data, typically a tablet or smart glasses.

[0496] Generative artificial intelligence model: An AI model with large-scale text generation capabilities that generates appropriate responses based on user input.

[0497] Basic system operation

[0498] 1. The user starts up the terminal and logs in. A training scenario for operating a factory robot is presented.

[0499] 2. The user enters a specific instruction or question.

[0500] 3. The server receives the user's input and generates a prompt based on the persona.

[0501] 4. The server sends the generated prompt to the AI ​​model.

[0502] 5. The AI ​​model parses the prompt and generates an appropriate response.

[0503] 6. The server receives the generated response and sends it to the user terminal.

[0504] 7. The user confirms the response and continues or asks an additional question or takes an action.

[0505] Program processing and hardware / software configuration

[0506] Hardware: User devices such as tablets and smart glasses, and cloud-based servers.

[0507] Software: Web server using Flask, AI model communication using OpenAI API.

[0508] The server first initializes the OpenAI API key and generates a prompt based on the persona. When the user enters input, the server generates a prompt based on the input and sends it to the AI ​​model. The AI ​​model then analyzes the prompt and generates the optimal response.

[0509] Specific examples

[0510] Examples of prompts:

[0511] User Input: "My robot arm suddenly stopped working. What should I do?"

[0512] Generated prompt:

[0513] "Senior Operator's Manual: Provides operating and troubleshooting instructions.\n\nNew Operator: The robot arm suddenly stopped working. What should I do?\n\nSenior Operator:"

[0514] Generated response:

[0515] "First, make sure your arm's power cable is properly connected. If that's OK, try resetting the software. Here's how to do it..."

[0516] In this way, by using a server and a generative artificial intelligence model, a system is provided that allows new graduate trainees to safely and efficiently learn factory robot operation techniques in a realistic environment.

[0517] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0518] Step 1:

[0519] The user starts up the terminal and logs in. The input is the user ID and password, and the output is a message that the user has successfully logged in to the system. This allows the user to access the training scenario.

[0520] Step 2:

[0521] The server receives login information and authenticates the user. The input is the user ID and password, and the output is the authentication result. If authentication is successful, the user is presented with a specific scenario.

[0522] Step 3:

[0523] The user inputs specific operation instructions and questions based on the factory robot operation training scenario. The inputs are operation instructions and questions, and the outputs are requests to the server.

[0524] Step 4:

[0525] The server receives input from the user and generates a prompt based on the persona. The input is the user's operation instructions or questions, and the output is a prompt. The server generates a prompt based on the persona's configuration information, and uses this prompt in the next step.

[0526] Step 5:

[0527] The server sends the generated prompt to the AI ​​model. The input is the prompt and the output is the response from the AI ​​model. Based on this prompt, the AI ​​model performs data analysis to generate an appropriate response.

[0528] Step 6:

[0529] The AI ​​model analyzes the prompt and generates the optimal response. The input is the prompt and the output is the generated response. The AI ​​model's internal algorithm is used to derive the appropriate response to the user's input.

[0530] Step 7:

[0531] The server receives the generated response and sends it to the user's device. The input is the response from the AI ​​model, and the output is a text message that is presented to the user, allowing the user to see the generated response.

[0532] Step 8:

[0533] The user confirms the presented response and, if necessary, continues or asks an additional question. The input is the user's new operation instruction or question, and the output is another request to the server. This cycle allows for continuous training.

[0534] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0535] This invention combines a simulation system for effective practical training for new graduate trainees with an emotion engine that recognizes the user's emotions. This system allows trainees to have an emotionally rich interactive experience through role-playing based on real business scenarios.

[0536] Example of a system

[0537] server:

[0538] The server sets an OpenAI API key and prepares to communicate with the generative artificial intelligence model (hereafter referred to as the AI ​​model).It also has an emotion engine that recognizes the user's emotions and reflects them in responses.

[0539] Device:

[0540] The device used by the user acts as an interface to receive input from the user and send it to the server. When the user provides input for a simulation scenario, such as requesting approval for a new business or preparing for an important meeting, this input is transmitted to the server via the emotion engine.

[0541] User:

[0542] The user, a new graduate trainee, uses the system to simulate interactions with a manager based on a simulation scenario. For example, the user reports the results of market research to a persona about launching a new business and requests approval for the project.

[0543] System Operation

[0544] 1. The server initializes the OpenAI API key and prepares to communicate with the AI ​​model. The emotion engine is also initialized at the same time. This allows the system to access the AI ​​model through the API and process the user's emotion information.

[0545] 2. The user inputs the following through the device: "After reporting on market research for a new business, we have found that there is greater demand than expected. Would you please give us permission to proceed with this project?" The device then sends this input to the emotion engine.

[0546] 3. The emotion engine analyzes user input and extracts emotional states. For example, text analysis can recognize emotions such as "excitement" or "fear."

[0547] 4. The device sends the user input, including the emotion recognition results, to the server.

[0548] 5. The server generates prompts that reflect the emotion recognition results using the persona of a specific person in a certain position (e.g., a manager). For example, in addition to the setting of "Persona: Manager: Manager interacting with a subordinate seeking approval for the launch of a new business," the server configures the prompts by taking into account the user's "excitement" state.

[0549] 6. The server sends the generated prompt to the AI ​​model, asking it to generate a response. The prompt includes the persona information, the specific question from the user, and the emotion recognition results.

[0550] 7. The generative AI model generates an appropriate response based on the prompt, such as "These results are very good. Can you also provide a specific budget and timeline?", and adapts the tone and expression to reflect the user's level of excitement.

[0551] 8. The server receives the response from the generative AI and converts it into a format that can be read by the user.

[0552] 9. The server sends the converted response to the terminal, ready to display to the user.

[0553] 10. The device displays the response received from the server to the user, for example, "Manager: These results are very good. Could you also provide a specific budget and timeline?", reflecting the user's sentiment.

[0554] Specific examples

[0555] 1. User types, "I've reported on my market research for a new business and found that there is more demand than expected. Do I have permission to move forward with this project?"

[0556] 2. The emotion engine analyzes this input and recognizes the user's "excited" state.

[0557] 3. The server receives this and generates a prompt based on the setting "Persona: Manager: Manager interacting with subordinate seeking approval for launching a new business." The prompt reflects the emotion of "excitement."

[0558] 4. Based on the prompt, the generative AI model generates a response like, "These results are very good. Can you also provide a specific budget and timeline?"

[0559] 5. The device displays this response to the user: "Manager: These results are very good. Can you also provide a specific budget and timeline?"

[0560] This system reduces the burden on managers and other executives, and allows trainees to practice in a variety of scenarios. The introduction of an emotion engine allows users to enjoy a more realistic dialogue experience, improving their skills in an environment that is closer to the real work environment.

[0561] The processing flow will be explained below.

[0562] Step 1:

[0563] The server sets the OpenAI API key and prepares for communication with the generative AI model. It also initializes the emotion engine and prepares for emotion analysis.

[0564] Step 2:

[0565] The user inputs information to start the simulation through the terminal. For example, the user might input, "After reporting on the market research for a new business, we have found that there is greater demand than expected. May I have your permission to proceed with this project?"

[0566] Step 3:

[0567] The device receives user input and first sends it to the emotion engine, which analyzes the user's input text and recognizes the user's emotional state (e.g., "excited" or "tense").

[0568] Step 4:

[0569] The emotion engine returns the analysis results to the terminal and sends the input, including the user's emotional state, to the server.

[0570] Step 5:

[0571] The server uses the persona of a specific person (e.g., a manager) to generate prompts based on user input. For example, in addition to the setting "Persona: Manager: Manager interacting with subordinate seeking approval for launching a new business," the server configures the prompt taking into account the user's "excitement" state.

[0572] Step 6:

[0573] The server sends the generated prompt and emotion recognition results to the AI ​​model, asking it to generate a response. The prompt includes persona information, a specific question from the user, and the emotion recognition results.

[0574] Step 7:

[0575] The generative AI model generates an appropriate response based on the prompt, such as "These results are very good. Can you also provide a specific budget and timeline?", reflecting the user's level of excitement in tone and expression.

[0576] Step 8:

[0577] The server receives the response from the generative AI and converts it into a format that can be read by the user.

[0578] Step 9:

[0579] The server sends the converted response to the terminal, ready to display to the user.

[0580] Step 10:

[0581] The terminal displays the response received from the server to the user, for example, "Manager: These results are very good. Could you also provide a specific budget proposal and timeline?", reflecting the user's feelings.

[0582] Step 11:

[0583] The user can review the displayed responses and continue the simulation by entering new questions or information as needed. By repeating this process, the user can receive advanced training that is tailored to real-world business scenarios.

[0584] Example 2

[0585] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0586] Conventional practical training systems for new graduates are unable to generate responses that take into account the user's emotions, making it difficult to provide the emotionally rich dialogue experience required in actual business scenarios. In addition, the simple persona settings of executives lack the precision required to obtain a realistic dialogue experience, limiting the effectiveness of the training.

[0587] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for receiving a user's input and analyzing the emotional state through an emotion engine, means for setting a persona of a specific manager, means for generating a prompt based on the persona taking the emotional state into consideration, means for sending a request to a generative AI model using the prompt to generate a response, and means for providing the generated response to the user. This enables a realistic dialogue experience that takes the user's emotions into consideration, allowing trainees to receive effective training in an environment that is close to actual work.

[0588] The "means for receiving user input and analyzing the emotional state through an emotion engine" is a device or program for receiving text entered by a user into a terminal and transmitting it to an emotion engine to extract emotional information.

[0589] A "means for setting the persona of a specific manager" is a device or program for specifically setting the personality and position of a manager used in practical training during new graduate training.

[0590] The "means for generating a prompt based on the persona while taking into account the emotional state" is a device or program that creates a prompt that reflects the user's emotional state based on set persona information.

[0591] "Means for sending a request to a generative artificial intelligence model using the prompt and generating a response" refers to a device or program that sends the generated prompt to an AI model and generates a response in response.

[0592] The "means for providing the generated response to the user" refers to a device or program that converts the generated response into a format that can be confirmed by the user and displays it through a terminal.

[0593] A "generative artificial intelligence model" is a type of artificial intelligence that generates human-like responses based on user-provided prompts.

[0594] A "persona" is a virtual character that defines the personality, position, and role of a specific person or character.

[0595] An "emotion engine" is software or algorithm that analyzes a user's text input and extracts the emotions contained therein.

[0596] This invention combines an emotion engine that recognizes user emotions in a simulation system for practical training for new graduate trainees. The system is designed to enable users to have an emotionally rich dialogue experience based on business scenarios through persona setting for executives, prompt generation, and a generative AI model.

[0597] Hardware and software used

[0598] The following hardware and software are used to implement this system.

[0599] Server: A server with high-performance computing power

[0600] Terminal: A computer or mobile device for receiving user input.

[0601] Emotion engine: Software that recognizes emotions through text analysis (e.g., Microsoft Azure Sentiment Analysis and IBM Watson Tone Analyzer)

[0602] Generative artificial intelligence model: An AI model that processes natural language (e.g., "OpenAI GPT-3")

[0603] Communication interface: API communication via the internet

[0604] Overall system flow

[0605] 1. The server first sets the OpenAI API key and prepares to communicate with the AI ​​model. It also initializes the emotion engine, which completes preparations for API communication and emotion analysis.

[0606] 2. The user inputs scenario information into the terminal and sends it. For example, the user might input a sentence like, "After reporting on market research for a new business, we have found that there is greater demand than expected. May I have your permission to proceed with this project?"

[0607] 3. The device sends the input data from the user to the emotion engine, allowing the emotion engine to analyze the data.

[0608] 4. The emotion engine analyzes the user's input and extracts the emotional state (e.g., "excited," "fear," etc.). The analysis result is encoded and sent back to the device.

[0609] 5. The device sends the user's input, including the emotion recognition results, to the server.

[0610] 6. The server generates a prompt using the persona of the specified manager and the user's emotion recognition results. For example, it generates a prompt with the content "Persona: Manager, interacting with subordinate seeking approval for launching a new business."

[0611] 7. The server sends the generated prompt to the AI ​​model, asking it to generate a response.

[0612] 8. The generative AI model generates an appropriate response based on the prompt and sends it back to the server, for example, "These results are very good. Can you also provide a specific budget and timeline?"

