System

Abstract

A system is provided.SOLUTION: A system comprising: data input means for customizing based on data corresponding to a user; scenario generation means for generating a role playing scenario based on the input data; interaction means for interacting with the user according to the role playing scenario; response generation means for generating a response based on an interaction of the user; feedback generation means for generating feedback after the interaction; and storage means for storing a result of the interaction and the feedback.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] Current role-playing in call centers and sales departments has problems such as participants other than the trainees simply watching, and the questions asked are often mundane, resulting in inconsistent quality depending on the instructor's skill. Furthermore, implementing efficient and effective training requires a great deal of money and time, and individual attention is particularly difficult for multiple trainees at once. A method is needed to solve these problems and achieve efficient and effective training. [Means for solving the problem]

[0005] The present invention includes a data input means for customizing the system based on user-specific data, and a scenario generation means for generating a role-playing scenario based on this data. The system further includes a dialogue means for interacting with the user in accordance with the generated role-playing scenario, a response generation means for generating a response based on the user's dialogue, a feedback generation means for generating feedback after the dialogue ends, and a storage means for storing the results of the dialogue and the feedback. This enables role-playing in real time using AI to respond to a variety of scenarios, resulting in efficient and effective training.

[0006] "Data input means" refers to the function of inputting data according to the user into the system.

[0007] "Scenario generation means" refers to the function of creating a role-playing scenario based on input data.

[0008] "Interaction means" refers to the function of interacting with the user according to a role-playing scenario.

[0009] "Response generation means" refers to a function that generates an appropriate response based on the content of the user's dialogue.

[0010] "Feedback generation means" refers to a function that creates feedback based on the user's performance after the dialogue ends.

[0011] "Storage means" refers to a function that stores the results of the interaction and feedback.

[0012] "Review means" refers to a function that allows users to later check the stored dialogue results and feedback. [Brief explanation of the drawings]

[0013] [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

[0014] 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.

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

[0016] 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).

[0017] 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.

[0018] 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.

[0019] 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.

[0020] 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."

[0021] [First embodiment]

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

[0023] 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.

[0024] 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).

[0025] 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.

[0026] 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.

[0027] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form 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.

[0028] 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.

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

[0030] 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.

[0031] 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.

[0032] 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.

[0033] 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."

[0034] This invention is a customizable role-playing system using AI that significantly improves training efficiency, especially in call centers and sales departments. The system consists of the following main components:

[0035] Data input method

[0036] Scenario generation method

[0037] Interaction methods

[0038] Response Generation Method

[0039] Feedback Generation Method

[0040] storage means

[0041] Review Method

[0042] The specific operation will be explained below.

[0043] Data input method

[0044] After a user logs in, the server checks the user's profile information (such as product information and past performance data) and customizes the system based on the necessary data, which may include general data from the Internet or original data provided by the company.

[0045] Scenario generation method

[0046] The scenario generation means creates a role-playing scenario based on the data input by the server through the data input means. The scenario is customized taking into account the profile information of the user.

[0047] Interaction methods

[0048] As a means of interaction, the server interacts with the user based on the generated scenario. An interactive screen is displayed on the terminal from the server, and the user asks questions and answers according to the scenario.

[0049] Response Generation Method

[0050] The response generation means uses the AI ​​model to generate an appropriate response based on the user's input (questions and responses) received by the server, and the generated response is provided to the user via the device.

[0051] Feedback Generation Method

[0052] The feedback generation means allows the server to analyze the user's performance after the dialogue is completed and generate feedback. The analysis includes the quality of the user's questions and responses, response time, etc. The generated feedback is displayed on the terminal.

[0053] storage means

[0054] As a storage means, the server stores the results and feedback of the interactions in a database for later review and analysis.

[0055] Review Method

[0056] The review function allows users to later check the stored dialogue results and feedback. The server displays the saved logs on the terminal, allowing users to review their past performance and use it to improve.

[0057] Specific examples

[0058] For example, consider a case where role-playing of product inquiries is carried out in a new employee training mode.

[0059] New user A logs in

[0060] The user logs in to the system from the terminal, and the server performs user authentication.

[0061] Select Onboarding Mode

[0062] The user selects "new employee training mode" on the terminal, and the server reads scenario data based on the selected mode information.

[0063] Inputting customized data

[0064] The server checks User_A's profile information (such as product information) and customizes the scenario based on the relevant data.

[0065] Role-playing begins

[0066] The user clicks the "Start Role-Playing" button, and the server launches the AI ​​model and displays the interactive screen on the device.

[0067] Response Generation

[0068] The user types "How long is the warranty period for this product?" into the terminal, and the server uses an AI model to generate and display the appropriate response: "This product has a one-year warranty period."

[0069] Providing Feedback

[0070] After the session ends, the server generates feedback based on the user's performance and displays it on the device.

[0071] Results storage and review

[0072] The server stores session logs in a database, and users can review past sessions on their devices to learn from them.

[0073] In this way, the use of AI makes it possible to efficiently conduct role-playing training that is in line with practical work.

[0074] The processing flow will be explained below.

[0075] Step 1:

[0076] The user opens the system login screen on the device. They enter their user ID and password, which the device then sends to the server. The server authenticates the user ID and password, and if authentication is successful, the server loads the user's profile information and displays the home screen on the device.

[0077] Step 2:

[0078] The user opens the training mode selection screen on the device and selects the desired mode from "New Employee Training Mode" or "Product Specialized Mode", etc. The device sends the selected mode information to the server. The server loads the scenario data corresponding to the selected training mode and displays the training start screen on the device.

[0079] Step 3:

[0080] The server checks the user's profile information and identifies the necessary customization data (product information, past performance data, etc.). The server collects general data from the internet and original data provided by companies, and inputs this into the AI ​​model to generate customized training scenarios.

[0081] Step 4:

[0082] The user clicks the "Start Role-playing" button on the device. The device notifies the server of this action. The server starts the AI ​​model and starts role-playing based on the customized scenario. The server displays a dialogue screen on the device, and the AI ​​presents the initial scenario.

[0083] Step 5:

[0084] The user enters a question or response into the device (e.g., "How long is the warranty on this product?"). The device sends the input information to the server. The server passes this input to the AI ​​model, which processes it to generate a response. The AI ​​model generates an appropriate response (e.g., "This product has a one-year warranty"). The server sends the generated response to the device, which displays it.

[0085] Step 6:

[0086] When the session ends, the server analyzes the user's questions, responses, response time, accuracy, etc., and generates feedback (e.g., "Your questions were specific and polite"). The feedback data is sent to the device and displayed on the device.

[0087] Step 7:

[0088] The server stores role-playing session logs (questions, responses, feedback, etc.) in a database. The server provides a function to retrieve the logs from the database so that users can review past sessions on their devices. Users can review the evaluations and feedback on their devices and learn from them to improve.

[0089] Example 1

[0090] 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."

[0091] Conventional role-playing training systems lacked sufficient customization based on individual user profile information and performance data, making it difficult to provide efficient training. Additionally, it was difficult to provide appropriate responses to user responses in real time, limiting the effectiveness of the training.

[0092] 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.

[0093] In this invention, the server includes data input means for customizing based on data corresponding to the user, scenario generation means for generating a role-playing scenario based on the input data, dialogue means for dialogue with the user according to the role-playing scenario, response generation means using a generative AI model for generating responses based on the user's dialogue, feedback generation means for generating feedback after the dialogue ends, storage means for storing the dialogue results and feedback, and review means for allowing the user to review the stored dialogue results and feedback. This makes it possible to provide efficient role-playing training customized for each user, significantly improving the effectiveness of the training.

[0094] "Data input means" is a function that collects data such as user profile information and past performance data, and performs customization based on this data.

[0095] The "scenario generation means" is a function that generates a scenario for role-playing training based on input data.

[0096] "Dialogue means" is a function for conducting dialogue with the user according to the generated scenario.

[0097] The "response generation means" is a function that uses a generative AI model to generate an appropriate response based on user input.

[0098] The "feedback generation means" is a function that analyzes the user's performance after the dialogue ends and generates feedback.

[0099] The "storage means" is a function that stores the results of the dialogue and feedback in a database.

[0100] The "review means" is a function that allows the user to later check the stored dialogue results and feedback and use them to make improvements.

[0101] A "generative AI model" is an artificial intelligence model that generates appropriate responses in real time based on user input.

[0102] A "prompt sentence" is an instruction sentence input to an AI model that provides the information necessary to generate a specific response.

[0103] MODE FOR CARRYING OUT THE INVENTION

[0104] This invention is a customizable role-playing system using AI that significantly improves training efficiency, especially in call centers and sales departments. The system consists of the following main components:

[0105] Data input method

[0106] Scenario generation method

[0107] Interaction methods

[0108] Response Generation Method

[0109] Feedback Generation Method

[0110] storage means

[0111] Review Method

[0112] Data input method

[0113] After the user logs in from their device, the server checks the user's profile information (product information, past performance data, etc.) and customizes the system based on the necessary data. This data includes information from the Internet and original data provided by the company.

[0114] Scenario generation method

[0115] The server generates a scenario for role-playing training based on the data acquired through the data input means. This scenario is customized based on the user's profile information. For example, in the new employee training mode, it generates an inquiry scenario about the product that the new employee is responsible for.

[0116] Interaction methods

[0117] The server interacts with the user through the interaction means based on the generated scenario. The interaction screen is displayed on the terminal, and the user can ask questions and respond according to the scenario.

[0118] Response Generation Method

[0119] The server receives input from the user and uses the generative AI model to generate an appropriate response. The generated response is provided to the user via the terminal. For example, if a user inputs, "How long is the warranty period for this product?", the server uses the generative AI model to generate the response, "The warranty period for this product is one year."

[0120] Feedback Generation Method

[0121] After the interaction is completed, the server analyzes the user's performance and generates feedback, including the quality of the user's questions and responses, response times, etc. The generated feedback is displayed on the terminal and serves as a reference for the user to evaluate themselves.

[0122] storage means

[0123] The server stores the results of the interaction and feedback in a database, allowing users to review their performance at a later date and identify ways to improve.

[0124] Review Method

[0125] The server provides a function that allows users to check the stored dialogue results and feedback at any time, allowing users to review past training sessions and maximize learning effectiveness.

[0126] Specific examples

[0127] For example, a case where role-playing of product inquiries is performed in the new employee training mode will be described.

[0128] 1. A user (new employee A) logs in to the system from a terminal. The server authenticates the user and obtains profile information.

[0129] 2. The user selects "New Employee Training Mode" on the device. The server generates a scenario based on this information.

[0130] 3. The server uses the user's profile information to customize the scenario and display the interactive screen on the terminal.

[0131] 4. The user clicks the "Start Role-Playing" button and enters a question according to the scenario, for example, "How long is the warranty on this product?"

[0132] 5. The server uses the generative AI model to generate the appropriate response, "This product has a one-year warranty," and displays it on the device.

[0133] 6. After the session ends, the server analyzes the user's performance and generates feedback that is displayed on the device.

[0134] 7. The server stores the session log in a database, allowing users to review past sessions at a later time.

[0135] Prompt Sentence Examples

[0136] Below are some examples of input prompts for generative AI models:

[0137] Generate an appropriate response when the user types, "How long is the warranty on this product?"

[0138] In this way, by using AI, it is possible to conduct role-playing training that is in line with practical work efficiently and effectively.

[0139] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0140] System program processing flow

[0141] Step 1: Log in the user and get their profile information

[0142] When a user logs in from a terminal, the server receives the login information and performs user authentication. If authentication is successful, the server retrieves the user's profile information (product information, past performance data, etc.) from the database.

[0143] Input: User login information (user ID, password)

[0144] Processing: User authentication, retrieval of profile information

[0145] Output: User profile information

[0146] Step 2: Collect customization data

[0147] Based on the profile information, the server collects additional data from the Internet and company-provided databases, which are used to generate scenarios.

[0148] Input: User profile information

[0149] Processing: API requests to external databases, data collection

[0150] Output: Additional data (product information, etc.)

[0151] Step 3: Scenario generation

[0152] The server generates a customized role-playing scenario using a scenario generation means based on the user's profile information and additional data.

[0153] Input: Profile information, additional data

[0154] Processing: Application of scenario generation algorithm

[0155] Output: Customized scenario

[0156] Step 4: Start role-playing

[0157] The user clicks the "Start Role-Playing" button on the terminal. The server starts the interactive means based on the scenario and displays an interactive screen on the terminal.

[0158] Input: User operation (start of role-playing)

[0159] Processing: Loading scenarios and displaying interactive screens

[0160] Output: Dialogue screen

[0161] Step 5: Dialogue and response generation

[0162] The user inputs a question into the device according to a scenario. For example, "How long is the warranty period for this product?" The server receives this input and generates a response using a generative AI model. The generated response is then displayed on the device.

[0163] Input: User question

[0164] Processing: Response generation by AI model

[0165] Output: The generated response

[0166] Step 6: Feedback generation

[0167] After the role-playing session is over, the server analyzes the user's performance and generates feedback, including the quality of the questions and responses, response time, etc. The generated feedback is displayed on the device.

[0168] Input: Dialogue log (question and response content, response time, etc.)

[0169] Processing: performance analysis, feedback generation

[0170] Output: Generated feedback

[0171] Step 7: Save and review results

[0172] The server stores the interaction results and feedback in a database, and the user can review the saved interaction results later from their terminal.

[0173] Input: The result of the interaction, the generated feedback

[0174] Process: Save to database

[0175] Output: Stored disposition and feedback

[0176] Examples of prompt statements

[0177] Below are some examples of input prompts for generative AI models:

[0178] Generate an appropriate response when the user types, "How long is the warranty on this product?"

[0179]

[0180] (Application example 1)

[0181] 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."

[0182] In modern factories, training is crucial for operators to operate industrial machinery safely and efficiently. However, traditional training methods are time-consuming and costly, making it difficult to provide individually customized training. There is a particular need to provide an effective means for new operators to acquire the necessary skills in a short period of time. Another problem is the lack of a system for effectively storing operator operation logs and providing feedback.

[0183] 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.

[0184] In this invention, the server includes data input means for customizing the system based on data corresponding to the user, scenario generation means for generating a role-playing scenario based on the input data, dialogue means for dialogue with the user according to the role-playing scenario, response generation means for generating a response based on the dialogue of the user, feedback generation means for generating feedback after the dialogue is completed, storage means for storing the results of the dialogue and the feedback, industrial machine training means for providing the dialogue and responses to the user based on the scenario generated for industrial machine operation training, and result storage means for storing operation results in a database. This allows operators to efficiently and effectively acquire industrial machine operation skills, and enables continuous learning and improvement by storing operation logs and feedback.

[0185] The "data input means" is a means for inputting data related to a user, such as the user's profile information and the machine information in charge, into the system.

[0186] The "scenario generation means" is a means for automatically generating scenarios for training and role-playing based on data input via the data input means.

[0187] "Dialogue means" refers to means for interacting with the user according to the generated scenario. This includes interfaces such as text input and voice recognition.

[0188] "Response generation means" refers to a means for generating an appropriate response based on the user's dialogue input. This uses AI models and natural language processing technology.

[0189] A "feedback generation means" is a means for analyzing the user's performance and providing appropriate feedback after the dialogue or role-playing has ended.

[0190] The "storage means" is a means for recording and storing the results of the dialogue and the generated feedback.

[0191] The "industrial machine training means" is a means for providing dialogue and responses to users based on a scenario for conducting training on the operation of industrial machines.

[0192] The "result storage means" is a means for storing operation results and training logs in a database.

[0193] A "review tool" is a tool that allows users to review stored results and feedback at a later time for improvement or revision.

[0194] MODE FOR CARRYING OUT THE INVENTION

[0195] System Program Overview

[0196] In this invention, a plurality of means are combined to provide an industrial machine operation training system customized for each user. The specific processing of each means and its implementation method will be described below.

[0197] Data input method

[0198] After the user logs in, the server checks the profile information and performs customization based on the necessary data. Specifically, the user logs in to the system using a factory tablet or smart glasses. The server obtains the user's past operation data and information about the machine they are responsible for as a profile, and inputs the necessary data based on that. An edge computing server is used for this process.

[0199] Scenario generation method

[0200] As a scenario generation method, the server generates training scenarios for operating industrial machinery based on the input data. Specifically, an AI model trained using an AI model building tool such as TensorFlow generates individually customized training scenarios.

[0201] Interaction methods

[0202] The server interacts with the user based on the scenario generated by the scenario generation means. This is done using a dialogue interface with text input and voice recognition functions. For example, if a dialogue screen is displayed on a tablet and the user types, "What is the inspection procedure for this device?", the server uses an AI model to generate an appropriate response.

[0203] Response Generation Method

[0204] To generate a response, the server analyzes the user's dialogue input and generates an appropriate response using natural language processing technology such as TensorFlow. For example, it generates a specific procedure such as "The inspection procedure is as follows..." and displays it on the screen.

[0205] Feedback Generation Method

[0206] After the interaction with the user is completed, the server evaluates the user's performance and generates feedback, including an evaluation of the accuracy of the operation and response time, which is displayed on the factory tablet or smart glasses.

[0207] storage means

[0208] The server stores the results and feedback of the interactions in a database, allowing for later review and analysis, using a database management system such as PostgreSQL.

[0209] Industrial Machinery Training Tools

[0210] The server provides dialogue and responses to users based on scenarios for training on the operation of industrial machinery, allowing users to efficiently and effectively acquire the skills to operate industrial machinery.

[0211] Results storage means

[0212] The server stores the results of the operation in a database, which users can later review and use as a reference for their studies.

[0213] Specific examples

[0214] When a new operator logs in to a factory tablet and selects the safety inspection training mode in the system, the server generates a customized scenario based on the machine information for which they are responsible. The AI ​​model then activates a dialogue screen on the tablet, providing specific responses to questions such as, "What is the inspection procedure for this equipment?" After completing the training, the operator is given a performance evaluation and feedback, and all operation logs and feedback are stored in a database.

[0215] Prompt Sentence Examples

[0216] “You are an AI that generates detailed inspection procedures for a factory operator training system. When a new operator asks, ‘What is the inspection procedure for this equipment?’ you provide them with the appropriate detailed inspection procedure.”

[0217] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0218] Specific process steps for carrying out the invention

[0219] Step 1:

[0220] Data input

[0221] Input: User login information, user profile information (past operation data, machine information, etc.)

[0222] The server checks the profile information after the user logs in to the device. It uses the edge computing server to acquire past operation data and information about the machine in charge, and inputs this information into the server as profile information. This input data is then used to generate scenarios.

[0223] Step 2:

[0224] Scenario Generation

[0225] Input: Entered profile information

[0226] Output: Customized industrial machine operation training scenario

[0227] The server uses a scenario generation means to generate industrial machine operation training scenarios based on the input profile information. An AI model trained using TensorFlow automatically generates individually customized training scenarios based on this profile information.

[0228] Step 3:

[0229] Start a dialogue

[0230] Input: Generated training scenarios

[0231] Output: Display of dialogue screen, initial dialogue content

[0232] The server displays an interactive screen on a device (tablet, smart glasses, etc.) based on the generated scenario. The user begins role-playing by viewing the interactive screen.

[0233] Step 4:

[0234] User interactive input

[0235] Input: User question or request (e.g., "What is the inspection procedure for this device?")

[0236] Output: Dialogue input data

[0237] Users enter questions or requests into an interactive screen on their device, and this data is sent to the server, which then generates the next response.

[0238] Step 5:

[0239] Response Generation

[0240] Input: Interactive input data

[0241] Output: Response content (e.g. "The inspection procedure is as follows...")

[0242] The server receives the user's dialogue input and generates an appropriate response using a response generation means, using natural language processing technology such as TensorFlow to provide an accurate response to the user's question.

[0243] Step 6:

[0244] Feedback Generation

[0245] Input: Dialogue logs, user operation data

[0246] Output: Feedback content (e.g., operation accuracy, response time, etc.)

[0247] After the interaction is completed, the server analyzes the user's performance data and generates feedback using the feedback generation means. Specific evaluations and suggestions are made based on the accuracy of the user's operations and response times.

[0248] Step 7:

[0249] Result memory

[0250] Input: Dialogue results, feedback

[0251] Output: Saved log data

[0252] The server uses a storage means to store the results of the interaction and the generated feedback in a database, using a database management system such as PostgreSQL to record the results for later review and analysis.

[0253] Step 8:

[0254] Confirmation by review method

[0255] Input: Saved log data

[0256] Output: Review screen

[0257] The server allows users to later check the saved dialogue results and feedback. Users can log in using their devices and check the review screen to learn from past training content.

[0258] Prompt Sentence Examples

[0259] “You are an AI that generates detailed inspection procedures for a factory operator training system. When a new operator asks, ‘What is the inspection procedure for this equipment?’ you provide them with the appropriate detailed inspection procedure.”

[0260] 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.

