System

Abstract

A system is provided.SOLUTION: A system comprising means for a user to input a question, means for a terminal to receive the question from the user and transmit it to a server, means for the server to receive the question and analyze it with a generated AI model, means for the generated AI model to generate an appropriate answer to the question, means for the server to transmit the generated answer to the terminal, and means for the terminal to display the answer to the user.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] While new employees are required to quickly acquire knowledge of business procedures and internal systems, traditional onboarding and training methods lack real-time response and personalized support. This results in a long adjustment period for new employees and reduced learning efficiency. Furthermore, if training materials and support are provided uniformly, it is difficult to address the needs of individual new employees and promote effective learning. The present invention aims to solve these problems, shorten the adjustment period for new employees, and promote efficient learning. [Means for solving the problem]

[0005] The present invention provides an onboarding and training support system that utilizes a generative AI model. The system includes a means for a user to input a question, a device to receive the question, and a server to transmit the question to. The server has a means for analyzing the received question using a generative AI model and generating an appropriate answer. The generated answer is transmitted from the server to the terminal, which then displays it to the user.

[0006] Furthermore, when a user requests training materials, the terminal has a means for receiving the request and transmitting it to the server. When the server receives the request, it has a means for generating appropriate training materials using the generative AI model and transmitting the generated training materials to the terminal. The terminal displays the generated materials to the user.

[0007] The present invention also includes a means for the terminal to receive and transmit an individual support request to a server when the user inputs the request. The server references the user's profile information, generates support information using a generative AI model, and transmits the generated support information to the terminal. The terminal then displays the generated support information to the user. This provides personalized support that meets the user's individual needs, dramatically improving learning efficiency.

[0008] "Users" refer to new hires and employees who use the onboarding and training support system that utilizes generative AI models.

[0009] A "terminal" is an interface for a user to input data and refers to a device that communicates with a server.

[0010] "Server" refers to the central processing unit that receives questions and requests sent by users, generates answers and training materials using generative AI models, and sends them to the terminal.

[0011] A "generative AI model" refers to an artificial intelligence model that analyzes user questions and requests and generates appropriate answers and training materials.

[0012] A "question" is an inquiry that a user inputs to the system, requesting information about business procedures or in-house systems.

[0013] An "answer" is information generated by a generative AI model based on a user's question, and includes explanations and instructions to resolve the user's concerns.

[0014] "Training materials" are information documents and guidelines generated by the generative AI model based on user requests, designed to help new employees acquire the knowledge necessary for their jobs.

[0015] A "support request" is a request entered by a user to seek individual support, and includes the provision of information regarding a specific task or issue.

[0016] "Profile Information" refers to historical and individual information about a user, and is the data that the server uses to provide personalized support to the user.

[0017] "Personalized support" refers to customized assistance and information provided to each user based on their specific needs and circumstances. [Brief explanation of the drawings]

[0018] [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

[0019] 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.

[0020] First, the terms used in the following description will be explained.

[0021] 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).

[0022] 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.

[0023] 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.

[0024] 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.

[0025] 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."

[0026] [First embodiment]

[0027] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0028] 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.

[0029] 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).

[0030] 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.

[0031] 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.

[0032] 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.

[0033] 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.

[0034] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0035] 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.

[0036] 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.

[0037] 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.

[0038] 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."

[0039] This invention is an onboarding and training support system that utilizes a generative AI model to improve the learning efficiency of new employees and employees. The main components of this system include a user, a terminal, a server, and a generative AI model.

[0040] Program processing overview

[0041] 1. Accepting user questions

[0042] A user inputs a specific question into the system via a terminal, for example, "Please tell me the procedure for starting a new project."

[0043] The terminal receives a question from the user and transmits the content of the question to the server.

[0044] 2. Question Analysis and Answer Generation

[0045] The server processes the questions received from the device and passes the received questions to the generative AI model for analysis.

[0046] The generative AI model analyzes the questions and generates appropriate answers to the user's questions, such as explaining how to use project management tools to launch a new project.

[0047] 3. Providing answers

[0048] The server receives the answer generated by the generative AI model and sends the answer to the device.

[0049] The terminal displays the answer received from the server to the user.

[0050] Specific examples

[0051] Example 1: Answering basic questions

[0052] 1. The user enters a question through the terminal.

[0053] For example: "How do you launch a new project?"

[0054] 2. The device sends a question to the server.

[0055] Submitted: "Question: 'How do you launch a new project?'"

[0056] 3. The server passes the received question to the generative AI model for analysis.

[0057] Analysis: "Check the steps for your new project..."

[0058] 4. The generative AI model generates appropriate answers to the questions.

[0059] Generated answer: "To start a new project, go to your project management tool, click the 'New Project' button, enter the required information, and click 'Save'."

[0060] 5. The server sends the generated response to the device.

[0061] What you sent: "Answer: 'To start a new project, go to your project management tool, click the 'New Project' button, enter the required information, and click 'Save.'"

[0062] 6. The terminal displays the received response to the user.

[0063] What it says: "To start a new project, go to your project management tool, click the 'New Project' button, enter the required information, and click 'Save'."

[0064] Example 2: Providing training materials

[0065] 1. The user inputs a request for training materials through the terminal.

[0066] For example: "How do I use a project management tool?"

[0067] 2. The device sends a request to the server.

[0068] Submission: "Request for Resources: 'How to Use Project Management Tools'"

[0069] 3. The server passes the received request to the generative AI model to generate training materials.

[0070] Generated content: "Basic functions of project management tools, how to set them up, task management, and team member management"

[0071] 4. The generative AI model generates appropriate training materials.

[0072] Generated material: "How to use project management tools - basic functions, configuration, task management, and team member management"

[0073] 5. The server sends the generated materials to the terminal.

[0074] Submission: "Document: 'How to use a project management tool - basic features, setup, task management, and team member management'"

[0075] 6. The terminal displays the received materials to the user.

[0076] Display content: "How to use project management tools - basic features, settings, task management, and team member management"

[0077] Example 3: Personalized support

[0078] 1. The user enters an individual support request via a terminal.

[0079] For example: "Can you tell me how things are going on with your latest project?"

[0080] 2. The device sends a request to the server.

[0081] Submitted: "Support Request: 'Latest Project Progress'"

[0082] 3. The server references the user's profile information and generates support information using a generative AI model.

[0083] Analysis: "Checking progress..."

[0084] 4. The generative AI model generates optimal support information based on the user's profile information and request content.

[0085] Generated information: "We're 70% complete on our latest project. The next major milestone is 'Spec Finalization,' due this Friday."

[0086] 5. The server sends the generated support information to the terminal.

[0087] What you sent: "Status: 'We're 70% done on our latest project. The next major milestone is 'Spec Finalized,' due this Friday.'"

[0088] 6. The device displays the support information it has received to the user.

[0089] It says: "Your latest project is 70% complete. The next major milestone is 'Spec Finalized', due this Friday."

[0090] As described above, the system of the present invention uses a generative AI model to provide efficient learning support tailored to the individual needs of new employees and employees, thereby shortening the adaptation period for new employees and enabling them to contribute to work more quickly.

[0091] The processing flow will be explained below.

[0092] Program processing flow steps

[0093] Accepting user questions

[0094] Step 1:

[0095] The user inputs a question through the terminal. For example, "Please tell me the procedure for starting a new project."

[0096] Step 2:

[0097] The terminal receives a question from the user.

[0098] Create a request to send the question received by the device to the server. For example, generate a request like "Question: 'Please tell me the steps to start a new project.'"

[0099] Question analysis and answer generation

[0100] Step 3:

[0101] The server receives a question request from the terminal.

[0102] The server passes the question to the generative AI model for analysis. For example, let's analyze the question "Question to be analyzed: 'Please tell me the steps to launch a new project.'"

[0103] Step 4:

[0104] A generative AI model receives a question and uses its internal database and pre-trained models to generate an appropriate answer, for example, by going through a process such as "matching against existing database to find an appropriate answer..."

[0105] Step 5:

[0106] The server receives the answer from the generative AI model.

[0107] The server creates a response to send the generated answer to the terminal. For example, it generates the response "Answer: 'To start a new project, click the 'New Project' button in the project management tool, enter the required information, and click 'Save'."

[0108] Providing answers

[0109] Step 6:

[0110] The terminal receives the response received from the server.

[0111] The terminal displays the received response to the user. For example, the response displayed to the user might be, "To start a new project, click the 'New Project' button in the project management tool, enter the required information, and click 'Save'."

[0112] Providing training materials

[0113] Step 1:

[0114] A user inputs a request for training materials through a terminal. For example, the user inputs "Teach me how to use a project management tool."

[0115] Step 2:

[0116] The terminal receives the request and creates a request to send to the server. For example, it creates a request called "Document Request: 'How to use project management tools'".

[0117] Step 3:

[0118] The server receives the request from the terminal.

[0119] The server passes the request to the AI ​​model to generate training materials. For example, let's generate materials about the basic functions, configuration, task management, and team member management of a project management tool.

[0120] Step 4:

[0121] A generative AI model receives the request and generates the appropriate training materials, for example, "Generating how-to documentation for a project management tool..."

[0122] Step 5:

[0123] The server receives the data from the generative AI model.

[0124] The server creates a response to send the generated materials to the terminal. For example, it creates a response such as "Training Materials: 'How to use project management tools - basic functions, configuration, task management, and team member management'".

[0125] Step 6:

[0126] The terminal receives the response received from the server.

[0127] The terminal displays the received materials to the user. For example, the material "How to use project management tools - basic functions, settings, task management, and team member management" is displayed to the user.

[0128] Personalized support

[0129] Step 1:

[0130] A user enters a specific support request through a terminal. For example, the user might enter, "Please let me know the progress on my latest project."

[0131] Step 2:

[0132] The device receives the request and creates a request to send to the server. For example, it creates a request called "Support request: 'Latest project progress'".

[0133] Step 3:

[0134] The server receives the request from the terminal.

[0135] The server references the user's profile information and generates support information using a generative AI model. For example, it goes through a process called "Checking progress..."

[0136] Step 4:

[0137] The generative AI model analyzes the user's profile information and request content to generate appropriate support information. For example, it goes through the process of "Generating the latest project progress information..."

[0138] Step 5:

[0139] The server receives support information from the generative AI model.

[0140] The server creates a response to send the generated support information to the terminal. For example, it generates a response such as "Progress: 'The progress rate of the latest project is 70%. The next milestone is 'Spec Finalization', and the deadline is this Friday.'"

[0141] Step 6:

[0142] The terminal receives the response received from the server.

[0143] The terminal displays the received support information to the user. For example, the following support information is displayed to the user: "The progress rate of the latest project is 70%. The next milestone is 'specification finalization', and the deadline is this Friday."

[0144] Example 1

[0145] 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."

[0146] Appropriate onboarding and training are necessary for new and current employees to quickly adapt to their work and learn efficiently. However, traditional systems rely mainly on manuals and documents for learning, making it difficult to meet individual needs. Another issue is that providing individual support and training is time-consuming and costly. Furthermore, the fact that a lot of information is scattered and difficult to access hinders efficient learning.

[0147] 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.

[0148] In this invention, the server includes a means for a user to input a question, a means for a terminal to receive the question from the user and transmit it to the server via a network, a means for the server to receive the question and analyze the question using a generative AI model, a means for the generative AI model to generate an appropriate answer to the question, a means for the server to transmit the generated answer to the terminal, and a means for the terminal to display the answer to the user, thereby enabling users to quickly and efficiently obtain individually customized information and training materials.

[0149] A "user" is an individual or organization that enters a question or request into the system and receives information or support.

[0150] A "terminal" is a device that allows a user to input a question or request and transmit that input to a server, and includes a computer, a smartphone, etc.

[0151] A "server" is a centralized computing system that receives questions and requests from users, processes them, generates answers and materials, and sends them to terminals.

[0152] A "generative AI model" is artificial intelligence-based software that analyzes user questions and requests and generates appropriate answers and materials.

[0153] A "question" is a textual content that a user enters into the system seeking specific information.

[0154] An "answer" is information generated by the generative AI model based on the user's question and sent to the device via the server.

[0155] "Training materials" are learning documents and presentation materials provided to users and generated by a generative AI model.

[0156] "Support information" refers to information and advice for obtaining specific support that is generated based on a user's individual request.

[0157] "Profile information" refers to a user's individual information and history that is used by the server to generate support information in response to the user's specific requests.

[0158] This invention is an onboarding and training support system that utilizes a generative AI model to improve the learning efficiency of new employees and employees. This system includes elements such as a user, a terminal, a server, and a generative AI model. This enables efficient learning support tailored to the individual needs of each employee.

[0159] In this system, a user first inputs a question or request via a terminal. For example, if a user wants to know the procedure for launching a new project, they input the question, "Please tell me the procedure for launching a new project." This input is sent to the terminal, which then transmits it to the server. The server receives the question and forwards it to the generative AI model for analysis.

[0160] The generative AI model analyzes the question in natural language and generates an appropriate answer. For example, it generates an answer such as, "To start a new project, access the project management tool, click the 'New Project' button, enter the required information, and click 'Save.'" The server sends the generated answer to the device, which then displays it to the user.

[0161] Next, when a user requests training materials, they input a materials request such as "Please teach me how to use a project management tool." This request is also sent from the device to the server, and the server generates appropriate materials using the generative AI model. Materials such as "How to use a project management tool - basic functions, settings, task management, and team member management" are generated and similarly displayed to the user via the device.

[0162] Additionally, when a user enters an individual support request, the request is "Please tell me about the progress of the latest project." The server references the user's profile information and generates support information using a generative AI model. Support information such as "The latest project is 70% complete. The next major milestone is 'specification finalization,' with a deadline of this Friday," is generated and displayed to the user via their device.

[0163] This system allows users to efficiently obtain information and training materials that are fast and personalized.

[0164] Specific examples

[0165] Example questions

[0166] "How do you launch a new project?"

[0167] Training Material Request Example

[0168] "How do I use a project management tool?"

[0169] Example of a personalized support request

[0170] Please let me know the progress on your latest project.

[0171] Using this system will shorten the adaptation period for new employees and employees, allowing them to contribute to work more quickly.

[0172] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0173] Step 1:

[0174] The user inputs a question via a terminal.

[0175] Specifically, the user enters a question such as "Please tell me the steps to start a new project" into the terminal interface (e.g., a text box) and clicks the send button.

[0176] Input: The user's question text.

[0177] Output: The question text stored in the device's temporary memory.

[0178] Step 2:

[0179] The terminal receives a question from the user and sends it to the server via the network.

[0180] Specifically, the terminal sends the question text to the server as an HTTP request.

[0181] Input: The question text stored in the device's temporary memory.

[0182] Output: The HTTP request sent to the server.

[0183] Step 3:

[0184] The server receives questions from the device and passes them to the generative AI model for analysis.

[0185] Specifically, the server extracts the question text from the payload of the HTTP request and sends the question text as a prompt to the generation AI model API.

[0186] Input: The question text of the HTTP request that arrives at the server.

[0187] Output: The prompt sent to the generative AI model.

[0188] Step 4:

[0189] The generative AI model analyzes the question and generates an appropriate answer.

[0190] Specifically, the generative AI model performs natural language processing to generate a text answer to a question. The generation part involves specific data analysis and model calculations.

[0191] Input: The prompt sentence passed to the generative AI model.

[0192] Output: The answer text provided by the generative AI model.

[0193] Step 5:

[0194] The server receives the answer generated by the generative AI model and sends it to the device.

[0195] Specifically, the server receives the answer from the generative AI model and returns it to the device as an HTTP response.

[0196] Input: Answer text from the generative AI model.

[0197] Output: The HTTP response sent to the device.

[0198] Step 6:

[0199] The terminal displays the answer received from the server to the user.

[0200] Specifically, the terminal extracts the response text from the payload of the HTTP response and displays it on the user's interface.

[0201] Input: The HTTP response received from the server.

[0202] Output: The answer text displayed to the user.

[0203] The above is the flow of processing by which the program of this system responds to user questions.

[0204] (Application example 1)

[0205] 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."

[0206] Training for the operation and maintenance of factory robots involves frequent updates and diverse operating procedures, making it difficult for new employees and current employees to learn. Furthermore, one-on-one training requires significant time and resources, making it difficult to provide uniform training to all employees. Therefore, there is a need for effective educational methods to support efficient operation and rapid troubleshooting of factory robots.

[0207] 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.

[0208] In this invention, the server includes a means for generating training materials related to factory work, a means for an AI to refer to the user's past operation history and generate individually customized support information, and a means for receiving the user's questions, analyzing them with the generative AI model, and generating appropriate answers. This allows users to learn how to operate and troubleshoot factory robots in real time, enabling efficient training and support.

[0209] A "user" is an individual person who uses the system.

[0210] A "means for inputting a question" is an interface through which a user can provide a question to the system in text or voice.

[0211] A "terminal" is a hardware device through which a user can input questions or requests and receive the results.

[0212] The "server" is a central computer system that receives questions or requests from users, sends them to the generative AI model, and sends the results back to the user.

[0213] A "generative AI model" is an artificial intelligence technology that analyzes questions and requests from users and generates appropriate answers and training materials.

[0214] "Training materials" are educational materials on the operation and maintenance of factory robots, generated by a generative AI model.

[0215] "Support information" is individually customized advice and assistance information that is generated based on the user's past operation history and profile information.

[0216] The "means for generating training materials for factory work" is a function that uses a generative AI model to automatically generate information necessary for operating and maintaining factory robots.

[0217] "Means for referencing operation history" refers to a function that allows a user to check the records of past operations and have the generative AI model generate information based on those records.

[0218] The "means for generating customized support information" is a function that generates optimal support information in real time based on the user's operation history and profile information.

[0219] The "means of generating an answer" is the function that enables the generative AI model to provide appropriate information based on a question from a user.

[0220] This invention is a system that supports training on the operation and maintenance of factory robots. This system provides a terminal interface for users to input questions and uses a generative AI model to provide appropriate answers and training materials. Specifically, the system uses the following hardware and software:

[0221] Hardware and software used

[0222] Hardware:

[0223] Smartphone (iOS / ANDROID (registered trademark))

[0224] Smart Glasses

[0225] software:

[0226] Frontend: React Native (Mobile Application)

[0227] Backend: Node.js, Express

[0228] Database: MongoDB

[0229] AI model: OpenAI (registered trademark) GPT-4 (registered trademark)

[0230] Natural Language Processing (NLP) technology: Used to generate training materials and support information

[0231] Overall system flow

[0232] 1. User questions:

[0233] Users input questions or requests through a smartphone or smart glasses app, such as "How do I calibrate the robot's sensors?"

[0234] 2. Submit your question:

[0235] The questions entered by the user are sent to the server through the terminal, and the technology used here uses React Native as the front end, with a back end built with Node.js and Express receiving the questions.

[0236] 3. Question analysis and answer generation:

[0237] The server sends the received question to a generative AI model (OpenAI GPT-4), which analyzes the question. The generative AI model uses natural language processing technology to generate an appropriate answer to the question.

[0238] 4. Providing answers:

[0239] The generated answer is sent to the device via the server, and the device's app displays the answer to the user.

[0240] Specific examples

[0241] A user uses a smartphone or smart glasses to input a question as follows:

[0242] User Question: "Please explain in detail the maintenance procedures for the robot."

[0243] Prompt Input: "What is the maintenance procedure for the robot?"

[0244] AI model response: "The robot maintenance procedure is as follows... (detailed instructions)"

[0245] Answer: "The robot maintenance procedure is as follows. First... (show detailed procedure)"

[0246] Also, when a user requests training materials, the flow is as follows:

[0247] User Request: "Please provide training materials on basic operation of factory robots."

[0248] Prompt Input: "Generate training materials on basic operation of factory robots."

[0249] AI model response: "The training materials for basic operation of factory robots include the following... (detailed material content)"

[0250] Display material: "The training material for basic operation of factory robots is as follows... (Display detailed material)"

[0251] In this way, the present invention provides a system that allows users to easily acquire knowledge about the operation and maintenance of factory robots. The system utilizes a generative AI model to quickly generate and display appropriate answers and training materials to users. This improves training efficiency and enables new employees and employees to quickly master their work.

[0252] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0253] Step 1:

[0254] Users input questions or requests through a smartphone or smart glasses app. For example, the input can be a specific question such as, "How do I calibrate the robot's sensors?"

[0255] Step 2:

[0256] The device sends the question received from the user to the server. The entered question data is sent from the device to the server. For example, a question is sent from a mobile app using React Native to a server built with Node.js and Express.

[0257] Step 3:

[0258] The server sends the received question to the generative AI model and requests analysis. The input here is the question data sent in step 2, and the output is a query to the generative AI model. The server uses natural language processing technology to convert the received question into an appropriate format and sends an analysis request to the AI ​​model (GPT-4).

[0259] Step 4:

[0260] The generative AI model analyzes the question and generates an appropriate answer. The AI ​​model analyzes the prompt received from the server and generates a corresponding answer. For example, if the prompt is "How do I calibrate the robot's sensors?", the AI ​​model generates specific calibration procedures.