[0613] 9. The server converts the received response into a user-readable format and sends it to the terminal.

[0614] 10. The terminal displays the response from the server to the user, for example, "Manager: These results are very good. Could you also provide a specific budget and timeline?"

[0615] Specific examples

[0616] For example, a new graduate trainee might input, "I reported on the market research for a new business and found that there is greater demand than expected. Can I have your permission to proceed with this project?" This input is analyzed through an emotion engine, which recognizes the "excited" state. The server then generates a prompt based on the setting "Persona: Manager interacting with subordinate seeking approval for launching a new business." The generative AI model then generates an appropriate response, such as, "These results are very good. Could you also provide a specific budget proposal and timeline?" This response is finally displayed on the user's device, providing the new graduate with a realistic dialogue experience.

[0617] By using this system in this way, new graduate trainees can practice in a variety of scenarios, reducing the burden on specific managers while allowing trainees to improve their skills through emotionally rich dialogue.

[0618] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0619] Step 1:

[0620] The server initializes the OpenAI API key and prepares to communicate with the AI ​​model. The emotion engine is also initialized at the same time, allowing the system to access the AI ​​model through the API and process the user's emotion information.

[0621] Specific operation: Enter the OpenAI API key in the server's configuration file and call the initialization method of the emotion engine (e.g., "Microsoft Azure Sentiment Analysis" or "IBM Watson Tone Analyzer").

[0622] Input: Basic configuration information to boot the system

[0623] Output: API communication and emotion engine initialization complete

[0624] Step 2:

[0625] The user inputs scenario information through the terminal and clicks the send button on the terminal. For example, the user can input a sentence such as, "After reporting on market research for a new business, we have found that there is greater demand than expected. May I have your permission to proceed with this project?"

[0626] Specific behavior: The user enters text into the input field on the terminal and clicks the send button.

[0627] Input: Text entered by the user

[0628] Output: Send button click event on the device

[0629] Step 3:

[0630] The device sends input data from the user to the emotion engine, which uses the data for emotion analysis.

[0631] Specific operation: An HTTP request is generated on the terminal side and the user's input text is sent to the emotion engine's API endpoint.

[0632] Input: User-entered text

[0633] Output: Text data sent to the emotion engine API

[0634] Step 4:

[0635] The emotion engine analyzes the user's input and extracts the emotional state (e.g., "excited," "fear," etc.), which is then encoded and sent back to the device.

[0636] What it does: Analyzes text using the sentiment engine API and generates a sentiment score.

[0637] Input: Text data sent to the emotion engine

[0638] Output: Emotion score (user's emotional state)

[0639] Step 5:

[0640] The device sends the user's input, including the emotion recognition results, to the server, which then receives the necessary information to generate prompts.

[0641] Specific operation: The device sends the data received from the emotion engine to the server's API endpoint.

[0642] Input: Sentiment score and user input text

[0643] Output: HTTP request to the server

[0644] Step 6:

[0645] The server generates a prompt using the persona of a specific manager and the emotion recognition results from the user, for example, "Persona: Manager, interacting with subordinate seeking approval for launching a new business."

[0646] Specific operation: A script on the server combines the persona information template and emotion recognition results to generate prompt text.

[0647] Input: Persona information, emotion recognition results, user input text

[0648] Output: The generated prompt text

[0649] Step 7:

[0650] The server sends the generated prompt to the AI ​​model, asking it to generate a response.

[0651] Specific operation: The server generates an HTTP request and sends prompt data to the OpenAI API.

[0652] Input: Generated prompt text

[0653] Output: The request sent to the OpenAI API

[0654] Step 8:

[0655] The generative AI model generates an appropriate response based on the prompt and sends it back to the server, for example, "These results are very good. Can you also provide a specific budget and timeline?"

[0656] What it does: The generative AI model analyzes the prompt and generates response text based on an algorithm.

[0657] Input: The prompt text sent to the AI ​​model

[0658] Output: The generated response text

[0659] Step 9:

[0660] The server converts the response from the AI ​​model into a user-readable format and sends it to the device.

[0661] Specific operation: The server script converts the response text from the AI ​​into HTML or JSON format and sends it to the terminal.

[0662] Input: Response text from the AI ​​model

[0663] Output: Formatted text data sent to the terminal

[0664] Step 10:

[0665] The terminal receives the response from the server and displays it to the user, for example, "Manager: These results are very good. Could you also provide a specific budget and timeline?"

[0666] Specific behavior: Renders text to the display area on the device's web page or application UI.

[0667] Input: Preformatted text data from the server

[0668] Output: The response text that is displayed to the user

[0669] (Application example 2)

[0670] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0671] When new graduates receive practical training based on actual work scenarios, they are required to be provided with a realistic dialogue experience that reflects emotions. However, conventional simulation systems lack the ability to recognize emotions and reflect them in responses, which means they are unable to provide sufficient dialogue scenarios for trainees. In addition, because the scenarios are fixed, it is difficult for trainees to effectively acquire skills that can be applied to actual work.

[0672] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0673] In this invention, the server includes means for setting a virtual personality of a specific manager, means for receiving user input and generating a prompt based on the virtual personality, means for sending a request to a generative AI model using the prompt and generating a response, means for using an emotion engine to recognize the user's emotions and reflect them in the response, and means for providing the generated response to the user. This allows trainees to receive practical training in realistic dialogue scenarios that reflect emotions.

[0674] "New graduate training" is the initial training that companies and organizations provide to newly hired employees.

[0675] "Practical training" refers to training based on real-world work scenarios, where trainees acquire the skills necessary for their jobs through hands-on experience.

[0676] A "simulation system" is a system that uses a virtual environment to reproduce actual business scenarios and provide training to users.

[0677] The "virtual personality of a specific executive" refers to the character or persona of an executive set up to interact with the user within the simulation.

[0678] A "prompting sentence" is a question or instruction sentence generated based on the user's input, and is linguistic content used to progress the simulation.

[0679] A "generative AI model" is an AI system that generates natural language based on given prompts and instructions.

[0680] An "emotion engine" is a technical means for analyzing a user's input, recognizing their emotional state, and reflecting that state in the system's responses.

[0681] A "response" is a reply or reaction generated by the system in response to input from the user, and reflects the analysis results of the emotion engine.

[0682] A "work scenario" is a simulation scenario that specifically recreates situations or problems that trainees may encounter in a particular work environment.

[0683] The system for carrying out the present invention is a simulation system for effectively carrying out practical training in new graduate training. A specific embodiment of this system will be described below.

[0684] 1. Hardware Configuration

[0685] It requires a server and a terminal. The server has the computing resources to run the generative AI model and emotion engine. The terminal is a device (e.g., PC, tablet, smartphone) that receives input from the user.

[0686] 2. Software Configuration

[0687] Install the following software components on the server:

[0688] Generative artificial intelligence model: Uses OpenAI's API.

[0689] Emotion engine: A library for analyzing user input and recognizing its emotional state. For example, the emotion_recognition module.

[0690] 3. Data processing and calculation

[0691] The server communicates with the generative artificial intelligence model using the OpenAI API key to receive queries from users.

[0692] The emotion engine analyzes the user's input text and recognizes emotional states such as excitement or anxiety.

[0693] The recognized emotion is incorporated into the prompt sentence for the generative AI model along with the user input. For example, the prompt sentence for the virtual personality mentioned above includes the information "User emotion: excitement."

[0694] The server sends a request to the generative artificial intelligence model using the generated prompt sentence and obtains a response.

[0695] 4. Specific Examples

[0696] For example, consider a new graduate training scenario in a factory. If the user types, "The machine has stopped working. What should I do?", the emotion engine recognizes the user's "anxious" state. The server generates a prompt sentence like this:

[0697] Example of a text prompt:

[0698] Persona: Factory Robot: A robot interacting with a new trainee. User Emotion: Anxiety. User Input: My machine has stopped working. What should I do?

[0699] When this prompt is sent to a generative artificial intelligence model, an example response it generates is, "Please stay calm, new trainee. First, check the machine's control panel to see if there are any error messages. If the problem persists, please contact your technician."

[0700] This allows trainees to receive practical training in realistic dialogue scenarios that reflect emotions. The system simulates various work scenarios that trainees will encounter in real life and provides responses that include emotional reactions, providing a more realistic learning experience.

[0701] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0702] Step 1:

[0703] The user inputs an inquiry about the new graduate training scenario through a terminal. The input information is imported into the terminal as text information.

[0704] Input: User text input (e.g., "My machine has stopped working. What should I do?")

[0705] Output: Data containing text information

[0706] Step 2:

[0707] The device sends text information to the server, which receives it and transfers it to the emotion engine.

[0708] Input: Text information (e.g., "My machine has stopped working. What should I do?")

[0709] Output: Text information sent to the emotion engine

[0710] Step 3:

[0711] The server uses an emotion engine to analyze the user's text input and recognize their emotional state. For example, the server obtains the emotion "anxiety" as the analysis result.

[0712] Input: Text information (user query)

[0713] Output: Perceived emotional state (e.g., "anxiety")

[0714] Step 4:

[0715] The server generates a prompt sentence that includes the user's emotional state, combines the virtual personality and the user's query, and prepares to send it to the generative AI model.

[0716] Input: Text information (user query) and emotional state

[0717] Output: Prompt statement (e.g., "Persona: Factory robot: A robot interacting with a new trainee. User emotion: Anxiety. User input: My machine has stopped working. What should I do?")

[0718] Step 5:

[0719] The server sends a prompt to the generative AI model, requesting it to generate a response. The generative AI model generates an appropriate response based on the prompt.

[0720] Input: prompt statement

[0721] Output: The generated response (e.g., "Please stay calm, new trainee. First, check the machine's control panel and see if there are any error messages. If the problem persists, please contact your technician.")

[0722] Step 6:

[0723] The generated response is received by the server and converted into a user-friendly format, for example, sent to the terminal in text format.

[0724] Input: The generated response

[0725] Output: Response data in a format that can be displayed to the user (e.g., "Please stay calm, new trainee. First, check the machine's control panel and see if there are any error messages. If the problem persists, please contact your technician.")

[0726] Step 7:

[0727] The terminal displays the responses received from the server to the user, allowing the user to have an appropriate interactive experience in the simulation scenario.

[0728] Input: Response data sent from the server

[0729] Output: The response message that is displayed to the user (e.g., "Please stay calm, new trainee. First, check the machine's control panel and see if there are any error messages. If the problem persists, please contact your technician.")

[0730] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0731] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0732] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the smart glasses 214.

[0733] [Third embodiment]

[0734] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0735] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0736] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0737] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0738] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0739] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0740] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0741] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0742] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0743] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0744] In the headset type terminal 314, a reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0745] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the headset type terminal 314 will be referred to as the "terminal."

[0746] This invention relates to a simulation system for providing effective practical training to new graduate trainees. The system sets the persona of a specific manager and uses a generative artificial intelligence model to generate appropriate responses based on user input, which are then provided to the user. This system allows trainees to role-play based on a variety of scenarios without the need for an actual manager.

[0747] Example of a system

[0748] server:

[0749] The server sets an OpenAI API key and prepares to communicate with the generative artificial intelligence model (hereafter referred to as the AI ​​model). By default, a persona of a specific role is prepared, and the server is responsible for sending prompts to the AI ​​model and obtaining responses based on this persona.

[0750] Device:

[0751] The user's device acts as an interface to receive and send input from the user to the server. When the user provides input for a simulation scenario, such as seeking approval for a new business venture or preparing for an important meeting, the input is communicated to the server.

[0752] User:

[0753] The user, a new graduate trainee, uses the system to simulate interactions with a manager based on a simulation scenario. For example, the user reports the results of market research to a persona about launching a new business and requests approval for the project.

[0754] System Operation

[0755] 1. The server initializes an OpenAI API key and prepares it for communication with the AI ​​model, allowing it to generate responses based on a specific persona.

[0756] 2. The user inputs the following through the terminal: "After reporting on market research for a new business, we have confirmed that there is greater demand than expected. Would you please give us permission to proceed with this project?" The terminal then sends this input to the server.

[0757] 3. The server uses the persona "Manager: Manager interacting with subordinate seeking approval for launching a new business" and generates a prompt based on the user's input.

[0758] 4. The server sends a request based on this prompt to the AI ​​model, which analyzes the prompt and generates the most appropriate response.