[0261] This invention is a customizable role-playing system using AI that significantly improves training efficiency, especially in call centers and sales departments. This system consists of the following components:

[0262] 1. Data input method

[0263] 2. Scenario Generation Method

[0264] 3. Means of interaction

[0265] 4. Response Generation Method

[0266] 5. Feedback Generation Methods

[0267] 6. Storage means

[0268] 7. Review Methods

[0269] 8. Emotion Engine

[0270] The specific operation of this system will now be described.

[0271] Data input method

[0272] After the user logs in, the server checks the profile information for the user and customizes the user's profile based on the necessary data. This data includes general data from the Internet and original data provided by the company.

[0273] Scenario generation method

[0274] The scenario generating means generates a role-playing scenario based on the data input by the server through the data input means. This scenario is customized taking into account the profile information of the user.

[0275] Interaction methods

[0276] As a dialogue method, the server dialogues with the user based on the generated scenario. The dialogue screen is displayed on the terminal from the server, and the user dialogues alternately according to the scenario.

[0277] Response Generation Method

[0278] The response generation means uses the AI ​​model to generate an appropriate response based on the user's input (questions and responses) received by the server. The generated response is then provided to the user via their device.

[0279] Feedback Generation Method

[0280] The feedback generation means allows the server to analyze the user's performance after the dialogue is completed and generate feedback. The analysis includes the quality of the user's questions and responses, response time, etc. The generated feedback is displayed on the terminal.

[0281] storage means

[0282] As a storage means, the server stores the results and feedback of the interactions in a database for later review and analysis.

[0283] Review Method

[0284] The review function allows users to later check the stored dialogue results and feedback. The server displays the saved logs on the terminal, allowing users to review their past performance and use it to improve.

[0285] Emotion Engine

[0286] The emotion engine analyzes emotions from the user's voice and text inputs and provides the results to the response generation means. The server recognizes emotions through the emotion engine and adjusts the tone and content of the dialogue in real time.

[0287] Specific examples

[0288] For example, consider a case where role-playing of product inquiries is carried out in a new employee training mode.

[0289] New user A logs in

[0290] The user logs in to the system from the terminal, and the server performs user authentication.

[0291] Select Onboarding Mode

[0292] The user selects "new employee training mode" on the terminal, and the server reads scenario data based on the selected mode information.

[0293] Inputting customized data

[0294] The server checks User A's profile information (such as product information) and customizes the scenario based on the relevant data.

[0295] Role-playing begins

[0296] The user clicks the "Start Role-Playing" button, and the server launches the AI ​​model and displays the interactive screen on the device.

[0297] Response Generation

[0298] The user types "How long is the warranty period for this product?" into the terminal, and the server uses an AI model to generate and display the appropriate response: "This product has a one-year warranty period."

[0299] Use of emotion engine

[0300] The server uses an emotion engine to analyze the emotions contained in the user's input and adjust the tone of the dialogue. For example, if the user's question sounds tired, the AI ​​model will generate a gentler response.

[0301] Providing Feedback

[0302] After the session ends, the server generates feedback based on the user's performance, including opinions based on emotion recognition.

[0303] Results storage and review

[0304] The server stores session logs in a database, and users can review past sessions on their devices to learn from them.

[0305] In this way, this system makes full use of AI and an emotion engine to realize role-playing that is more human-like, thereby helping users improve their skills.

[0306] The processing flow will be explained below.

[0307] Role-playing system processing steps

[0308] Step 1:

[0309] The user opens the system login screen on the device and enters their user ID and password. The device sends the entered information to the server. The server authenticates the user ID and password, and if authentication is successful, the server loads the user's profile information and displays the home screen on the device.

[0310] Step 2:

[0311] The user opens the training mode selection screen on the device and selects the desired mode from "New Employee Training Mode" or "Product Specialized Mode", etc. The device sends the selected mode information to the server. The server loads the scenario data corresponding to the selected training mode and displays the training start screen on the device.

[0312] Step 3:

[0313] The server checks the user's profile information and identifies the necessary customization data (product information, past performance data, etc.). The server collects general data from the internet and original data provided by companies, and inputs this into the AI ​​model to generate customized training scenarios.

[0314] Step 4:

[0315] The user clicks the "Start Role-playing" button on the device. The device notifies the server of this action. The server starts the AI ​​model and starts role-playing based on the customized scenario. The server displays a dialogue screen on the device, and the AI ​​presents the initial scenario.

[0316] Step 5:

[0317] The user enters a question or response into the device (e.g., "How long is the warranty on this product?"). The device sends the input information to the server. The server passes this input to the AI ​​model, which processes it to generate a response. The AI ​​model generates an appropriate response (e.g., "This product has a one-year warranty"). The server sends the generated response to the device, which displays it.

[0318] Step 6:

[0319] The server uses an emotion engine to analyze emotions from the user's voice and text input. The emotion engine analyzes the user's emotions and provides the results to the server. The server receives the emotion engine's output and adjusts the tone and content of the dialogue in real time. For example, if the user is tired, the AI ​​model will generate a gentler tone in the response.

[0320] Step 7:

[0321] When the session ends, the server analyzes the user's questions, responses, response time, accuracy, etc., and generates feedback (e.g., "Your questions were specific and polite"). The feedback data is sent to the device and displayed on the device.

[0322] Step 8:

[0323] The server stores role-playing session logs (questions, responses, feedback, etc.) in a database. The server provides a function to retrieve saved logs from the database so that users can review past sessions on their devices. Users can review the evaluations and feedback on their devices and learn from them to improve.

[0324] Example 2

[0325] 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."

[0326] Conventional role-playing systems lack the ability to customize to the individual needs of each user, analyze emotions during dialogue, and provide feedback. As a result, training effectiveness could not be maximized, and there were issues with improving individual skills and improving training efficiency.

[0327] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0328] In this invention, the server includes data input means for customizing based on data corresponding to the user, scenario generation means for generating a role-playing scenario based on the input data, dialogue means for dialogue with the user according to the role-playing scenario, response generation means for generating a response based on the user's dialogue, feedback generation means for generating feedback after the dialogue ends, storage means for storing the results of the dialogue and the feedback, and an emotion engine for analyzing emotions from the user's voice and text input and reflecting them in response generation. This makes it possible to provide training scenarios that correspond to the individual situation of each user, adjust dialogue based on emotions, and provide consistent performance evaluation and feedback.

[0329] "User" refers to any individual or entity who uses and receives training on this system.

[0330] "Data input means" refers to the means for acquiring data according to the user and inputting it into the system.

[0331] "Scenario generation means" refers to a means for generating a customized role-playing scenario based on input data.

[0332] "Interaction means" refers to a means for interacting with a user according to the generated role-playing scenario.

[0333] The "response generation means" refers to a means for generating an appropriate response based on the user's interaction.

[0334] "Feedback generation means" refers to a means for analyzing a user's performance and generating feedback after an interaction session has ended.

[0335] "Storage means" refers to a means for storing the results and feedback of an interaction for later review and analysis.

[0336] An "emotion engine" refers to a means of analyzing emotions from a user's voice and text input and reflecting the results in generating a response.

[0337] "Review means" refers to a means by which a user can later review the results and feedback stored in the storage means.

[0338] "Internet-derived data" means public or commercial data accessible through a wide area communications network.

[0339] "Original data provided by companies" refers to data that companies collect and provide independently.

[0340] This invention is a customizable role-playing system using AI that significantly improves training efficiency, especially in call centers and sales departments. The system consists of the following main components:

[0341] Data input method

[0342] After the user logs in, the server performs user authentication. At this time, it checks the user profile information and customizes the user's profile based on the necessary data. This data includes general data obtained from the Internet and original data provided by the company.

[0343] Scenario generation method

[0344] The scenario generation means generates a role-playing scenario based on the data input by the server through the data input means. This scenario is customized taking into account the user's profile information. Specifically, a scenario is generated based on the product and role that the user is responsible for.

[0345] Interaction methods

[0346] The server then interacts with the user based on the generated scenario. The interaction screen is displayed on the terminal, and the user interacts with the scenario in turn.

[0347] Response Generation Method

[0348] The server receives user input (questions and responses) and uses the generative AI model to generate an appropriate response. For example, if a user asks, "How long is the warranty period for this product?", the generative AI model responds, "This product has a one-year warranty period."

[0349] Emotion Engine

[0350] The emotion engine analyzes emotions from the user's voice and text input and provides the results to the response generation means. The server recognizes emotions through the emotion engine and adjusts the tone and content of the dialogue in real time. For example, if the user's input shows signs of fatigue, the AI ​​model will generate a response with a gentler tone.

[0351] Feedback Generation Method

[0352] After the interaction session, the server analyzes the user's performance and generates feedback, including the quality of the user's questions and responses, response times, and opinions based on emotion recognition.

[0353] storage means

[0354] The server stores the results and feedback of the interactions in a database for later review and further analysis.

[0355] Review Method

[0356] The server displays the saved interaction results and feedback on the device, allowing the user to check their past performance, facilitating self-evaluation and learning.

[0357] Specific examples

[0358] For example, consider a case where role-playing of product inquiries is carried out in a training mode for new employees at a call center.

[0359] New user A logs in

[0360] The user logs in to the system from the terminal, and the server performs user authentication.

[0361] Select Onboarding Mode

[0362] The user selects the "new employee training mode," and the server reads scenario data based on the selected mode information.

[0363] Inputting customized data

[0364] The server checks User A's profile information (such as product information) and customizes the scenario based on the relevant data.

[0365] Role-playing begins

[0366] The user clicks the "Start Role-Playing" button, and the server launches the generated AI model and displays the interactive screen on the device.

[0367] Response Generation

[0368] The user types, "How long is the warranty period for this product?", and the server uses a generative AI model to generate the appropriate response, "This product has a one-year warranty period," which is displayed on the device.

[0369] Use of emotion engine

[0370] The server uses an emotion engine to analyze the emotions contained in the user's input and adjust the tone of the dialogue. For example, if the user's question sounds tired, the AI ​​model will generate a gentler response.

[0371] Providing Feedback

[0372] After the session ends, the server generates feedback based on the user's performance and displays it on the device, including opinions based on emotion recognition.

[0373] Results storage and review

[0374] The server stores session logs in a database, and users can review past sessions on their devices to learn from them.

[0375] In this way, this system makes full use of AI and an emotion engine to realize role-playing in a manner that is close to human, thereby helping users improve their skills.

[0376] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0377] Step 1:

[0378] The user enters login information (username, password) into the terminal.

[0379] Input: Username, Password

[0380] The server receives this information and authenticates the user by checking the user information against a database.

[0381] Data processing: Verification of authentication information

[0382] Output: Authentication result (success / failure)

[0383] Step 2:

[0384] The server obtains user profile information based on the authentication result.

[0385] Input: Authentication result (user name)

[0386] The server retrieves the user's profile information (such as product information) from the database.

[0387] Data processing: Extracting user profiles

[0388] Output: User profile information

[0389] Step 3:

[0390] The user selects the mode to be used on the device (e.g., new employee training mode).

[0391] Input: Mode selection information

[0392] The server reads scenario data corresponding to the selected mode from the database.

[0393] Data processing: Extraction of scenario data

[0394] Output: Scenario data

[0395] Step 4:

[0396] The server customizes the scenario data based on the acquired user profile information.

[0397] Input: User profile information, scenario data

[0398] The server customizes the scenario based on the profile information (e.g., including specific inquiries about the product they are responsible for).

[0399] Data processing: Scenario customization

[0400] Output: Customized scenario

[0401] Step 5:

[0402] The user clicks the "Start Role-Playing" button on the device.

[0403] Input: Start signal

[0404] The server generates an interactive screen based on the customized scenario and displays it on the terminal.

[0405] Data processing: Generation of interactive screens

[0406] Output: Display of interactive screen

[0407] Step 6:

[0408] The user types a question or response into the terminal (e.g., "How long is the warranty on this product?").

[0409] Input: Question and response text

[0410] The server receives this input and inputs it as a prompt sentence into the generative AI model.

[0411] Data processing: Prompt sentence generation

[0412] Output: Input to the AI ​​model

[0413] Step 7:

[0414] The server uses the generative AI model to generate an appropriate response.

[0415] Input: prompt statement

[0416] The server generates a response from the AI ​​model and obtains the response text (e.g., "This product has a one-year warranty").

[0417] Data processing: response generation

[0418] Output: Response text

[0419] Step 8:

[0420] The server generates a response and displays it on the terminal.

[0421] Input: Response text

[0422] The server sends this response to the terminal and displays it to the user.

[0423] Data processing: Generation of data for display

[0424] Output: Display to terminal

[0425] Step 9:

[0426] The server uses an emotion engine to analyze the emotion contained in the user's input.

[0427] Input: User question and response text

[0428] The server analyzes the emotional state of the input text with an emotion engine and obtains the result.

[0429] Data Processing: Sentiment Analysis

[0430] Output: Sentiment analysis results

[0431] Step 10:

[0432] The server uses the results of the sentiment analysis to adjust the tone of the dialogue and feed it into the generative AI model.

[0433] Input: Sentiment analysis results

[0434] The server adjusts the output tone of the generative AI model based on the results of the emotion analysis.

[0435] Data processing: Adjusting the tone of the dialogue

[0436] Output: Adjusted response

[0437] Step 11:

[0438] The server analyzes the user's performance and generates feedback after the interactive session ends.

[0439] Input: conversation logs, response times, sentiment analysis results

[0440] The server analyzes this data and generates feedback.

[0441] Data processing: performance analysis and feedback generation

[0442] Output: Feedback

[0443] Step 12:

[0444] The server displays the feedback on the device.

[0445] Input: Feedback

[0446] The server sends the feedback to the terminal and displays it to the user.

[0447] Data processing: Generation of data for display

[0448] Output: Display to terminal

[0449] Step 13:

[0450] The server stores the results of the interaction and feedback in a database.

[0451] Input: Dialogue result, feedback

[0452] The server stores this data in a database.

[0453] Data processing: Data storage

[0454] Output: Saved

[0455] Step 14:

[0456] The user checks past sessions on the device.

[0457] Input: Review request

[0458] The server retrieves the saved dialogue results and feedback and displays them on the terminal.

[0459] Data processing: Data acquisition and generation of data for display

[0460] Output: Show past sessions

[0461] (Application example 2)

[0462] 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."

[0463] Traditional factory operator training systems lacked real-time interactive simulation and feedback, making effective training difficult. They also struggled to implement role-playing customized for specific scenarios and lacked the flexibility to adapt to diverse work environments. Furthermore, they lacked the ability to review training results afterward, limiting opportunities for operators to reflect on and improve their performance.

[0464] 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.

[0465] In this invention, the server includes: a data input means for customizing the system based on data corresponding to the user; a scenario generation means for generating a role-playing scenario based on the input data; a dialogue means for dialogue with the user according to the role-playing scenario; a response generation means for generating a response based on the dialogue of the user; a feedback generation means for generating feedback after the dialogue is completed; a storage means for storing the results of the dialogue and the feedback; a scenario generation means for generating a scenario to support the training of in-factory operators; a dialogue means for simulating a dialogue with the user based on the generated scenario; a generative AI model means for generating appropriate responses based on user input; and a review means for allowing the user to review the generated feedback after the training session is completed. This allows for real-time dialogue simulation and feedback to be provided to factory operators, enabling effective training and performance review.

[0466] The "data input means" is a means for inputting user profile information and related data into the server and customizing the system.

[0467] The "scenario generation means" is a means for generating a role-playing scenario suited to the user based on the information obtained from the data input means.

[0468] The "interaction means" is a means for interacting with the user based on the generated role-playing scenario.

[0469] The "response generation means" is a means for generating an appropriate response to an input from a user.

[0470] The "feedback generation means" is a means for analyzing the user's performance after the dialogue is completed and generating feedback.

[0471] "Storage means" is a means for storing the results of the interaction and the generated feedback.

[0472] The "role-playing system for in-factory operator training" is a system for training in-factory operators using actual work scenarios.

[0473] A "generative AI model means" is an artificial intelligence model used to generate an appropriate response based on user input.

[0474] A "review facility" is a facility that allows users to later review and reflect on the feedback and interaction logs generated after the training session is completed.

[0475] The "simulation means" is a means for simulating real-time interactions in a virtual environment and simulating actual operations.

[0476] An "appropriate response" is a context- and content-matched answer generated in response to user input using a generative AI model.

[0477] "Users" are those who will use this system and receive training, such as factory operators.

[0478] The present invention is a system for supporting the training of in-factory operators, and is realized using specific hardware and software. This system operates in the following steps.

[0479] Hardware and software used

[0480] The server installs the AI ​​model and performs the main computational processing required to execute the dialogue. Specifically, it is recommended to use an EC2 instance from Amazon Web Services (AWS). AWS RDS is suitable for storing the database. The AI ​​model uses the T5 model with the Hugging Face transformers library.

[0481] Data input and scenario generation

[0482] The server uses data input means to customize data based on user profile information, including general data obtained from the Internet and specific operational data provided by the enterprise.

[0483] Next, the server generates role-playing scenarios for in-factory operator training based on the information obtained from the data input means. The scenario generation means creates scenarios including specific work procedures and situations based on the user profile.

[0484] Interaction methods and response generation

[0485] When the user starts training, the server simulates a dialogue based on a scenario generated by the scenario generation means. At this time, the dialogue means interfaces with the user and guides the progress of the role-playing.

[0486] Based on the user's questions and input, the server generates an appropriate response using the response generation means. The generative AI model means (T5 model) provides an answer that matches the context and content based on the user's input.

[0487] Feedback generation and review features

[0488] After the interaction is completed, the server uses a feedback generating means to generate feedback on the user's performance, including the quality of the interaction, response time, and the emotion analysis results of the emotion engine.

[0489] The generated feedback and interaction logs are stored in a database using a storage means, and a review means is provided so that users can later reflect on their performance and identify areas for improvement.

[0490] Adding specific examples

[0491] For example, if a user asks, "What is the operating procedure for this machine?", the server uses the AI ​​model to generate a response such as, "The operating procedure for this machine is as follows: First, turn it on, then press the setting button..." After the training session, the server generates feedback such as, "Overall, good. You performed the work correctly, but there is room for improvement in efficiency."

[0492] As described above, the present invention is a system for effectively supporting factory operator skill improvement, and is capable of real-time interactive simulation and personalized feedback.

[0493] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0494] Step 1:

[0495] The server retrieves the user's profile information.

[0496] Input: User login information.

[0497] Output: User profile information.

[0498] Specific operation: Based on the login information provided by the terminal, the server accesses the database and retrieves the user's profile information, which includes past interaction history and information about the machine in charge.

[0499] Step 2:

[0500] The server populates the relevant data using the data populating means.

[0501] Input: User profile information.

[0502] Output: Data for customized scenario generation.

[0503] Specific Operation: The server uses internet and company-provided data to populate the role-playing scenario with data to customize it based on the user's profile information.

[0504] Step 3:

[0505] The server generates a role-playing scenario using a scenario generation means.

[0506] Input: Customized data.

[0507] Output: Scenarios for in-factory operator training.

[0508] Specific operation: Based on the input data, the server generates specific work scenarios within the factory. These scenarios are tailored to the user's work responsibilities and skill level.

[0509] Step 4:

[0510] The terminal starts a dialogue with the user using the dialogue means.

[0511] Input: The generated scenario.

[0512] Output: Interactive interface display.

[0513] Specific operation: A dialogue interface based on the generated scenario is displayed on the terminal, and the user begins dialogue according to the scenario.

[0514] Step 5:

[0515] The server uses a response generation means to generate a response to the user's input.

[0516] Input: User questions or input.

[0517] Output: Appropriate response.

[0518] Specific operation: The server receives the question entered by the user into the terminal, generates an appropriate response using the generative AI model means (T5 model), and displays it on the terminal. For example, in response to the user's input, "What is the operating procedure for this machine?", the server generates the response, "The operating procedure for this machine is as follows. First, turn on the power, then press the setting button..."

[0519] Step 6:

[0520] The server generates the feedback using the feedback generating means.

[0521] Input: The result of the user's interaction.

[0522] Output: Feedback information.

[0523] Specific operation: After the dialogue ends, the server analyzes the content of the dialogue and the response time of the user, and generates feedback, including the quality of the dialogue and the results of emotion analysis by the emotion engine.

[0524] Step 7:

[0525] The server uses a storage means to store the interaction results and feedback.

[0526] Input: Interaction outcome and feedback information.

[0527] Output: Saved interaction logs and feedback.

[0528] Specific Actions: The server stores the generated feedback and interaction logs in a database for later review.

[0529] Step 8:

[0530] The terminal uses the review means to display the feedback and interaction log to the user.

[0531] Input: Saved interaction logs and feedback.

[0532] Output: The review information displayed to the user.

[0533] What it does: Allows users to use their devices to review logs and feedback from past training sessions. For example, feedback such as "Overall good. You followed the correct procedures, but there is room for improvement" is displayed on the review screen.