[0261] Step 5:

[0262] The server processes the answer received from the generative AI model and sends it to the device. The input here is the answer output from the generative AI model, and the output is sending the answer data to the device. The server receives the answer data, reformats it, and sends it back to the device.

[0263] Step 6:

[0264] The device displays the received answers to the user. The input is the answer data sent from the server, and the output is what is displayed to the user. The device app has the function of displaying the answers in an easy-to-understand manner using React Native. For example, the user can see specific steps such as "To calibrate the robot's sensors, follow the steps below..."

[0265] Through this series of processing steps, users can receive real-time answers to questions about factory robot operation and maintenance procedures, thereby improving factory work efficiency and reducing errors.

[0266] 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.

[0267] This invention combines an onboarding and training support system that utilizes a generative AI model to improve the learning efficiency of new employees and employees with an emotion engine that recognizes user emotions. The main components of this system include a user, a terminal, a server, a generative AI model, and an emotion engine.

[0268] Program processing overview

[0269] 1. User question acceptance and emotion recognition

[0270] A user inputs a specific question into the system via a terminal, for example, "Please tell me the procedure for starting a new project."

[0271] The terminal receives a question from the user and sends the input information to the emotion engine.

[0272] The emotion engine analyzes emotions based on the user's input content, input speed, typing strength, and tone of voice (in the case of voice input), and generates emotional information.

[0273] 2. Considering emotions in question analysis and answer generation

[0274] The terminal transmits the emotion information received from the emotion engine to the server.

[0275] The server passes the question content and emotional information to the generative AI model for analysis, which then takes this emotional information into account to generate an appropriate answer.

[0276] For example, if the question expresses anxiety or confusion, the generated answers will be enhanced to be more detailed and easier to understand.

[0277] 3. Providing answers

[0278] The server receives the answer generated by the generative AI model and sends it to the device along with emotional information.

[0279] The device displays the answer and emotional information received from the server to the user, and adjusts the display method based on the emotional information (for example, if the user shows anxiety, it displays calm and encouraging words).

[0280] Specific examples

[0281] Example 1: Answering basic questions

[0282] 1. The user enters a question through the terminal.

[0283] For example: "How do you launch a new project?"

[0284] 2. The device sends the question to the emotion engine.

[0285] For example: "Question: 'How do you launch a new project?'"

[0286] 3. The emotion engine analyzes emotions based on the user's question.

[0287] Example: "User Sentiment: Anxiety"

[0288] 4. The device sends the emotion information to the server.

[0289] Sent: "Emotion: 'Anxiety'"

[0290] 5. The server passes the question and emotion information to the generative AI model for analysis.

[0291] Analysis: "Procedures for launching a new project. Detailed and thorough, as users are expressing anxiety."

[0292] 6. The generative AI model generates answers taking into account emotional information.

[0293] Generated answer: "To start a new project, click the 'New Project' button in the project management tool, enter the required information, and click 'Save'. If you have any questions, please feel free to ask."

[0294] 7. The server sends the generated response to the device.

[0295] Send content: "Answer and emotional response message"

[0296] 8. The terminal displays the received response to the user.

[0297] What it says: "To start a new project, click the 'New Project' button in your project management tool, enter the required information, and click 'Save.' If you have any questions, please don't hesitate to ask."

[0298] Example 2: Providing training materials

[0299] 1. The user inputs a request for training materials through the terminal.

[0300] For example: "How do I use a project management tool?"

[0301] 2. The device sends the request to the emotion engine.

[0302] Example: "Resource Request: 'How to use project management tools'"

[0303] 3. The emotion engine analyzes emotions based on the user request.

[0304] Example: "User sentiment: Interested"

[0305] 4. The device sends the emotion information to the server.

[0306] Send: "Emotion: 'Interested'"

[0307] 5. The server passes the request and emotion information to the generative AI model for analysis.

[0308] Analysis: "Basic functions of project management tools, how to set them up, task management, and team member management. Users are interested, so we've added relevant information."

[0309] 6. The generative AI model generates training materials taking into account emotional information.

[0310] Generated material: "How to use project management tools - basic functions, configuration, task management, team member management, and common troubleshooting tips"

[0311] 7. The server sends the generated materials to the terminal.

[0312] Send content: "Training materials"

[0313] 8. The terminal displays the received materials to the user.

[0314] What you'll see: "How to use a project management tool - basic features, configuration, task management, team member management, and common troubleshooting tips."

[0315] Example 3: Personalized support

[0316] 1. The user enters an individual support request via a terminal.

[0317] For example: "Can you tell me how things are going on with your latest project?"

[0318] 2. The device sends the request to the emotion engine.

[0319] Example: "Support Request: 'Latest Project Progress'"

[0320] 3. The emotion engine analyzes emotions based on the user's support request.

[0321] Example: "User Sentiment: Urgent"

[0322] 4. The device sends the emotion information to the server.

[0323] Sent: "Sentiment: 'urgent'"

[0324] 5. The server passes the request and emotion information to the generative AI model for analysis.

[0325] Analysis: "The latest project progress information. Urgent information is provided promptly."

[0326] 6. The generative AI model generates supporting information taking into account emotional information.

[0327] Generated information: "Our latest project is 70% complete. The next major milestone is 'specification finalization,' which is expected to be completed today."

[0328] 7. The server sends the generated support information to the terminal.

[0329] What to send: "Progress and emergency response messages"

[0330] 8. The device displays the support information it has received to the user.

[0331] It reads: "Our latest project is 70% complete. The next major milestone is 'Spec Finalization', which is expected to be completed today."

[0332] As described above, by combining a generative AI model and an emotion engine, the system of the present invention can provide efficient learning support that takes into account the emotional state of new employees and employees. This allows users to receive feedback and support that is appropriate for their emotions, resulting in more effective learning.

[0333] The processing flow will be explained below.

[0334] Program processing flow steps (when combined with emotion engine)

[0335] User question reception and emotion recognition

[0336] Step 1:

[0337] The user inputs a question through the terminal.

[0338] For example: "What are the steps to launching a new project?"

[0339] Step 2:

[0340] The terminal receives a question from the user.

[0341] The terminal sends the user's input to the emotion engine.

[0342] Step 3:

[0343] The emotion engine analyzes the user's input, as well as the speed, strength, and tone of voice (in the case of voice input), to recognize emotions.

[0344] Example: "User Sentiment: Anxiety"

[0345] Step 4:

[0346] The emotion engine returns the analysis results to the device.

[0347] The device transmits the emotion information to the server.

[0348] Considering emotions in question analysis and answer generation

[0349] Step 5:

[0350] The server receives the question and emotion information received from the terminal.

[0351] The server passes the question content and emotional information to the generative AI model for analysis.

[0352] Step 6:

[0353] Generative AI models take emotional information into account when generating appropriate answers to questions.

[0354] Example: "Provide a detailed and thorough explanation of the steps to launch a new project."

[0355] Step 7:

[0356] The server receives the answer from the generative AI model.

[0357] The server transmits the generated answer and emotion information to the terminal.

[0358] Providing answers

[0359] Step 8:

[0360] The terminal displays the answer and emotion information received from the server.

[0361] For example: "To start a new project, click the 'New Project' button in your project management tool, enter the required information, and click 'Save.' If you have any questions, please don't hesitate to ask."

[0362] Providing training materials

[0363] Step 1:

[0364] A user inputs a request for training materials through a terminal.

[0365] For example: "How do I use a project management tool?"

[0366] Step 2:

[0367] The device receives the request and sends it to the emotion engine.

[0368] The emotion engine analyzes the content, speed, strength and tone of the user's request.

[0369] Step 3:

[0370] The emotion engine returns the analysis results to the device.

[0371] The device transmits the emotion information to the server.

[0372] Step 4:

[0373] The server receives the request and emotion information and passes it to the generative AI model for analysis.

[0374] Step 5:

[0375] Generative AI models take emotional information into account when generating training materials.

[0376] Example: "Detailed documentation including basic project management tool features, setup, task management, and team member management."

[0377] Step 6:

[0378] The server receives the data from the generative AI model and sends it to the terminal.

[0379] Step 7:

[0380] The terminal displays materials and emotional information to the user.

[0381] Example: "How to use a project management tool - basic features, setup, task management, and team member management."

[0382] Personalized support

[0383] Step 1:

[0384] A user inputs an individual support request through a terminal.

[0385] For example: "Can you tell me how things are going on with your latest project?"

[0386] Step 2:

[0387] The device receives the request and sends it to the emotion engine.

[0388] The emotion engine analyzes the content, speed, strength and tone of the user's request.

[0389] Step 3:

[0390] The emotion engine returns the analysis results to the device.

[0391] The device transmits the emotion information to the server.

[0392] Step 4:

[0393] The server receives the request and emotion information, references the user's profile information, and passes it to the generative AI model for analysis.

[0394] Step 5:

[0395] The generative AI model takes emotional information into account when generating supporting information.

[0396] Example: "Detailed information on the progress of the latest project and next milestones."

[0397] Step 6:

[0398] The server receives support information from the generative AI model and sends it to the device.

[0399] Step 7:

[0400] The terminal displays support information and emotional information to the user.

[0401] Example: "We're 70% complete on our latest project. The next major milestone is 'Spec Finalization,' which is expected to be completed today."

[0402] Example 2

[0403] 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."

[0404] Current education, training, and support systems do not provide answers or support that take into account the user's emotional state, which can sometimes leave users feeling frustrated or anxious. To improve the learning efficiency of new employees and current employees in particular, it is important to recognize the user's emotions and provide appropriate answers and training materials according to their situation. However, conventional systems lack such functionality.

[0405] 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.

[0406] In this invention, the server includes a means for passing the user's question and emotional information to the generative AI model for analysis, a means for sending the generated answer to the terminal, and a means for adjusting the display method based on the emotional information. This makes it possible to improve the user's learning efficiency by recognizing the user's emotions and providing appropriate answers and training materials according to the situation.

[0407] "User" means a person who accesses the System and enters a question or request.

[0408] "Terminal" refers to a mechanical device through which a user inputs a question or request and transmits it to the system.

[0409] An "emotion engine" refers to a software component that analyzes a user's input and behavioral patterns when entering input to identify the user's emotional state.

[0410] "Emotion information" refers to data that indicates the user's emotional state extracted through analysis by the emotion engine.

[0411] "Server" refers to a central computer system that receives user queries and requests and performs any necessary analysis or data processing.

[0412] A "generative AI model" is an artificial intelligence algorithm used by the server that generates appropriate answers and materials in response to user questions and requests.

[0413] "Answer" refers to the explanation or description that a generative AI model provides in response to a user's question.

[0414] "Training Materials" refers to the educational materials created by the generative AI model based on the learning content requested by the User.

[0415] "Support information" refers to assistance information provided by the generative AI model in response to individual user requests.

[0416] "Adjusting the display method" refers to presenting information in an optimal format according to the user's emotional state based on emotional information.

[0417] This system recognizes a user's emotions and provides appropriate answers, training materials, and support information based on those emotions. The system consists of the following main components: the user, the device, the server, the generative AI model, and the emotion engine.

[0418] System Overview

[0419] 1. A terminal that provides an interface for users to enter questions or requests.

[0420] 2. The device receives the user's input, extracts emotional information through the emotion engine, and sends it to the server.

[0421] 3. The emotion engine analyzes the user's input and behavioral patterns when entering data to identify their emotional state.

[0422] 4. The server receives the user's questions, requests, and emotional information and analyzes them using a generative AI model.

[0423] 5. The generative AI model takes into account the question, request, and emotional information to generate appropriate answers, training materials, and support information.

[0424] 6. The device receives the information from the server and displays it in the most appropriate format for the user.

[0425] Hardware and Software Used

[0426] Device: A device such as a personal computer, tablet, or smartphone.

[0427] Emotion Engine: Software that includes a natural language processing (NLP) engine, a speech analysis system, and a typing analysis system.

[0428] Server: A high-performance computer or cloud computing platform.

[0429] Generative AI model: Deep learning model (e.g., large-scale generative model such as GPT-3 (registered trademark)).

[0430] Specific operation example

[0431] Example 1: Answering basic questions

[0432] 1. A user types the question "How do I start a new project?" into a terminal.

[0433] 2. The device sends a question to the emotion engine and identifies the user's emotion as "anxiety."

[0434] 3. The device sends the question, including the emotion information, to the server.

[0435] 4. The server passes the question and emotion information to the generative AI model, which generates an answer. For example, it might generate an answer like, "To start a new project, click the 'New Project' button in the project management tool, enter the required information, and click 'Save'. If you have any questions, please feel free to ask."

[0436] 5. The device receives the answer and displays it to the user.

[0437] Example 2: Providing training materials

[0438] 1. The user enters a request through the terminal: "Please teach me how to use the project management tool."

[0439] 2. The device sends a request to the emotion engine and identifies the user's emotion as "interest."

[0440] 3. The device sends a request including emotion information to the server.

[0441] 4. The server passes the request and sentiment information to the generative AI model to generate training materials, such as "How to use a project management tool - basic functions, configuration, task management, team member management, and common troubleshooting tips."

[0442] 5. The device receives the training materials and displays them to the user.

[0443] Example 3: Personalized support

[0444] 1. The user inputs a request through the terminal: "Please let me know the progress of the latest project."

[0445] 2. The device sends a request to the emotion engine and identifies the user's emotion as "urgent."

[0446] 3. The device sends a request including emotion information to the server.

[0447] 4. The server passes the request and emotion information to the generative AI model, which generates information about the latest progress. For example, it generates information like, "The latest project is 70% complete. The next major milestone is 'specification finalization,' which is expected to be completed today."

[0448] 5. The device receives the support information and displays it to the user.

[0449] This will provide answers and materials that take the user's emotions into consideration, which is expected to improve learning efficiency.

[0450] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0451] Step 1:

[0452] The user enters a question

[0453] Specific action: The user inputs a question into the input interface of the device, for example, "How do I start a new project?"

[0454] Input: The text data of the question entered by the user.

[0455] Output: The terminal obtains the user's question text data.

[0456] Step 2:

[0457] The device sends the user's question to the emotion engine.

[0458] Specific operation: The device sends the user's input data to the emotion engine, which receives data such as the user's input content, input speed, typing strength, and voice tone (in the case of voice input).

[0459] Input: Text data of the question entered by the user and behavioral data when entering the question.

[0460] Output: The emotion engine receives the input data.

[0461] Step 3:

[0462] Emotion engine analyzes user emotions

[0463] Specific operation: The emotion engine analyzes text data and behavioral data to identify the user's emotions. For example, it determines that the user is feeling "anxiety" based on the input content.

[0464] Input: Textual and behavioral data received by the emotion engine.

[0465] Output: Emotional information including the user's emotional state (e.g., anxiety, interest, urgency).

[0466] Step 4:

[0467] The device sends emotional information to the server.

[0468] Specific operation: The device sends the generated emotion information to the server along with the user's question text.

[0469] Input: User question text data and sentiment information.

[0470] Output: The server receives the question text and sentiment information.

[0471] Step 5:

[0472] The server passes the question and emotion information to the generative AI model

[0473] Specific operation: The server inputs the received question text and emotion information into the generative AI model, which then generates an appropriate answer based on this.

[0474] Input: Question text data and sentiment information received by the server.

[0475] Output: The generative AI model begins its analysis.

[0476] Step 6:

[0477] Generative AI models generate appropriate answers to questions

[0478] Specific operation: The generative AI model analyzes the question text data and emotional information, and generates an appropriate answer taking into account the user's emotional state. For example, if the user is feeling "anxious," the answer will be more detailed.

[0479] Input: Question text data and sentiment information.

[0480] Output: Emotion-sensitive answer text data.

[0481] Step 7:

[0482] The server generates a response and sends it to the device.

[0483] Specific operation: The server receives the answer text data generated from the generative AI model and sends it to the terminal.

[0484] Input: Generated answer text data.

[0485] Output: The terminal receives the response text data.

[0486] Step 8:

[0487] The device displays the answers to the user and adjusts the display based on the user's emotional information.

[0488] Specific operation: The device displays the received answer text to the user. At the same time, the display method is adjusted based on the user's emotional information. For example, if the user is feeling "anxious," a calm and encouraging message is added.

[0489] Input: Answer text data and sentiment information.

[0490] Output: A display tailored to the user.

[0491] (Application example 2)

[0492] 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."

[0493] Conventional onboarding and training systems provide uniform responses to user questions and requests, making it difficult to respond flexibly to the user's emotions and circumstances. In particular, new employees and employees who are unfamiliar with new environments and work procedures often lack support that adequately alleviates their anxiety and confusion. Due to the lack of individualized responses that take emotions into consideration, there is a need to improve learning and work efficiency.

[0494] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for analyzing the question and emotion information using a generative AI model, means for the generative AI model to generate an appropriate answer to the question taking the emotion information into consideration, and means for the emotion engine to analyze the user's emotion. This enables flexible responses that take the user's emotions into consideration.

[0495] A "user" is an entity that operates the system and enters questions and requests.

[0496] A "terminal" is a device that receives questions or requests entered by a user and transmits them to a server.

[0497] The "emotion engine" is a function that analyzes the user's input data (text, voice, input speed, etc.) and generates emotional information.

[0498] The "server" is a central device that analyzes questions, requests, and emotional information received from users and transmits the results to terminals.

[0499] A "generative AI model" is an artificial intelligence technology that generates appropriate answers and materials based on input questions or requests.

[0500] The present invention relates to a training support system that uses an application installed on a factory robot to improve employee learning efficiency. The system includes a user, a terminal, a server, a generative AI model, and an emotion engine.

[0501] The overall flow of the system is as follows: The user inputs a question or request via their device, which then sends it to the emotion engine. The emotion engine analyzes the user's input data and generates emotional information. The device then sends the input data along with the emotional information to the server. The server passes the input data and emotional information to the generative AI model for analysis, and sends the generated answer or materials back to the device. The device then finally displays or plays the answer or materials to the user.

[0502] This section explains the specific hardware and software. The hardware uses factory robots, voice input devices, display panels, and speakers. The software uses the Emotion Engine (emotion recognition engine) and AI Response Generator (generative AI model). The server is the central device that handles overall data exchange and analysis, and can also utilize edge computing and cloud services.

[0503] For example, let's consider a specific example where a worker asks a question about how to operate a new machine. When the user inputs a question into the device (voice input is also possible), such as "Please tell me how to operate this new press machine," the device sends that information to the emotion engine. The emotion engine analyzes the content, speed, and tone of voice of the input, and determines the user's emotion as "interest." The device then sends this as data to the server, and the server uses a generative AI model to generate an appropriate answer that takes the emotional information into consideration. As a specific example, the answer generated might be, "To operate this new press machine, first turn it on, then press the start button on the control panel. After that, adjust the settings and begin work. A detailed manual is also available, so please let us know if you need one."

[0504] As an example of a prompt, the following text is fed into the generative AI model:

[0505] Question: 'How do I operate the new press?'

[0506] Emotion: 'Interest'

[0507] This system is expected to improve the quality of work instruction and respond flexibly to the user's emotions. This application example is particularly effective in helping new and inexperienced employees to work with peace of mind.

[0508] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0509] Step 1:

[0510] A user inputs a question or request via a terminal. The input method can be text input or voice input. For example, if a user inputs a question such as "Please tell me how to operate the new press machine," the input contains the user's emotions and intentions.

[0511] Step 2:

[0512] The device receives a question from the user and sends it to the emotion engine. The input data includes text information and voice data, and the data is sent to the emotion engine for analysis.

[0513] Step 3:

[0514] The emotion engine analyzes emotions based on the user's input data. In this step, the content of the text, input speed, and tone of voice are analyzed to generate the user's emotion information (e.g., interest, anxiety, urgency, etc.). For example, in the case of voice input, "interest" is generated as emotion information by analyzing the tone of voice.

[0515] Step 4:

[0516] The device sends the emotion information received from the emotion engine to the server. This sent data includes the original question and emotion information. For example, data such as "Question: Please tell me how to operate the new press machine" and "Emotion information: Interest" is sent.

[0517] Step 5:

[0518] The server passes the question content and emotional information to the generative AI model for analysis. Based on the input question content and emotional information, data processing and analysis are performed to generate the most appropriate answer. The generative AI model analyzes the question and generates an answer that takes the emotional information into account.

[0519] Step 6:

[0520] The generative AI model takes emotional information into account to generate appropriate answers. The output answers are tailored to the user's emotions. For example, a detailed and engaging answer is generated for the "interest" emotion. Specifically, the model might generate an answer such as, "To operate a new press, first turn it on, then press the start button on the control panel. After that, adjust the settings and begin operation. A detailed manual is also available, so please let us know if you need one."

[0521] Step 7:

[0522] The server transmits the generated answer to the terminal. In this step, the generated answer includes an emotion-responsive message, and the answer is transmitted in an appropriate format based on the user's emotion.

[0523] Step 8:

[0524] The device displays or plays back the received answer and emotion-responsive message to the user. Depending on the user's emotion, an appropriate answer is provided in the form of a text display or audio playback. For example, if the emotion is "interested," detailed instructions are displayed on the screen and audio guidance is played. In this way, flexible responses and support that take the user's emotions into consideration are possible.