[0759] 5. The server sends the response received from the AI ​​model to the device, for example, "These results are very good. Could you also provide a specific budget and timeline?"

[0760] 6. The terminal displays this response to the user, who can then confirm the response and continue the dialogue.

[0761] Specific examples

[0762] 1. User types, "I've reported on my market research for a new business and found that there is more demand than expected. Do I have permission to move forward with this project?"

[0763] 2. The server receives this input and generates a prompt based on the setting "Persona: Manager: Manager interacting with subordinate seeking approval for launching a new business."

[0764] 3. The server sends the generated prompt to the AI ​​model, which generates a response saying, "These results are very good. Can you also provide a specific budget and timeline?"

[0765] 4. The terminal displays this response to the user, who can then ask further questions or provide further explanations based on the response.

[0766] This system will reduce the burden on managers and other executives and allow trainees to practice in a variety of scenarios, which is expected to improve skills efficiently in a realistic environment.

[0767] The processing flow will be explained below.

[0768] Step 1:

[0769] The server sets up an OpenAI API key and prepares communication with the generative AI model, allowing the system to access the AI ​​model through the API.

[0770] Step 2:

[0771] To start the new graduate training simulation, the user inputs information based on the scenario into the terminal. For example, the user inputs a sentence such as, "After reporting on the market research for a new business, we have found that there is greater demand than expected. May I have your permission to proceed with this project?"

[0772] Step 3:

[0773] The terminal receives user input and transmits the input to the server.

[0774] Step 4:

[0775] The server uses the persona of a specific person (e.g., a manager) to generate a prompt based on user input. For example, the prompt is configured as "Persona: Manager: Manager interacting with subordinate seeking approval for launching a new business."

[0776] Step 5:

[0777] The server sends the generated prompt to the AI ​​model, asking it to generate a response. The prompt includes the persona information and the specific question asked by the user.

[0778] Step 6:

[0779] The generative AI model generates an appropriate response based on the prompt, such as, "These results are very good. Can you also provide a specific budget and timeline?"

[0780] Step 7:

[0781] The server receives the response from the generative AI and converts it into a format that can be read by the user.

[0782] Step 8:

[0783] The server sends the converted response to the terminal, ready to display to the user.

[0784] Step 9:

[0785] The terminal displays the response received from the server to the user, for example, in the form "Manager: These results are very good. Could you also provide a specific budget proposal and timeline?"

[0786] Step 10:

[0787] The user can review the displayed responses and continue the simulation by entering new questions or information as needed. By repeating the process, the user can receive training tailored to real-world business scenarios.

[0788] Example 1

[0789] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0790] Traditional practical training for new graduates requires actual managers, which takes time and money, and places a burden on managers. Also, trainees have limited opportunities to practice in a variety of scenarios, which means the training is not as effective as it could be.

[0791] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0792] In this invention, the server includes means for setting a persona of a specific manager, means for receiving input from a user and transmitting the input from the terminal to the server, means for generating prompts based on the persona, means for using the generated prompts to send requests to a generative artificial intelligence model to generate responses, and means for transmitting the generated responses to the terminal and providing them to the user. This enables trainees to role-play based on a variety of scenarios without the need for an actual manager.

[0793] "New graduate training" is training given to new employees at a company to acquire the knowledge and skills necessary for their work.

[0794] A "simulation system" is a system that simulates and reproduces real-world situations to enable effective learning and training.

[0795] A "persona" is a fictional character created to represent a specific position or situation.

[0796] "User" refers to a person who uses the system and receives training.

[0797] "Input" refers to actions such as questions, requests, and information provided by a user to a system.

[0798] "Terminal" refers to the device used by a user to access the system.

[0799] A "server" refers to a system that receives input from a user and provides computing resources for processing.

[0800] A "prompt" refers to the act of writing a sentence containing instructions or questions to a generative artificial intelligence model to generate an appropriate response, or the sentence itself.

[0801] A "generative artificial intelligence model" refers to an algorithm or program that generates an optimal response based on a given input.

[0802] A "request" refers to a request made by a server to a generative artificial intelligence model to obtain or process information.

[0803] "Response" refers to the answer or result that a generative artificial intelligence model generates based on a request.

[0804] "Business scenario" refers to the content of a simulation created assuming a specific situation or case in business.

[0805] "Exit Condition" refers to a predefined condition for ending a training session.

[0806] This invention relates to a simulation system for providing effective practical training to new graduate trainees. This system creates a persona of a specific manager and uses a generative artificial intelligence model to generate appropriate responses based on user input, which are then provided to the user. This allows trainees to role-play based on a variety of scenarios without the need for an actual manager.

[0807] The server initializes the OpenAI API key and prepares to communicate with the AI ​​model. A specific role persona is prepared as the initial setting, and the server is responsible for sending prompts to the AI ​​model and obtaining responses based on this persona. The server runs on a cloud server such as AWS, GCP, or Azure, and is implemented using programming languages ​​such as Python and JavaScript.

[0808] A terminal is a device through which a user accesses the system, such as a PC, smartphone, or tablet. Operations on the terminal are performed through a web browser or a dedicated application (React, Vue.js, Flask, etc.). The terminal's role is to receive input from the user and send it to the server.

[0809] The user is a new graduate trainee who uses this system to simulate a dialogue with a manager based on a simulation scenario. For example, a scenario is imagined in which the user reports the results of market research to a persona about the launch of a new business and asks for approval for the project. The user inputs information through a terminal and receives responses from the server.

[0810] Specific examples

[0811] Here's an example of how it works:

[0812] 1. The user types into the terminal, "I have reported on the market research for a new business and found that there is more demand than expected. May I have permission to proceed with this project?"

[0813] 2. The device captures this input using JavaScript and sends it to the server using the axios library.

[0814] 3. The server receives this input and generates a prompt based on the persona: "Manager interacting with subordinate seeking approval for launching a new business."

[0815] 4. The server sends the generated prompt to the OpenAI API, where the AI ​​model analyzes the prompt and generates a response like, "These results are very good. Can you also provide a specific budget and timeline?"

[0816] 5. The server receives the response from the AI ​​model and sends it to the device as an HTTP response.

[0817] 6. The terminal displays the received response to the user, who can then ask further questions or continue the discussion based on the displayed response.

[0818] This system reduces the burden on managers and other executives and allows trainees to practice in a variety of scenarios, which is expected to improve skills efficiently in a realistic environment.

[0819] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0820] Step 1:

[0821] The server initializes the OpenAI API key, which prepares and configures the AI ​​model for communication. The server reads the API key and persona configuration from the config.json file and uses the Python requests library to prepare for communication with the OpenAI API. The data in the config.json file is used as input, and the AI ​​model is ready for communication as output.

[0822] Step 2:

[0823] The user types into the terminal, "After reporting on market research for a new business, we have found that there is more demand than expected. May I have permission to proceed with this project?" The input data is information based on the user's scenario. Specifically, it includes the action of entering text into an input form on a web browser. The terminal captures this input and sends it to the server as a POST request using the axios library. The input is the user's text input, and the output generates data that is sent to the server.

[0824] Step 3:

[0825] The server analyzes the input data received from the user and generates a prompt based on the persona. Specifically, the user's input data is stored in variables, and a prompt is created based on the persona set as "Manager: Manager conversing with subordinate seeking approval for launching a new business." As an example, prepare the following prompt: "Persona: Manager. Manager conversing with subordinate seeking approval for launching a new business. The subordinate reports the results of market research for the new business and requests permission to proceed with the project." The input is the user's text data, and the output is a prompt.

[0826] Step 4:

[0827] The server sends the generated prompt to the OpenAI API and receives a response from the AI ​​model. The server uses the requests.post method to send a request containing the prompt and receives the response generated by the AI ​​model. The input is the generated prompt, and the output is the response from the AI ​​model. For example, the response generated might be, "These results are very good. Could you also provide a specific budget and timeline?"

[0828] Step 5:

[0829] The server sends the response received from the AI ​​model to the terminal. The server analyzes the response returned from the AI ​​model and formats it in a format that is easy for the user to read. It then sends it to the terminal as an HTTP response. The response data from the AI ​​model is the input, and the formatted response data is sent to the terminal as the output.

[0830] Step 6:

[0831] The device receives the response from the server and displays it to the user. The device uses JavaScript to receive the response from the server and updates the HTML DOM. The displayed response is "These results are very good. Can you also provide a specific budget and timeline?", and the user can continue the dialogue based on this information. The input is the response data from the server, and the output is the response displayed to the user.

[0832] (Application example 1)

[0833] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0834] While practical training is important for new graduates, conducting real-time training in dialogue with managers and operating factory robots consumes a lot of time and resources. Furthermore, it places a heavy burden on managers, potentially reducing efficiency and resulting in inconsistent training quality. Furthermore, there is a high risk of mistakes when operating factory robots, so a method is needed to enable employees to acquire sufficient skills through simulation before undergoing actual training.

[0835] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0836] In this invention, the server includes a means for setting a persona for a specific manager, a means for receiving user input and generating a prompt based on the persona, a means for sending a request to a generative artificial intelligence model using the prompt to generate a response, a means for providing the generated response to the user, and a means for simulating a specific scenario for factory robot operation training and responding to user operations. This reduces the burden on managers during new graduate training, provides effective practical training, and enables users to safely and practically acquire factory robot operation skills. Furthermore, by supporting a variety of scenarios, the quality and efficiency of training can be improved.

[0837] A "job title persona" is a character that mimics the behavior and thoughts of a person with a specific job title, and is a setting used to simulate human interaction during training for new graduates.

[0838] "User input" refers to information provided in text or voice format, such as instructions or questions given by the trainee to the simulation system through the training terminal.

[0839] A "prompt" is input data sent to a generative artificial intelligence model. It is generated based on user input and persona settings and serves as a guide for the AI ​​to generate a response.

[0840] A "generative artificial intelligence model" is an algorithm or system that learns from large amounts of data and performs advanced text generation in response to input, and is a technology used to generate responses appropriate to user input.

[0841] A "response" is a text message or instruction that is created by a generative artificial intelligence model in response to user input and provided to the user.

[0842] A "factory robot" is a mechanical device used to automate manufacturing operations and is capable of performing a variety of tasks, but requires training to operate it.

[0843] "Operation training" is training to learn how to operate factory robots effectively and safely, and is an educational process to improve actual operating skills through simulation.

[0844] "Simulation" is a virtual training method that mimics real-life situations and work environments, and is a learning technique used to acquire practical skills while minimizing risk.

[0845] This invention is an example of a simulation system for effectively conducting practical training in new graduate training. In particular, a system applicable to training in the operation of factory robots will be described.

[0846] System Overview

[0847] The system consists of a server, a user terminal, and a generative artificial intelligence model.

[0848] Server: Holds OpenAI API keys and configuration information, communicates with AI models, sets personas, generates prompts, and manages user input.

[0849] User terminal: A device used by new operators to input data, typically a tablet or smart glasses.

[0850] Generative artificial intelligence model: An AI model with large-scale text generation capabilities that generates appropriate responses based on user input.

[0851] Basic system operation

[0852] 1. The user starts up the terminal and logs in. A training scenario for operating a factory robot is presented.

[0853] 2. The user enters a specific instruction or question.

[0854] 3. The server receives the user's input and generates a prompt based on the persona.

[0855] 4. The server sends the generated prompt to the AI ​​model.

[0856] 5. The AI ​​model parses the prompt and generates an appropriate response.

[0857] 6. The server receives the generated response and sends it to the user terminal.

[0858] 7. The user confirms the response and continues or asks an additional question or takes an action.

[0859] Program processing and hardware / software configuration

[0860] Hardware: User devices such as tablets and smart glasses, and cloud-based servers.

[0861] Software: Web server using Flask, AI model communication using OpenAI API.

[0862] The server first initializes the OpenAI API key and generates a prompt based on the persona. When the user enters input, the server generates a prompt based on the input and sends it to the AI ​​model. The AI ​​model then analyzes the prompt and generates the optimal response.

[0863] Specific examples

[0864] Examples of prompts:

[0865] User Input: "My robot arm suddenly stopped working. What should I do?"