[0534] 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.

[0535] 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.

[0536] 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.

[0537] [Second embodiment]

[0538] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0539] 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.

[0540] 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).

[0541] 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.

[0542] 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.

[0543] 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).

[0544] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0545] 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.

[0546] 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.

[0547] 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.

[0548] 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.

[0549] 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."

[0550] This invention is a customizable role-playing system using AI that significantly improves training efficiency, especially in call centers and sales departments. The system consists of the following main components:

[0551] Data input method

[0552] Scenario generation method

[0553] Interaction methods

[0554] Response Generation Method

[0555] Feedback Generation Method

[0556] storage means

[0557] Review Method

[0558] The specific operation will be explained below.

[0559] Data input method

[0560] After a user logs in, the server checks the user's profile information (such as product information and past performance data) and customizes the system based on the necessary data, which may include general data from the Internet or original data provided by the company.

[0561] Scenario generation method

[0562] The scenario generation means creates a role-playing scenario based on the data input by the server through the data input means. The scenario is customized taking into account the profile information of the user.

[0563] Interaction methods

[0564] As a means of interaction, the server interacts with the user based on the generated scenario. An interactive screen is displayed on the terminal from the server, and the user asks questions and answers according to the scenario.

[0565] Response Generation Method

[0566] The response generation means uses the AI ​​model to generate an appropriate response based on the user's input (questions and responses) received by the server, and the generated response is provided to the user via the device.

[0567] Feedback Generation Method

[0568] The feedback generation means allows the server to analyze the user's performance after the dialogue is completed and generate feedback. The analysis includes the quality of the user's questions and responses, response time, etc. The generated feedback is displayed on the terminal.

[0569] storage means

[0570] As a storage means, the server stores the results and feedback of the interactions in a database for later review and analysis.

[0571] Review Method

[0572] The review function allows users to later check the stored dialogue results and feedback. The server displays the saved logs on the terminal, allowing users to review their past performance and use it to improve.

[0573] Specific examples

[0574] For example, consider a case where role-playing of product inquiries is carried out in a new employee training mode.

[0575] New user A logs in

[0576] The user logs in to the system from the terminal, and the server performs user authentication.

[0577] Select Onboarding Mode

[0578] The user selects "new employee training mode" on the terminal, and the server reads scenario data based on the selected mode information.

[0579] Inputting customized data

[0580] The server checks User_A's profile information (such as product information) and customizes the scenario based on the relevant data.

[0581] Role-playing begins

[0582] The user clicks the "Start Role-Playing" button, and the server launches the AI ​​model and displays the interactive screen on the device.

[0583] Response Generation

[0584] The user types "How long is the warranty period for this product?" into the terminal, and the server uses an AI model to generate and display the appropriate response: "This product has a one-year warranty period."

[0585] Providing Feedback

[0586] After the session ends, the server generates feedback based on the user's performance and displays it on the device.

[0587] Results storage and review

[0588] The server stores session logs in a database, and users can review past sessions on their devices to learn from them.

[0589] In this way, the use of AI makes it possible to efficiently conduct role-playing training that is in line with practical work.

[0590] The processing flow will be explained below.

[0591] Step 1:

[0592] The user opens the system login screen on the device. They enter their user ID and password, which the device then sends to the server. The server authenticates the user ID and password, and if authentication is successful, the server loads the user's profile information and displays the home screen on the device.

[0593] Step 2:

[0594] The user opens the training mode selection screen on the device and selects the desired mode from "New Employee Training Mode" or "Product Specialized Mode", etc. The device sends the selected mode information to the server. The server loads the scenario data corresponding to the selected training mode and displays the training start screen on the device.

[0595] Step 3:

[0596] The server checks the user's profile information and identifies the necessary customization data (product information, past performance data, etc.). The server collects general data from the internet and original data provided by companies, and inputs this into the AI ​​model to generate customized training scenarios.

[0597] Step 4:

[0598] The user clicks the "Start Role-playing" button on the device. The device notifies the server of this action. The server starts the AI ​​model and starts role-playing based on the customized scenario. The server displays a dialogue screen on the device, and the AI ​​presents the initial scenario.

[0599] Step 5:

[0600] The user enters a question or response into the device (e.g., "How long is the warranty on this product?"). The device sends the input information to the server. The server passes this input to the AI ​​model, which processes it to generate a response. The AI ​​model generates an appropriate response (e.g., "This product has a one-year warranty"). The server sends the generated response to the device, which displays it.

[0601] Step 6:

[0602] When the session ends, the server analyzes the user's questions, responses, response time, accuracy, etc., and generates feedback (e.g., "Your questions were specific and polite"). The feedback data is sent to the device and displayed on the device.

[0603] Step 7:

[0604] The server stores role-playing session logs (questions, responses, feedback, etc.) in a database. The server provides a function to retrieve the logs from the database so that users can review past sessions on their devices. Users can review the evaluations and feedback on their devices and learn from them to improve.

[0605] Example 1

[0606] 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."

[0607] Conventional role-playing training systems lacked sufficient customization based on individual user profile information and performance data, making it difficult to provide efficient training. Additionally, it was difficult to provide appropriate responses to user responses in real time, limiting the effectiveness of the training.

[0608] 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.

[0609] In this invention, the server includes data input means for customizing based on data corresponding to the user, scenario generation means for generating a role-playing scenario based on the input data, dialogue means for dialogue with the user according to the role-playing scenario, response generation means using a generative AI model for generating responses based on the user's dialogue, feedback generation means for generating feedback after the dialogue ends, storage means for storing the dialogue results and feedback, and review means for allowing the user to review the stored dialogue results and feedback. This makes it possible to provide efficient role-playing training customized for each user, significantly improving the effectiveness of the training.

[0610] "Data input means" is a function that collects data such as user profile information and past performance data, and performs customization based on this data.

[0611] The "scenario generation means" is a function that generates a scenario for role-playing training based on input data.

[0612] "Dialogue means" is a function for conducting dialogue with the user according to the generated scenario.

[0613] The "response generation means" is a function that uses a generative AI model to generate an appropriate response based on user input.

[0614] The "feedback generation means" is a function that analyzes the user's performance after the dialogue ends and generates feedback.

[0615] The "storage means" is a function that stores the results of the dialogue and feedback in a database.

[0616] The "review means" is a function that allows the user to later check the stored dialogue results and feedback and use them to make improvements.

[0617] A "generative AI model" is an artificial intelligence model that generates appropriate responses in real time based on user input.

[0618] A "prompt sentence" is an instruction sentence input to an AI model that provides the information necessary to generate a specific response.

[0619] MODE FOR CARRYING OUT THE INVENTION

[0620] This invention is a customizable role-playing system using AI that significantly improves training efficiency, especially in call centers and sales departments. The system consists of the following main components:

[0621] Data input method

[0622] Scenario generation method

[0623] Interaction methods

[0624] Response Generation Method

[0625] Feedback Generation Method

[0626] storage means

[0627] Review Method

[0628] Data input method

[0629] After the user logs in from their device, the server checks the user's profile information (product information, past performance data, etc.) and customizes the system based on the necessary data. This data includes information from the Internet and original data provided by the company.

[0630] Scenario generation method

[0631] The server generates a scenario for role-playing training based on the data acquired through the data input means. This scenario is customized based on the user's profile information. For example, in the new employee training mode, it generates an inquiry scenario about the product that the new employee is responsible for.

[0632] Interaction methods

[0633] The server interacts with the user through the interaction means based on the generated scenario. The interaction screen is displayed on the terminal, and the user can ask questions and respond according to the scenario.

[0634] Response Generation Method

[0635] The server receives input from the user and uses the generative AI model to generate an appropriate response. The generated response is provided to the user via the terminal. For example, if a user inputs, "How long is the warranty period for this product?", the server uses the generative AI model to generate the response, "The warranty period for this product is one year."

[0636] Feedback Generation Method

[0637] After the interaction is completed, the server analyzes the user's performance and generates feedback, including the quality of the user's questions and responses, response times, etc. The generated feedback is displayed on the terminal and serves as a reference for the user to evaluate themselves.

[0638] storage means

[0639] The server stores the results of the interaction and feedback in a database, allowing users to review their performance at a later date and identify ways to improve.

[0640] Review Method

[0641] The server provides a function that allows users to check the stored dialogue results and feedback at any time, allowing users to review past training sessions and maximize learning effectiveness.

[0642] Specific examples

[0643] For example, a case where role-playing of product inquiries is performed in the new employee training mode will be described.

[0644] 1. A user (new employee A) logs in to the system from a terminal. The server authenticates the user and obtains profile information.

[0645] 2. The user selects "New Employee Training Mode" on the device. The server generates a scenario based on this information.

[0646] 3. The server uses the user's profile information to customize the scenario and display the interactive screen on the terminal.

[0647] 4. The user clicks the "Start Role-Playing" button and enters a question according to the scenario, for example, "How long is the warranty on this product?"

[0648] 5. The server uses the generative AI model to generate the appropriate response, "This product has a one-year warranty," and displays it on the device.

[0649] 6. After the session ends, the server analyzes the user's performance and generates feedback that is displayed on the device.

[0650] 7. The server stores the session log in a database, allowing users to review past sessions at a later time.

[0651] Prompt Sentence Examples

[0652] Below are some examples of input prompts for generative AI models:

[0653] Generate an appropriate response when the user types, "How long is the warranty on this product?"

[0654] In this way, by using AI, it is possible to conduct role-playing training that is in line with practical work efficiently and effectively.

[0655] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0656] System program processing flow

[0657] Step 1: Log in the user and get their profile information

[0658] When a user logs in from a terminal, the server receives the login information and performs user authentication. If authentication is successful, the server retrieves the user's profile information (product information, past performance data, etc.) from the database.

[0659] Input: User login information (user ID, password)

[0660] Processing: User authentication, retrieval of profile information

[0661] Output: User profile information

[0662] Step 2: Collect customization data

[0663] Based on the profile information, the server collects additional data from the Internet and company-provided databases, which are used to generate scenarios.

[0664] Input: User profile information

[0665] Processing: API requests to external databases, data collection

[0666] Output: Additional data (product information, etc.)

[0667] Step 3: Scenario generation

[0668] The server generates a customized role-playing scenario using a scenario generation means based on the user's profile information and additional data.

[0669] Input: Profile information, additional data

[0670] Processing: Application of scenario generation algorithm

[0671] Output: Customized scenario

[0672] Step 4: Start role-playing

[0673] The user clicks the "Start Role-Playing" button on the terminal. The server starts the interactive means based on the scenario and displays an interactive screen on the terminal.

[0674] Input: User operation (start of role-playing)

[0675] Processing: Loading scenarios and displaying interactive screens

[0676] Output: Dialogue screen

[0677] Step 5: Dialogue and response generation

[0678] The user inputs a question into the device according to a scenario. For example, "How long is the warranty period for this product?" The server receives this input and generates a response using a generative AI model. The generated response is then displayed on the device.

[0679] Input: User question

[0680] Processing: Response generation by AI model

[0681] Output: The generated response

[0682] Step 6: Feedback generation

[0683] After the role-playing session is over, the server analyzes the user's performance and generates feedback, including the quality of the questions and responses, response time, etc. The generated feedback is displayed on the device.

[0684] Input: Dialogue log (question and response content, response time, etc.)

[0685] Processing: performance analysis, feedback generation

[0686] Output: Generated feedback

[0687] Step 7: Save and review results

[0688] The server stores the interaction results and feedback in a database, and the user can review the saved interaction results later from their terminal.

[0689] Input: The result of the interaction, the generated feedback

[0690] Process: Save to database

[0691] Output: Stored disposition and feedback

[0692] Examples of prompt statements

[0693] Below are some examples of input prompts for generative AI models:

[0694] Generate an appropriate response when the user types, "How long is the warranty on this product?"

[0695]

[0696] (Application example 1)

[0697] 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."

[0698] In modern factories, training is crucial for operators to operate industrial machinery safely and efficiently. However, traditional training methods are time-consuming and costly, making it difficult to provide individually customized training. There is a particular need to provide an effective means for new operators to acquire the necessary skills in a short period of time. Another problem is the lack of a system for effectively storing operator operation logs and providing feedback.

[0699] 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.

[0700] In this invention, the server includes data input means for customizing the system based on data corresponding to the user, scenario generation means for generating a role-playing scenario based on the input data, dialogue means for dialogue with the user according to the role-playing scenario, response generation means for generating a response based on the dialogue of the user, feedback generation means for generating feedback after the dialogue is completed, storage means for storing the results of the dialogue and the feedback, industrial machine training means for providing the dialogue and responses to the user based on the scenario generated for industrial machine operation training, and result storage means for storing operation results in a database. This allows operators to efficiently and effectively acquire industrial machine operation skills, and enables continuous learning and improvement by storing operation logs and feedback.

[0701] The "data input means" is a means for inputting data related to a user, such as the user's profile information and the machine information in charge, into the system.

[0702] The "scenario generation means" is a means for automatically generating scenarios for training and role-playing based on data input via the data input means.

[0703] "Dialogue means" refers to means for interacting with the user according to the generated scenario. This includes interfaces such as text input and voice recognition.

[0704] "Response generation means" refers to a means for generating an appropriate response based on the user's dialogue input. This uses AI models and natural language processing technology.

[0705] A "feedback generation means" is a means for analyzing the user's performance and providing appropriate feedback after the dialogue or role-playing has ended.

[0706] The "storage means" is a means for recording and storing the results of the dialogue and the generated feedback.

[0707] The "industrial machine training means" is a means for providing dialogue and responses to users based on a scenario for conducting training on the operation of industrial machines.

[0708] The "result storage means" is a means for storing operation results and training logs in a database.

[0709] A "review tool" is a tool that allows users to review stored results and feedback at a later time for improvement or revision.

[0710] MODE FOR CARRYING OUT THE INVENTION

[0711] System Program Overview

[0712] In this invention, a plurality of means are combined to provide an industrial machine operation training system customized for each user. The specific processing of each means and its implementation method will be described below.

[0713] Data input method

[0714] After the user logs in, the server checks the profile information and performs customization based on the necessary data. Specifically, the user logs in to the system using a factory tablet or smart glasses. The server obtains the user's past operation data and information about the machine they are responsible for as a profile, and inputs the necessary data based on that. An edge computing server is used for this process.

[0715] Scenario generation method

[0716] As a scenario generation method, the server generates training scenarios for operating industrial machinery based on the input data. Specifically, an AI model trained using an AI model building tool such as TensorFlow generates individually customized training scenarios.

[0717] Interaction methods

[0718] The server interacts with the user based on the scenario generated by the scenario generation means. This is done using a dialogue interface with text input and voice recognition functions. For example, if a dialogue screen is displayed on a tablet and the user types, "What is the inspection procedure for this device?", the server uses an AI model to generate an appropriate response.

[0719] Response Generation Method

[0720] To generate a response, the server analyzes the user's dialogue input and generates an appropriate response using natural language processing technology such as TensorFlow. For example, it generates a specific procedure such as "The inspection procedure is as follows..." and displays it on the screen.

[0721] Feedback Generation Method

[0722] After the interaction with the user is completed, the server evaluates the user's performance and generates feedback, including an evaluation of the accuracy of the operation and response time, which is displayed on the factory tablet or smart glasses.

[0723] storage means

[0724] The server stores the results and feedback of the interactions in a database, allowing for later review and analysis, using a database management system such as PostgreSQL.

[0725] Industrial Machinery Training Tools

[0726] The server provides dialogue and responses to users based on scenarios for training on the operation of industrial machinery, allowing users to efficiently and effectively acquire the skills to operate industrial machinery.

[0727] Results storage means

[0728] The server stores the results of the operation in a database, which users can later review and use as a reference for their studies.

[0729] Specific examples

[0730] When a new operator logs in to a factory tablet and selects the safety inspection training mode in the system, the server generates a customized scenario based on the machine information for which they are responsible. The AI ​​model then activates a dialogue screen on the tablet, providing specific responses to questions such as, "What is the inspection procedure for this equipment?" After completing the training, the operator is given a performance evaluation and feedback, and all operation logs and feedback are stored in a database.

[0731] Prompt Sentence Examples

[0732] “You are an AI that generates detailed inspection procedures for a factory operator training system. When a new operator asks, ‘What is the inspection procedure for this equipment?’ you provide them with the appropriate detailed inspection procedure.”

[0733] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0734] Specific process steps for carrying out the invention

[0735] Step 1:

[0736] Data input

[0737] Input: User login information, user profile information (past operation data, machine information, etc.)

[0738] The server checks the profile information after the user logs in to the device. It uses the edge computing server to acquire past operation data and information about the machine in charge, and inputs this information into the server as profile information. This input data is then used to generate scenarios.

[0739] Step 2:

[0740] Scenario Generation

[0741] Input: Entered profile information

[0742] Output: Customized industrial machine operation training scenario

[0743] The server uses a scenario generation means to generate industrial machine operation training scenarios based on the input profile information. An AI model trained using TensorFlow automatically generates individually customized training scenarios based on this profile information.

[0744] Step 3:

[0745] Start a dialogue

[0746] Input: Generated training scenarios

[0747] Output: Display of dialogue screen, initial dialogue content

[0748] The server displays an interactive screen on a device (tablet, smart glasses, etc.) based on the generated scenario. The user begins role-playing by viewing the interactive screen.

[0749] Step 4:

[0750] User interactive input

[0751] Input: User question or request (e.g., "What is the inspection procedure for this device?")

[0752] Output: Dialogue input data

[0753] Users enter questions or requests into an interactive screen on their device, and this data is sent to the server, which then generates the next response.

[0754] Step 5:

[0755] Response Generation

[0756] Input: Interactive input data

[0757] Output: Response content (e.g. "The inspection procedure is as follows...")

[0758] The server receives the user's dialogue input and generates an appropriate response using a response generation means, using natural language processing technology such as TensorFlow to provide an accurate response to the user's question.

[0759] Step 6:

[0760] Feedback Generation

[0761] Input: Dialogue logs, user operation data

[0762] Output: Feedback content (e.g., operation accuracy, response time, etc.)

[0763] After the interaction is completed, the server analyzes the user's performance data and generates feedback using the feedback generation means. Specific evaluations and suggestions are made based on the accuracy of the user's operations and response times.

[0764] Step 7:

[0765] Result memory

[0766] Input: Dialogue results, feedback

[0767] Output: Saved log data

[0768] The server uses a storage means to store the results of the interaction and the generated feedback in a database, using a database management system such as PostgreSQL to record the results for later review and analysis.

[0769] Step 8:

[0770] Confirmation by review method

[0771] Input: Saved log data

[0772] Output: Review screen

[0773] The server allows users to later check the saved dialogue results and feedback. Users can log in using their devices and check the review screen to learn from past training content.

[0774] Prompt Sentence Examples

[0775] “You are an AI that generates detailed inspection procedures for a factory operator training system. When a new operator asks, ‘What is the inspection procedure for this equipment?’ you provide them with the appropriate detailed inspection procedure.”

[0776] 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.

[0777] This invention is a customizable role-playing system using AI that significantly improves training efficiency, especially in call centers and sales departments. This system consists of the following components:

[0778] 1. Data input method

[0779] 2. Scenario Generation Method

[0780] 3. Means of interaction

[0781] 4. Response Generation Method

[0782] 5. Feedback Generation Methods

[0783] 6. Storage means

[0784] 7. Review Methods

[0785] 8. Emotion Engine

[0786] The specific operation of this system will now be described.

[0787] Data input method

[0788] After the user logs in, the server checks the profile information for the user and customizes the user's profile based on the necessary data. This data includes general data from the Internet and original data provided by the company.

[0789] Scenario generation method

[0790] The scenario generating means generates a role-playing scenario based on the data input by the server through the data input means. This scenario is customized taking into account the profile information of the user.

[0791] Interaction methods

[0792] As a dialogue method, the server dialogues with the user based on the generated scenario. The dialogue screen is displayed on the terminal from the server, and the user dialogues alternately according to the scenario.

[0793] Response Generation Method

[0794] The response generation means uses the AI ​​model to generate an appropriate response based on the user's input (questions and responses) received by the server. The generated response is then provided to the user via their device.

[0795] Feedback Generation Method

[0796] The feedback generation means allows the server to analyze the user's performance after the dialogue is completed and generate feedback. The analysis includes the quality of the user's questions and responses, response time, etc. The generated feedback is displayed on the terminal.

[0797] storage means

[0798] As a storage means, the server stores the results and feedback of the interactions in a database for later review and analysis.

[0799] Review Method

[0800] The review function allows users to later check the stored dialogue results and feedback. The server displays the saved logs on the terminal, allowing users to review their past performance and use it to improve.

[0801] Emotion Engine

[0802] The emotion engine analyzes emotions from the user's voice and text inputs and provides the results to the response generation means. The server recognizes emotions through the emotion engine and adjusts the tone and content of the dialogue in real time.