[0525] 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.

[0526] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0527] 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.

[0528] [Second embodiment]

[0529] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0530] 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.

[0531] 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).

[0532] 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.

[0533] 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.

[0534] 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).

[0535] 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.

[0536] 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.

[0537] 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.

[0538] 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.

[0539] 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.

[0540] 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."

[0541] This invention is an onboarding and training support system that utilizes a generative AI model to improve the learning efficiency of new employees and employees. The main components of this system include a user, a terminal, a server, and a generative AI model.

[0542] Program processing overview

[0543] 1. Accepting user questions

[0544] A user inputs a specific question into the system via a terminal, for example, "Please tell me the procedure for starting a new project."

[0545] The terminal receives a question from the user and transmits the content of the question to the server.

[0546] 2. Question Analysis and Answer Generation

[0547] The server processes the questions received from the device and passes the received questions to the generative AI model for analysis.

[0548] The generative AI model analyzes the questions and generates appropriate answers to the user's questions, such as explaining how to use project management tools to launch a new project.

[0549] 3. Providing answers

[0550] The server receives the answer generated by the generative AI model and sends the answer to the device.

[0551] The terminal displays the answer received from the server to the user.

[0552] Specific examples

[0553] Example 1: Answering basic questions

[0554] 1. The user enters a question through the terminal.

[0555] For example: "How do you launch a new project?"

[0556] 2. The device sends a question to the server.

[0557] Submitted: "Question: 'How do you launch a new project?'"

[0558] 3. The server passes the received question to the generative AI model for analysis.

[0559] Analysis: "Check the steps for your new project..."

[0560] 4. The generative AI model generates appropriate answers to the questions.

[0561] Generated answer: "To start a new project, go to your project management tool, click the 'New Project' button, enter the required information, and click 'Save'."

[0562] 5. The server sends the generated response to the device.

[0563] What you sent: "Answer: 'To start a new project, go to your project management tool, click the 'New Project' button, enter the required information, and click 'Save.'"

[0564] 6. The terminal displays the received response to the user.

[0565] What it says: "To start a new project, go to your project management tool, click the 'New Project' button, enter the required information, and click 'Save'."

[0566] Example 2: Providing training materials

[0567] 1. The user inputs a request for training materials through the terminal.

[0568] For example: "How do I use a project management tool?"

[0569] 2. The device sends a request to the server.

[0570] Submission: "Request for Resources: 'How to Use Project Management Tools'"

[0571] 3. The server passes the received request to the generative AI model to generate training materials.

[0572] Generated content: "Basic functions of project management tools, how to set them up, task management, and team member management"

[0573] 4. The generative AI model generates appropriate training materials.

[0574] Generated material: "How to use project management tools - basic functions, configuration, task management, and team member management"

[0575] 5. The server sends the generated materials to the terminal.

[0576] Submission: "Document: 'How to use a project management tool - basic features, setup, task management, and team member management'"

[0577] 6. The terminal displays the received materials to the user.

[0578] Display content: "How to use project management tools - basic features, settings, task management, and team member management"

[0579] Example 3: Personalized support

[0580] 1. The user enters an individual support request via a terminal.

[0581] For example: "Can you tell me how things are going on with your latest project?"

[0582] 2. The device sends a request to the server.

[0583] Submitted: "Support Request: 'Latest Project Progress'"

[0584] 3. The server references the user's profile information and generates support information using a generative AI model.

[0585] Analysis: "Checking progress..."

[0586] 4. The generative AI model generates optimal support information based on the user's profile information and request content.

[0587] Generated information: "We're 70% complete on our latest project. The next major milestone is 'Spec Finalization,' due this Friday."

[0588] 5. The server sends the generated support information to the terminal.

[0589] What you sent: "Status: 'We're 70% done on our latest project. The next major milestone is 'Spec Finalized,' due this Friday.'"

[0590] 6. The device displays the support information it has received to the user.

[0591] It says: "Your latest project is 70% complete. The next major milestone is 'Spec Finalized', due this Friday."

[0592] As described above, the system of the present invention uses a generative AI model to provide efficient learning support tailored to the individual needs of new employees and employees, thereby shortening the adaptation period for new employees and enabling them to contribute to work more quickly.

[0593] The processing flow will be explained below.

[0594] Program processing flow steps

[0595] Accepting user questions

[0596] Step 1:

[0597] The user inputs a question through the terminal. For example, "Please tell me the procedure for starting a new project."

[0598] Step 2:

[0599] The terminal receives a question from the user.

[0600] Create a request to send the question received by the device to the server. For example, generate a request like "Question: 'Please tell me the steps to start a new project.'"

[0601] Question analysis and answer generation

[0602] Step 3:

[0603] The server receives a question request from the terminal.

[0604] The server passes the question to the generative AI model for analysis. For example, let's analyze the question "Question to be analyzed: 'Please tell me the steps to launch a new project.'"

[0605] Step 4:

[0606] A generative AI model receives a question and uses its internal database and pre-trained models to generate an appropriate answer, for example, by going through a process such as "matching against existing database to find an appropriate answer..."

[0607] Step 5:

[0608] The server receives the answer from the generative AI model.

[0609] The server creates a response to send the generated answer to the terminal. For example, it generates the response "Answer: 'To start a new project, click the 'New Project' button in the project management tool, enter the required information, and click 'Save'."

[0610] Providing answers

[0611] Step 6:

[0612] The terminal receives the response received from the server.

[0613] The terminal displays the received response to the user. For example, the response displayed to the user might be, "To start a new project, click the 'New Project' button in the project management tool, enter the required information, and click 'Save'."

[0614] Providing training materials

[0615] Step 1:

[0616] A user inputs a request for training materials through a terminal. For example, the user inputs "Teach me how to use a project management tool."

[0617] Step 2:

[0618] The terminal receives the request and creates a request to send to the server. For example, it creates a request called "Document Request: 'How to use project management tools'".

[0619] Step 3:

[0620] The server receives the request from the terminal.

[0621] The server passes the request to the AI ​​model to generate training materials. For example, let's generate materials about the basic functions, configuration, task management, and team member management of a project management tool.

[0622] Step 4:

[0623] A generative AI model receives the request and generates the appropriate training materials, for example, "Generating how-to documentation for a project management tool..."

[0624] Step 5:

[0625] The server receives the data from the generative AI model.

[0626] The server creates a response to send the generated materials to the terminal. For example, it creates a response such as "Training Materials: 'How to use project management tools - basic functions, configuration, task management, and team member management'".

[0627] Step 6:

[0628] The terminal receives the response received from the server.

[0629] The terminal displays the received materials to the user. For example, the material "How to use project management tools - basic functions, settings, task management, and team member management" is displayed to the user.

[0630] Personalized support

[0631] Step 1:

[0632] A user enters a specific support request through a terminal. For example, the user might enter, "Please let me know the progress on my latest project."

[0633] Step 2:

[0634] The device receives the request and creates a request to send to the server. For example, it creates a request called "Support request: 'Latest project progress'".

[0635] Step 3:

[0636] The server receives the request from the terminal.

[0637] The server references the user's profile information and generates support information using a generative AI model. For example, it goes through a process called "Checking progress..."

[0638] Step 4:

[0639] The generative AI model analyzes the user's profile information and request content to generate appropriate support information. For example, it goes through the process of "Generating the latest project progress information..."

[0640] Step 5:

[0641] The server receives support information from the generative AI model.

[0642] The server creates a response to send the generated support information to the terminal. For example, it generates a response such as "Progress: 'The progress rate of the latest project is 70%. The next milestone is 'Spec Finalization', and the deadline is this Friday.'"

[0643] Step 6:

[0644] The terminal receives the response received from the server.

[0645] The terminal displays the received support information to the user. For example, the following support information is displayed to the user: "The progress rate of the latest project is 70%. The next milestone is 'specification finalization', and the deadline is this Friday."

[0646] Example 1

[0647] 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."

[0648] Appropriate onboarding and training are necessary for new and current employees to quickly adapt to their work and learn efficiently. However, traditional systems rely mainly on manuals and documents for learning, making it difficult to meet individual needs. Another issue is that providing individual support and training is time-consuming and costly. Furthermore, the fact that a lot of information is scattered and difficult to access hinders efficient learning.

[0649] 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.

[0650] In this invention, the server includes a means for a user to input a question, a means for a terminal to receive the question from the user and transmit it to the server via a network, a means for the server to receive the question and analyze the question using a generative AI model, a means for the generative AI model to generate an appropriate answer to the question, a means for the server to transmit the generated answer to the terminal, and a means for the terminal to display the answer to the user, thereby enabling users to quickly and efficiently obtain individually customized information and training materials.

[0651] A "user" is an individual or organization that enters a question or request into the system and receives information or support.

[0652] A "terminal" is a device that allows a user to input a question or request and transmit that input to a server, and includes a computer, a smartphone, etc.

[0653] A "server" is a centralized computing system that receives questions and requests from users, processes them, generates answers and materials, and sends them to terminals.

[0654] A "generative AI model" is artificial intelligence-based software that analyzes user questions and requests and generates appropriate answers and materials.

[0655] A "question" is a textual content that a user enters into the system seeking specific information.

[0656] An "answer" is information generated by the generative AI model based on the user's question and sent to the device via the server.

[0657] "Training materials" are learning documents and presentation materials provided to users and generated by a generative AI model.

[0658] "Support information" refers to information and advice for obtaining specific support that is generated based on a user's individual request.

[0659] "Profile information" refers to a user's individual information and history that is used by the server to generate support information in response to the user's specific requests.

[0660] This invention is an onboarding and training support system that utilizes a generative AI model to improve the learning efficiency of new employees and employees. This system includes elements such as a user, a terminal, a server, and a generative AI model. This enables efficient learning support tailored to the individual needs of each employee.

[0661] In this system, a user first inputs a question or request via a terminal. For example, if a user wants to know the procedure for launching a new project, they input the question, "Please tell me the procedure for launching a new project." This input is sent to the terminal, which then transmits it to the server. The server receives the question and forwards it to the generative AI model for analysis.

[0662] The generative AI model analyzes the question in natural language and generates an appropriate answer. For example, it generates an answer such as, "To start a new project, access the project management tool, click the 'New Project' button, enter the required information, and click 'Save.'" The server sends the generated answer to the device, which then displays it to the user.

[0663] Next, when a user requests training materials, they input a materials request such as "Please teach me how to use a project management tool." This request is also sent from the device to the server, and the server generates appropriate materials using the generative AI model. Materials such as "How to use a project management tool - basic functions, settings, task management, and team member management" are generated and similarly displayed to the user via the device.

[0664] Additionally, when a user enters an individual support request, the request is "Please tell me about the progress of the latest project." The server references the user's profile information and generates support information using a generative AI model. Support information such as "The latest project is 70% complete. The next major milestone is 'specification finalization,' with a deadline of this Friday," is generated and displayed to the user via their device.

[0665] This system allows users to efficiently obtain information and training materials that are fast and personalized.

[0666] Specific examples

[0667] Example questions

[0668] "How do you launch a new project?"

[0669] Training Material Request Example

[0670] "How do I use a project management tool?"

[0671] Example of a personalized support request

[0672] Please let me know the progress on your latest project.

[0673] Using this system will shorten the adaptation period for new employees and employees, allowing them to contribute to work more quickly.

[0674] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0675] Step 1:

[0676] The user inputs a question via a terminal.

[0677] Specifically, the user enters a question such as "Please tell me the steps to start a new project" into the terminal interface (e.g., a text box) and clicks the send button.

[0678] Input: The user's question text.

[0679] Output: The question text stored in the device's temporary memory.

[0680] Step 2:

[0681] The terminal receives a question from the user and sends it to the server via the network.

[0682] Specifically, the terminal sends the question text to the server as an HTTP request.

[0683] Input: The question text stored in the device's temporary memory.

[0684] Output: The HTTP request sent to the server.

[0685] Step 3:

[0686] The server receives questions from the device and passes them to the generative AI model for analysis.

[0687] Specifically, the server extracts the question text from the payload of the HTTP request and sends the question text as a prompt to the generation AI model API.

[0688] Input: The question text of the HTTP request that arrives at the server.

[0689] Output: The prompt sent to the generative AI model.

[0690] Step 4:

[0691] The generative AI model analyzes the question and generates an appropriate answer.

[0692] Specifically, the generative AI model performs natural language processing to generate a text answer to a question. The generation part involves specific data analysis and model calculations.

[0693] Input: The prompt sentence passed to the generative AI model.

[0694] Output: The answer text provided by the generative AI model.

[0695] Step 5:

[0696] The server receives the answer generated by the generative AI model and sends it to the device.

[0697] Specifically, the server receives the answer from the generative AI model and returns it to the device as an HTTP response.

[0698] Input: Answer text from the generative AI model.

[0699] Output: The HTTP response sent to the device.

[0700] Step 6:

[0701] The terminal displays the answer received from the server to the user.

[0702] Specifically, the terminal extracts the response text from the payload of the HTTP response and displays it on the user's interface.

[0703] Input: The HTTP response received from the server.

[0704] Output: The answer text displayed to the user.

[0705] The above is the flow of processing by which the program of this system responds to user questions.

[0706] (Application example 1)

[0707] 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."

[0708] Training for the operation and maintenance of factory robots involves frequent updates and diverse operating procedures, making it difficult for new employees and current employees to learn. Furthermore, one-on-one training requires significant time and resources, making it difficult to provide uniform training to all employees. Therefore, there is a need for effective educational methods to support efficient operation and rapid troubleshooting of factory robots.

[0709] 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.

[0710] In this invention, the server includes a means for generating training materials related to factory work, a means for an AI to refer to the user's past operation history and generate individually customized support information, and a means for receiving the user's questions, analyzing them with the generative AI model, and generating appropriate answers. This allows users to learn how to operate and troubleshoot factory robots in real time, enabling efficient training and support.

[0711] A "user" is an individual person who uses the system.

[0712] A "means for inputting a question" is an interface through which a user can provide a question to the system in text or voice.

[0713] A "terminal" is a hardware device through which a user can input questions or requests and receive the results.

[0714] The "server" is a central computer system that receives questions or requests from users, sends them to the generative AI model, and sends the results back to the user.

[0715] A "generative AI model" is an artificial intelligence technology that analyzes questions and requests from users and generates appropriate answers and training materials.

[0716] "Training materials" are educational materials on the operation and maintenance of factory robots, generated by a generative AI model.

[0717] "Support information" is individually customized advice and assistance information that is generated based on the user's past operation history and profile information.

[0718] The "means for generating training materials for factory work" is a function that uses a generative AI model to automatically generate information necessary for operating and maintaining factory robots.

[0719] "Means for referencing operation history" refers to a function that allows a user to check the records of past operations and have the generative AI model generate information based on those records.

[0720] The "means for generating customized support information" is a function that generates optimal support information in real time based on the user's operation history and profile information.

[0721] The "means of generating an answer" is the function that enables the generative AI model to provide appropriate information based on a question from a user.

[0722] This invention is a system that supports training on the operation and maintenance of factory robots. This system provides a terminal interface for users to input questions and uses a generative AI model to provide appropriate answers and training materials. Specifically, the system uses the following hardware and software:

[0723] Hardware and software used

[0724] Hardware:

[0725] Smartphone (iOS / Android)

[0726] Smart Glasses

[0727] software:

[0728] Frontend: React Native (Mobile Application)

[0729] Backend: Node.js, Express

[0730] Database: MongoDB

[0731] AI model: OpenAI GPT-4

[0732] Natural Language Processing (NLP) technology: Used to generate training materials and support information

[0733] Overall system flow

[0734] 1. User questions:

[0735] Users input questions or requests through a smartphone or smart glasses app, such as "How do I calibrate the robot's sensors?"

[0736] 2. Submit your question:

[0737] The questions entered by the user are sent to the server through the terminal, and the technology used here uses React Native as the front end, with a back end built with Node.js and Express receiving the questions.

[0738] 3. Question analysis and answer generation:

[0739] The server sends the received question to a generative AI model (OpenAI GPT-4), which analyzes the question. The generative AI model uses natural language processing technology to generate an appropriate answer to the question.

[0740] 4. Providing answers:

[0741] The generated answer is sent to the device via the server, and the device's app displays the answer to the user.

[0742] Specific examples

[0743] A user uses a smartphone or smart glasses to input a question as follows:

[0744] User Question: "Please explain in detail the maintenance procedures for the robot."

[0745] Prompt Input: "What is the maintenance procedure for the robot?"

[0746] AI model response: "The robot maintenance procedure is as follows... (detailed instructions)"

[0747] Answer: "The robot maintenance procedure is as follows. First... (show detailed procedure)"

[0748] Also, when a user requests training materials, the flow is as follows:

[0749] User Request: "Please provide training materials on basic operation of factory robots."

[0750] Prompt Input: "Generate training materials on basic operation of factory robots."

[0751] AI model response: "The training materials for basic operation of factory robots include the following... (detailed material content)"

[0752] Display material: "The training material for basic operation of factory robots is as follows... (Display detailed material)"

[0753] In this way, the present invention provides a system that allows users to easily acquire knowledge about the operation and maintenance of factory robots. The system utilizes a generative AI model to quickly generate and display appropriate answers and training materials to users. This improves training efficiency and enables new employees and employees to quickly master their work.

[0754] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0755] Step 1:

[0756] Users input questions or requests through a smartphone or smart glasses app. For example, the input can be a specific question such as, "How do I calibrate the robot's sensors?"

[0757] Step 2:

[0758] The device sends the question received from the user to the server. The entered question data is sent from the device to the server. For example, a question is sent from a mobile app using React Native to a server built with Node.js and Express.

[0759] Step 3:

[0760] The server sends the received question to the generative AI model and requests analysis. The input here is the question data sent in step 2, and the output is a query to the generative AI model. The server uses natural language processing technology to convert the received question into an appropriate format and sends an analysis request to the AI ​​model (GPT-4).

[0761] Step 4:

[0762] The generative AI model analyzes the question and generates an appropriate answer. The AI ​​model analyzes the prompt received from the server and generates a corresponding answer. For example, if the prompt is "How do I calibrate the robot's sensors?", the AI ​​model generates specific calibration procedures.

[0763] Step 5:

[0764] The server processes the answer received from the generative AI model and sends it to the device. The input here is the answer output from the generative AI model, and the output is sending the answer data to the device. The server receives the answer data, reformats it, and sends it back to the device.

[0765] Step 6:

[0766] The device displays the received answers to the user. The input is the answer data sent from the server, and the output is what is displayed to the user. The device app has the function of displaying the answers in an easy-to-understand manner using React Native. For example, the user can see specific steps such as "To calibrate the robot's sensors, follow the steps below..."

[0767] Through this series of processing steps, users can receive real-time answers to questions about factory robot operation and maintenance procedures, thereby improving factory work efficiency and reducing errors.

[0768] 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.

[0769] This invention combines an onboarding and training support system that utilizes a generative AI model to improve the learning efficiency of new employees and employees with an emotion engine that recognizes user emotions. The main components of this system include a user, a terminal, a server, a generative AI model, and an emotion engine.

[0770] Program processing overview

[0771] 1. User question acceptance and emotion recognition

[0772] A user inputs a specific question into the system via a terminal, for example, "Please tell me the procedure for starting a new project."

[0773] The terminal receives a question from the user and sends the input information to the emotion engine.

[0774] The emotion engine analyzes emotions based on the user's input content, input speed, typing strength, and tone of voice (in the case of voice input), and generates emotional information.

[0775] 2. Considering emotions in question analysis and answer generation

[0776] The terminal transmits the emotion information received from the emotion engine to the server.

[0777] The server passes the question content and emotional information to the generative AI model for analysis, which then takes this emotional information into account to generate an appropriate answer.

[0778] For example, if the question expresses anxiety or confusion, the generated answers will be enhanced to be more detailed and easier to understand.

[0779] 3. Providing answers

[0780] The server receives the answer generated by the generative AI model and sends it to the device along with emotional information.

[0781] The device displays the answer and emotional information received from the server to the user, and adjusts the display method based on the emotional information (for example, if the user shows anxiety, it displays calm and encouraging words).

[0782] Specific examples

[0783] Example 1: Answering basic questions

[0784] 1. The user enters a question through the terminal.

[0785] For example: "How do you launch a new project?"

[0786] 2. The device sends the question to the emotion engine.

[0787] For example: "Question: 'How do you launch a new project?'"

[0788] 3. The emotion engine analyzes emotions based on the user's question.

[0789] Example: "User Sentiment: Anxiety"

[0790] 4. The device sends the emotion information to the server.

[0791] Sent: "Emotion: 'Anxiety'"

[0792] 5. The server passes the question and emotion information to the generative AI model for analysis.

[0793] Analysis: "Procedures for launching a new project. Detailed and thorough, as users are expressing anxiety."

[0794] 6. The generative AI model generates answers taking into account emotional information.

[0795] Generated answer: "To start a new project, click the 'New Project' button in the project management tool, enter the required information, and click 'Save'. If you have any questions, please feel free to ask."

[0796] 7. The server sends the generated response to the device.