[0866] Generated prompt:

[0867] "Senior Operator's Manual: Provides operating and troubleshooting instructions.\n\nNew Operator: The robot arm suddenly stopped working. What should I do?\n\nSenior Operator:"

[0868] Generated response:

[0869] "First, make sure your arm's power cable is properly connected. If that's OK, try resetting the software. Here's how to do it..."

[0870] In this way, by using a server and a generative artificial intelligence model, a system is provided that allows new graduate trainees to safely and efficiently learn factory robot operation techniques in a realistic environment.

[0871] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0872] Step 1:

[0873] The user starts up the terminal and logs in. The input is the user ID and password, and the output is a message that the user has successfully logged in to the system. This allows the user to access the training scenario.

[0874] Step 2:

[0875] The server receives login information and authenticates the user. The input is the user ID and password, and the output is the authentication result. If authentication is successful, the user is presented with a specific scenario.

[0876] Step 3:

[0877] The user inputs specific operation instructions and questions based on the factory robot operation training scenario. The inputs are operation instructions and questions, and the outputs are requests to the server.

[0878] Step 4:

[0879] The server receives input from the user and generates a prompt based on the persona. The input is the user's operation instructions or questions, and the output is a prompt. The server generates a prompt based on the persona's configuration information, and uses this prompt in the next step.

[0880] Step 5:

[0881] The server sends the generated prompt to the AI ​​model. The input is the prompt and the output is the response from the AI ​​model. Based on this prompt, the AI ​​model performs data analysis to generate an appropriate response.

[0882] Step 6:

[0883] The AI ​​model analyzes the prompt and generates the optimal response. The input is the prompt and the output is the generated response. The AI ​​model's internal algorithm is used to derive the appropriate response to the user's input.

[0884] Step 7:

[0885] The server receives the generated response and sends it to the user's device. The input is the response from the AI ​​model, and the output is a text message that is presented to the user, allowing the user to see the generated response.

[0886] Step 8:

[0887] The user confirms the presented response and, if necessary, continues or asks an additional question. The input is the user's new operation instruction or question, and the output is another request to the server. This cycle allows for continuous training.

[0888] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0889] This invention combines a simulation system for effective practical training for new graduate trainees with an emotion engine that recognizes the user's emotions. This system allows trainees to have an emotionally rich interactive experience through role-playing based on real business scenarios.

[0890] Example of a system

[0891] server:

[0892] The server sets an OpenAI API key and prepares to communicate with the generative artificial intelligence model (hereafter referred to as the AI ​​model).It also has an emotion engine that recognizes the user's emotions and reflects them in responses.

[0893] Device:

[0894] The device used by the user acts as an interface to receive input from the user and send it to the server. When the user provides input for a simulation scenario, such as requesting approval for a new business or preparing for an important meeting, this input is transmitted to the server via the emotion engine.

[0895] User:

[0896] The user, a new graduate trainee, uses the system to simulate interactions with a manager based on a simulation scenario. For example, the user reports the results of market research to a persona about launching a new business and requests approval for the project.

[0897] System Operation

[0898] 1. The server initializes the OpenAI API key and prepares to communicate with the AI ​​model. The emotion engine is also initialized at the same time. This allows the system to access the AI ​​model through the API and process the user's emotion information.

[0899] 2. The user inputs the following through the device: "After reporting on market research for a new business, we have found that there is greater demand than expected. Would you please give us permission to proceed with this project?" The device then sends this input to the emotion engine.

[0900] 3. The emotion engine analyzes user input and extracts emotional states. For example, text analysis can recognize emotions such as "excitement" or "fear."

[0901] 4. The device sends the user input, including the emotion recognition results, to the server.

[0902] 5. The server generates prompts that reflect the emotion recognition results using the persona of a specific person in a certain position (e.g., a manager). For example, in addition to the setting of "Persona: Manager: Manager interacting with a subordinate seeking approval for the launch of a new business," the server configures the prompts by taking into account the user's "excitement" state.

[0903] 6. The server sends the generated prompt to the AI ​​model, asking it to generate a response. The prompt includes the persona information, the specific question from the user, and the emotion recognition results.

[0904] 7. The generative AI model generates an appropriate response based on the prompt, such as "These results are very good. Can you also provide a specific budget and timeline?", and adapts the tone and expression to reflect the user's level of excitement.

[0905] 8. The server receives the response from the generative AI and converts it into a format that can be read by the user.

[0906] 9. The server sends the converted response to the terminal, ready to display to the user.

[0907] 10. The device displays the response received from the server to the user, for example, "Manager: These results are very good. Could you also provide a specific budget and timeline?", reflecting the user's sentiment.

[0908] Specific examples

[0909] 1. User types, "I've reported on my market research for a new business and found that there is more demand than expected. Do I have permission to move forward with this project?"

[0910] 2. The emotion engine analyzes this input and recognizes the user's "excited" state.

[0911] 3. The server receives this and generates a prompt based on the setting "Persona: Manager: Manager interacting with subordinate seeking approval for launching a new business." The prompt reflects the emotion of "excitement."

[0912] 4. Based on the prompt, the generative AI model generates a response like, "These results are very good. Can you also provide a specific budget and timeline?"

[0913] 5. The device displays this response to the user: "Manager: These results are very good. Can you also provide a specific budget and timeline?"

[0914] This system reduces the burden on managers and other executives, and allows trainees to practice in a variety of scenarios. The introduction of an emotion engine allows users to enjoy a more realistic dialogue experience, improving their skills in an environment that is closer to the real work environment.

[0915] The processing flow will be explained below.

[0916] Step 1:

[0917] The server sets the OpenAI API key and prepares for communication with the generative AI model. It also initializes the emotion engine and prepares for emotion analysis.

[0918] Step 2:

[0919] The user inputs information to start the simulation through the terminal. For example, the user might input, "After reporting on the market research for a new business, we have found that there is greater demand than expected. May I have your permission to proceed with this project?"

[0920] Step 3:

[0921] The device receives user input and first sends it to the emotion engine, which analyzes the user's input text and recognizes the user's emotional state (e.g., "excited" or "tense").

[0922] Step 4:

[0923] The emotion engine returns the analysis results to the terminal and sends the input, including the user's emotional state, to the server.

[0924] Step 5:

[0925] The server uses the persona of a specific person (e.g., a manager) to generate prompts based on user input. For example, in addition to the setting "Persona: Manager: Manager interacting with subordinate seeking approval for launching a new business," the server configures the prompt taking into account the user's "excitement" state.

[0926] Step 6:

[0927] The server sends the generated prompt and emotion recognition results to the AI ​​model, asking it to generate a response. The prompt includes persona information, a specific question from the user, and the emotion recognition results.

[0928] Step 7:

[0929] The generative AI model generates an appropriate response based on the prompt, such as "These results are very good. Can you also provide a specific budget and timeline?", reflecting the user's level of excitement in tone and expression.

[0930] Step 8:

[0931] The server receives the response from the generative AI and converts it into a format that can be read by the user.

[0932] Step 9:

[0933] The server sends the converted response to the terminal, ready to display to the user.

[0934] Step 10:

[0935] The terminal displays the response received from the server to the user, for example, "Manager: These results are very good. Could you also provide a specific budget proposal and timeline?", reflecting the user's feelings.

[0936] Step 11:

[0937] The user can review the displayed responses and continue the simulation by entering new questions or information as needed. By repeating this process, the user can receive advanced training that is tailored to real-world business scenarios.

[0938] Example 2

[0939] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0940] Conventional practical training systems for new graduates are unable to generate responses that take into account the user's emotions, making it difficult to provide the emotionally rich dialogue experience required in actual business scenarios. In addition, the simple persona settings of executives lack the precision required to obtain a realistic dialogue experience, limiting the effectiveness of the training.

[0941] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for receiving a user's input and analyzing the emotional state through an emotion engine, means for setting a persona of a specific manager, means for generating a prompt based on the persona taking the emotional state into consideration, means for sending a request to a generative AI model using the prompt to generate a response, and means for providing the generated response to the user. This enables a realistic dialogue experience that takes the user's emotions into consideration, allowing trainees to receive effective training in an environment that is close to actual work.

[0942] The "means for receiving user input and analyzing the emotional state through an emotion engine" is a device or program for receiving text entered by a user into a terminal and transmitting it to an emotion engine to extract emotional information.

[0943] A "means for setting the persona of a specific manager" is a device or program for specifically setting the personality and position of a manager used in practical training during new graduate training.

[0944] The "means for generating a prompt based on the persona while taking into account the emotional state" is a device or program that creates a prompt that reflects the user's emotional state based on set persona information.

[0945] "Means for sending a request to a generative artificial intelligence model using the prompt and generating a response" refers to a device or program that sends the generated prompt to an AI model and generates a response in response.

[0946] The "means for providing the generated response to the user" refers to a device or program that converts the generated response into a format that can be confirmed by the user and displays it through a terminal.

[0947] A "generative artificial intelligence model" is a type of artificial intelligence that generates human-like responses based on user-provided prompts.

[0948] A "persona" is a virtual character that defines the personality, position, and role of a specific person or character.

[0949] An "emotion engine" is software or algorithm that analyzes a user's text input and extracts the emotions contained therein.

[0950] This invention combines an emotion engine that recognizes user emotions in a simulation system for practical training for new graduate trainees. The system is designed to enable users to have an emotionally rich dialogue experience based on business scenarios through persona setting for executives, prompt generation, and a generative AI model.

[0951] Hardware and software used

[0952] The following hardware and software are used to implement this system.

[0953] Server: A server with high-performance computing power

[0954] Terminal: A computer or mobile device for receiving user input.

[0955] Emotion engine: Software that recognizes emotions through text analysis (e.g., Microsoft Azure Sentiment Analysis and IBM Watson Tone Analyzer)

[0956] Generative artificial intelligence model: An AI model that processes natural language (e.g., "OpenAI GPT-3")

[0957] Communication interface: API communication via the internet

[0958] Overall system flow

[0959] 1. The server first sets the OpenAI API key and prepares to communicate with the AI ​​model. It also initializes the emotion engine, which completes preparations for API communication and emotion analysis.

[0960] 2. The user inputs scenario information into the terminal and sends it. For example, the user might input a sentence like, "After reporting on market research for a new business, we have found that there is greater demand than expected. May I have your permission to proceed with this project?"

[0961] 3. The device sends the input data from the user to the emotion engine, allowing the emotion engine to analyze the data.

[0962] 4. The emotion engine analyzes the user's input and extracts the emotional state (e.g., "excited," "fear," etc.). The analysis result is encoded and sent back to the device.

[0963] 5. The device sends the user's input, including the emotion recognition results, to the server.

[0964] 6. The server generates a prompt using the persona of the specified manager and the user's emotion recognition results. For example, it generates a prompt with the content "Persona: Manager, interacting with subordinate seeking approval for launching a new business."

[0965] 7. The server sends the generated prompt to the AI ​​model, asking it to generate a response.

[0966] 8. The generative AI model generates an appropriate response based on the prompt and sends it back to the server, for example, "These results are very good. Can you also provide a specific budget and timeline?"

[0967] 9. The server converts the received response into a user-readable format and sends it to the terminal.

[0968] 10. The terminal displays the response from the server to the user, for example, "Manager: These results are very good. Could you also provide a specific budget and timeline?"

[0969] Specific examples

[0970] For example, a new graduate trainee might input, "I reported on the market research for a new business and found that there is greater demand than expected. Can I have your permission to proceed with this project?" This input is analyzed through an emotion engine, which recognizes the "excited" state. The server then generates a prompt based on the setting "Persona: Manager interacting with subordinate seeking approval for launching a new business." The generative AI model then generates an appropriate response, such as, "These results are very good. Could you also provide a specific budget proposal and timeline?" This response is finally displayed on the user's device, providing the new graduate with a realistic dialogue experience.

[0971] By using this system in this way, new graduate trainees can practice in a variety of scenarios, reducing the burden on specific managers while allowing trainees to improve their skills through emotionally rich dialogue.

[0972] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0973] Step 1:

[0974] The server initializes the OpenAI API key and prepares to communicate with the AI ​​model. The emotion engine is also initialized at the same time, allowing the system to access the AI ​​model through the API and process the user's emotion information.

[0975] Specific operation: Enter the OpenAI API key in the server's configuration file and call the initialization method of the emotion engine (e.g., "Microsoft Azure Sentiment Analysis" or "IBM Watson Tone Analyzer").