[0803] Specific examples

[0804] For example, consider a case where role-playing of product inquiries is carried out in a new employee training mode.

[0805] New user A logs in

[0806] The user logs in to the system from the terminal, and the server performs user authentication.

[0807] Select Onboarding Mode

[0808] The user selects "new employee training mode" on the terminal, and the server reads scenario data based on the selected mode information.

[0809] Inputting customized data

[0810] The server checks User A's profile information (such as product information) and customizes the scenario based on the relevant data.

[0811] Role-playing begins

[0812] The user clicks the "Start Role-Playing" button, and the server launches the AI ​​model and displays the interactive screen on the device.

[0813] Response Generation

[0814] The user types "How long is the warranty period for this product?" into the terminal, and the server uses an AI model to generate and display the appropriate response: "This product has a one-year warranty period."

[0815] Use of emotion engine

[0816] The server uses an emotion engine to analyze the emotions contained in the user's input and adjust the tone of the dialogue. For example, if the user's question sounds tired, the AI ​​model will generate a gentler response.

[0817] Providing Feedback

[0818] After the session ends, the server generates feedback based on the user's performance, including opinions based on emotion recognition.

[0819] Results storage and review

[0820] The server stores session logs in a database, and users can review past sessions on their devices to learn from them.

[0821] In this way, this system makes full use of AI and an emotion engine to realize role-playing that is more human-like, thereby helping users improve their skills.

[0822] The processing flow will be explained below.

[0823] Role-playing system processing steps

[0824] Step 1:

[0825] The user opens the system login screen on the device and enters their user ID and password. The device sends the entered information to the server. The server authenticates the user ID and password, and if authentication is successful, the server loads the user's profile information and displays the home screen on the device.

[0826] Step 2:

[0827] The user opens the training mode selection screen on the device and selects the desired mode from "New Employee Training Mode" or "Product Specialized Mode", etc. The device sends the selected mode information to the server. The server loads the scenario data corresponding to the selected training mode and displays the training start screen on the device.

[0828] Step 3:

[0829] The server checks the user's profile information and identifies the necessary customization data (product information, past performance data, etc.). The server collects general data from the internet and original data provided by companies, and inputs this into the AI ​​model to generate customized training scenarios.

[0830] Step 4:

[0831] The user clicks the "Start Role-playing" button on the device. The device notifies the server of this action. The server starts the AI ​​model and starts role-playing based on the customized scenario. The server displays a dialogue screen on the device, and the AI ​​presents the initial scenario.

[0832] Step 5:

[0833] The user enters a question or response into the device (e.g., "How long is the warranty on this product?"). The device sends the input information to the server. The server passes this input to the AI ​​model, which processes it to generate a response. The AI ​​model generates an appropriate response (e.g., "This product has a one-year warranty"). The server sends the generated response to the device, which displays it.

[0834] Step 6:

[0835] The server uses an emotion engine to analyze emotions from the user's voice and text input. The emotion engine analyzes the user's emotions and provides the results to the server. The server receives the emotion engine's output and adjusts the tone and content of the dialogue in real time. For example, if the user is tired, the AI ​​model will generate a gentler tone in the response.

[0836] Step 7:

[0837] When the session ends, the server analyzes the user's questions, responses, response time, accuracy, etc., and generates feedback (e.g., "Your questions were specific and polite"). The feedback data is sent to the device and displayed on the device.

[0838] Step 8:

[0839] The server stores role-playing session logs (questions, responses, feedback, etc.) in a database. The server provides a function to retrieve saved logs from the database so that users can review past sessions on their devices. Users can review the evaluations and feedback on their devices and learn from them to improve.

[0840] Example 2

[0841] 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."

[0842] Conventional role-playing systems lack the ability to customize to the individual needs of each user, analyze emotions during dialogue, and provide feedback. As a result, training effectiveness could not be maximized, and there were issues with improving individual skills and improving training efficiency.

[0843] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0844] In this invention, the server includes data input means for customizing based on data corresponding to the user, scenario generation means for generating a role-playing scenario based on the input data, dialogue means for dialogue with the user according to the role-playing scenario, response generation means for generating a response based on the user's dialogue, feedback generation means for generating feedback after the dialogue ends, storage means for storing the results of the dialogue and the feedback, and an emotion engine for analyzing emotions from the user's voice and text input and reflecting them in response generation. This makes it possible to provide training scenarios that correspond to the individual situation of each user, adjust dialogue based on emotions, and provide consistent performance evaluation and feedback.

[0845] "User" refers to any individual or entity who uses and receives training on this system.

[0846] "Data input means" refers to the means for acquiring data according to the user and inputting it into the system.

[0847] "Scenario generation means" refers to a means for generating a customized role-playing scenario based on input data.

[0848] "Interaction means" refers to a means for interacting with a user according to the generated role-playing scenario.

[0849] The "response generation means" refers to a means for generating an appropriate response based on the user's interaction.

[0850] "Feedback generation means" refers to a means for analyzing a user's performance and generating feedback after an interaction session has ended.

[0851] "Storage means" refers to a means for storing the results and feedback of an interaction for later review and analysis.

[0852] An "emotion engine" refers to a means of analyzing emotions from a user's voice and text input and reflecting the results in generating a response.

[0853] "Review means" refers to a means by which a user can later review the results and feedback stored in the storage means.

[0854] "Internet-derived data" means public or commercial data accessible through a wide area communications network.

[0855] "Original data provided by companies" refers to data that companies collect and provide independently.

[0856] This invention is a customizable role-playing system using AI that significantly improves training efficiency, especially in call centers and sales departments. The system consists of the following main components:

[0857] Data input method

[0858] After the user logs in, the server performs user authentication. At this time, it checks the user profile information and customizes the user's profile based on the necessary data. This data includes general data obtained from the Internet and original data provided by the company.

[0859] Scenario generation method

[0860] The scenario generation means generates a role-playing scenario based on the data input by the server through the data input means. This scenario is customized taking into account the user's profile information. Specifically, a scenario is generated based on the product and role that the user is responsible for.

[0861] Interaction methods

[0862] The server then interacts with the user based on the generated scenario. The interaction screen is displayed on the terminal, and the user interacts with the scenario in turn.

[0863] Response Generation Method

[0864] The server receives user input (questions and responses) and uses the generative AI model to generate an appropriate response. For example, if a user asks, "How long is the warranty period for this product?", the generative AI model responds, "This product has a one-year warranty period."

[0865] Emotion Engine

[0866] The emotion engine analyzes emotions from the user's voice and text input and provides the results to the response generation means. The server recognizes emotions through the emotion engine and adjusts the tone and content of the dialogue in real time. For example, if the user's input shows signs of fatigue, the AI ​​model will generate a response with a gentler tone.

[0867] Feedback Generation Method

[0868] After the interaction session, the server analyzes the user's performance and generates feedback, including the quality of the user's questions and responses, response times, and opinions based on emotion recognition.

[0869] storage means

[0870] The server stores the results and feedback of the interactions in a database for later review and further analysis.

[0871] Review Method

[0872] The server displays the saved interaction results and feedback on the device, allowing the user to check their past performance, facilitating self-evaluation and learning.

[0873] Specific examples

[0874] For example, consider a case where role-playing of product inquiries is carried out in a training mode for new employees at a call center.

[0875] New user A logs in

[0876] The user logs in to the system from the terminal, and the server performs user authentication.

[0877] Select Onboarding Mode

[0878] The user selects the "new employee training mode," and the server reads scenario data based on the selected mode information.

[0879] Inputting customized data

[0880] The server checks User A's profile information (such as product information) and customizes the scenario based on the relevant data.

[0881] Role-playing begins

[0882] The user clicks the "Start Role-Playing" button, and the server launches the generated AI model and displays the interactive screen on the device.

[0883] Response Generation

[0884] The user types, "How long is the warranty period for this product?", and the server uses a generative AI model to generate the appropriate response, "This product has a one-year warranty period," which is displayed on the device.

[0885] Use of emotion engine

[0886] The server uses an emotion engine to analyze the emotions contained in the user's input and adjust the tone of the dialogue. For example, if the user's question sounds tired, the AI ​​model will generate a gentler response.

[0887] Providing Feedback

[0888] After the session ends, the server generates feedback based on the user's performance and displays it on the device, including opinions based on emotion recognition.

[0889] Results storage and review

[0890] The server stores session logs in a database, and users can review past sessions on their devices to learn from them.

[0891] In this way, this system makes full use of AI and an emotion engine to realize role-playing in a manner that is close to human, thereby helping users improve their skills.

[0892] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0893] Step 1:

[0894] The user enters login information (username, password) into the terminal.

[0895] Input: Username, Password

[0896] The server receives this information and authenticates the user by checking the user information against a database.

[0897] Data processing: Verification of authentication information

[0898] Output: Authentication result (success / failure)

[0899] Step 2:

[0900] The server obtains user profile information based on the authentication result.

[0901] Input: Authentication result (user name)

[0902] The server retrieves the user's profile information (such as product information) from the database.

[0903] Data processing: Extracting user profiles

[0904] Output: User profile information

[0905] Step 3:

[0906] The user selects the mode to be used on the device (e.g., new employee training mode).

[0907] Input: Mode selection information

[0908] The server reads scenario data corresponding to the selected mode from the database.

[0909] Data processing: Extraction of scenario data

[0910] Output: Scenario data

[0911] Step 4:

[0912] The server customizes the scenario data based on the acquired user profile information.

[0913] Input: User profile information, scenario data

[0914] The server customizes the scenario based on the profile information (e.g., including specific inquiries about the product they are responsible for).

[0915] Data processing: Scenario customization

[0916] Output: Customized scenario

[0917] Step 5:

[0918] The user clicks the "Start Role-Playing" button on the device.

[0919] Input: Start signal

[0920] The server generates an interactive screen based on the customized scenario and displays it on the terminal.

[0921] Data processing: Generation of interactive screens

[0922] Output: Display of interactive screen

[0923] Step 6:

[0924] The user types a question or response into the terminal (e.g., "How long is the warranty on this product?").

[0925] Input: Question and response text

[0926] The server receives this input and inputs it as a prompt sentence into the generative AI model.

[0927] Data processing: Prompt sentence generation

[0928] Output: Input to the AI ​​model

[0929] Step 7:

[0930] The server uses the generative AI model to generate an appropriate response.

[0931] Input: prompt statement

[0932] The server generates a response from the AI ​​model and obtains the response text (e.g., "This product has a one-year warranty").

[0933] Data processing: response generation

[0934] Output: Response text

[0935] Step 8:

[0936] The server generates a response and displays it on the terminal.

[0937] Input: Response text

[0938] The server sends this response to the terminal and displays it to the user.

[0939] Data processing: Generation of data for display

[0940] Output: Display to terminal

[0941] Step 9:

[0942] The server uses an emotion engine to analyze the emotion contained in the user's input.

[0943] Input: User question and response text

[0944] The server analyzes the emotional state of the input text with an emotion engine and obtains the result.

[0945] Data Processing: Sentiment Analysis

[0946] Output: Sentiment analysis results

[0947] Step 10:

[0948] The server uses the results of the sentiment analysis to adjust the tone of the dialogue and feed it into the generative AI model.

[0949] Input: Sentiment analysis results

[0950] The server adjusts the output tone of the generative AI model based on the results of the emotion analysis.

[0951] Data processing: Adjusting the tone of the dialogue

[0952] Output: Adjusted response

[0953] Step 11:

[0954] The server analyzes the user's performance and generates feedback after the interactive session ends.

[0955] Input: conversation logs, response times, sentiment analysis results

[0956] The server analyzes this data and generates feedback.

[0957] Data processing: performance analysis and feedback generation

[0958] Output: Feedback

[0959] Step 12:

[0960] The server displays the feedback on the device.

[0961] Input: Feedback

[0962] The server sends the feedback to the terminal and displays it to the user.

[0963] Data processing: Generation of data for display

[0964] Output: Display to terminal

[0965] Step 13:

[0966] The server stores the results of the interaction and feedback in a database.

[0967] Input: Dialogue result, feedback

[0968] The server stores this data in a database.

[0969] Data processing: Data storage

[0970] Output: Saved

[0971] Step 14:

[0972] The user checks past sessions on the device.

[0973] Input: Review request

[0974] The server retrieves the saved dialogue results and feedback and displays them on the terminal.

[0975] Data processing: Data acquisition and generation of data for display

[0976] Output: Show past sessions

[0977] (Application example 2)

[0978] 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."

[0979] Traditional factory operator training systems lacked real-time interactive simulation and feedback, making effective training difficult. They also struggled to implement role-playing customized for specific scenarios and lacked the flexibility to adapt to diverse work environments. Furthermore, they lacked the ability to review training results afterward, limiting opportunities for operators to reflect on and improve their performance.

[0980] 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.

[0981] In this invention, the server includes: a data input means for customizing the system based on data corresponding to the user; a scenario generation means for generating a role-playing scenario based on the input data; a dialogue means for dialogue with the user according to the role-playing scenario; a response generation means for generating a response based on the dialogue of the user; a feedback generation means for generating feedback after the dialogue is completed; a storage means for storing the results of the dialogue and the feedback; a scenario generation means for generating a scenario to support the training of in-factory operators; a dialogue means for simulating a dialogue with the user based on the generated scenario; a generative AI model means for generating appropriate responses based on user input; and a review means for allowing the user to review the generated feedback after the training session is completed. This allows for real-time dialogue simulation and feedback to be provided to factory operators, enabling effective training and performance review.

[0982] The "data input means" is a means for inputting user profile information and related data into the server and customizing the system.

[0983] The "scenario generation means" is a means for generating a role-playing scenario suited to the user based on the information obtained from the data input means.

[0984] The "interaction means" is a means for interacting with the user based on the generated role-playing scenario.

[0985] The "response generation means" is a means for generating an appropriate response to an input from a user.

[0986] The "feedback generation means" is a means for analyzing the user's performance after the dialogue is completed and generating feedback.

[0987] "Storage means" is a means for storing the results of the interaction and the generated feedback.

[0988] The "role-playing system for in-factory operator training" is a system for training in-factory operators using actual work scenarios.

[0989] A "generative AI model means" is an artificial intelligence model used to generate an appropriate response based on user input.

[0990] A "review facility" is a facility that allows users to later review and reflect on the feedback and interaction logs generated after the training session is completed.

[0991] The "simulation means" is a means for simulating real-time interactions in a virtual environment and simulating actual operations.

[0992] An "appropriate response" is a context- and content-matched answer generated in response to user input using a generative AI model.

[0993] "Users" are those who will use this system and receive training, such as factory operators.

[0994] The present invention is a system for supporting the training of in-factory operators, and is realized using specific hardware and software. This system operates in the following steps.

[0995] Hardware and software used

[0996] The server installs the AI ​​model and performs the main computational processing required to execute the dialogue. Specifically, it is recommended to use an EC2 instance from Amazon Web Services (AWS). AWS RDS is suitable for storing the database. The AI ​​model uses the T5 model with the Hugging Face transformers library.

[0997] Data input and scenario generation

[0998] The server uses data input means to customize data based on user profile information, including general data obtained from the Internet and specific operational data provided by the enterprise.

[0999] Next, the server generates role-playing scenarios for in-factory operator training based on the information obtained from the data input means. The scenario generation means creates scenarios including specific work procedures and situations based on the user profile.

[1000] Interaction methods and response generation

[1001] When the user starts training, the server simulates a dialogue based on a scenario generated by the scenario generation means. At this time, the dialogue means interfaces with the user and guides the progress of the role-playing.

[1002] Based on the user's questions and input, the server generates an appropriate response using the response generation means. The generative AI model means (T5 model) provides an answer that matches the context and content based on the user's input.

[1003] Feedback generation and review features

[1004] After the interaction is completed, the server uses a feedback generating means to generate feedback on the user's performance, including the quality of the interaction, response time, and the emotion analysis results of the emotion engine.

[1005] The generated feedback and interaction logs are stored in a database using a storage means, and a review means is provided so that users can later reflect on their performance and identify areas for improvement.

[1006] Adding specific examples

[1007] For example, if a user asks, "What is the operating procedure for this machine?", the server uses the AI ​​model to generate a response such as, "The operating procedure for this machine is as follows: First, turn it on, then press the setting button..." After the training session, the server generates feedback such as, "Overall, good. You performed the work correctly, but there is room for improvement in efficiency."

[1008] As described above, the present invention is a system for effectively supporting factory operator skill improvement, and is capable of real-time interactive simulation and personalized feedback.

[1009] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1010] Step 1:

[1011] The server retrieves the user's profile information.

[1012] Input: User login information.

[1013] Output: User profile information.

[1014] Specific operation: Based on the login information provided by the terminal, the server accesses the database and retrieves the user's profile information, which includes past interaction history and information about the machine in charge.

[1015] Step 2:

[1016] The server populates the relevant data using the data populating means.

[1017] Input: User profile information.

[1018] Output: Data for customized scenario generation.

[1019] Specific Operation: The server uses internet and company-provided data to populate the role-playing scenario with data to customize it based on the user's profile information.

[1020] Step 3:

[1021] The server generates a role-playing scenario using a scenario generation means.

[1022] Input: Customized data.

[1023] Output: Scenarios for in-factory operator training.

[1024] Specific operation: Based on the input data, the server generates specific work scenarios within the factory. These scenarios are tailored to the user's work responsibilities and skill level.

[1025] Step 4:

[1026] The terminal starts a dialogue with the user using the dialogue means.

[1027] Input: The generated scenario.

[1028] Output: Interactive interface display.

[1029] Specific operation: A dialogue interface based on the generated scenario is displayed on the terminal, and the user begins dialogue according to the scenario.

[1030] Step 5:

[1031] The server uses a response generation means to generate a response to the user's input.

[1032] Input: User questions or input.

[1033] Output: Appropriate response.

[1034] Specific operation: The server receives the question entered by the user into the terminal, generates an appropriate response using the generative AI model means (T5 model), and displays it on the terminal. For example, in response to the user's input, "What is the operating procedure for this machine?", the server generates the response, "The operating procedure for this machine is as follows. First, turn on the power, then press the setting button..."

[1035] Step 6:

[1036] The server generates the feedback using the feedback generating means.

[1037] Input: The result of the user's interaction.

[1038] Output: Feedback information.

[1039] Specific operation: After the dialogue ends, the server analyzes the content of the dialogue and the response time of the user, and generates feedback, including the quality of the dialogue and the results of emotion analysis by the emotion engine.

[1040] Step 7:

[1041] The server uses a storage means to store the interaction results and feedback.

[1042] Input: Interaction outcome and feedback information.

[1043] Output: Saved interaction logs and feedback.

[1044] Specific Actions: The server stores the generated feedback and interaction logs in a database for later review.

[1045] Step 8:

[1046] The terminal uses the review means to display the feedback and interaction log to the user.

[1047] Input: Saved interaction logs and feedback.

[1048] Output: The review information displayed to the user.

[1049] What it does: Allows users to use their devices to review logs and feedback from past training sessions. For example, feedback such as "Overall good. You followed the correct procedures, but there is room for improvement" is displayed on the review screen.

[1050] 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.

[1051] 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.

[1052] 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.

[1053] [Third embodiment]

[1054] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[1055] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[1056] 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).

[1057] 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.

[1058] 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.

[1059] 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).

[1060] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1061] 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.

[1062] 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.

[1063] 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.

[1064] 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.

[1065] 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."

[1066] This invention is a customizable role-playing system using AI that significantly improves training efficiency, especially in call centers and sales departments. The system consists of the following main components:

[1067] Data input method

[1068] Scenario generation method

[1069] Interaction methods

[1070] Response Generation Method

[1071] Feedback Generation Method

[1072] storage means

[1073] Review Method

[1074] The specific operation will be explained below.

[1075] Data input method

[1076] After a user logs in, the server checks the user's profile information (such as product information and past performance data) and customizes the system based on the necessary data, which may include general data from the Internet or original data provided by the company.

[1077] Scenario generation method

[1078] The scenario generation means creates a role-playing scenario based on the data input by the server through the data input means. The scenario is customized taking into account the profile information of the user.

[1079] Interaction methods

[1080] As a means of interaction, the server interacts with the user based on the generated scenario. An interactive screen is displayed on the terminal from the server, and the user asks questions and answers according to the scenario.

[1081] Response Generation Method

[1082] The response generation means uses the AI ​​model to generate an appropriate response based on the user's input (questions and responses) received by the server, and the generated response is provided to the user via the device.

[1083] Feedback Generation Method

[1084] The feedback generation means allows the server to analyze the user's performance after the dialogue is completed and generate feedback. The analysis includes the quality of the user's questions and responses, response time, etc. The generated feedback is displayed on the terminal.

[1085] storage means

[1086] As a storage means, the server stores the results and feedback of the interactions in a database for later review and analysis.

[1087] Review Method

[1088] The review function allows users to later check the stored dialogue results and feedback. The server displays the saved logs on the terminal, allowing users to review their past performance and use it to improve.