[0797] Send content: "Answer and emotional response message"

[0798] 8. The terminal displays the received response to the user.

[0799] What it says: "To start a new project, click the 'New Project' button in your project management tool, enter the required information, and click 'Save.' If you have any questions, please don't hesitate to ask."

[0800] Example 2: Providing training materials

[0801] 1. The user inputs a request for training materials through the terminal.

[0802] For example: "How do I use a project management tool?"

[0803] 2. The device sends the request to the emotion engine.

[0804] Example: "Resource Request: 'How to use project management tools'"

[0805] 3. The emotion engine analyzes emotions based on the user request.

[0806] Example: "User sentiment: Interested"

[0807] 4. The device sends the emotion information to the server.

[0808] Send: "Emotion: 'Interested'"

[0809] 5. The server passes the request and emotion information to the generative AI model for analysis.

[0810] Analysis: "Basic functions of project management tools, how to set them up, task management, and team member management. Users are interested, so we've added relevant information."

[0811] 6. The generative AI model generates training materials taking into account emotional information.

[0812] Generated material: "How to use project management tools - basic functions, configuration, task management, team member management, and common troubleshooting tips"

[0813] 7. The server sends the generated materials to the terminal.

[0814] Send content: "Training materials"

[0815] 8. The terminal displays the received materials to the user.

[0816] What you'll see: "How to use a project management tool - basic features, configuration, task management, team member management, and common troubleshooting tips."

[0817] Example 3: Personalized support

[0818] 1. The user enters an individual support request via a terminal.

[0819] For example: "Can you tell me how things are going on with your latest project?"

[0820] 2. The device sends the request to the emotion engine.

[0821] Example: "Support Request: 'Latest Project Progress'"

[0822] 3. The emotion engine analyzes emotions based on the user's support request.

[0823] Example: "User Sentiment: Urgent"

[0824] 4. The device sends the emotion information to the server.

[0825] Sent: "Sentiment: 'urgent'"

[0826] 5. The server passes the request and emotion information to the generative AI model for analysis.

[0827] Analysis: "The latest project progress information. Urgent information is provided promptly."

[0828] 6. The generative AI model generates supporting information taking into account emotional information.

[0829] Generated information: "Our latest project is 70% complete. The next major milestone is 'specification finalization,' which is expected to be completed today."

[0830] 7. The server sends the generated support information to the terminal.

[0831] What to send: "Progress and emergency response messages"

[0832] 8. The device displays the support information it has received to the user.

[0833] It reads: "Our latest project is 70% complete. The next major milestone is 'Spec Finalization', which is expected to be completed today."

[0834] As described above, by combining a generative AI model and an emotion engine, the system of the present invention can provide efficient learning support that takes into account the emotional state of new employees and employees. This allows users to receive feedback and support that is appropriate for their emotions, resulting in more effective learning.

[0835] The processing flow will be explained below.

[0836] Program processing flow steps (when combined with emotion engine)

[0837] User question reception and emotion recognition

[0838] Step 1:

[0839] The user inputs a question through the terminal.

[0840] For example: "What are the steps to launching a new project?"

[0841] Step 2:

[0842] The terminal receives a question from the user.

[0843] The terminal sends the user's input to the emotion engine.

[0844] Step 3:

[0845] The emotion engine analyzes the user's input, as well as the speed, strength, and tone of voice (in the case of voice input), to recognize emotions.

[0846] Example: "User Sentiment: Anxiety"

[0847] Step 4:

[0848] The emotion engine returns the analysis results to the device.

[0849] The device transmits the emotion information to the server.

[0850] Considering emotions in question analysis and answer generation

[0851] Step 5:

[0852] The server receives the question and emotion information received from the terminal.

[0853] The server passes the question content and emotional information to the generative AI model for analysis.

[0854] Step 6:

[0855] Generative AI models take emotional information into account when generating appropriate answers to questions.

[0856] Example: "Provide a detailed and thorough explanation of the steps to launch a new project."

[0857] Step 7:

[0858] The server receives the answer from the generative AI model.

[0859] The server transmits the generated answer and emotion information to the terminal.

[0860] Providing answers

[0861] Step 8:

[0862] The terminal displays the answer and emotion information received from the server.

[0863] For example: "To start a new project, click the 'New Project' button in your project management tool, enter the required information, and click 'Save.' If you have any questions, please don't hesitate to ask."

[0864] Providing training materials

[0865] Step 1:

[0866] A user inputs a request for training materials through a terminal.

[0867] For example: "How do I use a project management tool?"

[0868] Step 2:

[0869] The device receives the request and sends it to the emotion engine.

[0870] The emotion engine analyzes the content, speed, strength and tone of the user's request.

[0871] Step 3:

[0872] The emotion engine returns the analysis results to the device.

[0873] The device transmits the emotion information to the server.

[0874] Step 4:

[0875] The server receives the request and emotion information and passes it to the generative AI model for analysis.

[0876] Step 5:

[0877] Generative AI models take emotional information into account when generating training materials.

[0878] Example: "Detailed documentation including basic project management tool features, setup, task management, and team member management."

[0879] Step 6:

[0880] The server receives the data from the generative AI model and sends it to the terminal.

[0881] Step 7:

[0882] The terminal displays materials and emotional information to the user.

[0883] Example: "How to use a project management tool - basic features, setup, task management, and team member management."

[0884] Personalized support

[0885] Step 1:

[0886] A user inputs an individual support request through a terminal.

[0887] For example: "Can you tell me how things are going on with your latest project?"

[0888] Step 2:

[0889] The device receives the request and sends it to the emotion engine.

[0890] The emotion engine analyzes the content, speed, strength and tone of the user's request.

[0891] Step 3:

[0892] The emotion engine returns the analysis results to the device.

[0893] The device transmits the emotion information to the server.

[0894] Step 4:

[0895] The server receives the request and emotion information, references the user's profile information, and passes it to the generative AI model for analysis.

[0896] Step 5:

[0897] The generative AI model takes emotional information into account when generating supporting information.

[0898] Example: "Detailed information on the progress of the latest project and next milestones."

[0899] Step 6:

[0900] The server receives support information from the generative AI model and sends it to the device.

[0901] Step 7:

[0902] The terminal displays support information and emotional information to the user.

[0903] Example: "We're 70% complete on our latest project. The next major milestone is 'Spec Finalization,' which is expected to be completed today."

[0904] Example 2

[0905] 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."

[0906] Current education, training, and support systems do not provide answers or support that take into account the user's emotional state, which can sometimes leave users feeling frustrated or anxious. To improve the learning efficiency of new employees and current employees in particular, it is important to recognize the user's emotions and provide appropriate answers and training materials according to their situation. However, conventional systems lack such functionality.

[0907] 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.

[0908] In this invention, the server includes a means for passing the user's question and emotional information to the generative AI model for analysis, a means for sending the generated answer to the terminal, and a means for adjusting the display method based on the emotional information. This makes it possible to improve the user's learning efficiency by recognizing the user's emotions and providing appropriate answers and training materials according to the situation.

[0909] "User" means a person who accesses the System and enters a question or request.

[0910] "Terminal" refers to a mechanical device through which a user inputs a question or request and transmits it to the system.

[0911] An "emotion engine" refers to a software component that analyzes a user's input and behavioral patterns when entering input to identify the user's emotional state.

[0912] "Emotion information" refers to data that indicates the user's emotional state extracted through analysis by the emotion engine.

[0913] "Server" refers to a central computer system that receives user queries and requests and performs any necessary analysis or data processing.

[0914] A "generative AI model" is an artificial intelligence algorithm used by the server that generates appropriate answers and materials in response to user questions and requests.

[0915] "Answer" refers to the explanation or description that a generative AI model provides in response to a user's question.

[0916] "Training Materials" refers to the educational materials created by the generative AI model based on the learning content requested by the User.

[0917] "Support information" refers to assistance information provided by the generative AI model in response to individual user requests.

[0918] "Adjusting the display method" refers to presenting information in an optimal format according to the user's emotional state based on emotional information.

[0919] This system recognizes a user's emotions and provides appropriate answers, training materials, and support information based on those emotions. The system consists of the following main components: the user, the device, the server, the generative AI model, and the emotion engine.

[0920] System Overview

[0921] 1. A terminal that provides an interface for users to enter questions or requests.

[0922] 2. The device receives the user's input, extracts emotional information through the emotion engine, and sends it to the server.

[0923] 3. The emotion engine analyzes the user's input and behavioral patterns when entering data to identify their emotional state.

[0924] 4. The server receives the user's questions, requests, and emotional information and analyzes them using a generative AI model.

[0925] 5. The generative AI model takes into account the question, request, and emotional information to generate appropriate answers, training materials, and support information.

[0926] 6. The device receives the information from the server and displays it in the most appropriate format for the user.

[0927] Hardware and Software Used

[0928] Device: A device such as a personal computer, tablet, or smartphone.

[0929] Emotion Engine: Software that includes a natural language processing (NLP) engine, a speech analysis system, and a typing analysis system.

[0930] Server: A high-performance computer or cloud computing platform.

[0931] Generative AI models: Deep learning models (e.g., large-scale generative models such as GPT-3).

[0932] Specific operation example

[0933] Example 1: Answering basic questions

[0934] 1. A user types the question "How do I start a new project?" into a terminal.

[0935] 2. The device sends a question to the emotion engine and identifies the user's emotion as "anxiety."

[0936] 3. The device sends the question, including the emotion information, to the server.

[0937] 4. The server passes the question and emotion information to the generative AI model, which generates an answer. For example, it might generate an answer like, "To start a new project, click the 'New Project' button in the project management tool, enter the required information, and click 'Save'. If you have any questions, please feel free to ask."

[0938] 5. The device receives the answer and displays it to the user.

[0939] Example 2: Providing training materials

[0940] 1. The user enters a request through the terminal: "Please teach me how to use the project management tool."

[0941] 2. The device sends a request to the emotion engine and identifies the user's emotion as "interest."

[0942] 3. The device sends a request including emotion information to the server.

[0943] 4. The server passes the request and sentiment information to the generative AI model to generate training materials, such as "How to use a project management tool - basic functions, configuration, task management, team member management, and common troubleshooting tips."

[0944] 5. The device receives the training materials and displays them to the user.

[0945] Example 3: Personalized support

[0946] 1. The user inputs a request through the terminal: "Please let me know the progress of the latest project."

[0947] 2. The device sends a request to the emotion engine and identifies the user's emotion as "urgent."

[0948] 3. The device sends a request including emotion information to the server.

[0949] 4. The server passes the request and emotion information to the generative AI model, which generates information about the latest progress. For example, it generates information like, "The latest project is 70% complete. The next major milestone is 'specification finalization,' which is expected to be completed today."

[0950] 5. The device receives the support information and displays it to the user.

[0951] This will provide answers and materials that take the user's emotions into consideration, which is expected to improve learning efficiency.

[0952] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0953] Step 1:

[0954] The user enters a question

[0955] Specific action: The user inputs a question into the input interface of the device, for example, "How do I start a new project?"

[0956] Input: The text data of the question entered by the user.

[0957] Output: The terminal obtains the user's question text data.

[0958] Step 2:

[0959] The device sends the user's question to the emotion engine.

[0960] Specific operation: The device sends the user's input data to the emotion engine, which receives data such as the user's input content, input speed, typing strength, and voice tone (in the case of voice input).

[0961] Input: Text data of the question entered by the user and behavioral data when entering the question.

[0962] Output: The emotion engine receives the input data.

[0963] Step 3:

[0964] Emotion engine analyzes user emotions

[0965] Specific operation: The emotion engine analyzes text data and behavioral data to identify the user's emotions. For example, it determines that the user is feeling "anxiety" based on the input content.

[0966] Input: Textual and behavioral data received by the emotion engine.

[0967] Output: Emotional information including the user's emotional state (e.g., anxiety, interest, urgency).

[0968] Step 4:

[0969] The device sends emotional information to the server.

[0970] Specific operation: The device sends the generated emotion information to the server along with the user's question text.

[0971] Input: User question text data and sentiment information.

[0972] Output: The server receives the question text and sentiment information.

[0973] Step 5:

[0974] The server passes the question and emotion information to the generative AI model

[0975] Specific operation: The server inputs the received question text and emotion information into the generative AI model, which then generates an appropriate answer based on this.

[0976] Input: Question text data and sentiment information received by the server.

[0977] Output: The generative AI model begins its analysis.

[0978] Step 6:

[0979] Generative AI models generate appropriate answers to questions

[0980] Specific operation: The generative AI model analyzes the question text data and emotional information, and generates an appropriate answer taking into account the user's emotional state. For example, if the user is feeling "anxious," the answer will be more detailed.

[0981] Input: Question text data and sentiment information.

[0982] Output: Emotion-sensitive answer text data.

[0983] Step 7:

[0984] The server generates a response and sends it to the device.

[0985] Specific operation: The server receives the answer text data generated from the generative AI model and sends it to the terminal.

[0986] Input: Generated answer text data.

[0987] Output: The terminal receives the response text data.

[0988] Step 8:

[0989] The device displays the answers to the user and adjusts the display based on the user's emotional information.

[0990] Specific operation: The device displays the received answer text to the user. At the same time, the display method is adjusted based on the user's emotional information. For example, if the user is feeling "anxious," a calm and encouraging message is added.

[0991] Input: Answer text data and sentiment information.

[0992] Output: A display tailored to the user.

[0993] (Application example 2)

[0994] 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."

[0995] Conventional onboarding and training systems provide uniform responses to user questions and requests, making it difficult to respond flexibly to the user's emotions and circumstances. In particular, new employees and employees who are unfamiliar with new environments and work procedures often lack support that adequately alleviates their anxiety and confusion. Due to the lack of individualized responses that take emotions into consideration, there is a need to improve learning and work efficiency.

[0996] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for analyzing the question and emotion information using a generative AI model, means for the generative AI model to generate an appropriate answer to the question taking the emotion information into consideration, and means for the emotion engine to analyze the user's emotion. This enables flexible responses that take the user's emotions into consideration.

[0997] A "user" is an entity that operates the system and enters questions and requests.

[0998] A "terminal" is a device that receives questions or requests entered by a user and transmits them to a server.

[0999] The "emotion engine" is a function that analyzes the user's input data (text, voice, input speed, etc.) and generates emotional information.

[1000] The "server" is a central device that analyzes questions, requests, and emotional information received from users and transmits the results to terminals.

[1001] A "generative AI model" is an artificial intelligence technology that generates appropriate answers and materials based on input questions or requests.

[1002] The present invention relates to a training support system that uses an application installed on a factory robot to improve employee learning efficiency. The system includes a user, a terminal, a server, a generative AI model, and an emotion engine.

[1003] The overall flow of the system is as follows: The user inputs a question or request via their device, which then sends it to the emotion engine. The emotion engine analyzes the user's input data and generates emotional information. The device then sends the input data along with the emotional information to the server. The server passes the input data and emotional information to the generative AI model for analysis, and sends the generated answer or materials back to the device. The device then finally displays or plays the answer or materials to the user.

[1004] This section explains the specific hardware and software. The hardware uses factory robots, voice input devices, display panels, and speakers. The software uses the Emotion Engine (emotion recognition engine) and AI Response Generator (generative AI model). The server is the central device that handles overall data exchange and analysis, and can also utilize edge computing and cloud services.

[1005] For example, let's consider a specific example where a worker asks a question about how to operate a new machine. When the user inputs a question into the device (voice input is also possible), such as "Please tell me how to operate this new press machine," the device sends that information to the emotion engine. The emotion engine analyzes the content, speed, and tone of voice of the input, and determines the user's emotion as "interest." The device then sends this as data to the server, and the server uses a generative AI model to generate an appropriate answer that takes the emotional information into consideration. As a specific example, the answer generated might be, "To operate this new press machine, first turn it on, then press the start button on the control panel. After that, adjust the settings and begin work. A detailed manual is also available, so please let us know if you need one."

[1006] As an example of a prompt, the following text is fed into the generative AI model:

[1007] Question: 'How do I operate the new press?'

[1008] Emotion: 'Interest'

[1009] This system is expected to improve the quality of work instruction and respond flexibly to the user's emotions. This application example is particularly effective in helping new and inexperienced employees to work with peace of mind.

[1010] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1011] Step 1:

[1012] A user inputs a question or request via a terminal. The input method can be text input or voice input. For example, if a user inputs a question such as "Please tell me how to operate the new press machine," the input contains the user's emotions and intentions.

[1013] Step 2:

[1014] The device receives a question from the user and sends it to the emotion engine. The input data includes text information and voice data, and the data is sent to the emotion engine for analysis.

[1015] Step 3:

[1016] The emotion engine analyzes emotions based on the user's input data. In this step, the content of the text, input speed, and tone of voice are analyzed to generate the user's emotion information (e.g., interest, anxiety, urgency, etc.). For example, in the case of voice input, "interest" is generated as emotion information by analyzing the tone of voice.

[1017] Step 4:

[1018] The device sends the emotion information received from the emotion engine to the server. This sent data includes the original question and emotion information. For example, data such as "Question: Please tell me how to operate the new press machine" and "Emotion information: Interest" is sent.

[1019] Step 5:

[1020] The server passes the question content and emotional information to the generative AI model for analysis. Based on the input question content and emotional information, data processing and analysis are performed to generate the most appropriate answer. The generative AI model analyzes the question and generates an answer that takes the emotional information into account.

[1021] Step 6:

[1022] The generative AI model takes emotional information into account to generate appropriate answers. The output answers are tailored to the user's emotions. For example, a detailed and engaging answer is generated for the "interest" emotion. Specifically, the model might generate an answer such as, "To operate a new press, first turn it on, then press the start button on the control panel. After that, adjust the settings and begin operation. A detailed manual is also available, so please let us know if you need one."

[1023] Step 7:

[1024] The server transmits the generated answer to the terminal. In this step, the generated answer includes an emotion-responsive message, and the answer is transmitted in an appropriate format based on the user's emotion.

[1025] Step 8:

[1026] The device displays or plays back the received answer and emotion-responsive message to the user. Depending on the user's emotion, an appropriate answer is provided in the form of a text display or audio playback. For example, if the emotion is "interested," detailed instructions are displayed on the screen and audio guidance is played. In this way, flexible responses and support that take the user's emotions into consideration are possible.

[1027] 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.

[1028] 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.

[1029] 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.

[1030] [Third embodiment]

[1031] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[1032] 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.

[1033] 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).

[1034] 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.

[1035] 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.

[1036] 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).

[1037] 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.

[1038] 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.

[1039] 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.

[1040] 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.

[1041] 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.

[1042] 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."

[1043] This invention is an onboarding and training support system that utilizes a generative AI model to improve the learning efficiency of new employees and employees. The main components of this system include a user, a terminal, a server, and a generative AI model.

[1044] Program processing overview

[1045] 1. Accepting user questions

[1046] A user inputs a specific question into the system via a terminal, for example, "Please tell me the procedure for starting a new project."

[1047] The terminal receives a question from the user and transmits the content of the question to the server.

[1048] 2. Question Analysis and Answer Generation

[1049] The server processes the questions received from the device and passes the received questions to the generative AI model for analysis.

[1050] The generative AI model analyzes the questions and generates appropriate answers to the user's questions, such as explaining how to use project management tools to launch a new project.

[1051] 3. Providing answers

[1052] The server receives the answer generated by the generative AI model and sends the answer to the device.

[1053] The terminal displays the answer received from the server to the user.

[1054] Specific examples

[1055] Example 1: Answering basic questions

[1056] 1. The user enters a question through the terminal.

[1057] For example: "How do you launch a new project?"

[1058] 2. The device sends a question to the server.

[1059] Submitted: "Question: 'How do you launch a new project?'"

[1060] 3. The server passes the received question to the generative AI model for analysis.

[1061] Analysis: "Check the steps for your new project..."

[1062] 4. The generative AI model generates appropriate answers to the questions.

[1063] Generated answer: "To start a new project, go to your project management tool, click the 'New Project' button, enter the required information, and click 'Save'."

[1064] 5. The server sends the generated response to the device.

[1065] What you sent: "Answer: 'To start a new project, go to your project management tool, click the 'New Project' button, enter the required information, and click 'Save.'"

[1066] 6. The terminal displays the received response to the user.

[1067] What it says: "To start a new project, go to your project management tool, click the 'New Project' button, enter the required information, and click 'Save'."

[1068] Example 2: Providing training materials

[1069] 1. The user inputs a request for training materials through the terminal.

[1070] For example: "How do I use a project management tool?"

[1071] 2. The device sends a request to the server.

[1072] Submission: "Request for Resources: 'How to Use Project Management Tools'"

[1073] 3. The server passes the received request to the generative AI model to generate training materials.

[1074] Generated content: "Basic functions of project management tools, how to set them up, task management, and team member management"

[1075] 4. The generative AI model generates appropriate training materials.

[1076] Generated material: "How to use project management tools - basic functions, configuration, task management, and team member management"

[1077] 5. The server sends the generated materials to the terminal.

[1078] Submission: "Document: 'How to use a project management tool - basic features, setup, task management, and team member management'"

[1079] 6. The terminal displays the received materials to the user.