[0976] Input: Basic configuration information to boot the system

[0977] Output: API communication and emotion engine initialization complete

[0978] Step 2:

[0979] The user inputs scenario information through the terminal and clicks the send button on the terminal. For example, the user can input a sentence such as, "After reporting on market research for a new business, we have found that there is greater demand than expected. May I have your permission to proceed with this project?"

[0980] Specific behavior: The user enters text into the input field on the terminal and clicks the send button.

[0981] Input: Text entered by the user

[0982] Output: Send button click event on the device

[0983] Step 3:

[0984] The device sends input data from the user to the emotion engine, which uses the data for emotion analysis.

[0985] Specific operation: An HTTP request is generated on the terminal side and the user's input text is sent to the emotion engine's API endpoint.

[0986] Input: User-entered text

[0987] Output: Text data sent to the emotion engine API

[0988] Step 4:

[0989] The emotion engine analyzes the user's input and extracts the emotional state (e.g., "excited," "fear," etc.), which is then encoded and sent back to the device.

[0990] What it does: Analyzes text using the sentiment engine API and generates a sentiment score.

[0991] Input: Text data sent to the emotion engine

[0992] Output: Emotion score (user's emotional state)

[0993] Step 5:

[0994] The device sends the user's input, including the emotion recognition results, to the server, which then receives the necessary information to generate prompts.

[0995] Specific operation: The device sends the data received from the emotion engine to the server's API endpoint.

[0996] Input: Sentiment score and user input text

[0997] Output: HTTP request to the server

[0998] Step 6:

[0999] The server generates a prompt using the persona of a specific manager and the emotion recognition results from the user, for example, "Persona: Manager, interacting with subordinate seeking approval for launching a new business."

[1000] Specific operation: A script on the server combines the persona information template and emotion recognition results to generate prompt text.

[1001] Input: Persona information, emotion recognition results, user input text

[1002] Output: The generated prompt text

[1003] Step 7:

[1004] The server sends the generated prompt to the AI ​​model, asking it to generate a response.

[1005] Specific operation: The server generates an HTTP request and sends prompt data to the OpenAI API.

[1006] Input: Generated prompt text

[1007] Output: The request sent to the OpenAI API

[1008] Step 8:

[1009] The generative AI model generates an appropriate response based on the prompt and sends it back to the server, for example, "These results are very good. Can you also provide a specific budget and timeline?"

[1010] What it does: The generative AI model analyzes the prompt and generates response text based on an algorithm.

[1011] Input: The prompt text sent to the AI ​​model

[1012] Output: The generated response text

[1013] Step 9:

[1014] The server converts the response from the AI ​​model into a user-readable format and sends it to the device.

[1015] Specific operation: The server script converts the response text from the AI ​​into HTML or JSON format and sends it to the terminal.

[1016] Input: Response text from the AI ​​model

[1017] Output: Formatted text data sent to the terminal

[1018] Step 10:

[1019] The terminal receives the response from the server and displays it to the user, for example, "Manager: These results are very good. Could you also provide a specific budget and timeline?"

[1020] Specific behavior: Renders text to the display area on the device's web page or application UI.

[1021] Input: Preformatted text data from the server

[1022] Output: The response text that is displayed to the user

[1023] (Application example 2)

[1024] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1025] When new graduates receive practical training based on actual work scenarios, they are required to be provided with a realistic dialogue experience that reflects emotions. However, conventional simulation systems lack the ability to recognize emotions and reflect them in responses, which means they are unable to provide sufficient dialogue scenarios for trainees. In addition, because the scenarios are fixed, it is difficult for trainees to effectively acquire skills that can be applied to actual work.

[1026] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1027] In this invention, the server includes means for setting a virtual personality of a specific manager, means for receiving user input and generating a prompt based on the virtual personality, means for sending a request to a generative AI model using the prompt and generating a response, means for using an emotion engine to recognize the user's emotions and reflect them in the response, and means for providing the generated response to the user. This allows trainees to receive practical training in realistic dialogue scenarios that reflect emotions.

[1028] "New graduate training" is the initial training that companies and organizations provide to newly hired employees.

[1029] "Practical training" refers to training based on real-world work scenarios, where trainees acquire the skills necessary for their jobs through hands-on experience.

[1030] A "simulation system" is a system that uses a virtual environment to reproduce actual business scenarios and provide training to users.

[1031] The "virtual personality of a specific executive" refers to the character or persona of an executive set up to interact with the user within the simulation.

[1032] A "prompting sentence" is a question or instruction sentence generated based on the user's input, and is linguistic content used to progress the simulation.

[1033] A "generative AI model" is an AI system that generates natural language based on given prompts and instructions.

[1034] An "emotion engine" is a technical means for analyzing a user's input, recognizing their emotional state, and reflecting that state in the system's responses.

[1035] A "response" is a reply or reaction generated by the system in response to input from the user, and reflects the analysis results of the emotion engine.

[1036] A "work scenario" is a simulation scenario that specifically recreates situations or problems that trainees may encounter in a particular work environment.

[1037] The system for carrying out the present invention is a simulation system for effectively carrying out practical training in new graduate training. A specific embodiment of this system will be described below.

[1038] 1. Hardware Configuration

[1039] It requires a server and a terminal. The server has the computing resources to run the generative AI model and emotion engine. The terminal is a device (e.g., PC, tablet, smartphone) that receives input from the user.

[1040] 2. Software Configuration

[1041] Install the following software components on the server:

[1042] Generative artificial intelligence model: Uses OpenAI's API.

[1043] Emotion engine: A library for analyzing user input and recognizing its emotional state. For example, the emotion_recognition module.

[1044] 3. Data processing and calculation

[1045] The server communicates with the generative artificial intelligence model using the OpenAI API key to receive queries from users.

[1046] The emotion engine analyzes the user's input text and recognizes emotional states such as excitement or anxiety.

[1047] The recognized emotion is incorporated into the prompt sentence for the generative AI model along with the user input. For example, the prompt sentence for the virtual personality mentioned above includes the information "User emotion: excitement."

[1048] The server sends a request to the generative artificial intelligence model using the generated prompt sentence and obtains a response.

[1049] 4. Specific Examples

[1050] For example, consider a new graduate training scenario in a factory. If the user types, "The machine has stopped working. What should I do?", the emotion engine recognizes the user's "anxious" state. The server generates a prompt sentence like this:

[1051] Example of a text prompt:

[1052] Persona: Factory Robot: A robot interacting with a new trainee. User Emotion: Anxiety. User Input: My machine has stopped working. What should I do?

[1053] When this prompt is sent to a generative artificial intelligence model, an example response it generates is, "Please stay calm, new trainee. First, check the machine's control panel to see if there are any error messages. If the problem persists, please contact your technician."

[1054] This allows trainees to receive practical training in realistic dialogue scenarios that reflect emotions. The system simulates various work scenarios that trainees will encounter in real life and provides responses that include emotional reactions, providing a more realistic learning experience.

[1055] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1056] Step 1:

[1057] The user inputs an inquiry about the new graduate training scenario through a terminal. The input information is imported into the terminal as text information.

[1058] Input: User text input (e.g., "My machine has stopped working. What should I do?")

[1059] Output: Data containing text information

[1060] Step 2:

[1061] The device sends text information to the server, which receives it and transfers it to the emotion engine.

[1062] Input: Text information (e.g., "My machine has stopped working. What should I do?")

[1063] Output: Text information sent to the emotion engine

[1064] Step 3:

[1065] The server uses an emotion engine to analyze the user's text input and recognize their emotional state. For example, the server obtains the emotion "anxiety" as the analysis result.

[1066] Input: Text information (user query)

[1067] Output: Perceived emotional state (e.g., "anxiety")

[1068] Step 4:

[1069] The server generates a prompt sentence that includes the user's emotional state, combines the virtual personality and the user's query, and prepares to send it to the generative AI model.

[1070] Input: Text information (user query) and emotional state

[1071] Output: Prompt statement (e.g., "Persona: Factory robot: A robot interacting with a new trainee. User emotion: Anxiety. User input: My machine has stopped working. What should I do?")

[1072] Step 5:

[1073] The server sends a prompt to the generative AI model, requesting it to generate a response. The generative AI model generates an appropriate response based on the prompt.

[1074] Input: prompt statement

[1075] Output: The generated response (e.g., "Please stay calm, new trainee. First, check the machine's control panel and see if there are any error messages. If the problem persists, please contact your technician.")

[1076] Step 6:

[1077] The generated response is received by the server and converted into a user-friendly format, for example, sent to the terminal in text format.

[1078] Input: The generated response

[1079] Output: Response data in a format that can be displayed to the user (e.g., "Please stay calm, new trainee. First, check the machine's control panel and see if there are any error messages. If the problem persists, please contact your technician.")

[1080] Step 7:

[1081] The terminal displays the responses received from the server to the user, allowing the user to have an appropriate interactive experience in the simulation scenario.

[1082] Input: Response data sent from the server

[1083] Output: The response message that is displayed to the user (e.g., "Please stay calm, new trainee. First, check the machine's control panel and see if there are any error messages. If the problem persists, please contact your technician.")

[1084] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[1085] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1086] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314.

[1087] [Fourth embodiment]

[1088] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1089] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[1090] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1091] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[1092] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[1093] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[1094] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1095] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[1096] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1097] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[1098] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1099] In the robot 414, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1100] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1101] This invention relates to a simulation system for providing effective practical training to new graduate trainees. The system sets the persona of a specific manager and uses a generative artificial intelligence model to generate appropriate responses based on user input, which are then provided to the user. This system allows trainees to role-play based on a variety of scenarios without the need for an actual manager.

[1102] Example of a system

[1103] server:

[1104] The server sets an OpenAI API key and prepares to communicate with the generative artificial intelligence model (hereafter referred to as the AI ​​model). By default, a persona of a specific role is prepared, and the server is responsible for sending prompts to the AI ​​model and obtaining responses based on this persona.

[1105] Device:

[1106] The user's device acts as an interface to receive and send input from the user to the server. When the user provides input for a simulation scenario, such as seeking approval for a new business venture or preparing for an important meeting, the input is communicated to the server.

[1107] User:

[1108] The user, a new graduate trainee, uses the system to simulate interactions with a manager based on a simulation scenario. For example, the user reports the results of market research to a persona about launching a new business and requests approval for the project.

[1109] System Operation

[1110] 1. The server initializes an OpenAI API key and prepares it for communication with the AI ​​model, allowing it to generate responses based on a specific persona.

[1111] 2. The user inputs the following through the terminal: "After reporting on market research for a new business, we have confirmed that there is greater demand than expected. Would you please give us permission to proceed with this project?" The terminal then sends this input to the server.

[1112] 3. The server uses the persona "Manager: Manager interacting with subordinate seeking approval for launching a new business" and generates a prompt based on the user's input.

[1113] 4. The server sends a request based on this prompt to the AI ​​model, which analyzes the prompt and generates the most appropriate response.

[1114] 5. The server sends the response received from the AI ​​model to the device, for example, "These results are very good. Could you also provide a specific budget and timeline?"

[1115] 6. The terminal displays this response to the user, who can then confirm the response and continue the dialogue.

[1116] Specific examples

[1117] 1. User types, "I've reported on my market research for a new business and found that there is more demand than expected. Do I have permission to move forward with this project?"

[1118] 2. The server receives this input and generates a prompt based on the setting "Persona: Manager: Manager interacting with subordinate seeking approval for launching a new business."

[1119] 3. The server sends the generated prompt to the AI ​​model, which generates a response saying, "These results are very good. Can you also provide a specific budget and timeline?"

[1120] 4. The terminal displays this response to the user, who can then ask further questions or provide further explanations based on the response.

[1121] This system will reduce the burden on managers and other executives and allow trainees to practice in a variety of scenarios, which is expected to improve skills efficiently in a realistic environment.

[1122] The processing flow will be explained below.

[1123] Step 1:

[1124] The server sets up an OpenAI API key and prepares communication with the generative AI model, allowing the system to access the AI ​​model through the API.

[1125] Step 2:

[1126] To start the new graduate training simulation, the user inputs information based on the scenario into the terminal. For example, the user inputs a sentence such as, "After reporting on the market research for a new business, we have found that there is greater demand than expected. May I have your permission to proceed with this project?"

[1127] Step 3:

[1128] The terminal receives user input and transmits the input to the server.