[1089] Specific examples

[1090] For example, consider a case where role-playing of product inquiries is carried out in a new employee training mode.

[1091] New user A logs in

[1092] The user logs in to the system from the terminal, and the server performs user authentication.

[1093] Select Onboarding Mode

[1094] The user selects "new employee training mode" on the terminal, and the server reads scenario data based on the selected mode information.

[1095] Inputting customized data

[1096] The server checks User_A's profile information (such as product information) and customizes the scenario based on the relevant data.

[1097] Role-playing begins

[1098] The user clicks the "Start Role-Playing" button, and the server launches the AI ​​model and displays the interactive screen on the device.

[1099] Response Generation

[1100] The user types "How long is the warranty period for this product?" into the terminal, and the server uses an AI model to generate and display the appropriate response: "This product has a one-year warranty period."

[1101] Providing Feedback

[1102] After the session ends, the server generates feedback based on the user's performance and displays it on the device.

[1103] Results storage and review

[1104] The server stores session logs in a database, and users can review past sessions on their devices to learn from them.

[1105] In this way, the use of AI makes it possible to efficiently conduct role-playing training that is in line with practical work.

[1106] The processing flow will be explained below.

[1107] Step 1:

[1108] The user opens the system login screen on the device. They enter their user ID and password, which the device then sends to the server. The server authenticates the user ID and password, and if authentication is successful, the server loads the user's profile information and displays the home screen on the device.

[1109] Step 2:

[1110] The user opens the training mode selection screen on the device and selects the desired mode from "New Employee Training Mode" or "Product Specialized Mode", etc. The device sends the selected mode information to the server. The server loads the scenario data corresponding to the selected training mode and displays the training start screen on the device.

[1111] Step 3:

[1112] The server checks the user's profile information and identifies the necessary customization data (product information, past performance data, etc.). The server collects general data from the internet and original data provided by companies, and inputs this into the AI ​​model to generate customized training scenarios.

[1113] Step 4:

[1114] The user clicks the "Start Role-playing" button on the device. The device notifies the server of this action. The server starts the AI ​​model and starts role-playing based on the customized scenario. The server displays a dialogue screen on the device, and the AI ​​presents the initial scenario.

[1115] Step 5:

[1116] The user enters a question or response into the device (e.g., "How long is the warranty on this product?"). The device sends the input information to the server. The server passes this input to the AI ​​model, which processes it to generate a response. The AI ​​model generates an appropriate response (e.g., "This product has a one-year warranty"). The server sends the generated response to the device, which displays it.

[1117] Step 6:

[1118] When the session ends, the server analyzes the user's questions, responses, response time, accuracy, etc., and generates feedback (e.g., "Your questions were specific and polite"). The feedback data is sent to the device and displayed on the device.

[1119] Step 7:

[1120] The server stores role-playing session logs (questions, responses, feedback, etc.) in a database. The server provides a function to retrieve the logs from the database so that users can review past sessions on their devices. Users can review the evaluations and feedback on their devices and learn from them to improve.

[1121] Example 1

[1122] 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."

[1123] Conventional role-playing training systems lacked sufficient customization based on individual user profile information and performance data, making it difficult to provide efficient training. Additionally, it was difficult to provide appropriate responses to user responses in real time, limiting the effectiveness of the training.

[1124] 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.

[1125] In this invention, the server includes data input means for customizing based on data corresponding to the user, scenario generation means for generating a role-playing scenario based on the input data, dialogue means for dialogue with the user according to the role-playing scenario, response generation means using a generative AI model for generating responses based on the user's dialogue, feedback generation means for generating feedback after the dialogue ends, storage means for storing the dialogue results and feedback, and review means for allowing the user to review the stored dialogue results and feedback. This makes it possible to provide efficient role-playing training customized for each user, significantly improving the effectiveness of the training.

[1126] "Data input means" is a function that collects data such as user profile information and past performance data, and performs customization based on this data.

[1127] The "scenario generation means" is a function that generates a scenario for role-playing training based on input data.

[1128] "Dialogue means" is a function for conducting dialogue with the user according to the generated scenario.

[1129] The "response generation means" is a function that uses a generative AI model to generate an appropriate response based on user input.

[1130] The "feedback generation means" is a function that analyzes the user's performance after the dialogue ends and generates feedback.

[1131] The "storage means" is a function that stores the results of the dialogue and feedback in a database.

[1132] The "review means" is a function that allows the user to later check the stored dialogue results and feedback and use them to make improvements.

[1133] A "generative AI model" is an artificial intelligence model that generates appropriate responses in real time based on user input.

[1134] A "prompt sentence" is an instruction sentence input to an AI model that provides the information necessary to generate a specific response.

[1135] MODE FOR CARRYING OUT THE INVENTION

[1136] This invention is a customizable role-playing system using AI that significantly improves training efficiency, especially in call centers and sales departments. The system consists of the following main components:

[1137] Data input method

[1138] Scenario generation method

[1139] Interaction methods

[1140] Response Generation Method

[1141] Feedback Generation Method

[1142] storage means

[1143] Review Method

[1144] Data input method

[1145] After the user logs in from their device, the server checks the user's profile information (product information, past performance data, etc.) and customizes the system based on the necessary data. This data includes information from the Internet and original data provided by the company.

[1146] Scenario generation method

[1147] The server generates a scenario for role-playing training based on the data acquired through the data input means. This scenario is customized based on the user's profile information. For example, in the new employee training mode, it generates an inquiry scenario about the product that the new employee is responsible for.

[1148] Interaction methods

[1149] The server interacts with the user through the interaction means based on the generated scenario. The interaction screen is displayed on the terminal, and the user can ask questions and respond according to the scenario.

[1150] Response Generation Method

[1151] The server receives input from the user and uses the generative AI model to generate an appropriate response. The generated response is provided to the user via the terminal. For example, if a user inputs, "How long is the warranty period for this product?", the server uses the generative AI model to generate the response, "The warranty period for this product is one year."

[1152] Feedback Generation Method

[1153] After the interaction is completed, the server analyzes the user's performance and generates feedback, including the quality of the user's questions and responses, response times, etc. The generated feedback is displayed on the terminal and serves as a reference for the user to evaluate themselves.

[1154] storage means

[1155] The server stores the results of the interaction and feedback in a database, allowing users to review their performance at a later date and identify ways to improve.

[1156] Review Method

[1157] The server provides a function that allows users to check the stored dialogue results and feedback at any time, allowing users to review past training sessions and maximize learning effectiveness.

[1158] Specific examples

[1159] For example, a case where role-playing of product inquiries is performed in the new employee training mode will be described.

[1160] 1. A user (new employee A) logs in to the system from a terminal. The server authenticates the user and obtains profile information.

[1161] 2. The user selects "New Employee Training Mode" on the device. The server generates a scenario based on this information.

[1162] 3. The server uses the user's profile information to customize the scenario and display the interactive screen on the terminal.

[1163] 4. The user clicks the "Start Role-Playing" button and enters a question according to the scenario, for example, "How long is the warranty on this product?"

[1164] 5. The server uses the generative AI model to generate the appropriate response, "This product has a one-year warranty," and displays it on the device.

[1165] 6. After the session ends, the server analyzes the user's performance and generates feedback that is displayed on the device.

[1166] 7. The server stores the session log in a database, allowing users to review past sessions at a later time.

[1167] Prompt Sentence Examples

[1168] Below are some examples of input prompts for generative AI models:

[1169] Generate an appropriate response when the user types, "How long is the warranty on this product?"

[1170] In this way, by using AI, it is possible to conduct role-playing training that is in line with practical work efficiently and effectively.

[1171] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1172] System program processing flow

[1173] Step 1: Log in the user and get their profile information

[1174] When a user logs in from a terminal, the server receives the login information and performs user authentication. If authentication is successful, the server retrieves the user's profile information (product information, past performance data, etc.) from the database.

[1175] Input: User login information (user ID, password)

[1176] Processing: User authentication, retrieval of profile information

[1177] Output: User profile information

[1178] Step 2: Collect customization data

[1179] Based on the profile information, the server collects additional data from the Internet and company-provided databases, which are used to generate scenarios.

[1180] Input: User profile information

[1181] Processing: API requests to external databases, data collection

[1182] Output: Additional data (product information, etc.)

[1183] Step 3: Scenario generation

[1184] The server generates a customized role-playing scenario using a scenario generation means based on the user's profile information and additional data.

[1185] Input: Profile information, additional data

[1186] Processing: Application of scenario generation algorithm

[1187] Output: Customized scenario

[1188] Step 4: Start role-playing

[1189] The user clicks the "Start Role-Playing" button on the terminal. The server starts the interactive means based on the scenario and displays an interactive screen on the terminal.

[1190] Input: User operation (start of role-playing)

[1191] Processing: Loading scenarios and displaying interactive screens

[1192] Output: Dialogue screen

[1193] Step 5: Dialogue and response generation

[1194] The user inputs a question into the device according to a scenario. For example, "How long is the warranty period for this product?" The server receives this input and generates a response using a generative AI model. The generated response is then displayed on the device.

[1195] Input: User question

[1196] Processing: Response generation by AI model

[1197] Output: The generated response

[1198] Step 6: Feedback generation

[1199] After the role-playing session is over, the server analyzes the user's performance and generates feedback, including the quality of the questions and responses, response time, etc. The generated feedback is displayed on the device.

[1200] Input: Dialogue log (question and response content, response time, etc.)

[1201] Processing: performance analysis, feedback generation

[1202] Output: Generated feedback

[1203] Step 7: Save and review results

[1204] The server stores the interaction results and feedback in a database, and the user can review the saved interaction results later from their terminal.

[1205] Input: The result of the interaction, the generated feedback

[1206] Process: Save to database

[1207] Output: Stored disposition and feedback

[1208] Examples of prompt statements

[1209] Below are some examples of input prompts for generative AI models:

[1210] Generate an appropriate response when the user types, "How long is the warranty on this product?"

[1211]

[1212] (Application example 1)

[1213] 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."

[1214] In modern factories, training is crucial for operators to operate industrial machinery safely and efficiently. However, traditional training methods are time-consuming and costly, making it difficult to provide individually customized training. There is a particular need to provide an effective means for new operators to acquire the necessary skills in a short period of time. Another problem is the lack of a system for effectively storing operator operation logs and providing feedback.

[1215] 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.

[1216] In this invention, the server includes data input means for customizing the system based on data corresponding to the user, scenario generation means for generating a role-playing scenario based on the input data, dialogue means for dialogue with the user according to the role-playing scenario, response generation means for generating a response based on the dialogue of the user, feedback generation means for generating feedback after the dialogue is completed, storage means for storing the results of the dialogue and the feedback, industrial machine training means for providing the dialogue and responses to the user based on the scenario generated for industrial machine operation training, and result storage means for storing operation results in a database. This allows operators to efficiently and effectively acquire industrial machine operation skills, and enables continuous learning and improvement by storing operation logs and feedback.

[1217] The "data input means" is a means for inputting data related to a user, such as the user's profile information and the machine information in charge, into the system.

[1218] The "scenario generation means" is a means for automatically generating scenarios for training and role-playing based on data input via the data input means.

[1219] "Dialogue means" refers to means for interacting with the user according to the generated scenario. This includes interfaces such as text input and voice recognition.

[1220] "Response generation means" refers to a means for generating an appropriate response based on the user's dialogue input. This uses AI models and natural language processing technology.

[1221] A "feedback generation means" is a means for analyzing the user's performance and providing appropriate feedback after the dialogue or role-playing has ended.

[1222] The "storage means" is a means for recording and storing the results of the dialogue and the generated feedback.

[1223] The "industrial machine training means" is a means for providing dialogue and responses to users based on a scenario for conducting training on the operation of industrial machines.

[1224] The "result storage means" is a means for storing operation results and training logs in a database.

[1225] A "review tool" is a tool that allows users to review stored results and feedback at a later time for improvement or revision.

[1226] MODE FOR CARRYING OUT THE INVENTION

[1227] System Program Overview

[1228] In this invention, a plurality of means are combined to provide an industrial machine operation training system customized for each user. The specific processing of each means and its implementation method will be described below.

[1229] Data input method

[1230] After the user logs in, the server checks the profile information and performs customization based on the necessary data. Specifically, the user logs in to the system using a factory tablet or smart glasses. The server obtains the user's past operation data and information about the machine they are responsible for as a profile, and inputs the necessary data based on that. An edge computing server is used for this process.

[1231] Scenario generation method

[1232] As a scenario generation method, the server generates training scenarios for operating industrial machinery based on the input data. Specifically, an AI model trained using an AI model building tool such as TensorFlow generates individually customized training scenarios.

[1233] Interaction methods

[1234] The server interacts with the user based on the scenario generated by the scenario generation means. This is done using a dialogue interface with text input and voice recognition functions. For example, if a dialogue screen is displayed on a tablet and the user types, "What is the inspection procedure for this device?", the server uses an AI model to generate an appropriate response.

[1235] Response Generation Method

[1236] To generate a response, the server analyzes the user's dialogue input and generates an appropriate response using natural language processing technology such as TensorFlow. For example, it generates a specific procedure such as "The inspection procedure is as follows..." and displays it on the screen.

[1237] Feedback Generation Method

[1238] After the interaction with the user is completed, the server evaluates the user's performance and generates feedback, including an evaluation of the accuracy of the operation and response time, which is displayed on the factory tablet or smart glasses.

[1239] storage means

[1240] The server stores the results and feedback of the interactions in a database, allowing for later review and analysis, using a database management system such as PostgreSQL.

[1241] Industrial Machinery Training Tools

[1242] The server provides dialogue and responses to users based on scenarios for training on the operation of industrial machinery, allowing users to efficiently and effectively acquire the skills to operate industrial machinery.

[1243] Results storage means

[1244] The server stores the results of the operation in a database, which users can later review and use as a reference for their studies.

[1245] Specific examples

[1246] When a new operator logs in to a factory tablet and selects the safety inspection training mode in the system, the server generates a customized scenario based on the machine information for which they are responsible. The AI ​​model then activates a dialogue screen on the tablet, providing specific responses to questions such as, "What is the inspection procedure for this equipment?" After completing the training, the operator is given a performance evaluation and feedback, and all operation logs and feedback are stored in a database.

[1247] Prompt Sentence Examples

[1248] “You are an AI that generates detailed inspection procedures for a factory operator training system. When a new operator asks, ‘What is the inspection procedure for this equipment?’ you provide them with the appropriate detailed inspection procedure.”

[1249] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1250] Specific process steps for carrying out the invention

[1251] Step 1:

[1252] Data input

[1253] Input: User login information, user profile information (past operation data, machine information, etc.)

[1254] The server checks the profile information after the user logs in to the device. It uses the edge computing server to acquire past operation data and information about the machine in charge, and inputs this information into the server as profile information. This input data is then used to generate scenarios.

[1255] Step 2:

[1256] Scenario Generation

[1257] Input: Entered profile information

[1258] Output: Customized industrial machine operation training scenario

[1259] The server uses a scenario generation means to generate industrial machine operation training scenarios based on the input profile information. An AI model trained using TensorFlow automatically generates individually customized training scenarios based on this profile information.

[1260] Step 3:

[1261] Start a dialogue

[1262] Input: Generated training scenarios

[1263] Output: Display of dialogue screen, initial dialogue content

[1264] The server displays an interactive screen on a device (tablet, smart glasses, etc.) based on the generated scenario. The user begins role-playing by viewing the interactive screen.

[1265] Step 4:

[1266] User interactive input

[1267] Input: User question or request (e.g., "What is the inspection procedure for this device?")

[1268] Output: Dialogue input data

[1269] Users enter questions or requests into an interactive screen on their device, and this data is sent to the server, which then generates the next response.

[1270] Step 5:

[1271] Response Generation

[1272] Input: Interactive input data

[1273] Output: Response content (e.g. "The inspection procedure is as follows...")

[1274] The server receives the user's dialogue input and generates an appropriate response using a response generation means, using natural language processing technology such as TensorFlow to provide an accurate response to the user's question.

[1275] Step 6:

[1276] Feedback Generation

[1277] Input: Dialogue logs, user operation data

[1278] Output: Feedback content (e.g., operation accuracy, response time, etc.)

[1279] After the interaction is completed, the server analyzes the user's performance data and generates feedback using the feedback generation means. Specific evaluations and suggestions are made based on the accuracy of the user's operations and response times.

[1280] Step 7:

[1281] Result memory

[1282] Input: Dialogue results, feedback

[1283] Output: Saved log data

[1284] The server uses a storage means to store the results of the interaction and the generated feedback in a database, using a database management system such as PostgreSQL to record the results for later review and analysis.

[1285] Step 8:

[1286] Confirmation by review method

[1287] Input: Saved log data

[1288] Output: Review screen

[1289] The server allows users to later check the saved dialogue results and feedback. Users can log in using their devices and check the review screen to learn from past training content.

[1290] Prompt Sentence Examples

[1291] “You are an AI that generates detailed inspection procedures for a factory operator training system. When a new operator asks, ‘What is the inspection procedure for this equipment?’ you provide them with the appropriate detailed inspection procedure.”

[1292] 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.

[1293] This invention is a customizable role-playing system using AI that significantly improves training efficiency, especially in call centers and sales departments. This system consists of the following components:

[1294] 1. Data input method

[1295] 2. Scenario Generation Method

[1296] 3. Means of interaction

[1297] 4. Response Generation Method

[1298] 5. Feedback Generation Methods

[1299] 6. Storage means

[1300] 7. Review Methods

[1301] 8. Emotion Engine

[1302] The specific operation of this system will now be described.

[1303] Data input method

[1304] After the user logs in, the server checks the profile information for the user and customizes the user's profile based on the necessary data. This data includes general data from the Internet and original data provided by the company.

[1305] Scenario generation method

[1306] The scenario generating means generates a role-playing scenario based on the data input by the server through the data input means. This scenario is customized taking into account the profile information of the user.

[1307] Interaction methods

[1308] As a dialogue method, the server dialogues with the user based on the generated scenario. The dialogue screen is displayed on the terminal from the server, and the user dialogues alternately according to the scenario.

[1309] Response Generation Method

[1310] The response generation means uses the AI ​​model to generate an appropriate response based on the user's input (questions and responses) received by the server. The generated response is then provided to the user via their device.

[1311] Feedback Generation Method

[1312] The feedback generation means allows the server to analyze the user's performance after the dialogue is completed and generate feedback. The analysis includes the quality of the user's questions and responses, response time, etc. The generated feedback is displayed on the terminal.

[1313] storage means

[1314] As a storage means, the server stores the results and feedback of the interactions in a database for later review and analysis.

[1315] Review Method

[1316] The review function allows users to later check the stored dialogue results and feedback. The server displays the saved logs on the terminal, allowing users to review their past performance and use it to improve.

[1317] Emotion Engine

[1318] The emotion engine analyzes emotions from the user's voice and text inputs and provides the results to the response generation means. The server recognizes emotions through the emotion engine and adjusts the tone and content of the dialogue in real time.

[1319] Specific examples

[1320] For example, consider a case where role-playing of product inquiries is carried out in a new employee training mode.

[1321] New user A logs in

[1322] The user logs in to the system from the terminal, and the server performs user authentication.

[1323] Select Onboarding Mode

[1324] The user selects "new employee training mode" on the terminal, and the server reads scenario data based on the selected mode information.

[1325] Inputting customized data

[1326] The server checks User A's profile information (such as product information) and customizes the scenario based on the relevant data.

[1327] Role-playing begins

[1328] The user clicks the "Start Role-Playing" button, and the server launches the AI ​​model and displays the interactive screen on the device.

[1329] Response Generation

[1330] The user types "How long is the warranty period for this product?" into the terminal, and the server uses an AI model to generate and display the appropriate response: "This product has a one-year warranty period."

[1331] Use of emotion engine

[1332] The server uses an emotion engine to analyze the emotions contained in the user's input and adjust the tone of the dialogue. For example, if the user's question sounds tired, the AI ​​model will generate a gentler response.

[1333] Providing Feedback

[1334] After the session ends, the server generates feedback based on the user's performance, including opinions based on emotion recognition.

[1335] Results storage and review

[1336] The server stores session logs in a database, and users can review past sessions on their devices to learn from them.

[1337] In this way, this system makes full use of AI and an emotion engine to realize role-playing that is more human-like, thereby helping users improve their skills.

[1338] The processing flow will be explained below.

[1339] Role-playing system processing steps

[1340] Step 1:

[1341] The user opens the system login screen on the device and enters their user ID and password. The device sends the entered information to the server. The server authenticates the user ID and password, and if authentication is successful, the server loads the user's profile information and displays the home screen on the device.

[1342] Step 2:

[1343] The user opens the training mode selection screen on the device and selects the desired mode from "New Employee Training Mode" or "Product Specialized Mode", etc. The device sends the selected mode information to the server. The server loads the scenario data corresponding to the selected training mode and displays the training start screen on the device.