[1080] Display content: "How to use project management tools - basic features, settings, task management, and team member management"

[1081] Example 3: Personalized support

[1082] 1. The user enters an individual support request via a terminal.

[1083] For example: "Can you tell me how things are going on with your latest project?"

[1084] 2. The device sends a request to the server.

[1085] Submitted: "Support Request: 'Latest Project Progress'"

[1086] 3. The server references the user's profile information and generates support information using a generative AI model.

[1087] Analysis: "Checking progress..."

[1088] 4. The generative AI model generates optimal support information based on the user's profile information and request content.

[1089] Generated information: "We're 70% complete on our latest project. The next major milestone is 'Spec Finalization,' due this Friday."

[1090] 5. The server sends the generated support information to the terminal.

[1091] What you sent: "Status: 'We're 70% done on our latest project. The next major milestone is 'Spec Finalized,' due this Friday.'"

[1092] 6. The device displays the support information it has received to the user.

[1093] It says: "Your latest project is 70% complete. The next major milestone is 'Spec Finalized', due this Friday."

[1094] As described above, the system of the present invention uses a generative AI model to provide efficient learning support tailored to the individual needs of new employees and employees, thereby shortening the adaptation period for new employees and enabling them to contribute to work more quickly.

[1095] The processing flow will be explained below.

[1096] Program processing flow steps

[1097] Accepting user questions

[1098] Step 1:

[1099] The user inputs a question through the terminal. For example, "Please tell me the procedure for starting a new project."

[1100] Step 2:

[1101] The terminal receives a question from the user.

[1102] Create a request to send the question received by the device to the server. For example, generate a request like "Question: 'Please tell me the steps to start a new project.'"

[1103] Question analysis and answer generation

[1104] Step 3:

[1105] The server receives a question request from the terminal.

[1106] The server passes the question to the generative AI model for analysis. For example, let's analyze the question "Question to be analyzed: 'Please tell me the steps to launch a new project.'"

[1107] Step 4:

[1108] A generative AI model receives a question and uses its internal database and pre-trained models to generate an appropriate answer, for example, by going through a process such as "matching against existing database to find an appropriate answer..."

[1109] Step 5:

[1110] The server receives the answer from the generative AI model.

[1111] The server creates a response to send the generated answer to the terminal. For example, it generates the response "Answer: 'To start a new project, click the 'New Project' button in the project management tool, enter the required information, and click 'Save'."

[1112] Providing answers

[1113] Step 6:

[1114] The terminal receives the response received from the server.

[1115] The terminal displays the received response to the user. For example, the response displayed to the user might be, "To start a new project, click the 'New Project' button in the project management tool, enter the required information, and click 'Save'."

[1116] Providing training materials

[1117] Step 1:

[1118] A user inputs a request for training materials through a terminal. For example, the user inputs "Teach me how to use a project management tool."

[1119] Step 2:

[1120] The terminal receives the request and creates a request to send to the server. For example, it creates a request called "Document Request: 'How to use project management tools'".

[1121] Step 3:

[1122] The server receives the request from the terminal.

[1123] The server passes the request to the AI ​​model to generate training materials. For example, let's generate materials about the basic functions, configuration, task management, and team member management of a project management tool.

[1124] Step 4:

[1125] A generative AI model receives the request and generates the appropriate training materials, for example, "Generating how-to documentation for a project management tool..."

[1126] Step 5:

[1127] The server receives the data from the generative AI model.

[1128] The server creates a response to send the generated materials to the terminal. For example, it creates a response such as "Training Materials: 'How to use project management tools - basic functions, configuration, task management, and team member management'".

[1129] Step 6:

[1130] The terminal receives the response received from the server.

[1131] The terminal displays the received materials to the user. For example, the material "How to use project management tools - basic functions, settings, task management, and team member management" is displayed to the user.

[1132] Personalized support

[1133] Step 1:

[1134] A user enters a specific support request through a terminal. For example, the user might enter, "Please let me know the progress on my latest project."

[1135] Step 2:

[1136] The device receives the request and creates a request to send to the server. For example, it creates a request called "Support request: 'Latest project progress'".

[1137] Step 3:

[1138] The server receives the request from the terminal.

[1139] The server references the user's profile information and generates support information using a generative AI model. For example, it goes through a process called "Checking progress..."

[1140] Step 4:

[1141] The generative AI model analyzes the user's profile information and request content to generate appropriate support information. For example, it goes through the process of "Generating the latest project progress information..."

[1142] Step 5:

[1143] The server receives support information from the generative AI model.

[1144] The server creates a response to send the generated support information to the terminal. For example, it generates a response such as "Progress: 'The progress rate of the latest project is 70%. The next milestone is 'Spec Finalization', and the deadline is this Friday.'"

[1145] Step 6:

[1146] The terminal receives the response received from the server.

[1147] The terminal displays the received support information to the user. For example, the following support information is displayed to the user: "The progress rate of the latest project is 70%. The next milestone is 'specification finalization', and the deadline is this Friday."

[1148] Example 1

[1149] 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."

[1150] Appropriate onboarding and training are necessary for new and current employees to quickly adapt to their work and learn efficiently. However, traditional systems rely mainly on manuals and documents for learning, making it difficult to meet individual needs. Another issue is that providing individual support and training is time-consuming and costly. Furthermore, the fact that a lot of information is scattered and difficult to access hinders efficient learning.

[1151] 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.

[1152] In this invention, the server includes a means for a user to input a question, a means for a terminal to receive the question from the user and transmit it to the server via a network, a means for the server to receive the question and analyze the question using a generative AI model, a means for the generative AI model to generate an appropriate answer to the question, a means for the server to transmit the generated answer to the terminal, and a means for the terminal to display the answer to the user, thereby enabling users to quickly and efficiently obtain individually customized information and training materials.

[1153] A "user" is an individual or organization that enters a question or request into the system and receives information or support.

[1154] A "terminal" is a device that allows a user to input a question or request and transmit that input to a server, and includes a computer, a smartphone, etc.

[1155] A "server" is a centralized computing system that receives questions and requests from users, processes them, generates answers and materials, and sends them to terminals.

[1156] A "generative AI model" is artificial intelligence-based software that analyzes user questions and requests and generates appropriate answers and materials.

[1157] A "question" is a textual content that a user enters into the system seeking specific information.

[1158] An "answer" is information generated by the generative AI model based on the user's question and sent to the device via the server.

[1159] "Training materials" are learning documents and presentation materials provided to users and generated by a generative AI model.

[1160] "Support information" refers to information and advice for obtaining specific support that is generated based on a user's individual request.

[1161] "Profile information" refers to a user's individual information and history that is used by the server to generate support information in response to the user's specific requests.

[1162] This invention is an onboarding and training support system that utilizes a generative AI model to improve the learning efficiency of new employees and employees. This system includes elements such as a user, a terminal, a server, and a generative AI model. This enables efficient learning support tailored to the individual needs of each employee.

[1163] In this system, a user first inputs a question or request via a terminal. For example, if a user wants to know the procedure for launching a new project, they input the question, "Please tell me the procedure for launching a new project." This input is sent to the terminal, which then transmits it to the server. The server receives the question and forwards it to the generative AI model for analysis.

[1164] The generative AI model analyzes the question in natural language and generates an appropriate answer. For example, it generates an answer such as, "To start a new project, access the project management tool, click the 'New Project' button, enter the required information, and click 'Save.'" The server sends the generated answer to the device, which then displays it to the user.

[1165] Next, when a user requests training materials, they input a materials request such as "Please teach me how to use a project management tool." This request is also sent from the device to the server, and the server generates appropriate materials using the generative AI model. Materials such as "How to use a project management tool - basic functions, settings, task management, and team member management" are generated and similarly displayed to the user via the device.

[1166] Additionally, when a user enters an individual support request, the request is "Please tell me about the progress of the latest project." The server references the user's profile information and generates support information using a generative AI model. Support information such as "The latest project is 70% complete. The next major milestone is 'specification finalization,' with a deadline of this Friday," is generated and displayed to the user via their device.

[1167] This system allows users to efficiently obtain information and training materials that are fast and personalized.

[1168] Specific examples

[1169] Example questions

[1170] "How do you launch a new project?"

[1171] Training Material Request Example

[1172] "How do I use a project management tool?"

[1173] Example of a personalized support request

[1174] Please let me know the progress on your latest project.

[1175] Using this system will shorten the adaptation period for new employees and employees, allowing them to contribute to work more quickly.

[1176] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1177] Step 1:

[1178] The user inputs a question via a terminal.

[1179] Specifically, the user enters a question such as "Please tell me the steps to start a new project" into the terminal interface (e.g., a text box) and clicks the send button.

[1180] Input: The user's question text.

[1181] Output: The question text stored in the device's temporary memory.

[1182] Step 2:

[1183] The terminal receives a question from the user and sends it to the server via the network.

[1184] Specifically, the terminal sends the question text to the server as an HTTP request.

[1185] Input: The question text stored in the device's temporary memory.

[1186] Output: The HTTP request sent to the server.

[1187] Step 3:

[1188] The server receives questions from the device and passes them to the generative AI model for analysis.

[1189] Specifically, the server extracts the question text from the payload of the HTTP request and sends the question text as a prompt to the generation AI model API.

[1190] Input: The question text of the HTTP request that arrives at the server.

[1191] Output: The prompt sent to the generative AI model.

[1192] Step 4:

[1193] The generative AI model analyzes the question and generates an appropriate answer.

[1194] Specifically, the generative AI model performs natural language processing to generate a text answer to a question. The generation part involves specific data analysis and model calculations.

[1195] Input: The prompt sentence passed to the generative AI model.

[1196] Output: The answer text provided by the generative AI model.

[1197] Step 5:

[1198] The server receives the answer generated by the generative AI model and sends it to the device.

[1199] Specifically, the server receives the answer from the generative AI model and returns it to the device as an HTTP response.

[1200] Input: Answer text from the generative AI model.

[1201] Output: The HTTP response sent to the device.

[1202] Step 6:

[1203] The terminal displays the answer received from the server to the user.

[1204] Specifically, the terminal extracts the response text from the payload of the HTTP response and displays it on the user's interface.

[1205] Input: The HTTP response received from the server.

[1206] Output: The answer text displayed to the user.

[1207] The above is the flow of processing by which the program of this system responds to user questions.

[1208] (Application example 1)

[1209] 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."

[1210] Training for the operation and maintenance of factory robots involves frequent updates and diverse operating procedures, making it difficult for new employees and current employees to learn. Furthermore, one-on-one training requires significant time and resources, making it difficult to provide uniform training to all employees. Therefore, there is a need for effective educational methods to support efficient operation and rapid troubleshooting of factory robots.

[1211] 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.

[1212] In this invention, the server includes a means for generating training materials related to factory work, a means for an AI to refer to the user's past operation history and generate individually customized support information, and a means for receiving the user's questions, analyzing them with the generative AI model, and generating appropriate answers. This allows users to learn how to operate and troubleshoot factory robots in real time, enabling efficient training and support.

[1213] A "user" is an individual person who uses the system.

[1214] A "means for inputting a question" is an interface through which a user can provide a question to the system in text or voice.

[1215] A "terminal" is a hardware device through which a user can input questions or requests and receive the results.

[1216] The "server" is a central computer system that receives questions or requests from users, sends them to the generative AI model, and sends the results back to the user.

[1217] A "generative AI model" is an artificial intelligence technology that analyzes questions and requests from users and generates appropriate answers and training materials.

[1218] "Training materials" are educational materials on the operation and maintenance of factory robots, generated by a generative AI model.

[1219] "Support information" is individually customized advice and assistance information that is generated based on the user's past operation history and profile information.

[1220] The "means for generating training materials for factory work" is a function that uses a generative AI model to automatically generate information necessary for operating and maintaining factory robots.

[1221] "Means for referencing operation history" refers to a function that allows a user to check the records of past operations and have the generative AI model generate information based on those records.

[1222] The "means for generating customized support information" is a function that generates optimal support information in real time based on the user's operation history and profile information.

[1223] The "means of generating an answer" is the function that enables the generative AI model to provide appropriate information based on a question from a user.

[1224] This invention is a system that supports training on the operation and maintenance of factory robots. This system provides a terminal interface for users to input questions and uses a generative AI model to provide appropriate answers and training materials. Specifically, the system uses the following hardware and software:

[1225] Hardware and software used

[1226] Hardware:

[1227] Smartphone (iOS / Android)

[1228] Smart Glasses

[1229] software:

[1230] Frontend: React Native (Mobile Application)

[1231] Backend: Node.js, Express

[1232] Database: MongoDB

[1233] AI model: OpenAI GPT-4

[1234] Natural Language Processing (NLP) technology: Used to generate training materials and support information

[1235] Overall system flow

[1236] 1. User questions:

[1237] Users input questions or requests through a smartphone or smart glasses app, such as "How do I calibrate the robot's sensors?"

[1238] 2. Submit your question:

[1239] The questions entered by the user are sent to the server through the terminal, and the technology used here uses React Native as the front end, with a back end built with Node.js and Express receiving the questions.

[1240] 3. Question analysis and answer generation:

[1241] The server sends the received question to a generative AI model (OpenAI GPT-4), which analyzes the question. The generative AI model uses natural language processing technology to generate an appropriate answer to the question.

[1242] 4. Providing answers:

[1243] The generated answer is sent to the device via the server, and the device's app displays the answer to the user.

[1244] Specific examples

[1245] A user uses a smartphone or smart glasses to input a question as follows:

[1246] User Question: "Please explain in detail the maintenance procedures for the robot."

[1247] Prompt Input: "What is the maintenance procedure for the robot?"

[1248] AI model response: "The robot maintenance procedure is as follows... (detailed instructions)"

[1249] Answer: "The robot maintenance procedure is as follows. First... (show detailed procedure)"

[1250] Also, when a user requests training materials, the flow is as follows:

[1251] User Request: "Please provide training materials on basic operation of factory robots."

[1252] Prompt Input: "Generate training materials on basic operation of factory robots."

[1253] AI model response: "The training materials for basic operation of factory robots include the following... (detailed material content)"

[1254] Display material: "The training material for basic operation of factory robots is as follows... (Display detailed material)"

[1255] In this way, the present invention provides a system that allows users to easily acquire knowledge about the operation and maintenance of factory robots. The system utilizes a generative AI model to quickly generate and display appropriate answers and training materials to users. This improves training efficiency and enables new employees and employees to quickly master their work.

[1256] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1257] Step 1:

[1258] Users input questions or requests through a smartphone or smart glasses app. For example, the input can be a specific question such as, "How do I calibrate the robot's sensors?"

[1259] Step 2:

[1260] The device sends the question received from the user to the server. The entered question data is sent from the device to the server. For example, a question is sent from a mobile app using React Native to a server built with Node.js and Express.

[1261] Step 3:

[1262] The server sends the received question to the generative AI model and requests analysis. The input here is the question data sent in step 2, and the output is a query to the generative AI model. The server uses natural language processing technology to convert the received question into an appropriate format and sends an analysis request to the AI ​​model (GPT-4).

[1263] Step 4:

[1264] The generative AI model analyzes the question and generates an appropriate answer. The AI ​​model analyzes the prompt received from the server and generates a corresponding answer. For example, if the prompt is "How do I calibrate the robot's sensors?", the AI ​​model generates specific calibration procedures.

[1265] Step 5:

[1266] The server processes the answer received from the generative AI model and sends it to the device. The input here is the answer output from the generative AI model, and the output is sending the answer data to the device. The server receives the answer data, reformats it, and sends it back to the device.

[1267] Step 6:

[1268] The device displays the received answers to the user. The input is the answer data sent from the server, and the output is what is displayed to the user. The device app has the function of displaying the answers in an easy-to-understand manner using React Native. For example, the user can see specific steps such as "To calibrate the robot's sensors, follow the steps below..."

[1269] Through this series of processing steps, users can receive real-time answers to questions about factory robot operation and maintenance procedures, thereby improving factory work efficiency and reducing errors.

[1270] 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.

[1271] This invention combines an onboarding and training support system that utilizes a generative AI model to improve the learning efficiency of new employees and employees with an emotion engine that recognizes user emotions. The main components of this system include a user, a terminal, a server, a generative AI model, and an emotion engine.

[1272] Program processing overview

[1273] 1. User question acceptance and emotion recognition

[1274] A user inputs a specific question into the system via a terminal, for example, "Please tell me the procedure for starting a new project."

[1275] The terminal receives a question from the user and sends the input information to the emotion engine.

[1276] The emotion engine analyzes emotions based on the user's input content, input speed, typing strength, and tone of voice (in the case of voice input), and generates emotional information.

[1277] 2. Considering emotions in question analysis and answer generation

[1278] The terminal transmits the emotion information received from the emotion engine to the server.

[1279] The server passes the question content and emotional information to the generative AI model for analysis, which then takes this emotional information into account to generate an appropriate answer.

[1280] For example, if the question expresses anxiety or confusion, the generated answers will be enhanced to be more detailed and easier to understand.

[1281] 3. Providing answers

[1282] The server receives the answer generated by the generative AI model and sends it to the device along with emotional information.

[1283] The device displays the answer and emotional information received from the server to the user, and adjusts the display method based on the emotional information (for example, if the user shows anxiety, it displays calm and encouraging words).

[1284] Specific examples

[1285] Example 1: Answering basic questions

[1286] 1. The user enters a question through the terminal.

[1287] For example: "How do you launch a new project?"

[1288] 2. The device sends the question to the emotion engine.

[1289] For example: "Question: 'How do you launch a new project?'"

[1290] 3. The emotion engine analyzes emotions based on the user's question.

[1291] Example: "User Sentiment: Anxiety"

[1292] 4. The device sends the emotion information to the server.

[1293] Sent: "Emotion: 'Anxiety'"

[1294] 5. The server passes the question and emotion information to the generative AI model for analysis.

[1295] Analysis: "Procedures for launching a new project. Detailed and thorough, as users are expressing anxiety."

[1296] 6. The generative AI model generates answers taking into account emotional information.

[1297] Generated answer: "To start a new project, click the 'New Project' button in the project management tool, enter the required information, and click 'Save'. If you have any questions, please feel free to ask."

[1298] 7. The server sends the generated response to the device.

[1299] Send content: "Answer and emotional response message"

[1300] 8. The terminal displays the received response to the user.

[1301] What it says: "To start a new project, click the 'New Project' button in your project management tool, enter the required information, and click 'Save.' If you have any questions, please don't hesitate to ask."

[1302] Example 2: Providing training materials

[1303] 1. The user inputs a request for training materials through the terminal.

[1304] For example: "How do I use a project management tool?"

[1305] 2. The device sends the request to the emotion engine.

[1306] Example: "Resource Request: 'How to use project management tools'"

[1307] 3. The emotion engine analyzes emotions based on the user request.

[1308] Example: "User sentiment: Interested"

[1309] 4. The device sends the emotion information to the server.

[1310] Send: "Emotion: 'Interested'"

[1311] 5. The server passes the request and emotion information to the generative AI model for analysis.

[1312] Analysis: "Basic functions of project management tools, how to set them up, task management, and team member management. Users are interested, so we've added relevant information."

[1313] 6. The generative AI model generates training materials taking into account emotional information.

[1314] Generated material: "How to use project management tools - basic functions, configuration, task management, team member management, and common troubleshooting tips"

[1315] 7. The server sends the generated materials to the terminal.

[1316] Send content: "Training materials"

[1317] 8. The terminal displays the received materials to the user.

[1318] What you'll see: "How to use a project management tool - basic features, configuration, task management, team member management, and common troubleshooting tips."

[1319] Example 3: Personalized support

[1320] 1. The user enters an individual support request via a terminal.

[1321] For example: "Can you tell me how things are going on with your latest project?"

[1322] 2. The device sends the request to the emotion engine.

[1323] Example: "Support Request: 'Latest Project Progress'"

[1324] 3. The emotion engine analyzes emotions based on the user's support request.

[1325] Example: "User Sentiment: Urgent"

[1326] 4. The device sends the emotion information to the server.

[1327] Sent: "Sentiment: 'urgent'"

[1328] 5. The server passes the request and emotion information to the generative AI model for analysis.

[1329] Analysis: "The latest project progress information. Urgent information is provided promptly."

[1330] 6. The generative AI model generates supporting information taking into account emotional information.

[1331] Generated information: "Our latest project is 70% complete. The next major milestone is 'specification finalization,' which is expected to be completed today."

[1332] 7. The server sends the generated support information to the terminal.

[1333] What to send: "Progress and emergency response messages"

[1334] 8. The device displays the support information it has received to the user.

[1335] It reads: "Our latest project is 70% complete. The next major milestone is 'Spec Finalization', which is expected to be completed today."

[1336] As described above, by combining a generative AI model and an emotion engine, the system of the present invention can provide efficient learning support that takes into account the emotional state of new employees and employees. This allows users to receive feedback and support that is appropriate for their emotions, resulting in more effective learning.

[1337] The processing flow will be explained below.

[1338] Program processing flow steps (when combined with emotion engine)

[1339] User question reception and emotion recognition

[1340] Step 1:

[1341] The user inputs a question through the terminal.