[1129] Step 4:

[1130] The server uses the persona of a specific person (e.g., a manager) to generate a prompt based on user input. For example, the prompt is configured as "Persona: Manager: Manager interacting with subordinate seeking approval for launching a new business."

[1131] Step 5:

[1132] The server sends the generated prompt to the AI ​​model, asking it to generate a response. The prompt includes the persona information and the specific question asked by the user.

[1133] Step 6:

[1134] The generative AI model generates an appropriate response based on the prompt, such as, "These results are very good. Can you also provide a specific budget and timeline?"

[1135] Step 7:

[1136] The server receives the response from the generative AI and converts it into a format that can be read by the user.

[1137] Step 8:

[1138] The server sends the converted response to the terminal, ready to display to the user.

[1139] Step 9:

[1140] The terminal displays the response received from the server to the user, for example, in the form "Manager: These results are very good. Could you also provide a specific budget proposal and timeline?"

[1141] Step 10:

[1142] The user can review the displayed responses and continue the simulation by entering new questions or information as needed. By repeating the process, the user can receive training tailored to real-world business scenarios.

[1143] Example 1

[1144] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1145] Traditional practical training for new graduates requires actual managers, which takes time and money, and places a burden on managers. Also, trainees have limited opportunities to practice in a variety of scenarios, which means the training is not as effective as it could be.

[1146] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1147] In this invention, the server includes means for setting a persona of a specific manager, means for receiving input from a user and transmitting the input from the terminal to the server, means for generating prompts based on the persona, means for using the generated prompts to send requests to a generative artificial intelligence model to generate responses, and means for transmitting the generated responses to the terminal and providing them to the user. This enables trainees to role-play based on a variety of scenarios without the need for an actual manager.

[1148] "New graduate training" is training given to new employees at a company to acquire the knowledge and skills necessary for their work.

[1149] A "simulation system" is a system that simulates and reproduces real-world situations to enable effective learning and training.

[1150] A "persona" is a fictional character created to represent a specific position or situation.

[1151] "User" refers to a person who uses the system and receives training.

[1152] "Input" refers to actions such as questions, requests, and information provided by a user to a system.

[1153] "Terminal" refers to the device used by a user to access the system.

[1154] A "server" refers to a system that receives input from a user and provides computing resources for processing.

[1155] A "prompt" refers to the act of writing a sentence containing instructions or questions to a generative artificial intelligence model to generate an appropriate response, or the sentence itself.

[1156] A "generative artificial intelligence model" refers to an algorithm or program that generates an optimal response based on a given input.

[1157] A "request" refers to a request made by a server to a generative artificial intelligence model to obtain or process information.

[1158] "Response" refers to the answer or result that a generative artificial intelligence model generates based on a request.

[1159] "Business scenario" refers to the content of a simulation created assuming a specific situation or case in business.

[1160] "Exit Condition" refers to a predefined condition for ending a training session.

[1161] This invention relates to a simulation system for providing effective practical training to new graduate trainees. This system creates a persona of a specific manager and uses a generative artificial intelligence model to generate appropriate responses based on user input, which are then provided to the user. This allows trainees to role-play based on a variety of scenarios without the need for an actual manager.

[1162] The server initializes the OpenAI API key and prepares to communicate with the AI ​​model. A specific role persona is prepared as the initial setting, and the server is responsible for sending prompts to the AI ​​model and obtaining responses based on this persona. The server runs on a cloud server such as AWS, GCP, or Azure, and is implemented using programming languages ​​such as Python and JavaScript.

[1163] A terminal is a device through which a user accesses the system, such as a PC, smartphone, or tablet. Operations on the terminal are performed through a web browser or a dedicated application (React, Vue.js, Flask, etc.). The terminal's role is to receive input from the user and send it to the server.

[1164] The user is a new graduate trainee who uses this system to simulate a dialogue with a manager based on a simulation scenario. For example, a scenario is imagined in which the user reports the results of market research to a persona about the launch of a new business and asks for approval for the project. The user inputs information through a terminal and receives responses from the server.

[1165] Specific examples

[1166] Here's an example of how it works:

[1167] 1. The user types into the terminal, "I have reported on the market research for a new business and found that there is more demand than expected. May I have permission to proceed with this project?"

[1168] 2. The device captures this input using JavaScript and sends it to the server using the axios library.

[1169] 3. The server receives this input and generates a prompt based on the persona: "Manager interacting with subordinate seeking approval for launching a new business."

[1170] 4. The server sends the generated prompt to the OpenAI API, where the AI ​​model analyzes the prompt and generates a response like, "These results are very good. Can you also provide a specific budget and timeline?"

[1171] 5. The server receives the response from the AI ​​model and sends it to the device as an HTTP response.

[1172] 6. The terminal displays the received response to the user, who can then ask further questions or continue the discussion based on the displayed response.

[1173] This system reduces the burden on managers and other executives and allows trainees to practice in a variety of scenarios, which is expected to improve skills efficiently in a realistic environment.

[1174] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1175] Step 1:

[1176] The server initializes the OpenAI API key, which prepares and configures the AI ​​model for communication. The server reads the API key and persona configuration from the config.json file and uses the Python requests library to prepare for communication with the OpenAI API. The data in the config.json file is used as input, and the AI ​​model is ready for communication as output.

[1177] Step 2:

[1178] The user types into the terminal, "After reporting on market research for a new business, we have found that there is more demand than expected. May I have permission to proceed with this project?" The input data is information based on the user's scenario. Specifically, it includes the action of entering text into an input form on a web browser. The terminal captures this input and sends it to the server as a POST request using the axios library. The input is the user's text input, and the output generates data that is sent to the server.

[1179] Step 3:

[1180] The server analyzes the input data received from the user and generates a prompt based on the persona. Specifically, the user's input data is stored in variables, and a prompt is created based on the persona set as "Manager: Manager conversing with subordinate seeking approval for launching a new business." As an example, prepare the following prompt: "Persona: Manager. Manager conversing with subordinate seeking approval for launching a new business. The subordinate reports the results of market research for the new business and requests permission to proceed with the project." The input is the user's text data, and the output is a prompt.

[1181] Step 4:

[1182] The server sends the generated prompt to the OpenAI API and receives a response from the AI ​​model. The server uses the requests.post method to send a request containing the prompt and receives the response generated by the AI ​​model. The input is the generated prompt, and the output is the response from the AI ​​model. For example, the response generated might be, "These results are very good. Could you also provide a specific budget and timeline?"

[1183] Step 5:

[1184] The server sends the response received from the AI ​​model to the terminal. The server analyzes the response returned from the AI ​​model and formats it in a format that is easy for the user to read. It then sends it to the terminal as an HTTP response. The response data from the AI ​​model is the input, and the formatted response data is sent to the terminal as the output.

[1185] Step 6:

[1186] The device receives the response from the server and displays it to the user. The device uses JavaScript to receive the response from the server and updates the HTML DOM. The displayed response is "These results are very good. Can you also provide a specific budget and timeline?", and the user can continue the dialogue based on this information. The input is the response data from the server, and the output is the response displayed to the user.

[1187] (Application example 1)

[1188] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1189] While practical training is important for new graduates, conducting real-time training in dialogue with managers and operating factory robots consumes a lot of time and resources. Furthermore, it places a heavy burden on managers, potentially reducing efficiency and resulting in inconsistent training quality. Furthermore, there is a high risk of mistakes when operating factory robots, so a method is needed to enable employees to acquire sufficient skills through simulation before undergoing actual training.

[1190] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1191] In this invention, the server includes a means for setting a persona for a specific manager, a means for receiving user input and generating a prompt based on the persona, a means for sending a request to a generative artificial intelligence model using the prompt to generate a response, a means for providing the generated response to the user, and a means for simulating a specific scenario for factory robot operation training and responding to user operations. This reduces the burden on managers during new graduate training, provides effective practical training, and enables users to safely and practically acquire factory robot operation skills. Furthermore, by supporting a variety of scenarios, the quality and efficiency of training can be improved.

[1192] A "job title persona" is a character that mimics the behavior and thoughts of a person with a specific job title, and is a setting used to simulate human interaction during training for new graduates.

[1193] "User input" refers to information provided in text or voice format, such as instructions or questions given by the trainee to the simulation system through the training terminal.

[1194] A "prompt" is input data sent to a generative artificial intelligence model. It is generated based on user input and persona settings and serves as a guide for the AI ​​to generate a response.

[1195] A "generative artificial intelligence model" is an algorithm or system that learns from large amounts of data and performs advanced text generation in response to input, and is a technology used to generate responses appropriate to user input.

[1196] A "response" is a text message or instruction that is created by a generative artificial intelligence model in response to user input and provided to the user.

[1197] A "factory robot" is a mechanical device used to automate manufacturing operations and is capable of performing a variety of tasks, but requires training to operate it.

[1198] "Operation training" is training to learn how to operate factory robots effectively and safely, and is an educational process to improve actual operating skills through simulation.

[1199] "Simulation" is a virtual training method that mimics real-life situations and work environments, and is a learning technique used to acquire practical skills while minimizing risk.

[1200] This invention is an example of a simulation system for effectively conducting practical training in new graduate training. In particular, a system applicable to training in the operation of factory robots will be described.

[1201] System Overview

[1202] The system consists of a server, a user terminal, and a generative artificial intelligence model.

[1203] Server: Holds OpenAI API keys and configuration information, communicates with AI models, sets personas, generates prompts, and manages user input.

[1204] User terminal: A device used by new operators to input data, typically a tablet or smart glasses.

[1205] Generative artificial intelligence model: An AI model with large-scale text generation capabilities that generates appropriate responses based on user input.

[1206] Basic system operation

[1207] 1. The user starts up the terminal and logs in. A training scenario for operating a factory robot is presented.

[1208] 2. The user enters a specific instruction or question.

[1209] 3. The server receives the user's input and generates a prompt based on the persona.

[1210] 4. The server sends the generated prompt to the AI ​​model.

[1211] 5. The AI ​​model parses the prompt and generates an appropriate response.

[1212] 6. The server receives the generated response and sends it to the user terminal.

[1213] 7. The user confirms the response and continues or asks an additional question or takes an action.

[1214] Program processing and hardware / software configuration

[1215] Hardware: User devices such as tablets and smart glasses, and cloud-based servers.

[1216] Software: Web server using Flask, AI model communication using OpenAI API.

[1217] The server first initializes the OpenAI API key and generates a prompt based on the persona. When the user enters input, the server generates a prompt based on the input and sends it to the AI ​​model. The AI ​​model then analyzes the prompt and generates the optimal response.

[1218] Specific examples

[1219] Examples of prompts:

[1220] User Input: "My robot arm suddenly stopped working. What should I do?"

[1221] Generated prompt:

[1222] "Senior Operator's Manual: Provides operating and troubleshooting instructions.\n\nNew Operator: The robot arm suddenly stopped working. What should I do?\n\nSenior Operator:"

[1223] Generated response:

[1224] "First, make sure your arm's power cable is properly connected. If that's OK, try resetting the software. Here's how to do it..."

[1225] In this way, by using a server and a generative artificial intelligence model, a system is provided that allows new graduate trainees to safely and efficiently learn factory robot operation techniques in a realistic environment.

[1226] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1227] Step 1:

[1228] The user starts up the terminal and logs in. The input is the user ID and password, and the output is a message that the user has successfully logged in to the system. This allows the user to access the training scenario.

[1229] Step 2:

[1230] The server receives login information and authenticates the user. The input is the user ID and password, and the output is the authentication result. If authentication is successful, the user is presented with a specific scenario.

[1231] Step 3:

[1232] The user inputs specific operation instructions and questions based on the factory robot operation training scenario. The inputs are operation instructions and questions, and the outputs are requests to the server.

[1233] Step 4:

[1234] The server receives input from the user and generates a prompt based on the persona. The input is the user's operation instructions or questions, and the output is a prompt. The server generates a prompt based on the persona's configuration information, and uses this prompt in the next step.

[1235] Step 5:

[1236] The server sends the generated prompt to the AI ​​model. The input is the prompt and the output is the response from the AI ​​model. Based on this prompt, the AI ​​model performs data analysis to generate an appropriate response.

[1237] Step 6:

[1238] The AI ​​model analyzes the prompt and generates the optimal response. The input is the prompt and the output is the generated response. The AI ​​model's internal algorithm is used to derive the appropriate response to the user's input.