[1344] Step 3:

[1345] The server checks the user's profile information and identifies the necessary customization data (product information, past performance data, etc.). The server collects general data from the internet and original data provided by companies, and inputs this into the AI ​​model to generate customized training scenarios.

[1346] Step 4:

[1347] The user clicks the "Start Role-playing" button on the device. The device notifies the server of this action. The server starts the AI ​​model and starts role-playing based on the customized scenario. The server displays a dialogue screen on the device, and the AI ​​presents the initial scenario.

[1348] Step 5:

[1349] The user enters a question or response into the device (e.g., "How long is the warranty on this product?"). The device sends the input information to the server. The server passes this input to the AI ​​model, which processes it to generate a response. The AI ​​model generates an appropriate response (e.g., "This product has a one-year warranty"). The server sends the generated response to the device, which displays it.

[1350] Step 6:

[1351] The server uses an emotion engine to analyze emotions from the user's voice and text input. The emotion engine analyzes the user's emotions and provides the results to the server. The server receives the emotion engine's output and adjusts the tone and content of the dialogue in real time. For example, if the user is tired, the AI ​​model will generate a gentler tone in the response.

[1352] Step 7:

[1353] When the session ends, the server analyzes the user's questions, responses, response time, accuracy, etc., and generates feedback (e.g., "Your questions were specific and polite"). The feedback data is sent to the device and displayed on the device.

[1354] Step 8:

[1355] The server stores role-playing session logs (questions, responses, feedback, etc.) in a database. The server provides a function to retrieve saved logs from the database so that users can review past sessions on their devices. Users can review the evaluations and feedback on their devices and learn from them to improve.

[1356] Example 2

[1357] 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."

[1358] Conventional role-playing systems lack the ability to customize to the individual needs of each user, analyze emotions during dialogue, and provide feedback. As a result, training effectiveness could not be maximized, and there were issues with improving individual skills and improving training efficiency.

[1359] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1360] In this invention, the server includes data input means for customizing based on data corresponding to the user, scenario generation means for generating a role-playing scenario based on the input data, dialogue means for dialogue with the user according to the role-playing scenario, response generation means for generating a response based on the user's dialogue, feedback generation means for generating feedback after the dialogue ends, storage means for storing the results of the dialogue and the feedback, and an emotion engine for analyzing emotions from the user's voice and text input and reflecting them in response generation. This makes it possible to provide training scenarios that correspond to the individual situation of each user, adjust dialogue based on emotions, and provide consistent performance evaluation and feedback.

[1361] "User" refers to any individual or entity who uses and receives training on this system.

[1362] "Data input means" refers to the means for acquiring data according to the user and inputting it into the system.

[1363] "Scenario generation means" refers to a means for generating a customized role-playing scenario based on input data.

[1364] "Interaction means" refers to a means for interacting with a user according to the generated role-playing scenario.

[1365] The "response generation means" refers to a means for generating an appropriate response based on the user's interaction.

[1366] "Feedback generation means" refers to a means for analyzing a user's performance and generating feedback after an interaction session has ended.

[1367] "Storage means" refers to a means for storing the results and feedback of an interaction for later review and analysis.

[1368] An "emotion engine" refers to a means of analyzing emotions from a user's voice and text input and reflecting the results in generating a response.

[1369] "Review means" refers to a means by which a user can later review the results and feedback stored in the storage means.

[1370] "Internet-derived data" means public or commercial data accessible through a wide area communications network.

[1371] "Original data provided by companies" refers to data that companies collect and provide independently.

[1372] This invention is a customizable role-playing system using AI that significantly improves training efficiency, especially in call centers and sales departments. The system consists of the following main components:

[1373] Data input method

[1374] After the user logs in, the server performs user authentication. At this time, it checks the user profile information and customizes the user's profile based on the necessary data. This data includes general data obtained from the Internet and original data provided by the company.

[1375] Scenario generation method

[1376] The scenario generation means generates a role-playing scenario based on the data input by the server through the data input means. This scenario is customized taking into account the user's profile information. Specifically, a scenario is generated based on the product and role that the user is responsible for.

[1377] Interaction methods

[1378] The server then interacts with the user based on the generated scenario. The interaction screen is displayed on the terminal, and the user interacts with the scenario in turn.

[1379] Response Generation Method

[1380] The server receives user input (questions and responses) and uses the generative AI model to generate an appropriate response. For example, if a user asks, "How long is the warranty period for this product?", the generative AI model responds, "This product has a one-year warranty period."

[1381] Emotion Engine

[1382] The emotion engine analyzes emotions from the user's voice and text input and provides the results to the response generation means. The server recognizes emotions through the emotion engine and adjusts the tone and content of the dialogue in real time. For example, if the user's input shows signs of fatigue, the AI ​​model will generate a response with a gentler tone.

[1383] Feedback Generation Method

[1384] After the interaction session, the server analyzes the user's performance and generates feedback, including the quality of the user's questions and responses, response times, and opinions based on emotion recognition.

[1385] storage means

[1386] The server stores the results and feedback of the interactions in a database for later review and further analysis.

[1387] Review Method

[1388] The server displays the saved interaction results and feedback on the device, allowing the user to check their past performance, facilitating self-evaluation and learning.

[1389] Specific examples

[1390] For example, consider a case where role-playing of product inquiries is carried out in a training mode for new employees at a call center.

[1391] New user A logs in

[1392] The user logs in to the system from the terminal, and the server performs user authentication.

[1393] Select Onboarding Mode

[1394] The user selects the "new employee training mode," and the server reads scenario data based on the selected mode information.

[1395] Inputting customized data

[1396] The server checks User A's profile information (such as product information) and customizes the scenario based on the relevant data.

[1397] Role-playing begins

[1398] The user clicks the "Start Role-Playing" button, and the server launches the generated AI model and displays the interactive screen on the device.

[1399] Response Generation

[1400] The user types, "How long is the warranty period for this product?", and the server uses a generative AI model to generate the appropriate response, "This product has a one-year warranty period," which is displayed on the device.

[1401] Use of emotion engine

[1402] The server uses an emotion engine to analyze the emotions contained in the user's input and adjust the tone of the dialogue. For example, if the user's question sounds tired, the AI ​​model will generate a gentler response.

[1403] Providing Feedback

[1404] After the session ends, the server generates feedback based on the user's performance and displays it on the device, including opinions based on emotion recognition.

[1405] Results storage and review

[1406] The server stores session logs in a database, and users can review past sessions on their devices to learn from them.

[1407] In this way, this system makes full use of AI and an emotion engine to realize role-playing in a manner that is close to human, thereby helping users improve their skills.

[1408] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1409] Step 1:

[1410] The user enters login information (username, password) into the terminal.

[1411] Input: Username, Password

[1412] The server receives this information and authenticates the user by checking the user information against a database.

[1413] Data processing: Verification of authentication information

[1414] Output: Authentication result (success / failure)

[1415] Step 2:

[1416] The server obtains user profile information based on the authentication result.

[1417] Input: Authentication result (user name)

[1418] The server retrieves the user's profile information (such as product information) from the database.

[1419] Data processing: Extracting user profiles

[1420] Output: User profile information

[1421] Step 3:

[1422] The user selects the mode to be used on the device (e.g., new employee training mode).

[1423] Input: Mode selection information

[1424] The server reads scenario data corresponding to the selected mode from the database.

[1425] Data processing: Extraction of scenario data

[1426] Output: Scenario data

[1427] Step 4:

[1428] The server customizes the scenario data based on the acquired user profile information.

[1429] Input: User profile information, scenario data

[1430] The server customizes the scenario based on the profile information (e.g., including specific inquiries about the product they are responsible for).

[1431] Data processing: Scenario customization

[1432] Output: Customized scenario

[1433] Step 5:

[1434] The user clicks the "Start Role-Playing" button on the device.

[1435] Input: Start signal

[1436] The server generates an interactive screen based on the customized scenario and displays it on the terminal.

[1437] Data processing: Generation of interactive screens

[1438] Output: Display of interactive screen

[1439] Step 6:

[1440] The user types a question or response into the terminal (e.g., "How long is the warranty on this product?").

[1441] Input: Question and response text

[1442] The server receives this input and inputs it as a prompt sentence into the generative AI model.

[1443] Data processing: Prompt sentence generation

[1444] Output: Input to the AI ​​model

[1445] Step 7:

[1446] The server uses the generative AI model to generate an appropriate response.

[1447] Input: prompt statement

[1448] The server generates a response from the AI ​​model and obtains the response text (e.g., "This product has a one-year warranty").

[1449] Data processing: response generation

[1450] Output: Response text

[1451] Step 8:

[1452] The server generates a response and displays it on the terminal.

[1453] Input: Response text

[1454] The server sends this response to the terminal and displays it to the user.

[1455] Data processing: Generation of data for display

[1456] Output: Display to terminal

[1457] Step 9:

[1458] The server uses an emotion engine to analyze the emotion contained in the user's input.

[1459] Input: User question and response text

[1460] The server analyzes the emotional state of the input text with an emotion engine and obtains the result.

[1461] Data Processing: Sentiment Analysis

[1462] Output: Sentiment analysis results

[1463] Step 10:

[1464] The server uses the results of the sentiment analysis to adjust the tone of the dialogue and feed it into the generative AI model.

[1465] Input: Sentiment analysis results

[1466] The server adjusts the output tone of the generative AI model based on the results of the emotion analysis.

[1467] Data processing: Adjusting the tone of the dialogue

[1468] Output: Adjusted response

[1469] Step 11:

[1470] The server analyzes the user's performance and generates feedback after the interactive session ends.

[1471] Input: conversation logs, response times, sentiment analysis results

[1472] The server analyzes this data and generates feedback.

[1473] Data processing: performance analysis and feedback generation

[1474] Output: Feedback

[1475] Step 12:

[1476] The server displays the feedback on the device.

[1477] Input: Feedback

[1478] The server sends the feedback to the terminal and displays it to the user.

[1479] Data processing: Generation of data for display

[1480] Output: Display to terminal

[1481] Step 13:

[1482] The server stores the results of the interaction and feedback in a database.

[1483] Input: Dialogue result, feedback

[1484] The server stores this data in a database.

[1485] Data processing: Data storage

[1486] Output: Saved

[1487] Step 14:

[1488] The user checks past sessions on the device.

[1489] Input: Review request

[1490] The server retrieves the saved dialogue results and feedback and displays them on the terminal.

[1491] Data processing: Data acquisition and generation of data for display

[1492] Output: Show past sessions

[1493] (Application example 2)

[1494] 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."

[1495] Traditional factory operator training systems lacked real-time interactive simulation and feedback, making effective training difficult. They also struggled to implement role-playing customized for specific scenarios and lacked the flexibility to adapt to diverse work environments. Furthermore, they lacked the ability to review training results afterward, limiting opportunities for operators to reflect on and improve their performance.

[1496] 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.

[1497] In this invention, the server includes: a data input means for customizing the system based on data corresponding to the user; a scenario generation means for generating a role-playing scenario based on the input data; a dialogue means for dialogue with the user according to the role-playing scenario; a response generation means for generating a response based on the dialogue of the user; a feedback generation means for generating feedback after the dialogue is completed; a storage means for storing the results of the dialogue and the feedback; a scenario generation means for generating a scenario to support the training of in-factory operators; a dialogue means for simulating a dialogue with the user based on the generated scenario; a generative AI model means for generating appropriate responses based on user input; and a review means for allowing the user to review the generated feedback after the training session is completed. This allows for real-time dialogue simulation and feedback to be provided to factory operators, enabling effective training and performance review.

[1498] The "data input means" is a means for inputting user profile information and related data into the server and customizing the system.

[1499] The "scenario generation means" is a means for generating a role-playing scenario suited to the user based on the information obtained from the data input means.

[1500] The "interaction means" is a means for interacting with the user based on the generated role-playing scenario.

[1501] The "response generation means" is a means for generating an appropriate response to an input from a user.

[1502] The "feedback generation means" is a means for analyzing the user's performance after the dialogue is completed and generating feedback.

[1503] "Storage means" is a means for storing the results of the interaction and the generated feedback.

[1504] The "role-playing system for in-factory operator training" is a system for training in-factory operators using actual work scenarios.

[1505] A "generative AI model means" is an artificial intelligence model used to generate an appropriate response based on user input.

[1506] A "review facility" is a facility that allows users to later review and reflect on the feedback and interaction logs generated after the training session is completed.

[1507] The "simulation means" is a means for simulating real-time interactions in a virtual environment and simulating actual operations.

[1508] An "appropriate response" is a context- and content-matched answer generated in response to user input using a generative AI model.

[1509] "Users" are those who will use this system and receive training, such as factory operators.

[1510] The present invention is a system for supporting the training of in-factory operators, and is realized using specific hardware and software. This system operates in the following steps.

[1511] Hardware and software used

[1512] The server installs the AI ​​model and performs the main computational processing required to execute the dialogue. Specifically, it is recommended to use an EC2 instance from Amazon Web Services (AWS). AWS RDS is suitable for storing the database. The AI ​​model uses the T5 model with the Hugging Face transformers library.

[1513] Data input and scenario generation

[1514] The server uses data input means to customize data based on user profile information, including general data obtained from the Internet and specific operational data provided by the enterprise.

[1515] Next, the server generates role-playing scenarios for in-factory operator training based on the information obtained from the data input means. The scenario generation means creates scenarios including specific work procedures and situations based on the user profile.

[1516] Interaction methods and response generation

[1517] When the user starts training, the server simulates a dialogue based on a scenario generated by the scenario generation means. At this time, the dialogue means interfaces with the user and guides the progress of the role-playing.

[1518] Based on the user's questions and input, the server generates an appropriate response using the response generation means. The generative AI model means (T5 model) provides an answer that matches the context and content based on the user's input.

[1519] Feedback generation and review features

[1520] After the interaction is completed, the server uses a feedback generating means to generate feedback on the user's performance, including the quality of the interaction, response time, and the emotion analysis results of the emotion engine.

[1521] The generated feedback and interaction logs are stored in a database using a storage means, and a review means is provided so that users can later reflect on their performance and identify areas for improvement.

[1522] Adding specific examples

[1523] For example, if a user asks, "What is the operating procedure for this machine?", the server uses the AI ​​model to generate a response such as, "The operating procedure for this machine is as follows: First, turn it on, then press the setting button..." After the training session, the server generates feedback such as, "Overall, good. You performed the work correctly, but there is room for improvement in efficiency."

[1524] As described above, the present invention is a system for effectively supporting factory operator skill improvement, and is capable of real-time interactive simulation and personalized feedback.

[1525] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1526] Step 1:

[1527] The server retrieves the user's profile information.

[1528] Input: User login information.

[1529] Output: User profile information.

[1530] Specific operation: Based on the login information provided by the terminal, the server accesses the database and retrieves the user's profile information, which includes past interaction history and information about the machine in charge.

[1531] Step 2:

[1532] The server populates the relevant data using the data populating means.

[1533] Input: User profile information.

[1534] Output: Data for customized scenario generation.

[1535] Specific Operation: The server uses internet and company-provided data to populate the role-playing scenario with data to customize it based on the user's profile information.

[1536] Step 3:

[1537] The server generates a role-playing scenario using a scenario generation means.

[1538] Input: Customized data.

[1539] Output: Scenarios for in-factory operator training.

[1540] Specific operation: Based on the input data, the server generates specific work scenarios within the factory. These scenarios are tailored to the user's work responsibilities and skill level.

[1541] Step 4:

[1542] The terminal starts a dialogue with the user using the dialogue means.

[1543] Input: The generated scenario.

[1544] Output: Interactive interface display.

[1545] Specific operation: A dialogue interface based on the generated scenario is displayed on the terminal, and the user begins dialogue according to the scenario.

[1546] Step 5:

[1547] The server uses a response generation means to generate a response to the user's input.

[1548] Input: User questions or input.

[1549] Output: Appropriate response.

[1550] Specific operation: The server receives the question entered by the user into the terminal, generates an appropriate response using the generative AI model means (T5 model), and displays it on the terminal. For example, in response to the user's input, "What is the operating procedure for this machine?", the server generates the response, "The operating procedure for this machine is as follows. First, turn on the power, then press the setting button..."

[1551] Step 6:

[1552] The server generates the feedback using the feedback generating means.

[1553] Input: The result of the user's interaction.

[1554] Output: Feedback information.

[1555] Specific operation: After the dialogue ends, the server analyzes the content of the dialogue and the response time of the user, and generates feedback, including the quality of the dialogue and the results of emotion analysis by the emotion engine.

[1556] Step 7:

[1557] The server uses a storage means to store the interaction results and feedback.

[1558] Input: Interaction outcome and feedback information.

[1559] Output: Saved interaction logs and feedback.

[1560] Specific Actions: The server stores the generated feedback and interaction logs in a database for later review.

[1561] Step 8:

[1562] The terminal uses the review means to display the feedback and interaction log to the user.

[1563] Input: Saved interaction logs and feedback.

[1564] Output: The review information displayed to the user.

[1565] What it does: Allows users to use their devices to review logs and feedback from past training sessions. For example, feedback such as "Overall good. You followed the correct procedures, but there is room for improvement" is displayed on the review screen.

[1566] 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.

[1567] 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.

[1568] 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.

[1569] [Fourth embodiment]

[1570] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1571] 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.

[1572] 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).

[1573] 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.

[1574] 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.

[1575] 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).

[1576] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1577] 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.

[1578] 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.

[1579] 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.

[1580] 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.

[1581] 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.

[1582] 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."

[1583] This invention is a customizable role-playing system using AI that significantly improves training efficiency, especially in call centers and sales departments. The system consists of the following main components:

[1584] Data input method

[1585] Scenario generation method

[1586] Interaction methods

[1587] Response Generation Method

[1588] Feedback Generation Method

[1589] storage means

[1590] Review Method

[1591] The specific operation will be explained below.

[1592] Data input method

[1593] After a user logs in, the server checks the user's profile information (such as product information and past performance data) and customizes the system based on the necessary data, which may include general data from the Internet or original data provided by the company.

[1594] Scenario generation method

[1595] The scenario generation means creates a role-playing scenario based on the data input by the server through the data input means. The scenario is customized taking into account the profile information of the user.

[1596] Interaction methods

[1597] As a means of interaction, the server interacts with the user based on the generated scenario. An interactive screen is displayed on the terminal from the server, and the user asks questions and answers according to the scenario.

[1598] Response Generation Method

[1599] The response generation means uses the AI ​​model to generate an appropriate response based on the user's input (questions and responses) received by the server, and the generated response is provided to the user via the device.

[1600] Feedback Generation Method

[1601] The feedback generation means allows the server to analyze the user's performance after the dialogue is completed and generate feedback. The analysis includes the quality of the user's questions and responses, response time, etc. The generated feedback is displayed on the terminal.

[1602] storage means

[1603] As a storage means, the server stores the results and feedback of the interactions in a database for later review and analysis.

[1604] Review Method

[1605] The review function allows users to later check the stored dialogue results and feedback. The server displays the saved logs on the terminal, allowing users to review their past performance and use it to improve.

[1606] Specific examples

[1607] For example, consider a case where role-playing of product inquiries is carried out in a new employee training mode.

[1608] New user A logs in

[1609] The user logs in to the system from the terminal, and the server performs user authentication.

[1610] Select Onboarding Mode

[1611] The user selects "new employee training mode" on the terminal, and the server reads scenario data based on the selected mode information.

[1612] Inputting customized data

[1613] The server checks User_A's profile information (such as product information) and customizes the scenario based on the relevant data.

[1614] Role-playing begins

[1615] The user clicks the "Start Role-Playing" button, and the server launches the AI ​​model and displays the interactive screen on the device.

[1616] Response Generation

[1617] The user types "How long is the warranty period for this product?" into the terminal, and the server uses an AI model to generate and display the appropriate response: "This product has a one-year warranty period."

[1618] Providing Feedback

[1619] After the session ends, the server generates feedback based on the user's performance and displays it on the device.

[1620] Results storage and review

[1621] The server stores session logs in a database, and users can review past sessions on their devices to learn from them.

[1622] In this way, the use of AI makes it possible to efficiently conduct role-playing training that is in line with practical work.

[1623] The processing flow will be explained below.

[1624] Step 1:

[1625] The user opens the system login screen on the device. They enter their user ID and password, which the device then sends to the server. The server authenticates the user ID and password, and if authentication is successful, the server loads the user's profile information and displays the home screen on the device.

[1626] Step 2:

[1627] The user opens the training mode selection screen on the device and selects the desired mode from "New Employee Training Mode" or "Product Specialized Mode", etc. The device sends the selected mode information to the server. The server loads the scenario data corresponding to the selected training mode and displays the training start screen on the device.