[1342] For example: "What are the steps to launching a new project?"

[1343] Step 2:

[1344] The terminal receives a question from the user.

[1345] The terminal sends the user's input to the emotion engine.

[1346] Step 3:

[1347] The emotion engine analyzes the user's input, as well as the speed, strength, and tone of voice (in the case of voice input), to recognize emotions.

[1348] Example: "User Sentiment: Anxiety"

[1349] Step 4:

[1350] The emotion engine returns the analysis results to the device.

[1351] The device transmits the emotion information to the server.

[1352] Considering emotions in question analysis and answer generation

[1353] Step 5:

[1354] The server receives the question and emotion information received from the terminal.

[1355] The server passes the question content and emotional information to the generative AI model for analysis.

[1356] Step 6:

[1357] Generative AI models take emotional information into account when generating appropriate answers to questions.

[1358] Example: "Provide a detailed and thorough explanation of the steps to launch a new project."

[1359] Step 7:

[1360] The server receives the answer from the generative AI model.

[1361] The server transmits the generated answer and emotion information to the terminal.

[1362] Providing answers

[1363] Step 8:

[1364] The terminal displays the answer and emotion information received from the server.

[1365] For example: "To start a new project, click the 'New Project' button in your project management tool, enter the required information, and click 'Save.' If you have any questions, please don't hesitate to ask."

[1366] Providing training materials

[1367] Step 1:

[1368] A user inputs a request for training materials through a terminal.

[1369] For example: "How do I use a project management tool?"

[1370] Step 2:

[1371] The device receives the request and sends it to the emotion engine.

[1372] The emotion engine analyzes the content, speed, strength and tone of the user's request.

[1373] Step 3:

[1374] The emotion engine returns the analysis results to the device.

[1375] The device transmits the emotion information to the server.

[1376] Step 4:

[1377] The server receives the request and emotion information and passes it to the generative AI model for analysis.

[1378] Step 5:

[1379] Generative AI models take emotional information into account when generating training materials.

[1380] Example: "Detailed documentation including basic project management tool features, setup, task management, and team member management."

[1381] Step 6:

[1382] The server receives the data from the generative AI model and sends it to the terminal.

[1383] Step 7:

[1384] The terminal displays materials and emotional information to the user.

[1385] Example: "How to use a project management tool - basic features, setup, task management, and team member management."

[1386] Personalized support

[1387] Step 1:

[1388] A user inputs an individual support request through a terminal.

[1389] For example: "Can you tell me how things are going on with your latest project?"

[1390] Step 2:

[1391] The device receives the request and sends it to the emotion engine.

[1392] The emotion engine analyzes the content, speed, strength and tone of the user's request.

[1393] Step 3:

[1394] The emotion engine returns the analysis results to the device.

[1395] The device transmits the emotion information to the server.

[1396] Step 4:

[1397] The server receives the request and emotion information, references the user's profile information, and passes it to the generative AI model for analysis.

[1398] Step 5:

[1399] The generative AI model takes emotional information into account when generating supporting information.

[1400] Example: "Detailed information on the progress of the latest project and next milestones."

[1401] Step 6:

[1402] The server receives support information from the generative AI model and sends it to the device.

[1403] Step 7:

[1404] The terminal displays support information and emotional information to the user.

[1405] Example: "We're 70% complete on our latest project. The next major milestone is 'Spec Finalization,' which is expected to be completed today."

[1406] Example 2

[1407] 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."

[1408] Current education, training, and support systems do not provide answers or support that take into account the user's emotional state, which can sometimes leave users feeling frustrated or anxious. To improve the learning efficiency of new employees and current employees in particular, it is important to recognize the user's emotions and provide appropriate answers and training materials according to their situation. However, conventional systems lack such functionality.

[1409] 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.

[1410] In this invention, the server includes a means for passing the user's question and emotional information to the generative AI model for analysis, a means for sending the generated answer to the terminal, and a means for adjusting the display method based on the emotional information. This makes it possible to improve the user's learning efficiency by recognizing the user's emotions and providing appropriate answers and training materials according to the situation.

[1411] "User" means a person who accesses the System and enters a question or request.

[1412] "Terminal" refers to a mechanical device through which a user inputs a question or request and transmits it to the system.

[1413] An "emotion engine" refers to a software component that analyzes a user's input and behavioral patterns when entering input to identify the user's emotional state.

[1414] "Emotion information" refers to data that indicates the user's emotional state extracted through analysis by the emotion engine.

[1415] "Server" refers to a central computer system that receives user queries and requests and performs any necessary analysis or data processing.

[1416] A "generative AI model" is an artificial intelligence algorithm used by the server that generates appropriate answers and materials in response to user questions and requests.

[1417] "Answer" refers to the explanation or description that a generative AI model provides in response to a user's question.

[1418] "Training Materials" refers to the educational materials created by the generative AI model based on the learning content requested by the User.

[1419] "Support information" refers to assistance information provided by the generative AI model in response to individual user requests.

[1420] "Adjusting the display method" refers to presenting information in an optimal format according to the user's emotional state based on emotional information.

[1421] This system recognizes a user's emotions and provides appropriate answers, training materials, and support information based on those emotions. The system consists of the following main components: the user, the device, the server, the generative AI model, and the emotion engine.

[1422] System Overview

[1423] 1. A terminal that provides an interface for users to enter questions or requests.

[1424] 2. The device receives the user's input, extracts emotional information through the emotion engine, and sends it to the server.

[1425] 3. The emotion engine analyzes the user's input and behavioral patterns when entering data to identify their emotional state.

[1426] 4. The server receives the user's questions, requests, and emotional information and analyzes them using a generative AI model.

[1427] 5. The generative AI model takes into account the question, request, and emotional information to generate appropriate answers, training materials, and support information.

[1428] 6. The device receives the information from the server and displays it in the most appropriate format for the user.

[1429] Hardware and Software Used

[1430] Device: A device such as a personal computer, tablet, or smartphone.

[1431] Emotion Engine: Software that includes a natural language processing (NLP) engine, a speech analysis system, and a typing analysis system.

[1432] Server: A high-performance computer or cloud computing platform.

[1433] Generative AI models: Deep learning models (e.g., large-scale generative models such as GPT-3).

[1434] Specific operation example

[1435] Example 1: Answering basic questions

[1436] 1. A user types the question "How do I start a new project?" into a terminal.

[1437] 2. The device sends a question to the emotion engine and identifies the user's emotion as "anxiety."

[1438] 3. The device sends the question, including the emotion information, to the server.

[1439] 4. The server passes the question and emotion information to the generative AI model, which generates an answer. For example, it might generate an answer like, "To start a new project, click the 'New Project' button in the project management tool, enter the required information, and click 'Save'. If you have any questions, please feel free to ask."

[1440] 5. The device receives the answer and displays it to the user.

[1441] Example 2: Providing training materials

[1442] 1. The user enters a request through the terminal: "Please teach me how to use the project management tool."

[1443] 2. The device sends a request to the emotion engine and identifies the user's emotion as "interest."

[1444] 3. The device sends a request including emotion information to the server.

[1445] 4. The server passes the request and sentiment information to the generative AI model to generate training materials, such as "How to use a project management tool - basic functions, configuration, task management, team member management, and common troubleshooting tips."

[1446] 5. The device receives the training materials and displays them to the user.

[1447] Example 3: Personalized support

[1448] 1. The user inputs a request through the terminal: "Please let me know the progress of the latest project."

[1449] 2. The device sends a request to the emotion engine and identifies the user's emotion as "urgent."

[1450] 3. The device sends a request including emotion information to the server.

[1451] 4. The server passes the request and emotion information to the generative AI model, which generates information about the latest progress. For example, it generates information like, "The latest project is 70% complete. The next major milestone is 'specification finalization,' which is expected to be completed today."

[1452] 5. The device receives the support information and displays it to the user.

[1453] This will provide answers and materials that take the user's emotions into consideration, which is expected to improve learning efficiency.

[1454] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1455] Step 1:

[1456] The user enters a question

[1457] Specific action: The user inputs a question into the input interface of the device, for example, "How do I start a new project?"

[1458] Input: The text data of the question entered by the user.

[1459] Output: The terminal obtains the user's question text data.

[1460] Step 2:

[1461] The device sends the user's question to the emotion engine.

[1462] Specific operation: The device sends the user's input data to the emotion engine, which receives data such as the user's input content, input speed, typing strength, and voice tone (in the case of voice input).

[1463] Input: Text data of the question entered by the user and behavioral data when entering the question.

[1464] Output: The emotion engine receives the input data.

[1465] Step 3:

[1466] Emotion engine analyzes user emotions

[1467] Specific operation: The emotion engine analyzes text data and behavioral data to identify the user's emotions. For example, it determines that the user is feeling "anxiety" based on the input content.

[1468] Input: Textual and behavioral data received by the emotion engine.

[1469] Output: Emotional information including the user's emotional state (e.g., anxiety, interest, urgency).

[1470] Step 4:

[1471] The device sends emotional information to the server.

[1472] Specific operation: The device sends the generated emotion information to the server along with the user's question text.

[1473] Input: User question text data and sentiment information.

[1474] Output: The server receives the question text and sentiment information.

[1475] Step 5:

[1476] The server passes the question and emotion information to the generative AI model

[1477] Specific operation: The server inputs the received question text and emotion information into the generative AI model, which then generates an appropriate answer based on this.

[1478] Input: Question text data and sentiment information received by the server.

[1479] Output: The generative AI model begins its analysis.

[1480] Step 6:

[1481] Generative AI models generate appropriate answers to questions

[1482] Specific operation: The generative AI model analyzes the question text data and emotional information, and generates an appropriate answer taking into account the user's emotional state. For example, if the user is feeling "anxious," the answer will be more detailed.

[1483] Input: Question text data and sentiment information.

[1484] Output: Emotion-sensitive answer text data.

[1485] Step 7:

[1486] The server generates a response and sends it to the device.

[1487] Specific operation: The server receives the answer text data generated from the generative AI model and sends it to the terminal.

[1488] Input: Generated answer text data.

[1489] Output: The terminal receives the response text data.

[1490] Step 8:

[1491] The device displays the answers to the user and adjusts the display based on the user's emotional information.

[1492] Specific operation: The device displays the received answer text to the user. At the same time, the display method is adjusted based on the user's emotional information. For example, if the user is feeling "anxious," a calm and encouraging message is added.

[1493] Input: Answer text data and sentiment information.

[1494] Output: A display tailored to the user.

[1495] (Application example 2)

[1496] 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."

[1497] Conventional onboarding and training systems provide uniform responses to user questions and requests, making it difficult to respond flexibly to the user's emotions and circumstances. In particular, new employees and employees who are unfamiliar with new environments and work procedures often lack support that adequately alleviates their anxiety and confusion. Due to the lack of individualized responses that take emotions into consideration, there is a need to improve learning and work efficiency.

[1498] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for analyzing the question and emotion information using a generative AI model, means for the generative AI model to generate an appropriate answer to the question taking the emotion information into consideration, and means for the emotion engine to analyze the user's emotion. This enables flexible responses that take the user's emotions into consideration.

[1499] A "user" is an entity that operates the system and enters questions and requests.

[1500] A "terminal" is a device that receives questions or requests entered by a user and transmits them to a server.

[1501] The "emotion engine" is a function that analyzes the user's input data (text, voice, input speed, etc.) and generates emotional information.

[1502] The "server" is a central device that analyzes questions, requests, and emotional information received from users and transmits the results to terminals.

[1503] A "generative AI model" is an artificial intelligence technology that generates appropriate answers and materials based on input questions or requests.

[1504] The present invention relates to a training support system that uses an application installed on a factory robot to improve employee learning efficiency. The system includes a user, a terminal, a server, a generative AI model, and an emotion engine.

[1505] The overall flow of the system is as follows: The user inputs a question or request via their device, which then sends it to the emotion engine. The emotion engine analyzes the user's input data and generates emotional information. The device then sends the input data along with the emotional information to the server. The server passes the input data and emotional information to the generative AI model for analysis, and sends the generated answer or materials back to the device. The device then finally displays or plays the answer or materials to the user.

[1506] This section explains the specific hardware and software. The hardware uses factory robots, voice input devices, display panels, and speakers. The software uses the Emotion Engine (emotion recognition engine) and AI Response Generator (generative AI model). The server is the central device that handles overall data exchange and analysis, and can also utilize edge computing and cloud services.

[1507] For example, let's consider a specific example where a worker asks a question about how to operate a new machine. When the user inputs a question into the device (voice input is also possible), such as "Please tell me how to operate this new press machine," the device sends that information to the emotion engine. The emotion engine analyzes the content, speed, and tone of voice of the input, and determines the user's emotion as "interest." The device then sends this as data to the server, and the server uses a generative AI model to generate an appropriate answer that takes the emotional information into consideration. As a specific example, the answer generated might be, "To operate this new press machine, first turn it on, then press the start button on the control panel. After that, adjust the settings and begin work. A detailed manual is also available, so please let us know if you need one."

[1508] As an example of a prompt, the following text is fed into the generative AI model:

[1509] Question: 'How do I operate the new press?'

[1510] Emotion: 'Interest'

[1511] This system is expected to improve the quality of work instruction and respond flexibly to the user's emotions. This application example is particularly effective in helping new and inexperienced employees to work with peace of mind.

[1512] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1513] Step 1:

[1514] A user inputs a question or request via a terminal. The input method can be text input or voice input. For example, if a user inputs a question such as "Please tell me how to operate the new press machine," the input contains the user's emotions and intentions.

[1515] Step 2:

[1516] The device receives a question from the user and sends it to the emotion engine. The input data includes text information and voice data, and the data is sent to the emotion engine for analysis.

[1517] Step 3:

[1518] The emotion engine analyzes emotions based on the user's input data. In this step, the content of the text, input speed, and tone of voice are analyzed to generate the user's emotion information (e.g., interest, anxiety, urgency, etc.). For example, in the case of voice input, "interest" is generated as emotion information by analyzing the tone of voice.

[1519] Step 4:

[1520] The device sends the emotion information received from the emotion engine to the server. This sent data includes the original question and emotion information. For example, data such as "Question: Please tell me how to operate the new press machine" and "Emotion information: Interest" is sent.

[1521] Step 5:

[1522] The server passes the question content and emotional information to the generative AI model for analysis. Based on the input question content and emotional information, data processing and analysis are performed to generate the most appropriate answer. The generative AI model analyzes the question and generates an answer that takes the emotional information into account.

[1523] Step 6:

[1524] The generative AI model takes emotional information into account to generate appropriate answers. The output answers are tailored to the user's emotions. For example, a detailed and engaging answer is generated for the "interest" emotion. Specifically, the model might generate an answer such as, "To operate a new press, first turn it on, then press the start button on the control panel. After that, adjust the settings and begin operation. A detailed manual is also available, so please let us know if you need one."

[1525] Step 7:

[1526] The server transmits the generated answer to the terminal. In this step, the generated answer includes an emotion-responsive message, and the answer is transmitted in an appropriate format based on the user's emotion.

[1527] Step 8:

[1528] The device displays or plays back the received answer and emotion-responsive message to the user. Depending on the user's emotion, an appropriate answer is provided in the form of a text display or audio playback. For example, if the emotion is "interested," detailed instructions are displayed on the screen and audio guidance is played. In this way, flexible responses and support that take the user's emotions into consideration are possible.

[1529] 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.

[1530] 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.

[1531] 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.

[1532] [Fourth embodiment]

[1533] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1534] 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.

[1535] 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).

[1536] 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.

[1537] 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.

[1538] 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).

[1539] 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.

[1540] 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.

[1541] 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.

[1542] 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.

[1543] 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.

[1544] 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.

[1545] 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."

[1546] This invention is an onboarding and training support system that utilizes a generative AI model to improve the learning efficiency of new employees and employees. The main components of this system include a user, a terminal, a server, and a generative AI model.

[1547] Program processing overview

[1548] 1. Accepting user questions

[1549] A user inputs a specific question into the system via a terminal, for example, "Please tell me the procedure for starting a new project."

[1550] The terminal receives a question from the user and transmits the content of the question to the server.

[1551] 2. Question Analysis and Answer Generation

[1552] The server processes the questions received from the device and passes the received questions to the generative AI model for analysis.

[1553] The generative AI model analyzes the questions and generates appropriate answers to the user's questions, such as explaining how to use project management tools to launch a new project.

[1554] 3. Providing answers

[1555] The server receives the answer generated by the generative AI model and sends the answer to the device.

[1556] The terminal displays the answer received from the server to the user.

[1557] Specific examples

[1558] Example 1: Answering basic questions

[1559] 1. The user enters a question through the terminal.

[1560] For example: "How do you launch a new project?"

[1561] 2. The device sends a question to the server.

[1562] Submitted: "Question: 'How do you launch a new project?'"

[1563] 3. The server passes the received question to the generative AI model for analysis.

[1564] Analysis: "Check the steps for your new project..."

[1565] 4. The generative AI model generates appropriate answers to the questions.

[1566] Generated answer: "To start a new project, go to your project management tool, click the 'New Project' button, enter the required information, and click 'Save'."

[1567] 5. The server sends the generated response to the device.

[1568] What you sent: "Answer: 'To start a new project, go to your project management tool, click the 'New Project' button, enter the required information, and click 'Save.'"

[1569] 6. The terminal displays the received response to the user.

[1570] What it says: "To start a new project, go to your project management tool, click the 'New Project' button, enter the required information, and click 'Save'."

[1571] Example 2: Providing training materials

[1572] 1. The user inputs a request for training materials through the terminal.

[1573] For example: "How do I use a project management tool?"

[1574] 2. The device sends a request to the server.

[1575] Submission: "Request for Resources: 'How to Use Project Management Tools'"

[1576] 3. The server passes the received request to the generative AI model to generate training materials.

[1577] Generated content: "Basic functions of project management tools, how to set them up, task management, and team member management"

[1578] 4. The generative AI model generates appropriate training materials.

[1579] Generated material: "How to use project management tools - basic functions, configuration, task management, and team member management"

[1580] 5. The server sends the generated materials to the terminal.

[1581] Submission: "Document: 'How to use a project management tool - basic features, setup, task management, and team member management'"

[1582] 6. The terminal displays the received materials to the user.

[1583] Display content: "How to use project management tools - basic features, settings, task management, and team member management"

[1584] Example 3: Personalized support

[1585] 1. The user enters an individual support request via a terminal.

[1586] For example: "Can you tell me how things are going on with your latest project?"

[1587] 2. The device sends a request to the server.

[1588] Submitted: "Support Request: 'Latest Project Progress'"

[1589] 3. The server references the user's profile information and generates support information using a generative AI model.

[1590] Analysis: "Checking progress..."

[1591] 4. The generative AI model generates optimal support information based on the user's profile information and request content.

[1592] Generated information: "We're 70% complete on our latest project. The next major milestone is 'Spec Finalization,' due this Friday."

[1593] 5. The server sends the generated support information to the terminal.

[1594] What you sent: "Status: 'We're 70% done on our latest project. The next major milestone is 'Spec Finalized,' due this Friday.'"

[1595] 6. The device displays the support information it has received to the user.

[1596] It says: "Your latest project is 70% complete. The next major milestone is 'Spec Finalized', due this Friday."

[1597] As described above, the system of the present invention uses a generative AI model to provide efficient learning support tailored to the individual needs of new employees and employees, thereby shortening the adaptation period for new employees and enabling them to contribute to work more quickly.

[1598] The processing flow will be explained below.

[1599] Program processing flow steps

[1600] Accepting user questions

[1601] Step 1:

[1602] The user inputs a question through the terminal. For example, "Please tell me the procedure for starting a new project."

[1603] Step 2:

[1604] The terminal receives a question from the user.

[1605] Create a request to send the question received by the device to the server. For example, generate a request like "Question: 'Please tell me the steps to start a new project.'"

[1606] Question analysis and answer generation

[1607] Step 3:

[1608] The server receives a question request from the terminal.

[1609] The server passes the question to the generative AI model for analysis. For example, let's analyze the question "Question to be analyzed: 'Please tell me the steps to launch a new project.'"

[1610] Step 4:

[1611] A generative AI model receives a question and uses its internal database and pre-trained models to generate an appropriate answer, for example, by going through a process such as "matching against existing database to find an appropriate answer..."

[1612] Step 5:

[1613] The server receives the answer from the generative AI model.

[1614] The server creates a response to send the generated answer to the terminal. For example, it generates the response "Answer: 'To start a new project, click the 'New Project' button in the project management tool, enter the required information, and click 'Save'."

[1615] Providing answers

[1616] Step 6:

[1617] The terminal receives the response received from the server.

[1618] The terminal displays the received response to the user. For example, the response displayed to the user might be, "To start a new project, click the 'New Project' button in the project management tool, enter the required information, and click 'Save'."

[1619] Providing training materials

[1620] Step 1:

[1621] A user inputs a request for training materials through a terminal. For example, the user inputs "Teach me how to use a project management tool."