[1239] Step 7:

[1240] The server receives the generated response and sends it to the user's device. The input is the response from the AI ​​model, and the output is a text message that is presented to the user, allowing the user to see the generated response.

[1241] Step 8:

[1242] The user confirms the presented response and, if necessary, continues or asks an additional question. The input is the user's new operation instruction or question, and the output is another request to the server. This cycle allows for continuous training.

[1243] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1244] This invention combines a simulation system for effective practical training for new graduate trainees with an emotion engine that recognizes the user's emotions. This system allows trainees to have an emotionally rich interactive experience through role-playing based on real business scenarios.

[1245] Example of a system

[1246] server:

[1247] The server sets an OpenAI API key and prepares to communicate with the generative artificial intelligence model (hereafter referred to as the AI ​​model).It also has an emotion engine that recognizes the user's emotions and reflects them in responses.

[1248] Device:

[1249] The device used by the user acts as an interface to receive input from the user and send it to the server. When the user provides input for a simulation scenario, such as requesting approval for a new business or preparing for an important meeting, this input is transmitted to the server via the emotion engine.

[1250] User:

[1251] The user, a new graduate trainee, uses the system to simulate interactions with a manager based on a simulation scenario. For example, the user reports the results of market research to a persona about launching a new business and requests approval for the project.

[1252] System Operation

[1253] 1. The server initializes the OpenAI API key and prepares to communicate with the AI ​​model. The emotion engine is also initialized at the same time. This allows the system to access the AI ​​model through the API and process the user's emotion information.

[1254] 2. The user inputs the following through the device: "After reporting on market research for a new business, we have found that there is greater demand than expected. Would you please give us permission to proceed with this project?" The device then sends this input to the emotion engine.

[1255] 3. The emotion engine analyzes user input and extracts emotional states. For example, text analysis can recognize emotions such as "excitement" or "fear."

[1256] 4. The device sends the user input, including the emotion recognition results, to the server.

[1257] 5. The server generates prompts that reflect the emotion recognition results using the persona of a specific person in a certain position (e.g., a manager). For example, in addition to the setting of "Persona: Manager: Manager interacting with a subordinate seeking approval for the launch of a new business," the server configures the prompts by taking into account the user's "excitement" state.

[1258] 6. The server sends the generated prompt to the AI ​​model, asking it to generate a response. The prompt includes the persona information, the specific question from the user, and the emotion recognition results.

[1259] 7. The generative AI model generates an appropriate response based on the prompt, such as "These results are very good. Can you also provide a specific budget and timeline?", and adapts the tone and expression to reflect the user's level of excitement.

[1260] 8. The server receives the response from the generative AI and converts it into a format that can be read by the user.

[1261] 9. The server sends the converted response to the terminal, ready to display to the user.

[1262] 10. The device displays the response received from the server to the user, for example, "Manager: These results are very good. Could you also provide a specific budget and timeline?", reflecting the user's sentiment.

[1263] Specific examples

[1264] 1. User types, "I've reported on my market research for a new business and found that there is more demand than expected. Do I have permission to move forward with this project?"

[1265] 2. The emotion engine analyzes this input and recognizes the user's "excited" state.

[1266] 3. The server receives this and generates a prompt based on the setting "Persona: Manager: Manager interacting with subordinate seeking approval for launching a new business." The prompt reflects the emotion of "excitement."

[1267] 4. Based on the prompt, the generative AI model generates a response like, "These results are very good. Can you also provide a specific budget and timeline?"

[1268] 5. The device displays this response to the user: "Manager: These results are very good. Can you also provide a specific budget and timeline?"

[1269] This system reduces the burden on managers and other executives, and allows trainees to practice in a variety of scenarios. The introduction of an emotion engine allows users to enjoy a more realistic dialogue experience, improving their skills in an environment that is closer to the real work environment.

[1270] The processing flow will be explained below.

[1271] Step 1:

[1272] The server sets the OpenAI API key and prepares for communication with the generative AI model. It also initializes the emotion engine and prepares for emotion analysis.

[1273] Step 2:

[1274] The user inputs information to start the simulation through the terminal. For example, the user might input, "After reporting on the market research for a new business, we have found that there is greater demand than expected. May I have your permission to proceed with this project?"

[1275] Step 3:

[1276] The device receives user input and first sends it to the emotion engine, which analyzes the user's input text and recognizes the user's emotional state (e.g., "excited" or "tense").

[1277] Step 4:

[1278] The emotion engine returns the analysis results to the terminal and sends the input, including the user's emotional state, to the server.

[1279] Step 5:

[1280] The server uses the persona of a specific person (e.g., a manager) to generate prompts based on user input. For example, in addition to the setting "Persona: Manager: Manager interacting with subordinate seeking approval for launching a new business," the server configures the prompt taking into account the user's "excitement" state.

[1281] Step 6:

[1282] The server sends the generated prompt and emotion recognition results to the AI ​​model, asking it to generate a response. The prompt includes persona information, a specific question from the user, and the emotion recognition results.

[1283] Step 7:

[1284] The generative AI model generates an appropriate response based on the prompt, such as "These results are very good. Can you also provide a specific budget and timeline?", reflecting the user's level of excitement in tone and expression.

[1285] Step 8:

[1286] The server receives the response from the generative AI and converts it into a format that can be read by the user.

[1287] Step 9:

[1288] The server sends the converted response to the terminal, ready to display to the user.

[1289] Step 10:

[1290] The terminal displays the response received from the server to the user, for example, "Manager: These results are very good. Could you also provide a specific budget proposal and timeline?", reflecting the user's feelings.

[1291] Step 11:

[1292] The user can review the displayed responses and continue the simulation by entering new questions or information as needed. By repeating this process, the user can receive advanced training that is tailored to real-world business scenarios.

[1293] Example 2

[1294] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1295] Conventional practical training systems for new graduates are unable to generate responses that take into account the user's emotions, making it difficult to provide the emotionally rich dialogue experience required in actual business scenarios. In addition, the simple persona settings of executives lack the precision required to obtain a realistic dialogue experience, limiting the effectiveness of the training.

[1296] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for receiving a user's input and analyzing the emotional state through an emotion engine, means for setting a persona of a specific manager, means for generating a prompt based on the persona taking the emotional state into consideration, means for sending a request to a generative AI model using the prompt to generate a response, and means for providing the generated response to the user. This enables a realistic dialogue experience that takes the user's emotions into consideration, allowing trainees to receive effective training in an environment that is close to actual work.

[1297] The "means for receiving user input and analyzing the emotional state through an emotion engine" is a device or program for receiving text entered by a user into a terminal and transmitting it to an emotion engine to extract emotional information.

[1298] A "means for setting the persona of a specific manager" is a device or program for specifically setting the personality and position of a manager used in practical training during new graduate training.

[1299] The "means for generating a prompt based on the persona while taking into account the emotional state" is a device or program that creates a prompt that reflects the user's emotional state based on set persona information.

[1300] "Means for sending a request to a generative artificial intelligence model using the prompt and generating a response" refers to a device or program that sends the generated prompt to an AI model and generates a response in response.

[1301] The "means for providing the generated response to the user" refers to a device or program that converts the generated response into a format that can be confirmed by the user and displays it through a terminal.

[1302] A "generative artificial intelligence model" is a type of artificial intelligence that generates human-like responses based on user-provided prompts.

[1303] A "persona" is a virtual character that defines the personality, position, and role of a specific person or character.

[1304] An "emotion engine" is software or algorithm that analyzes a user's text input and extracts the emotions contained therein.

[1305] This invention combines an emotion engine that recognizes user emotions in a simulation system for practical training for new graduate trainees. The system is designed to enable users to have an emotionally rich dialogue experience based on business scenarios through persona setting for executives, prompt generation, and a generative AI model.

[1306] Hardware and software used

[1307] The following hardware and software are used to implement this system.

[1308] Server: A server with high-performance computing power

[1309] Terminal: A computer or mobile device for receiving user input.

[1310] Emotion engine: Software that recognizes emotions through text analysis (e.g., Microsoft Azure Sentiment Analysis and IBM Watson Tone Analyzer)

[1311] Generative artificial intelligence model: An AI model that processes natural language (e.g., "OpenAI GPT-3")

[1312] Communication interface: API communication via the internet

[1313] Overall system flow

[1314] 1. The server first sets the OpenAI API key and prepares to communicate with the AI ​​model. It also initializes the emotion engine, which completes preparations for API communication and emotion analysis.

[1315] 2. The user inputs scenario information into the terminal and sends it. For example, the user might input a sentence like, "After reporting on market research for a new business, we have found that there is greater demand than expected. May I have your permission to proceed with this project?"

[1316] 3. The device sends the input data from the user to the emotion engine, allowing the emotion engine to analyze the data.

[1317] 4. The emotion engine analyzes the user's input and extracts the emotional state (e.g., "excited," "fear," etc.). The analysis result is encoded and sent back to the device.

[1318] 5. The device sends the user's input, including the emotion recognition results, to the server.

[1319] 6. The server generates a prompt using the persona of the specified manager and the user's emotion recognition results. For example, it generates a prompt with the content "Persona: Manager, interacting with subordinate seeking approval for launching a new business."

[1320] 7. The server sends the generated prompt to the AI ​​model, asking it to generate a response.

[1321] 8. The generative AI model generates an appropriate response based on the prompt and sends it back to the server, for example, "These results are very good. Can you also provide a specific budget and timeline?"

[1322] 9. The server converts the received response into a user-readable format and sends it to the terminal.

[1323] 10. The terminal displays the response from the server to the user, for example, "Manager: These results are very good. Could you also provide a specific budget and timeline?"

[1324] Specific examples

[1325] For example, a new graduate trainee might input, "I reported on the market research for a new business and found that there is greater demand than expected. Can I have your permission to proceed with this project?" This input is analyzed through an emotion engine, which recognizes the "excited" state. The server then generates a prompt based on the setting "Persona: Manager interacting with subordinate seeking approval for launching a new business." The generative AI model then generates an appropriate response, such as, "These results are very good. Could you also provide a specific budget proposal and timeline?" This response is finally displayed on the user's device, providing the new graduate with a realistic dialogue experience.

[1326] By using this system in this way, new graduate trainees can practice in a variety of scenarios, reducing the burden on specific managers while allowing trainees to improve their skills through emotionally rich dialogue.

[1327] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1328] Step 1:

[1329] The server initializes the OpenAI API key and prepares to communicate with the AI ​​model. The emotion engine is also initialized at the same time, allowing the system to access the AI ​​model through the API and process the user's emotion information.

[1330] Specific operation: Enter the OpenAI API key in the server's configuration file and call the initialization method of the emotion engine (e.g., "Microsoft Azure Sentiment Analysis" or "IBM Watson Tone Analyzer").

[1331] Input: Basic configuration information to boot the system

[1332] Output: API communication and emotion engine initialization complete

[1333] Step 2:

[1334] The user inputs scenario information through the terminal and clicks the send button on the terminal. For example, the user can input a sentence such as, "After reporting on market research for a new business, we have found that there is greater demand than expected. May I have your permission to proceed with this project?"

[1335] Specific behavior: The user enters text into the input field on the terminal and clicks the send button.

[1336] Input: Text entered by the user

[1337] Output: Send button click event on the device

[1338] Step 3:

[1339] The device sends input data from the user to the emotion engine, which uses the data for emotion analysis.

[1340] Specific operation: An HTTP request is generated on the terminal side and the user's input text is sent to the emotion engine's API endpoint.

[1341] Input: User-entered text

[1342] Output: Text data sent to the emotion engine API

[1343] Step 4:

[1344] The emotion engine analyzes the user's input and extracts the emotional state (e.g., "excited," "fear," etc.), which is then encoded and sent back to the device.

[1345] What it does: Analyzes text using the sentiment engine API and generates a sentiment score.

[1346] Input: Text data sent to the emotion engine

[1347] Output: Emotion score (user's emotional state)

[1348] Step 5:

[1349] The device sends the user's input, including the emotion recognition results, to the server, which then receives the necessary information to generate prompts.

[1350] Specific operation: The device sends the data received from the emotion engine to the server's API endpoint.