[1628] Step 3:

[1629] The server checks the user's profile information and identifies the necessary customization data (product information, past performance data, etc.). The server collects general data from the internet and original data provided by companies, and inputs this into the AI ​​model to generate customized training scenarios.

[1630] Step 4:

[1631] The user clicks the "Start Role-playing" button on the device. The device notifies the server of this action. The server starts the AI ​​model and starts role-playing based on the customized scenario. The server displays a dialogue screen on the device, and the AI ​​presents the initial scenario.

[1632] Step 5:

[1633] The user enters a question or response into the device (e.g., "How long is the warranty on this product?"). The device sends the input information to the server. The server passes this input to the AI ​​model, which processes it to generate a response. The AI ​​model generates an appropriate response (e.g., "This product has a one-year warranty"). The server sends the generated response to the device, which displays it.

[1634] Step 6:

[1635] When the session ends, the server analyzes the user's questions, responses, response time, accuracy, etc., and generates feedback (e.g., "Your questions were specific and polite"). The feedback data is sent to the device and displayed on the device.

[1636] Step 7:

[1637] The server stores role-playing session logs (questions, responses, feedback, etc.) in a database. The server provides a function to retrieve the logs from the database so that users can review past sessions on their devices. Users can review the evaluations and feedback on their devices and learn from them to improve.

[1638] Example 1

[1639] 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."

[1640] Conventional role-playing training systems lacked sufficient customization based on individual user profile information and performance data, making it difficult to provide efficient training. Additionally, it was difficult to provide appropriate responses to user responses in real time, limiting the effectiveness of the training.

[1641] 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.

[1642] In this invention, the server includes data input means for customizing based on data corresponding to the user, scenario generation means for generating a role-playing scenario based on the input data, dialogue means for dialogue with the user according to the role-playing scenario, response generation means using a generative AI model for generating responses based on the user's dialogue, feedback generation means for generating feedback after the dialogue ends, storage means for storing the dialogue results and feedback, and review means for allowing the user to review the stored dialogue results and feedback. This makes it possible to provide efficient role-playing training customized for each user, significantly improving the effectiveness of the training.

[1643] "Data input means" is a function that collects data such as user profile information and past performance data, and performs customization based on this data.

[1644] The "scenario generation means" is a function that generates a scenario for role-playing training based on input data.

[1645] "Dialogue means" is a function for conducting dialogue with the user according to the generated scenario.

[1646] The "response generation means" is a function that uses a generative AI model to generate an appropriate response based on user input.

[1647] The "feedback generation means" is a function that analyzes the user's performance after the dialogue ends and generates feedback.

[1648] The "storage means" is a function that stores the results of the dialogue and feedback in a database.

[1649] The "review means" is a function that allows the user to later check the stored dialogue results and feedback and use them to make improvements.

[1650] A "generative AI model" is an artificial intelligence model that generates appropriate responses in real time based on user input.

[1651] A "prompt sentence" is an instruction sentence input to an AI model that provides the information necessary to generate a specific response.

[1652] MODE FOR CARRYING OUT THE INVENTION

[1653] This invention is a customizable role-playing system using AI that significantly improves training efficiency, especially in call centers and sales departments. The system consists of the following main components:

[1654] Data input method

[1655] Scenario generation method

[1656] Interaction methods

[1657] Response Generation Method

[1658] Feedback Generation Method

[1659] storage means

[1660] Review Method

[1661] Data input method

[1662] After the user logs in from their device, the server checks the user's profile information (product information, past performance data, etc.) and customizes the system based on the necessary data. This data includes information from the Internet and original data provided by the company.

[1663] Scenario generation method

[1664] The server generates a scenario for role-playing training based on the data acquired through the data input means. This scenario is customized based on the user's profile information. For example, in the new employee training mode, it generates an inquiry scenario about the product that the new employee is responsible for.

[1665] Interaction methods

[1666] The server interacts with the user through the interaction means based on the generated scenario. The interaction screen is displayed on the terminal, and the user can ask questions and respond according to the scenario.

[1667] Response Generation Method

[1668] The server receives input from the user and uses the generative AI model to generate an appropriate response. The generated response is provided to the user via the terminal. For example, if a user inputs, "How long is the warranty period for this product?", the server uses the generative AI model to generate the response, "The warranty period for this product is one year."

[1669] Feedback Generation Method

[1670] After the interaction is completed, the server analyzes the user's performance and generates feedback, including the quality of the user's questions and responses, response times, etc. The generated feedback is displayed on the terminal and serves as a reference for the user to evaluate themselves.

[1671] storage means

[1672] The server stores the results of the interaction and feedback in a database, allowing users to review their performance at a later date and identify ways to improve.

[1673] Review Method

[1674] The server provides a function that allows users to check the stored dialogue results and feedback at any time, allowing users to review past training sessions and maximize learning effectiveness.

[1675] Specific examples

[1676] For example, a case where role-playing of product inquiries is performed in the new employee training mode will be described.

[1677] 1. A user (new employee A) logs in to the system from a terminal. The server authenticates the user and obtains profile information.

[1678] 2. The user selects "New Employee Training Mode" on the device. The server generates a scenario based on this information.

[1679] 3. The server uses the user's profile information to customize the scenario and display the interactive screen on the terminal.

[1680] 4. The user clicks the "Start Role-Playing" button and enters a question according to the scenario, for example, "How long is the warranty on this product?"

[1681] 5. The server uses the generative AI model to generate the appropriate response, "This product has a one-year warranty," and displays it on the device.

[1682] 6. After the session ends, the server analyzes the user's performance and generates feedback that is displayed on the device.

[1683] 7. The server stores the session log in a database, allowing users to review past sessions at a later time.

[1684] Prompt Sentence Examples

[1685] Below are some examples of input prompts for generative AI models:

[1686] Generate an appropriate response when the user types, "How long is the warranty on this product?"

[1687] In this way, by using AI, it is possible to conduct role-playing training that is in line with practical work efficiently and effectively.

[1688] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1689] System program processing flow

[1690] Step 1: Log in the user and get their profile information

[1691] When a user logs in from a terminal, the server receives the login information and performs user authentication. If authentication is successful, the server retrieves the user's profile information (product information, past performance data, etc.) from the database.

[1692] Input: User login information (user ID, password)

[1693] Processing: User authentication, retrieval of profile information

[1694] Output: User profile information

[1695] Step 2: Collect customization data

[1696] Based on the profile information, the server collects additional data from the Internet and company-provided databases, which are used to generate scenarios.

[1697] Input: User profile information

[1698] Processing: API requests to external databases, data collection

[1699] Output: Additional data (product information, etc.)

[1700] Step 3: Scenario generation

[1701] The server generates a customized role-playing scenario using a scenario generation means based on the user's profile information and additional data.

[1702] Input: Profile information, additional data

[1703] Processing: Application of scenario generation algorithm

[1704] Output: Customized scenario

[1705] Step 4: Start role-playing

[1706] The user clicks the "Start Role-Playing" button on the terminal. The server starts the interactive means based on the scenario and displays an interactive screen on the terminal.

[1707] Input: User operation (start of role-playing)

[1708] Processing: Loading scenarios and displaying interactive screens

[1709] Output: Dialogue screen

[1710] Step 5: Dialogue and response generation

[1711] The user inputs a question into the device according to a scenario. For example, "How long is the warranty period for this product?" The server receives this input and generates a response using a generative AI model. The generated response is then displayed on the device.

[1712] Input: User question

[1713] Processing: Response generation by AI model

[1714] Output: The generated response

[1715] Step 6: Feedback generation

[1716] After the role-playing session is over, the server analyzes the user's performance and generates feedback, including the quality of the questions and responses, response time, etc. The generated feedback is displayed on the device.

[1717] Input: Dialogue log (question and response content, response time, etc.)

[1718] Processing: performance analysis, feedback generation

[1719] Output: Generated feedback

[1720] Step 7: Save and review results

[1721] The server stores the interaction results and feedback in a database, and the user can review the saved interaction results later from their terminal.

[1722] Input: The result of the interaction, the generated feedback

[1723] Process: Save to database

[1724] Output: Stored disposition and feedback

[1725] Examples of prompt statements

[1726] Below are some examples of input prompts for generative AI models:

[1727] Generate an appropriate response when the user types, "How long is the warranty on this product?"

[1728]

[1729] (Application example 1)

[1730] 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."

[1731] In modern factories, training is crucial for operators to operate industrial machinery safely and efficiently. However, traditional training methods are time-consuming and costly, making it difficult to provide individually customized training. There is a particular need to provide an effective means for new operators to acquire the necessary skills in a short period of time. Another problem is the lack of a system for effectively storing operator operation logs and providing feedback.

[1732] 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.

[1733] In this invention, the server includes data input means for customizing the system based on data corresponding to the user, scenario generation means for generating a role-playing scenario based on the input data, dialogue means for dialogue with the user according to the role-playing scenario, response generation means for generating a response based on the dialogue of the user, feedback generation means for generating feedback after the dialogue is completed, storage means for storing the results of the dialogue and the feedback, industrial machine training means for providing the dialogue and responses to the user based on the scenario generated for industrial machine operation training, and result storage means for storing operation results in a database. This allows operators to efficiently and effectively acquire industrial machine operation skills, and enables continuous learning and improvement by storing operation logs and feedback.

[1734] The "data input means" is a means for inputting data related to a user, such as the user's profile information and the machine information in charge, into the system.

[1735] The "scenario generation means" is a means for automatically generating scenarios for training and role-playing based on data input via the data input means.

[1736] "Dialogue means" refers to means for interacting with the user according to the generated scenario. This includes interfaces such as text input and voice recognition.

[1737] "Response generation means" refers to a means for generating an appropriate response based on the user's dialogue input. This uses AI models and natural language processing technology.

[1738] A "feedback generation means" is a means for analyzing the user's performance and providing appropriate feedback after the dialogue or role-playing has ended.

[1739] The "storage means" is a means for recording and storing the results of the dialogue and the generated feedback.

[1740] The "industrial machine training means" is a means for providing dialogue and responses to users based on a scenario for conducting training on the operation of industrial machines.

[1741] The "result storage means" is a means for storing operation results and training logs in a database.

[1742] A "review tool" is a tool that allows users to review stored results and feedback at a later time for improvement or revision.

[1743] MODE FOR CARRYING OUT THE INVENTION

[1744] System Program Overview

[1745] In this invention, a plurality of means are combined to provide an industrial machine operation training system customized for each user. The specific processing of each means and its implementation method will be described below.

[1746] Data input method

[1747] After the user logs in, the server checks the profile information and performs customization based on the necessary data. Specifically, the user logs in to the system using a factory tablet or smart glasses. The server obtains the user's past operation data and information about the machine they are responsible for as a profile, and inputs the necessary data based on that. An edge computing server is used for this process.

[1748] Scenario generation method

[1749] As a scenario generation method, the server generates training scenarios for operating industrial machinery based on the input data. Specifically, an AI model trained using an AI model building tool such as TensorFlow generates individually customized training scenarios.

[1750] Interaction methods

[1751] The server interacts with the user based on the scenario generated by the scenario generation means. This is done using a dialogue interface with text input and voice recognition functions. For example, if a dialogue screen is displayed on a tablet and the user types, "What is the inspection procedure for this device?", the server uses an AI model to generate an appropriate response.

[1752] Response Generation Method

[1753] To generate a response, the server analyzes the user's dialogue input and generates an appropriate response using natural language processing technology such as TensorFlow. For example, it generates a specific procedure such as "The inspection procedure is as follows..." and displays it on the screen.

[1754] Feedback Generation Method

[1755] After the interaction with the user is completed, the server evaluates the user's performance and generates feedback, including an evaluation of the accuracy of the operation and response time, which is displayed on the factory tablet or smart glasses.

[1756] storage means

[1757] The server stores the results and feedback of the interactions in a database, allowing for later review and analysis, using a database management system such as PostgreSQL.

[1758] Industrial Machinery Training Tools

[1759] The server provides dialogue and responses to users based on scenarios for training on the operation of industrial machinery, allowing users to efficiently and effectively acquire the skills to operate industrial machinery.

[1760] Results storage means

[1761] The server stores the results of the operation in a database, which users can later review and use as a reference for their studies.

[1762] Specific examples

[1763] When a new operator logs in to a factory tablet and selects the safety inspection training mode in the system, the server generates a customized scenario based on the machine information for which they are responsible. The AI ​​model then activates a dialogue screen on the tablet, providing specific responses to questions such as, "What is the inspection procedure for this equipment?" After completing the training, the operator is given a performance evaluation and feedback, and all operation logs and feedback are stored in a database.

[1764] Prompt Sentence Examples

[1765] “You are an AI that generates detailed inspection procedures for a factory operator training system. When a new operator asks, ‘What is the inspection procedure for this equipment?’ you provide them with the appropriate detailed inspection procedure.”

[1766] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1767] Specific process steps for carrying out the invention

[1768] Step 1:

[1769] Data input

[1770] Input: User login information, user profile information (past operation data, machine information, etc.)

[1771] The server checks the profile information after the user logs in to the device. It uses the edge computing server to acquire past operation data and information about the machine in charge, and inputs this information into the server as profile information. This input data is then used to generate scenarios.

[1772] Step 2:

[1773] Scenario Generation

[1774] Input: Entered profile information

[1775] Output: Customized industrial machine operation training scenario

[1776] The server uses a scenario generation means to generate industrial machine operation training scenarios based on the input profile information. An AI model trained using TensorFlow automatically generates individually customized training scenarios based on this profile information.

[1777] Step 3:

[1778] Start a dialogue

[1779] Input: Generated training scenarios

[1780] Output: Display of dialogue screen, initial dialogue content

[1781] The server displays an interactive screen on a device (tablet, smart glasses, etc.) based on the generated scenario. The user begins role-playing by viewing the interactive screen.

[1782] Step 4:

[1783] User interactive input

[1784] Input: User question or request (e.g., "What is the inspection procedure for this device?")

[1785] Output: Dialogue input data

[1786] Users enter questions or requests into an interactive screen on their device, and this data is sent to the server, which then generates the next response.

[1787] Step 5:

[1788] Response Generation

[1789] Input: Interactive input data

[1790] Output: Response content (e.g. "The inspection procedure is as follows...")

[1791] The server receives the user's dialogue input and generates an appropriate response using a response generation means, using natural language processing technology such as TensorFlow to provide an accurate response to the user's question.

[1792] Step 6:

[1793] Feedback Generation

[1794] Input: Dialogue logs, user operation data

[1795] Output: Feedback content (e.g., operation accuracy, response time, etc.)

[1796] After the interaction is completed, the server analyzes the user's performance data and generates feedback using the feedback generation means. Specific evaluations and suggestions are made based on the accuracy of the user's operations and response times.

[1797] Step 7:

[1798] Result memory

[1799] Input: Dialogue results, feedback

[1800] Output: Saved log data

[1801] The server uses a storage means to store the results of the interaction and the generated feedback in a database, using a database management system such as PostgreSQL to record the results for later review and analysis.

[1802] Step 8:

[1803] Confirmation by review method

[1804] Input: Saved log data

[1805] Output: Review screen

[1806] The server allows users to later check the saved dialogue results and feedback. Users can log in using their devices and check the review screen to learn from past training content.

[1807] Prompt Sentence Examples

[1808] “You are an AI that generates detailed inspection procedures for a factory operator training system. When a new operator asks, ‘What is the inspection procedure for this equipment?’ you provide them with the appropriate detailed inspection procedure.”

[1809] 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.

[1810] This invention is a customizable role-playing system using AI that significantly improves training efficiency, especially in call centers and sales departments. This system consists of the following components:

[1811] 1. Data input method

[1812] 2. Scenario Generation Method

[1813] 3. Means of interaction

[1814] 4. Response Generation Method

[1815] 5. Feedback Generation Methods

[1816] 6. Storage means

[1817] 7. Review Methods

[1818] 8. Emotion Engine

[1819] The specific operation of this system will now be described.

[1820] Data input method

[1821] After the user logs in, the server checks the profile information for the user and customizes the user's profile based on the necessary data. This data includes general data from the Internet and original data provided by the company.

[1822] Scenario generation method

[1823] The scenario generating means generates a role-playing scenario based on the data input by the server through the data input means. This scenario is customized taking into account the profile information of the user.

[1824] Interaction methods

[1825] As a dialogue method, the server dialogues with the user based on the generated scenario. The dialogue screen is displayed on the terminal from the server, and the user dialogues alternately according to the scenario.

[1826] Response Generation Method

[1827] The response generation means uses the AI ​​model to generate an appropriate response based on the user's input (questions and responses) received by the server. The generated response is then provided to the user via their device.

[1828] Feedback Generation Method

[1829] The feedback generation means allows the server to analyze the user's performance after the dialogue is completed and generate feedback. The analysis includes the quality of the user's questions and responses, response time, etc. The generated feedback is displayed on the terminal.

[1830] storage means

[1831] As a storage means, the server stores the results and feedback of the interactions in a database for later review and analysis.

[1832] Review Method

[1833] The review function allows users to later check the stored dialogue results and feedback. The server displays the saved logs on the terminal, allowing users to review their past performance and use it to improve.

[1834] Emotion Engine

[1835] The emotion engine analyzes emotions from the user's voice and text inputs and provides the results to the response generation means. The server recognizes emotions through the emotion engine and adjusts the tone and content of the dialogue in real time.

[1836] Specific examples

[1837] For example, consider a case where role-playing of product inquiries is carried out in a new employee training mode.

[1838] New user A logs in

[1839] The user logs in to the system from the terminal, and the server performs user authentication.

[1840] Select Onboarding Mode

[1841] The user selects "new employee training mode" on the terminal, and the server reads scenario data based on the selected mode information.

[1842] Inputting customized data

[1843] The server checks User A's profile information (such as product information) and customizes the scenario based on the relevant data.

[1844] Role-playing begins

[1845] The user clicks the "Start Role-Playing" button, and the server launches the AI ​​model and displays the interactive screen on the device.

[1846] Response Generation

[1847] The user types "How long is the warranty period for this product?" into the terminal, and the server uses an AI model to generate and display the appropriate response: "This product has a one-year warranty period."

[1848] Use of emotion engine

[1849] The server uses an emotion engine to analyze the emotions contained in the user's input and adjust the tone of the dialogue. For example, if the user's question sounds tired, the AI ​​model will generate a gentler response.

[1850] Providing Feedback

[1851] After the session ends, the server generates feedback based on the user's performance, including opinions based on emotion recognition.

[1852] Results storage and review

[1853] The server stores session logs in a database, and users can review past sessions on their devices to learn from them.

[1854] In this way, this system makes full use of AI and an emotion engine to realize role-playing that is more human-like, thereby helping users improve their skills.

[1855] The processing flow will be explained below.

[1856] Role-playing system processing steps

[1857] Step 1:

[1858] The user opens the system login screen on the device and enters their user ID and password. The device sends the entered information to the server. The server authenticates the user ID and password, and if authentication is successful, the server loads the user's profile information and displays the home screen on the device.

[1859] Step 2:

[1860] The user opens the training mode selection screen on the device and selects the desired mode from "New Employee Training Mode" or "Product Specialized Mode", etc. The device sends the selected mode information to the server. The server loads the scenario data corresponding to the selected training mode and displays the training start screen on the device.

[1861] Step 3:

[1862] The server checks the user's profile information and identifies the necessary customization data (product information, past performance data, etc.). The server collects general data from the internet and original data provided by companies, and inputs this into the AI ​​model to generate customized training scenarios.

[1863] Step 4:

[1864] The user clicks the "Start Role-playing" button on the device. The device notifies the server of this action. The server starts the AI ​​model and starts role-playing based on the customized scenario. The server displays a dialogue screen on the device, and the AI ​​presents the initial scenario.

[1865] Step 5:

[1866] The user enters a question or response into the device (e.g., "How long is the warranty on this product?"). The device sends the input information to the server. The server passes this input to the AI ​​model, which processes it to generate a response. The AI ​​model generates an appropriate response (e.g., "This product has a one-year warranty"). The server sends the generated response to the device, which displays it.

[1867] Step 6:

[1868] The server uses an emotion engine to analyze emotions from the user's voice and text input. The emotion engine analyzes the user's emotions and provides the results to the server. The server receives the emotion engine's output and adjusts the tone and content of the dialogue in real time. For example, if the user is tired, the AI ​​model will generate a gentler tone in the response.

[1869] Step 7:

[1870] When the session ends, the server analyzes the user's questions, responses, response time, accuracy, etc., and generates feedback (e.g., "Your questions were specific and polite"). The feedback data is sent to the device and displayed on the device.

[1871] Step 8:

[1872] The server stores role-playing session logs (questions, responses, feedback, etc.) in a database. The server provides a function to retrieve saved logs from the database so that users can review past sessions on their devices. Users can review the evaluations and feedback on their devices and learn from them to improve.

[1873] Example 2

[1874] 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."