[1622] Step 2:

[1623] The terminal receives the request and creates a request to send to the server. For example, it creates a request called "Document Request: 'How to use project management tools'".

[1624] Step 3:

[1625] The server receives the request from the terminal.

[1626] The server passes the request to the AI ​​model to generate training materials. For example, let's generate materials about the basic functions, configuration, task management, and team member management of a project management tool.

[1627] Step 4:

[1628] A generative AI model receives the request and generates the appropriate training materials, for example, "Generating how-to documentation for a project management tool..."

[1629] Step 5:

[1630] The server receives the data from the generative AI model.

[1631] The server creates a response to send the generated materials to the terminal. For example, it creates a response such as "Training Materials: 'How to use project management tools - basic functions, configuration, task management, and team member management'".

[1632] Step 6:

[1633] The terminal receives the response received from the server.

[1634] The terminal displays the received materials to the user. For example, the material "How to use project management tools - basic functions, settings, task management, and team member management" is displayed to the user.

[1635] Personalized support

[1636] Step 1:

[1637] A user enters a specific support request through a terminal. For example, the user might enter, "Please let me know the progress on my latest project."

[1638] Step 2:

[1639] The device receives the request and creates a request to send to the server. For example, it creates a request called "Support request: 'Latest project progress'".

[1640] Step 3:

[1641] The server receives the request from the terminal.

[1642] The server references the user's profile information and generates support information using a generative AI model. For example, it goes through a process called "Checking progress..."

[1643] Step 4:

[1644] The generative AI model analyzes the user's profile information and request content to generate appropriate support information. For example, it goes through the process of "Generating the latest project progress information..."

[1645] Step 5:

[1646] The server receives support information from the generative AI model.

[1647] The server creates a response to send the generated support information to the terminal. For example, it generates a response such as "Progress: 'The progress rate of the latest project is 70%. The next milestone is 'Spec Finalization', and the deadline is this Friday.'"

[1648] Step 6:

[1649] The terminal receives the response received from the server.

[1650] The terminal displays the received support information to the user. For example, the following support information is displayed to the user: "The progress rate of the latest project is 70%. The next milestone is 'specification finalization', and the deadline is this Friday."

[1651] Example 1

[1652] 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."

[1653] Appropriate onboarding and training are necessary for new and current employees to quickly adapt to their work and learn efficiently. However, traditional systems rely mainly on manuals and documents for learning, making it difficult to meet individual needs. Another issue is that providing individual support and training is time-consuming and costly. Furthermore, the fact that a lot of information is scattered and difficult to access hinders efficient learning.

[1654] 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.

[1655] In this invention, the server includes a means for a user to input a question, a means for a terminal to receive the question from the user and transmit it to the server via a network, a means for the server to receive the question and analyze the question using a generative AI model, a means for the generative AI model to generate an appropriate answer to the question, a means for the server to transmit the generated answer to the terminal, and a means for the terminal to display the answer to the user, thereby enabling users to quickly and efficiently obtain individually customized information and training materials.

[1656] A "user" is an individual or organization that enters a question or request into the system and receives information or support.

[1657] A "terminal" is a device that allows a user to input a question or request and transmit that input to a server, and includes a computer, a smartphone, etc.

[1658] A "server" is a centralized computing system that receives questions and requests from users, processes them, generates answers and materials, and sends them to terminals.

[1659] A "generative AI model" is artificial intelligence-based software that analyzes user questions and requests and generates appropriate answers and materials.

[1660] A "question" is a textual content that a user enters into the system seeking specific information.

[1661] An "answer" is information generated by the generative AI model based on the user's question and sent to the device via the server.

[1662] "Training materials" are learning documents and presentation materials provided to users and generated by a generative AI model.

[1663] "Support information" refers to information and advice for obtaining specific support that is generated based on a user's individual request.

[1664] "Profile information" refers to a user's individual information and history that is used by the server to generate support information in response to the user's specific requests.

[1665] This invention is an onboarding and training support system that utilizes a generative AI model to improve the learning efficiency of new employees and employees. This system includes elements such as a user, a terminal, a server, and a generative AI model. This enables efficient learning support tailored to the individual needs of each employee.

[1666] In this system, a user first inputs a question or request via a terminal. For example, if a user wants to know the procedure for launching a new project, they input the question, "Please tell me the procedure for launching a new project." This input is sent to the terminal, which then transmits it to the server. The server receives the question and forwards it to the generative AI model for analysis.

[1667] The generative AI model analyzes the question in natural language and generates an appropriate answer. For example, it generates an answer such as, "To start a new project, access the project management tool, click the 'New Project' button, enter the required information, and click 'Save.'" The server sends the generated answer to the device, which then displays it to the user.

[1668] Next, when a user requests training materials, they input a materials request such as "Please teach me how to use a project management tool." This request is also sent from the device to the server, and the server generates appropriate materials using the generative AI model. Materials such as "How to use a project management tool - basic functions, settings, task management, and team member management" are generated and similarly displayed to the user via the device.

[1669] Additionally, when a user enters an individual support request, the request is "Please tell me about the progress of the latest project." The server references the user's profile information and generates support information using a generative AI model. Support information such as "The latest project is 70% complete. The next major milestone is 'specification finalization,' with a deadline of this Friday," is generated and displayed to the user via their device.

[1670] This system allows users to efficiently obtain information and training materials that are fast and personalized.

[1671] Specific examples

[1672] Example questions

[1673] "How do you launch a new project?"

[1674] Training Material Request Example

[1675] "How do I use a project management tool?"

[1676] Example of a personalized support request

[1677] Please let me know the progress on your latest project.

[1678] Using this system will shorten the adaptation period for new employees and employees, allowing them to contribute to work more quickly.

[1679] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1680] Step 1:

[1681] The user inputs a question via a terminal.

[1682] Specifically, the user enters a question such as "Please tell me the steps to start a new project" into the terminal interface (e.g., a text box) and clicks the send button.

[1683] Input: The user's question text.

[1684] Output: The question text stored in the device's temporary memory.

[1685] Step 2:

[1686] The terminal receives a question from the user and sends it to the server via the network.

[1687] Specifically, the terminal sends the question text to the server as an HTTP request.

[1688] Input: The question text stored in the device's temporary memory.

[1689] Output: The HTTP request sent to the server.

[1690] Step 3:

[1691] The server receives questions from the device and passes them to the generative AI model for analysis.

[1692] Specifically, the server extracts the question text from the payload of the HTTP request and sends the question text as a prompt to the generation AI model API.

[1693] Input: The question text of the HTTP request that arrives at the server.

[1694] Output: The prompt sent to the generative AI model.

[1695] Step 4:

[1696] The generative AI model analyzes the question and generates an appropriate answer.

[1697] Specifically, the generative AI model performs natural language processing to generate a text answer to a question. The generation part involves specific data analysis and model calculations.

[1698] Input: The prompt sentence passed to the generative AI model.

[1699] Output: The answer text provided by the generative AI model.

[1700] Step 5:

[1701] The server receives the answer generated by the generative AI model and sends it to the device.

[1702] Specifically, the server receives the answer from the generative AI model and returns it to the device as an HTTP response.

[1703] Input: Answer text from the generative AI model.

[1704] Output: The HTTP response sent to the device.

[1705] Step 6:

[1706] The terminal displays the answer received from the server to the user.

[1707] Specifically, the terminal extracts the response text from the payload of the HTTP response and displays it on the user's interface.

[1708] Input: The HTTP response received from the server.

[1709] Output: The answer text displayed to the user.

[1710] The above is the flow of processing by which the program of this system responds to user questions.

[1711] (Application example 1)

[1712] 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."

[1713] Training for the operation and maintenance of factory robots involves frequent updates and diverse operating procedures, making it difficult for new employees and current employees to learn. Furthermore, one-on-one training requires significant time and resources, making it difficult to provide uniform training to all employees. Therefore, there is a need for effective educational methods to support efficient operation and rapid troubleshooting of factory robots.

[1714] 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.

[1715] In this invention, the server includes a means for generating training materials related to factory work, a means for an AI to refer to the user's past operation history and generate individually customized support information, and a means for receiving the user's questions, analyzing them with the generative AI model, and generating appropriate answers. This allows users to learn how to operate and troubleshoot factory robots in real time, enabling efficient training and support.

[1716] A "user" is an individual person who uses the system.

[1717] A "means for inputting a question" is an interface through which a user can provide a question to the system in text or voice.

[1718] A "terminal" is a hardware device through which a user can input questions or requests and receive the results.

[1719] The "server" is a central computer system that receives questions or requests from users, sends them to the generative AI model, and sends the results back to the user.

[1720] A "generative AI model" is an artificial intelligence technology that analyzes questions and requests from users and generates appropriate answers and training materials.

[1721] "Training materials" are educational materials on the operation and maintenance of factory robots, generated by a generative AI model.

[1722] "Support information" is individually customized advice and assistance information that is generated based on the user's past operation history and profile information.

[1723] The "means for generating training materials for factory work" is a function that uses a generative AI model to automatically generate information necessary for operating and maintaining factory robots.

[1724] "Means for referencing operation history" refers to a function that allows a user to check the records of past operations and have the generative AI model generate information based on those records.

[1725] The "means for generating customized support information" is a function that generates optimal support information in real time based on the user's operation history and profile information.

[1726] The "means of generating an answer" is the function that enables the generative AI model to provide appropriate information based on a question from a user.

[1727] This invention is a system that supports training on the operation and maintenance of factory robots. This system provides a terminal interface for users to input questions and uses a generative AI model to provide appropriate answers and training materials. Specifically, the system uses the following hardware and software:

[1728] Hardware and software used

[1729] Hardware:

[1730] Smartphone (iOS / Android)

[1731] Smart Glasses

[1732] software:

[1733] Frontend: React Native (Mobile Application)

[1734] Backend: Node.js, Express

[1735] Database: MongoDB

[1736] AI model: OpenAI GPT-4

[1737] Natural Language Processing (NLP) technology: Used to generate training materials and support information

[1738] Overall system flow

[1739] 1. User questions:

[1740] Users input questions or requests through a smartphone or smart glasses app, such as "How do I calibrate the robot's sensors?"

[1741] 2. Submit your question:

[1742] The questions entered by the user are sent to the server through the terminal, and the technology used here uses React Native as the front end, with a back end built with Node.js and Express receiving the questions.

[1743] 3. Question analysis and answer generation:

[1744] The server sends the received question to a generative AI model (OpenAI GPT-4), which analyzes the question. The generative AI model uses natural language processing technology to generate an appropriate answer to the question.

[1745] 4. Providing answers:

[1746] The generated answer is sent to the device via the server, and the device's app displays the answer to the user.

[1747] Specific examples

[1748] A user uses a smartphone or smart glasses to input a question as follows:

[1749] User Question: "Please explain in detail the maintenance procedures for the robot."

[1750] Prompt Input: "What is the maintenance procedure for the robot?"

[1751] AI model response: "The robot maintenance procedure is as follows... (detailed instructions)"

[1752] Answer: "The robot maintenance procedure is as follows. First... (show detailed procedure)"

[1753] Also, when a user requests training materials, the flow is as follows:

[1754] User Request: "Please provide training materials on basic operation of factory robots."

[1755] Prompt Input: "Generate training materials on basic operation of factory robots."

[1756] AI model response: "The training materials for basic operation of factory robots include the following... (detailed material content)"

[1757] Display material: "The training material for basic operation of factory robots is as follows... (Display detailed material)"

[1758] In this way, the present invention provides a system that allows users to easily acquire knowledge about the operation and maintenance of factory robots. The system utilizes a generative AI model to quickly generate and display appropriate answers and training materials to users. This improves training efficiency and enables new employees and employees to quickly master their work.

[1759] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1760] Step 1:

[1761] Users input questions or requests through a smartphone or smart glasses app. For example, the input can be a specific question such as, "How do I calibrate the robot's sensors?"

[1762] Step 2:

[1763] The device sends the question received from the user to the server. The entered question data is sent from the device to the server. For example, a question is sent from a mobile app using React Native to a server built with Node.js and Express.

[1764] Step 3:

[1765] The server sends the received question to the generative AI model and requests analysis. The input here is the question data sent in step 2, and the output is a query to the generative AI model. The server uses natural language processing technology to convert the received question into an appropriate format and sends an analysis request to the AI ​​model (GPT-4).

[1766] Step 4:

[1767] The generative AI model analyzes the question and generates an appropriate answer. The AI ​​model analyzes the prompt received from the server and generates a corresponding answer. For example, if the prompt is "How do I calibrate the robot's sensors?", the AI ​​model generates specific calibration procedures.

[1768] Step 5:

[1769] The server processes the answer received from the generative AI model and sends it to the device. The input here is the answer output from the generative AI model, and the output is sending the answer data to the device. The server receives the answer data, reformats it, and sends it back to the device.

[1770] Step 6:

[1771] The device displays the received answers to the user. The input is the answer data sent from the server, and the output is what is displayed to the user. The device app has the function of displaying the answers in an easy-to-understand manner using React Native. For example, the user can see specific steps such as "To calibrate the robot's sensors, follow the steps below..."

[1772] Through this series of processing steps, users can receive real-time answers to questions about factory robot operation and maintenance procedures, thereby improving factory work efficiency and reducing errors.

[1773] 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.

[1774] This invention combines an onboarding and training support system that utilizes a generative AI model to improve the learning efficiency of new employees and employees with an emotion engine that recognizes user emotions. The main components of this system include a user, a terminal, a server, a generative AI model, and an emotion engine.

[1775] Program processing overview

[1776] 1. User question acceptance and emotion recognition

[1777] A user inputs a specific question into the system via a terminal, for example, "Please tell me the procedure for starting a new project."

[1778] The terminal receives a question from the user and sends the input information to the emotion engine.

[1779] The emotion engine analyzes emotions based on the user's input content, input speed, typing strength, and tone of voice (in the case of voice input), and generates emotional information.

[1780] 2. Considering emotions in question analysis and answer generation

[1781] The terminal transmits the emotion information received from the emotion engine to the server.

[1782] The server passes the question content and emotional information to the generative AI model for analysis, which then takes this emotional information into account to generate an appropriate answer.

[1783] For example, if the question expresses anxiety or confusion, the generated answers will be enhanced to be more detailed and easier to understand.

[1784] 3. Providing answers

[1785] The server receives the answer generated by the generative AI model and sends it to the device along with emotional information.

[1786] The device displays the answer and emotional information received from the server to the user, and adjusts the display method based on the emotional information (for example, if the user shows anxiety, it displays calm and encouraging words).

[1787] Specific examples

[1788] Example 1: Answering basic questions

[1789] 1. The user enters a question through the terminal.

[1790] For example: "How do you launch a new project?"

[1791] 2. The device sends the question to the emotion engine.

[1792] For example: "Question: 'How do you launch a new project?'"

[1793] 3. The emotion engine analyzes emotions based on the user's question.

[1794] Example: "User Sentiment: Anxiety"

[1795] 4. The device sends the emotion information to the server.

[1796] Sent: "Emotion: 'Anxiety'"

[1797] 5. The server passes the question and emotion information to the generative AI model for analysis.

[1798] Analysis: "Procedures for launching a new project. Detailed and thorough, as users are expressing anxiety."

[1799] 6. The generative AI model generates answers taking into account emotional information.

[1800] Generated answer: "To start a new project, click the 'New Project' button in the project management tool, enter the required information, and click 'Save'. If you have any questions, please feel free to ask."

[1801] 7. The server sends the generated response to the device.

[1802] Send content: "Answer and emotional response message"

[1803] 8. The terminal displays the received response to the user.

[1804] What it says: "To start a new project, click the 'New Project' button in your project management tool, enter the required information, and click 'Save.' If you have any questions, please don't hesitate to ask."

[1805] Example 2: Providing training materials

[1806] 1. The user inputs a request for training materials through the terminal.

[1807] For example: "How do I use a project management tool?"

[1808] 2. The device sends the request to the emotion engine.

[1809] Example: "Resource Request: 'How to use project management tools'"

[1810] 3. The emotion engine analyzes emotions based on the user request.

[1811] Example: "User sentiment: Interested"

[1812] 4. The device sends the emotion information to the server.

[1813] Send: "Emotion: 'Interested'"

[1814] 5. The server passes the request and emotion information to the generative AI model for analysis.

[1815] Analysis: "Basic functions of project management tools, how to set them up, task management, and team member management. Users are interested, so we've added relevant information."

[1816] 6. The generative AI model generates training materials taking into account emotional information.

[1817] Generated material: "How to use project management tools - basic functions, configuration, task management, team member management, and common troubleshooting tips"

[1818] 7. The server sends the generated materials to the terminal.

[1819] Send content: "Training materials"

[1820] 8. The terminal displays the received materials to the user.

[1821] What you'll see: "How to use a project management tool - basic features, configuration, task management, team member management, and common troubleshooting tips."

[1822] Example 3: Personalized support

[1823] 1. The user enters an individual support request via a terminal.

[1824] For example: "Can you tell me how things are going on with your latest project?"

[1825] 2. The device sends the request to the emotion engine.

[1826] Example: "Support Request: 'Latest Project Progress'"

[1827] 3. The emotion engine analyzes emotions based on the user's support request.

[1828] Example: "User Sentiment: Urgent"

[1829] 4. The device sends the emotion information to the server.

[1830] Sent: "Sentiment: 'urgent'"

[1831] 5. The server passes the request and emotion information to the generative AI model for analysis.

[1832] Analysis: "The latest project progress information. Urgent information is provided promptly."

[1833] 6. The generative AI model generates supporting information taking into account emotional information.

[1834] Generated information: "Our latest project is 70% complete. The next major milestone is 'specification finalization,' which is expected to be completed today."

[1835] 7. The server sends the generated support information to the terminal.

[1836] What to send: "Progress and emergency response messages"

[1837] 8. The device displays the support information it has received to the user.

[1838] It reads: "Our latest project is 70% complete. The next major milestone is 'Spec Finalization', which is expected to be completed today."

[1839] As described above, by combining a generative AI model and an emotion engine, the system of the present invention can provide efficient learning support that takes into account the emotional state of new employees and employees. This allows users to receive feedback and support that is appropriate for their emotions, resulting in more effective learning.

[1840] The processing flow will be explained below.

[1841] Program processing flow steps (when combined with emotion engine)

[1842] User question reception and emotion recognition

[1843] Step 1:

[1844] The user inputs a question through the terminal.

[1845] For example: "What are the steps to launching a new project?"

[1846] Step 2:

[1847] The terminal receives a question from the user.

[1848] The terminal sends the user's input to the emotion engine.

[1849] Step 3:

[1850] The emotion engine analyzes the user's input, as well as the speed, strength, and tone of voice (in the case of voice input), to recognize emotions.

[1851] Example: "User Sentiment: Anxiety"

[1852] Step 4:

[1853] The emotion engine returns the analysis results to the device.

[1854] The device transmits the emotion information to the server.

[1855] Considering emotions in question analysis and answer generation

[1856] Step 5:

[1857] The server receives the question and emotion information received from the terminal.

[1858] The server passes the question content and emotional information to the generative AI model for analysis.

[1859] Step 6:

[1860] Generative AI models take emotional information into account when generating appropriate answers to questions.

[1861] Example: "Provide a detailed and thorough explanation of the steps to launch a new project."

[1862] Step 7:

[1863] The server receives the answer from the generative AI model.

[1864] The server transmits the generated answer and emotion information to the terminal.

[1865] Providing answers

[1866] Step 8:

[1867] The terminal displays the answer and emotion information received from the server.

[1868] For example: "To start a new project, click the 'New Project' button in your project management tool, enter the required information, and click 'Save.' If you have any questions, please don't hesitate to ask."

[1869] Providing training materials

[1870] Step 1:

[1871] A user inputs a request for training materials through a terminal.

[1872] For example: "How do I use a project management tool?"

[1873] Step 2:

[1874] The device receives the request and sends it to the emotion engine.

[1875] The emotion engine analyzes the content, speed, strength and tone of the user's request.

[1876] Step 3:

[1877] The emotion engine returns the analysis results to the device.

[1878] The device transmits the emotion information to the server.

[1879] Step 4:

[1880] The server receives the request and emotion information and passes it to the generative AI model for analysis.

[1881] Step 5:

[1882] Generative AI models take emotional information into account when generating training materials.

[1883] Example: "Detailed documentation including basic project management tool features, setup, task management, and team member management."

[1884] Step 6:

[1885] The server receives the data from the generative AI model and sends it to the terminal.

[1886] Step 7:

[1887] The terminal displays materials and emotional information to the user.

[1888] Example: "How to use a project management tool - basic features, setup, task management, and team member management."

[1889] Personalized support

[1890] Step 1:

[1891] A user inputs an individual support request through a terminal.

[1892] For example: "Can you tell me how things are going on with your latest project?"

[1893] Step 2:

[1894] The device receives the request and sends it to the emotion engine.

[1895] The emotion engine analyzes the content, speed, strength and tone of the user's request.

[1896] Step 3:

[1897] The emotion engine returns the analysis results to the device.

[1898] The device transmits the emotion information to the server.

[1899] Step 4:

[1900] The server receives the request and emotion information, references the user's profile information, and passes it to the generative AI model for analysis.