[1351] Input: Sentiment score and user input text

[1352] Output: HTTP request to the server

[1353] Step 6:

[1354] The server generates a prompt using the persona of a specific manager and the emotion recognition results from the user, for example, "Persona: Manager, interacting with subordinate seeking approval for launching a new business."

[1355] Specific operation: A script on the server combines the persona information template and emotion recognition results to generate prompt text.

[1356] Input: Persona information, emotion recognition results, user input text

[1357] Output: The generated prompt text

[1358] Step 7:

[1359] The server sends the generated prompt to the AI ​​model, asking it to generate a response.

[1360] Specific operation: The server generates an HTTP request and sends prompt data to the OpenAI API.

[1361] Input: Generated prompt text

[1362] Output: The request sent to the OpenAI API

[1363] Step 8:

[1364] The generative AI model generates an appropriate response based on the prompt and sends it back to the server, for example, "These results are very good. Can you also provide a specific budget and timeline?"

[1365] What it does: The generative AI model analyzes the prompt and generates response text based on an algorithm.

[1366] Input: The prompt text sent to the AI ​​model

[1367] Output: The generated response text

[1368] Step 9:

[1369] The server converts the response from the AI ​​model into a user-readable format and sends it to the device.

[1370] Specific operation: The server script converts the response text from the AI ​​into HTML or JSON format and sends it to the terminal.

[1371] Input: Response text from the AI ​​model

[1372] Output: Formatted text data sent to the terminal

[1373] Step 10:

[1374] The terminal receives the response from the server and displays it to the user, for example, "Manager: These results are very good. Could you also provide a specific budget and timeline?"

[1375] Specific behavior: Renders text to the display area on the device's web page or application UI.

[1376] Input: Preformatted text data from the server

[1377] Output: The response text that is displayed to the user

[1378] (Application example 2)

[1379] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1380] When new graduates receive practical training based on actual work scenarios, they are required to be provided with a realistic dialogue experience that reflects emotions. However, conventional simulation systems lack the ability to recognize emotions and reflect them in responses, which means they are unable to provide sufficient dialogue scenarios for trainees. In addition, because the scenarios are fixed, it is difficult for trainees to effectively acquire skills that can be applied to actual work.

[1381] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1382] In this invention, the server includes means for setting a virtual personality of a specific manager, means for receiving user input and generating a prompt based on the virtual personality, means for sending a request to a generative AI model using the prompt and generating a response, means for using an emotion engine to recognize the user's emotions and reflect them in the response, and means for providing the generated response to the user. This allows trainees to receive practical training in realistic dialogue scenarios that reflect emotions.

[1383] "New graduate training" is the initial training that companies and organizations provide to newly hired employees.

[1384] "Practical training" refers to training based on real-world work scenarios, where trainees acquire the skills necessary for their jobs through hands-on experience.

[1385] A "simulation system" is a system that uses a virtual environment to reproduce actual business scenarios and provide training to users.

[1386] The "virtual personality of a specific executive" refers to the character or persona of an executive set up to interact with the user within the simulation.

[1387] A "prompting sentence" is a question or instruction sentence generated based on the user's input, and is linguistic content used to progress the simulation.

[1388] A "generative AI model" is an AI system that generates natural language based on given prompts and instructions.

[1389] An "emotion engine" is a technical means for analyzing a user's input, recognizing their emotional state, and reflecting that state in the system's responses.

[1390] A "response" is a reply or reaction generated by the system in response to input from the user, and reflects the analysis results of the emotion engine.

[1391] A "work scenario" is a simulation scenario that specifically recreates situations or problems that trainees may encounter in a particular work environment.

[1392] The system for carrying out the present invention is a simulation system for effectively carrying out practical training in new graduate training. A specific embodiment of this system will be described below.

[1393] 1. Hardware Configuration

[1394] It requires a server and a terminal. The server has the computing resources to run the generative AI model and emotion engine. The terminal is a device (e.g., PC, tablet, smartphone) that receives input from the user.

[1395] 2. Software Configuration

[1396] Install the following software components on the server:

[1397] Generative artificial intelligence model: Uses OpenAI's API.

[1398] Emotion engine: A library for analyzing user input and recognizing its emotional state. For example, the emotion_recognition module.

[1399] 3. Data processing and calculation

[1400] The server communicates with the generative artificial intelligence model using the OpenAI API key to receive queries from users.

[1401] The emotion engine analyzes the user's input text and recognizes emotional states such as excitement or anxiety.

[1402] The recognized emotion is incorporated into the prompt sentence for the generative AI model along with the user input. For example, the prompt sentence for the virtual personality mentioned above includes the information "User emotion: excitement."

[1403] The server sends a request to the generative artificial intelligence model using the generated prompt sentence and obtains a response.

[1404] 4. Specific Examples

[1405] For example, consider a new graduate training scenario in a factory. If the user types, "The machine has stopped working. What should I do?", the emotion engine recognizes the user's "anxious" state. The server generates a prompt sentence like this:

[1406] Example of a text prompt:

[1407] Persona: Factory Robot: A robot interacting with a new trainee. User Emotion: Anxiety. User Input: My machine has stopped working. What should I do?

[1408] When this prompt is sent to a generative artificial intelligence model, an example response it generates is, "Please stay calm, new trainee. First, check the machine's control panel to see if there are any error messages. If the problem persists, please contact your technician."

[1409] This allows trainees to receive practical training in realistic dialogue scenarios that reflect emotions. The system simulates various work scenarios that trainees will encounter in real life and provides responses that include emotional reactions, providing a more realistic learning experience.

[1410] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1411] Step 1:

[1412] The user inputs an inquiry about the new graduate training scenario through a terminal. The input information is imported into the terminal as text information.

[1413] Input: User text input (e.g., "My machine has stopped working. What should I do?")

[1414] Output: Data containing text information

[1415] Step 2:

[1416] The device sends text information to the server, which receives it and transfers it to the emotion engine.

[1417] Input: Text information (e.g., "My machine has stopped working. What should I do?")

[1418] Output: Text information sent to the emotion engine

[1419] Step 3:

[1420] The server uses an emotion engine to analyze the user's text input and recognize their emotional state. For example, the server obtains the emotion "anxiety" as the analysis result.

[1421] Input: Text information (user query)

[1422] Output: Perceived emotional state (e.g., "anxiety")

[1423] Step 4:

[1424] The server generates a prompt sentence that includes the user's emotional state, combines the virtual personality and the user's query, and prepares to send it to the generative AI model.

[1425] Input: Text information (user query) and emotional state

[1426] Output: Prompt statement (e.g., "Persona: Factory robot: A robot interacting with a new trainee. User emotion: Anxiety. User input: My machine has stopped working. What should I do?")

[1427] Step 5:

[1428] The server sends a prompt to the generative AI model, requesting it to generate a response. The generative AI model generates an appropriate response based on the prompt.

[1429] Input: prompt statement

[1430] Output: The generated response (e.g., "Please stay calm, new trainee. First, check the machine's control panel and see if there are any error messages. If the problem persists, please contact your technician.")

[1431] Step 6:

[1432] The generated response is received by the server and converted into a user-friendly format, for example, sent to the terminal in text format.

[1433] Input: The generated response

[1434] Output: Response data in a format that can be displayed to the user (e.g., "Please stay calm, new trainee. First, check the machine's control panel and see if there are any error messages. If the problem persists, please contact your technician.")

[1435] Step 7:

[1436] The terminal displays the responses received from the server to the user, allowing the user to have an appropriate interactive experience in the simulation scenario.

[1437] Input: Response data sent from the server

[1438] Output: The response message that is displayed to the user (e.g., "Please stay calm, new trainee. First, check the machine's control panel and see if there are any error messages. If the problem persists, please contact your technician.")

[1439] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[1440] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1441] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1442] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1443] FIG. 9 illustrates an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and behaviors arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1444] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[1445] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[1446] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[1447] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[1448] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[1449] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[1450] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[1451] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[1452] 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.

[1453] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[1454] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[1455] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific processing may be a single processor.

[1456] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[1457] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[1458] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[1459] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[1460] The following is further disclosed regarding the above embodiment.

[1461] (Claim 1)

[1462] A simulation system for practical training in new graduate training,

[1463] A means of setting personas for specific executives;

[1464] means for receiving user input and generating prompts based on said persona;

[1465] means for sending a request to a generative artificial intelligence model using the prompt to generate a response;

[1466] means for providing the generated response to a user;

[1467] A system including:

[1468] (Claim 2)

[1469] The system of claim 1, wherein the generative artificial intelligence model is configured to maintain multiple personas corresponding to specific business scenarios and to generate different prompts based on each persona.

[1470] (Claim 3)

[1471] 10. The system of claim 1, configured to end the training session when the input from the user meets a specified ending condition.

[1472] "Example 1"

[1473] (Claim 1)

[1474] A simulation system for practical training in new graduate training,

[1475] A means of setting personas for specific executives;

[1476] means for receiving input from a user and transmitting the input from the terminal to a server;

[1477] means for generating a prompt based on the persona;

[1478] means for sending a request to a generative artificial intelligence model using the generated prompt to generate a response;

[1479] means for transmitting the generated response to a terminal and providing it to a user;

[1480] ...

[1481] A system including:

[1482] (Claim 2)

[1483] The system of claim 1, wherein the generative artificial intelligence model is configured to maintain multiple personas corresponding to specific business scenarios and to generate different prompts based on each persona.

[1484] (Claim 3)

[1485] 10. The system of claim 1, configured to end the training session when the input from the user meets a specified ending condition.

[1486] "Application Example 1"

[1487] (Claim 1)

[1488] A simulation system for practical training in new graduate training,

[1489] A means of setting personas for specific executives;

[1490] means for receiving user input and generating prompts based on said persona;

[1491] means for sending a request to a generative artificial intelligence model using the prompt to generate a response;

[1492] means for providing the generated response to a user;

[1493] A means for simulating a specific scenario for performing training on the operation of a factory robot and responding to user operations;

[1494] A system including:

[1495] (Claim 2)

[1496] The system of claim 1, wherein the generative artificial intelligence model is configured to maintain multiple personas corresponding to specific business scenarios and to generate different prompts based on each persona.

[1497] (Claim 3)

[1498] 10. The system of claim 1, configured to end the training session when the input from the user meets a specified ending condition.

[1499] "Example 2: Combining Emotion Engines"

[1500] (Claim 1)

[1501] means for receiving user input and analyzing the user's emotional state through an emotion engine;

[1502] A means of setting personas for specific executives;

[1503] means for generating prompts based on said persona taking into account an emotional state;

[1504] means for sending a request to a generative artificial intelligence model using the prompt to generate a response;

[1505] means for providing the generated response to a user;

[1506] A system including:

[1507] (Claim 2)

[1508] The system of claim 1, wherein the generative artificial intelligence model is configured to maintain multiple personas corresponding to specific business scenarios and to generate different prompts based on each persona.

[1509] (Claim 3)

[1510] 10. The system of claim 1, configured to end the training session when the input from the user meets a specified ending condition.

[1511] "Application example 2 when combining emotion engines"

[1512] (Claim 1)

[1513] A simulation system for practical training in new graduate training,

[1514] A means for setting a virtual personality of a specific official;

[1515] means for receiving a user's input and generating a prompt based on the virtual personality;

[1516] means for sending a request to a generative artificial intelligence model using the elicitation sentence to generate a response;

[1517] means for using an emotion engine to recognize the emotion of the user and reflect it in the response;

[1518] means for providing the generated response to a user;

[1519] A system including:

[1520] (Claim 2)

[1521] The system of claim 1, wherein the generative artificial intelligence model is configured to hold multiple virtual personalities corresponding to specific business scenarios and to generate different elicitation sentences based on each virtual personality.

[1522] (Claim 3)

[1523] 10. The system of claim 1, configured to end the training session when the input from the user meets a specified ending condition. [Explanation of symbols]

[1524] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. A simulation system for practical training in new graduate training, A means of setting personas for specific executives; means for receiving user input and generating prompts based on said persona; means for sending a request to a generative artificial intelligence model using the prompt to generate a response; means for providing the generated response to a user; A system including:

2. The system according to claim 1 , wherein the generative artificial intelligence model is configured to hold a plurality of personas corresponding to specific business scenarios and to generate different prompts based on each persona.

3. 10. The system of claim 1, configured to end a training session when the input from the user meets a specified ending condition.

Images