[1875] Conventional role-playing systems lack the ability to customize to the individual needs of each user, analyze emotions during dialogue, and provide feedback. As a result, training effectiveness could not be maximized, and there were issues with improving individual skills and improving training efficiency.

[1876] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1877] In this invention, the server includes data input means for customizing based on data corresponding to the user, scenario generation means for generating a role-playing scenario based on the input data, dialogue means for dialogue with the user according to the role-playing scenario, response generation means for generating a response based on the user's dialogue, feedback generation means for generating feedback after the dialogue ends, storage means for storing the results of the dialogue and the feedback, and an emotion engine for analyzing emotions from the user's voice and text input and reflecting them in response generation. This makes it possible to provide training scenarios that correspond to the individual situation of each user, adjust dialogue based on emotions, and provide consistent performance evaluation and feedback.

[1878] "User" refers to any individual or entity who uses and receives training on this system.

[1879] "Data input means" refers to the means for acquiring data according to the user and inputting it into the system.

[1880] "Scenario generation means" refers to a means for generating a customized role-playing scenario based on input data.

[1881] "Interaction means" refers to a means for interacting with a user according to the generated role-playing scenario.

[1882] The "response generation means" refers to a means for generating an appropriate response based on the user's interaction.

[1883] "Feedback generation means" refers to a means for analyzing a user's performance and generating feedback after an interaction session has ended.

[1884] "Storage means" refers to a means for storing the results and feedback of an interaction for later review and analysis.

[1885] An "emotion engine" refers to a means of analyzing emotions from a user's voice and text input and reflecting the results in generating a response.

[1886] "Review means" refers to a means by which a user can later review the results and feedback stored in the storage means.

[1887] "Internet-derived data" means public or commercial data accessible through a wide area communications network.

[1888] "Original data provided by companies" refers to data that companies collect and provide independently.

[1889] This invention is a customizable role-playing system using AI that significantly improves training efficiency, especially in call centers and sales departments. The system consists of the following main components:

[1890] Data input method

[1891] After the user logs in, the server performs user authentication. At this time, it checks the user profile information and customizes the user's profile based on the necessary data. This data includes general data obtained from the Internet and original data provided by the company.

[1892] Scenario generation method

[1893] The scenario generation means generates a role-playing scenario based on the data input by the server through the data input means. This scenario is customized taking into account the user's profile information. Specifically, a scenario is generated based on the product and role that the user is responsible for.

[1894] Interaction methods

[1895] The server then interacts with the user based on the generated scenario. The interaction screen is displayed on the terminal, and the user interacts with the scenario in turn.

[1896] Response Generation Method

[1897] The server receives user input (questions and responses) and uses the generative AI model to generate an appropriate response. For example, if a user asks, "How long is the warranty period for this product?", the generative AI model responds, "This product has a one-year warranty period."

[1898] Emotion Engine

[1899] The emotion engine analyzes emotions from the user's voice and text input and provides the results to the response generation means. The server recognizes emotions through the emotion engine and adjusts the tone and content of the dialogue in real time. For example, if the user's input shows signs of fatigue, the AI ​​model will generate a response with a gentler tone.

[1900] Feedback Generation Method

[1901] After the interaction session, the server analyzes the user's performance and generates feedback, including the quality of the user's questions and responses, response times, and opinions based on emotion recognition.

[1902] storage means

[1903] The server stores the results and feedback of the interactions in a database for later review and further analysis.

[1904] Review Method

[1905] The server displays the saved interaction results and feedback on the device, allowing the user to check their past performance, facilitating self-evaluation and learning.

[1906] Specific examples

[1907] For example, consider a case where role-playing of product inquiries is carried out in a training mode for new employees at a call center.

[1908] New user A logs in

[1909] The user logs in to the system from the terminal, and the server performs user authentication.

[1910] Select Onboarding Mode

[1911] The user selects the "new employee training mode," and the server reads scenario data based on the selected mode information.

[1912] Inputting customized data

[1913] The server checks User A's profile information (such as product information) and customizes the scenario based on the relevant data.

[1914] Role-playing begins

[1915] The user clicks the "Start Role-Playing" button, and the server launches the generated AI model and displays the interactive screen on the device.

[1916] Response Generation

[1917] The user types, "How long is the warranty period for this product?", and the server uses a generative AI model to generate the appropriate response, "This product has a one-year warranty period," which is displayed on the device.

[1918] Use of emotion engine

[1919] The server uses an emotion engine to analyze the emotions contained in the user's input and adjust the tone of the dialogue. For example, if the user's question sounds tired, the AI ​​model will generate a gentler response.

[1920] Providing Feedback

[1921] After the session ends, the server generates feedback based on the user's performance and displays it on the device, including opinions based on emotion recognition.

[1922] Results storage and review

[1923] The server stores session logs in a database, and users can review past sessions on their devices to learn from them.

[1924] In this way, this system makes full use of AI and an emotion engine to realize role-playing in a manner that is close to human, thereby helping users improve their skills.

[1925] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1926] Step 1:

[1927] The user enters login information (username, password) into the terminal.

[1928] Input: Username, Password

[1929] The server receives this information and authenticates the user by checking the user information against a database.

[1930] Data processing: Verification of authentication information

[1931] Output: Authentication result (success / failure)

[1932] Step 2:

[1933] The server obtains user profile information based on the authentication result.

[1934] Input: Authentication result (user name)

[1935] The server retrieves the user's profile information (such as product information) from the database.

[1936] Data processing: Extracting user profiles

[1937] Output: User profile information

[1938] Step 3:

[1939] The user selects the mode to be used on the device (e.g., new employee training mode).

[1940] Input: Mode selection information

[1941] The server reads scenario data corresponding to the selected mode from the database.

[1942] Data processing: Extraction of scenario data

[1943] Output: Scenario data

[1944] Step 4:

[1945] The server customizes the scenario data based on the acquired user profile information.

[1946] Input: User profile information, scenario data

[1947] The server customizes the scenario based on the profile information (e.g., including specific inquiries about the product they are responsible for).

[1948] Data processing: Scenario customization

[1949] Output: Customized scenario

[1950] Step 5:

[1951] The user clicks the "Start Role-Playing" button on the device.

[1952] Input: Start signal

[1953] The server generates an interactive screen based on the customized scenario and displays it on the terminal.

[1954] Data processing: Generation of interactive screens

[1955] Output: Display of interactive screen

[1956] Step 6:

[1957] The user types a question or response into the terminal (e.g., "How long is the warranty on this product?").

[1958] Input: Question and response text

[1959] The server receives this input and inputs it as a prompt sentence into the generative AI model.

[1960] Data processing: Prompt sentence generation

[1961] Output: Input to the AI ​​model

[1962] Step 7:

[1963] The server uses the generative AI model to generate an appropriate response.

[1964] Input: prompt statement

[1965] The server generates a response from the AI ​​model and obtains the response text (e.g., "This product has a one-year warranty").

[1966] Data processing: response generation

[1967] Output: Response text

[1968] Step 8:

[1969] The server generates a response and displays it on the terminal.

[1970] Input: Response text

[1971] The server sends this response to the terminal and displays it to the user.

[1972] Data processing: Generation of data for display

[1973] Output: Display to terminal

[1974] Step 9:

[1975] The server uses an emotion engine to analyze the emotion contained in the user's input.

[1976] Input: User question and response text

[1977] The server analyzes the emotional state of the input text with an emotion engine and obtains the result.

[1978] Data Processing: Sentiment Analysis

[1979] Output: Sentiment analysis results

[1980] Step 10:

[1981] The server uses the results of the sentiment analysis to adjust the tone of the dialogue and feed it into the generative AI model.

[1982] Input: Sentiment analysis results

[1983] The server adjusts the output tone of the generative AI model based on the results of the emotion analysis.

[1984] Data processing: Adjusting the tone of the dialogue

[1985] Output: Adjusted response

[1986] Step 11:

[1987] The server analyzes the user's performance and generates feedback after the interactive session ends.

[1988] Input: conversation logs, response times, sentiment analysis results

[1989] The server analyzes this data and generates feedback.

[1990] Data processing: performance analysis and feedback generation

[1991] Output: Feedback

[1992] Step 12:

[1993] The server displays the feedback on the device.

[1994] Input: Feedback

[1995] The server sends the feedback to the terminal and displays it to the user.

[1996] Data processing: Generation of data for display

[1997] Output: Display to terminal

[1998] Step 13:

[1999] The server stores the results of the interaction and feedback in a database.

[2000] Input: Dialogue result, feedback

[2001] The server stores this data in a database.

[2002] Data processing: Data storage

[2003] Output: Saved

[2004] Step 14:

[2005] The user checks past sessions on the device.

[2006] Input: Review request

[2007] The server retrieves the saved dialogue results and feedback and displays them on the terminal.

[2008] Data processing: Data acquisition and generation of data for display

[2009] Output: Show past sessions

[2010] (Application example 2)

[2011] 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."

[2012] Traditional factory operator training systems lacked real-time interactive simulation and feedback, making effective training difficult. They also struggled to implement role-playing customized for specific scenarios and lacked the flexibility to adapt to diverse work environments. Furthermore, they lacked the ability to review training results afterward, limiting opportunities for operators to reflect on and improve their performance.

[2013] 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.

[2014] In this invention, the server includes: a data input means for customizing the system based on data corresponding to the user; a scenario generation means for generating a role-playing scenario based on the input data; a dialogue means for dialogue with the user according to the role-playing scenario; a response generation means for generating a response based on the dialogue of the user; a feedback generation means for generating feedback after the dialogue is completed; a storage means for storing the results of the dialogue and the feedback; a scenario generation means for generating a scenario to support the training of in-factory operators; a dialogue means for simulating a dialogue with the user based on the generated scenario; a generative AI model means for generating appropriate responses based on user input; and a review means for allowing the user to review the generated feedback after the training session is completed. This allows for real-time dialogue simulation and feedback to be provided to factory operators, enabling effective training and performance review.

[2015] The "data input means" is a means for inputting user profile information and related data into the server and customizing the system.

[2016] The "scenario generation means" is a means for generating a role-playing scenario suited to the user based on the information obtained from the data input means.

[2017] The "interaction means" is a means for interacting with the user based on the generated role-playing scenario.

[2018] The "response generation means" is a means for generating an appropriate response to an input from a user.

[2019] The "feedback generation means" is a means for analyzing the user's performance after the dialogue is completed and generating feedback.

[2020] "Storage means" is a means for storing the results of the interaction and the generated feedback.

[2021] The "role-playing system for in-factory operator training" is a system for training in-factory operators using actual work scenarios.

[2022] A "generative AI model means" is an artificial intelligence model used to generate an appropriate response based on user input.

[2023] A "review facility" is a facility that allows users to later review and reflect on the feedback and interaction logs generated after the training session is completed.

[2024] The "simulation means" is a means for simulating real-time interactions in a virtual environment and simulating actual operations.

[2025] An "appropriate response" is a context- and content-matched answer generated in response to user input using a generative AI model.

[2026] "Users" are those who will use this system and receive training, such as factory operators.

[2027] The present invention is a system for supporting the training of in-factory operators, and is realized using specific hardware and software. This system operates in the following steps.

[2028] Hardware and software used

[2029] The server installs the AI ​​model and performs the main computational processing required to execute the dialogue. Specifically, it is recommended to use an EC2 instance from Amazon Web Services (AWS). AWS RDS is suitable for storing the database. The AI ​​model uses the T5 model with the Hugging Face transformers library.

[2030] Data input and scenario generation

[2031] The server uses data input means to customize data based on user profile information, including general data obtained from the Internet and specific operational data provided by the enterprise.

[2032] Next, the server generates role-playing scenarios for in-factory operator training based on the information obtained from the data input means. The scenario generation means creates scenarios including specific work procedures and situations based on the user profile.

[2033] Interaction methods and response generation

[2034] When the user starts training, the server simulates a dialogue based on a scenario generated by the scenario generation means. At this time, the dialogue means interfaces with the user and guides the progress of the role-playing.

[2035] Based on the user's questions and input, the server generates an appropriate response using the response generation means. The generative AI model means (T5 model) provides an answer that matches the context and content based on the user's input.

[2036] Feedback generation and review features

[2037] After the interaction is completed, the server uses a feedback generating means to generate feedback on the user's performance, including the quality of the interaction, response time, and the emotion analysis results of the emotion engine.

[2038] The generated feedback and interaction logs are stored in a database using a storage means, and a review means is provided so that users can later reflect on their performance and identify areas for improvement.

[2039] Adding specific examples

[2040] For example, if a user asks, "What is the operating procedure for this machine?", the server uses the AI ​​model to generate a response such as, "The operating procedure for this machine is as follows: First, turn it on, then press the setting button..." After the training session, the server generates feedback such as, "Overall, good. You performed the work correctly, but there is room for improvement in efficiency."

[2041] As described above, the present invention is a system for effectively supporting factory operator skill improvement, and is capable of real-time interactive simulation and personalized feedback.

[2042] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[2043] Step 1:

[2044] The server retrieves the user's profile information.

[2045] Input: User login information.

[2046] Output: User profile information.

[2047] Specific operation: Based on the login information provided by the terminal, the server accesses the database and retrieves the user's profile information, which includes past interaction history and information about the machine in charge.

[2048] Step 2:

[2049] The server populates the relevant data using the data populating means.

[2050] Input: User profile information.

[2051] Output: Data for customized scenario generation.

[2052] Specific Operation: The server uses internet and company-provided data to populate the role-playing scenario with data to customize it based on the user's profile information.

[2053] Step 3:

[2054] The server generates a role-playing scenario using a scenario generation means.

[2055] Input: Customized data.

[2056] Output: Scenarios for in-factory operator training.

[2057] Specific operation: Based on the input data, the server generates specific work scenarios within the factory. These scenarios are tailored to the user's work responsibilities and skill level.

[2058] Step 4:

[2059] The terminal starts a dialogue with the user using the dialogue means.

[2060] Input: The generated scenario.

[2061] Output: Interactive interface display.

[2062] Specific operation: A dialogue interface based on the generated scenario is displayed on the terminal, and the user begins dialogue according to the scenario.

[2063] Step 5:

[2064] The server uses a response generation means to generate a response to the user's input.

[2065] Input: User questions or input.

[2066] Output: Appropriate response.

[2067] Specific operation: The server receives the question entered by the user into the terminal, generates an appropriate response using the generative AI model means (T5 model), and displays it on the terminal. For example, in response to the user's input, "What is the operating procedure for this machine?", the server generates the response, "The operating procedure for this machine is as follows. First, turn on the power, then press the setting button..."

[2068] Step 6:

[2069] The server generates the feedback using the feedback generating means.

[2070] Input: The result of the user's interaction.

[2071] Output: Feedback information.

[2072] Specific operation: After the dialogue ends, the server analyzes the content of the dialogue and the response time of the user, and generates feedback, including the quality of the dialogue and the results of emotion analysis by the emotion engine.

[2073] Step 7:

[2074] The server uses a storage means to store the interaction results and feedback.

[2075] Input: Interaction outcome and feedback information.

[2076] Output: Saved interaction logs and feedback.

[2077] Specific Actions: The server stores the generated feedback and interaction logs in a database for later review.

[2078] Step 8:

[2079] The terminal uses the review means to display the feedback and interaction log to the user.

[2080] Input: Saved interaction logs and feedback.

[2081] Output: The review information displayed to the user.

[2082] What it does: Allows users to use their devices to review logs and feedback from past training sessions. For example, feedback such as "Overall good. You followed the correct procedures, but there is room for improvement" is displayed on the review screen.

[2083] 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.

[2084] 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.

[2085] 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.

[2086] 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.

[2087] FIG. 9 is a diagram illustrating an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[2088] 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.

[2089] 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).

[2090] 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.

[2091] 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."

[2092] 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.

[2093] 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).

[2094] 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.

[2095] 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.

[2096] 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.

[2097] 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.

[2098] 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.

[2099] 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.

[2100] 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.

[2101] 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.

[2102] 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.

[2103] 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.

[2104] The following is further disclosed regarding the above embodiment.

[2105] (Claim 1)

[2106] A data input means for customizing the service based on data according to the user;

[2107] a scenario generation means for generating a role-playing scenario based on the input data;

[2108] a dialogue means for dialogue with a user according to the role-playing scenario;

[2109] a response generation means for generating a response based on the user's interaction;

[2110] a feedback generating means for generating feedback after the dialogue is completed;

[2111] a storage means for storing the results and feedback of said interaction;

[2112] A system including:

[2113] (Claim 2)

[2114] 10. The system of claim 1, further comprising review means for allowing a user to later review the stored results and feedback.

[2115] (Claim 3)

[2116] 10. The system of claim 1, wherein the interaction means is customized using data obtained from the Internet and original data provided by the company.

[2117] "Example 1"

[2118] (Claim 1)

[2119] A data input means for customizing the service based on data according to the user;

[2120] a scenario generation means for generating a role-playing scenario based on the input data;

[2121] a dialogue means for dialogue with a user according to the role-playing scenario;

[2122] a response generation means using a generative AI model that generates a response based on the user's dialogue;

[2123] a feedback generating means for generating feedback after the dialogue is completed;

[2124] a storage means for storing the results and feedback of said interaction;

[2125] review means for allowing a user to review the stored interaction results and feedback;

[2126] A system including:

[2127] (Claim 2)

[2128] 2. The system according to claim 1, wherein said interactive means displays an interactive screen on a terminal when a user asks questions and answers according to a scenario in order to improve productivity.

[2129] (Claim 3)

[2130] 10. The system of claim 1, wherein the interaction means is customized using data obtained from the Internet and original data provided by the company.

[2131] "Application Example 1"

[2132] (Claim 1)

[2133] A data input means for customizing the service based on data according to the user;

[2134] a scenario generation means for generating a role-playing scenario based on the input data;

[2135] a dialogue means for dialogue with a user according to the role-playing scenario;

[2136] a response generation means for generating a response based on the user's interaction;

[2137] a feedback generating means for generating feedback after the dialogue is completed;

[2138] a storage means for storing the results and feedback of said interaction;

[2139] an industrial machine training means for providing a user with dialogue and response based on a generated scenario for conducting training on the operation of the industrial machine;

[2140] a result storage means for storing the operation result in a database;

[2141] A system including:

[2142] (Claim 2)

[2143] 10. The system of claim 1, further comprising review means for allowing a user to later review the stored results and feedback.

[2144] (Claim 3)

[2145] 10. The system of claim 1, wherein the interaction means is customized using data obtained from the Internet and original data provided by the company.

[2146] "Example 2: Combining Emotion Engines"

[2147] (Claim 1)

[2148] A data input means for customizing the service based on data according to the user;

[2149] a scenario generation means for generating a role-playing scenario based on the input data;

[2150] a dialogue means for dialogue with a user according to the role-playing scenario;

[2151] a response generation means for generating a response based on the user's interaction;

[2152] a feedback generating means for generating feedback after the dialogue is completed;

[2153] a storage means for storing the results and feedback of said interaction;

[2154] An emotion engine that analyzes emotions from user voice and text input and reflects them in response generation;

[2155] A system including:

[2156] (Claim 2)

[2157] 10. The system of claim 1, further comprising review means for allowing a user to later review the stored results and feedback.

[2158] (Claim 3)

[2159] 10. The system of claim 1, wherein the interaction means is customized using data obtained from the Internet and original data provided by the company.

[2160] "Application example 2 when combining emotion engines"

[2161] (Claim 1)

[2162] A data input means for customizing the service based on data according to the user;

[2163] a scenario generation means for generating a role-playing scenario based on the input data;

[2164] a dialogue means for dialogue with a user according to the role-playing scenario;

[2165] a response generation means for generating a response based on the user's interaction;

[2166] a feedback generating means for generating feedback after the dialogue is completed;

[2167] a storage means for storing the results and feedback of said interaction;

[2168] a scenario generation means for generating a scenario to assist in training of an operator in a factory;

[2169] an interaction means for simulating an interaction with a user based on the generated scenario;

[2170] a generative AI model means for generating an appropriate response based on a user's input;

[2171] a review mechanism that allows users to review the feedback generated after the training session is completed; and

[2172] A system including:

[2173] (Claim 2)

[2174] 10. The system of claim 1, further comprising review means for allowing a user to later review the stored results and feedback.

[2175] (Claim 3)

[2176] 10. The system of claim 1, wherein the interaction means is customized using data obtained from the Internet and original data provided by the company. [Explanation of symbols]

[2177] 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 data input means for customizing the service based on data according to the user; a scenario generation means for generating a role-playing scenario based on the input data; a dialogue means for dialogue with a user according to the role-playing scenario; a response generation means for generating a response based on the user's interaction; a feedback generating means for generating feedback after the dialogue is completed; a storage means for storing the results and feedback of said interaction; A system including:

2. 10. The system of claim 1, further comprising review means for allowing a user to later review the stored results and feedback.

3. 10. The system of claim 1, wherein the interaction means is customized using data obtained from the Internet and original data provided by the company.

Images