[1901] Step 5:

[1902] The generative AI model takes emotional information into account when generating supporting information.

[1903] Example: "Detailed information on the progress of the latest project and next milestones."

[1904] Step 6:

[1905] The server receives support information from the generative AI model and sends it to the device.

[1906] Step 7:

[1907] The terminal displays support information and emotional information to the user.

[1908] Example: "We're 70% complete on our latest project. The next major milestone is 'Spec Finalization,' which is expected to be completed today."

[1909] Example 2

[1910] 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."

[1911] Current education, training, and support systems do not provide answers or support that take into account the user's emotional state, which can sometimes leave users feeling frustrated or anxious. To improve the learning efficiency of new employees and current employees in particular, it is important to recognize the user's emotions and provide appropriate answers and training materials according to their situation. However, conventional systems lack such functionality.

[1912] 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.

[1913] In this invention, the server includes a means for passing the user's question and emotional information to the generative AI model for analysis, a means for sending the generated answer to the terminal, and a means for adjusting the display method based on the emotional information. This makes it possible to improve the user's learning efficiency by recognizing the user's emotions and providing appropriate answers and training materials according to the situation.

[1914] "User" means a person who accesses the System and enters a question or request.

[1915] "Terminal" refers to a mechanical device through which a user inputs a question or request and transmits it to the system.

[1916] An "emotion engine" refers to a software component that analyzes a user's input and behavioral patterns when entering input to identify the user's emotional state.

[1917] "Emotion information" refers to data that indicates the user's emotional state extracted through analysis by the emotion engine.

[1918] "Server" refers to a central computer system that receives user queries and requests and performs any necessary analysis or data processing.

[1919] A "generative AI model" is an artificial intelligence algorithm used by the server that generates appropriate answers and materials in response to user questions and requests.

[1920] "Answer" refers to the explanation or description that a generative AI model provides in response to a user's question.

[1921] "Training Materials" refers to the educational materials created by the generative AI model based on the learning content requested by the User.

[1922] "Support information" refers to assistance information provided by the generative AI model in response to individual user requests.

[1923] "Adjusting the display method" refers to presenting information in an optimal format according to the user's emotional state based on emotional information.

[1924] This system recognizes a user's emotions and provides appropriate answers, training materials, and support information based on those emotions. The system consists of the following main components: the user, the device, the server, the generative AI model, and the emotion engine.

[1925] System Overview

[1926] 1. A terminal that provides an interface for users to enter questions or requests.

[1927] 2. The device receives the user's input, extracts emotional information through the emotion engine, and sends it to the server.

[1928] 3. The emotion engine analyzes the user's input and behavioral patterns when entering data to identify their emotional state.

[1929] 4. The server receives the user's questions, requests, and emotional information and analyzes them using a generative AI model.

[1930] 5. The generative AI model takes into account the question, request, and emotional information to generate appropriate answers, training materials, and support information.

[1931] 6. The device receives the information from the server and displays it in the most appropriate format for the user.

[1932] Hardware and Software Used

[1933] Device: A device such as a personal computer, tablet, or smartphone.

[1934] Emotion Engine: Software that includes a natural language processing (NLP) engine, a speech analysis system, and a typing analysis system.

[1935] Server: A high-performance computer or cloud computing platform.

[1936] Generative AI models: Deep learning models (e.g., large-scale generative models such as GPT-3).

[1937] Specific operation example

[1938] Example 1: Answering basic questions

[1939] 1. A user types the question "How do I start a new project?" into a terminal.

[1940] 2. The device sends a question to the emotion engine and identifies the user's emotion as "anxiety."

[1941] 3. The device sends the question, including the emotion information, to the server.

[1942] 4. The server passes the question and emotion information to the generative AI model, which generates an answer. For example, it might generate an answer like, "To start a new project, click the 'New Project' button in the project management tool, enter the required information, and click 'Save'. If you have any questions, please feel free to ask."

[1943] 5. The device receives the answer and displays it to the user.

[1944] Example 2: Providing training materials

[1945] 1. The user enters a request through the terminal: "Please teach me how to use the project management tool."

[1946] 2. The device sends a request to the emotion engine and identifies the user's emotion as "interest."

[1947] 3. The device sends a request including emotion information to the server.

[1948] 4. The server passes the request and sentiment information to the generative AI model to generate training materials, such as "How to use a project management tool - basic functions, configuration, task management, team member management, and common troubleshooting tips."

[1949] 5. The device receives the training materials and displays them to the user.

[1950] Example 3: Personalized support

[1951] 1. The user inputs a request through the terminal: "Please let me know the progress of the latest project."

[1952] 2. The device sends a request to the emotion engine and identifies the user's emotion as "urgent."

[1953] 3. The device sends a request including emotion information to the server.

[1954] 4. The server passes the request and emotion information to the generative AI model, which generates information about the latest progress. For example, it generates information like, "The latest project is 70% complete. The next major milestone is 'specification finalization,' which is expected to be completed today."

[1955] 5. The device receives the support information and displays it to the user.

[1956] This will provide answers and materials that take the user's emotions into consideration, which is expected to improve learning efficiency.

[1957] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1958] Step 1:

[1959] The user enters a question

[1960] Specific action: The user inputs a question into the input interface of the device, for example, "How do I start a new project?"

[1961] Input: The text data of the question entered by the user.

[1962] Output: The terminal obtains the user's question text data.

[1963] Step 2:

[1964] The device sends the user's question to the emotion engine.

[1965] Specific operation: The device sends the user's input data to the emotion engine, which receives data such as the user's input content, input speed, typing strength, and voice tone (in the case of voice input).

[1966] Input: Text data of the question entered by the user and behavioral data when entering the question.

[1967] Output: The emotion engine receives the input data.

[1968] Step 3:

[1969] Emotion engine analyzes user emotions

[1970] Specific operation: The emotion engine analyzes text data and behavioral data to identify the user's emotions. For example, it determines that the user is feeling "anxiety" based on the input content.

[1971] Input: Textual and behavioral data received by the emotion engine.

[1972] Output: Emotional information including the user's emotional state (e.g., anxiety, interest, urgency).

[1973] Step 4:

[1974] The device sends emotional information to the server.

[1975] Specific operation: The device sends the generated emotion information to the server along with the user's question text.

[1976] Input: User question text data and sentiment information.

[1977] Output: The server receives the question text and sentiment information.

[1978] Step 5:

[1979] The server passes the question and emotion information to the generative AI model

[1980] Specific operation: The server inputs the received question text and emotion information into the generative AI model, which then generates an appropriate answer based on this.

[1981] Input: Question text data and sentiment information received by the server.

[1982] Output: The generative AI model begins its analysis.

[1983] Step 6:

[1984] Generative AI models generate appropriate answers to questions

[1985] Specific operation: The generative AI model analyzes the question text data and emotional information, and generates an appropriate answer taking into account the user's emotional state. For example, if the user is feeling "anxious," the answer will be more detailed.

[1986] Input: Question text data and sentiment information.

[1987] Output: Emotion-sensitive answer text data.

[1988] Step 7:

[1989] The server generates a response and sends it to the device.

[1990] Specific operation: The server receives the answer text data generated from the generative AI model and sends it to the terminal.

[1991] Input: Generated answer text data.

[1992] Output: The terminal receives the response text data.

[1993] Step 8:

[1994] The device displays the answers to the user and adjusts the display based on the user's emotional information.

[1995] Specific operation: The device displays the received answer text to the user. At the same time, the display method is adjusted based on the user's emotional information. For example, if the user is feeling "anxious," a calm and encouraging message is added.

[1996] Input: Answer text data and sentiment information.

[1997] Output: A display tailored to the user.

[1998] (Application example 2)

[1999] 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."

[2000] Conventional onboarding and training systems provide uniform responses to user questions and requests, making it difficult to respond flexibly to the user's emotions and circumstances. In particular, new employees and employees who are unfamiliar with new environments and work procedures often lack support that adequately alleviates their anxiety and confusion. Due to the lack of individualized responses that take emotions into consideration, there is a need to improve learning and work efficiency.

[2001] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for analyzing the question and emotion information using a generative AI model, means for the generative AI model to generate an appropriate answer to the question taking the emotion information into consideration, and means for the emotion engine to analyze the user's emotion. This enables flexible responses that take the user's emotions into consideration.

[2002] A "user" is an entity that operates the system and enters questions and requests.

[2003] A "terminal" is a device that receives questions or requests entered by a user and transmits them to a server.

[2004] The "emotion engine" is a function that analyzes the user's input data (text, voice, input speed, etc.) and generates emotional information.

[2005] The "server" is a central device that analyzes questions, requests, and emotional information received from users and transmits the results to terminals.

[2006] A "generative AI model" is an artificial intelligence technology that generates appropriate answers and materials based on input questions or requests.

[2007] The present invention relates to a training support system that uses an application installed on a factory robot to improve employee learning efficiency. The system includes a user, a terminal, a server, a generative AI model, and an emotion engine.

[2008] The overall flow of the system is as follows: The user inputs a question or request via their device, which then sends it to the emotion engine. The emotion engine analyzes the user's input data and generates emotional information. The device then sends the input data along with the emotional information to the server. The server passes the input data and emotional information to the generative AI model for analysis, and sends the generated answer or materials back to the device. The device then finally displays or plays the answer or materials to the user.

[2009] This section explains the specific hardware and software. The hardware uses factory robots, voice input devices, display panels, and speakers. The software uses the Emotion Engine (emotion recognition engine) and AI Response Generator (generative AI model). The server is the central device that handles overall data exchange and analysis, and can also utilize edge computing and cloud services.

[2010] For example, let's consider a specific example where a worker asks a question about how to operate a new machine. When the user inputs a question into the device (voice input is also possible), such as "Please tell me how to operate this new press machine," the device sends that information to the emotion engine. The emotion engine analyzes the content, speed, and tone of voice of the input, and determines the user's emotion as "interest." The device then sends this as data to the server, and the server uses a generative AI model to generate an appropriate answer that takes the emotional information into consideration. As a specific example, the answer generated might be, "To operate this new press machine, first turn it on, then press the start button on the control panel. After that, adjust the settings and begin work. A detailed manual is also available, so please let us know if you need one."

[2011] As an example of a prompt, the following text is fed into the generative AI model:

[2012] Question: 'How do I operate the new press?'

[2013] Emotion: 'Interest'

[2014] This system is expected to improve the quality of work instruction and respond flexibly to the user's emotions. This application example is particularly effective in helping new and inexperienced employees to work with peace of mind.

[2015] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[2016] Step 1:

[2017] A user inputs a question or request via a terminal. The input method can be text input or voice input. For example, if a user inputs a question such as "Please tell me how to operate the new press machine," the input contains the user's emotions and intentions.

[2018] Step 2:

[2019] The device receives a question from the user and sends it to the emotion engine. The input data includes text information and voice data, and the data is sent to the emotion engine for analysis.

[2020] Step 3:

[2021] The emotion engine analyzes emotions based on the user's input data. In this step, the content of the text, input speed, and tone of voice are analyzed to generate the user's emotion information (e.g., interest, anxiety, urgency, etc.). For example, in the case of voice input, "interest" is generated as emotion information by analyzing the tone of voice.

[2022] Step 4:

[2023] The device sends the emotion information received from the emotion engine to the server. This sent data includes the original question and emotion information. For example, data such as "Question: Please tell me how to operate the new press machine" and "Emotion information: Interest" is sent.

[2024] Step 5:

[2025] The server passes the question content and emotional information to the generative AI model for analysis. Based on the input question content and emotional information, data processing and analysis are performed to generate the most appropriate answer. The generative AI model analyzes the question and generates an answer that takes the emotional information into account.

[2026] Step 6:

[2027] The generative AI model takes emotional information into account to generate appropriate answers. The output answers are tailored to the user's emotions. For example, a detailed and engaging answer is generated for the "interest" emotion. Specifically, the model might generate an answer such as, "To operate a new press, first turn it on, then press the start button on the control panel. After that, adjust the settings and begin operation. A detailed manual is also available, so please let us know if you need one."

[2028] Step 7:

[2029] The server transmits the generated answer to the terminal. In this step, the generated answer includes an emotion-responsive message, and the answer is transmitted in an appropriate format based on the user's emotion.

[2030] Step 8:

[2031] The device displays or plays back the received answer and emotion-responsive message to the user. Depending on the user's emotion, an appropriate answer is provided in the form of a text display or audio playback. For example, if the emotion is "interested," detailed instructions are displayed on the screen and audio guidance is played. In this way, flexible responses and support that take the user's emotions into consideration are possible.

[2032] 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.

[2033] 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.

[2034] 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.

[2035] 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.

[2036] 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.

[2037] 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.

[2038] 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).

[2039] 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.

[2040] 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."

[2041] 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.

[2042] 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).

[2043] 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.

[2044] 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.

[2045] 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.

[2046] 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.

[2047] 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.

[2048] 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.

[2049] 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.

[2050] 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.

[2051] 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.

[2052] 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.

[2053] The following is further disclosed regarding the above embodiment.

[2054] (Claim 1)

[2055] a means for a user to input a question;

[2056] A means for the terminal to receive a question from a user and transmit the question to a server;

[2057] A means for the server to receive the question and analyze it with a generative AI model;

[2058] A means by which the generative AI model generates appropriate answers to questions; and

[2059] means for the server to transmit the generated response to the terminal;

[2060] means for the terminal to display the answer to the user;

[2061] A system including:

[2062] (Claim 2)

[2063] a means for a user to input a request for training materials;

[2064] a means for the terminal to receive and transmit requests to a server;

[2065] a means for the server to receive the request and generate training materials using the generative AI model;

[2066] A means for transmitting the generated material from the generative AI model to a server;

[2067] means for the terminal to display training materials to the user;

[2068] 10. The system of claim 1, comprising:

[2069] (Claim 3)

[2070] a means for users to input individual support requests;

[2071] a means for the terminal to receive and transmit requests to a server;

[2072] A means for the server to refer to the user's profile information and generate support information using a generative AI model;

[2073] A means for transmitting the generated support information to a server by the generative AI model;

[2074] means for the terminal to display support information to a user;

[2075] 10. The system of claim 1, comprising:

[2076] "Example 1"

[2077] (Claim 1)

[2078] a means for a user to input a question;

[2079] A means for the terminal to receive a question from a user and transmit it to a server via a network;

[2080] a means for the server to receive the question and analyze the question using the generative AI model;

[2081] A means by which the generative AI model generates appropriate answers to questions; and

[2082] means for the server to transmit the generated response to the terminal;

[2083] means for the terminal to display the answer to the user;

[2084] A system including:

[2085] (Claim 2)

[2086] a means for a user to input a request for training materials;

[2087] a means for the terminal to receive and transmit requests to a server;

[2088] a means for the server to receive the request and generate training materials using the generative AI model;

[2089] A means for transmitting the generated material from the generative AI model to a server;

[2090] means for the terminal to display training materials to the user;

[2091] 10. The system of claim 1, comprising:

[2092] (Claim 3)

[2093] a means for users to input individual support requests;

[2094] a means for the terminal to receive and transmit requests to a server;

[2095] A means for the server to refer to the user's profile information and generate support information using a generative AI model;

[2096] A means for transmitting the generated support information to a server by the generative AI model;

[2097] means for the terminal to display support information to a user;

[2098] 10. The system of claim 1, comprising:

[2099] "Application Example 1"

[2100] (Claim 1)

[2101] a means for a user to input a question;

[2102] A means for the terminal to receive a question from a user and transmit the question to a server;

[2103] A means for the server to receive the question and analyze it with a generative AI model;

[2104] A means by which the generative AI model generates appropriate answers to questions; and

[2105] means for the server to transmit the generated response to the terminal;

[2106] means for the terminal to display the answer to the user;

[2107] means for generating training materials relating to factory operations;

[2108] A method for AI to refer to the user's past operation history and generate individually customized support information;

[2109] A system including:

[2110] (Claim 2)

[2111] a means for a user to input a request for training materials;

[2112] a means for the terminal to receive and transmit requests to a server;

[2113] a means for the server to receive the request and generate training materials using the generative AI model;

[2114] A means for transmitting the generated material from the generative AI model to a server;

[2115] means for the terminal to display training materials to the user;

[2116] 10. The system of claim 1, comprising:

[2117] (Claim 3)

[2118] a means for users to input individual support requests;

[2119] a means for the terminal to receive and transmit requests to a server;

[2120] A means for the server to refer to the user's profile information and generate support information using a generative AI model;

[2121] A means for transmitting the generated support information to a server by the generative AI model;

[2122] means for the terminal to display support information to a user;

[2123] 10. The system of claim 1, comprising:

[2124] "Example 2: Combining Emotion Engines"

[2125] (Claim 1)

[2126] a means for a user to input a question;

[2127] a means for the terminal to receive a question from a user and transmit the question to the emotion engine;

[2128] A means for the emotion engine to analyze the user's emotion and transmit the result to the terminal;

[2129] A means for the terminal to transmit emotion information to a server;

[2130] The server receives the question and emotion information, and passes it to the generative AI model for analysis.

[2131] A means for the generative AI model to generate appropriate answers to questions, taking into account emotional information;

[2132] A means for the server to transmit the generated answer and emotion information to the terminal;

[2133] a means for the terminal to display the answer to the user and adjust the display method based on the emotion information;

[2134] A system including:

[2135] (Claim 2)

[2136] a means for a user to input a request for training materials;

[2137] a means for the device to send a request to the emotion engine;

[2138] A means for the emotion engine to analyze the user's emotion and transmit the result to the terminal;

[2139] A means for the terminal to transmit emotion information to a server;

[2140] The server receives the request and emotion information, and passes it to the generative AI model for analysis.

[2141] A means for the generative AI model to generate training materials based on the request and taking into account emotional information;

[2142] A means for the server to transmit the generated material to the terminal;

[2143] means for the terminal to display training materials to the user;

[2144] 10. The system of claim 1, comprising:

[2145] (Claim 3)

[2146] a means for users to input individual support requests;

[2147] a means for the device to send a request to the emotion engine;

[2148] A means for the emotion engine to analyze the user's emotion and transmit the result to the terminal;

[2149] A means for the terminal to transmit emotion information to a server;

[2150] The server receives the request and emotion information, and passes it to the generative AI model for analysis.

[2151] A means for the generative AI model to generate supporting information based on the request and taking into account emotional information;

[2152] A means for the server to transmit the generated support information to the terminal;

[2153] means for the terminal to display support information to a user;

[2154] 10. The system of claim 1, comprising:

[2155] "Application example 2 when combining emotion engines"

[2156] (Claim 1)

[2157] a means for a user to input a question;

[2158] a means for the terminal to receive a question from a user and transmit the question to the emotion engine;

[2159] a means for the emotion engine to analyze the user's emotion;

[2160] A means for the terminal to transmit emotion information to a server;

[2161] The server analyzes the questions and emotion information using a generative AI model,

[2162] A means for the generative AI model to generate appropriate answers to questions by taking into account emotional information; and

[2163] means for the server to transmit the generated response to the terminal;

[2164] means for the terminal to display the answer to the user;

[2165] A system including:

[2166] (Claim 2)

[2167] a means for a user to input a request for training materials;

[2168] a means for the device to receive and transmit requests to the emotion engine;

[2169] a means for the emotion engine to analyze the user's emotion;

[2170] A means for the terminal to transmit emotion information to a server;

[2171] A means for the server to analyze the request and emotion information using a generative AI model;

[2172] A means for the generative AI model to generate training materials taking into account emotional information; and

[2173] A means for the server to transmit the generated material to the terminal;

[2174] means for the terminal to display training materials to the user;

[2175] 10. The system of claim 1, comprising:

[2176] (Claim 3)

[2177] a means for users to input individual support requests;

[2178] a means for the device to receive and transmit requests to the emotion engine;

[2179] a means for the emotion engine to analyze the user's emotion;

[2180] A means for the terminal to transmit emotion information to a server;

[2181] A means for the server to refer to the user's profile information and emotion information and generate support information using a generative AI model;

[2182] A means for transmitting support information generated by the generative AI model in consideration of emotional information to a server;

[2183] means for the terminal to display support information to a user;

[2184] 10. The system of claim 1, comprising: [Explanation of symbols]

[2185] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. a means for a user to input a question; A means for the terminal to receive a question from a user and transmit the question to a server; A means for the server to receive the question and analyze it with a generative AI model; A means by which the generative AI model generates appropriate answers to questions; and means for the server to transmit the generated response to the terminal; means for the terminal to display the answer to the user; A system including:

2. a means for a user to input a request for training materials; a means for the terminal to receive and transmit requests to a server; a means for the server to receive the request and generate training materials using the generative AI model; A means for transmitting the generated material from the generative AI model to a server; means for the terminal to display training materials to the user; The system of claim 1 , comprising:

3. a means for users to input individual support requests; a means for the terminal to receive and transmit requests to a server; A means for the server to refer to the user's profile information and generate support information using a generative AI model; A means for transmitting the generated support information to a server by the generative AI model; means for the terminal to display support information to a user; The system of claim 1 , comprising:

Images